fix(plugins): accept empty navigation anchor ranges as positions

A document indexer that anchors a whole-file definition at the file's start (an empty range at 0:0) had the whole document rejected with "invalid navigation anchors". Empty ranges inside the document are now accepted: Go to Declaration lands on them, while Find Usages and Rename skip them so a rename never inserts the new name at that position. The error for a document that is still rejected names the plugin and the file.
feat(debugger): debug Kotlin with kotlin-lsp's debugger (#2651 )
2026-11-11 10:41:28 -10:00 · 2026-11-12 00:11:01 +08:00 · 2026-11-12 00:05:41 +08:00 · 2026-11-12 00:03:13 +08:00 · 2026-11-11 23:53:24 +08:00 · 2026-11-11 23:40:04 +08:00
406 changed files with 31426 additions and 1724 deletions
@@ -0,0 +1,2 @@
+custom:
+  - https://github.com/l0ng-ai/openidea#sponsor
@@ -4145,7 +4145,7 @@ checksum = "3d3067d79b975e8844ca9eb072e16b31c3c1c36928edf9c6789548c524d0d954"

 [[package]]
 name = "ide-agent"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "dunce",
 "encoding_rs",
@@ -4169,7 +4169,7 @@ dependencies = [

 [[package]]
 name = "ide-analysis"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "ast-grep-core",
 "ide-core",
@@ -4183,7 +4183,7 @@ dependencies = [

 [[package]]
 name = "ide-android"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "ide-core",
 "serde",
@@ -4194,7 +4194,7 @@ dependencies = [

 [[package]]
 name = "ide-build"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "blake3",
 "chardetng",
@@ -4212,7 +4212,7 @@ dependencies = [

 [[package]]
 name = "ide-cli"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "dirs 6.0.0",
 "serde",
@@ -4226,7 +4226,7 @@ dependencies = [

 [[package]]
 name = "ide-clipboard"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "gtk",
 "objc2 0.6.5",
@@ -4236,7 +4236,7 @@ dependencies = [

 [[package]]
 name = "ide-core"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "dunce",
 "encoding_rs",
@@ -4253,7 +4253,7 @@ dependencies = [

 [[package]]
 name = "ide-coverage"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "ide-core",
 "ide-run",
@@ -4267,10 +4267,11 @@ dependencies = [

 [[package]]
 name = "ide-dap"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "futures",
 "ide-core",
+ "ide-heap",
 "ide-jdwp",
 "ide-jsonrpc",
 "ide-jvm-attach",
@@ -4292,7 +4293,7 @@ dependencies = [

 [[package]]
 name = "ide-db"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "bb8",
 "blake3",
@@ -4322,7 +4323,7 @@ dependencies = [

 [[package]]
 name = "ide-docker"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "ide-core",
 "serde",
@@ -4335,7 +4336,7 @@ dependencies = [

 [[package]]
 name = "ide-extension"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "base64 0.22.1",
 "blake3",
@@ -4356,7 +4357,7 @@ dependencies = [

 [[package]]
 name = "ide-fonts"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "objc2-core-foundation",
 "objc2-core-text",
@@ -4368,7 +4369,7 @@ dependencies = [

 [[package]]
 name = "ide-github"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "ide-core",
 "ide-vcs",
@@ -4379,9 +4380,27 @@ dependencies = [
 "which",
 ]

+[[package]]
+name = "ide-heap"
+version = "0.1.42"
+dependencies = [
+ "criterion",
+ "ide-core",
+ "libc",
+ "memmap2",
+ "proptest",
+ "serde",
+ "serde_json",
+ "specta",
+ "tempfile",
+ "thiserror 2.0.21",
+ "tracing",
+ "uuid",
+]
+
 [[package]]
 name = "ide-host"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "base64 0.22.1",
 "blake3",
@@ -4401,6 +4420,7 @@ dependencies = [
 "ide-db",
 "ide-docker",
 "ide-extension",
+ "ide-heap",
 "ide-http",
 "ide-index",
 "ide-jsonrpc",
@@ -4449,7 +4469,7 @@ dependencies = [

 [[package]]
 name = "ide-http"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "ide-core",
 "ide-vfs",
@@ -4468,7 +4488,7 @@ dependencies = [

 [[package]]
 name = "ide-index"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "blake3",
 "criterion",
@@ -4490,7 +4510,7 @@ dependencies = [

 [[package]]
 name = "ide-jdwp"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "ide-jvm-inspect",
 "proptest",
@@ -4502,7 +4522,7 @@ dependencies = [

 [[package]]
 name = "ide-jsonrpc"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "encoding_rs",
 "futures",
@@ -4519,7 +4539,7 @@ dependencies = [

 [[package]]
 name = "ide-jvm-attach"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "libc",
 "tempfile",
@@ -4528,7 +4548,7 @@ dependencies = [

 [[package]]
 name = "ide-jvm-inspect"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "futures",
 "serde",
@@ -4539,7 +4559,7 @@ dependencies = [

 [[package]]
 name = "ide-language"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "blake3",
 "criterion",
@@ -4595,7 +4615,7 @@ dependencies = [

 [[package]]
 name = "ide-lsp"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "dunce",
 "futures",
@@ -4622,7 +4642,7 @@ dependencies = [

 [[package]]
 name = "ide-mcp"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "bytes",
 "dunce",
@@ -4641,7 +4661,7 @@ dependencies = [

 [[package]]
 name = "ide-notebook"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "futures",
 "ide-core",
@@ -4664,7 +4684,7 @@ dependencies = [

 [[package]]
 name = "ide-plugin"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "blake3",
 "dunce",
@@ -4687,9 +4707,10 @@ dependencies = [

 [[package]]
 name = "ide-profiler"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "ide-core",
+ "ide-jvm-attach",
 "ide-run",
 "serde",
 "serde_json",
@@ -4700,7 +4721,7 @@ dependencies = [

 [[package]]
 name = "ide-remote"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "dunce",
 "globset",
@@ -4719,7 +4740,7 @@ dependencies = [

 [[package]]
 name = "ide-run"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "dunce",
 "encoding_rs",
@@ -4743,7 +4764,7 @@ dependencies = [

 [[package]]
 name = "ide-scaffold"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "ide-core",
 "ide-tools",
@@ -4759,7 +4780,7 @@ dependencies = [

 [[package]]
 name = "ide-sdk"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "dunce",
 "ide-core",
@@ -4779,7 +4800,7 @@ dependencies = [

 [[package]]
 name = "ide-search"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "criterion",
 "encoding_rs",
@@ -4800,7 +4821,7 @@ dependencies = [

 [[package]]
 name = "ide-spell"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "ide-core",
 "parking_lot",
@@ -4813,7 +4834,7 @@ dependencies = [

 [[package]]
 name = "ide-ssh"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "dirs 6.0.0",
 "flate2",
@@ -4834,7 +4855,7 @@ dependencies = [

 [[package]]
 name = "ide-syntax"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "ide-core",
 "ide-language",
@@ -4849,7 +4870,7 @@ dependencies = [

 [[package]]
 name = "ide-terminal"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "ide-core",
 "libc",
@@ -4862,7 +4883,7 @@ dependencies = [

 [[package]]
 name = "ide-text"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "criterion",
 "ide-core",
@@ -4875,7 +4896,7 @@ dependencies = [

 [[package]]
 name = "ide-tools"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "flate2",
 "hex",
@@ -4896,7 +4917,7 @@ dependencies = [

 [[package]]
 name = "ide-vcs"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "blake3",
 "dunce",
@@ -4917,7 +4938,7 @@ dependencies = [

 [[package]]
 name = "ide-vfs"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "chardetng",
 "dunce",
@@ -4941,11 +4962,11 @@ dependencies = [

 [[package]]
 name = "ide-web"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
+ "dirs 6.0.0",
 "ide-core",
 "open",
- "parking_lot",
 "percent-encoding",
 "serde",
 "specta",
@@ -4957,7 +4978,7 @@ dependencies = [

 [[package]]
 name = "ide-workspace"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "blake3",
 "dunce",
@@ -6535,7 +6556,7 @@ dependencies = [

 [[package]]
 name = "openidea"
-version = "0.1.41"
+version = "0.1.42"
 dependencies = [
 "base64 0.22.1",
 "blake3",
@@ -7776,9 +7797,9 @@ dependencies = [

 [[package]]
 name = "rustix"
-version = "1.1.5"
+version = "1.1.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "891efababe418670775f199f0d233d84843c227a0949a883ce15b37c78d6629d"
+checksum = "e5e76742e5294153d4dde1207dbec5bdd81eef6fabdc0d2118babadabfd858aa"
 dependencies = [
 "bitflags 2.13.2",
 "errno",
@@ -5,7 +5,7 @@ members = ["crates/*", "src-tauri"]
 exclude = ["sdk", "plugins"]

 [workspace.package]
-version = "0.1.41"
+version = "0.1.42"
 edition = "2024"
 rust-version = "1.96"
 license = "Apache-2.0"
@@ -51,6 +51,7 @@ ide-cli = { path = "crates/ide-cli" }
 ide-jvm-attach = { path = "crates/ide-jvm-attach" }
 ide-jvm-inspect = { path = "crates/ide-jvm-inspect" }
 ide-jdwp = { path = "crates/ide-jdwp" }
+ide-heap = { path = "crates/ide-heap" }

 # serialization & IPC typing
 serde = { version = "1", features = ["derive"] }
@@ -86,6 +87,7 @@ trash = "5"
 blake3 = "1"
 dunce = "1"
 dirs = "6"
+memmap2 = "0.9"
 zip = { version = "9.2.3", default-features = false, features = ["deflate"] }

 # search, index, language
@@ -19,6 +19,8 @@
  <a href="#plugins">Plugins</a>
  &nbsp;·&nbsp;
  <a href="#community">Community</a>
+  &nbsp;·&nbsp;
+  <a href="#sponsor">Sponsor</a>
 </p>

 https://github.com/user-attachments/assets/234dd54c-1255-4b3a-b35c-533d78d737c0
@@ -68,6 +70,17 @@ the [official plugins](plugins/official). The plugin API is still a preview.

 - Contributing: see [CONTRIBUTING.md](CONTRIBUTING.md) and the [contributor docs](https://openidea.sh/en/contribute/setup).

+## Sponsor
+
+If OpenIDEA saves you time, you can support its development with Alipay or WeChat Pay.
+
+<table>
+  <tr>
+    <td align="center"><img src=".github/assets/sponsor-alipay.png" alt="Alipay QR code" width="200"><br>Alipay</td>
+    <td align="center"><img src=".github/assets/sponsor-wechat.png" alt="WeChat Pay QR code" width="200"><br>WeChat Pay</td>
+  </tr>
+</table>
+
 ## License

 [Apache 2.0](LICENSE). Bundled third-party assets are listed in [`THIRD_PARTY_LICENSES.md`](THIRD_PARTY_LICENSES.md).
@@ -0,0 +1,102 @@
+//! A short-lived ACP session to learn models, effort levels and other config options
+//! before the user's first task (Cursor and other ACP agents do not expose these in
+//! `initialize` alone).
+
+use super::{Conn, Dialect};
+use crate::config;
+use crate::model::AgentConfigOption;
+use crate::provider::ProviderSpec;
+use crate::{Shared, client_info};
+use parking_lot::Mutex;
+use serde_json::{Value, json};
+use std::sync::Arc;
+use std::time::Duration;
+
+const DISCOVER_TIMEOUT: Duration = if cfg!(test) { Duration::from_secs(3) } else { Duration::from_secs(120) };
+
+/// Opens `session/new`, reads `configOptions`, and records per-model `thought_level` choices.
+pub(crate) async fn run(shared: &Arc<Shared>, spec: &ProviderSpec) -> Result<(), String> {
+    let root = shared.paths.project_root.clone();
+    let launch = spec.clone();
+    let launch = tokio::task::spawn_blocking({
+        let root = root.clone();
+        move || launch.resolve_for_launch(&root)
+    })
+    .await
+    .map_err(|e| e.to_string())?;
+    let cwd = dunce::canonicalize(&root).unwrap_or(root);
+    let stderr: Arc<Mutex<Vec<String>>> = Arc::default();
+    let lines = stderr.clone();
+    let on_stderr: Box<dyn Fn(String) + Send + Sync> = Box::new(move |l| lines.lock().push(l));
+    let client = Dialect::wrap(Arc::new(ide_jsonrpc::NoopHandler));
+    let peer = (shared.connector)(&launch, &cwd, client.clone(), on_stderr)
+        .map_err(|e| format!("Couldn't start {} (`{}`): {e}", launch.name, launch.command))?;
+    let conn = Conn::new(peer.clone(), client);
+    let work = async {
+        conn.initialize(&client_info()).await.map_err(|e| e.to_string())?;
+        let cwd_s = cwd.to_string_lossy().into_owned();
+        // No project MCP during discovery: Cursor can spend a long time spawning servers.
+        let new: Value = conn
+            .request("session/new", json!({ "cwd": cwd_s, "mcpServers": [] }), None)
+            .await
+            .map_err(|e| e.to_string())?;
+        let mut options = config::options_of(&new);
+        config::add_client_options(&launch.id, &mut options);
+        let model_option = options.iter().find(|o| o.category.as_deref() == Some("model"));
+        let effort = levels_for_model_from_slice(&options);
+        let levels: Vec<(String, Vec<AgentConfigOption>)> = match (model_option, effort) {
+            (Some(model), Some(effort)) if !model.values.is_empty() => {
+                model.values.iter().map(|v| (v.value.clone(), effort.clone())).collect()
+            }
+            (Some(model), Some(effort)) => model.current.clone().map(|m| vec![(m, effort)]).unwrap_or_default(),
+            _ => Vec::new(),
+        };
+        let option_ids: Vec<_> = options.iter().map(|o| o.id.as_str()).collect();
+        tracing::info!(
+            "agent {}: settings discovery got {} config option(s) {:?}, {} model effort list(s)",
+            launch.id,
+            options.len(),
+            option_ids,
+            levels.len()
+        );
+        shared.remember_discovered(&launch.id, &options, &[], &levels);
+        Ok::<(), String>(())
+    };
+    let result = tokio::time::timeout(DISCOVER_TIMEOUT, work).await;
+    peer.kill();
+    match result {
+        Ok(Ok(())) => Ok(()),
+        Ok(Err(e)) => Err(match stderr.lock().last() {
+            Some(line) => format!("{e}: {line}"),
+            None => e,
+        }),
+        Err(_) => {
+            let tail = stderr.lock().join("\n");
+            if tail.is_empty() {
+                Err("the agent did not answer in time".into())
+            } else {
+                Err(format!("the agent did not answer in time:\n{tail}"))
+            }
+        }
+    }
+}
+
+fn is_thought_level(o: &AgentConfigOption) -> bool {
+    o.category.as_deref() == Some("thought_level")
+        || matches!(o.id.as_str(), "effort" | "reasoning_effort" | "thinking" | "reasoning")
+}
+
+fn levels_for_model_from_slice(options: &[AgentConfigOption]) -> Option<Vec<AgentConfigOption>> {
+    let levels: Vec<_> = options
+        .iter()
+        .filter(|o| is_thought_level(o))
+        .cloned()
+        .map(|mut o| {
+            if o.category.as_deref() != Some("thought_level") {
+                o.category = Some("thought_level".into());
+            }
+            o
+        })
+        .collect();
+    (!levels.is_empty()).then_some(levels)
+}
@@ -14,6 +14,7 @@
 //! - Agent → client ([`Dialect`]): `session/update`s are normalized ([`normalize`]) and
 //!   permission requests get the v1 `toolCall`.

+pub(crate) mod discover;
 mod normalize;

 use ide_jsonrpc::{Handler, Peer, RpcError, codes};
@@ -57,6 +58,9 @@ fn client_capabilities() -> Value {
        "terminal": false,
        // Subagents as sessions of their own (ACP subagents RFD; v2 baseline).
        "subagents": {},
+        // Cursor exposes model parameters (e.g. Composer `fast`) as separate config options
+        // only when the client advertises this flag (undocumented Cursor ACP extension).
+        "_meta": { "parameterizedModelPicker": true },
    })
 }

@@ -93,9 +93,81 @@ fn the_negotiating_request_carries_both_versions() {
    assert!(p["capabilities"].is_object());
    assert_eq!(p["clientCapabilities"]["subagents"], json!({}));
    assert_eq!(p["clientCapabilities"]["terminal"], false);
+    assert_eq!(
+        p["clientCapabilities"]["_meta"]["parameterizedModelPicker"], true,
+        "Cursor and similar agents need parameterized model options (e.g. fast on/off)"
+    );
    // What we sent in the capture is what claude-agent-acp negotiated v2 and v1 from.
-    let sent = &frames(TURN, "out")[0]["params"];
-    assert_eq!(sent["clientCapabilities"], p["clientCapabilities"]);
+    let sent = frames(TURN, "out")[0]["params"]["clientCapabilities"].clone();
+    let mut expected = sent;
+    expected["_meta"] = p["clientCapabilities"]["_meta"].clone();
+    assert_eq!(expected, p["clientCapabilities"]);
+}
+
+#[tokio::test(flavor = "multi_thread")]
+async fn discovery_reads_effort_and_fast_from_session_new_then_stops_the_agent() {
+    #[derive(Default)]
+    struct DiscoveryAgent {
+        peer: std::sync::OnceLock<Peer>,
+        calls: parking_lot::Mutex<Vec<(String, Value)>>,
+    }
+    impl Handler for DiscoveryAgent {
+        fn on_notification(&self, _: &str, _: Value) {}
+        fn on_request(&self, method: &str, params: Value) -> Result<Value, (i64, String)> {
+            self.calls.lock().push((method.to_owned(), params));
+            match method {
+                "initialize" => Ok(json!({
+                    "protocolVersion": 1,
+                    "agentCapabilities": { "loadSession": true }
+                })),
+                "session/new" => Ok(json!({
+                    "sessionId": "discover",
+                    "configOptions": [
+                        {"id": "model", "category": "model", "type": "select", "currentValue": "m1",
+                         "options": [{"value": "m1", "name": "One"}, {"value": "m2", "name": "Two"}]},
+                        {"id": "effort", "type": "select", "currentValue": "medium",
+                         "options": [{"value": "low"}, {"value": "medium"}, {"value": "high"}]},
+                        {"id": "fast", "type": "select", "currentValue": "false",
+                         "options": [{"value": "false", "name": "Off"}, {"value": "true", "name": "On"}]}
+                    ]
+                })),
+                _ => Ok(json!({})),
+            }
+        }
+    }
+    let agent = Arc::new(DiscoveryAgent::default());
+    let tmp = tempfile::tempdir().unwrap();
+    let agent_for_connector = agent.clone();
+    let connector: crate::Connector = Arc::new(move |_, _, client, _| {
+        let (ca, cb) = tokio::io::duplex(1 << 20);
+        let (car, caw) = tokio::io::split(ca);
+        let (cbr, cbw) = tokio::io::split(cb);
+        let agent_peer = Peer::connect_framed(cbr, cbw, agent_for_connector.clone(), Framing::Lines);
+        let _ = agent_for_connector.peer.set(agent_peer);
+        Ok(Peer::connect_framed(car, caw, client, Framing::Lines))
+    });
+    let mgr = crate::AgentManager::with_connector(
+        crate::AgentPaths {
+            project_root: tmp.path().to_path_buf(),
+            store_dir: tmp.path().join("store"),
+            worktrees_dir: tmp.path().join("worktrees"),
+            models_file: tmp.path().join("models.json"),
+            custom_agents_dir: None,
+            home_dir: None,
+        },
+        tokio::runtime::Handle::current(),
+        connector,
+    );
+    mgr.commands("cursor", None).await.unwrap();
+    let calls = agent.calls.lock();
+    assert_eq!(calls.iter().map(|(m, _)| m.as_str()).collect::<Vec<_>>(), ["initialize", "session/new"]);
+    assert_eq!(calls[1].1["mcpServers"], json!([]));
+    let cursor = mgr.providers().into_iter().find(|p| p.id == "cursor").unwrap();
+    let fast = cursor.config.iter().find(|o| o.id == "fast").expect("fast option");
+    assert_eq!(fast.category.as_deref(), Some("model_config"));
+    assert_eq!(fast.current.as_deref(), Some("false"));
+    assert!(cursor.thought_levels.contains_key("m1") && cursor.thought_levels.contains_key("m2"));
+    assert!(cursor.thought_levels["m1"].iter().any(|o| o.category.as_deref() == Some("thought_level")));
 }

 #[test]
@@ -107,7 +107,15 @@ pub(crate) fn parse_options(options: &Value) -> Vec<AgentConfigOption> {
            Some(AgentConfigOption {
                name: str_of(o, "name").unwrap_or_else(|| id.clone()),
                description: str_of(o, "description"),
-                category: str_of(o, "category").or_else(|| matches!(id.as_str(), "model" | "mode").then(|| id.clone())),
+                category: str_of(o, "category").or_else(|| {
+                    matches!(id.as_str(), "model" | "mode")
+                        .then(|| id.clone())
+                        .or_else(|| {
+                            matches!(id.as_str(), "effort" | "reasoning_effort" | "thinking" | "reasoning")
+                                .then(|| "thought_level".into())
+                        })
+                        .or_else(|| matches!(id.as_str(), "fast").then(|| "model_config".into()))
+                }),
                current: str_of(o, "currentValue"),
                values,
                via: AgentConfigVia::Option,
@@ -333,6 +341,21 @@ mod tests {
        assert!(bypass_approvals(&url_mode));
    }

+    #[test]
+    fn effort_and_fast_categories_are_inferred_from_ids() {
+        let c = options_of(&json!({
+            "configOptions": [
+                {"id": "effort", "type": "select", "currentValue": "high",
+                 "options": [{"value": "low"}, {"value": "high"}]},
+                {"id": "fast", "type": "select", "currentValue": "false",
+                 "options": [{"value": "false", "name": "Off"}, {"value": "true", "name": "On"}]}
+            ]
+        }));
+        assert_eq!(c.len(), 2);
+        assert_eq!(c[0].category.as_deref(), Some("thought_level"));
+        assert_eq!(c[1].category.as_deref(), Some("model_config"));
+    }
+
    #[test]
    fn command_sources_in_updates_and_stored_tasks() {
        let update = json!({"availableCommands": [
@@ -8,6 +8,7 @@
 use super::native::claude::history;
 use serde::Serialize;
 use specta::Type;
+use std::io::BufRead;
 use std::path::{Path, PathBuf};

 /// A session on this machine that no task holds yet.
@@ -62,11 +63,28 @@ fn message_text(e: &serde_json::Value) -> Option<String> {
    }
 }

-/// Claude Code transcripts: `<config>/projects/*/<id>.jsonl`.
-pub fn claude_sessions(config_dir: &Path) -> Vec<ExternalSession> {
+/// Whether a session that ran in `cwd` belongs to the project at `root` (in it or below it).
+fn in_project(cwd: Option<&str>, root: &Path) -> bool {
+    cwd.is_some_and(|cwd| Path::new(cwd).starts_with(root))
+}
+
+/// Claude Code transcripts of the project at `root`: `<config>/projects/<escaped cwd>/<id>.jsonl`.
+/// Only the folders named after `root` or a folder below it are read, so other projects'
+/// transcripts (often gigabytes) are never opened.
+pub fn claude_sessions(config_dir: &Path, root: &Path) -> Vec<ExternalSession> {
    let mut out = Vec::new();
    let projects = config_dir.join("projects");
-    let dirs: Vec<PathBuf> = std::fs::read_dir(&projects).into_iter().flatten().flatten().map(|d| d.path()).collect();
+    let escaped = history::escape(root);
+    let dirs: Vec<PathBuf> = std::fs::read_dir(&projects)
+        .into_iter()
+        .flatten()
+        .flatten()
+        .filter(|d| {
+            let name = d.file_name().to_string_lossy().into_owned();
+            name == escaped || name.starts_with(&format!("{escaped}-"))
+        })
+        .map(|d| d.path())
+        .collect();
    for dir in dirs {
        let files: Vec<PathBuf> = std::fs::read_dir(&dir)
            .into_iter()
@@ -93,6 +111,10 @@ pub fn claude_sessions(config_dir: &Path) -> Vec<ExternalSession> {
                .filter_map(|e| e.get("cwd").and_then(serde_json::Value::as_str))
                .next()
                .map(str::to_owned);
+            // Escaping is lossy (`a/b-c` and `a/b/c` share a folder): the transcript decides.
+            if !in_project(cwd.as_deref(), root) {
+                continue;
+            }
            out.push(ExternalSession {
                provider: "claude".to_owned(),
                session_id: id,
@@ -138,12 +160,13 @@ fn codex_user_text(line: &serde_json::Value) -> Option<String> {

 /// One rollout file's session, or `None` when it names no `session_meta`.
 fn codex_file(path: &Path) -> Option<ExternalSession> {
-    let text = std::fs::read_to_string(path).ok()?;
+    let file = std::fs::File::open(path).ok()?;
    let mut id: Option<(String, Option<String>)> = None;
    let mut title: Option<String> = None;
    // `session_meta` is first, but cap the scan: giant rollouts must not stall listing.
-    for line in text.lines().take(400) {
-        let Ok(v) = serde_json::from_str::<serde_json::Value>(line) else { continue };
+    for line in std::io::BufReader::new(file).lines().take(400) {
+        let Ok(line) = line else { break };
+        let Ok(v) = serde_json::from_str::<serde_json::Value>(&line) else { continue };
        if id.is_none()
            && let Some(meta) = codex_meta(&v)
        {
@@ -183,11 +206,11 @@ fn rollout_files(dir: &Path, depth: usize, out: &mut Vec<PathBuf>) {
    }
 }

-/// Codex sessions: `<home>/.codex/sessions/**`.
-pub fn codex_sessions(codex_home: &Path) -> Vec<ExternalSession> {
+/// Codex sessions of the project at `root`: `<home>/.codex/sessions/**`.
+pub fn codex_sessions(codex_home: &Path, root: &Path) -> Vec<ExternalSession> {
    let mut files = Vec::new();
    rollout_files(&codex_home.join("sessions"), 4, &mut files);
-    files.iter().filter_map(|p| codex_file(p)).collect()
+    files.iter().filter_map(|p| codex_file(p)).filter(|s| in_project(s.cwd.as_deref(), root)).collect()
 }

 #[cfg(test)]
@@ -222,7 +245,7 @@ mod tests {
            ],
        );
        write(&tmp.path().join("projects/-work-app/empty.jsonl"), &[]);
-        let sessions = claude_sessions(tmp.path());
+        let sessions = claude_sessions(tmp.path(), Path::new("/work/app"));
        assert_eq!(sessions.len(), 1);
        let s = &sessions[0];
        assert_eq!((s.provider.as_str(), s.session_id.as_str()), ("claude", "abc123"));
@@ -234,8 +257,8 @@ mod tests {
    #[test]
    fn claude_title_falls_back_to_the_first_prompt() {
        let tmp = tempfile::tempdir().unwrap();
-        write(&tmp.path().join("projects/-x/def456.jsonl"), &[claude_user("u1", "hello there")]);
-        let sessions = claude_sessions(tmp.path());
+        write(&tmp.path().join("projects/-work-app/def456.jsonl"), &[claude_user("u1", "hello there")]);
+        let sessions = claude_sessions(tmp.path(), Path::new("/work/app"));
        assert_eq!(sessions.len(), 1);
        assert_eq!(sessions[0].title, "hello there");
    }
@@ -253,7 +276,7 @@ mod tests {
            ],
        );
        write(&tmp.path().join("sessions/notes.jsonl"), &[json!({"nope": true})]);
-        let sessions = codex_sessions(tmp.path());
+        let sessions = codex_sessions(tmp.path(), Path::new("/work"));
        assert_eq!(sessions.len(), 1);
        let s = &sessions[0];
        assert_eq!((s.provider.as_str(), s.session_id.as_str()), ("codex", "thread-1"));
@@ -264,7 +287,39 @@ mod tests {
    #[test]
    fn missing_directories_list_nothing() {
        let tmp = tempfile::tempdir().unwrap();
-        assert!(claude_sessions(&tmp.path().join("nope")).is_empty());
-        assert!(codex_sessions(&tmp.path().join("nope")).is_empty());
+        assert!(claude_sessions(&tmp.path().join("nope"), Path::new("/work")).is_empty());
+        assert!(codex_sessions(&tmp.path().join("nope"), Path::new("/work")).is_empty());
+    }
+
+    #[test]
+    fn only_sessions_of_the_project_are_listed() {
+        let tmp = tempfile::tempdir().unwrap();
+        let user = |cwd: &str| {
+            json!({"type": "user", "uuid": "u1", "parentUuid": null,
+                "message": {"role": "user", "content": "hi"}, "cwd": cwd})
+        };
+        write(&tmp.path().join("projects/-work-app/in-root.jsonl"), &[user("/work/app")]);
+        write(&tmp.path().join("projects/-work-app-web/below.jsonl"), &[user("/work/app/web")]);
+        // `/work/app-old` escapes like a folder below `/work/app`; its transcript says otherwise.
+        write(&tmp.path().join("projects/-work-app-old/sibling.jsonl"), &[user("/work/app-old")]);
+        write(&tmp.path().join("projects/-other/elsewhere.jsonl"), &[user("/other")]);
+        let mut ids: Vec<String> =
+            claude_sessions(tmp.path(), Path::new("/work/app")).into_iter().map(|s| s.session_id).collect();
+        ids.sort();
+        assert_eq!(ids, ["below", "in-root"]);
+
+        let rollout = |name: &str, cwd: &str| {
+            write(
+                &tmp.path().join(format!("codex/sessions/2026/01/02/{name}.jsonl")),
+                &[json!({"payload": {"type": "session_meta", "payload": {"id": name, "cwd": cwd}}})],
+            )
+        };
+        rollout("mine", "/work/app/api");
+        rollout("theirs", "/other");
+        let codex: Vec<String> = codex_sessions(&tmp.path().join("codex"), Path::new("/work/app"))
+            .into_iter()
+            .map(|s| s.session_id)
+            .collect();
+        assert_eq!(codex, ["mine"]);
    }
 }
@@ -16,6 +16,7 @@ mod model;
 mod native;
 mod provider;
 pub mod registry;
+pub mod security;
 mod skills;
 mod timeline;
 mod worktree;
@@ -39,6 +40,9 @@ use std::time::Duration;
 /// Receives the events of one project's tasks.
 pub type AgentSink = Arc<dyn Fn(AgentEvent) + Send + Sync>;

+/// Returns the active command execution security policy for the project.
+pub type SecurityHook = Arc<dyn Fn() -> ide_core::settings::AgentSecuritySettings + Send + Sync>;
+
 /// Entry changes are batched for this long before they are sent.
 const FLUSH_DELAY: Duration = Duration::from_millis(40);
 /// Updates that arrive this late after `session/load` returns are still replayed history.
@@ -102,6 +106,7 @@ struct Shared {
    runtime: tokio::runtime::Handle,
    connector: Connector,
    sink: RwLock<Option<AgentSink>>,
+    security: RwLock<Option<SecurityHook>>,
    known: Mutex<HashMap<String, Known>>,
    providers: RwLock<Vec<provider::ProviderSpec>>,
    /// Last probe of each provider.
@@ -177,9 +182,15 @@ impl Shared {
                    let shared = self.clone();
                    // Keep the lookup alive if a composer unmounts while it is waiting.
                    self.runtime.spawn(async move {
-                        if let Ok(found) =
-                            native::claude::discover(spec.clone(), shared.paths.project_root.clone()).await
-                        {
+                        tracing::info!("agent {}: settings discovery started", spec.id);
+                        let discovered = if spec.driver == provider::Driver::Acp {
+                            acp::discover::run(&shared, &spec).await.map(|_| None)
+                        } else if spec.driver == provider::Driver::Claude {
+                            native::claude::discover(spec.clone(), shared.paths.project_root.clone()).await.map(Some)
+                        } else {
+                            return;
+                        };
+                        if let Ok(Some(found)) = discovered {
                            let commands =
                                config::commands_of(&json!({ "availableCommands": found.commands }), &spec.id);
                            let options = config::options_of(&json!({ "configOptions": found.options }));
@@ -198,6 +209,8 @@ impl Shared {
                                shared.remember_discovered(&spec.id, &options, &commands, &levels);
                            })
                            .await;
+                        } else if let Err(e) = discovered {
+                            tracing::info!("agent {}: settings discovery failed: {e}", spec.id);
                        }
                        let _ = done.send(true);
                    });
@@ -220,12 +233,17 @@ impl Shared {
    fn knows_all_levels(&self, provider: &str) -> bool {
        let cache = self.known.lock();
        let Some(known) = cache.get(provider) else { return false };
-        known
+        let models: Vec<&str> = known
            .config
            .iter()
            .filter(|o| o.category.as_deref() == Some("model"))
-            .flat_map(|o| &o.values)
-            .all(|v| known.thought_levels.contains_key(&v.value))
+            .flat_map(|o| o.values.iter().map(|v| v.value.as_str()))
+            .collect();
+        // No advertised models yet: nothing to attach effort levels to.
+        if models.is_empty() {
+            return false;
+        }
+        models.iter().all(|id| known.thought_levels.contains_key(*id))
    }

    fn root_key(&self) -> String {
@@ -434,6 +452,7 @@ impl AgentManager {
            runtime,
            connector,
            sink: RwLock::new(None),
+            security: RwLock::new(None),
            known: Mutex::new(known),
            providers,
            probes: Mutex::new(HashMap::new()),
@@ -477,6 +496,11 @@ impl AgentManager {
        tasks
    }

+    /// Sets the callback used to read the active command execution security policy.
+    pub fn set_security_hook(&self, hook: SecurityHook) {
+        *self.shared.security.write() = Some(hook);
+    }
+
    /// The agents (custom ones re-read), whether each is installed, and what they offered last time.
    pub fn providers(&self) -> Vec<AgentProvider> {
        let specs = provider::load(self.shared.paths.custom_agents_dir.as_deref());
@@ -501,7 +525,9 @@ impl AgentManager {
            let new = specs.iter().find(|p| &p.id == id);
            matches!((old, new), (Some(a), Some(b)) if a.command == b.command && a.args == b.args && a.env == b.env)
        });
-        *prev = specs;
+        *prev = specs.clone();
+        drop(probes);
+        drop(prev);
        list
    }

@@ -522,6 +548,30 @@ impl AgentManager {
        provider::set_builtin_env(&dir, id, env)
    }

+    /// Saves a new custom ACP agent through its agent file.
+    pub fn save_custom_agent(&self, input: CustomAgentInput) -> IdeResult<()> {
+        let Some(dir) = self.shared.paths.custom_agents_dir.clone() else {
+            return Err(IdeError::unavailable("there is no custom agents directory"));
+        };
+        provider::save_custom(&dir, &input)
+    }
+
+    /// Removes a custom agent's file (registry installs go through `registry_remove`).
+    pub fn remove_custom_agent(&self, id: &str) -> IdeResult<()> {
+        let Some(dir) = self.shared.paths.custom_agents_dir.clone() else {
+            return Err(IdeError::unavailable("there is no custom agents directory"));
+        };
+        provider::remove_custom(&dir, id)
+    }
+
+    /// Imports a JetBrains `acp.json` file's `agent_servers` entries as custom agents.
+    pub fn import_acp_agents(&self, text: &str) -> IdeResult<Vec<AcpImportOutcome>> {
+        let Some(dir) = self.shared.paths.custom_agents_dir.clone() else {
+            return Err(IdeError::unavailable("there is no custom agents directory"));
+        };
+        provider::import_acp(&dir, text)
+    }
+
    /// Re-reads configured/installed agents, drops cached probes, and notifies subscribers.
    pub fn reload_providers(&self) {
        let specs = provider::load(self.shared.paths.custom_agents_dir.as_deref());
@@ -552,10 +602,16 @@ impl AgentManager {
        let mut offered = offered;
        if task.is_none()
            && (offered.is_empty() || !self.shared.has_config(&provider) || !self.shared.knows_all_levels(&provider))
-            && let Some(spec) = self.shared.spec(&provider).filter(|s| s.driver == provider::Driver::Claude)
+            && let Some(spec) = self
+                .shared
+                .spec(&provider)
+                .filter(|s| matches!(s.driver, provider::Driver::Claude | provider::Driver::Acp))
        {
+            let claude = spec.driver == provider::Driver::Claude;
            self.shared.fetch_settings(spec).await;
-            offered = self.shared.known_commands(&provider);
+            if claude {
+                offered = self.shared.known_commands(&provider);
+            }
        }
        for &(name, description) in builtin_commands(&provider) {
            if !offered.iter().any(|c| c.name == name) {
@@ -592,17 +648,19 @@ impl AgentManager {
        self.tasks.read().values().filter_map(|t| t.state.lock().session_id.clone()).collect()
    }

-    /// Sessions on this machine that no task holds yet, newest first (#312).
+    /// Sessions of this project on this machine that no task holds yet, newest first. Reads
+    /// transcripts from disk: call it off the UI and command threads.
    pub fn external_sessions(&self) -> Vec<ExternalSession> {
        let mut out = Vec::new();
+        let root = self.shared.paths.project_root.clone();
        if let Some(spec) = self.shared.spec("claude")
            && let Some(dir) = native::claude::cli::config_dir(&spec.env)
        {
-            out.extend(external::claude_sessions(&dir));
+            out.extend(external::claude_sessions(&dir, &root));
        }
        let home = self.shared.paths.home_dir.clone().or_else(home_dir);
        if let Some(home) = home {
-            out.extend(external::codex_sessions(&home.join(".codex")));
+            out.extend(external::codex_sessions(&home.join(".codex"), &root));
        }
        let known = self.imported_session_ids();
        out.retain(|s| !known.contains(&s.session_id));
@@ -886,14 +944,38 @@ impl AgentManager {
            }
            o.clone()
        };
+        let previous = target.current.clone();
+        // Cursor's `session/set_config_option` (Fast, effort) can take seconds. Show the
+        // choice first so the switch and slider move immediately.
+        apply_config_choice(&task, option, &value);
+        task.persist();
+        task.emit_task();
+
        let live = task.live.lock().clone().filter(|l| !l.peer.is_closed());
        let mut model_options =
-            target.category.as_deref() != Some("model") || target.current.as_deref() == Some(value.as_str());
+            target.category.as_deref() != Some("model") || previous.as_deref() == Some(value.as_str());
        if let Some(live) = live.filter(|_| option != config::CURSOR_APPROVAL) {
            let (method, mut params) = config::set_request(&target, &value);
            params["sessionId"] = json!(live.session);
-            let reply: Value =
-                live.peer.request(method, params, None).await.map_err(|e| IdeError::internal(task.describe(e)))?;
+            let reply: Value = match live.peer.request(method, params, None).await {
+                Ok(reply) => reply,
+                Err(e) => {
+                    {
+                        let mut s = task.state.lock();
+                        s.wanted.retain(|c| c.id != option);
+                        if let Some(prev) = previous.clone() {
+                            s.wanted.push(AgentConfigChoice { id: option.to_owned(), value: prev });
+                        }
+                        if let Some(o) = s.task.config.iter_mut().find(|o| o.id == option) {
+                            o.current = previous.clone();
+                        }
+                        s.task.model = model_of(&s.task.config).or(s.task.model.take());
+                    }
+                    task.persist();
+                    task.emit_task();
+                    return Err(IdeError::internal(task.describe(e)));
+                }
+            };
            if let Some(options) = reply.get("configOptions") {
                config::merge_update(&mut task.state.lock().task.config, options);
                model_options = true;
@@ -904,8 +986,6 @@ impl AgentManager {
            if !model_options {
                s.task.config.retain(|o| o.category.as_deref() != Some("thought_level"));
            }
-            s.wanted.retain(|c| c.id != option);
-            s.wanted.push(AgentConfigChoice { id: option.to_owned(), value: value.clone() });
            if let Some(o) = s.task.config.iter_mut().find(|o| o.id == option) {
                o.current = Some(value);
            }
@@ -1232,15 +1312,6 @@ impl AgentManager {
        };
        // A copy of the task (a fork) may work in the same worktree.
        let shared = self.tasks.read().values().any(|t| t.id != id && t.state.lock().task.cwd.0 == cwd);
-        if remove_worktree && !shared && isolation == Isolation::Worktree && cwd.exists() {
-            // On Windows the agent's processes lock the folder (their working directory,
-            // open files) until they have exited.
-            if let Some(peer) = live {
-                let _ = tokio::time::timeout(EXIT_WAIT, peer.exited()).await;
-            }
-            let worktrees = self.shared.paths.worktrees_dir.clone();
-            blocking(move || worktree::remove(&root, &worktrees, &cwd)).await?;
-        }
        self.tasks.write().remove(id);
        *task.deleted.lock() = true;
        let _ = std::fs::remove_file(self.shared.paths.store_dir.join(format!("{id}.json")));
@@ -1250,7 +1321,17 @@ impl AgentManager {
        {
            let _ = std::fs::remove_dir_all(self.shared.paths.store_dir.join(saved));
        }
+        // The list drops the task now; removing a large worktree's folder can take a while.
        self.shared.emit(AgentEvent::Removed { id: id.to_owned() });
+        if remove_worktree && !shared && isolation == Isolation::Worktree && cwd.exists() {
+            // On Windows the agent's processes lock the folder (their working directory,
+            // open files) until they have exited.
+            if let Some(peer) = live {
+                let _ = tokio::time::timeout(EXIT_WAIT, peer.exited()).await;
+            }
+            let worktrees = self.shared.paths.worktrees_dir.clone();
+            blocking(move || worktree::remove(&root, &worktrees, &cwd)).await?;
+        }
        Ok(())
    }

@@ -1303,6 +1384,41 @@ impl AgentManager {
        Ok(())
    }

+    /// Accept: copies the task's changed files among `rel_paths` (all with `None`) from its
+    /// worktree into the local checkout, uncommitted, for the user to review and commit.
+    /// Files the checkout changed itself are left alone and reported. Only worktree tasks
+    /// have anything to accept.
+    pub async fn accept_changes(&self, id: &str, rel_paths: Option<Vec<String>>) -> IdeResult<AgentAcceptOutcome> {
+        let task = self.task(id)?;
+        if task.state.lock().busy {
+            return Err(IdeError::invalid("the agent is working: stop it before accepting its changes"));
+        }
+        let (isolation, cwd, base, root, before) = {
+            let s = task.state.lock();
+            (
+                s.task.isolation,
+                s.task.cwd.0.clone(),
+                s.task.base_commit.clone(),
+                s.task.project_root.clone().map(|p| p.0).unwrap_or_else(|| self.shared.paths.project_root.clone()),
+                (*s.before).clone(),
+            )
+        };
+        if isolation != Isolation::Worktree {
+            return Err(IdeError::invalid("the task works in the local checkout: there is nothing to accept"));
+        }
+        let Some(base) = base else {
+            return Err(IdeError::invalid("the task has no base revision to accept from"));
+        };
+        blocking(move || {
+            let wanted: Vec<AgentChange> = worktree::without_untouched(worktree::changes(&cwd, &base)?, &before)
+                .into_iter()
+                .filter(|c| rel_paths.as_ref().is_none_or(|p| p.contains(&c.rel_path)))
+                .collect();
+            worktree::accept(&root, &cwd, &base, &wanted)
+        })
+        .await
+    }
+
    /// Stops every agent (project closed).
    pub fn shutdown(&self) {
        for task in self.tasks.read().values() {
@@ -2121,6 +2237,44 @@ impl Task {
            .iter()
            .map(|question| question.answer_key.clone().unwrap_or_else(|| question.question.clone()))
            .collect();
+        if let Some(hook) = self.shared.security.read().clone()
+            && let Some(command) = security::extract_command(params)
+        {
+            match security::evaluate_command(&command, &hook()) {
+                security::PolicyDecision::Blocked(pattern) => {
+                    let reject = options.iter().find(|o| o.kind.starts_with("reject")).cloned();
+                    let _ = self.push_entry(AgentEntry::Permission {
+                        id,
+                        title,
+                        options,
+                        questions: Vec::new(),
+                        chosen: Some(format!("Blocked by policy ({pattern})")),
+                    });
+                    return match reject {
+                        Some(option) => json!({ "outcome": { "outcome": "selected", "optionId": option.id } }),
+                        None => json!({ "outcome": { "outcome": "cancelled" } }),
+                    };
+                }
+                security::PolicyDecision::Allowed => {
+                    if let Some(allow) = options
+                        .iter()
+                        .find(|o| o.kind == "allow_once")
+                        .or_else(|| options.iter().find(|o| o.kind.starts_with("allow")))
+                        .cloned()
+                    {
+                        let _ = self.push_entry(AgentEntry::Permission {
+                            id,
+                            title,
+                            options,
+                            questions: Vec::new(),
+                            chosen: Some(format!("{} (whitelisted)", allow.name)),
+                        });
+                        return json!({ "outcome": { "outcome": "selected", "optionId": allow.id } });
+                    }
+                }
+                security::PolicyDecision::AskUser => {}
+            }
+        }
        let (tx, rx) = std::sync::mpsc::channel();
        let entry =
            self.push_entry(AgentEntry::Permission { id, title, options: options.clone(), questions, chosen: None });
@@ -2434,7 +2588,7 @@ fn with_details(message: String, data: Option<&Value>) -> String {
    }
 }

-fn client_info() -> Value {
+pub(crate) fn client_info() -> Value {
    json!({ "name": "OpenIDEA", "version": env!("CARGO_PKG_VERSION") })
 }

@@ -2493,6 +2647,16 @@ fn retry_of(update: &Value, now: f64) -> Option<AgentRetry> {
    })
 }

+fn apply_config_choice(task: &Task, option: &str, value: &str) {
+    let mut s = task.state.lock();
+    s.wanted.retain(|c| c.id != option);
+    s.wanted.push(AgentConfigChoice { id: option.to_owned(), value: value.to_owned() });
+    if let Some(o) = s.task.config.iter_mut().find(|o| o.id == option) {
+        o.current = Some(value.to_owned());
+    }
+    s.task.model = model_of(&s.task.config).or(s.task.model.take());
+}
+
 fn model_of(config: &[AgentConfigOption]) -> Option<String> {
    config.iter().find(|o| o.category.as_deref() == Some("model")).and_then(|o| o.current.clone())
 }
@@ -602,3 +602,49 @@ pub struct McpServerInput {
 fn default_true() -> bool {
    true
 }
+
+/// Payload for creating a custom ACP agent (always the ACP driver); the id
+/// becomes the `<config>/agents/<id>.toml` file name.
+#[derive(Clone, Debug, Deserialize, Type)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct CustomAgentInput {
+    pub id: String,
+    pub name: String,
+    pub command: String,
+    #[serde(default)]
+    pub args: Vec<String>,
+    #[serde(default)]
+    pub env: BTreeMap<String, String>,
+}
+
+/// What importing one entry of a JetBrains `acp.json` file did.
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
+#[serde(rename_all = "camelCase")]
+pub struct AcpImportOutcome {
+    /// The `agent_servers` key the entry was imported from.
+    pub name: String,
+    /// The id its agent file would get (also when skipped).
+    pub id: String,
+    pub saved: bool,
+    /// Why the entry was skipped; empty when it was saved.
+    #[serde(default)]
+    pub reason: String,
+}
+
+/// What accepting a worktree task's changes copied into the local checkout.
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
+#[serde(rename_all = "camelCase")]
+pub struct AgentAcceptOutcome {
+    /// Relative paths copied into the checkout (uncommitted), including ones already identical.
+    pub accepted: Vec<String>,
+    /// Files left alone because the checkout has its own edits to them.
+    pub skipped: Vec<AgentAcceptSkipped>,
+}
+
+/// A file accept left alone, with why.
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
+#[serde(rename_all = "camelCase")]
+pub struct AgentAcceptSkipped {
+    pub path: String,
+    pub reason: String,
+}
@@ -31,7 +31,7 @@ pub(super) fn transcript(config_dir: &Path, cwd: &Path, id: &str) -> PathBuf {
 }

 /// The project directory name Claude Code uses for `cwd`.
-pub(super) fn escape(cwd: &Path) -> String {
+pub(crate) fn escape(cwd: &Path) -> String {
    cwd.to_string_lossy().chars().map(|c| if c.is_ascii_alphanumeric() { c } else { '-' }).collect()
 }

@@ -2,7 +2,7 @@
 //! `<config>/agents/<id>.toml` (written by hand, or by installing one from the ACP
 //! Registry, see `registry`).

-use crate::{AgentCommandReadOnlyReason, AgentProvider, AgentSource};
+use crate::{AcpImportOutcome, AgentCommandReadOnlyReason, AgentProvider, AgentSource, CustomAgentInput};
 use ide_core::{IdeError, IdeResult};
 use serde::{Deserialize, Serialize};
 use serde_json::Value;
@@ -278,6 +278,127 @@ fn update_builtin(custom_dir: &Path, id: &str, change: impl FnOnce(&mut CustomAg
    Ok(())
 }

+/// Saves a new custom agent; refuses built-in and ACP Registry ids, taken ids
+/// and an empty command. The id is also the agent file's name, so it must be
+/// a safe file stem.
+pub(crate) fn save_custom(custom_dir: &Path, input: &CustomAgentInput) -> IdeResult<()> {
+    let id = validated_custom_id(&input.id)?;
+    if builtin_spec(&id).is_some() {
+        return Err(IdeError::invalid(format!("{id} is a built-in agent; change its command instead")));
+    }
+    if input.command.trim().is_empty() {
+        return Err(IdeError::invalid("the agent command must not be empty"));
+    }
+    let file = custom_dir.join(format!("{id}.toml"));
+    if file.try_exists()? {
+        if CustomAgent::read(&file).is_ok_and(|a| a.registry.is_some()) {
+            return Err(IdeError::invalid(format!(
+                "{id} is installed from the ACP Registry; uninstall it there to replace it"
+            )));
+        }
+        return Err(IdeError::invalid(format!("there is already a custom agent '{id}'")));
+    }
+    CustomAgent {
+        name: Some(input.name.clone()),
+        driver: Driver::Acp,
+        command: input.command.clone(),
+        args: input.args.clone(),
+        env: input.env.clone(),
+        registry: None,
+    }
+    .write(&file)?;
+    Ok(())
+}
+
+/// Removes a custom agent's file; refuses built-in, ACP Registry and missing ids.
+pub(crate) fn remove_custom(custom_dir: &Path, id: &str) -> IdeResult<()> {
+    let id = validated_custom_id(id)?;
+    let id = id.as_str();
+    if builtin_spec(id).is_some() {
+        return Err(IdeError::invalid(format!("{id} is a built-in agent and cannot be removed")));
+    }
+    let file = custom_dir.join(format!("{id}.toml"));
+    let agent =
+        CustomAgent::read(&file).map_err(|_| IdeError::not_found(format!("there is no custom agent '{id}'")))?;
+    if agent.registry.is_some() {
+        return Err(IdeError::invalid(format!("{id} is installed from the ACP Registry; uninstall it there")));
+    }
+    match std::fs::remove_file(&file) {
+        Err(e) if e.kind() != std::io::ErrorKind::NotFound => Err(e.into()),
+        _ => Ok(()),
+    }
+}
+
+/// Imports a JetBrains `acp.json` file's `agent_servers` entries as custom
+/// agents, one outcome per entry; entries that collide, lack a command or
+/// have no usable name are skipped with a reason.
+pub(crate) fn import_acp(custom_dir: &Path, text: &str) -> IdeResult<Vec<AcpImportOutcome>> {
+    #[derive(Deserialize)]
+    struct AcpJson {
+        #[serde(default)]
+        agent_servers: BTreeMap<String, AcpServer>,
+    }
+    #[derive(Deserialize)]
+    struct AcpServer {
+        #[serde(default)]
+        command: String,
+        #[serde(default)]
+        args: Vec<String>,
+        #[serde(default)]
+        env: BTreeMap<String, String>,
+    }
+    let parsed: AcpJson =
+        serde_json::from_str(text).map_err(|e| IdeError::invalid(format!("not an acp.json file: {e}")))?;
+    let mut outcomes = Vec::with_capacity(parsed.agent_servers.len());
+    for (name, server) in parsed.agent_servers {
+        let id = slugify_id(&name);
+        let mut outcome = AcpImportOutcome { name, id: id.clone(), saved: false, reason: String::new() };
+        if id.is_empty() {
+            outcome.reason = "the name has no usable characters for an id".to_owned();
+        } else if builtin_spec(&id).is_some() {
+            outcome.reason = format!("{id} is a built-in agent");
+        } else if server.command.trim().is_empty() {
+            outcome.reason = "the entry has no command".to_owned();
+        } else if custom_dir.join(format!("{id}.toml")).try_exists()? {
+            outcome.reason = format!("there is already a custom agent '{id}'");
+        } else {
+            CustomAgent {
+                name: Some(outcome.name.clone()),
+                driver: Driver::Acp,
+                command: server.command,
+                args: server.args,
+                env: server.env,
+                registry: None,
+            }
+            .write(&custom_dir.join(format!("{id}.toml")))?;
+            outcome.saved = true;
+        }
+        outcomes.push(outcome);
+    }
+    Ok(outcomes)
+}
+
+/// A custom agent id doubles as a file stem: letters, digits, `-` and `_` only.
+fn validated_custom_id(id: &str) -> IdeResult<String> {
+    if !id.is_empty() && id.chars().all(|c| c.is_ascii_alphanumeric() || c == '-' || c == '_') {
+        return Ok(id.to_owned());
+    }
+    Err(IdeError::invalid(format!("'{id}' is not a usable agent id (letters, digits, '-' and '_' only)")))
+}
+
+/// Turns an `acp.json` server name into a file-stem id (`"My Agent!"` → `"my-agent"`).
+fn slugify_id(name: &str) -> String {
+    let mut id = String::with_capacity(name.len());
+    for c in name.chars() {
+        if c.is_ascii_alphanumeric() {
+            id.push(c.to_ascii_lowercase());
+        } else if !id.ends_with('-') {
+            id.push('-');
+        }
+    }
+    id.trim_matches('-').to_owned()
+}
+
 /// An agent file, `<config>/agents/<id>.toml`.
 #[derive(Debug, PartialEq, Serialize, Deserialize)]
 #[serde(deny_unknown_fields)]
@@ -753,4 +874,80 @@ mod tests {
        assert_eq!(spec.source, AgentSource::Registry { version: "0.10.0".into(), update: None });
        assert!(toml::from_str::<CustomAgent>("command = \"x\"\n[registry]\nid = \"x\"\n").is_err());
    }
+
+    fn custom_input(id: &str) -> CustomAgentInput {
+        CustomAgentInput {
+            id: id.into(),
+            name: "Mine".into(),
+            command: "/opt/mine".into(),
+            args: vec!["acp".into()],
+            env: BTreeMap::from([("K".to_owned(), "v".to_owned())]),
+        }
+    }
+
+    #[test]
+    fn custom_agents_save_list_and_remove() {
+        let dir = tempfile::tempdir().unwrap();
+        save_custom(dir.path(), &custom_input("mine")).unwrap();
+        let mine = load(Some(dir.path())).into_iter().find(|s| s.id == "mine").unwrap();
+        assert_eq!((mine.name.as_str(), mine.command.as_str()), ("Mine", "/opt/mine"));
+        assert_eq!(mine.env, vec![("K".to_owned(), "v".to_owned())]);
+        assert_eq!(mine.source, AgentSource::Custom);
+        remove_custom(dir.path(), "mine").unwrap();
+        assert!(!load(Some(dir.path())).iter().any(|s| s.id == "mine"));
+        remove_custom(dir.path(), "mine").unwrap_err();
+    }
+
+    #[test]
+    fn custom_agents_refuse_builtin_registry_and_bad_ids() {
+        let dir = tempfile::tempdir().unwrap();
+        save_custom(dir.path(), &custom_input("claude")).unwrap_err();
+        save_custom(dir.path(), &custom_input("../evil")).unwrap_err();
+        save_custom(dir.path(), &custom_input("")).unwrap_err();
+        let mut empty_command = custom_input("mine");
+        empty_command.command = "  ".into();
+        save_custom(dir.path(), &empty_command).unwrap_err();
+        save_custom(dir.path(), &custom_input("mine")).unwrap();
+        save_custom(dir.path(), &custom_input("mine")).unwrap_err();
+        remove_custom(dir.path(), "claude").unwrap_err();
+        // An id that isn't a plain file stem never reaches outside the agents directory.
+        let outside = dir.path().join("outside.toml");
+        std::fs::write(&outside, "command = \"/bin/sh\"\n").unwrap();
+        let agents = dir.path().join("agents");
+        std::fs::create_dir(&agents).unwrap();
+        remove_custom(&agents, "../outside").unwrap_err();
+        assert!(outside.exists());
+        std::fs::write(
+            dir.path().join("amp-acp.toml"),
+            "command = \"/registry/amp\"\n[registry]\nid = \"amp-acp\"\nversion = \"1.0\"\n",
+        )
+        .unwrap();
+        save_custom(dir.path(), &custom_input("amp-acp")).unwrap_err();
+        remove_custom(dir.path(), "amp-acp").unwrap_err();
+    }
+
+    #[test]
+    fn acp_json_imports_servers_and_skips_collisions() {
+        let dir = tempfile::tempdir().unwrap();
+        save_custom(dir.path(), &custom_input("taken")).unwrap();
+        let outcomes = import_acp(
+            dir.path(),
+            r#"{"agent_servers": {
+                "My Agent!": {"command": "/opt/agent", "args": ["--acp"], "env": {"K": "v"}},
+                "taken": {"command": "/opt/taken"},
+                "claude": {"command": "/opt/claude"},
+                "!!!": {"command": "/opt/noname"},
+                "silent": {"args": []}
+            }}"#,
+        )
+        .unwrap();
+        let saved: Vec<&str> = outcomes.iter().filter(|o| o.saved).map(|o| o.id.as_str()).collect();
+        assert_eq!(saved, ["my-agent"]);
+        assert!(outcomes.iter().filter(|o| !o.saved).all(|o| !o.reason.is_empty()));
+        let mine = load(Some(dir.path())).into_iter().find(|s| s.id == "my-agent").unwrap();
+        assert_eq!((mine.name.as_str(), mine.command.as_str()), ("My Agent!", "/opt/agent"));
+        assert_eq!(mine.source, AgentSource::Custom);
+        import_acp(dir.path(), "not json").unwrap_err();
+        assert!(import_acp(dir.path(), "{}").unwrap().is_empty());
+    }
 }
@@ -0,0 +1,487 @@
+//! Command execution security policy (Whitelist / Blacklist) for coding agents.
+
+use ide_core::settings::AgentSecuritySettings;
+use serde_json::Value;
+
+#[derive(Clone, Debug, PartialEq, Eq)]
+pub enum PolicyDecision {
+    /// Command matched a blacklist pattern (`pattern`).
+    Blocked(String),
+    /// Command matched the whitelist and no blacklist pattern.
+    Allowed,
+    /// Neither matched; prompt the user as usual.
+    AskUser,
+}
+
+/// Extracts the shell command string from an ACP `session/request_permission` payload
+/// when the request is for executing a command.
+pub fn extract_command(params: &Value) -> Option<String> {
+    let tool = params.get("toolCall").or_else(|| params.pointer("/subject/toolCall"))?;
+    let raw_cmd = tool.pointer("/rawInput/command").or_else(|| tool.pointer("/rawInput/cmd"));
+    if let Some(cmd) = raw_cmd.and_then(command_from_value) {
+        return Some(cmd);
+    }
+    let kind = tool.get("kind").and_then(Value::as_str).unwrap_or_default();
+    let name = tool.get("name").and_then(Value::as_str).unwrap_or_default();
+    let title =
+        tool.get("title").and_then(Value::as_str).or_else(|| params.get("title").and_then(Value::as_str))?.trim();
+    if let Some(cmd) = title.strip_prefix("Run ").map(str::trim).filter(|s| !s.is_empty()) {
+        return Some(cmd.to_owned());
+    }
+    if (kind == "execute" || matches!(name, "Bash" | "PowerShell" | "Execute" | "Run" | "terminal"))
+        && !title.is_empty()
+        && title != "Terminal"
+        && title != "Run a command"
+    {
+        return Some(title.to_owned());
+    }
+    None
+}
+
+fn command_from_value(val: &Value) -> Option<String> {
+    match val {
+        Value::String(s) => {
+            let trimmed = s.trim();
+            (!trimmed.is_empty()).then(|| trimmed.to_owned())
+        }
+        Value::Array(items) => {
+            let words: Vec<&str> = items.iter().filter_map(Value::as_str).collect();
+            if words.is_empty() {
+                return None;
+            }
+            let cmd = match words.as_slice() {
+                [_, flag, script] if flag.starts_with('-') && flag.ends_with('c') => (*script).trim().to_owned(),
+                _ => words.join(" ").trim().to_owned(),
+            };
+            (!cmd.is_empty()).then_some(cmd)
+        }
+        _ => None,
+    }
+}
+
+/// Checks whether a single pattern matches `command` using prefix + glob rules:
+/// - If `pattern` contains `*` or `?`, matches using glob wildcards (where `*` matches
+///   any sequence of characters). A trailing ` *` in the pattern also matches the bare
+///   command without arguments (e.g. `git status *` matches `git status`).
+/// - Otherwise, matches when `command` equals `pattern` or starts with `pattern` followed
+///   by whitespace (prefix match at word boundary).
+pub fn matches_command(pattern: &str, command: &str) -> bool {
+    let pat = pattern.trim();
+    let cmd = command.trim();
+    if pat.is_empty() || cmd.is_empty() {
+        return false;
+    }
+    if pat.contains('*') || pat.contains('?') {
+        if let Some(stem) = pat.strip_suffix(" *")
+            && cmd == stem.trim()
+        {
+            return true;
+        }
+        wildcard_match(pat.as_bytes(), cmd.as_bytes())
+    } else {
+        cmd == pat || cmd.strip_prefix(pat).is_some_and(|rest| rest.starts_with(char::is_whitespace))
+    }
+}
+
+fn wildcard_match(pat: &[u8], text: &[u8]) -> bool {
+    let (mut p, mut t) = (0, 0);
+    let (mut star_p, mut star_t) = (None, 0);
+    while t < text.len() {
+        if p < pat.len() && (pat[p] == b'?' || pat[p] == text[t]) {
+            p += 1;
+            t += 1;
+        } else if p < pat.len() && pat[p] == b'*' {
+            star_p = Some(p);
+            p += 1;
+            star_t = t;
+        } else if let Some(sp) = star_p {
+            p = sp + 1;
+            star_t += 1;
+            t = star_t;
+        } else {
+            return false;
+        }
+    }
+    while p < pat.len() && pat[p] == b'*' {
+        p += 1;
+    }
+    p == pat.len()
+}
+
+/// Matches an allowed command entry against a sub-command.
+/// An allow entry is a whole command or a prefix only up to a word boundary:
+/// e.g. `git status` matches `git status` and `git status -s`, but NOT `git statusx`.
+/// Any accidental trailing `*` in the allow entry is stripped so `git status*` behaves
+/// cleanly as a prefix at word boundaries instead of a glob wildcard.
+pub fn matches_allow_entry(entry: &str, command: &str) -> bool {
+    let mut entry = entry.trim();
+    if let Some(stripped) = entry.strip_suffix('*') {
+        entry = stripped.trim_end();
+    }
+    let cmd = command.trim();
+    if entry.is_empty() || cmd.is_empty() {
+        return false;
+    }
+    cmd == entry || cmd.strip_prefix(entry).is_some_and(|rest| rest.starts_with(char::is_whitespace))
+}
+
+/// Checks whether a word is an environment variable assignment (`IDENTIFIER=...`).
+fn is_env_assignment_word(word: &str) -> bool {
+    let Some((name, _)) = word.split_once('=') else {
+        return false;
+    };
+    if name.is_empty() {
+        return false;
+    }
+    let mut chars = name.chars();
+    match chars.next() {
+        Some(c) if c.is_ascii_alphabetic() || c == '_' => {}
+        _ => return false,
+    }
+    chars.all(|c| c.is_ascii_alphanumeric() || c == '_')
+}
+
+/// Returns true if the sub-command starts with an environment variable assignment,
+/// e.g. `FOO=bar cmd` or `PORT=3000`.
+fn has_leading_env_assignment(cmd: &str) -> bool {
+    let trimmed = cmd.trim_start();
+    let bytes = trimmed.as_bytes();
+    let mut i = 0;
+    let mut quote: Option<u8> = None;
+    while i < bytes.len() {
+        let b = bytes[i];
+        if b == b'\\' && quote != Some(b'\'') && i + 1 < bytes.len() {
+            i += 2;
+            continue;
+        }
+        if let Some(q) = quote {
+            if b == q {
+                quote = None;
+            }
+            i += 1;
+            continue;
+        }
+        if b == b'\'' || b == b'"' {
+            quote = Some(b);
+            i += 1;
+            continue;
+        }
+        if b.is_ascii_whitespace() {
+            break;
+        }
+        i += 1;
+    }
+    let first_word = &trimmed[..i];
+    is_env_assignment_word(first_word)
+}
+
+/// Checks whether `command` contains shell constructs that must never be auto-approved:
+/// - Command substitution: `$(...)` or backticks
+/// - Redirection: `>`, `>>`, `<`
+/// - Here-docs: `<<`
+/// - Subshells: `(...)`
+/// - Leading environment assignments: `VAR=val cmd`
+pub fn has_unsafe_shell_syntax(command: &str) -> bool {
+    let cmd = command.trim();
+    if cmd.is_empty() {
+        return false;
+    }
+
+    if has_leading_env_assignment(cmd) {
+        return true;
+    }
+
+    let bytes = cmd.as_bytes();
+    let mut i = 0;
+    let mut quote: Option<u8> = None;
+
+    while i < bytes.len() {
+        let b = bytes[i];
+
+        if b == b'\\' && quote != Some(b'\'') && i + 1 < bytes.len() {
+            i += 2;
+            continue;
+        }
+
+        if let Some(q) = quote {
+            if b == q {
+                quote = None;
+                i += 1;
+                continue;
+            }
+            // Inside double quotes: $(...) and `...` are evaluated by the shell.
+            if q == b'"' {
+                if b == b'`' {
+                    return true;
+                }
+                if b == b'$' && i + 1 < bytes.len() && bytes[i + 1] == b'(' {
+                    return true;
+                }
+            }
+            i += 1;
+            continue;
+        }
+
+        match b {
+            b'\'' | b'"' => {
+                quote = Some(b);
+                i += 1;
+            }
+            b'`' => return true,
+            b'$' if i + 1 < bytes.len() && bytes[i + 1] == b'(' => return true,
+            b'<' | b'>' => return true,
+            b'(' | b')' => return true,
+            _ => i += 1,
+        }
+    }
+
+    false
+}
+
+/// Splits a shell command into sub-commands separated by `;`, `&&`, `||`, `|`, or `\n`
+/// (outside single/double quotes) so compound commands cannot bypass policy checks.
+fn split_subcommands(command: &str) -> Vec<&str> {
+    let bytes = command.as_bytes();
+    let mut out = Vec::new();
+    let mut start = 0;
+    let mut i = 0;
+    let mut quote: Option<u8> = None;
+
+    while i < bytes.len() {
+        let b = bytes[i];
+        if let Some(q) = quote {
+            if b == b'\\' && q == b'"' && i + 1 < bytes.len() {
+                i += 2;
+                continue;
+            }
+            if b == q {
+                quote = None;
+            }
+            i += 1;
+            continue;
+        }
+        match b {
+            b'\'' | b'"' => {
+                quote = Some(b);
+                i += 1;
+            }
+            b'\\' if i + 1 < bytes.len() => {
+                i += 2;
+            }
+            b';' | b'\n' => {
+                let seg = command[start..i].trim();
+                if !seg.is_empty() {
+                    out.push(seg);
+                }
+                i += 1;
+                start = i;
+            }
+            b'&' | b'|' => {
+                let seg = command[start..i].trim();
+                if !seg.is_empty() {
+                    out.push(seg);
+                }
+                if i + 1 < bytes.len() && bytes[i + 1] == b {
+                    i += 2;
+                } else {
+                    i += 1;
+                }
+                start = i;
+            }
+            _ => i += 1,
+        }
+    }
+    let tail = command[start..].trim();
+    if !tail.is_empty() {
+        out.push(tail);
+    }
+    out
+}
+
+/// Evaluates `command` against `settings`:
+/// 1. Blacklist takes precedence: if the full command or any sub-command matches a
+///    `blocked_commands` entry, returns [`PolicyDecision::Blocked`].
+/// 2. Whitelist: allowed_commands cannot auto-approve when empty.
+/// 3. Every sub-command in a chain must be safe (no command substitution, redirection,
+///    subshell, or env assignments) and match at least one `allowed_commands` entry
+///    exactly or up to word boundary; otherwise falls back to [`PolicyDecision::AskUser`].
+pub fn evaluate_command(command: &str, settings: &AgentSecuritySettings) -> PolicyDecision {
+    let cmd = command.trim();
+    if cmd.is_empty() {
+        return PolicyDecision::AskUser;
+    }
+    let subcommands = split_subcommands(cmd);
+
+    for pat in &settings.blocked_commands {
+        let pat = pat.trim();
+        if pat.is_empty() {
+            continue;
+        }
+        if matches_command(pat, cmd) || subcommands.iter().any(|sub| matches_command(pat, sub)) {
+            return PolicyDecision::Blocked(pat.to_owned());
+        }
+    }
+
+    if settings.allowed_commands.is_empty() || subcommands.is_empty() {
+        return PolicyDecision::AskUser;
+    }
+
+    let all_allowed = subcommands.iter().all(|sub| {
+        let s = sub.trim();
+        if s.is_empty() || has_unsafe_shell_syntax(s) {
+            return false;
+        }
+        settings.allowed_commands.iter().any(|entry| matches_allow_entry(entry, s))
+    });
+
+    if all_allowed {
+        return PolicyDecision::Allowed;
+    }
+
+    PolicyDecision::AskUser
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use serde_json::json;
+
+    #[test]
+    fn prefix_and_glob_matching() {
+        assert!(matches_command("git status", "git status"));
+        assert!(matches_command("git status", "git status -s"));
+        assert!(!matches_command("git status", "git statusbar"));
+        assert!(matches_command("git status*", "git status"));
+        assert!(matches_command("git status*", "git status --short"));
+        assert!(matches_command("npm test *", "npm test"));
+        assert!(matches_command("npm test *", "npm test unit"));
+        assert!(matches_command("rm -rf *", "rm -rf /tmp/foo"));
+        assert!(matches_command("rm -rf *", "rm -rf /"));
+    }
+
+    #[test]
+    fn blacklist_takes_precedence_and_catches_chained_commands() {
+        let settings = AgentSecuritySettings::default();
+        assert_eq!(evaluate_command("rm -rf /tmp/build", &settings), PolicyDecision::Blocked("rm -rf *".into()));
+        assert_eq!(evaluate_command("git status && rm -rf /", &settings), PolicyDecision::Blocked("rm -rf *".into()));
+        assert_eq!(evaluate_command(":(){ :|:& };:", &settings), PolicyDecision::Blocked(":(){ :|:& };:".into()));
+    }
+
+    #[test]
+    fn allow_entry_matching_word_boundary() {
+        assert!(matches_allow_entry("git status", "git status"));
+        assert!(matches_allow_entry("git status", "git status -s"));
+        assert!(!matches_allow_entry("git status", "git statusbar"));
+        assert!(!matches_allow_entry("git status", "git statusx"));
+        // Trailing asterisk in allow entry normalizes cleanly to word boundary prefix
+        assert!(matches_allow_entry("git status*", "git status"));
+        assert!(matches_allow_entry("git status*", "git status --short"));
+        assert!(!matches_allow_entry("git status*", "git statusbar"));
+        assert!(matches_allow_entry("ls", "ls"));
+        assert!(matches_allow_entry("ls", "ls -la"));
+        assert!(!matches_allow_entry("ls", "lsof"));
+        assert!(matches_allow_entry("cargo check", "cargo check"));
+        assert!(matches_allow_entry("cargo check", "cargo check --workspace"));
+        assert!(!matches_allow_entry("cargo check", "cargo checkmate"));
+    }
+
+    #[test]
+    fn unsafe_shell_syntax_detection() {
+        // Command substitutions: $(...) and `...`
+        assert!(has_unsafe_shell_syntax("echo $(whoami)"));
+        assert!(has_unsafe_shell_syntax("echo \"user: $(whoami)\""));
+        assert!(has_unsafe_shell_syntax("echo `whoami`"));
+        assert!(has_unsafe_shell_syntax("echo \"`whoami`\""));
+
+        // Redirections: >, >>, <
+        assert!(has_unsafe_shell_syntax("git status > /tmp/out"));
+        assert!(has_unsafe_shell_syntax("git status >> /tmp/out"));
+        assert!(has_unsafe_shell_syntax("cat < /tmp/in"));
+        assert!(has_unsafe_shell_syntax("cat << 'EOF'"));
+
+        // Subshells: (...)
+        assert!(has_unsafe_shell_syntax("(cd /tmp && ls)"));
+        assert!(has_unsafe_shell_syntax("git status && (exit 1)"));
+
+        // Environment assignments: VAR=val ...
+        assert!(has_unsafe_shell_syntax("FOO=bar git status"));
+        assert!(has_unsafe_shell_syntax("PORT=3000 npm test"));
+        assert!(has_unsafe_shell_syntax("_SECRET=123 cargo test"));
+        assert!(has_unsafe_shell_syntax("A=\"b c\" git status"));
+
+        // Safe constructs with characters inside quotes or command flags
+        assert!(!has_unsafe_shell_syntax("git commit -m \"fix <bug> and (issue)\""));
+        assert!(!has_unsafe_shell_syntax("git commit -m 'fix <bug>'"));
+        assert!(!has_unsafe_shell_syntax("cargo test --test=unit"));
+        assert!(!has_unsafe_shell_syntax("git status -s"));
+    }
+
+    #[test]
+    fn default_settings_has_no_auto_approval_and_blocks_dangerous_defaults() {
+        let settings = AgentSecuritySettings::default();
+        assert!(settings.allowed_commands.is_empty(), "allowed_commands must start empty");
+        // Safe commands ask user by default
+        assert_eq!(evaluate_command("git status", &settings), PolicyDecision::AskUser);
+        assert_eq!(evaluate_command("ls", &settings), PolicyDecision::AskUser);
+        assert_eq!(evaluate_command("cargo check", &settings), PolicyDecision::AskUser);
+        // Blacklist patterns are still blocked by default
+        assert_eq!(evaluate_command("rm -rf /", &settings), PolicyDecision::Blocked("rm -rf *".into()));
+        assert_eq!(evaluate_command("rm -rf /tmp/test", &settings), PolicyDecision::Blocked("rm -rf *".into()));
+    }
+
+    #[test]
+    fn whitelist_allows_safe_single_and_chained_commands_only() {
+        let settings = AgentSecuritySettings {
+            allowed_commands: vec!["git status".into(), "git diff".into(), "cargo test".into()],
+            blocked_commands: vec!["rm -rf *".into()],
+        };
+        assert_eq!(evaluate_command("git status -s", &settings), PolicyDecision::Allowed);
+        assert_eq!(evaluate_command("git diff HEAD~1", &settings), PolicyDecision::Allowed);
+        assert_eq!(evaluate_command("git status && cargo test", &settings), PolicyDecision::Allowed);
+
+        // Word boundary: git statusx must not match git status
+        assert_eq!(evaluate_command("git statusx", &settings), PolicyDecision::AskUser);
+
+        // Unsafe syntax (redirection, command substitution, env assignment) falls back to AskUser
+        assert_eq!(evaluate_command("git status > out.txt", &settings), PolicyDecision::AskUser);
+        assert_eq!(evaluate_command("git status $(whoami)", &settings), PolicyDecision::AskUser);
+        assert_eq!(evaluate_command("FOO=bar git status", &settings), PolicyDecision::AskUser);
+
+        // Chaining an unapproved command must still ask the user.
+        assert_eq!(evaluate_command("git status && curl https://example.com", &settings), PolicyDecision::AskUser);
+        assert_eq!(evaluate_command("cargo publish", &settings), PolicyDecision::AskUser);
+
+        // Blacklist still takes precedence over whitelist
+        assert_eq!(evaluate_command("git status && rm -rf /", &settings), PolicyDecision::Blocked("rm -rf *".into()));
+    }
+
+    #[test]
+    fn extracts_command_from_v1_v2_and_codex_payloads() {
+        let claude = json!({
+            "toolCall": {
+                "title": "git status",
+                "kind": "execute",
+                "rawInput": { "command": "git status --short" }
+            }
+        });
+        assert_eq!(extract_command(&claude).as_deref(), Some("git status --short"));
+
+        let codex = json!({
+            "toolCall": {
+                "title": "Run cargo test",
+                "kind": "execute",
+                "rawInput": { "command": ["/bin/zsh", "-lc", "cargo test --workspace"] }
+            }
+        });
+        assert_eq!(extract_command(&codex).as_deref(), Some("cargo test --workspace"));
+
+        let write = json!({
+            "toolCall": {
+                "title": "Write foo.txt",
+                "kind": "edit",
+                "rawInput": { "file_path": "foo.txt" }
+            }
+        });
+        assert_eq!(extract_command(&write), None);
+    }
+}
@@ -43,6 +43,11 @@ struct FakeAgent {
    /// Hold the late mode reply until the prompt's permission request is already waiting.
    hold_late_mode: bool,
    empty_config: AtomicBool,
+    /// Blocks `session/new` until discovery times out (see `acp::discover` test timeout).
+    hold_session_new: AtomicBool,
+    /// Sleeps this long at the start of `session/set_config_option`, after noting the time.
+    delay_config: Duration,
+    config_entered: Mutex<Option<std::time::Instant>>,
    /// Config options `session/new` reports after the model one (per-model efforts, say).
    extra_options: Mutex<Vec<Value>>,
    model_options: Mutex<HashMap<String, Vec<Value>>>,
@@ -157,6 +162,9 @@ impl Handler for FakeAgent {
                )
            }
            "session/new" => {
+                if self.hold_session_new.load(Ordering::Acquire) {
+                    std::thread::sleep(Duration::from_secs(5));
+                }
                if self.empty_config.load(Ordering::Acquire) {
                    return Ok(json!({"sessionId": "s1"}));
                }
@@ -190,6 +198,10 @@ impl Handler for FakeAgent {
                }
            }
            "session/set_config_option" | "session/set_mode" => {
+                if method == "session/set_config_option" && !self.delay_config.is_zero() {
+                    *self.config_entered.lock() = Some(std::time::Instant::now());
+                    std::thread::sleep(self.delay_config);
+                }
                self.calls.lock().push(format!("{method} {}", params.get("value").or(params.get("modeId")).unwrap()));
                if params["configId"] == "model" && !self.model_options.lock().is_empty() {
                    return Ok(json!({"configOptions": self.options_for(params["value"].as_str().unwrap())}));
@@ -2631,6 +2643,92 @@ async fn session_settings_win_over_discovery_in_memory_and_on_disk() {
    }
 }

+#[tokio::test(flavor = "multi_thread")]
+async fn provider_reload_does_not_start_acp_discovery() {
+    let agent = Arc::new(FakeAgent::default());
+    let mgr = manager(tempfile::tempdir().unwrap().path(), agent.clone());
+    mgr.reload_providers();
+    tokio::time::sleep(Duration::from_millis(100)).await;
+    assert!(agent.calls.lock().is_empty(), "reload must not spawn cursor-agent");
+}
+
+#[tokio::test(flavor = "multi_thread")]
+async fn composer_commands_discover_cursor_effort_and_fast() {
+    let agent = Arc::new(FakeAgent {
+        extra_options: Mutex::new(vec![
+            json!({"id": "effort", "type": "select", "currentValue": "medium",
+                "options": [{"value": "low"}, {"value": "medium"}, {"value": "high"}]}),
+            json!({"id": "fast", "type": "select", "currentValue": "false",
+                "options": [{"value": "false", "name": "Off"}, {"value": "true", "name": "On"}]}),
+        ]),
+        ..Default::default()
+    });
+    let mgr = manager(tempfile::tempdir().unwrap().path(), agent.clone());
+    mgr.commands("cursor", None).await.unwrap();
+    let calls = agent.calls.lock();
+    assert!(calls.iter().any(|m| m.as_str() == "session/new"));
+    assert_eq!(calls.iter().filter(|m| m.as_str() == "initialize").count(), 1);
+    let cursor = mgr.providers().into_iter().find(|p| p.id == "cursor").unwrap();
+    assert_eq!(cursor.config.iter().find(|o| o.id == "fast").unwrap().current.as_deref(), Some("false"));
+    assert!(
+        cursor
+            .thought_levels
+            .values()
+            .next()
+            .is_some_and(|levels| { levels.iter().any(|o| o.category.as_deref() == Some("thought_level")) })
+    );
+}
+
+#[tokio::test(flavor = "multi_thread")]
+async fn config_choice_shows_before_the_agent_answers() {
+    let agent = Arc::new(FakeAgent {
+        extra_options: Mutex::new(vec![json!({
+            "id": "fast", "category": "model_config", "type": "select", "currentValue": "true",
+            "options": [{"value": "true", "name": "On"}, {"value": "false", "name": "Off"}]
+        })]),
+        delay_config: Duration::from_millis(300),
+        ..Default::default()
+    });
+    let mgr = manager(tempfile::tempdir().unwrap().path(), agent.clone());
+    let shown: Arc<Mutex<Option<std::time::Instant>>> = Arc::default();
+    let mark = shown.clone();
+    mgr.subscribe(Arc::new(move |e| {
+        if let AgentEvent::Task { task } = e
+            && task.config.iter().any(|o| o.id == "fast" && o.current.as_deref() == Some("false"))
+            && mark.lock().is_none()
+        {
+            *mark.lock() = Some(std::time::Instant::now());
+        }
+    }));
+    let task = mgr
+        .create(NewAgentTask {
+            project_root: None,
+            prompt: text("again"),
+            provider: "claude".into(),
+            config: vec![],
+            isolation: Isolation::Local,
+            base: None,
+        })
+        .await
+        .unwrap();
+    wait_for(&mgr, &task.id, AgentStatus::Ready).await;
+    mgr.set_config(&task.id, "fast", "false".into()).await.unwrap();
+    let shown = (*shown.lock()).expect("the switch moved");
+    let entered = (*agent.config_entered.lock()).expect("the agent received the change");
+    assert!(shown < entered, "the composer updates before the agent answers");
+}
+
+#[tokio::test(flavor = "multi_thread")]
+async fn discovery_times_out_when_session_new_hangs() {
+    let agent = Arc::new(FakeAgent { hold_session_new: AtomicBool::new(true), ..Default::default() });
+    let mgr = manager(tempfile::tempdir().unwrap().path(), agent.clone());
+    let started = std::time::Instant::now();
+    mgr.commands("cursor", None).await.unwrap();
+    assert!(started.elapsed() < Duration::from_secs(10), "discovery should time out quickly in tests");
+    let cursor = mgr.providers().into_iter().find(|p| p.id == "cursor").unwrap();
+    assert!(!cursor.config.iter().any(|o| o.category.as_deref() == Some("model")));
+}
+
 #[tokio::test(flavor = "multi_thread")]
 async fn discovered_effort_levels_fill_models_no_session_has_reported() {
    let tmp = tempfile::tempdir().unwrap();
@@ -2770,3 +2868,71 @@ async fn rolling_back_restores_the_start_of_the_task_and_keeps_the_users_own_edi
    mgr.delete(&task.id, false).await.unwrap();
    assert!(!dir.join("store").join(format!("{}.before", task.id)).exists());
 }
+
+#[tokio::test(flavor = "multi_thread")]
+async fn security_policy_auto_approves_whitelist_and_rejects_blacklist() {
+    use ide_core::settings::AgentSecuritySettings;
+
+    // 1. Whitelist auto-approves "cargo test" without waiting for manual respond().
+    let tmp = tempfile::tempdir().unwrap();
+    let agent = Arc::new(FakeAgent::default());
+    let mgr = manager(tmp.path(), agent);
+    mgr.set_security_hook(Arc::new(|| AgentSecuritySettings {
+        allowed_commands: vec!["cargo test".into()],
+        blocked_commands: vec!["rm -rf *".into()],
+    }));
+    let task = mgr
+        .create(NewAgentTask {
+            project_root: None,
+            prompt: text("run tests"),
+            provider: "claude".into(),
+            config: vec![],
+            isolation: Isolation::Local,
+            base: None,
+        })
+        .await
+        .unwrap();
+    wait_for(&mgr, &task.id, AgentStatus::Ready).await;
+    let entries = mgr.entries(&task.id, None).unwrap();
+    assert!(
+        entries.iter().any(|e| matches!(e, AgentEntry::Agent { text } if text.contains("chose yes"))),
+        "{entries:?}"
+    );
+    assert!(
+        entries.iter().any(|e| matches!(
+            e,
+            AgentEntry::Permission { chosen: Some(c), .. } if c.contains("whitelisted")
+        )),
+        "{entries:?}"
+    );
+
+    // 2. Blacklist auto-rejects "cargo test" when matched by blocked_commands.
+    mgr.set_security_hook(Arc::new(|| AgentSecuritySettings {
+        allowed_commands: vec!["cargo test".into()],
+        blocked_commands: vec!["cargo test*".into()],
+    }));
+    let blocked_task = mgr
+        .create(NewAgentTask {
+            project_root: None,
+            prompt: text("run blocked"),
+            provider: "claude".into(),
+            config: vec![],
+            isolation: Isolation::Local,
+            base: None,
+        })
+        .await
+        .unwrap();
+    wait_for(&mgr, &blocked_task.id, AgentStatus::Ready).await;
+    let blocked_entries = mgr.entries(&blocked_task.id, None).unwrap();
+    assert!(
+        blocked_entries.iter().any(|e| matches!(e, AgentEntry::Agent { text } if text.contains("chose no"))),
+        "{blocked_entries:?}"
+    );
+    assert!(
+        blocked_entries.iter().any(|e| matches!(
+            e,
+            AgentEntry::Permission { chosen: Some(c), .. } if c.contains("Blocked by policy")
+        )),
+        "{blocked_entries:?}"
+    );
+}
@@ -14,8 +14,18 @@ pub(crate) struct Created {
    pub base_commit: String,
 }

+/// The repository of `path`, free to execute: the host runs every agent command that
+/// reaches a repository only in a trusted project.
+fn discover(path: &Path) -> IdeResult<Option<Repo>> {
+    let repo = Repo::discover(path)?;
+    if let Some(repo) = &repo {
+        repo.set_execution_allowed(true);
+    }
+    Ok(repo)
+}
+
 fn repo_at(path: &Path) -> IdeResult<Repo> {
-    Repo::discover(path)?.ok_or_else(|| IdeError::unavailable(format!("{} is not in a git repository", path.display())))
+    discover(path)?.ok_or_else(|| IdeError::unavailable(format!("{} is not in a git repository", path.display())))
 }

 /// The current branch (or commit when detached) and its commit.
@@ -91,10 +101,11 @@ fn retrying(attempts: u32, pause: Duration, mut op: impl FnMut() -> std::io::Res
 /// Files under `cwd` that differ from `base` (untracked files included), with line counts.
 /// Outside a repository there is nothing to compare against: no changes.
 pub(crate) fn changes(cwd: &Path, base: &str) -> IdeResult<Vec<AgentChange>> {
-    let Some(repo) = Repo::discover(cwd)? else { return Ok(Vec::new()) };
+    let Some(repo) = discover(cwd)? else { return Ok(Vec::new()) };
    let root = repo.root().to_path_buf();
-    let stats = repo.numstat_with_worktree(base)?;
-    let stat = |rel: &str| stats.iter().find(|(p, ..)| p == rel).map_or((0, 0), |&(_, a, r)| (a, r));
+    let stats: std::collections::HashMap<String, (u32, u32)> =
+        repo.numstat_with_worktree(base)?.into_iter().map(|(p, a, r)| (p, (a, r))).collect();
+    let stat = |rel: &str| stats.get(rel).copied().unwrap_or((0, 0));
    let mut out: Vec<AgentChange> = repo
        .diff_with_worktree(base)?
        .into_iter()
@@ -103,8 +114,9 @@ pub(crate) fn changes(cwd: &Path, base: &str) -> IdeResult<Vec<AgentChange>> {
            AgentChange { path: IpcPath(root.join(&f.path)), rel_path: f.path, kind: f.kind, added, removed }
        })
        .collect();
+    let tracked: std::collections::HashSet<String> = out.iter().map(|c| c.rel_path.clone()).collect();
    for s in repo.status()? {
-        if s.unstaged == Some(ChangeKind::Untracked) && !out.iter().any(|c| c.rel_path == s.rel_path) {
+        if s.unstaged == Some(ChangeKind::Untracked) && !tracked.contains(&s.rel_path) {
            let added = std::fs::read_to_string(&*s.path).map_or(0, |t| t.lines().count() as u32);
            out.push(AgentChange { path: s.path, rel_path: s.rel_path, kind: ChangeKind::Added, added, removed: 0 });
        }
@@ -113,6 +125,50 @@ pub(crate) fn changes(cwd: &Path, base: &str) -> IdeResult<Vec<AgentChange>> {
    Ok(out)
 }

+/// Copies the task's `changes` (against `base`) from the worktree `cwd` into the
+/// local checkout `root`, uncommitted: the user reviews and commits them with the
+/// VCS tools. Files the checkout changed itself are left alone and reported, so
+/// accepting never destroys the user's own edits. Returns accepted and skipped paths.
+pub(crate) fn accept(
+    root: &Path,
+    cwd: &Path,
+    base: &str,
+    changes: &[AgentChange],
+) -> IdeResult<crate::AgentAcceptOutcome> {
+    let repo = repo_at(cwd)?;
+    let mut accepted = Vec::with_capacity(changes.len());
+    let mut skipped = Vec::new();
+    for change in changes {
+        let local = root.join(&change.rel_path);
+        let base_bytes = repo.file_bytes_at(&change.path.0, Some(base))?;
+        let current = std::fs::read(&change.path.0).ok();
+        let local_bytes = std::fs::read(&local).ok();
+        if local_bytes == current {
+            accepted.push(change.rel_path.clone());
+        } else if local_bytes == base_bytes {
+            match current {
+                Some(bytes) => {
+                    if let Some(parent) = local.parent() {
+                        std::fs::create_dir_all(parent)?;
+                    }
+                    std::fs::write(&local, bytes)?;
+                }
+                None => match std::fs::remove_file(&local) {
+                    Err(e) if e.kind() != std::io::ErrorKind::NotFound => return Err(e.into()),
+                    _ => {}
+                },
+            }
+            accepted.push(change.rel_path.clone());
+        } else {
+            skipped.push(crate::AgentAcceptSkipped {
+                path: change.rel_path.clone(),
+                reason: "the checkout has changes of its own to it; accept it by hand".to_owned(),
+            });
+        }
+    }
+    Ok(crate::AgentAcceptOutcome { accepted, skipped })
+}
+
 /// Size and modification time of a file, `None` once it is gone.
 pub(crate) type Stamp = Option<(u64, u128)>;

@@ -124,7 +180,10 @@ pub(crate) fn stamp(path: &Path) -> Stamp {

 /// The files already changed in `cwd` against `HEAD`, stamped so later edits to them show.
 pub(crate) fn snapshot(cwd: &Path) -> IdeResult<BTreeMap<String, Stamp>> {
-    Ok(changes(cwd, "HEAD")?.into_iter().map(|c| (c.rel_path, stamp(&c.path))).collect())
+    // Paths and stamps only: no diff and no line counts, which read every untracked file
+    // and held up starting a task in a checkout with many of them.
+    let Some(repo) = Repo::discover(cwd)? else { return Ok(BTreeMap::new()) };
+    Ok(repo.status()?.into_iter().map(|s| (s.rel_path, stamp(&s.path))).collect())
 }

 /// Drops the changes that were there before the task and haven't been touched since.
@@ -204,7 +263,7 @@ pub(crate) fn restore(
 }

 pub(crate) fn file_at(cwd: &Path, path: &Path, rev: &str) -> IdeResult<Option<String>> {
-    let Some(repo) = Repo::discover(cwd)? else { return Ok(None) };
+    let Some(repo) = discover(cwd)? else { return Ok(None) };
    let encoding = match ide_vfs::load_text(path) {
        Ok(loaded) => encoding_rs::Encoding::for_label(loaded.encoding.as_bytes()).unwrap_or(encoding_rs::UTF_8),
        Err(_) => ide_vfs::detect_encoding(&repo.file_bytes_at(path, Some(rev))?.unwrap_or_default(), None),
@@ -391,4 +450,61 @@ mod tests {
        assert!(remove(&repo, &tmp.path().join("wt"), &elsewhere).is_err());
        assert!(elsewhere.join("keep.txt").exists());
    }
+
+    fn accept_repo() -> (tempfile::TempDir, PathBuf, Created) {
+        let tmp = tempfile::tempdir().unwrap();
+        let repo = tmp.path().join("repo");
+        std::fs::create_dir(&repo).unwrap();
+        git(&repo, &["init", "-q", "-b", "main"]);
+        std::fs::write(repo.join("a.txt"), "one\ntwo\n").unwrap();
+        std::fs::write(repo.join("gone.txt"), "bye\n").unwrap();
+        git(&repo, &["add", "."]);
+        git(&repo, &["commit", "-q", "-m", "init"]);
+        let created = create(&repo, &tmp.path().join("wt"), "Edit A", None).unwrap();
+        (tmp, repo, created)
+    }
+
+    fn listed(cwd: &Path, base: &str) -> Vec<AgentChange> {
+        without_untouched(changes(cwd, base).unwrap(), &BTreeMap::new())
+    }
+
+    #[test]
+    fn accept_copies_new_modified_and_deleted_files_into_the_checkout() {
+        let (_tmp, repo, created) = accept_repo();
+        std::fs::write(created.path.join("a.txt"), "one\nTWO\n").unwrap();
+        std::fs::write(created.path.join("new.txt"), "x\n").unwrap();
+        std::fs::remove_file(created.path.join("gone.txt")).unwrap();
+
+        let outcome =
+            accept(&repo, &created.path, &created.base_commit, &listed(&created.path, &created.base_commit)).unwrap();
+        assert!(outcome.skipped.is_empty());
+        assert_eq!(outcome.accepted, ["a.txt", "gone.txt", "new.txt"]);
+        assert_eq!(std::fs::read_to_string(repo.join("a.txt")).unwrap(), "one\nTWO\n");
+        assert_eq!(std::fs::read_to_string(repo.join("new.txt")).unwrap(), "x\n");
+        assert!(!repo.join("gone.txt").exists());
+
+        // Accepting again changes nothing: the checkout already matches.
+        let again =
+            accept(&repo, &created.path, &created.base_commit, &listed(&created.path, &created.base_commit)).unwrap();
+        assert!(again.skipped.is_empty());
+        assert_eq!(again.accepted, ["a.txt", "gone.txt", "new.txt"]);
+    }
+
+    #[test]
+    fn accept_leaves_files_the_checkout_changed_itself() {
+        let (_tmp, repo, created) = accept_repo();
+        std::fs::write(created.path.join("a.txt"), "one\nTWO\n").unwrap();
+        std::fs::write(created.path.join("gone.txt"), "bye\nbye\n").unwrap();
+        std::fs::write(repo.join("a.txt"), "one\nMINE\n").unwrap();
+
+        let outcome =
+            accept(&repo, &created.path, &created.base_commit, &listed(&created.path, &created.base_commit)).unwrap();
+        assert_eq!(outcome.accepted, ["gone.txt"]);
+        assert_eq!(outcome.skipped.len(), 1);
+        assert_eq!(outcome.skipped[0].path, "a.txt");
+        assert!(!outcome.skipped[0].reason.is_empty());
+        // The user's own edit survives; the other file comes over.
+        assert_eq!(std::fs::read_to_string(repo.join("a.txt")).unwrap(), "one\nMINE\n");
+        assert_eq!(std::fs::read_to_string(repo.join("gone.txt")).unwrap(), "bye\nbye\n");
+    }
 }
@@ -265,6 +265,14 @@ pub fn menu_fingerprint(
 }

 impl LaunchFingerprint {
+    /// Folders (relative to the project) of the Maven projects whose POM is an input.
+    pub(super) fn project_dirs(&self) -> impl Iterator<Item = &Path> {
+        self.files
+            .keys()
+            .filter(|p| p.is_relative() && p.file_name().is_some_and(|n| n == "pom.xml"))
+            .map(|pom| pom.parent().unwrap_or(Path::new("")))
+    }
+
    /// Relative paths whose content changed while `(length, mtime)` stayed the same
    /// compared to `previous` (timestamp-preserving external edits, coarse-granularity
    /// filesystems). Timestamp-incremental builders (Maven, the Kotlin plugin) would
@@ -0,0 +1,253 @@
+//! Resources a Gradle build changes while copying them (filters, `expand`, renames, extra
+//! sources). The Java language server copies them as they are into Buildship's
+//! `bin/<source set>` folders, which launches run from; IntelliJ IDEA runs Gradle's copy.
+//! Before a launch, Gradle processes them and its output replaces those plain copies, so
+//! each resource is on the classpath once, as the build produces it.
+use super::{BuildPlan, BuildStep, BuildSystem, Format, run, subdir};
+use crate::BuildModel;
+use crate::gradle::{self, GradleModel, ReportedProject};
+use ide_core::{CancellationToken, IdeError, IdeResult, Severity};
+use std::fs;
+use std::path::{Path, PathBuf};
+
+/// A source set whose resources Gradle processes, with the folder the launch reads them from.
+#[derive(Debug, PartialEq)]
+struct Target {
+    /// Task path from the root build (`:app:processResources`).
+    task: String,
+    /// Where the task writes the resources.
+    output: PathBuf,
+    /// The Java language server's output folder of the source set, on the launch classpath.
+    jdtls: PathBuf,
+}
+
+fn targets(reported: &[ReportedProject], class_paths: &[String]) -> Vec<Target> {
+    // buildSrc is built before the build, never addressable as `:buildSrc:<task>`.
+    let addressable = |p: &&ReportedProject| !p.build.as_deref().is_some_and(|b| b.ends_with(":buildSrc"));
+    let sets: Vec<_> = reported
+        .iter()
+        .filter(addressable)
+        .flat_map(|p| p.source_sets.iter().filter_map(move |s| Some((p, s, s.processed.as_ref()?))))
+        .collect();
+    if sets.is_empty() {
+        return Vec::new();
+    }
+    // Canonical, as Gradle reports its folders: jdtls may spell them differently.
+    let entries: Vec<PathBuf> = class_paths.iter().filter_map(|p| dunce::canonicalize(p).ok()).collect();
+    sets.into_iter()
+        .filter_map(|(p, set, resources)| {
+            // Buildship's output folder of the source set.
+            let jdtls = dunce::canonicalize(Path::new(&p.dir).join("bin").join(&set.name)).ok()?;
+            let project = if p.path == ":" { "" } else { p.path.as_str() };
+            entries.contains(&jdtls).then(|| Target {
+                task: format!("{project}:{}", resources.task),
+                output: PathBuf::from(&resources.dir),
+                jdtls,
+            })
+        })
+        .collect()
+}
+
+/// Before a JVM launch from the Java language server's output folders on `class_paths`:
+/// runs the Gradle tasks that process resources of those folders' source sets (see the
+/// module docs) and copies their output over the plain copies. `cache_dir` holds the
+/// linked builds' last syncs. Returns the tasks run, none for builds that copy their
+/// resources as they are.
+pub fn process_launch_resources(
+    root: &Path,
+    model: &BuildModel,
+    cache_dir: &Path,
+    class_paths: &[String],
+    cancel: &CancellationToken,
+) -> IdeResult<Vec<String>> {
+    // A composite also reports the builds it includes: the deepest build owning a folder runs its task.
+    let mut builds: Vec<&GradleModel> = model.gradle.iter().collect();
+    builds.sort_by_key(|g| std::cmp::Reverse(subdir(root, &g.dir).components().count()));
+    let mut done: Vec<PathBuf> = Vec::new();
+    let mut tasks = Vec::new();
+    for g in builds {
+        let reported = crate::sync::reported_gradle_projects(&gradle::cache_dir(cache_dir, &g.dir));
+        let targets: Vec<Target> =
+            targets(&reported, class_paths).into_iter().filter(|t| !done.contains(&t.jdtls)).collect();
+        if targets.is_empty() {
+            continue;
+        }
+        let mut step = BuildStep::new(&g.command, &["--console=plain"], &subdir(root, &g.dir), Format::Gradle);
+        step.args.extend(targets.iter().map(|t| t.task.clone()));
+        step.env = g.env.clone();
+        let plan = BuildPlan { system: BuildSystem::Gradle, title: "Process resources".into(), steps: vec![step] };
+        let result = run(root, &plan, cancel, &|_| {})?;
+        if !result.success {
+            let errors: Vec<&str> = result
+                .messages
+                .iter()
+                .filter(|m| m.severity == Severity::Error)
+                .take(5)
+                .map(|m| m.text.as_str())
+                .collect();
+            return Err(IdeError::internal(errors.join("\n")));
+        }
+        for t in targets {
+            if cancel.is_cancelled() {
+                return Err(IdeError::cancelled());
+            }
+            overlay(&t.output, &t.output, &t.jdtls)?;
+            done.push(t.jdtls);
+            tasks.push(t.task);
+        }
+    }
+    Ok(tasks)
+}
+
+/// Copies the files under `dir` to the same place under `to` (relative to `base`) where
+/// they differ, so unchanged resources are not rewritten on every launch.
+fn overlay(base: &Path, dir: &Path, to: &Path) -> IdeResult<()> {
+    let entries = match fs::read_dir(dir) {
+        // No resources: the task had nothing to copy.
+        Err(e) if e.kind() == std::io::ErrorKind::NotFound => return Ok(()),
+        entries => entries?,
+    };
+    for entry in entries {
+        let entry = entry?;
+        let path = entry.path();
+        let kind = entry.file_type()?;
+        if kind.is_dir() {
+            overlay(base, &path, to)?;
+        } else if kind.is_file() {
+            let dest = to.join(path.strip_prefix(base).map_err(|e| IdeError::internal(e.to_string()))?);
+            if !same_content(&path, &dest) {
+                if let Some(parent) = dest.parent() {
+                    fs::create_dir_all(parent)?;
+                }
+                fs::copy(&path, &dest)?;
+            }
+        }
+    }
+    Ok(())
+}
+
+fn same_content(a: &Path, b: &Path) -> bool {
+    match (fs::metadata(a), fs::metadata(b)) {
+        (Ok(m), Ok(n)) if m.len() == n.len() => matches!((fs::read(a), fs::read(b)), (Ok(x), Ok(y)) if x == y),
+        _ => false,
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::gradle::{ProcessedResources, ReportedSourceSet};
+
+    fn write(path: &Path, text: &str) {
+        fs::create_dir_all(path.parent().unwrap()).unwrap();
+        fs::write(path, text).unwrap();
+    }
+
+    fn set(name: &str, processed: Option<&Path>) -> ReportedSourceSet {
+        ReportedSourceSet {
+            name: name.into(),
+            test: name == "test",
+            processed: processed.map(|dir| ProcessedResources {
+                task: if name == "main" { "processResources".into() } else { "processTestResources".into() },
+                dir: dir.to_string_lossy().into_owned(),
+            }),
+            ..Default::default()
+        }
+    }
+
+    fn project(path: &str, dir: &Path, sets: Vec<ReportedSourceSet>) -> ReportedProject {
+        ReportedProject {
+            path: path.into(),
+            dir: dir.to_string_lossy().into_owned(),
+            source_sets: sets,
+            ..Default::default()
+        }
+    }
+
+    /// Only processed source sets whose jdtls output is on the classpath: the launched
+    /// module, upstream modules of the build, tests only for a test classpath; never buildSrc.
+    #[test]
+    fn targets_are_processed_sets_on_the_classpath() {
+        let tmp = tempfile::tempdir().unwrap();
+        let root = dunce::canonicalize(tmp.path()).unwrap();
+        let (app, lib, plain, src) = (root.join("app"), root.join("lib"), root.join("plain"), root.join("buildSrc"));
+        for dir in [&root, &app, &lib, &plain, &src] {
+            for set in ["main", "test"] {
+                fs::create_dir_all(dir.join("bin").join(set)).unwrap();
+            }
+        }
+        let out = |dir: &Path, set: &str| dir.join("build/resources").join(set);
+        let mut build_src = project(":buildSrc", &src, vec![set("main", Some(&out(&src, "main")))]);
+        build_src.build = Some(":buildSrc".into());
+        let reported = [
+            project(":", &root, vec![set("main", Some(&out(&root, "main")))]),
+            project(":app", &app, vec![set("main", Some(&out(&app, "main"))), set("test", Some(&out(&app, "test")))]),
+            project(":lib", &lib, vec![set("main", Some(&out(&lib, "main")))]),
+            project(":plain", &plain, vec![set("main", None)]),
+            build_src,
+        ];
+        let entry = |dir: &Path, set: &str| dir.join("bin").join(set).to_string_lossy().into_owned();
+        let runtime = [
+            entry(&app, "main"),
+            // Spelled differently from Gradle's canonical folders.
+            format!("{}/", entry(&lib, "main")),
+            entry(&plain, "main"),
+            entry(&src, "main"),
+            "/m2/spring-core.jar".into(),
+        ];
+        let tasks = |cp: &[String]| targets(&reported, cp).into_iter().map(|t| t.task).collect::<Vec<_>>();
+        assert_eq!(tasks(&runtime), [":app:processResources", ":lib:processResources"]);
+        let mut test = runtime.to_vec();
+        test.insert(0, entry(&app, "test"));
+        assert_eq!(tasks(&test), [":app:processResources", ":app:processTestResources", ":lib:processResources"]);
+        assert_eq!(tasks(&[entry(&root, "main")]), [":processResources"], "the root project");
+        let app_targets = targets(&reported, &runtime);
+        let t = &app_targets[0];
+        assert_eq!(
+            (t.output.as_path(), t.jdtls.as_path()),
+            (out(&app, "main").as_path(), app.join("bin/main").as_path())
+        );
+
+        let unprocessed = [project(":app", &app, vec![set("main", None)])];
+        assert!(targets(&unprocessed, &runtime).is_empty());
+    }
+
+    /// The processed copy replaces jdtls's plain one (the reported `@version@` case), new
+    /// files are added, identical ones are left alone and files Gradle doesn't produce stay.
+    #[test]
+    fn overlay_replaces_plain_copies_with_gradle_output() {
+        let tmp = tempfile::tempdir().unwrap();
+        let (output, jdtls) = (tmp.path().join("build/resources/main"), tmp.path().join("bin/main"));
+        write(&output.join("application.yaml"), "spring:\n  application:\n    version: 0.0.1\n");
+        write(&output.join("static/extra.txt"), "from an extra source");
+        write(&output.join("migrations/V1__init.sql"), "create table t (id int);");
+        write(&jdtls.join("application.yaml"), "spring:\n  application:\n    version: @version@\n");
+        write(&jdtls.join("migrations/V1__init.sql"), "create table t (id int);");
+        write(&jdtls.join("com/example/App.class"), "bytecode");
+        let unchanged = fs::metadata(jdtls.join("migrations/V1__init.sql")).unwrap().modified().unwrap();
+        std::thread::sleep(std::time::Duration::from_millis(20));
+
+        overlay(&output, &output, &jdtls).unwrap();
+        let read = |rel: &str| fs::read_to_string(jdtls.join(rel)).unwrap();
+        assert_eq!(read("application.yaml"), "spring:\n  application:\n    version: 0.0.1\n");
+        assert_eq!(read("static/extra.txt"), "from an extra source");
+        assert_eq!(read("com/example/App.class"), "bytecode");
+        let modified = fs::metadata(jdtls.join("migrations/V1__init.sql")).unwrap().modified().unwrap();
+        assert_eq!(modified, unchanged, "identical files are not rewritten");
+
+        overlay(&tmp.path().join("missing"), &tmp.path().join("missing"), &jdtls).unwrap();
+    }
+
+    #[test]
+    fn builds_without_processed_resources_run_nothing() {
+        let tmp = tempfile::tempdir().unwrap();
+        // Running this command would fail the call.
+        let missing = tmp.path().join("missing-gradle").to_string_lossy().into_owned();
+        let model =
+            BuildModel { gradle: vec![GradleModel { command: missing, ..Default::default() }], ..Default::default() };
+        let class_paths = [tmp.path().join("bin/main").to_string_lossy().into_owned()];
+        let tasks =
+            process_launch_resources(tmp.path(), &model, tmp.path(), &class_paths, &CancellationToken::new()).unwrap();
+        assert!(tasks.is_empty());
+    }
+}
@@ -4,11 +4,13 @@
 //! for the Build tool window, the Problems view and the editor.

 mod fingerprint;
+mod launch_resources;
 mod parse;
 mod single;
 mod up_to_date;

 pub use fingerprint::{LaunchFingerprint, launch_fingerprint, menu_fingerprint};
+pub use launch_resources::process_launch_resources;
 pub use single::{
    SingleFileTarget, compile_file_plan, find_javac, javac_step, single_file_classpath, single_file_target,
 };
@@ -264,6 +266,11 @@ pub(super) fn maven_steps(
        BuildKind::Rebuild => &["clean", "test-compile"],
        BuildKind::Artifacts => &["package", "-DskipTests"],
    };
+    // The IDE's compile builds are not coverage runs. JaCoCo's offline `instrument`
+    // rewrites target/classes in `process-classes`; `jacoco.skip` prevents that in this
+    // build. It does not restore classes instrumented by an earlier build: Rebuild's
+    // `clean` removes those, while an incremental Build can still reuse them.
+    let skip_jacoco = matches!(kind, BuildKind::Build | BuildKind::Rebuild);
    let tops: Vec<&maven::MavenProject> = m.projects.iter().filter(|p| !p.aggregated).collect();
    if tops.is_empty() {
        return Err(IdeError::not_found("no Maven project found"));
@@ -276,6 +283,9 @@ pub(super) fn maven_steps(
            Format::Maven,
        );
        s.args.extend(p.options.iter().cloned());
+        if skip_jacoco {
+            s.args.push("-Djacoco.skip=true".into());
+        }
        s.args.extend(extra.iter().cloned());
        s.args.extend(goals.iter().map(|g| (*g).to_owned()));
        s.env = p.env.clone();
@@ -1039,6 +1049,22 @@ mod tests {
        std::fs::write(p, text).unwrap();
    }

+    #[test]
+    fn maven_compile_steps_skip_jacoco_but_artifacts_do_not() {
+        let tmp = tempfile::tempdir().unwrap();
+        let root = tmp.path().join("demo");
+        write(&root, "pom.xml", "<project><artifactId>demo</artifactId></project>");
+        let model = crate::load(&root, &tmp.path().join("cache"), None);
+        for (kind, expected) in [(BuildKind::Build, true), (BuildKind::Rebuild, true), (BuildKind::Artifacts, false)] {
+            let plan = plan(&root, &model, kind, None, None).unwrap();
+            assert_eq!(
+                plan.steps[0].args.iter().any(|arg| arg == "-Djacoco.skip=true"),
+                expected,
+                "{kind:?}: {plan:?}"
+            );
+        }
+    }
+
    #[test]
    fn plans_per_build_system() {
        let tmp = tempfile::tempdir().unwrap();
@@ -1055,7 +1081,10 @@ mod tests {
        assert_eq!(p.system, BuildSystem::Maven);
        assert_eq!(p.title, "demo");
        assert_eq!(p.steps.len(), 1);
-        assert_eq!(p.steps[0].args, ["-B", "-Dstyle.color=never", maven::LOCAL_REPO_TRACKING_ARG, "test-compile"]);
+        assert_eq!(
+            p.steps[0].args,
+            ["-B", "-Dstyle.color=never", maven::LOCAL_REPO_TRACKING_ARG, "-Djacoco.skip=true", "test-compile"]
+        );
        let p = plan(&root, &model, BuildKind::Rebuild, Some(&root.join("core/src/main/java/A.java")), None).unwrap();
        assert_eq!(
            p.steps[0].args,
@@ -1063,6 +1092,7 @@ mod tests {
                "-B",
                "-Dstyle.color=never",
                maven::LOCAL_REPO_TRACKING_ARG,
+                "-Djacoco.skip=true",
                "-pl",
                "core",
                "-am",
@@ -1351,6 +1381,7 @@ mod tests {
                    maven::LOCAL_REPO_TRACKING_ARG,
                    "-s",
                    "settings.xml",
+                    "-Djacoco.skip=true",
                    "-pl",
                    "app",
                    "-am",
@@ -1367,6 +1398,7 @@ mod tests {
                    maven::LOCAL_REPO_TRACKING_ARG,
                    "-s",
                    "settings.xml",
+                    "-Djacoco.skip=true",
                    "-pl",
                    "app",
                    "-am",
@@ -79,6 +79,14 @@ pub fn find_javac(env: &BTreeMap<String, String>) -> String {
 /// so `-am` stays cheap). Entries are platform-separated (`;` on Windows).
 pub fn single_file_classpath(root: &Path, model: &BuildModel, target: &SingleFileTarget) -> IdeResult<String> {
    let mut entries: Vec<String> = Vec::new();
+    // The module's own classes first: the file almost always uses classes next to it.
+    let own: &[&str] = if target.test { &["target/test-classes", "target/classes"] } else { &["target/classes"] };
+    for out in own {
+        let path = target.module.join(out);
+        if path.is_dir() {
+            entries.push(path.to_string_lossy().into_owned());
+        }
+    }
    if let Some(m) = &model.maven {
        // Upstream reactor modules first: their freshly built classes shadow
        // installed snapshots of the same artifacts.
@@ -139,6 +147,16 @@ pub fn javac_step(target: &SingleFileTarget, file: &Path, classpath: &str, javac
    step.args.push(target.out_dir.to_string_lossy().into_owned());
    step.args.push("-cp".into());
    step.args.push(classpath.to_owned());
+    // Classes of the module that were never built (or are older than their source) are read
+    // from its sources; only `file` is written, so a test compile never puts main classes
+    // into test-classes.
+    let sources = source_roots(target);
+    if !sources.is_empty() {
+        let separator = if cfg!(windows) { ";" } else { ":" };
+        step.args.push("-sourcepath".into());
+        step.args.push(sources.iter().map(|p| p.to_string_lossy()).collect::<Vec<_>>().join(separator));
+        step.args.push("-implicit:none".into());
+    }
    if let Some(version) = target.java_version {
        step.args.push("--release".into());
        step.args.push(version.to_string());
@@ -148,6 +166,27 @@ pub fn javac_step(target: &SingleFileTarget, file: &Path, classpath: &str, javac
    Ok(step)
 }

+/// The module's Java source folders that exist, generated ones included; test sources see
+/// the main ones too.
+fn source_roots(target: &SingleFileTarget) -> Vec<PathBuf> {
+    let scopes: &[(&str, &str)] = if target.test {
+        &[("src/test/java", "target/generated-test-sources"), ("src/main/java", "target/generated-sources")]
+    } else {
+        &[("src/main/java", "target/generated-sources")]
+    };
+    let mut roots = Vec::new();
+    for (src, generated) in scopes {
+        roots.push(target.module.join(src));
+        let generated = target.module.join(generated);
+        let mut dirs: Vec<PathBuf> =
+            fs::read_dir(&generated).into_iter().flatten().flatten().map(|d| d.path()).filter(|p| p.is_dir()).collect();
+        dirs.sort();
+        roots.extend(dirs);
+    }
+    roots.retain(|p| p.is_dir());
+    roots
+}
+
 /// Resolves the classpath and plans the `javac` invocation for one Java source.
 pub fn compile_file_plan(root: &Path, model: &BuildModel, file: &Path) -> IdeResult<BuildPlan> {
    let target = single_file_target(root, model, file)?;
@@ -243,6 +282,11 @@ mod tests {
        assert!(args.contains("-d ") && args.contains("test-classes"), "{args}");
        assert!(args.contains("-cp /repo/a.jar"), "{args}");
        assert!(args.contains("MainTest.java"), "{args}");
+        // Test sources resolve their own and the main sources, without writing them.
+        let sourcepath = step.args.iter().position(|a| a == "-sourcepath").map(|i| step.args[i + 1].clone());
+        let roots = sourcepath.expect("a -sourcepath");
+        assert!(roots.contains("src/test/java") && roots.contains("src/main/java"), "{roots}");
+        assert!(step.args.iter().any(|a| a == "-implicit:none"), "{args}");
        // No `JAVA_HOME`: plain `javac` from `PATH`.
        assert_eq!(find_javac(&BTreeMap::new()), exe);
    }
@@ -275,6 +319,11 @@ mod tests {
        // Reactor class directories first, so fresh outputs shadow installed snapshots.
        let lib = root.join("lib/target/classes").to_string_lossy().into_owned();
        assert!(cp.starts_with(&lib), "{cp}");
+        // The module's own classes come first once they exist.
+        fs::create_dir_all(root.join("app/target/classes")).unwrap();
+        let cp = single_file_classpath(root, &model, &target).unwrap();
+        let own = root.join("app/target/classes").to_string_lossy().into_owned();
+        assert!(cp.starts_with(&format!("{own}:{lib}")), "{cp}");
        assert!(cp.contains("/repo/a.jar"), "{cp}");
        assert!(cp.contains("/repo/b.jar"), "{cp}");
        assert!(cp.split(separator).count() >= 3, "{cp}");
@@ -14,6 +14,20 @@ use std::fs;
 #[derive(serde::Serialize, serde::Deserialize)]
 struct Record {
    fingerprint: LaunchFingerprint,
+    /// Output folders of the built projects that existed after the build, relative to the
+    /// project. Deleting one outside the IDE (`mvn clean` in a terminal) leaves every input
+    /// unchanged, so a build is skipped only while they are all still there.
+    #[serde(default)]
+    outputs: Vec<PathBuf>,
+}
+
+/// The build's output folders that exist now, relative to `root`.
+fn existing_outputs(root: &Path, fingerprint: &LaunchFingerprint) -> Vec<PathBuf> {
+    fingerprint
+        .project_dirs()
+        .flat_map(|dir| ["target/classes", "target/test-classes"].map(|out| dir.join(out)))
+        .filter(|rel| root.join(rel).is_dir())
+        .collect()
 }

 fn record_path(cache: &Path, root: &Path, file: Option<&Path>) -> PathBuf {
@@ -69,7 +83,7 @@ pub fn menu_up_to_date(
        restamp(root, &record.fingerprint.mtime_preserved_edits(&current));
        return false;
    }
-    true
+    record.outputs.iter().all(|out| root.join(out).is_dir())
 }

 /// Records a successful menu build as the baseline for future up-to-date
@@ -91,7 +105,8 @@ pub fn record_menu_build(
    if path.parent().is_some_and(|p| fs::create_dir_all(p).is_err()) {
        return;
    }
-    let bytes = match serde_json::to_vec(&Record { fingerprint: current }) {
+    let outputs = existing_outputs(root, &current);
+    let bytes = match serde_json::to_vec(&Record { fingerprint: current, outputs }) {
        Ok(bytes) => bytes,
        _ => return,
    };
@@ -151,6 +166,25 @@ mod tests {
        assert!(menu_up_to_date(&cache, root, &model, None, &cancel));
    }

+    #[test]
+    fn deleted_outputs_invalidate_the_record() {
+        let dir = tempfile::tempdir().unwrap();
+        let root = dir.path();
+        let model = fixture(root);
+        let cache = root.join("cache");
+        let cancel = CancellationToken::new();
+        for out in ["app/target/classes/t", "lib/target/classes/t", "app/target/test-classes"] {
+            fs::create_dir_all(root.join(out)).unwrap();
+        }
+        record_menu_build(&cache, root, &model, None, &cancel);
+        assert!(menu_up_to_date(&cache, root, &model, None, &cancel));
+        // `mvn clean` outside the IDE: no input changed, but the classes are gone.
+        fs::remove_dir_all(root.join("lib/target")).unwrap();
+        assert!(!menu_up_to_date(&cache, root, &model, None, &cancel));
+        fs::create_dir_all(root.join("lib/target/classes")).unwrap();
+        assert!(menu_up_to_date(&cache, root, &model, None, &cancel));
+    }
+
    #[test]
    fn edit_invalidates_and_rerecord_restores_skip() {
        let dir = tempfile::tempdir().unwrap();
@@ -8,6 +8,24 @@ def canon = { File f -> f.canonicalPath }
 // the identity path (`:lib:core`, `:buildSrc`) tells them apart and addresses their tasks
 // from the root build. Internal API, hence the fallback.
 def identity = { Project p -> try { p.identityPath.toString() } catch (ignored) { p.path } }
+// The task copying a source set's resources and its output folder, when it changes them on the
+// way (filters, `expand`, renames, includes / excludes, extra sources): jdtls copies resources as
+// they are, so launches take them from Gradle. Internal API, hence the fallback.
+def processedResources = { Project p, s ->
+    try {
+        def task = p.tasks.findByName(s.processResourcesTaskName)
+        if (task == null) return null
+        def specs = 0
+        def changes = task.mainSpec.sourcePaths.size() > 1
+        task.rootSpec.buildRootResolver().walk { r ->
+            specs++
+            changes |= !r.allCopyActions.isEmpty() || !r.allIncludes.isEmpty() || !r.allExcludes.isEmpty() ||
+                !r.allIncludeSpecs.isEmpty() || !r.allExcludeSpecs.isEmpty() || r.destPath.segments.length > 0
+        }
+        // The root and main specs exist for every task; more come from `from(…) { … }`.
+        (changes || specs > 2) ? [task: task.name, dir: canon(task.destinationDir)] : null
+    } catch (ignored) { null }
+}

 def describe = { Project p ->
    def m = [path: identity(p), dir: canon(p.projectDir), buildDir: canon(p.layout.buildDirectory.get().asFile)]
@@ -26,7 +44,10 @@ def describe = { Project p ->
            def test = s.name == 'test' || s.name == 'testFixtures' || suites.contains(s.name) ||
                s.name.endsWith('Test') || s.name.endsWith('Tests') ||
                (!src.isEmpty() && src.every { ideaTests.contains(it) })
-            [name: s.name, test: test, src: src, res: res]
+            def set = [name: s.name, test: test, src: src, res: res]
+            def processed = processedResources(p, s)
+            if (processed != null) set.processed = processed
+            set
        }
    }
    try {
@@ -335,6 +335,19 @@ pub struct ReportedSourceSet {
    /// Absolute resource folders.
    #[serde(default)]
    pub res: Vec<String>,
+    /// Set when Gradle changes the resources while copying them (filters, `expand`, renames,
+    /// includes / excludes, extra sources), which the Java language server's copy does not.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub processed: Option<ProcessedResources>,
+}
+
+/// The task that copies a source set's resources, and where it writes them.
+#[derive(Clone, Debug, Default, PartialEq, Eq, Serialize, Deserialize)]
+pub struct ProcessedResources {
+    /// Task name in its project (`processResources`).
+    pub task: String,
+    /// Absolute output folder.
+    pub dir: String,
 }

 const MODEL_LINE: &str = "@openidea-model\t";
@@ -536,6 +536,7 @@ mod tests {
                        crate::maven::LOCAL_REPO_TRACKING_ARG,
                        "-o",
                        "-Peditor",
+                        "-Djacoco.skip=true",
                        "test-compile"
                    ]
                );
@@ -73,6 +73,9 @@ struct GradleCache {
    /// The projects as Gradle evaluated them; empty in caches from before they were read.
    #[serde(default)]
    projects: Vec<ReportedProject>,
+    /// The projects report how their resources are processed; older caches are stale.
+    #[serde(default)]
+    resources: bool,
 }

 /// Init script printing every project, its source sets and Java version once configured.
@@ -244,11 +247,12 @@ pub fn apply_gradle_cache(root: &Path, cache_dir: &Path, model: &mut GradleModel
            }
        }
    }
-    // A successful sync from before projects were cached has not seen computed includes.
-    let without_projects = cache.error.is_none() && cache.projects.is_empty();
+    // A successful sync from before projects were cached has not seen computed includes,
+    // nor, before resources were read, which launches need Gradle to process them.
+    let outdated = cache.error.is_none() && (cache.projects.is_empty() || !cache.resources);
    model.synced_at = Some(cache.at_ms);
    model.sync_error = cache.error;
-    model.stale = without_projects || cache.hash != hash_gradle_files(&gradle::build_files(root, model));
+    model.stale = outdated || cache.hash != hash_gradle_files(&gradle::build_files(root, model));
 }

 // ---------------------------------------------------------------- processes
@@ -462,6 +466,7 @@ pub fn sync_gradle_model(
        error: (!out.success).then(|| error_summary(&out.text)),
        tasks: if out.success { gradle::parse_tasks(&out.text) } else { Vec::new() },
        projects,
+        resources: true,
    };
    write_cache(&cache_dir, GRADLE_CACHE, &cache)
 }
@@ -713,6 +718,7 @@ mod tests {
            test,
            src: src.iter().map(|p| core_src(p)).collect(),
            res: res.iter().map(|p| core_src(p)).collect(),
+            processed: None,
        };
        // A settings script's own println comes first; task listing lines follow.
        let out = format!(
@@ -737,6 +743,15 @@ mod tests {
        );
        let projects = parse_reported_projects(&out);
        assert_eq!(projects.len(), 3, "the malformed line is skipped");
+        // As the init script prints a set whose resources Gradle filters or renames.
+        let processed = parse_reported_projects(&format!(
+            "@openidea-model\t{}",
+            r#"{"path":":","dir":"/p","sourceSets":[{"name":"main","test":false,"src":[],"res":[],"processed":{"task":"processResources","dir":"/p/build/resources/main"}}]}"#
+        ));
+        assert_eq!(
+            processed[0].source_sets[0].processed,
+            Some(gradle::ProcessedResources { task: "processResources".into(), dir: "/p/build/resources/main".into() })
+        );
        let src = |p: &str| PathBuf::from(core_src(p));
        assert_eq!(
            gradle::reported_source_roots(&projects),
@@ -802,12 +817,18 @@ mod tests {
                    ..Default::default()
                })
                .collect(),
+            resources: true,
        };
        write_cache(&cache_dir, GRADLE_CACHE, &cache).unwrap();
        apply_gradle_cache(&root, &cache_dir, &mut model);
        assert_eq!(model.projects[1].tasks.len(), 1);
        assert!(model.projects[0].tasks.iter().any(|t| t.name == "wrapper"), "root keeps its defaults");
        assert!(!model.stale);
+        write_cache(&cache_dir, GRADLE_CACHE, &GradleCache { resources: false, ..cache.clone() }).unwrap();
+        let mut m = gradle::load(&root).unwrap();
+        apply_gradle_cache(&root, &cache_dir, &mut m);
+        assert!(m.stale, "synced before resource processing was read");
+        write_cache(&cache_dir, GRADLE_CACHE, &cache).unwrap();

        let stale_after = |script: &str| {
            std::fs::write(root.join("app/build.gradle"), script).unwrap();
@@ -841,6 +862,7 @@ mod tests {
                dir: root.to_string_lossy().into_owned(),
                ..Default::default()
            }],
+            resources: true,
            ..Default::default()
        };
        write_cache(&cache_dir, GRADLE_CACHE, &cache).unwrap();
@@ -333,6 +333,23 @@ pub struct InlayHintsSettings {
    pub code_vision_usages: bool,
    /// Code vision: last author of a declaration (VCS blame) beside its usages.
    pub code_vision_author: bool,
+    /// Code vision: "no usages" on declarations nothing uses (IDEA shows it; clicking searches everywhere).
+    pub code_vision_no_usages: bool,
+    /// Code vision: where the usages go, above the declaration or at the end of its line.
+    pub code_vision_usages_position: CodeVisionPosition,
+    /// Code vision: where the author goes, above the declaration or at the end of its line.
+    pub code_vision_author_position: CodeVisionPosition,
+}
+
+/// Editor › Inlay Hints › Code Vision position (IDEA's "Default position for metrics").
+#[derive(Clone, Copy, Debug, Default, PartialEq, Serialize, Deserialize, Type)]
+#[serde(rename_all = "camelCase")]
+pub enum CodeVisionPosition {
+    /// A row of its own above the declaration.
+    #[default]
+    Top,
+    /// After the end of the declaration's first line.
+    Right,
 }

 impl Default for InlayHintsSettings {
@@ -344,6 +361,9 @@ impl Default for InlayHintsSettings {
            disabled_languages: Vec::new(),
            code_vision_usages: true,
            code_vision_author: true,
+            code_vision_no_usages: true,
+            code_vision_usages_position: CodeVisionPosition::Top,
+            code_vision_author_position: CodeVisionPosition::Top,
        }
    }
 }
@@ -275,6 +275,11 @@ pub enum DebugEvent {
    },
    /// The session's capabilities changed after it started: fetch them again.
    Capabilities,
+    /// The adapter's `invalidated` event: what it shows for `areas` (`all`, `stacks`, `threads`,
+    /// `variables`; empty means all) is stale and has to be fetched again.
+    Invalidated {
+        areas: Vec<String>,
+    },
    JvmBackend {
        state: JvmBackendState,
    },
@@ -330,4 +335,12 @@ mod tests {
        );
        assert_eq!(serde_json::to_value(DebugEvent::Capabilities).unwrap(), json!({"kind": "capabilities"}));
    }
+
+    #[test]
+    fn invalidated_event_json_shape() {
+        assert_eq!(
+            serde_json::to_value(DebugEvent::Invalidated { areas: vec!["variables".into()] }).unwrap(),
+            json!({"kind": "invalidated", "areas": ["variables"]})
+        );
+    }
 }
@@ -63,6 +63,8 @@ pub struct Settings {
    pub agents: AgentSettings,
    /// Agents › MCP Server (global only).
    pub mcp_server: McpServerSettings,
+    /// Tools › Agents: Command Execution Policy.
+    pub agent_security: AgentSecuritySettings,
    /// Plugin settings (`[contributes.settings]`): plugin id → its values by key.
    #[specta(type = BTreeMap<String, BTreeMap<String, specta_typescript::Unknown>>)]
    pub plugins: BTreeMap<String, serde_json::Map<String, serde_json::Value>>,
@@ -261,6 +263,9 @@ pub enum WhileRunning {
 pub struct McpServerSettings {
    /// Serve the tools on 127.0.0.1 while the IDE runs.
    pub enabled: bool,
+    /// Run the tools that change the project or start processes without asking first
+    /// (IDEA's brave mode). Read from the IDE's own settings only, never a project's.
+    pub run_without_confirmation: bool,
 }

 /// Absent profiles retain automatic discovery for existing projects.
@@ -408,6 +413,7 @@ impl Default for Settings {
            cmake: CMakeSettings::default(),
            agents: AgentSettings::default(),
            mcp_server: McpServerSettings::default(),
+            agent_security: AgentSecuritySettings::default(),
            plugins: BTreeMap::new(),
        }
    }
@@ -580,12 +586,10 @@ pub struct AppearanceSettings {
    pub project_colors_in_toolbar: bool,
    pub dnd_with_alt_only: bool,
    pub menu_icons: bool,
-    /// `hamburger` | `merged`: main menu presentation in the frameless title bar.
+    /// `hamburger` | `merged` | `toolbar` (a separate row): main menu presentation in the frameless title bar.
    pub main_menu_style: String,
    /// A lone Alt press focuses or opens the main menu (IDEA `ide.windows.main.menu.focus.on.alt`).
    pub main_menu_alt: bool,
-    /// Always show the main menu titles instead of the hamburger button (#1521).
-    pub always_show_main_menu: bool,
    /// `subpixel` | `greyscale` | `none`
    pub ide_antialiasing: String,
    pub editor_antialiasing: String,
@@ -663,7 +667,6 @@ impl Default for AppearanceSettings {
            menu_icons: true,
            main_menu_style: "hamburger".into(),
            main_menu_alt: true,
-            always_show_main_menu: false,
            ide_antialiasing: "greyscale".into(),
            editor_antialiasing: "greyscale".into(),
            show_tool_window_bars: true,
@@ -1579,11 +1582,6 @@ mod tests {
        let off: Settings = serde_json::from_str(r#"{"appearance":{"mainMenuAlt":false}}"#).unwrap();
        assert!(!off.appearance.main_menu_alt);
        assert_eq!(serde_json::to_value(off).unwrap()["appearance"]["mainMenuAlt"], false);
-        let old: Settings = serde_json::from_str(r#"{"appearance":{"compactMode":true}}"#).unwrap();
-        assert!(!old.appearance.always_show_main_menu);
-        let shown: Settings = serde_json::from_str(r#"{"appearance":{"alwaysShowMainMenu":true}}"#).unwrap();
-        assert!(shown.appearance.always_show_main_menu);
-        assert_eq!(serde_json::to_value(shown).unwrap()["appearance"]["alwaysShowMainMenu"], true);
    }

    #[test]
@@ -412,3 +412,30 @@ impl Default for ExternalTool {
        }
    }
 }
+
+/// Tools › Agents: Command Execution Policy (whitelist and blacklist patterns).
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
+#[serde(default, rename_all = "camelCase")]
+pub struct AgentSecuritySettings {
+    /// Commands or patterns (`git status*`, `pwd`) automatically approved without prompting.
+    pub allowed_commands: Vec<String>,
+    /// Commands or patterns (`rm -rf *`, `mkfs*`) automatically rejected.
+    pub blocked_commands: Vec<String>,
+}
+
+impl Default for AgentSecuritySettings {
+    fn default() -> Self {
+        Self {
+            allowed_commands: Vec::new(),
+            blocked_commands: vec![
+                "rm -rf *".into(),
+                "rm -rf /".into(),
+                "mkfs*".into(),
+                "dd *".into(),
+                ":(){ :|:& };:".into(),
+                "shutdown*".into(),
+                "reboot*".into(),
+            ],
+        }
+    }
+}
@@ -14,6 +14,7 @@ ide-jsonrpc.workspace = true
 ide-jvm-attach.workspace = true
 ide-jvm-inspect.workspace = true
 ide-jdwp.workspace = true
+ide-heap.workspace = true
 serde.workspace = true
 serde_json.workspace = true
 specta.workspace = true
@@ -72,6 +72,13 @@ fn builtin(adapter: &str) -> Option<DebuggerConfig> {
            "stdio",
            "Install Kotlin Debug Adapter in Settings › Languages & Frameworks › Language Servers",
        ),
+        // Inside the language server: reached through `debugServer`, never started.
+        "kotlin-lsp" => cfg(
+            "kotlin-lsp",
+            &[],
+            "tcp",
+            "Install JetBrains Kotlin LSP in Settings › Languages & Frameworks › Language Servers",
+        ),
        // Windows installs `python.exe`; `python3.exe` there is at most a Store alias.
        "debugpy" => cfg(
            if cfg!(windows) { "python" } else { "python3" },
@@ -342,4 +342,16 @@ mod tests {
        assert_eq!(error_message(&msg), "cannot find a.py");
        assert_eq!(error_message(&json!({"message": "nope"})), "nope");
    }
+
+    #[test]
+    fn a_failed_launch_response_keeps_delves_too_old_error_verbatim() {
+        // The UI's repair offer keys off this exact wording (`missingAdapter`), so the
+        // conversion to the IPC error must not fold it into a generic message.
+        let message = "Failed to launch /p/api: Version of Delve is too old for Go version go1.27.0 \
+                       (maximum supported version 1.26, suppress this error with --check-go-version=false)";
+        let e = ide_core::IdeError::from(DapError::Failed { command: "launch".into(), message: message.into() });
+        assert_eq!(e.kind, ide_core::error::ErrorKind::InvalidInput);
+        assert_eq!(e.message, format!("launch failed: {message}"));
+        assert!(e.message.contains("Version of Delve is too old for Go version go1.27.0"));
+    }
 }
@@ -0,0 +1,293 @@
+//! A heap dump of a debugged JVM, written over its attach listener into a snapshot directory.
+
+use super::snapshot::{AttachProbe, JdkProbe, attach_failure, gone, pick_jvm_pid};
+use super::{
+    JvmMemoryState, JvmMemoryUnavailable, JvmTarget, histogram_pid, keep_found, lookup, resolve_jvm,
+    safe_while_suspended, session_target,
+};
+use crate::session::Session;
+use ide_core::{CancellationToken, IdeError, IdeResult};
+use ide_jvm_attach::{AttachError, HeapDumpReply};
+use serde::{Deserialize, Serialize};
+use specta::Type;
+use std::future::Future;
+use std::path::{Path, PathBuf};
+use std::sync::Arc;
+
+const DUMP_FILE: &str = "dump.hprof";
+/// For a refusal whose reply holds no reason: empty, or only the line announcing the dump.
+const NO_REASON: &str = "the JVM wrote no heap dump and gave no reason";
+
+#[derive(Clone, Debug, PartialEq, Serialize, Deserialize, Type)]
+#[serde(tag = "kind", rename_all = "camelCase", rename_all_fields = "camelCase")]
+pub enum JvmHeapUnavailable {
+    /// The reason a class table could not be read applies to the dump too.
+    Memory {
+        reason: JvmMemoryUnavailable,
+    },
+    /// Bytes.
+    NotEnoughDiskSpace {
+        needed: u64,
+        available: u64,
+    },
+    DumpFailed {
+        message: String,
+    },
+    DumpTimedOut {
+        seconds: u32,
+    },
+}
+
+#[derive(Clone, Debug, PartialEq)]
+pub struct JvmHeapDump {
+    pub path: PathBuf,
+    /// The class histogram taken just before the dump.
+    pub histogram: Vec<ide_heap::HistogramEntry>,
+    /// Raw `VM.flags`; empty when the JVM did not answer.
+    pub vm_flags: String,
+    /// 0 when unknown.
+    pub java_major: u32,
+    /// Empty when unknown.
+    pub java_version: String,
+    pub pid: u32,
+    pub taken_while_suspended: bool,
+    pub dump_ms: u32,
+}
+
+#[derive(Clone, Debug, PartialEq)]
+pub enum JvmHeapOutcome {
+    Ready(JvmHeapDump),
+    /// The snapshot directory has been deleted.
+    Unavailable(JvmHeapUnavailable),
+    /// The snapshot directory has been deleted.
+    Cancelled,
+}
+
+pub(crate) async fn session_heap_dump(
+    session: Arc<Session>,
+    dir: PathBuf,
+    cancel: CancellationToken,
+) -> IdeResult<JvmHeapOutcome> {
+    let launched = histogram_pid(&session);
+    let capture = {
+        let (dir, cancel) = (dir.clone(), cancel.clone());
+        async move {
+            let target = session_target(&session, launched);
+            let probe = |suspended| -> Arc<dyn AttachProbe> { Arc::new(JdkProbe { suspended }) };
+            let stopped = session.clone();
+            let suspended = move || capture_suspended(&stopped);
+            heap_dump_with(&session.jvm_memory, suspended, probe, target, dir, cancel).await
+        }
+    };
+    detached(capture, dir, cancel).await
+}
+
+/// The JVM can be suspended before the adapter reports the stop, so a session with a JDWP link
+/// also counts the link's view.
+pub(super) fn capture_suspended(session: &Session) -> bool {
+    session.suspended.get()
+        || session
+            .jdwp_link
+            .lock()
+            .as_ref()
+            .is_some_and(|link| matches!(link.state(), ide_jdwp::LinkState::Suspended { .. }))
+}
+
+/// Runs `capture` in a task of its own, so a caller that stops waiting cannot release the
+/// session's lock while the JVM is still writing the dump and let a class-table request run
+/// next to it. On `cancel` returns at once and deletes `dir`.
+pub(super) async fn detached(
+    capture: impl Future<Output = IdeResult<JvmHeapOutcome>> + Send + 'static,
+    dir: PathBuf,
+    cancel: CancellationToken,
+) -> IdeResult<JvmHeapOutcome> {
+    let task = tokio::spawn(capture);
+    tokio::select! {
+        joined = task => joined.map_err(|e| IdeError::internal(format!("JVM heap dump failed: {e}")))?,
+        () = cancel.cancelled() => {
+            discard_later(dir).await;
+            Ok(JvmHeapOutcome::Cancelled)
+        }
+    }
+}
+
+/// Holds `state`'s lock throughout, as a class-table request does; `suspended` and then `probe`
+/// are read once it is held, and `suspended` again by [`take_heap_dump`]. Anything but `Ready`
+/// deletes `dir`.
+pub(super) async fn heap_dump_with(
+    state: &tokio::sync::Mutex<JvmMemoryState>,
+    suspended: impl Fn() -> bool + Send + Sync + 'static,
+    probe: impl FnOnce(bool) -> Arc<dyn AttachProbe>,
+    target: JvmTarget<'_>,
+    dir: PathBuf,
+    cancel: CancellationToken,
+) -> IdeResult<JvmHeapOutcome> {
+    // The capture's histogram never becomes the Memory view's baseline, so the state is unused.
+    let _turn = state.lock().await;
+    let outcome = capture(suspended, probe, target, dir.clone(), cancel).await;
+    if !matches!(outcome, Ok(JvmHeapOutcome::Ready(_))) {
+        discard_later(dir).await;
+    }
+    outcome
+}
+
+async fn capture(
+    suspended_now: impl Fn() -> bool + Send + Sync + 'static,
+    probe: impl FnOnce(bool) -> Arc<dyn AttachProbe>,
+    target: JvmTarget<'_>,
+    dir: PathBuf,
+    cancel: CancellationToken,
+) -> IdeResult<JvmHeapOutcome> {
+    if cancel.is_cancelled() {
+        return Ok(JvmHeapOutcome::Cancelled);
+    }
+    let suspended = suspended_now();
+    let lookup = match lookup(target) {
+        Ok(lookup) => lookup,
+        Err(reason) => return Ok(memory(reason)),
+    };
+    let probe = probe(suspended);
+    let (found, outcome) = tokio::task::spawn_blocking(move || match resolve_jvm(lookup, &*probe, suspended) {
+        Ok((tree, found)) => (found, take_heap_dump(&*probe, &tree, suspended, &suspended_now, &dir, &cancel)),
+        Err(reason) => (None, Ok(memory(reason))),
+    })
+    .await
+    .map_err(|e| IdeError::internal(format!("JVM heap dump failed: {e}")))?;
+    keep_found(target, found);
+    outcome
+}
+
+/// `tree` starts with the session's reported pid, followed by its descendants. `suspended` is
+/// the stop read when the capture began; `suspended_now` reads it again. Anything but `Ready`
+/// deletes `dir`.
+pub(crate) fn take_heap_dump(
+    probe: &dyn AttachProbe,
+    tree: &[i32],
+    suspended: bool,
+    suspended_now: &dyn Fn() -> bool,
+    dir: &Path,
+    cancel: &CancellationToken,
+) -> IdeResult<JvmHeapOutcome> {
+    let outcome = dump(probe, tree, suspended, suspended_now, dir, cancel);
+    if !matches!(outcome, Ok(JvmHeapOutcome::Ready(_))) {
+        discard(dir);
+    }
+    outcome
+}
+
+fn dump(
+    probe: &dyn AttachProbe,
+    tree: &[i32],
+    suspended: bool,
+    suspended_now: &dyn Fn() -> bool,
+    dir: &Path,
+    cancel: &CancellationToken,
+) -> IdeResult<JvmHeapOutcome> {
+    use JvmHeapUnavailable as H;
+    use JvmMemoryUnavailable as U;
+    let Some(root) = tree.first().and_then(|&p| u32::try_from(p).ok()) else {
+        return Ok(memory(U::NoJvmProcess));
+    };
+    let Some(jvm) = pick_jvm_pid(tree, |p| probe.has_listener(p)) else {
+        return Ok(memory(gone(probe, root)));
+    };
+
+    let version = probe.version(jvm);
+    let java_major = version.as_ref().map_or(0, |v| v.major);
+    let safe = safe_while_suspended(version.as_ref());
+    let unsafe_stop = || Ok(memory(U::UnsafeWhileSuspended { java_major }));
+    if suspended && !safe {
+        return unsafe_stop();
+    }
+    // The program may stop during the histogram, and a stopped JDK below 17 hangs on the next
+    // request until it resumes.
+    let stopped_since = || !safe && suspended_now();
+
+    let text = match probe.histogram(jvm) {
+        Ok(text) => text,
+        Err(e) => return attach_failure(probe, jvm, e, "class histogram").map(memory),
+    };
+    let histogram: Vec<ide_heap::HistogramEntry> = ide_jvm_attach::parse_class_histogram(&text)
+        .rows
+        .into_iter()
+        .map(|r| ide_heap::HistogramEntry { name: r.name, instances: r.instances, bytes: r.bytes })
+        .collect();
+    let (instances, bytes) =
+        histogram.iter().fold((0u64, 0u64), |(i, b), e| (i.saturating_add(e.instances), b.saturating_add(e.bytes)));
+    let needed = ide_heap::capture_need(bytes, instances);
+    if let Some(available) = probe.free_bytes(dir)
+        && available < needed
+    {
+        return Ok(JvmHeapOutcome::Unavailable(H::NotEnoughDiskSpace { needed, available }));
+    }
+
+    if stopped_since() {
+        return unsafe_stop();
+    }
+    // Without flags the index assumes the default object layout.
+    let vm_flags = probe.vm_flags(jvm).unwrap_or_else(|e| {
+        tracing::debug!("VM.flags of JVM {jvm}: {e}");
+        String::new()
+    });
+    if cancel.is_cancelled() {
+        return Ok(JvmHeapOutcome::Cancelled);
+    }
+    if stopped_since() {
+        return unsafe_stop();
+    }
+
+    let path = dir.join(DUMP_FILE);
+    let timeout = ide_jvm_attach::dump_timeout(bytes);
+    let started = std::time::Instant::now();
+    let reply = probe.heap_dump(jvm, &path, timeout);
+    let dump_ms = u32::try_from(started.elapsed().as_millis()).unwrap_or(u32::MAX);
+    if cancel.is_cancelled() {
+        return Ok(JvmHeapOutcome::Cancelled);
+    }
+    let failed = |message: String| Ok(JvmHeapOutcome::Unavailable(H::DumpFailed { message }));
+    match reply {
+        Ok(HeapDumpReply::Created { .. }) => {
+            if !std::fs::metadata(&path).is_ok_and(|m| m.is_file() && m.len() > 0) {
+                return failed(format!("the JVM reported a heap dump, but {} is missing or empty", path.display()));
+            }
+            Ok(JvmHeapOutcome::Ready(JvmHeapDump {
+                path,
+                histogram,
+                vm_flags,
+                java_major,
+                java_version: version.map(|v| v.text).unwrap_or_default(),
+                pid: jvm,
+                taken_while_suspended: suspended,
+                dump_ms,
+            }))
+        }
+        Ok(HeapDumpReply::Refused { message }) if message.is_empty() || message.starts_with("Dumping heap to") => {
+            failed(NO_REASON.into())
+        }
+        Ok(HeapDumpReply::Refused { message }) => failed(message),
+        Err(AttachError::Timeout) => {
+            let seconds = u32::try_from(timeout.as_secs()).unwrap_or(u32::MAX);
+            Ok(JvmHeapOutcome::Unavailable(H::DumpTimedOut { seconds }))
+        }
+        // A running JDK rejects an argument with a non-zero result code.
+        Err(AttachError::Command { message, .. }) => failed(message),
+        Err(e) => attach_failure(probe, jvm, e, "heap dump").map(memory),
+    }
+}
+
+fn memory(reason: JvmMemoryUnavailable) -> JvmHeapOutcome {
+    JvmHeapOutcome::Unavailable(JvmHeapUnavailable::Memory { reason })
+}
+
+fn discard(dir: &Path) {
+    if let Err(e) = std::fs::remove_dir_all(dir)
+        && e.kind() != std::io::ErrorKind::NotFound
+    {
+        tracing::warn!("could not delete heap snapshot directory {}: {e}", dir.display());
+    }
+}
+
+/// A dump may be large, so it is deleted off the async threads.
+async fn discard_later(dir: PathBuf) {
+    let _ = tokio::task::spawn_blocking(move || discard(&dir)).await;
+}
@@ -2,6 +2,7 @@
 //! that is unavailable, counted by the debugger; and the JVM's objects through the debugger.

 mod fallback;
+mod heap;
 mod inspect;
 mod scan;
 mod snapshot;
@@ -20,6 +21,7 @@ use std::sync::Arc;
 use std::sync::atomic::{AtomicI64, Ordering};
 use std::time::Duration;

+pub use heap::*;
 pub use inspect::{JvmFieldsResult, JvmInspectUnavailable, JvmInstancesResult, JvmObjectRef, JvmReferrersResult};
 pub(crate) use inspect::{fields, instances, referrers, set_inspector, watch_link};
 #[cfg(all(test, unix))]
@@ -27,7 +29,7 @@ pub(crate) use scan::watch_for_attached_jvm;
 pub(crate) use scan::{JvmFinder, attach_target, find_attached_jvm, find_local_jvm, local_jdwp_port};
 use snapshot::{AttachProbe, JdkProbe, take_snapshot};

-pub const JVM_MEMORY_ADAPTERS: &[&str] = &["java-debug", crate::kotlin::ADAPTER];
+pub const JVM_MEMORY_ADAPTERS: &[&str] = &["java-debug", crate::kotlin::ADAPTER, crate::kotlin_lsp::ADAPTER];
 pub const HISTOGRAM_TIMEOUT: Duration = Duration::from_secs(10);

 #[derive(Clone, Debug, PartialEq, Serialize, Deserialize, Type)]
@@ -6,14 +6,16 @@ use super::{
    safe_while_suspended,
 };
 use ide_core::IdeResult;
-use ide_jvm_attach::{AttachError, HistogramRow, JavaVersion};
+use ide_jvm_attach::{AttachError, HeapDumpReply, HistogramRow, JavaVersion};
 use std::collections::HashMap;
+use std::path::Path;
 use std::time::Duration;

 /// Version probe for a JVM whose `release` file could not be read.
 const VERSION_TIMEOUT: Duration = Duration::from_secs(2);
+const FLAGS_TIMEOUT: Duration = Duration::from_secs(2);

-/// The attach calls a snapshot makes, so tests can stand in for a JVM.
+/// The attach calls a snapshot or a heap dump makes, so tests can stand in for a JVM.
 pub(crate) trait AttachProbe: Send + Sync {
    fn has_listener(&self, pid: u32) -> bool;
    /// Asks only the JVMs whose pid `may_query` accepts.
@@ -21,6 +23,10 @@ pub(crate) trait AttachProbe: Send + Sync {
    fn version(&self, pid: u32) -> Option<JavaVersion>;
    fn histogram(&self, pid: u32) -> Result<String, AttachError>;
    fn alive(&self, pid: u32) -> bool;
+    fn vm_flags(&self, pid: u32) -> Result<String, AttachError>;
+    fn heap_dump(&self, pid: u32, path: &Path, timeout: Duration) -> Result<HeapDumpReply, AttachError>;
+    /// `None` where the free space is not known.
+    fn free_bytes(&self, dir: &Path) -> Option<u64>;
 }

 pub(super) struct JdkProbe {
@@ -55,6 +61,18 @@ impl AttachProbe for JdkProbe {
    fn alive(&self, pid: u32) -> bool {
        alive(pid)
    }
+
+    fn vm_flags(&self, pid: u32) -> Result<String, AttachError> {
+        ide_jvm_attach::vm_flags(pid, FLAGS_TIMEOUT)
+    }
+
+    fn heap_dump(&self, pid: u32, path: &Path, timeout: Duration) -> Result<HeapDumpReply, AttachError> {
+        ide_jvm_attach::heap_dump(pid, path, timeout)
+    }
+
+    fn free_bytes(&self, dir: &Path) -> Option<u64> {
+        ide_heap::free_bytes(dir)
+    }
 }

 fn alive(pid: u32) -> bool {
@@ -1,10 +1,13 @@
 use super::fallback::{debugger_snapshot, falls_back};
+use super::heap::*;
 use super::scan::*;
 use super::snapshot::*;
 use super::test_support::{BareSession, FakeInspector, bare_session, bare_session_of};
 use super::*;
-use ide_jvm_attach::{AttachError, HistogramRow, JavaVersion};
+use ide_core::CancellationToken;
+use ide_jvm_attach::{AttachError, HeapDumpReply, HistogramRow, JavaVersion};
 use std::collections::VecDeque;
+use std::path::{Path, PathBuf};
 use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering};

 fn row(name: &str, instances: u64, bytes: u64) -> HistogramRow {
@@ -25,8 +28,52 @@ struct FakeProbe {
    asked: parking_lot::Mutex<Vec<u32>>,
    /// Pids the scan sent a request to.
    queried: parking_lot::Mutex<Vec<u32>>,
-    /// Attach commands sent, in order.
+    /// Attach commands sent, in order: `histogram`, `vm_flags`, `heap_dump`.
    commands: parking_lot::Mutex<Vec<&'static str>>,
+    dumps: parking_lot::Mutex<VecDeque<Result<HeapDumpReply, AttachError>>>,
+    dump_paths: parking_lot::Mutex<Vec<PathBuf>>,
+    /// Each heap dump waits for this gate to open.
+    dump_gate: Option<Arc<Gate>>,
+    /// A `Created` reply writes this many bytes to the dump path first.
+    dump_bytes: usize,
+    free: Option<u64>,
+    /// Answering this command stops the program: runs the hook.
+    stops_on: Option<(&'static str, StopHook)>,
+}
+
+type StopHook = Box<dyn Fn() + Send + Sync>;
+
+/// Holds a blocking call until the test opens it.
+#[derive(Default)]
+struct Gate {
+    entered: tokio::sync::Notify,
+    open: parking_lot::Mutex<bool>,
+    opened: parking_lot::Condvar,
+}
+
+impl Gate {
+    fn pass(&self) {
+        self.entered.notify_one();
+        let mut open = self.open.lock();
+        while !*open {
+            self.opened.wait(&mut open);
+        }
+    }
+
+    fn release(&self) {
+        *self.open.lock() = true;
+        self.opened.notify_all();
+    }
+}
+
+/// Opens the gate when dropped: a failed assertion must not leave a blocking thread waiting,
+/// since the runtime's shutdown waits for it.
+struct OpenOnDrop(Arc<Gate>);
+
+impl Drop for OpenOnDrop {
+    fn drop(&mut self) {
+        self.0.release();
+    }
 }

 impl FakeProbe {
@@ -44,11 +91,26 @@ impl FakeProbe {
            asked: parking_lot::Mutex::new(Vec::new()),
            queried: parking_lot::Mutex::new(Vec::new()),
            commands: parking_lot::Mutex::new(Vec::new()),
+            dumps: parking_lot::Mutex::new(VecDeque::new()),
+            dump_paths: parking_lot::Mutex::new(Vec::new()),
+            dump_gate: None,
+            dump_bytes: 64,
+            free: None,
+            stops_on: None,
+        }
+    }
+
+    fn record(&self, command: &'static str) {
+        self.commands.lock().push(command);
+        if let Some((on, stop)) = &self.stops_on
+            && *on == command
+        {
+            stop();
        }
    }

    fn enter(&self, command: &'static str) {
-        self.commands.lock().push(command);
+        self.record(command);
        let now = self.in_flight.fetch_add(1, Ordering::SeqCst) + 1;
        self.max_in_flight.fetch_max(now, Ordering::SeqCst);
    }
@@ -84,8 +146,31 @@ impl AttachProbe for FakeProbe {
    fn alive(&self, _pid: u32) -> bool {
        self.alive
    }
+    fn vm_flags(&self, _pid: u32) -> Result<String, AttachError> {
+        self.record("vm_flags");
+        Ok(FLAGS.into())
+    }
+    fn heap_dump(&self, _pid: u32, path: &Path, _timeout: Duration) -> Result<HeapDumpReply, AttachError> {
+        self.enter("heap_dump");
+        self.dump_paths.lock().push(path.to_owned());
+        if let Some(gate) = &self.dump_gate {
+            gate.pass();
+        }
+        let reply = self.dumps.lock().pop_front().expect("unexpected heap dump request");
+        if matches!(reply, Ok(HeapDumpReply::Created { .. })) && self.dump_bytes > 0 {
+            // Fails like the JVM's write once the directory is gone.
+            let _ = std::fs::write(path, vec![0; self.dump_bytes]);
+        }
+        self.leave();
+        reply
+    }
+    fn free_bytes(&self, _dir: &Path) -> Option<u64> {
+        self.free
+    }
 }

+const FLAGS: &str = "-XX:+UseCompressedOops -XX:+StartAttachListener";
+
 const HISTOGRAM: &str = " num     #instances         #bytes  class name (module)\n-------------------------------------------------------\n   1:             5             80  A\n   2:             1             16  B\nTotal             6             96\n";

 fn unavailable(r: IdeResult<Result<(JvmMemorySnapshot, ClassCounts), JvmMemoryUnavailable>>) -> JvmMemoryUnavailable {
@@ -691,12 +776,416 @@ fn debugger_rows_are_ordered_by_instances() {
    assert_eq!(names, ["A", "C", "B"]);
 }

+/// A snapshot directory inside a temporary one, so the capture may delete it.
+fn snapshot_dir(name: &str) -> (tempfile::TempDir, PathBuf) {
+    let root = tempfile::tempdir().unwrap();
+    let dir = root.path().join(name);
+    std::fs::create_dir(&dir).unwrap();
+    (root, dir)
+}
+
+/// JVM 12 at Java `major`, answering [`HISTOGRAM`] once and `dumps` in turn.
+fn dumping(major: u32, dumps: Vec<Result<HeapDumpReply, AttachError>>) -> FakeProbe {
+    let mut probe = FakeProbe::new(12, vec![Ok(HISTOGRAM.into())]);
+    probe.version = Some(JavaVersion { major, text: format!("{major}.0.1") });
+    probe.dumps = parking_lot::Mutex::new(dumps.into());
+    probe
+}
+
+fn created() -> Result<HeapDumpReply, AttachError> {
+    Ok(HeapDumpReply::Created { bytes: Some(64) })
+}
+
+fn memory(reason: JvmMemoryUnavailable) -> JvmHeapOutcome {
+    JvmHeapOutcome::Unavailable(JvmHeapUnavailable::Memory { reason })
+}
+
+fn dump_failed(message: &str) -> JvmHeapOutcome {
+    JvmHeapOutcome::Unavailable(JvmHeapUnavailable::DumpFailed { message: message.into() })
+}
+
+fn ready(outcome: IdeResult<JvmHeapOutcome>) -> JvmHeapDump {
+    match outcome.unwrap() {
+        JvmHeapOutcome::Ready(dump) => dump,
+        other => panic!("{other:?}"),
+    }
+}
+
+fn entry(name: &str, instances: u64, bytes: u64) -> ide_heap::HistogramEntry {
+    ide_heap::HistogramEntry { name: name.into(), instances, bytes }
+}
+
+#[test]
+fn suspended_jdk11_refuses_without_sending() {
+    let (_root, dir) = snapshot_dir("snap");
+    let probe = dumping(11, vec![created()]);
+    let outcome = take_heap_dump(&probe, &[12], true, &|| true, &dir, &CancellationToken::new()).unwrap();
+    assert_eq!(outcome, memory(JvmMemoryUnavailable::UnsafeWhileSuspended { java_major: 11 }));
+    assert!(probe.commands.lock().is_empty());
+    assert!(!dir.exists());
+}
+
+#[test]
+fn suspended_jdk17_dumps() {
+    let (_root, dir) = snapshot_dir("snap");
+    let probe = dumping(17, vec![created()]);
+    let dump = ready(take_heap_dump(&probe, &[10, 12], true, &|| true, &dir, &CancellationToken::new()));
+    assert_eq!(*probe.commands.lock(), ["histogram", "vm_flags", "heap_dump"]);
+    assert_eq!(*probe.dump_paths.lock(), [dir.join("dump.hprof")]);
+    let expected = JvmHeapDump {
+        path: dir.join("dump.hprof"),
+        histogram: vec![entry("A", 5, 80), entry("B", 1, 16)],
+        vm_flags: FLAGS.into(),
+        java_major: 17,
+        java_version: "17.0.1".into(),
+        pid: 12,
+        taken_while_suspended: true,
+        dump_ms: dump.dump_ms,
+    };
+    assert_eq!(dump, expected);
+    assert!(dump.path.is_file());
+}
+
+#[test]
+fn running_jdk8_dumps() {
+    let (_root, dir) = snapshot_dir("snap");
+    let probe = dumping(8, vec![created()]);
+    let dump = ready(take_heap_dump(&probe, &[12], false, &|| false, &dir, &CancellationToken::new()));
+    assert_eq!((dump.java_major, dump.taken_while_suspended), (8, false));
+    assert_eq!(*probe.commands.lock(), ["histogram", "vm_flags", "heap_dump"]);
+}
+
+#[test]
+fn not_enough_disk_space_refuses_before_dump() {
+    let (_root, dir) = snapshot_dir("snap");
+    let mut probe = dumping(21, vec![created()]);
+    let gib = 1u64 << 30;
+    let histogram = format!("   1:      10000000     {gib}  [B\nTotal      10000000     {gib}\n");
+    probe.histograms = parking_lot::Mutex::new(vec![Ok(histogram)].into());
+    probe.free = Some(512 << 20);
+    let outcome = take_heap_dump(&probe, &[12], false, &|| false, &dir, &CancellationToken::new()).unwrap();
+    let needed = gib + 1_060_000_000 + gib;
+    assert_eq!(
+        outcome,
+        JvmHeapOutcome::Unavailable(JvmHeapUnavailable::NotEnoughDiskSpace { needed, available: 512 << 20 })
+    );
+    assert_eq!(*probe.commands.lock(), ["histogram"]);
+    assert!(!dir.exists());
+}
+
+#[test]
+fn refused_dump_reports_message() {
+    let (_root, dir) = snapshot_dir("snap");
+    let message = "Unable to create /tmp/snap/dump.hprof: File exists";
+    let probe = dumping(21, vec![Ok(HeapDumpReply::Refused { message: message.into() })]);
+    let outcome = take_heap_dump(&probe, &[12], false, &|| false, &dir, &CancellationToken::new()).unwrap();
+    assert_eq!(outcome, dump_failed(message));
+    assert!(!dir.exists());
+}
+
+#[test]
+fn refused_dump_without_a_reason_says_so() {
+    for body in ["", "Dumping heap to /tmp/snap/dump.hprof ..."] {
+        let (_root, dir) = snapshot_dir("snap");
+        let probe = dumping(21, vec![Ok(HeapDumpReply::Refused { message: body.into() })]);
+        let outcome = take_heap_dump(&probe, &[12], false, &|| false, &dir, &CancellationToken::new()).unwrap();
+        let JvmHeapOutcome::Unavailable(JvmHeapUnavailable::DumpFailed { message }) = outcome else {
+            panic!("{body:?}: {outcome:?}")
+        };
+        assert!(!message.is_empty() && !message.starts_with("Dumping heap to"), "{body:?}: {message:?}");
+        assert!(!dir.exists());
+    }
+}
+
+#[test]
+fn timed_out_dump_removes_snapshot_dir() {
+    let (_root, dir) = snapshot_dir("snap");
+    let probe = dumping(21, vec![Err(AttachError::Timeout)]);
+    let outcome = take_heap_dump(&probe, &[12], false, &|| false, &dir, &CancellationToken::new()).unwrap();
+    assert_eq!(outcome, JvmHeapOutcome::Unavailable(JvmHeapUnavailable::DumpTimedOut { seconds: 30 }));
+    assert!(!dir.exists());
+}
+
+#[test]
+fn capture_dir_with_space_is_quoted() {
+    let (_root, dir) = snapshot_dir("a b");
+    let probe = dumping(21, vec![created()]);
+    ready(take_heap_dump(&probe, &[12], false, &|| false, &dir, &CancellationToken::new()));
+    let path = probe.dump_paths.lock()[0].clone();
+    assert!(path.to_str().unwrap().contains("a b"), "{path:?}");
+    let command = ide_jvm_attach::heap_dump_command(&path).unwrap();
+    assert_eq!(command, format!("GC.heap_dump -all \"{}\"", path.display()));
+}
+
+#[test]
+fn created_without_a_file_fails() {
+    let (_root, dir) = snapshot_dir("snap");
+    let mut probe = dumping(21, vec![created()]);
+    probe.dump_bytes = 0;
+    let outcome = take_heap_dump(&probe, &[12], false, &|| false, &dir, &CancellationToken::new()).unwrap();
+    assert!(matches!(outcome, JvmHeapOutcome::Unavailable(JvmHeapUnavailable::DumpFailed { .. })), "{outcome:?}");
+    assert!(!dir.exists());
+}
+
+#[test]
+fn dump_errors_map_like_the_class_table() {
+    let message = "java.lang.IllegalArgumentException: Unknown argument";
+    let cases = [
+        (Err(AttachError::Refused), false, memory(JvmMemoryUnavailable::ProgramExited)),
+        (Err(AttachError::NoListener), true, memory(JvmMemoryUnavailable::ListenerNotRunning)),
+        (Err(AttachError::Command { code: -1, message: message.into() }), true, dump_failed(message)),
+    ];
+    for (reply, alive, expected) in cases {
+        let (_root, dir) = snapshot_dir("snap");
+        let mut probe = dumping(21, vec![reply]);
+        probe.alive = alive;
+        assert_eq!(take_heap_dump(&probe, &[12], false, &|| false, &dir, &CancellationToken::new()).unwrap(), expected);
+        assert!(!dir.exists());
+    }
+
+    let (_root, dir) = snapshot_dir("snap");
+    let probe = dumping(21, vec![Err(AttachError::Protocol("bad".into()))]);
+    assert!(take_heap_dump(&probe, &[12], false, &|| false, &dir, &CancellationToken::new()).is_err());
+    assert!(!dir.exists());
+}
+
+/// JDK `major`, running when the capture starts, stopped by the time it answers `command`.
+fn stopping_after(major: u32, command: &'static str) -> (FakeProbe, Arc<AtomicBool>) {
+    let stopped = Arc::new(AtomicBool::new(false));
+    let mut probe = dumping(major, vec![created()]);
+    let flag = stopped.clone();
+    probe.stops_on = Some((command, Box::new(move || flag.store(true, Ordering::SeqCst))));
+    (probe, stopped)
+}
+
+#[test]
+fn jdk11_stopped_during_the_histogram_gets_no_further_request() {
+    for (command, sent) in [("histogram", &["histogram"][..]), ("vm_flags", &["histogram", "vm_flags"][..])] {
+        let (_root, dir) = snapshot_dir("snap");
+        let (probe, stopped) = stopping_after(11, command);
+        let suspended_now = || stopped.load(Ordering::SeqCst);
+        let outcome = take_heap_dump(&probe, &[12], false, &suspended_now, &dir, &CancellationToken::new()).unwrap();
+        assert_eq!(outcome, memory(JvmMemoryUnavailable::UnsafeWhileSuspended { java_major: 11 }), "{command}");
+        assert_eq!(*probe.commands.lock(), sent, "{command}");
+        assert!(!dir.exists(), "{command}");
+    }
+}
+
+#[tokio::test]
+async fn session_stopped_during_the_histogram_is_read_again_before_the_dump() {
+    let bare = bare_session("attach");
+    let mut probe = dumping(11, vec![created()]);
+    let stopping = bare.session.clone();
+    probe.stops_on = Some(("histogram", Box::new(move || stopping.suspended.stopped(Some(1), true))));
+    let fake = Arc::new(probe);
+    let probe: Arc<dyn AttachProbe> = fake.clone();
+    let pid = AtomicI64::new(12);
+    let target = JvmTarget::Attached { pid: &pid, jdwp_port: None };
+    let (_root, dir) = snapshot_dir("snap");
+    let session = bare.session.clone();
+    let suspended = move || capture_suspended(&session);
+    let s = &bare.session;
+    let outcome = heap_dump_with(&s.jvm_memory, suspended, |_| probe, target, dir.clone(), CancellationToken::new())
+        .await
+        .unwrap();
+    assert_eq!(outcome, memory(JvmMemoryUnavailable::UnsafeWhileSuspended { java_major: 11 }));
+    assert_eq!(*fake.commands.lock(), ["histogram"]);
+    assert!(!dir.exists());
+    assert!(s.jvm_memory.try_lock().is_ok(), "the lock is released");
+}
+
+#[test]
+fn jdk17_stopped_during_the_histogram_still_dumps() {
+    let (_root, dir) = snapshot_dir("snap");
+    let (probe, stopped) = stopping_after(17, "histogram");
+    let suspended_now = || stopped.load(Ordering::SeqCst);
+    let dump = ready(take_heap_dump(&probe, &[12], false, &suspended_now, &dir, &CancellationToken::new()));
+    assert!(!dump.taken_while_suspended, "the stop read when the capture began");
+    assert_eq!(*probe.commands.lock(), ["histogram", "vm_flags", "heap_dump"]);
+}
+
+#[test]
+fn cancelled_capture_sends_no_dump() {
+    let (_root, dir) = snapshot_dir("snap");
+    let probe = dumping(21, vec![created()]);
+    let cancel = CancellationToken::new();
+    cancel.cancel();
+    assert_eq!(take_heap_dump(&probe, &[12], false, &|| false, &dir, &cancel).unwrap(), JvmHeapOutcome::Cancelled);
+    assert!(!probe.commands.lock().contains(&"heap_dump"));
+    assert!(!dir.exists());
+}
+
+#[tokio::test]
+async fn cancelled_capture_releases_lock() {
+    let state = Arc::new(tokio::sync::Mutex::new(JvmMemoryState::default()));
+    let gate = Arc::new(Gate::default());
+    let opener = OpenOnDrop(gate.clone());
+    let mut fake = dumping(21, vec![created()]);
+    fake.histograms.lock().push_back(Ok(HISTOGRAM.into()));
+    fake.dump_gate = Some(gate.clone());
+    let fake = Arc::new(fake);
+    let jvm_pid = Arc::new(AtomicI64::new(12));
+    let (_root, dir) = snapshot_dir("snap");
+    let cancel = CancellationToken::new();
+    let capture = {
+        let (state, fake, jvm_pid, dir, cancel) =
+            (state.clone(), fake.clone(), jvm_pid.clone(), dir.clone(), cancel.clone());
+        async move {
+            let target = JvmTarget::Attached { pid: &jvm_pid, jdwp_port: None };
+            heap_dump_with(&state, || false, |_| -> Arc<dyn AttachProbe> { fake }, target, dir, cancel).await
+        }
+    };
+    let caller = tokio::spawn(detached(capture, dir.clone(), cancel.clone()));
+    gate.entered.notified().await;
+    cancel.cancel();
+    assert_eq!(caller.await.unwrap().unwrap(), JvmHeapOutcome::Cancelled);
+    assert_eq!(fake.in_flight.load(Ordering::SeqCst), 1, "the JVM is still writing the dump");
+    assert!(!dir.exists());
+
+    let mut table = tokio::spawn({
+        let (state, fake, jvm_pid) = (state.clone(), fake.clone(), jvm_pid.clone());
+        async move {
+            let target = JvmTarget::Attached { pid: &jvm_pid, jdwp_port: None };
+            let probe: Arc<dyn AttachProbe> = fake;
+            snapshot(&state, &Suspension::default(), |_| probe, target, None).await
+        }
+    });
+    // While the gate is shut the dump holds the session's turn, so the class table cannot finish.
+    let early = tokio::time::timeout(Duration::from_millis(100), &mut table).await;
+    assert!(early.is_err(), "the class table ran beside the dump: {early:?}");
+    drop(opener);
+    let table = table.await.unwrap().unwrap();
+    assert!(matches!(table, JvmMemoryResult::Ready { .. }), "{table:?}");
+    assert_eq!(fake.max_in_flight.load(Ordering::SeqCst), 1);
+    assert_eq!(*fake.commands.lock(), ["histogram", "vm_flags", "heap_dump", "histogram"]);
+    assert!(!dir.exists(), "the dump that finished after the cancel is deleted");
+}
+
+#[tokio::test]
+async fn capture_keeps_the_memory_baseline() {
+    let state = tokio::sync::Mutex::new(JvmMemoryState::default());
+    let running = Suspension::default();
+    let pid = AtomicI64::new(12);
+    let target = || JvmTarget::Attached { pid: &pid, jdwp_port: None };
+    let table = |fake: FakeProbe| {
+        let probe: Arc<dyn AttachProbe> = Arc::new(fake);
+        snapshot(&state, &running, |_| probe, target(), None)
+    };
+    table(FakeProbe::new(12, vec![Ok(HISTOGRAM.into())])).await.unwrap();
+
+    let mut capture = dumping(21, vec![created()]);
+    let grown = "   1:            50            800  A\nTotal            50            800\n";
+    capture.histograms = parking_lot::Mutex::new(vec![Ok(grown.into())].into());
+    let probe: Arc<dyn AttachProbe> = Arc::new(capture);
+    let (_root, dir) = snapshot_dir("snap");
+    ready(heap_dump_with(&state, || false, |_| probe, target(), dir, CancellationToken::new()).await);
+
+    let JvmMemoryResult::Ready { snapshot } = table(FakeProbe::new(12, vec![Ok(HISTOGRAM.into())])).await.unwrap()
+    else {
+        panic!("no class table")
+    };
+    let a = snapshot.rows.iter().find(|r| r.name == "A").unwrap();
+    assert_eq!((a.delta_instances, a.delta_bytes), (Some(0), Some(0)));
+}
+
+#[tokio::test]
+async fn attached_session_dumps_the_scanned_jvm() {
+    let mut fake = dumping(21, vec![created()]);
+    fake.listener = 4242;
+    fake.jdwp = Some((5005, 4242));
+    let fake = Arc::new(fake);
+    let probe: Arc<dyn AttachProbe> = fake.clone();
+    let state = tokio::sync::Mutex::new(JvmMemoryState::default());
+    let pid = AtomicI64::new(0);
+    let target = JvmTarget::Attached { pid: &pid, jdwp_port: Some(5005) };
+    let (_root, dir) = snapshot_dir("snap");
+    let dump = ready(heap_dump_with(&state, || false, |_| probe, target, dir, CancellationToken::new()).await);
+    assert_eq!(dump.pid, 4242);
+    assert_eq!(pid.load(Ordering::SeqCst), 4242);
+    assert_eq!(fake.scans.load(Ordering::SeqCst), 1);
+}
+
+/// A JDWP link whose fake JVM sent a suspending event, which the adapter would report next:
+/// (link, adapter end, JVM end).
+async fn suspended_link() -> (ide_jdwp::JdwpLink, tokio::net::TcpStream, tokio::net::TcpStream) {
+    use tokio::io::{AsyncReadExt, AsyncWriteExt};
+    const HANDSHAKE: &[u8; 14] = b"JDWP-Handshake";
+    let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
+    let port = listener.local_addr().unwrap().port();
+    let options = ide_jdwp::LinkOptions { hold_resumes: false };
+    let (link, link_port) = ide_jdwp::JdwpLink::start("127.0.0.1".into(), port, options).await.unwrap();
+    let mut adapter = tokio::net::TcpStream::connect(("127.0.0.1", link_port)).await.unwrap();
+    adapter.write_all(HANDSHAKE).await.unwrap();
+    let (mut jvm, _) = tokio::time::timeout(Duration::from_secs(2), listener.accept()).await.unwrap().unwrap();
+    let mut buf = [0; 14];
+    jvm.read_exact(&mut buf).await.unwrap();
+    jvm.write_all(HANDSHAKE).await.unwrap();
+    adapter.read_exact(&mut buf).await.unwrap();
+    // Event.Composite (64/100): SUSPEND_ALL, one VM_START event, request 0, thread 1.
+    let body = [2, 0, 0, 0, 1, 90, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1];
+    let mut packet = u32::try_from(11 + body.len()).unwrap().to_be_bytes().to_vec();
+    packet.extend(1u32.to_be_bytes());
+    packet.extend([0, 64, 100]);
+    packet.extend(body);
+    jvm.write_all(&packet).await.unwrap();
+    let mut states = link.subscribe();
+    let suspended = states.wait_for(|s| matches!(s, ide_jdwp::LinkState::Suspended { .. }));
+    tokio::time::timeout(Duration::from_secs(2), suspended).await.unwrap().unwrap();
+    (link, adapter, jvm)
+}
+
+#[tokio::test]
+async fn jdk11_is_refused_while_the_link_is_suspended_before_dap_stops() {
+    let bare = bare_session_of(crate::kotlin::ADAPTER, "attach");
+    let s = &bare.session;
+    let (link, _adapter, _jvm) = suspended_link().await;
+    *s.jdwp_link.lock() = Some(link);
+    assert!(!s.suspended.get());
+
+    let fake = Arc::new(jdk11(12));
+    let probe: Arc<dyn AttachProbe> = fake.clone();
+    let probe = |suspended: bool| {
+        assert!(suspended, "the probe must not ask a suspended JVM's version over attach");
+        probe
+    };
+    let pid = AtomicI64::new(12);
+    let target = JvmTarget::Attached { pid: &pid, jdwp_port: None };
+    let (_root, dir) = snapshot_dir("snap");
+    let session = bare.session.clone();
+    let suspended = move || capture_suspended(&session);
+    let outcome =
+        heap_dump_with(&s.jvm_memory, suspended, probe, target, dir.clone(), CancellationToken::new()).await.unwrap();
+    assert_eq!(outcome, memory(JvmMemoryUnavailable::UnsafeWhileSuspended { java_major: 11 }));
+    assert!(fake.commands.lock().is_empty());
+    assert!(!dir.exists());
+}
+
 #[tokio::test]
 async fn capability_matches_memory() {
    for adapter in JVM_MEMORY_ADAPTERS.iter().copied().chain(["debugpy"]) {
        let bare = bare_session_of(adapter, "launch");
        let caps = crate::session_capabilities(&bare.session);
        let jvm = adapter != "debugpy";
-        assert_eq!(caps.jvm_memory, jvm, "{adapter}");
+        assert_eq!((caps.jvm_heap, caps.jvm_memory), (jvm, jvm), "{adapter}");
    }
 }
+
+#[cfg(unix)]
+#[tokio::test]
+async fn session_without_a_jvm_reports_no_process() {
+    let bare = bare_session("launch");
+    let (_root, dir) = snapshot_dir("snap");
+    let outcome = session_heap_dump(bare.session.clone(), dir.clone(), CancellationToken::new()).await.unwrap();
+    assert_eq!(outcome, memory(JvmMemoryUnavailable::NoJvmProcess));
+    assert!(!dir.exists());
+}
+
+#[cfg(not(unix))]
+#[tokio::test]
+async fn capture_is_unsupported_off_unix() {
+    let bare = bare_session("launch");
+    let (_root, dir) = snapshot_dir("snap");
+    let outcome = session_heap_dump(bare.session.clone(), dir.clone(), CancellationToken::new()).await.unwrap();
+    assert_eq!(outcome, memory(JvmMemoryUnavailable::UnsupportedPlatform));
+    assert!(!dir.exists());
+}
@@ -9,11 +9,15 @@ use std::{

 pub const ADAPTER: &str = "kotlin-debug-adapter";

-/// The adapter attaches to a JVM the IDE starts, through the JDWP link. It resumes the VM while
-/// constructing its debuggee, before its breakpoint hooks exist, so the link holds resumes back
-/// until the attach is done.
-pub(crate) fn link_options() -> ide_jdwp::LinkOptions {
-    ide_jdwp::LinkOptions { hold_resumes: true }
+/// fwcd's adapter or kotlin-lsp's: both debug a JVM the IDE starts, through the JDWP link.
+pub fn is_kotlin(adapter: &str) -> bool {
+    adapter == ADAPTER || adapter == crate::kotlin_lsp::ADAPTER
+}
+
+/// fwcd's adapter resumes the VM while constructing its debuggee, before its breakpoint hooks
+/// exist, so only its link holds resumes back until the attach is done.
+pub(crate) fn link_options(adapter: &str) -> ide_jdwp::LinkOptions {
+    ide_jdwp::LinkOptions { hold_resumes: adapter == ADAPTER }
 }

 pub struct SourceMirror {
@@ -0,0 +1,147 @@
+//! JetBrains kotlin-lsp's debugger: a DAP server inside the language server, reached through
+//! the `debugServer` port it opens once the project is imported.
+//!
+//! Known limits, with no guard here: an evaluate that calls a function with a breakpoint, right
+//! after a step over a suspension point, loses every later stop at that breakpoint; while
+//! stepping, breakpoints hit by other coroutines are skipped.
+
+use ide_core::{IdeError, IdeResult};
+use parking_lot::Mutex;
+use std::collections::HashSet;
+use std::path::PathBuf;
+use std::sync::atomic::{AtomicBool, Ordering};
+
+pub const ADAPTER: &str = "kotlin-lsp";
+/// The `adapterID` its debug server expects in `initialize`.
+pub const DAP_ADAPTER_ID: &str = "intellij_jvm";
+
+/// The path of a `file:` URI, as kotlin-lsp reports some sources (percent-encoded); `None` for
+/// anything else, including a URI naming another host.
+pub(crate) fn source_path(path: &str) -> Option<PathBuf> {
+    let rest = path.strip_prefix("file:")?;
+    let path = match rest.strip_prefix("//") {
+        Some(authority) => {
+            let slash = authority.find('/')?;
+            if !matches!(&authority[..slash], "" | "localhost") {
+                return None;
+            }
+            &authority[slash..]
+        }
+        None => rest,
+    };
+    let decoded = percent_encoding::percent_decode_str(path).decode_utf8().ok()?;
+    // `/C:/p/App.kt` on Windows.
+    let decoded = match decoded.strip_prefix('/') {
+        Some(drive) if cfg!(windows) && drive.as_bytes().get(1) == Some(&b':') => drive,
+        _ => &decoded,
+    };
+    Some(PathBuf::from(decoded))
+}
+
+pub(crate) fn frame_name(name: &str) -> &str {
+    name.strip_prefix("at ").unwrap_or(name)
+}
+
+/// What kotlin-lsp's DAP server does unlike other adapters.
+///
+/// It never answers a request that carries a thread id from an earlier stop (K1 G4), so such a
+/// request would wait out `REQUEST_TIMEOUT`: [`Self::check_thread`] refuses it first. Only thread
+/// ids were measured; a stale `frameId` or `variablesReference` may wait the same way. A step
+/// ends with `reason: "breakpoint"`; a real breakpoint hit during a step is then reported as a
+/// step too, since the stop carries neither `hitBreakpointIds` nor a description.
+#[derive(Default)]
+pub(crate) struct Quirks {
+    step_pending: AtomicBool,
+    /// The stop (a `Suspension` ticket) and the thread ids seen in it.
+    threads: Mutex<(u64, HashSet<i64>)>,
+}
+
+impl Quirks {
+    /// Before `next`, `stepIn`, `stepOut` or a forced step.
+    pub fn step_sent(&self) {
+        self.step_pending.store(true, Ordering::Release);
+    }
+
+    /// Before `continue` or run to cursor, or after a step request failed.
+    pub fn resume_sent(&self) {
+        self.step_pending.store(false, Ordering::Release);
+    }
+
+    /// The reason to report for a `stopped` event.
+    pub fn stop_reason(&self, reason: String) -> String {
+        let stepped = self.step_pending.swap(false, Ordering::AcqRel);
+        if stepped && reason == "breakpoint" { "step".into() } else { reason }
+    }
+
+    /// Thread ids seen in stop `stop`: a `stopped` event's, or a `threads` reply to a request sent
+    /// during that stop. A reply from an older stop changes nothing.
+    pub fn saw_threads(&self, stop: u64, ids: impl IntoIterator<Item = i64>) {
+        let mut threads = self.threads.lock();
+        if stop > threads.0 {
+            *threads = (stop, ids.into_iter().collect());
+        } else if stop == threads.0 {
+            threads.1.extend(ids);
+        }
+    }
+
+    /// Refuses a thread id that is not one of current stop `stop`'s, once some are known.
+    pub fn check_thread(&self, stop: u64, suspended: bool, id: i64) -> IdeResult<()> {
+        let threads = self.threads.lock();
+        if suspended && threads.0 == stop && !threads.1.is_empty() && !threads.1.contains(&id) {
+            return Err(IdeError::invalid(format!("thread {id} belongs to an earlier stop")));
+        }
+        Ok(())
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::path::Path;
+
+    #[test]
+    fn file_uris_become_paths() {
+        assert_eq!(source_path("file:///p/a%20b/App.kt").as_deref(), Some(Path::new("/p/a b/App.kt")));
+        assert_eq!(source_path("file://localhost/p/x.kt").as_deref(), Some(Path::new("/p/x.kt")));
+        assert_eq!(source_path("/p/x.kt"), None);
+    }
+
+    #[test]
+    fn frame_names_lose_the_at_prefix() {
+        assert_eq!(frame_name("at com.x.AppKt.main(App.kt:13)"), "com.x.AppKt.main(App.kt:13)");
+        assert_eq!(frame_name("main"), "main");
+    }
+
+    #[test]
+    fn only_a_pending_step_turns_a_breakpoint_into_a_step() {
+        let quirks = Quirks::default();
+        quirks.step_sent();
+        assert_eq!(quirks.stop_reason("breakpoint".into()), "step");
+        assert_eq!(quirks.stop_reason("breakpoint".into()), "breakpoint");
+        quirks.step_sent();
+        quirks.resume_sent();
+        assert_eq!(quirks.stop_reason("breakpoint".into()), "breakpoint");
+    }
+
+    #[test]
+    fn threads_are_checked_against_the_current_stop() {
+        let quirks = Quirks::default();
+        quirks.saw_threads(3, [18]);
+        assert!(quirks.check_thread(3, true, 18).is_ok());
+        assert!(quirks.check_thread(3, true, 6).is_err());
+        assert!(quirks.check_thread(4, true, 6).is_ok(), "nothing known about stop 4 yet");
+        assert!(quirks.check_thread(3, false, 6).is_ok());
+    }
+
+    #[test]
+    fn an_older_threads_reply_does_not_change_a_newer_stop() {
+        let quirks = Quirks::default();
+        quirks.saw_threads(4, [2]);
+        quirks.saw_threads(3, [1]);
+        assert!(quirks.check_thread(4, true, 1).is_err());
+        quirks.saw_threads(4, [7]);
+        assert!(quirks.check_thread(4, true, 2).is_ok() && quirks.check_thread(4, true, 7).is_ok());
+        quirks.saw_threads(5, [9]);
+        assert!(quirks.check_thread(5, true, 2).is_err());
+    }
+}
@@ -15,6 +15,7 @@ pub mod connection;
 pub mod jdwp;
 mod jvm_memory;
 pub mod kotlin;
+pub mod kotlin_lsp;
 mod session;

 use adapter::{AdapterLauncher, AdapterSpec, ProcessLauncher};
@@ -133,6 +134,8 @@ pub struct DebugCapabilities {
    /// The session has a JVM inspector: instances, fields and referrers while suspended. Can
    /// change during the session ([`ide_core::event::DebugEvent::Capabilities`]).
    pub jvm_instances: bool,
+    /// The session can be asked for a heap dump ([`DebugManager::jvm_heap_dump`]).
+    pub jvm_heap: bool,
 }

 /// Result of [`DebugManager::redefine_classes`].
@@ -576,6 +579,7 @@ pub(crate) fn capabilities_from(caps: &Value) -> DebugCapabilities {
        hot_code_replace: false,
        jvm_memory: false,
        jvm_instances: false,
+        jvm_heap: false,
    }
 }

@@ -584,6 +588,7 @@ pub(crate) fn session_capabilities(session: &Session) -> DebugCapabilities {
    caps.hot_code_replace = HOT_CODE_REPLACE_ADAPTERS.contains(&session.adapter.as_str());
    caps.jvm_memory = JVM_MEMORY_ADAPTERS.contains(&session.adapter.as_str());
    caps.jvm_instances = session.jvm_inspector.lock().is_some();
+    caps.jvm_heap = JVM_MEMORY_ADAPTERS.contains(&session.adapter.as_str());
    caps
 }

@@ -606,6 +611,16 @@ fn unverified(enabled: impl Iterator<Item = bool>) -> Vec<BreakpointState> {
        .collect()
 }

+/// A step request's outcome; a failed one leaves no step pending, so the next stop keeps its reason.
+fn step_settled(session: &Session, sent: Result<Value, DapError>) -> Result<Value, DapError> {
+    if sent.is_err()
+        && let Some(quirks) = session.kotlin_lsp_quirks()
+    {
+        quirks.resume_sent();
+    }
+    sent
+}
+
 /// Delve compiles the debuggee to `__debug_bin` in the session's cwd (on Windows
 /// `__debug_bin.exe` plus `__debug_bin.exe<digits>` in DAP mode) and removes it on a
 /// graceful exit — a shutdown it doesn't always reach, so the files pile up. Sweep
@@ -977,6 +992,7 @@ impl DebugManager {
            arguments["projectRoot"] = json!(mirror.root());
            *s.kotlin_mirror.lock() = Some(mirror);
        }
+        let is_kotlin_lsp = s.adapter == kotlin_lsp::ADAPTER;
        let caps = s
            .conn
            .request_timeout(
@@ -984,7 +1000,7 @@ impl DebugManager {
                json!({
                    "clientID": "openidea",
                    "clientName": "OpenIDEA",
-                    "adapterID": s.adapter,
+                    "adapterID": if is_kotlin_lsp { kotlin_lsp::DAP_ADAPTER_ID } else { s.adapter.as_str() },
                    "locale": "en",
                    "linesStartAt1": true,
                    "columnsStartAt1": true,
@@ -994,7 +1010,8 @@ impl DebugManager {
                    "supportsRunInTerminalRequest": true,
                    "supportsStartDebuggingRequest": true,
                    "supportsProgressReporting": true,
-                    "supportsInvalidatedEvent": false,
+                    // kotlin-lsp sends `invalidated` either way.
+                    "supportsInvalidatedEvent": is_kotlin_lsp,
                    "supportsMemoryReferences": false,
                    "supportsArgsCanBeInterpretedByShell": false,
                }),
@@ -1004,7 +1021,7 @@ impl DebugManager {
        *s.caps.lock() = if caps.is_object() { caps } else { json!({}) };

        // The Kotlin adapters ignore the resolved classpath and project runtime on launch.
-        let request = if s.adapter == kotlin::ADAPTER && s.request == "launch" {
+        let request = if kotlin::is_kotlin(&s.adapter) && s.request == "launch" {
            session::start_kotlin_debuggee(s, &mut arguments).await?;
            "attach"
        } else {
@@ -1028,7 +1045,7 @@ impl DebugManager {
                jvm_memory::find_attached_jvm(s, port, finder).await;
            }
        }
-        if s.adapter == kotlin::ADAPTER {
+        if kotlin::is_kotlin(&s.adapter) {
            let host = arguments
                .get("hostName")
                .and_then(Value::as_str)
@@ -1040,7 +1057,7 @@ impl DebugManager {
                .and_then(|p| u16::try_from(p).ok())
                .filter(|p| *p != 0)
                .ok_or_else(|| IdeError::invalid("Invalid Kotlin JDWP port"))?;
-            let (link, port) = ide_jdwp::JdwpLink::start(host, port, kotlin::link_options()).await?;
+            let (link, port) = ide_jdwp::JdwpLink::start(host, port, kotlin::link_options(&s.adapter)).await?;
            *s.jvm_inspector.lock() = Some(Arc::new(ide_jdwp::LinkInspector::new(link.clone())));
            jvm_memory::watch_link(s, &link);
            *s.jdwp_link.lock() = Some(link);
@@ -1377,6 +1394,8 @@ impl DebugManager {

    pub async fn threads(&self, s: DebugSessionId) -> IdeResult<Vec<ThreadInfo>> {
        let session = self.session(s)?;
+        // Before sending: a stop that overtakes the reply must not take the reply's ids as its own.
+        let stop = session.suspended.ticket();
        let body = session.conn.request_timeout("threads", Value::Null, REQUEST_TIMEOUT).await?;
        let threads: Vec<ThreadInfo> = body
            .get("threads")
@@ -1390,11 +1409,15 @@ impl DebugManager {
                    .collect()
            })
            .unwrap_or_default();
+        if let Some(quirks) = session.kotlin_lsp_quirks() {
+            quirks.saw_threads(stop, threads.iter().map(|t| t.id));
+        }
        Ok(threads)
    }

    pub async fn stack_trace(&self, s: DebugSessionId, thread_id: i64) -> IdeResult<Vec<StackFrame>> {
        let session = self.session(s)?;
+        session.check_thread(thread_id)?;
        let body = session
            .conn
            .request_timeout(
@@ -1403,11 +1426,15 @@ impl DebugManager {
                REQUEST_TIMEOUT,
            )
            .await?;
+        let kotlin_lsp = session.kotlin_lsp_quirks().is_some();
        let frame = |f: &Value| {
            let mut frame = frame_from(f);
            if let Some(client) = frame.path.as_deref().and_then(|p| session.client_path(&p.to_string_lossy())) {
                frame.path = Some(client.into());
            }
+            if kotlin_lsp {
+                frame.name = kotlin_lsp::frame_name(&frame.name).to_owned();
+            }
            frame
        };
        Ok(body.get("stackFrames").and_then(Value::as_array).map(|f| f.iter().map(frame).collect()).unwrap_or_default())
@@ -1519,6 +1546,10 @@ impl DebugManager {

    pub async fn resume(&self, s: DebugSessionId, thread_id: i64) -> IdeResult<()> {
        let session = self.session(s)?;
+        session.check_thread(thread_id)?;
+        if let Some(quirks) = session.kotlin_lsp_quirks() {
+            quirks.resume_sent();
+        }
        let ticket = session.suspended.ticket();
        let body = session.conn.request_timeout("continue", json!({ "threadId": thread_id }), REQUEST_TIMEOUT).await?;
        // DAP: a response without the flag continued every thread.
@@ -1563,8 +1594,13 @@ impl DebugManager {
            StepKind::Out => "stepOut",
        };
        let session = self.session(s)?;
+        session.check_thread(thread_id)?;
+        if let Some(quirks) = session.kotlin_lsp_quirks() {
+            quirks.step_sent();
+        }
        let ticket = session.suspended.ticket();
-        session.conn.request_timeout(command, json!({ "threadId": thread_id }), REQUEST_TIMEOUT).await?;
+        let sent = session.conn.request_timeout(command, json!({ "threadId": thread_id }), REQUEST_TIMEOUT).await;
+        step_settled(&session, sent)?;
        // A step runs its thread; other threads stopped by their own events stay stopped.
        session.suspended.resumed(ticket, thread_id, false);
        session.emit(ide_core::event::DebugEvent::Continued { thread_id, all_threads_continued: true });
@@ -1583,6 +1619,8 @@ impl DebugManager {
        force: bool,
    ) -> IdeResult<()> {
        let session = self.session(s)?;
+        // Before touching breakpoints: a refused `continue` would leave them replaced.
+        session.check_thread(thread_id)?;
        if force {
            self.suspend_breakpoints(&session, Some(&path)).await?;
        }
@@ -1657,6 +1695,7 @@ impl DebugManager {
    /// Force Step Over: `next` with every breakpoint suspended until the step ends.
    pub async fn force_step_over(&self, s: DebugSessionId, thread_id: i64) -> IdeResult<()> {
        let session = self.session(s)?;
+        session.check_thread(thread_id)?;
        self.suspend_breakpoints(&session, None).await?;
        self.step(s, thread_id, StepKind::Over).await
    }
@@ -1664,11 +1703,16 @@ impl DebugManager {
    /// Step into a specific call of the current line (Smart Step Into).
    pub async fn step_in_target(&self, s: DebugSessionId, thread_id: i64, target_id: i64) -> IdeResult<()> {
        let session = self.session(s)?;
+        session.check_thread(thread_id)?;
+        if let Some(quirks) = session.kotlin_lsp_quirks() {
+            quirks.step_sent();
+        }
        let ticket = session.suspended.ticket();
-        session
+        let sent = session
            .conn
            .request_timeout("stepIn", json!({ "threadId": thread_id, "targetId": target_id }), REQUEST_TIMEOUT)
-            .await?;
+            .await;
+        step_settled(&session, sent)?;
        session.suspended.resumed(ticket, thread_id, false);
        session.emit(ide_core::event::DebugEvent::Continued { thread_id, all_threads_continued: true });
        Ok(())
@@ -1714,6 +1758,20 @@ impl DebugManager {
        jvm_memory::session_classes(session).await
    }

+    /// Writes a heap dump of the session's JVM to `dir/dump.hprof`, one class-table or dump
+    /// request per session at a time. Anything but `Ready` deletes `dir`, unless `s` is not a
+    /// session. On `cancel` the result is `Cancelled` at once, while a dump the JVM is writing
+    /// still holds the session's turn until the JVM answers.
+    pub async fn jvm_heap_dump(
+        &self,
+        s: DebugSessionId,
+        dir: PathBuf,
+        cancel: ide_core::CancellationToken,
+    ) -> IdeResult<JvmHeapOutcome> {
+        let session = self.session(s)?;
+        jvm_memory::session_heap_dump(session, dir, cancel).await
+    }
+
    /// Gives the session the backend for [`Self::jvm_memory_instances`] and the debugger's class
    /// counts; the UI is told to reload the session's capabilities.
    pub fn set_jvm_inspector(
@@ -3,6 +3,7 @@

 use crate::adapter::AdapterSpec;
 use crate::connection::{Connection, DapError, Incoming};
+use crate::kotlin_lsp;
 use crate::{Breakpoint, BreakpointState, DataBreakpoint, DebugManager, FunctionBreakpoint, SessionOwner};
 use ide_core::event::DebugEvent;
 #[cfg(unix)]
@@ -103,6 +104,8 @@ pub(crate) struct Session {
    pub jvm_located: watch::Sender<bool>,
    pub kotlin_mirror: Mutex<Option<crate::kotlin::SourceMirror>>,
    pub jvm_memory: tokio::sync::Mutex<crate::JvmMemoryState>,
+    /// Used only by a kotlin-lsp session: see [`Session::kotlin_lsp_quirks`].
+    pub(crate) quirks: kotlin_lsp::Quirks,
 }

 /// Which threads of the program are suspended: each from its `stopped` event until a
@@ -252,6 +255,19 @@ impl Session {
            jvm_located: watch::channel(false).0,
            kotlin_mirror: Mutex::new(None),
            jvm_memory: tokio::sync::Mutex::default(),
+            quirks: kotlin_lsp::Quirks::default(),
+        }
+    }
+
+    pub fn kotlin_lsp_quirks(&self) -> Option<&kotlin_lsp::Quirks> {
+        (self.adapter == kotlin_lsp::ADAPTER).then_some(&self.quirks)
+    }
+
+    /// Call before sending a request for thread `id`.
+    pub fn check_thread(&self, id: i64) -> ide_core::IdeResult<()> {
+        match self.kotlin_lsp_quirks() {
+            Some(quirks) => quirks.check_thread(self.suspended.ticket(), self.suspended.get(), id),
+            None => Ok(()),
        }
    }

@@ -283,6 +299,11 @@ impl Session {

    /// A path from the adapter as the IDE knows it (undoes [`Session::adapter_path`]).
    pub fn client_path(&self, path: &str) -> Option<PathBuf> {
+        if self.adapter == kotlin_lsp::ADAPTER
+            && let Some(path) = kotlin_lsp::source_path(path)
+        {
+            return Some(path);
+        }
        if let Some(real) = self.kotlin_mirror.lock().as_ref().and_then(|m| m.client_path(Path::new(path))) {
            return Some(real);
        }
@@ -697,7 +718,11 @@ async fn on_event(mgr: &Arc<DebugManager>, s: &Arc<Session>, event: &str, mut bo
        "stopped" => {
            let all = body.get("allThreadsStopped").and_then(Value::as_bool).unwrap_or(false);
            s.suspended.stopped(int("threadId"), all);
-            let reason = str_("reason").unwrap_or_else(|| "pause".into());
+            let mut reason = str_("reason").unwrap_or_else(|| "pause".into());
+            if let Some(quirks) = s.kotlin_lsp_quirks() {
+                quirks.saw_threads(s.suspended.ticket(), int("threadId"));
+                reason = quirks.stop_reason(reason);
+            }
            mgr.restore_breakpoints(s).await;
            s.emit(DebugEvent::Stopped {
                thread_id: int("threadId").unwrap_or(0),
@@ -799,6 +824,14 @@ async fn on_event(mgr: &Arc<DebugManager>, s: &Arc<Session>, event: &str, mut bo
            change_type: crate::hot_code_replace_type(body.get("changeType")),
            message: str_("message").unwrap_or_default(),
        }),
+        // Sent only by adapters told `supportsInvalidatedEvent` (kotlin-lsp).
+        "invalidated" => s.emit(DebugEvent::Invalidated {
+            areas: body
+                .get("areas")
+                .and_then(Value::as_array)
+                .map(|a| a.iter().filter_map(Value::as_str).map(str::to_owned).collect())
+                .unwrap_or_default(),
+        }),
        _ => tracing::trace!("dap: ignored event {event}"),
    }
 }
@@ -126,8 +126,22 @@ struct Script {
    continued_after_stop: bool,
    /// Close the connection when a `pause` request arrives (the adapter dies).
    hang_up_on_pause: bool,
+    /// Close the connection at the first request after the first `stopped` event.
+    hang_up_after_stop: bool,
    /// Answer `continue` with this body and keep the program running, instead of letting it exit.
    continue_reply: Option<Value>,
+    /// Answer `continue` and stop at a breakpoint again, instead of letting the program exit.
+    stop_after_continue: bool,
+    /// The `reason` of the stop a `next` ends with (`step` when unset; kotlin-lsp says `breakpoint`).
+    step_reason: Option<&'static str>,
+    /// Refuse `next`, then stop at a breakpoint (one the program hit meanwhile).
+    refuse_next: bool,
+    /// Send `invalidated { areas: ["variables"] }` right after the first `stopped` event.
+    invalidated_after_stop: bool,
+    /// On `threads`: stop again on thread 2 first, then answer with thread 1 of the earlier stop.
+    stop_during_threads: bool,
+    /// Name of the first stack frame (`main` when unset).
+    frame_name: Option<&'static str>,
    /// Answer `initialize` only after this long (a slow adapter keeps the session connecting).
    delay_initialize: Option<Duration>,
    initialized_delay: Duration,
@@ -156,7 +170,14 @@ impl Default for Script {
            hold_set_breakpoints: 0,
            continued_after_stop: false,
            hang_up_on_pause: false,
+            hang_up_after_stop: false,
            continue_reply: None,
+            stop_after_continue: false,
+            step_reason: None,
+            refuse_next: false,
+            invalidated_after_stop: false,
+            stop_during_threads: false,
+            frame_name: None,
            delay_initialize: None,
            initialized_delay: Duration::ZERO,
            launch_delay: Duration::ZERO,
@@ -202,6 +223,7 @@ async fn fake_adapter<S: AsyncRead + AsyncWrite + Unpin + Send + 'static>(stream
    let mut seq = 1000;
    let mut pending_launch: Option<i64> = None;
    let mut held: Vec<Value> = Vec::new();
+    let mut stopped = false;
    let mut running = false;
    macro_rules! send {
        ($v:expr) => {{
@@ -222,6 +244,9 @@ async fn fake_adapter<S: AsyncRead + AsyncWrite + Unpin + Send + 'static>(stream
        if msg["type"] == "response" {
            continue;
        }
+        if script.hang_up_after_stop && stopped {
+            break;
+        }
        match msg["command"].as_str().unwrap_or_default() {
            "initialize" => {
                if let Some(delay) = script.delay_initialize {
@@ -320,9 +345,18 @@ async fn fake_adapter<S: AsyncRead + AsyncWrite + Unpin + Send + 'static>(stream
                ok!(msg, Value::Null);
                send!(json!({"type": "event", "event": "stopped", "body": {"reason": "restart", "threadId": 1}}));
            }
+            "next" if script.refuse_next => {
+                send!(
+                    json!({"type": "response", "request_seq": msg["seq"], "command": "next", "success": false, "message": "refused"})
+                );
+                // Lets the client handle the refusal before the stop.
+                tokio::time::sleep(Duration::from_millis(50)).await;
+                send!(json!({"type": "event", "event": "stopped", "body": {"reason": "breakpoint", "threadId": 1}}));
+            }
            "next" => {
                ok!(msg, Value::Null);
-                send!(json!({"type": "event", "event": "stopped", "body": {"reason": "step", "threadId": 1}}));
+                let reason = script.step_reason.unwrap_or("step");
+                send!(json!({"type": "event", "event": "stopped", "body": {"reason": reason, "threadId": 1}}));
            }
            "setVariable" => {
                ok!(msg, json!({"value": format!("{}!", msg["arguments"]["value"].as_str().unwrap()), "type": "int"}))
@@ -358,6 +392,12 @@ async fn fake_adapter<S: AsyncRead + AsyncWrite + Unpin + Send + 'static>(stream
                send!(
                    json!({"type": "event", "event": "stopped", "body": {"reason": "breakpoint", "threadId": 1, "allThreadsStopped": true}})
                );
+                stopped = true;
+                if script.invalidated_after_stop {
+                    send!(
+                        json!({"type": "event", "event": "invalidated", "body": {"areas": ["variables"], "threadId": 1}})
+                    );
+                }
                if script.continued_after_stop {
                    send!(json!({"type": "event", "event": "continued", "body": {"threadId": 1}}));
                }
@@ -365,11 +405,19 @@ async fn fake_adapter<S: AsyncRead + AsyncWrite + Unpin + Send + 'static>(stream
                    json!({"type": "event", "event": "breakpoint", "body": {"reason": "changed", "breakpoint": {"id": 1, "verified": false, "message": "moved", "line": 9, "source": {"path": script.source_path}}}})
                );
            }
+            "threads" if script.stop_during_threads => {
+                send!(
+                    json!({"type": "event", "event": "stopped", "body": {"reason": "breakpoint", "threadId": 2, "allThreadsStopped": true}})
+                );
+                // Lets the client handle the stop before it reads the reply.
+                tokio::time::sleep(Duration::from_millis(50)).await;
+                ok!(msg, json!({"threads": [{"id": 1, "name": "\"main\"@1"}]}));
+            }
            "threads" => ok!(msg, json!({"threads": [{"id": 1, "name": "MainThread"}]})),
            "stackTrace" => ok!(
                msg,
                json!({"stackFrames": [
-                    {"id": 10, "name": "main", "line": 5, "column": 3, "source": {"path": script.source_path.as_deref().unwrap_or("/p/a.py")}},
+                    {"id": 10, "name": script.frame_name.unwrap_or("main"), "line": 5, "column": 3, "source": {"path": script.source_path.as_deref().unwrap_or("/p/a.py")}},
                    {"id": 11, "name": "lib", "line": 1, "column": 1, "source": {"path": "/usr/lib/x.py", "presentationHint": "deemphasize"}},
                ]})
            ),
@@ -393,6 +441,12 @@ async fn fake_adapter<S: AsyncRead + AsyncWrite + Unpin + Send + 'static>(stream
                ]})
            ),
            "continue" if script.continue_reply.is_some() => ok!(msg, script.continue_reply.clone().unwrap()),
+            "continue" if script.stop_after_continue => {
+                ok!(msg, json!({"allThreadsContinued": true}));
+                send!(
+                    json!({"type": "event", "event": "stopped", "body": {"reason": "breakpoint", "threadId": 1, "allThreadsStopped": true}})
+                );
+            }
            "continue" => {
                ok!(msg, json!({"allThreadsContinued": true}));
                send!(json!({"type": "event", "event": "exited", "body": {"exitCode": 3}}));
@@ -2155,11 +2209,13 @@ async fn attach_session_reports_capability() {
        let id = h.start(remote_attach(adapter, project.path())).await.unwrap();
        let caps = h.manager.capabilities(id).unwrap();
        assert!(caps.jvm_memory, "{adapter}");
+        assert_eq!(caps.jvm_heap, caps.jvm_memory, "{adapter}");
    }

    let id = h.start(config()).await.unwrap();
    let caps = h.manager.capabilities(id).unwrap();
    assert!(!caps.jvm_memory);
+    assert_eq!(caps.jvm_heap, caps.jvm_memory);
    assert_eq!(
        h.manager.jvm_memory_classes(id).await.unwrap(),
        JvmMemoryResult::Unavailable { reason: JvmMemoryUnavailable::NoJvmProcess, can_count_when_paused: false }
@@ -2399,6 +2455,13 @@ fn kotlin_attach(project: &std::path::Path, host: &str, port: u16) -> LaunchConf
    }
 }

+#[test]
+fn link_options_hold_only_for_fwcd() {
+    assert!(kotlin::link_options(kotlin::ADAPTER).hold_resumes);
+    assert!(!kotlin::link_options(kotlin_lsp::ADAPTER).hold_resumes);
+    assert!(!kotlin::link_options("x").hold_resumes);
+}
+
 #[tokio::test]
 async fn kotlin_session_installs_link_inspector() {
    let h = harness(Script::default());
@@ -2470,6 +2533,229 @@ async fn closing_the_session_drops_the_link() {
    assert!(session.jvm_inspector.lock().is_none());
 }

+/// kotlin-lsp's debugger, reached through the language server's `debugServer` port (the fake ignores it).
+fn kotlin_lsp_attach(project: &std::path::Path) -> LaunchConfig {
+    LaunchConfig {
+        adapter: kotlin_lsp::ADAPTER.into(),
+        request: "attach".into(),
+        cwd: Some(project.to_owned().into()),
+        extra_json: Some(
+            json!({"debugServer": 4711, "hostName": "127.0.0.1", "port": 5005, "projectRoot": project}).to_string(),
+        ),
+        ..config()
+    }
+}
+
+#[tokio::test]
+async fn kotlin_lsp_initializes_as_intellij_jvm() {
+    let project = tempfile::tempdir().unwrap();
+    for (config, adapter_id, invalidated) in [
+        (kotlin_lsp_attach(project.path()), "intellij_jvm", true),
+        (kotlin_attach(project.path(), "127.0.0.1", 5005), "kotlin-debug-adapter", false),
+    ] {
+        let h = harness(Script::default());
+        let id = h.start(config).await.unwrap();
+        let init = &h.request("initialize")["arguments"];
+        assert_eq!(init["adapterID"], adapter_id);
+        assert_eq!(init["supportsInvalidatedEvent"], invalidated, "{adapter_id}");
+        h.manager.stop(id).await.unwrap();
+    }
+}
+
+#[tokio::test]
+async fn kotlin_lsp_gets_real_paths_and_its_link_holds_nothing() {
+    let h = harness(Script::default());
+    let project = tempfile::tempdir().unwrap();
+    let path = project.path().join("Main.kt");
+    std::fs::write(&path, "package org.example\nfun main() {}\n").unwrap();
+    h.manager.set_breakpoints(path.clone(), vec![bp(1)]).await.unwrap();
+    let id = h.start(kotlin_lsp_attach(project.path())).await.unwrap();
+    assert_eq!(h.request("setBreakpoints")["arguments"]["source"]["path"], json!(path));
+    let sent = &h.request("attach")["arguments"];
+    assert_eq!(sent["projectRoot"], json!(project.path()));
+    assert!(sent.get("debugServer").is_none());
+    assert_eq!(sent["hostName"], "127.0.0.1");
+    let link_port = sent["port"].as_u64().unwrap();
+    assert!(link_port != 0 && link_port != 5005);
+    let session = h.manager.session(id).unwrap();
+    assert!(session.kotlin_mirror.lock().is_none());
+    assert!(session.jdwp_link.lock().is_some() && session.jvm_inspector.lock().is_some());
+    assert_eq!(session.attach_target.get(), Some(&("127.0.0.1".to_owned(), 5005)));
+    assert!(!kotlin::link_options(&session.adapter).hold_resumes);
+    h.manager.stop(id).await.unwrap();
+}
+
+#[tokio::test]
+async fn kotlin_lsp_waits_for_the_configuration_done_reply() {
+    let project = tempfile::tempdir().unwrap();
+    // fwcd never answers it (`kotlin_configures_without_configuration_done_response`).
+    let h = harness(Script { ignore_configuration_done: true, ..Default::default() });
+    let fwcd = h.start(kotlin_attach(project.path(), "127.0.0.1", 5005));
+    let id = tokio::time::timeout(Duration::from_secs(2), fwcd).await.unwrap().unwrap();
+    h.manager.stop(id).await.unwrap();
+
+    tokio::time::pause();
+    let h = harness(Script { ignore_configuration_done: true, ..Default::default() });
+    let started = tokio::time::Instant::now();
+    let err = h.start(kotlin_lsp_attach(project.path())).await.unwrap_err();
+    assert!(started.elapsed() >= REQUEST_TIMEOUT, "{:?}", started.elapsed());
+    assert!(err.message.contains("configurationDone"), "{err:?}");
+    assert!(h.manager.sessions(None).is_empty());
+}
+
+#[tokio::test]
+async fn kotlin_lsp_sessions_have_the_memory_tab() {
+    let h = harness(Script::default());
+    let project = tempfile::tempdir().unwrap();
+    let id = h.start(kotlin_lsp_attach(project.path())).await.unwrap();
+    assert!(h.manager.capabilities(id).unwrap().jvm_memory);
+    h.manager.stop(id).await.unwrap();
+}
+
+#[tokio::test]
+async fn losing_the_kotlin_lsp_connection_ends_the_session() {
+    let h = harness(Script { hang_up_after_stop: true, ..Script::default() });
+    let project = tempfile::tempdir().unwrap();
+    let id = h.start(kotlin_lsp_attach(project.path())).await.unwrap();
+    h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
+    let session = h.manager.session(id).unwrap();
+    assert!(session.jdwp_link.lock().is_some());
+    let _ = session.conn.request_timeout("threads", Value::Null, Duration::from_secs(2)).await;
+    h.wait_event(|e| matches!(e, DebugEvent::Terminated)).await;
+    assert!(h.manager.sessions(None).is_empty());
+    assert!(session.jdwp_link.lock().is_none());
+    assert!(session.jvm_inspector.lock().is_none());
+}
+
+/// The reasons of the first `count` stops, once that many arrived.
+async fn stop_reasons(h: &Harness, count: usize) -> Vec<String> {
+    for _ in 0..200 {
+        let reasons: Vec<String> = h
+            .events
+            .lock()
+            .iter()
+            .filter_map(|e| match e {
+                IdeEvent::Debug { event: DebugEvent::Stopped { reason, .. }, .. } => Some(reason.clone()),
+                _ => None,
+            })
+            .collect();
+        if reasons.len() >= count {
+            return reasons;
+        }
+        tokio::time::sleep(Duration::from_millis(10)).await;
+    }
+    panic!("{count} stops not received; got {:?}", h.events.lock());
+}
+
+#[tokio::test]
+async fn a_step_stop_is_reported_as_a_step() {
+    let project = tempfile::tempdir().unwrap();
+    for (config, reason) in [(kotlin_lsp_attach(project.path()), "step"), (config(), "breakpoint")] {
+        let h = harness(Script { step_reason: Some("breakpoint"), ..Script::default() });
+        let id = h.start(config).await.unwrap();
+        h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
+        h.manager.step(id, 1, StepKind::Over).await.unwrap();
+        assert_eq!(stop_reasons(&h, 2).await, ["breakpoint", reason]);
+        h.manager.stop(id).await.unwrap();
+    }
+}
+
+#[tokio::test]
+async fn a_breakpoint_after_continue_stays_a_breakpoint() {
+    let h = harness(Script { step_reason: Some("breakpoint"), stop_after_continue: true, ..Script::default() });
+    let project = tempfile::tempdir().unwrap();
+    let id = h.start(kotlin_lsp_attach(project.path())).await.unwrap();
+    h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
+    h.manager.step(id, 1, StepKind::Over).await.unwrap();
+    stop_reasons(&h, 2).await;
+    // The fake ends `stepIn` with no stop: the `continue` after it decides the next one.
+    h.manager.step(id, 1, StepKind::Into).await.unwrap();
+    h.manager.resume(id, 1).await.unwrap();
+    assert_eq!(stop_reasons(&h, 3).await, ["breakpoint", "step", "breakpoint"]);
+    h.manager.stop(id).await.unwrap();
+}
+
+#[tokio::test]
+async fn a_breakpoint_after_a_refused_step_stays_a_breakpoint() {
+    let h = harness(Script { refuse_next: true, ..Script::default() });
+    let project = tempfile::tempdir().unwrap();
+    let id = h.start(kotlin_lsp_attach(project.path())).await.unwrap();
+    h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
+    assert!(h.manager.step(id, 1, StepKind::Over).await.is_err());
+    assert_eq!(stop_reasons(&h, 2).await, ["breakpoint", "breakpoint"]);
+    h.manager.stop(id).await.unwrap();
+}
+
+#[tokio::test]
+async fn a_thread_from_an_earlier_stop_is_refused() {
+    let project = tempfile::tempdir().unwrap();
+    for (config, kotlin_lsp) in [(kotlin_lsp_attach(project.path()), true), (config(), false)] {
+        let h = harness(Script::default());
+        let id = h.start(config).await.unwrap();
+        h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
+        assert_eq!(h.manager.threads(id).await.unwrap().len(), 1);
+        let started = tokio::time::Instant::now();
+        let stale = h.manager.stack_trace(id, 99).await;
+        let asked =
+            |command: &str| h.log.lock().iter().any(|m| m["command"] == command && m["arguments"]["threadId"] == 99);
+        if kotlin_lsp {
+            assert!(stale.is_err() && started.elapsed() < Duration::from_millis(100), "{stale:?}");
+            assert!(h.manager.step(id, 99, StepKind::Over).await.is_err());
+            assert!(h.manager.resume(id, 99).await.is_err());
+            assert!(!asked("stackTrace") && !asked("next") && !asked("continue"));
+        } else {
+            assert!(stale.is_ok() && asked("stackTrace"), "{stale:?}");
+        }
+        assert!(h.manager.stack_trace(id, 1).await.is_ok());
+        h.manager.stop(id).await.unwrap();
+    }
+}
+
+#[tokio::test]
+async fn a_threads_reply_from_before_a_stop_does_not_vouch_for_its_ids() {
+    let h = harness(Script { stop_during_threads: true, ..Script::default() });
+    let project = tempfile::tempdir().unwrap();
+    let id = h.start(kotlin_lsp_attach(project.path())).await.unwrap();
+    h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
+    let threads = h.manager.threads(id).await.unwrap();
+    // M3 maps kotlin-lsp's threads by these names.
+    assert_eq!((threads[0].id, threads[0].name.as_str()), (1, "\"main\"@1"));
+    stop_reasons(&h, 2).await;
+    assert!(h.manager.stack_trace(id, 1).await.is_err());
+    assert!(h.manager.stack_trace(id, 2).await.is_ok());
+    h.manager.stop(id).await.unwrap();
+}
+
+#[tokio::test]
+async fn kotlin_lsp_frames_get_real_paths() {
+    let project = tempfile::tempdir().unwrap();
+    let at = "at com.x.AppKt.main(App.kt:13)";
+    for (config, path, name) in [
+        (kotlin_lsp_attach(project.path()), "/p/App.kt", "com.x.AppKt.main(App.kt:13)"),
+        (java_config("launch"), "file:///p/App.kt", at),
+    ] {
+        let script = Script { source_path: Some("file:///p/App.kt".into()), frame_name: Some(at), ..Script::default() };
+        let h = harness(script);
+        let id = h.start(config).await.unwrap();
+        h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
+        let frames = h.manager.stack_trace(id, 1).await.unwrap();
+        assert_eq!(frames[0].path.as_ref().map(|p| p.0.clone()), Some(PathBuf::from(path)));
+        assert_eq!(frames[0].name, name);
+        h.manager.stop(id).await.unwrap();
+    }
+}
+
+#[tokio::test]
+async fn invalidated_events_reach_the_client() {
+    let h = harness(Script { invalidated_after_stop: true, ..Script::default() });
+    let project = tempfile::tempdir().unwrap();
+    let id = h.start(kotlin_lsp_attach(project.path())).await.unwrap();
+    match h.wait_event(|e| matches!(e, DebugEvent::Invalidated { .. })).await {
+        DebugEvent::Invalidated { areas } => assert_eq!(areas, ["variables"]),
+        other => panic!("{other:?}"),
+    }
+    h.manager.stop(id).await.unwrap();
+}
 #[cfg(unix)]
 #[tokio::test]
 async fn rdbg_drains_test_output_after_dap_closes_before_killing_the_process() {
@@ -136,24 +136,19 @@ pub struct DockerRegistry {
    pub username: String,
 }

-#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
+#[derive(Clone, Debug, Default, PartialEq, Eq, Serialize, Deserialize, Type)]
 #[serde(rename_all = "camelCase")]
 pub struct DockerSettings {
-    #[serde(default = "default_connections")]
+    #[serde(default)]
    pub connections: Vec<DockerConnection>,
    #[serde(default)]
    pub registries: Vec<DockerRegistry>,
 }

-impl Default for DockerSettings {
-    fn default() -> Self {
-        Self { connections: default_connections(), registries: Vec::new() }
-    }
-}
-
-/// Before anything is configured the CLI's own daemon is shown, as before connections existed.
-fn default_connections() -> Vec<DockerConnection> {
-    vec![DockerConnection { id: "default".into(), name: "Docker".into(), endpoint: DockerEndpoint::Default }]
+/// Whether `c` is the connection older versions injected when nothing was configured:
+/// Services lists only connections the user added, so this one is dropped on load.
+fn is_injected_default(c: &DockerConnection) -> bool {
+    c.id == "default" && c.name == "Docker" && c.endpoint == DockerEndpoint::Default
 }

 const SETTINGS_FILE: &str = "docker.json";
@@ -161,10 +156,17 @@ const PASSWORDS_FILE: &str = "docker-passwords.json";

 pub fn load_settings(data_dir: &Path) -> DockerSettings {
    match std::fs::read(data_dir.join(SETTINGS_FILE)) {
-        Ok(bytes) => serde_json::from_slice(&bytes).unwrap_or_else(|e| {
-            tracing::warn!("{SETTINGS_FILE}: {e}");
-            DockerSettings::default()
-        }),
+        // A file written before the opt-in Services rework carries the injected default
+        // (saved along with a registry or another connection); drop it unless edited.
+        Ok(bytes) => serde_json::from_slice(&bytes)
+            .map(|mut s: DockerSettings| {
+                s.connections.retain(|c| !is_injected_default(c));
+                s
+            })
+            .unwrap_or_else(|e| {
+                tracing::warn!("{SETTINGS_FILE}: {e}");
+                DockerSettings::default()
+            }),
        Err(_) => DockerSettings::default(),
    }
 }
@@ -373,7 +375,8 @@ mod tests {
    fn settings_round_trip_and_passwords() {
        let tmp = tempfile::tempdir().unwrap();
        let dir = tmp.path();
-        assert_eq!(load_settings(dir).connections[0].endpoint, DockerEndpoint::Default);
+        // Nothing configured: no connection is invented.
+        assert!(load_settings(dir).connections.is_empty());
        let settings = DockerSettings {
            connections: vec![DockerConnection {
                id: "c1".into(),
@@ -395,8 +398,32 @@ mod tests {
        assert!(auth_for(dir, "postgres").is_none());
        save_settings(dir, &DockerSettings { registries: Vec::new(), ..settings }).unwrap();
        assert_eq!(registry_password(dir, "r1"), None);
-        // An empty list stays empty (the default connection is only for a missing file).
+        // An empty list stays empty.
        save_settings(dir, &DockerSettings { connections: Vec::new(), registries: Vec::new() }).unwrap();
        assert!(load_settings(dir).connections.is_empty());
    }
+
+    #[test]
+    fn load_drops_the_injected_default_connection() {
+        let tmp = tempfile::tempdir().unwrap();
+        let dir = tmp.path();
+        let injected =
+            || DockerConnection { id: "default".into(), name: "Docker".into(), endpoint: DockerEndpoint::Default };
+        let registry =
+            DockerRegistry { id: "r1".into(), name: "GHCR".into(), address: "ghcr.io".into(), username: "me".into() };
+        // Saved untouched by an older version (e.g. along with a registry): dropped on load.
+        save_settings(dir, &DockerSettings { connections: vec![injected()], registries: vec![registry.clone()] })
+            .unwrap();
+        let loaded = load_settings(dir);
+        assert!(loaded.connections.is_empty());
+        assert_eq!(loaded.registries, vec![registry]);
+        // A connection the user renamed or re-pointed stays theirs.
+        let renamed = DockerConnection { name: "Local engine".into(), ..injected() };
+        save_settings(dir, &DockerSettings { connections: vec![renamed.clone()], registries: Vec::new() }).unwrap();
+        assert_eq!(load_settings(dir).connections, vec![renamed]);
+        let repointed =
+            DockerConnection { endpoint: DockerEndpoint::Socket { path: "/var/run/docker.sock".into() }, ..injected() };
+        save_settings(dir, &DockerSettings { connections: vec![repointed.clone()], registries: Vec::new() }).unwrap();
+        assert_eq!(load_settings(dir).connections, vec![repointed]);
+    }
 }
@@ -71,7 +71,6 @@ impl Capability {
        match self {
            Self::ProjectRead | Self::EditorRead | Self::Storage | Self::Events | Self::VcsRead => Risk::Low,
            Self::EditorWrite
-            | Self::ProjectWrite
            | Self::DatabaseSources
            | Self::VcsWrite
            | Self::Net(_)
@@ -80,7 +79,14 @@ impl Capability {
            | Self::Secrets
            | Self::InputEvents
            | Self::Clipboard => Risk::Medium,
-            Self::IdeCommands | Self::Ipc(_) | Self::Process(_) | Self::FsRead(_) | Self::FsWrite(_) => Risk::High,
+            // A trusted project's own files name the programs the IDE starts (its settings, its
+            // build scripts), so writing them is running code.
+            Self::ProjectWrite
+            | Self::IdeCommands
+            | Self::Ipc(_)
+            | Self::Process(_)
+            | Self::FsRead(_)
+            | Self::FsWrite(_) => Risk::High,
        }
    }

@@ -402,6 +408,15 @@ mod tests {
        assert!(Capability::Storage.auto_migrates() && !Capability::EditorWrite.auto_migrates());
    }

+    /// A trusted project's files name programs the IDE starts by itself: the git and language
+    /// server executables in `.openidea/settings.toml`, its build scripts. Writing them is
+    /// running code, and the install dialog says so.
+    #[test]
+    fn writing_project_files_is_a_high_risk_grant() {
+        assert_eq!(Capability::ProjectWrite.risk(), Risk::High);
+        assert!(!Capability::ProjectWrite.auto_migrates());
+    }
+
    #[test]
    fn host_patterns() {
        assert!(host_matches("crates.io", "crates.io"));
@@ -352,6 +352,22 @@ pub struct IndexEntry {
    /// the IDE before showing it.
    #[serde(default)]
    pub icon: Option<PluginIcon>,
+    /// Where to read more: the manifest's homepage, else the registry's source repository.
+    #[serde(default)]
+    pub homepage: Option<String>,
+    /// This version's release notes (the manifest's `change-notes`).
+    #[serde(default)]
+    pub notes: Option<String>,
+    /// Downloads of the plugin's packages, as counted by whoever serves them.
+    #[serde(default)]
+    pub downloads: Option<u64>,
+    /// Picked by the marketplace's maintainers.
+    #[serde(default)]
+    pub featured: bool,
+    /// Project-relative paths whose presence makes the plugin worth suggesting
+    /// (`pom.xml`, `config/routes.rb`).
+    #[serde(default)]
+    pub suggest: Vec<String>,
 }

 impl IndexEntry {
@@ -389,10 +405,31 @@ impl Index {
    /// revocations, publisher keys (revoked ones) and `moved` — and lists no
    /// plugins ([`Index::is_newer`]): the IDE needs updating to install from it.
    pub fn parse(text: &str) -> Result<Self, String> {
+        let (index, dropped) = Self::parse_dropping(text)?;
+        if let Some(first) = dropped.first() {
+            // One line per index, and a bounded one: whoever wrote the index chose the text.
+            let id: String = first.id.chars().take(80).collect();
+            tracing::warn!(
+                "index: {} entries are not offered, their id or version is not one a manifest may carry (first: {id:?})",
+                dropped.len()
+            );
+        }
+        Ok(index)
+    }
+
+    /// [`Index::parse`], with the entries it does not offer: those whose id or
+    /// version no manifest may carry, so no IDE could install them.
+    pub fn parse_dropping(text: &str) -> Result<(Self, Vec<IndexEntry>), String> {
        let value: serde_json::Value = serde_json::from_str(text).map_err(|e| format!("index: {e}"))?;
        let format = value.get("format").and_then(serde_json::Value::as_u64).ok_or("index: `format` is missing")?;
        if format == u64::from(INDEX_FORMAT) {
-            return serde_json::from_value(value).map_err(|e| format!("index: {e}"));
+            let mut index: Index = serde_json::from_value(value).map_err(|e| format!("index: {e}"))?;
+            // What no manifest may carry is not offered: the id and version also name files on disk.
+            let (offered, dropped) = std::mem::take(&mut index.plugins)
+                .into_iter()
+                .partition(|e| crate::validate_plugin_id(&e.id).is_ok() && e.semver().is_some());
+            index.plugins = offered;
+            return Ok((index, dropped));
        }
        if format < u64::from(INDEX_FORMAT) {
            return Err(format!("index format {format} is not supported (this IDE reads {INDEX_FORMAT})"));
@@ -401,13 +438,14 @@ impl Index {
            let items = value.get(field).and_then(serde_json::Value::as_array);
            items.into_iter().flatten().filter_map(|v| serde_json::from_value(v.clone()).ok()).collect()
        }
-        Ok(Index {
+        let index = Index {
            format: u32::try_from(format).unwrap_or(u32::MAX),
            publishers: each(&value, "publishers"),
            plugins: Vec::new(),
            revoked: each(&value, "revoked"),
            moved: value.get("moved").and_then(serde_json::Value::as_str).map(str::to_owned),
-        })
+        };
+        Ok((index, Vec::new()))
    }

    /// Written in a format newer than this IDE reads: it lists no plugins.
@@ -685,9 +723,33 @@ mod tests {
            engine: "^1.0".into(),
            categories: Vec::new(),
            icon: None,
+            homepage: None,
+            notes: None,
+            downloads: None,
+            featured: false,
+            suggest: Vec::new(),
        }
    }

+    #[test]
+    fn listing_details_are_optional() {
+        let mut json = serde_json::to_value(entry("acme.a", "acme")).unwrap();
+        for key in ["homepage", "notes", "downloads", "featured", "suggest"] {
+            json.as_object_mut().unwrap().remove(key);
+        }
+        assert_eq!(serde_json::from_value::<IndexEntry>(json).unwrap(), entry("acme.a", "acme"));
+        let full = IndexEntry {
+            homepage: Some("https://example.com".into()),
+            notes: Some("Fixes".into()),
+            downloads: Some(42),
+            featured: true,
+            suggest: vec!["pom.xml".into()],
+            ..entry("acme.a", "acme")
+        };
+        let back: IndexEntry = serde_json::from_str(&serde_json::to_string(&full).unwrap()).unwrap();
+        assert_eq!(back, full);
+    }
+
    fn version(id: &str, version: &str, engine: &str) -> IndexEntry {
        IndexEntry { version: version.into(), engine: engine.into(), ..entry(id, "acme") }
    }
@@ -868,6 +930,51 @@ mod tests {
        }
    }

+    #[test]
+    fn an_index_offers_only_the_ids_and_versions_a_manifest_may_carry() {
+        let invalid_ids = [
+            "../x",
+            "../../escape",
+            "acme/../x",
+            r"acme.\..\x",
+            "acme./../../../escape",
+            "/abs",
+            r"C:\x",
+            "ACME.x",
+            "acme.",
+            "acme..x",
+            "acme.x y",
+            "",
+        ];
+        let invalid_versions =
+            ["../1.0.0", "1.0.0/../../../escape", r"1.0.0\..\x", "1.0.0-..", " 1.0.0", "1.0", "latest", ""];
+        let valid = [("acme.x", "1.0.0"), ("acme.tools-2_b", "1.0.0-rc.1+b.2")];
+        let mut listed: Vec<(&str, &str)> = valid.to_vec();
+        listed.extend(invalid_ids.iter().map(|id| (*id, "1.0.0")));
+        listed.extend(invalid_versions.iter().map(|version| ("acme.x", *version)));
+        let plugins: Vec<serde_json::Value> = listed
+            .iter()
+            .map(|(id, version)| {
+                serde_json::json!({
+                    "id": id, "name": "X", "version": version, "publisher": "acme",
+                    "download": "x.oiplugin", "digest": "d", "engine": "^1.0",
+                })
+            })
+            .collect();
+        let text = serde_json::json!({ "format": INDEX_FORMAT, "plugins": plugins }).to_string();
+        let pairs = |entries: &[IndexEntry]| -> Vec<(String, String)> {
+            entries.iter().map(|e| (e.id.clone(), e.version.clone())).collect()
+        };
+        let owned = |pairs: &[(&str, &str)]| -> Vec<(String, String)> {
+            pairs.iter().map(|(id, version)| ((*id).to_owned(), (*version).to_owned())).collect()
+        };
+
+        assert_eq!(pairs(&Index::parse(&text).unwrap().plugins), owned(&valid));
+        let (index, dropped) = Index::parse_dropping(&text).unwrap();
+        assert_eq!(pairs(&index.plugins), owned(&valid));
+        assert_eq!(pairs(&dropped), owned(&listed[valid.len()..]));
+    }
+
    #[test]
    fn a_newer_index_still_revokes_and_moves() {
        let newer = format!(
@@ -102,6 +102,14 @@ fn parse<T>(r: serde_json::Result<T>) -> IdeResult<T> {
    r.map_err(|e| IdeError::new(ide_core::error::ErrorKind::Protocol, format!("unexpected gh output: {e}")))
 }

+/// The repository of `root`, free to execute: the host runs the `gh_*` commands only in a
+/// trusted project.
+fn trusted_repo(root: &Path) -> IdeResult<Repo> {
+    let repo = Repo::discover(root)?.ok_or_else(|| IdeError::invalid("not a git repository"))?;
+    repo.set_execution_allowed(true);
+    Ok(repo)
+}
+
 /// Whether gh is installed and signed in, and which GitHub repository `root` maps to.
 pub fn availability(root: &Path) -> GhAvailability {
    if gh_executable().is_none() {
@@ -233,7 +241,7 @@ pub fn create(
        return Err(IdeError::invalid("choose a base branch"));
    }
    if req.push {
-        let repo = Repo::discover(root)?.ok_or_else(|| IdeError::invalid("not a git repository"))?;
+        let repo = trusted_repo(root)?;
        repo.push(false, true, cancel, on_output)?;
    }
    let mut args = vec!["pr", "create", "--title", req.title.trim(), "--body", &req.body, "--base", req.base.trim()];
@@ -354,7 +362,7 @@ pub fn prepare_diff(
    cancel: &CancellationToken,
    on_output: &dyn Fn(String),
 ) -> IdeResult<PrDiffRevisions> {
-    let repo = Repo::discover(root)?.ok_or_else(|| IdeError::invalid("not a git repository"))?;
+    let repo = trusted_repo(root)?;
    if !repo.has_commit(head_oid) || !repo.has_commit(base_oid) {
        let remotes = repo.remotes()?;
        let remote = remote_for(&remotes, name_with_owner)
@@ -0,0 +1,28 @@
+[package]
+name = "ide-heap"
+description = "HotSpot .hprof parser and heap-snapshot analysis for the debugger's JVM Memory view"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+
+[dependencies]
+ide-core.workspace = true
+memmap2.workspace = true
+serde.workspace = true
+serde_json.workspace = true
+specta.workspace = true
+thiserror.workspace = true
+tracing.workspace = true
+uuid.workspace = true
+
+[target.'cfg(unix)'.dependencies]
+libc = "0.2"
+
+[dev-dependencies]
+criterion = { version = "0.5", default-features = false }
+proptest.workspace = true
+tempfile.workspace = true
+
+[[bench]]
+name = "heap"
+harness = false
@@ -0,0 +1,100 @@
+//! `cargo bench -p ide-heap`: whole-dump analysis and the dominator tree at a million objects.
+
+use criterion::{Criterion, black_box, criterion_group, criterion_main};
+use ide_core::CancellationToken;
+use ide_heap::testing::{MiniHeap, XorShift};
+use ide_heap::{AnalyzeOptions, BasicType, HeapError, HeapPhase, HeapRootKind, Store, analyze, dominators};
+
+const CHAINS: u64 = 100_000;
+const CHAIN_LEN: u64 = 5;
+const NODES: u64 = CHAINS * CHAIN_LEN;
+/// Every object takes one slot: node `k` at slot `2k`, its payload at `2k + 1`.
+const BASE: u64 = 0x1_0000_0000;
+const SLOT: u64 = 0x20;
+
+fn node_addr(k: u64) -> u64 {
+    BASE + 2 * k * SLOT
+}
+
+fn payload_addr(k: u64) -> u64 {
+    node_addr(k) + SLOT
+}
+
+/// 100k rooted chains of five `Node { next, payload }`, each node with its own `byte[16]`. Every
+/// seventh node points at the payload of the same position in the next chain instead, so that
+/// payload has two owners and its own one is garbage: 1M objects in all.
+fn million_objects() -> MiniHeap {
+    let mut heap = MiniHeap::new();
+    heap.class("Node", Some("java.lang.Object"), &[("next", BasicType::Object), ("payload", BasicType::Object)]);
+    for k in 0..NODES {
+        let next = if (k + 1) % CHAIN_LEN == 0 { 0 } else { node_addr(k + 1) };
+        let payload = if k % 7 == 0 { payload_addr((k + CHAIN_LEN) % NODES) } else { payload_addr(k) };
+        heap.object(node_addr(k), "Node", &[("next", next), ("payload", payload)]);
+        heap.prim(payload_addr(k), BasicType::Byte, 16);
+        if k % CHAIN_LEN == 0 {
+            heap.root(HeapRootKind::JniGlobal, node_addr(k));
+        }
+    }
+    heap
+}
+
+/// CSR of a random tree on `nodes` nodes rooted at 0 plus `extra` random edges, targets of each
+/// node in scrambled order.
+fn random_graph(nodes: u32, extra: u32, seed: u64) -> (Vec<u32>, Vec<u32>) {
+    let mut rng = XorShift::new(seed);
+    let mut edges: Vec<(u32, u32)> = (1..nodes).map(|v| (rng.below(v), v)).collect();
+    edges.extend((0..extra).map(|_| (rng.below(nodes), rng.below(nodes))));
+    for i in (1..edges.len()).rev() {
+        edges.swap(i, rng.below(i as u32 + 1) as usize);
+    }
+    let mut start = vec![0u32; nodes as usize + 1];
+    for &(from, _) in &edges {
+        start[from as usize + 1] += 1;
+    }
+    for v in 0..nodes as usize {
+        start[v + 1] += start[v];
+    }
+    let mut cursor = start.clone();
+    let mut out = vec![0u32; edges.len()];
+    for &(from, to) in &edges {
+        out[cursor[from as usize] as usize] = to;
+        cursor[from as usize] += 1;
+    }
+    (start, out)
+}
+
+fn no_progress(_: HeapPhase, _: u64, _: u64) -> Result<(), HeapError> {
+    Ok(())
+}
+
+fn bench(c: &mut Criterion) {
+    let dir = tempfile::tempdir().expect("temp dir");
+    let hprof = dir.path().join("dump.hprof");
+    million_objects().write_to(&hprof);
+    let (start, out) = random_graph(1_000_000, 500_000, 0x5EED_D0D0);
+    let cancel = CancellationToken::new();
+    let opts = AnalyzeOptions { in_memory: true, ..AnalyzeOptions::default() };
+    let summary = analyze(&hprof, dir.path(), opts, &no_progress, &cancel).expect("analyze").summary;
+    assert_eq!(summary.objects, 2 * NODES, "{summary:?}");
+    assert_eq!(summary.unreachable_objects, NODES.div_ceil(7), "{summary:?}");
+
+    let mut g = c.benchmark_group("heap");
+    g.sample_size(10);
+    g.bench_function("index_1m_objects", |b| {
+        b.iter(|| {
+            let opts = AnalyzeOptions { in_memory: true, ..AnalyzeOptions::default() };
+            let index = analyze(&hprof, dir.path(), opts, &no_progress, &cancel).expect("analyze");
+            black_box(index.summary.objects)
+        })
+    });
+    g.bench_function("dominators_1m_random", |b| {
+        b.iter(|| {
+            let d = dominators(&start, &out, 0, &Store::Ram, &no_progress, &cancel).expect("dominators");
+            black_box(d.reachable)
+        })
+    });
+    g.finish();
+}
+
+criterion_group!(benches, bench);
+criterion_main!(benches);
@@ -0,0 +1,202 @@
+//! Ties the passes together: graph, dominators, shallow and retained sizes, the class table and
+//! paths to GC roots, into a [`HeapIndex`].
+
+mod classes;
+mod paths;
+mod retained;
+
+use std::collections::HashMap;
+use std::fs::File;
+use std::path::Path;
+use std::time::Instant;
+
+use ide_core::CancellationToken;
+use memmap2::Mmap;
+
+use crate::column::Store;
+use crate::dominators::{Dominators, dominators};
+use crate::error::HeapError;
+use crate::files::INDEX_FILES;
+use crate::graph::{HeapGraph, build_graph};
+use crate::index::{HeapIndex, HeapSummary, write_summary};
+use crate::progress::{CHECK_EVERY, HeapPhase, Progress};
+use crate::shallow::{HistogramEntry, ShallowModel, VmLayout};
+
+#[derive(Clone, Debug, Default)]
+pub struct AnalyzeOptions {
+    /// The JVM's class histogram from the same stop as the dump.
+    pub histogram: Option<Vec<HistogramEntry>>,
+    /// `VM.flags` output of the JVM that wrote the dump.
+    pub vm_flags: Option<String>,
+    pub java_major: Option<u32>,
+    /// Keep every array in RAM and write nothing to `index_dir`.
+    pub in_memory: bool,
+}
+
+/// Analyzes the dump at `hprof`, writing the index columns and `summary.json` into `index_dir`
+/// (which must exist and may hold the dump itself). `progress` gets every [`HeapPhase`] in order;
+/// an `Err` from it, a cancel or any other error removes every index file from `index_dir` and
+/// leaves the rest of the directory alone.
+pub fn analyze(
+    hprof: &Path,
+    index_dir: &Path,
+    opts: AnalyzeOptions,
+    progress: &dyn Fn(HeapPhase, u64, u64) -> Result<(), HeapError>,
+    cancel: &CancellationToken,
+) -> Result<HeapIndex, HeapError> {
+    let store = if opts.in_memory { Store::Ram } else { Store::Dir(index_dir.to_path_buf()) };
+    let result = run(hprof, &store, opts, progress, cancel);
+    // `run` has dropped every column by now: Windows cannot delete a mapped file.
+    if result.is_err() && !matches!(store, Store::Ram) {
+        remove_index_files(index_dir);
+    }
+    result
+}
+
+fn run(
+    hprof: &Path,
+    store: &Store,
+    opts: AnalyzeOptions,
+    report: &dyn Fn(HeapPhase, u64, u64) -> Result<(), HeapError>,
+    cancel: &CancellationToken,
+) -> Result<HeapIndex, HeapError> {
+    let started = Instant::now();
+    let progress = Progress::new(report, cancel);
+    let file = File::open(hprof)?;
+    // SAFETY: nothing writes the dump while it is analyzed or viewed: a capture finishes writing
+    // it before analysis and deletes it only with the snapshot that holds this index.
+    let dump = unsafe { Mmap::map(&file)? };
+    let graph = build_graph(&dump, store, report, cancel)?;
+    let Dominators { idom, preorder, .. } =
+        dominators(&graph.out_start, &graph.out, graph.root, store, report, cancel)?;
+
+    let nodes = u64::from(graph.root) + 1;
+    // Seven walks over the nodes, roughly: sizes, retained, child counts, child sorting, class
+    // counts and the tree walk, which visits every node twice.
+    let mut meter = Meter::start(&progress, HeapPhase::Retained, 7 * nodes)?;
+    let layout = VmLayout::from_vm_flags(opts.vm_flags.as_deref().unwrap_or(""), opts.java_major);
+    let model = ShallowModel::new(&graph, layout, opts.histogram.as_deref(), cancel)?;
+    let (shallow8, retained) = retained::sizes(&graph, &model, &idom, &preorder, store, &mut meter)?;
+    drop(preorder);
+    let (kids_start, kids) = retained::children(&idom, &retained, graph.root, store, &mut meter)?;
+    let tree = retained::Tree { idom, shallow8, retained, kids_start, kids };
+    let (classes, totals) = classes::table(&graph, &tree, store, &mut meter)?;
+    meter.finish()?;
+
+    let mut meter = Meter::start(&progress, HeapPhase::Paths, nodes + graph.out.len() as u64)?;
+    let gc_parent = paths::gc_parents(&graph, store, &mut meter)?;
+    meter.finish()?;
+
+    progress.report(HeapPhase::Saving, 0, 1)?;
+    let HeapGraph {
+        ids,
+        types,
+        offsets,
+        roots,
+        classes: class_info,
+        class_slot,
+        thread_objects,
+        weak_edges_skipped,
+        id_size,
+        ..
+    } = graph;
+    let summary = HeapSummary {
+        objects: totals.reachable_objects + totals.unreachable_objects,
+        reachable_objects: totals.reachable_objects,
+        reachable_bytes: totals.reachable_bytes,
+        unreachable_objects: totals.unreachable_objects,
+        unreachable_bytes: totals.unreachable_bytes,
+        classes: class_info.iter().filter(|c| c.id != 0).count() as u32,
+        weak_edges_skipped,
+        size_source: model.source,
+        analysis_ms: u32::try_from(started.elapsed().as_millis()).unwrap_or(u32::MAX),
+    };
+    if let Store::Dir(dir) = store {
+        write_summary(dir, &summary)?;
+    }
+    let mut root_kinds = HashMap::with_capacity(roots.len());
+    for (object, kind, serial) in roots {
+        root_kinds.entry(object).or_insert((kind, serial));
+    }
+    progress.report(HeapPhase::Saving, 1, 1)?;
+
+    let retained::Tree { idom, shallow8, retained, kids_start, kids } = tree;
+    Ok(HeapIndex {
+        hprof: dump,
+        ids,
+        types,
+        offsets,
+        shallow8,
+        retained,
+        idom,
+        kids_start,
+        kids,
+        gc_parent,
+        classes,
+        class_info,
+        class_slot,
+        roots: root_kinds,
+        thread_objects,
+        id_size,
+        summary,
+    })
+}
+
+/// Removes what an analysis may have written; a file that is not there is fine.
+fn remove_index_files(dir: &Path) {
+    for name in INDEX_FILES {
+        let path = dir.join(name);
+        if let Err(err) = std::fs::remove_file(&path)
+            && err.kind() != std::io::ErrorKind::NotFound
+        {
+            tracing::warn!("could not remove {}: {err}", path.display());
+        }
+    }
+}
+
+/// Steps of one phase: reports progress every [`CHECK_EVERY`] steps, and each loop looks at the
+/// token before its first step.
+pub(super) struct Meter<'a> {
+    progress: &'a Progress<'a>,
+    phase: HeapPhase,
+    /// An estimate; `done` is clamped to it.
+    total: u64,
+    done: u64,
+    next_report: u64,
+}
+
+impl<'a> Meter<'a> {
+    fn start(progress: &'a Progress<'a>, phase: HeapPhase, total: u64) -> Result<Self, HeapError> {
+        progress.report(phase, 0, total)?;
+        Ok(Self { progress, phase, total, done: 0, next_report: CHECK_EVERY })
+    }
+
+    pub(super) fn begin_loop(&self) -> Result<(), HeapError> {
+        self.progress.check()
+    }
+
+    pub(super) fn token(&self) -> &'a CancellationToken {
+        self.progress.token()
+    }
+
+    #[inline]
+    pub(super) fn tick(&mut self) -> Result<(), HeapError> {
+        self.advance(1)
+    }
+
+    pub(super) fn advance(&mut self, steps: u64) -> Result<(), HeapError> {
+        self.done += steps;
+        if self.done < self.next_report {
+            return Ok(());
+        }
+        self.next_report = self.done + CHECK_EVERY;
+        self.progress.report(self.phase, self.done.min(self.total), self.total)
+    }
+
+    fn finish(self) -> Result<(), HeapError> {
+        self.progress.report(self.phase, self.total, self.total)
+    }
+}
+
+#[cfg(test)]
+mod tests;
@@ -0,0 +1,117 @@
+//! The class table: counts and shallow sizes per type slot, retained sizes per type from a walk of
+//! the dominator tree, and the reachable / unreachable totals of the summary.
+
+use super::Meter;
+use super::retained::Tree;
+use crate::column::{NONE, Store};
+use crate::error::HeapError;
+use crate::graph::{HeapGraph, PRIM_SLOTS};
+use crate::hprof::BasicType;
+use crate::index::ClassStat;
+use crate::names::display_name;
+
+/// Instances and arrays only: class objects are left out.
+#[derive(Default)]
+pub(super) struct Totals {
+    pub(super) reachable_objects: u64,
+    pub(super) reachable_bytes: u64,
+    pub(super) unreachable_objects: u64,
+    pub(super) unreachable_bytes: u64,
+}
+
+pub(super) fn table(
+    graph: &HeapGraph,
+    tree: &Tree,
+    store: &Store,
+    meter: &mut Meter,
+) -> Result<(Vec<ClassStat>, Totals), HeapError> {
+    let slots = graph.classes.len() + PRIM_SLOTS as usize;
+    let mut classes: Vec<ClassStat> = (0..slots as u32)
+        .map(|slot| ClassStat { name: slot_name(graph, slot), count: 0, shallow: 0, retained: 0, unreachable_count: 0 })
+        .collect();
+    let mut totals = Totals::default();
+    meter.begin_loop()?;
+    for v in 0..graph.root as usize {
+        meter.tick()?;
+        let slot = graph.types[v];
+        let bytes = u64::from(tree.shallow8[v]) * 8;
+        let stat = &mut classes[slot as usize];
+        let instance = slot != graph.class_slot;
+        if tree.idom[v] == NONE {
+            stat.unreachable_count += 1;
+            if instance {
+                totals.unreachable_objects += 1;
+                totals.unreachable_bytes += bytes;
+            }
+        } else {
+            stat.count += 1;
+            stat.shallow += bytes;
+            if instance {
+                totals.reachable_objects += 1;
+                totals.reachable_bytes += bytes;
+            }
+        }
+    }
+    retained_by_type(graph, tree, &mut classes, store, meter)?;
+    Ok((classes, totals))
+}
+
+/// Adds to each type the retained size of its instances that have no instance of the same type
+/// above them in the dominator tree. The walk keeps no stack: it goes up through `idom` and
+/// resumes a node's children from `cursor`, while `active[t]` counts the instances of type `t` on
+/// the path from the root.
+fn retained_by_type(
+    graph: &HeapGraph,
+    tree: &Tree,
+    classes: &mut [ClassStat],
+    store: &Store,
+    meter: &mut Meter,
+) -> Result<(), HeapError> {
+    let root = graph.root;
+    let mut cursor = store.scratch::<u32>(root as usize + 1, 0)?;
+    let mut active = vec![0u32; classes.len()];
+    cursor[root as usize] = tree.kids_start[root as usize];
+    let mut v = root;
+    meter.begin_loop()?;
+    loop {
+        meter.tick()?;
+        let next = cursor[v as usize];
+        if next < tree.kids_start[v as usize + 1] {
+            cursor[v as usize] = next + 1;
+            let child = tree.kids[next as usize];
+            let slot = graph.types[child as usize] as usize;
+            if active[slot] == 0 {
+                classes[slot].retained += tree.retained[child as usize];
+            }
+            active[slot] += 1;
+            cursor[child as usize] = tree.kids_start[child as usize];
+            v = child;
+        } else if v == root {
+            return Ok(());
+        } else {
+            active[graph.types[v as usize] as usize] -= 1;
+            v = tree.idom[v as usize];
+        }
+    }
+}
+
+fn slot_name(graph: &HeapGraph, slot: u32) -> String {
+    match graph.classes.get(slot as usize) {
+        Some(class) => display_name(&class.name),
+        None => graph.prim_type(slot).map_or_else(String::new, |ty| prim_array_name(ty).to_owned()),
+    }
+}
+
+fn prim_array_name(ty: BasicType) -> &'static str {
+    match ty {
+        BasicType::Object => "java.lang.Object[]",
+        BasicType::Boolean => "boolean[]",
+        BasicType::Char => "char[]",
+        BasicType::Float => "float[]",
+        BasicType::Double => "double[]",
+        BasicType::Byte => "byte[]",
+        BasicType::Short => "short[]",
+        BasicType::Int => "int[]",
+        BasicType::Long => "long[]",
+    }
+}
@@ -0,0 +1,32 @@
+//! Parents on shortest paths from the GC roots, by breadth-first search over strong edges.
+
+use super::Meter;
+use crate::column::{Column, NONE, Store};
+use crate::error::HeapError;
+use crate::files::GC_PARENT_FILE;
+use crate::graph::HeapGraph;
+
+pub(super) fn gc_parents(graph: &HeapGraph, store: &Store, meter: &mut Meter) -> Result<Column<u32>, HeapError> {
+    let root = graph.root;
+    let nodes = root as usize + 1;
+    let mut parent = store.column::<u32>(GC_PARENT_FILE, nodes, NONE)?;
+    let mut queue = store.scratch::<u32>(nodes, 0)?;
+    parent[root as usize] = root;
+    queue[0] = root;
+    let (mut head, mut tail) = (0, 1);
+    meter.begin_loop()?;
+    while head < tail {
+        meter.tick()?;
+        let v = queue[head];
+        head += 1;
+        for &w in graph.out_edges(v) {
+            meter.tick()?;
+            if parent[w as usize] == NONE {
+                parent[w as usize] = v;
+                queue[tail] = w;
+                tail += 1;
+            }
+        }
+    }
+    Ok(parent)
+}
@@ -0,0 +1,209 @@
+//! Shallow and retained sizes, and the dominator tree as child lists sorted by retained size.
+
+use std::cmp::Reverse;
+
+use super::Meter;
+use crate::column::{Column, NONE, Store};
+use crate::error::HeapError;
+use crate::files::{KIDS_FILE, KIDS_START_FILE, RETAINED_FILE, SHALLOW8_FILE};
+use crate::graph::{HeapGraph, accumulate};
+use crate::progress::CHECK_EVERY;
+use crate::shallow::ShallowModel;
+
+/// The dominator tree with sizes; see [`crate::HeapIndex`] for each column.
+pub(super) struct Tree {
+    pub(super) idom: Column<u32>,
+    pub(super) shallow8: Column<u32>,
+    pub(super) retained: Column<u64>,
+    pub(super) kids_start: Column<u32>,
+    pub(super) kids: Column<u32>,
+}
+
+/// `(shallow8, retained)` of every node, the root included. `preorder` is the DFS preorder of the
+/// reachable nodes, from the root.
+pub(super) fn sizes(
+    graph: &HeapGraph,
+    model: &ShallowModel,
+    idom: &[u32],
+    preorder: &[u32],
+    store: &Store,
+    meter: &mut Meter,
+) -> Result<(Column<u32>, Column<u64>), HeapError> {
+    let nodes = idom.len();
+    let mut shallow8 = store.column::<u32>(SHALLOW8_FILE, nodes, 0)?;
+    let mut retained = store.column::<u64>(RETAINED_FILE, nodes, 0)?;
+    meter.begin_loop()?;
+    for v in 0..graph.root {
+        meter.tick()?;
+        let units = u32::try_from(model.size_of(graph, v).div_ceil(8)).unwrap_or(u32::MAX);
+        shallow8[v as usize] = units;
+        if idom[v as usize] != NONE {
+            retained[v as usize] = u64::from(units) * 8;
+        }
+    }
+    // A dominator is a DFS ancestor, so in reverse preorder every node is complete before it is
+    // added to its dominator.
+    meter.begin_loop()?;
+    for &v in preorder.iter().skip(1).rev() {
+        meter.tick()?;
+        let own = retained[v as usize];
+        retained[idom[v as usize] as usize] += own;
+    }
+    Ok((shallow8, retained))
+}
+
+/// `(kids_start, kids)`: the children of every reachable node in the dominator tree, as CSR.
+pub(super) fn children(
+    idom: &[u32],
+    retained: &[u64],
+    root: u32,
+    store: &Store,
+    meter: &mut Meter,
+) -> Result<(Column<u32>, Column<u32>), HeapError> {
+    let nodes = idom.len();
+    // Counted into `starts[d + 1]`; filled through `starts[d]` as a cursor, which leaves it at d's
+    // end until the column is shifted one slot.
+    let mut starts = store.column::<u32>(KIDS_START_FILE, nodes + 1, 0)?;
+    let mut longest = 0;
+    meter.begin_loop()?;
+    for (v, &d) in idom.iter().enumerate() {
+        meter.tick()?;
+        if d != NONE && v != root as usize {
+            let count = &mut starts[d as usize + 1];
+            *count += 1;
+            longest = longest.max(*count);
+        }
+    }
+    let total = accumulate(&mut starts, meter.token())?;
+    let mut kids = store.column::<u32>(KIDS_FILE, total as usize, 0)?;
+    meter.begin_loop()?;
+    for (v, &d) in idom.iter().enumerate() {
+        meter.tick()?;
+        if d != NONE && v != root as usize {
+            let cursor = &mut starts[d as usize];
+            kids[*cursor as usize] = v as u32;
+            *cursor += 1;
+        }
+    }
+    starts.copy_within(0..nodes, 1);
+    starts[0] = 0;
+    sort_children(&mut kids, &starts, retained, longest as usize, CHECK_EVERY as usize, store, meter)?;
+    Ok((starts, kids))
+}
+
+/// Sorts each child list by retained size descending, then by node. A list longer than `run` is
+/// sorted in runs of `run` that are then merged, so no single step takes longer than one run.
+fn sort_children(
+    kids: &mut [u32],
+    starts: &[u32],
+    retained: &[u64],
+    longest: usize,
+    run: usize,
+    store: &Store,
+    meter: &mut Meter,
+) -> Result<(), HeapError> {
+    let key = |&k: &u32| (Reverse(retained[k as usize]), k);
+    let mut buffer = if longest > run { store.scratch::<u32>(longest, 0)? } else { Column::ram(0, 0) };
+    meter.begin_loop()?;
+    for v in 0..starts.len() - 1 {
+        meter.tick()?;
+        let list = &mut kids[starts[v] as usize..starts[v + 1] as usize];
+        if list.len() <= run {
+            list.sort_unstable_by_key(key);
+            meter.advance(list.len() as u64)?;
+            continue;
+        }
+        for chunk in list.chunks_mut(run) {
+            meter.begin_loop()?;
+            chunk.sort_unstable_by_key(key);
+            meter.advance(chunk.len() as u64)?;
+        }
+        let len = list.len();
+        let (mut from, mut to) = (list, &mut buffer[..len]);
+        let mut in_buffer = false;
+        let mut width = run;
+        while width < len {
+            meter.begin_loop()?;
+            for start in (0..len).step_by(2 * width) {
+                let mid = (start + width).min(len);
+                let end = (start + 2 * width).min(len);
+                merge(&from[start..mid], &from[mid..end], &mut to[start..end], &key, meter)?;
+            }
+            std::mem::swap(&mut from, &mut to);
+            in_buffer = !in_buffer;
+            width *= 2;
+        }
+        if in_buffer {
+            to.copy_from_slice(from);
+        }
+    }
+    Ok(())
+}
+
+fn merge<K: Ord>(
+    left: &[u32],
+    right: &[u32],
+    out: &mut [u32],
+    key: &impl Fn(&u32) -> K,
+    meter: &mut Meter,
+) -> Result<(), HeapError> {
+    let (mut i, mut j) = (0, 0);
+    for slot in out.iter_mut() {
+        meter.tick()?;
+        let take_left = j == right.len() || (i < left.len() && key(&left[i]) <= key(&right[j]));
+        if take_left {
+            *slot = left[i];
+            i += 1;
+        } else {
+            *slot = right[j];
+            j += 1;
+        }
+    }
+    Ok(())
+}
+
+#[cfg(test)]
+mod tests {
+    use ide_core::CancellationToken;
+
+    use super::*;
+    use crate::error::HeapError;
+    use crate::progress::{HeapPhase, Progress};
+    use crate::testing::XorShift;
+
+    fn sorted_with_run(lists: &[Vec<u32>], retained: &[u64], run: usize) -> Vec<u32> {
+        let report = |_, _, _| Ok::<(), HeapError>(());
+        let cancel = CancellationToken::new();
+        let progress = Progress::new(&report, &cancel);
+        let mut meter = Meter::start(&progress, HeapPhase::Retained, 1).unwrap();
+        let mut starts = vec![0u32];
+        for list in lists {
+            starts.push(starts.last().unwrap() + list.len() as u32);
+        }
+        let mut kids: Vec<u32> = lists.concat();
+        let longest = lists.iter().map(Vec::len).max().unwrap_or(0);
+        sort_children(&mut kids, &starts, retained, longest, run, &Store::Ram, &mut meter).unwrap();
+        kids
+    }
+
+    #[test]
+    fn long_child_lists_are_merged_from_sorted_runs() {
+        let mut rng = XorShift::new(7);
+        let retained: Vec<u64> = (0..500).map(|_| u64::from(rng.below(40))).collect();
+        let mut nodes: Vec<u32> = (0..500).collect();
+        for i in (1..nodes.len()).rev() {
+            nodes.swap(i, rng.below(i as u32 + 1) as usize);
+        }
+        // Lists below, at and above the run length, and one that ends on a partial run.
+        let lists = vec![nodes[..3].to_vec(), nodes[3..7].to_vec(), nodes[7..400].to_vec(), nodes[400..].to_vec()];
+        for run in [1, 4, 7, 64, 1000] {
+            let mut expected = Vec::new();
+            for list in &lists {
+                let mut list = list.clone();
+                list.sort_by_key(|&k| (Reverse(retained[k as usize]), k));
+                expected.extend(list);
+            }
+            assert_eq!(sorted_with_run(&lists, &retained, run), expected, "run {run}");
+        }
+    }
+}
@@ -0,0 +1,265 @@
+use std::cell::Cell;
+use std::collections::BTreeSet;
+use std::path::PathBuf;
+
+use super::*;
+use crate::column::{Column, NONE};
+use crate::files::INDEX_FILES;
+use crate::hprof::{BasicType, HeapRootKind};
+use crate::index::{ClassStat, HeapSummary};
+use crate::shallow::SizeSource;
+use crate::testing::{MiniHeap, sample};
+
+const DUMP: &str = "dump.hprof";
+const ROOT: Option<&str> = Some("java.lang.Object");
+const NODE_FIELDS: [(&str, BasicType); 2] = [("next", BasicType::Object), ("v", BasicType::Long)];
+
+fn no_progress(_: HeapPhase, _: u64, _: u64) -> Result<(), HeapError> {
+    Ok(())
+}
+
+fn in_memory() -> AnalyzeOptions {
+    AnalyzeOptions { in_memory: true, ..AnalyzeOptions::default() }
+}
+
+/// A temp dir holding `heap` as `dump.hprof`, the way a capture lays out its snapshot dir.
+fn dump_dir(heap: &MiniHeap) -> (tempfile::TempDir, PathBuf) {
+    let dir = tempfile::tempdir().unwrap();
+    let dump = dir.path().join(DUMP);
+    heap.write_to(&dump);
+    (dir, dump)
+}
+
+fn analyze_with(heap: &MiniHeap, opts: AnalyzeOptions) -> HeapIndex {
+    let (dir, dump) = dump_dir(heap);
+    analyze(&dump, dir.path(), opts, &no_progress, &CancellationToken::new()).unwrap()
+}
+
+fn file_names(dir: &Path) -> BTreeSet<String> {
+    std::fs::read_dir(dir).unwrap().map(|e| e.unwrap().file_name().into_string().unwrap()).collect()
+}
+
+fn node(index: &HeapIndex, addr: u64) -> u32 {
+    index.ids.rank(addr).unwrap_or_else(|| panic!("{addr:#x} is not in the dump"))
+}
+
+fn shallow(index: &HeapIndex, addr: u64) -> u64 {
+    u64::from(index.shallow8[node(index, addr) as usize]) * 8
+}
+
+fn retained(index: &HeapIndex, addr: u64) -> u64 {
+    index.retained[node(index, addr) as usize]
+}
+
+fn idom(index: &HeapIndex, addr: u64) -> u32 {
+    index.idom[node(index, addr) as usize]
+}
+
+fn class<'a>(index: &'a HeapIndex, name: &str) -> &'a ClassStat {
+    let mut rows = index.classes.iter().filter(|c| c.name == name);
+    let row = rows.next().unwrap_or_else(|| panic!("no class {name}"));
+    assert!(rows.next().is_none(), "two classes named {name}");
+    row
+}
+
+fn stat(c: &ClassStat) -> (u64, u64, u64, u64) {
+    (c.count, c.shallow, c.retained, c.unreachable_count)
+}
+
+fn kids_of(index: &HeapIndex, v: u32) -> &[u32] {
+    &index.kids[index.kids_start[v as usize] as usize..index.kids_start[v as usize + 1] as usize]
+}
+
+const H: u64 = 0x1000;
+const N1: u64 = 0x1100;
+const N2: u64 = 0x1200;
+const N3: u64 = 0x1300;
+const L: u64 = 0x1400;
+const R: u64 = 0x1500;
+const W: u64 = 0x1600;
+const N4: u64 = 0x1700;
+
+#[test]
+fn sample_retained_sizes() {
+    let index = analyze_with(&sample(), in_memory());
+    let shallows: Vec<u64> = [H, N1, L, W, R].iter().map(|&a| shallow(&index, a)).collect();
+    assert_eq!(shallows, [24, 24, 32, 24, 32]);
+    let retained_sizes: Vec<u64> = [L, N3, N1, N2, H, W].iter().map(|&a| retained(&index, a)).collect();
+    assert_eq!(retained_sizes, [32, 56, 24, 24, 72, 24]);
+    let root = index.root();
+    assert_eq!(
+        [idom(&index, N1), idom(&index, N2), idom(&index, N3), idom(&index, L)],
+        [node(&index, H), node(&index, H), root, node(&index, N3)]
+    );
+    assert_eq!((idom(&index, R), idom(&index, N4)), (NONE, NONE));
+    assert_eq!((retained(&index, R), retained(&index, N4)), (0, 0));
+
+    // Children by retained size descending, ties by node.
+    assert_eq!(kids_of(&index, node(&index, H)), [node(&index, N1), node(&index, N2)]);
+    let top = kids_of(&index, root);
+    assert_eq!(top[..2], [node(&index, H), node(&index, N3)]);
+    assert!(top.windows(2).all(|p| (index.retained[p[0] as usize], p[1]) > (index.retained[p[1] as usize], p[0])));
+    assert_eq!(index.retained[root as usize], top.iter().map(|&k| index.retained[k as usize]).sum::<u64>());
+}
+
+#[test]
+fn sample_class_table() {
+    let index = analyze_with(&sample(), in_memory());
+    assert_eq!(stat(class(&index, "Node")), (3, 72, 104, 1));
+    assert_eq!(stat(class(&index, "Holder")), (1, 24, 72, 0));
+    assert_eq!(stat(class(&index, "long[]")), (1, 32, 32, 0));
+    assert_eq!(stat(class(&index, "java.lang.ref.WeakReference")), (1, 24, 24, 0));
+    let objects = class(&index, "java.lang.Object[]");
+    assert_eq!((objects.count, objects.unreachable_count), (0, 1));
+    // Indexed by type slot, primitive array slots included.
+    assert_eq!(index.classes.len(), index.class_info.len() + crate::graph::PRIM_SLOTS as usize);
+    let slot = index.types[node(&index, H) as usize] as usize;
+    assert_eq!(index.classes[slot].name, "Holder");
+    assert_eq!(index.class_info[slot].name, "Holder");
+}
+
+#[test]
+fn sample_summary() {
+    let index = analyze_with(&sample(), in_memory());
+    let s = &index.summary;
+    assert_eq!(
+        (s.reachable_objects, s.reachable_bytes, s.unreachable_objects, s.unreachable_bytes, s.weak_edges_skipped),
+        (6, 152, 2, 56, 1)
+    );
+    assert_eq!(s.objects, 8);
+    assert_eq!(s.classes, 7);
+    assert_eq!(s.size_source, SizeSource::Layout);
+}
+
+#[test]
+fn sample_gc_parents() {
+    let index = analyze_with(&sample(), in_memory());
+    let parent = |addr| index.gc_parent[node(&index, addr) as usize];
+    let root = index.root();
+    assert_eq!(index.gc_parent[root as usize], root);
+    assert_eq!([parent(H), parent(N3), parent(W)], [root; 3]);
+    assert_eq!([parent(N1), parent(L)], [node(&index, H), node(&index, N3)]);
+    assert_eq!((parent(R), parent(N4)), (NONE, NONE));
+    assert_eq!(index.roots[&node(&index, N3)], (HeapRootKind::JavaFrame, Some(1)));
+}
+
+#[test]
+fn cycle_is_retained_once() {
+    let mut heap = MiniHeap::new();
+    heap.class("Node", ROOT, &NODE_FIELDS)
+        .object(0xA000, "Node", &[("next", 0xB000)])
+        .object(0xB000, "Node", &[("next", 0xA000)])
+        .root(HeapRootKind::JniGlobal, 0xA000);
+    let index = analyze_with(&heap, in_memory());
+    assert_eq!((retained(&index, 0xA000), retained(&index, 0xB000)), (48, 24));
+    assert_eq!(class(&index, "Node").retained, 48);
+}
+
+#[test]
+fn deep_chain_retained_by_class() {
+    // A small stack proves no pass recurses along the chain.
+    std::thread::Builder::new()
+        .stack_size(256 << 10)
+        .spawn(|| {
+            const NODES: u64 = 1_000_000;
+            let addr = |i: u64| 0x10_0000 + i * 0x100;
+            let mut heap = MiniHeap::new();
+            heap.class("Node", ROOT, &NODE_FIELDS);
+            for i in 0..NODES {
+                let next = if i + 1 < NODES { addr(i + 1) } else { 0 };
+                heap.object(addr(i), "Node", &[("next", next)]);
+            }
+            heap.root(HeapRootKind::JniGlobal, addr(0));
+            let index = analyze_with(&heap, in_memory());
+            assert_eq!(retained(&index, addr(0)), 24_000_000);
+            assert_eq!(retained(&index, addr(NODES - 1)), 24);
+            assert_eq!(class(&index, "Node").retained, 24_000_000);
+            assert_eq!(index.summary.reachable_objects, NODES);
+        })
+        .unwrap()
+        .join()
+        .unwrap();
+}
+
+#[test]
+fn histogram_sizes_flow_into_retained() {
+    let histogram = vec![HistogramEntry { name: "Node".to_owned(), instances: 3, bytes: 96 }];
+    let index = analyze_with(&sample(), AnalyzeOptions { histogram: Some(histogram), ..in_memory() });
+    assert_eq!(shallow(&index, N3), 32);
+    assert_eq!(retained(&index, N3), 64);
+    assert_eq!(index.summary.size_source, SizeSource::Jvm);
+}
+
+#[test]
+fn vm_flags_of_an_unknown_jdk_set_the_layout() {
+    // Without compressed oops a Node is 12 + 8 + 8 = 28 → 32.
+    let opts = AnalyzeOptions { vm_flags: Some("-XX:MaxHeapSize=42949672960".to_owned()), ..in_memory() };
+    let index = analyze_with(&sample(), opts);
+    assert_eq!(shallow(&index, N4), 32);
+}
+
+#[test]
+fn cancel_stops_analysis() {
+    let (dir, dump) = dump_dir(&sample());
+    let cancel = CancellationToken::new();
+    let phases = Cell::new(Vec::new());
+    let progress = |phase, _, _| {
+        let mut seen = phases.take();
+        seen.push(phase);
+        phases.set(seen);
+        if phase == HeapPhase::Dominators {
+            cancel.cancel();
+        }
+        Ok(())
+    };
+    let result = analyze(&dump, dir.path(), AnalyzeOptions::default(), &progress, &cancel);
+    assert!(matches!(result, Err(HeapError::Cancelled)), "{:?}", result.err());
+    assert_eq!(phases.take().last(), Some(&HeapPhase::Dominators), "stops at the first check");
+    // The dump the capture analyzes in place stays; every file the analysis wrote is gone.
+    assert_eq!(file_names(dir.path()), BTreeSet::from([DUMP.to_owned()]));
+}
+
+#[test]
+fn progress_error_stops_analysis_and_removes_its_files() {
+    let (dir, dump) = dump_dir(&sample());
+    // The last report, once every index file is written.
+    let progress = |phase, done, _| match (phase, done) {
+        (HeapPhase::Saving, 1) => Err(HeapError::NotEnoughDiskSpace { needed: 2, available: 1 }),
+        _ => Ok(()),
+    };
+    let result = analyze(&dump, dir.path(), AnalyzeOptions::default(), &progress, &CancellationToken::new());
+    assert!(matches!(result, Err(HeapError::NotEnoughDiskSpace { .. })), "{:?}", result.err());
+    assert_eq!(file_names(dir.path()), BTreeSet::from([DUMP.to_owned()]));
+}
+
+#[test]
+fn writes_index_files() {
+    let (dir, dump) = dump_dir(&sample());
+    let index = analyze(&dump, dir.path(), AnalyzeOptions::default(), &no_progress, &CancellationToken::new()).unwrap();
+    let names = file_names(dir.path());
+    for name in [
+        "types.u32",
+        "shallow8.u32",
+        "retained.u64",
+        "idom.u32",
+        "kids_start.u32",
+        "kids.u32",
+        "gc_parent.u32",
+        "offsets.u64",
+        "summary.json",
+    ] {
+        assert!(names.contains(name), "{name} missing from {names:?}");
+    }
+    assert!(names.iter().any(|n| n.starts_with("ids.")), "{names:?}");
+    // Nothing but the index files and the dump: scratch arrays are gone.
+    let unexpected: Vec<_> = names.iter().filter(|n| *n != DUMP && !INDEX_FILES.contains(&n.as_str())).collect();
+    assert!(unexpected.is_empty(), "{unexpected:?}");
+
+    let summary: HeapSummary =
+        serde_json::from_slice(&std::fs::read(dir.path().join("summary.json")).unwrap()).unwrap();
+    assert_eq!(summary, index.summary);
+    drop(index);
+    let retained = Column::<u64>::open(&dir.path().join("retained.u64")).unwrap();
+    let in_ram = analyze_with(&sample(), in_memory());
+    assert_eq!(&*retained, &*in_ram.retained);
+}
@@ -0,0 +1,306 @@
+//! Fixed-width arrays that live in RAM or in memory-mapped files, so the analysis arrays of a
+//! large heap do not count against the process's anonymous memory.
+
+use std::fs::{File, OpenOptions};
+use std::io;
+use std::marker::PhantomData;
+use std::mem::size_of;
+use std::ops::{Deref, DerefMut};
+use std::path::{Path, PathBuf};
+
+use memmap2::{Mmap, MmapMut};
+
+/// Index value meaning "no object" in every `u32` column.
+pub const NONE: u32 = u32::MAX;
+
+/// # Safety
+/// Every bit pattern of `Self` is a valid value and `Self` has no padding, so a mapped file's
+/// bytes can be viewed as `[Self]` and a file can be written from one.
+pub unsafe trait Pod: Copy + 'static {}
+
+unsafe impl Pod for u8 {}
+unsafe impl Pod for u32 {}
+unsafe impl Pod for u64 {}
+
+enum Backing<T> {
+    Ram(Vec<T>),
+    Map(MmapMut),
+    ReadOnly(Mmap),
+}
+
+/// A fixed-length array of `T`. File contents use the machine's byte order: the arrays are a
+/// cache for this machine and are never moved to another one.
+pub struct Column<T: Pod> {
+    backing: Backing<T>,
+    /// Scratch file to delete on drop where it could not be unlinked while mapped.
+    delete_on_drop: Option<PathBuf>,
+    _marker: PhantomData<T>,
+}
+
+fn byte_len<T: Pod>(len: usize) -> io::Result<usize> {
+    len.checked_mul(size_of::<T>())
+        .filter(|&bytes| bytes <= isize::MAX as usize)
+        .ok_or_else(|| io::Error::new(io::ErrorKind::InvalidInput, "column is too long"))
+}
+
+fn is_zero<T: Pod>(value: &T) -> bool {
+    // SAFETY: `Pod` types have no padding, so all `size_of::<T>()` bytes are initialized.
+    let bytes = unsafe { std::slice::from_raw_parts((value as *const T).cast::<u8>(), size_of::<T>()) };
+    bytes.iter().all(|&b| b == 0)
+}
+
+impl<T: Pod> Column<T> {
+    fn new(backing: Backing<T>, delete_on_drop: Option<PathBuf>) -> Self {
+        Self { backing, delete_on_drop, _marker: PhantomData }
+    }
+
+    pub fn ram(len: usize, fill: T) -> Self {
+        Self::new(Backing::Ram(vec![fill; len]), None)
+    }
+
+    /// Creates (or truncates) `path` and maps it; the file stays after the column is dropped.
+    pub fn file(path: &Path, len: usize, fill: T) -> io::Result<Self> {
+        let bytes = byte_len::<T>(len)?;
+        let file = OpenOptions::new().read(true).write(true).create(true).truncate(true).open(path)?;
+        match Self::map_new(&file, len, bytes, fill) {
+            Ok(column) => Ok(column),
+            Err(err) => {
+                drop(file);
+                let _ = std::fs::remove_file(path);
+                Err(err)
+            }
+        }
+    }
+
+    /// A temporary column in `dir` that never outlives the process. On unix the file is unlinked
+    /// right after mapping, so even a crash leaves nothing behind; elsewhere (Windows cannot delete
+    /// a mapped file) it is deleted on drop.
+    pub fn scratch(dir: &Path, len: usize, fill: T) -> io::Result<Self> {
+        let bytes = byte_len::<T>(len)?;
+        if bytes == 0 {
+            return Ok(Self::ram(0, fill));
+        }
+        let path = dir.join(format!("scratch-{}.tmp", uuid::Uuid::new_v4().simple()));
+        let file = OpenOptions::new().read(true).write(true).create_new(true).open(&path)?;
+        let mut column = match Self::map_new(&file, len, bytes, fill) {
+            Ok(column) => column,
+            Err(err) => {
+                drop(file);
+                let _ = std::fs::remove_file(&path);
+                return Err(err);
+            }
+        };
+        // If the unlink fails the drop-time delete is the fallback, so the file is never left behind.
+        if !cfg!(unix) || std::fs::remove_file(&path).is_err() {
+            column.delete_on_drop = Some(path);
+        }
+        Ok(column)
+    }
+
+    /// Maps an existing file read-only; writing through the column panics.
+    pub fn open(path: &Path) -> io::Result<Self> {
+        let file = File::open(path)?;
+        let bytes = file.metadata()?.len();
+        if bytes % size_of::<T>() as u64 != 0 {
+            return Err(io::Error::new(
+                io::ErrorKind::InvalidData,
+                format!("{} is {bytes} bytes, not a multiple of {}", path.display(), size_of::<T>()),
+            ));
+        }
+        if bytes == 0 {
+            return Ok(Self::ram(0, zero_value()));
+        }
+        // SAFETY: the file is private to the snapshot directory; nothing truncates it while mapped.
+        let map = unsafe { Mmap::map(&file)? };
+        Ok(Self::new(Backing::ReadOnly(map), None))
+    }
+
+    fn map_new(file: &File, len: usize, bytes: usize, fill: T) -> io::Result<Self> {
+        if bytes == 0 {
+            return Ok(Self::ram(0, fill));
+        }
+        file.set_len(bytes as u64)?;
+        // SAFETY: as in `open`; the file was just created by this process.
+        let map = unsafe { MmapMut::map_mut(file)? };
+        let mut column = Self::new(Backing::Map(map), None);
+        // A fresh file reads as zeros, and writing a zero fill would fault in every page.
+        if !is_zero(&fill) {
+            debug_assert_eq!(column.len(), len);
+            column.fill(fill);
+        }
+        Ok(column)
+    }
+}
+
+fn zero_value<T: Pod>() -> T {
+    // SAFETY: every bit pattern of a `Pod` type is a valid value.
+    unsafe { std::mem::zeroed() }
+}
+
+impl<T: Pod> Deref for Column<T> {
+    type Target = [T];
+
+    fn deref(&self) -> &[T] {
+        match &self.backing {
+            Backing::Ram(v) => v,
+            // SAFETY: maps are page-aligned, `T` is `Pod` and the length is a multiple of its width.
+            Backing::Map(m) => unsafe { std::slice::from_raw_parts(m.as_ptr().cast(), m.len() / size_of::<T>()) },
+            Backing::ReadOnly(m) => unsafe { std::slice::from_raw_parts(m.as_ptr().cast(), m.len() / size_of::<T>()) },
+        }
+    }
+}
+
+impl<T: Pod> DerefMut for Column<T> {
+    fn deref_mut(&mut self) -> &mut [T] {
+        match &mut self.backing {
+            Backing::Ram(v) => v,
+            // SAFETY: as in `deref`; `&mut self` makes the access exclusive.
+            Backing::Map(m) => unsafe {
+                std::slice::from_raw_parts_mut(m.as_mut_ptr().cast(), m.len() / size_of::<T>())
+            },
+            Backing::ReadOnly(_) => panic!("column opened from a file is read-only"),
+        }
+    }
+}
+
+impl<T: Pod> Drop for Column<T> {
+    fn drop(&mut self) {
+        if let Some(path) = self.delete_on_drop.take() {
+            // Unmap before deleting: Windows refuses to delete a mapped file.
+            self.backing = Backing::Ram(Vec::new());
+            let _ = std::fs::remove_file(path);
+        }
+    }
+}
+
+/// Where a computation puts its arrays: result columns are named files in `Dir`, temporary arrays
+/// are scratch columns in the same directory.
+pub enum Store {
+    Ram,
+    Dir(PathBuf),
+}
+
+impl Store {
+    /// `name` is the whole file name (`types.u32`); it is used as given.
+    pub fn column<T: Pod>(&self, name: &str, len: usize, fill: T) -> io::Result<Column<T>> {
+        match self {
+            Store::Ram => Ok(Column::ram(len, fill)),
+            Store::Dir(dir) => Column::file(&dir.join(name), len, fill),
+        }
+    }
+
+    pub fn scratch<T: Pod>(&self, len: usize, fill: T) -> io::Result<Column<T>> {
+        match self {
+            Store::Ram => Ok(Column::ram(len, fill)),
+            Store::Dir(dir) => Column::scratch(dir, len, fill),
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn dir_is_empty(dir: &Path) -> bool {
+        std::fs::read_dir(dir).unwrap().next().is_none()
+    }
+
+    #[test]
+    fn file_column_round_trips() {
+        let dir = tempfile::tempdir().unwrap();
+        let path = dir.path().join("x.u32");
+        {
+            let mut col = Column::<u32>::file(&path, 4, 7).unwrap();
+            assert_eq!(&*col, &[7, 7, 7, 7]);
+            col.copy_from_slice(&[1, 2, 3, 4]);
+        }
+        let col = Column::<u32>::open(&path).unwrap();
+        assert_eq!(&*col, &[1, 2, 3, 4]);
+    }
+
+    #[test]
+    fn scratch_column_leaves_no_file() {
+        let dir = tempfile::tempdir().unwrap();
+        {
+            let mut col = Column::<u64>::scratch(dir.path(), 1024, 9).unwrap();
+            col[1023] = 5;
+            assert_eq!((col[0], col[1023]), (9, 5));
+            // Windows cannot delete a mapped file, so only unix unlinks while the map is alive.
+            #[cfg(unix)]
+            assert!(dir_is_empty(dir.path()));
+        }
+        assert!(dir_is_empty(dir.path()));
+    }
+
+    #[test]
+    fn zero_fill_and_non_zero_fill() {
+        let dir = tempfile::tempdir().unwrap();
+        let zeros = Column::<u64>::file(&dir.path().join("z.u64"), 3000, 0).unwrap();
+        assert!(zeros.iter().all(|&v| v == 0));
+        let ones = Column::<u8>::file(&dir.path().join("o.u8"), 10_000, 0xAB).unwrap();
+        assert!(ones.iter().all(|&v| v == 0xAB));
+        let ram = Column::<u32>::ram(5, NONE);
+        assert_eq!(&*ram, &[NONE; 5]);
+    }
+
+    #[test]
+    fn empty_columns_work_everywhere() {
+        let dir = tempfile::tempdir().unwrap();
+        let path = dir.path().join("e.u32");
+        assert_eq!(Column::<u32>::ram(0, 1).len(), 0);
+        assert_eq!(Column::<u32>::file(&path, 0, 1).unwrap().len(), 0);
+        assert_eq!(Column::<u32>::open(&path).unwrap().len(), 0);
+        assert_eq!(Column::<u32>::scratch(dir.path(), 0, 1).unwrap().len(), 0);
+    }
+
+    #[test]
+    fn open_rejects_a_length_that_is_not_a_multiple_of_the_width() {
+        let dir = tempfile::tempdir().unwrap();
+        let path = dir.path().join("odd.u32");
+        std::fs::write(&path, [0u8; 6]).unwrap();
+        let err = Column::<u32>::open(&path).err().unwrap();
+        assert_eq!(err.kind(), io::ErrorKind::InvalidData);
+    }
+
+    #[test]
+    fn file_rejects_a_byte_length_that_overflows() {
+        let dir = tempfile::tempdir().unwrap();
+        let err = Column::<u64>::file(&dir.path().join("big.u64"), usize::MAX, 0).err().unwrap();
+        assert_eq!(err.kind(), io::ErrorKind::InvalidInput);
+        assert!(dir_is_empty(dir.path()));
+    }
+
+    #[test]
+    #[should_panic(expected = "read-only")]
+    fn opened_columns_are_read_only() {
+        let dir = tempfile::tempdir().unwrap();
+        let path = dir.path().join("r.u32");
+        drop(Column::<u32>::file(&path, 2, 0).unwrap());
+        let mut col = Column::<u32>::open(&path).unwrap();
+        col[0] = 1;
+    }
+
+    #[test]
+    fn store_names_files_exactly_as_given() {
+        let dir = tempfile::tempdir().unwrap();
+        let store = Store::Dir(dir.path().to_path_buf());
+        let mut col = store.column::<u32>("types.u32", 3, 0).unwrap();
+        col[2] = 8;
+        drop(col);
+        let names: Vec<_> =
+            std::fs::read_dir(dir.path()).unwrap().map(|e| e.unwrap().file_name().into_string().unwrap()).collect();
+        assert_eq!(names, ["types.u32"]);
+        assert_eq!(&*Column::<u32>::open(&dir.path().join("types.u32")).unwrap(), &[0, 0, 8]);
+    }
+
+    #[test]
+    fn store_scratch_is_anonymous_and_ram_store_touches_no_disk() {
+        let dir = tempfile::tempdir().unwrap();
+        let store = Store::Dir(dir.path().to_path_buf());
+        drop(store.scratch::<u32>(16, 1).unwrap());
+        assert!(dir_is_empty(dir.path()));
+        let ram = Store::Ram.column::<u8>("ignored.u8", 4, 2).unwrap();
+        assert_eq!(&*ram, &[2; 4]);
+        assert_eq!(&*Store::Ram.scratch::<u8>(2, 3).unwrap(), &[3, 3]);
+    }
+}
@@ -0,0 +1,59 @@
+//! Class-by-class differences between two snapshots.
+
+use std::collections::HashMap;
+
+use serde::{Deserialize, Serialize};
+
+use crate::index::HeapIndex;
+
+/// One class name in two snapshots; a side without the name has zeros.
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(rename_all = "camelCase")]
+pub struct HeapClassDiff {
+    pub name: String,
+    pub base_count: u64,
+    pub count: u64,
+    pub base_shallow: u64,
+    pub shallow: u64,
+    pub base_retained: u64,
+    pub retained: u64,
+    /// Several classes have this name on one side or both, so the sides cannot be matched: each
+    /// side shows the sum over its classes, and there is no difference to show.
+    pub ambiguous: bool,
+}
+
+/// Joined by class name, the only key two dumps share. By the change in retained size
+/// descending (none for an ambiguous name), then by name.
+pub fn compare(base: &HeapIndex, current: &HeapIndex) -> Vec<HeapClassDiff> {
+    let mut by_name: HashMap<String, HeapClassDiff> = HashMap::new();
+    for (index, is_base) in [(base, true), (current, false)] {
+        for row in index.class_rows() {
+            let diff = by_name.entry(row.name).or_insert_with_key(|name| HeapClassDiff {
+                name: name.clone(),
+                base_count: 0,
+                count: 0,
+                base_shallow: 0,
+                shallow: 0,
+                base_retained: 0,
+                retained: 0,
+                ambiguous: false,
+            });
+            let (count, shallow, retained) = if is_base {
+                (&mut diff.base_count, &mut diff.base_shallow, &mut diff.base_retained)
+            } else {
+                (&mut diff.count, &mut diff.shallow, &mut diff.retained)
+            };
+            *count = count.saturating_add(row.count);
+            *shallow = shallow.saturating_add(row.shallow);
+            *retained = retained.saturating_add(row.retained);
+            diff.ambiguous |= row.ambiguous;
+        }
+    }
+    let change = |d: &HeapClassDiff| if d.ambiguous { 0 } else { d.retained.abs_diff(d.base_retained) };
+    let mut diffs: Vec<HeapClassDiff> = by_name.into_values().collect();
+    diffs.sort_by(|a, b| change(b).cmp(&change(a)).then_with(|| a.name.cmp(&b.name)));
+    diffs
+}
+
+#[cfg(test)]
+mod tests;
@@ -0,0 +1,78 @@
+use super::*;
+use crate::hprof::HeapRootKind;
+use crate::test_index::analyzed;
+use crate::testing::{MiniHeap, sample, sample_with_two_more_nodes};
+
+fn diff<'a>(diffs: &'a [HeapClassDiff], name: &str) -> &'a HeapClassDiff {
+    let mut rows = diffs.iter().filter(|d| d.name == name);
+    let row = rows.next().unwrap_or_else(|| panic!("no diff for {name}"));
+    assert!(rows.next().is_none(), "two diffs for {name}");
+    row
+}
+
+fn sort_key(d: &HeapClassDiff) -> u64 {
+    if d.ambiguous { 0 } else { d.retained.abs_diff(d.base_retained) }
+}
+
+fn assert_sorted(diffs: &[HeapClassDiff]) {
+    assert!(diffs.windows(2).all(|p| (sort_key(&p[1]), &p[0].name) < (sort_key(&p[0]), &p[1].name)), "{diffs:#?}");
+}
+
+#[test]
+fn compare_counts_by_class() {
+    let base = analyzed(&sample());
+    let mut current = sample_with_two_more_nodes();
+    current
+        .class("Extra", Some("java.lang.Object"), &[])
+        .object(0x4000, "Extra", &[])
+        .root(HeapRootKind::JniGlobal, 0x4000);
+    let diffs = compare(&base, &analyzed(&current));
+    let node = diff(&diffs, "Node");
+    assert_eq!((node.base_count, node.count), (3, 5));
+    assert_eq!(node.shallow - node.base_shallow, 48);
+    assert_eq!((node.base_retained, node.retained), (104, 152));
+    assert!(!node.ambiguous);
+    let extra = diff(&diffs, "Extra");
+    assert_eq!((extra.base_count, extra.base_shallow, extra.base_retained, extra.count), (0, 0, 0, 1));
+    assert_eq!(diffs[0].name, "Node");
+    let holder = diff(&diffs, "Holder");
+    assert_eq!((holder.base_count, holder.count, holder.base_retained, holder.retained), (1, 1, 72, 72));
+    assert_sorted(&diffs);
+
+    // A class only in the base snapshot.
+    let gone = compare(&analyzed(&current), &base);
+    let extra = diff(&gone, "Extra");
+    assert_eq!((extra.base_count, extra.count, extra.shallow, extra.retained), (1, 0, 0, 0));
+    assert_sorted(&gone);
+}
+
+fn two_foos(extra: bool) -> MiniHeap {
+    let mut heap = sample();
+    heap.class("Foo", Some("java.lang.Object"), &[])
+        .object(0x3000, "Foo", &[])
+        .class("Foo", Some("java.lang.Object"), &[])
+        .object(0x3100, "Foo", &[]);
+    if extra {
+        heap.object(0x3200, "Foo", &[]);
+    }
+    for addr in [0x3000, 0x3100, 0x3200] {
+        heap.root(HeapRootKind::JniGlobal, addr);
+    }
+    heap
+}
+
+#[test]
+fn compare_gives_no_diff_for_a_name_of_several_classes() {
+    let diffs = compare(&analyzed(&two_foos(false)), &analyzed(&two_foos(true)));
+    let foo = diff(&diffs, "Foo");
+    assert!(foo.ambiguous);
+    assert_eq!((foo.base_count, foo.count), (2, 3));
+    assert!(diffs.iter().filter(|d| d.name != "Foo").all(|d| !d.ambiguous));
+    assert_sorted(&diffs);
+
+    // Ambiguous on one side only is still ambiguous.
+    let diffs = compare(&analyzed(&sample()), &analyzed(&two_foos(false)));
+    let foo = diff(&diffs, "Foo");
+    assert!(foo.ambiguous);
+    assert_eq!((foo.base_count, foo.count), (0, 2));
+}
@@ -0,0 +1,137 @@
+//! Disk-space estimates and the per-snapshot directories under the app's cache.
+//!
+//! A snapshot directory holds the index columns and, for a capture, the dump itself. Its `owner`
+//! file names the host process that created it, so a host that starts later can remove the
+//! directories of hosts that died without cleaning up.
+
+use std::fs;
+use std::io::{self, Read};
+use std::path::{Path, PathBuf};
+use std::time::{Duration, SystemTime};
+
+/// Space to leave free on top of an estimate.
+pub const DISK_MARGIN: u64 = 1 << 30;
+
+/// hprof ≈ `bytes + 16 × instances`; index columns and scratch arrays ≈ `90 × instances`.
+const CAPTURE_BYTES_PER_INSTANCE: u64 = 106;
+const INDEX_BYTES_PER_OBJECT: u64 = 90;
+
+const OWNER_FILE: &str = "owner";
+const TMP_SUFFIX: &str = ".tmp";
+/// A directory still being created by a live host has no `owner` for a moment; one that stays
+/// unfinished for longer than this was abandoned.
+const TMP_GRACE: Duration = Duration::from_secs(60 * 60);
+
+/// Bytes of free space that a dump of `heap_bytes` bytes holding `instances` instances needs,
+/// including its index.
+pub fn capture_need(heap_bytes: u64, instances: u64) -> u64 {
+    heap_bytes.saturating_add(CAPTURE_BYTES_PER_INSTANCE.saturating_mul(instances)).saturating_add(DISK_MARGIN)
+}
+
+/// Bytes of free space that indexing a dump of `objects` objects needs.
+pub fn index_need(objects: u64) -> u64 {
+    INDEX_BYTES_PER_OBJECT.saturating_mul(objects).saturating_add(DISK_MARGIN)
+}
+
+/// Bytes available to this process on the volume holding `dir`; `None` where it is not checked
+/// (not unix) or cannot be read, so callers go ahead rather than refuse.
+pub fn free_bytes(dir: &Path) -> Option<u64> {
+    #[cfg(unix)]
+    {
+        use std::os::unix::ffi::OsStrExt;
+
+        let path = std::ffi::CString::new(dir.as_os_str().as_bytes()).ok()?;
+        // SAFETY: `path` is NUL-terminated and `stat` is only read after `statvfs` filled it in.
+        let stat = unsafe {
+            let mut stat = std::mem::MaybeUninit::<libc::statvfs>::zeroed();
+            if libc::statvfs(path.as_ptr(), stat.as_mut_ptr()) != 0 {
+                return None;
+            }
+            stat.assume_init()
+        };
+        // The field widths differ between unix targets.
+        #[allow(clippy::unnecessary_cast)]
+        Some((stat.f_bavail as u64).saturating_mul(stat.f_frsize as u64))
+    }
+    #[cfg(not(unix))]
+    {
+        let _ = dir;
+        None
+    }
+}
+
+/// `<local_data_dir>/cache/heap-snapshots`.
+pub fn snapshots_root(local_data_dir: &Path) -> PathBuf {
+    local_data_dir.join("cache").join("heap-snapshots")
+}
+
+/// Creates `<root>/<uuid>/` holding an `owner` file with this process's pid. The directory is
+/// built as `<uuid>.tmp` and renamed, so another host scanning `root` never sees it without its
+/// owner and removes it as abandoned.
+pub fn create_snapshot_dir(root: &Path) -> io::Result<PathBuf> {
+    fs::create_dir_all(root)?;
+    let name = uuid::Uuid::new_v4().to_string();
+    let building = root.join(format!("{name}{TMP_SUFFIX}"));
+    let dir = root.join(&name);
+    create_private_dir(&building)?;
+    let published =
+        fs::write(building.join(OWNER_FILE), std::process::id().to_string()).and_then(|()| fs::rename(&building, &dir));
+    if let Err(err) = published {
+        let _ = fs::remove_dir_all(&building);
+        return Err(err);
+    }
+    Ok(dir)
+}
+
+/// A dump holds whatever was in the JVM's memory, passwords and tokens included, so on unix only
+/// the owner may enter the directory. Windows keeps the ACL inherited from the user's data dir.
+fn create_private_dir(path: &Path) -> io::Result<()> {
+    #[cfg(unix)]
+    {
+        use std::os::unix::fs::DirBuilderExt;
+        fs::DirBuilder::new().mode(0o700).create(path)
+    }
+    #[cfg(not(unix))]
+    {
+        fs::DirBuilder::new().create(path)
+    }
+}
+
+/// Removes the directories under `root` whose owner file is missing, unreadable or names a pid
+/// for which `alive` is false, and unfinished `*.tmp` ones older than an hour. Only directories
+/// directly under `root` are touched; a symlink there is left alone.
+pub fn remove_stale(root: &Path, alive: impl Fn(u32) -> bool) {
+    remove_stale_at(root, alive, SystemTime::now());
+}
+
+fn remove_stale_at(root: &Path, alive: impl Fn(u32) -> bool, now: SystemTime) {
+    let Ok(entries) = fs::read_dir(root) else { return };
+    for entry in entries.flatten() {
+        let path = entry.path();
+        // `symlink_metadata` does not follow: a link out of `root` is not a directory here.
+        let Ok(meta) = fs::symlink_metadata(&path) else { continue };
+        if !meta.file_type().is_dir() {
+            continue;
+        }
+        let stale = if path.extension().is_some_and(|ext| ext == "tmp") {
+            meta.modified()
+                .ok()
+                .and_then(|modified| now.duration_since(modified).ok())
+                .is_some_and(|age| age >= TMP_GRACE)
+        } else {
+            read_owner(&path).is_none_or(|pid| !alive(pid))
+        };
+        if stale && let Err(err) = fs::remove_dir_all(&path) {
+            tracing::warn!(dir = %path.display(), %err, "could not remove a stale heap snapshot directory");
+        }
+    }
+}
+
+fn read_owner(dir: &Path) -> Option<u32> {
+    let mut text = String::new();
+    fs::File::open(dir.join(OWNER_FILE)).ok()?.take(32).read_to_string(&mut text).ok()?;
+    text.trim().parse().ok()
+}
+
+#[cfg(test)]
+mod tests;
@@ -0,0 +1,137 @@
+use std::time::{Duration, SystemTime};
+
+use super::*;
+
+fn names(dir: &Path) -> Vec<String> {
+    let mut names: Vec<_> =
+        std::fs::read_dir(dir).unwrap().map(|e| e.unwrap().file_name().into_string().unwrap()).collect();
+    names.sort();
+    names
+}
+
+fn dir_with_owner(root: &Path, name: &str, owner: Option<&str>) {
+    let dir = root.join(name);
+    std::fs::create_dir(&dir).unwrap();
+    std::fs::write(dir.join("dump.hprof"), b"x").unwrap();
+    if let Some(owner) = owner {
+        std::fs::write(dir.join(OWNER_FILE), owner).unwrap();
+    }
+}
+
+#[test]
+fn estimates() {
+    assert_eq!(capture_need(664_018_520, 20_087_506), 664_018_520 + 106 * 20_087_506 + (1 << 30));
+    assert_eq!(index_need(10), 900 + (1 << 30));
+}
+
+#[test]
+fn estimates_saturate_instead_of_wrapping() {
+    assert_eq!(capture_need(u64::MAX, u64::MAX), u64::MAX);
+    assert_eq!(index_need(u64::MAX), u64::MAX);
+}
+
+#[cfg(unix)]
+#[test]
+fn not_enough_space_for_estimate() {
+    let dir = tempfile::tempdir().unwrap();
+    let free = free_bytes(dir.path()).expect("statvfs works on a temp dir");
+    assert!(free > 0);
+    assert!(capture_need(u64::MAX / 4, 0) > free);
+}
+
+#[cfg(unix)]
+#[test]
+fn free_bytes_of_a_missing_dir_is_unknown() {
+    let dir = tempfile::tempdir().unwrap();
+    assert_eq!(free_bytes(&dir.path().join("missing")), None);
+}
+
+#[cfg(not(unix))]
+#[test]
+fn free_space_is_not_checked_off_unix() {
+    assert_eq!(free_bytes(Path::new(".")), None);
+}
+
+#[test]
+fn snapshots_root_is_under_the_cache() {
+    let local = Path::new("local");
+    assert_eq!(snapshots_root(local), local.join("cache").join("heap-snapshots"));
+}
+
+#[test]
+fn snapshot_dir_records_its_owner_and_leaves_no_tmp() {
+    let root = tempfile::tempdir().unwrap();
+    let missing_parent = root.path().join("cache").join("heap-snapshots");
+    let dir = create_snapshot_dir(&missing_parent).unwrap();
+    assert_eq!(dir.parent(), Some(missing_parent.as_path()));
+    assert!(uuid::Uuid::parse_str(dir.file_name().unwrap().to_str().unwrap()).is_ok());
+    assert_eq!(std::fs::read_to_string(dir.join(OWNER_FILE)).unwrap(), std::process::id().to_string());
+    assert_eq!(names(&missing_parent), [dir.file_name().unwrap().to_str().unwrap()]);
+    assert_ne!(create_snapshot_dir(&missing_parent).unwrap(), dir);
+}
+
+#[cfg(unix)]
+#[test]
+fn snapshot_dir_is_private_to_the_owner() {
+    use std::os::unix::fs::PermissionsExt;
+
+    let root = tempfile::tempdir().unwrap();
+    let dir = create_snapshot_dir(root.path()).unwrap();
+    assert_eq!(std::fs::metadata(&dir).unwrap().permissions().mode() & 0o777, 0o700);
+}
+
+#[test]
+fn stale_dirs_removed_on_start() {
+    let root = tempfile::tempdir().unwrap();
+    dir_with_owner(root.path(), "a", Some("999999"));
+    dir_with_owner(root.path(), "b", Some(&std::process::id().to_string()));
+    dir_with_owner(root.path(), "c", None);
+    remove_stale(root.path(), |pid| pid == std::process::id());
+    assert_eq!(names(root.path()), ["b"]);
+}
+
+#[test]
+fn owner_that_is_not_a_pid_is_stale() {
+    let root = tempfile::tempdir().unwrap();
+    dir_with_owner(root.path(), "empty", Some(""));
+    dir_with_owner(root.path(), "word", Some("not-a-pid"));
+    dir_with_owner(root.path(), "negative", Some("-1"));
+    dir_with_owner(root.path(), "padded", Some(&format!(" {}\n", std::process::id())));
+    remove_stale(root.path(), |pid| pid == std::process::id());
+    assert_eq!(names(root.path()), ["padded"]);
+}
+
+#[test]
+fn stale_scan_tolerates_a_missing_root_and_leaves_loose_files_alone() {
+    let root = tempfile::tempdir().unwrap();
+    remove_stale(&root.path().join("missing"), |_| false);
+    std::fs::write(root.path().join("notes.txt"), b"keep").unwrap();
+    remove_stale(root.path(), |_| false);
+    assert_eq!(names(root.path()), ["notes.txt"]);
+}
+
+#[test]
+fn unfinished_dir_is_left_alone_for_an_hour() {
+    let root = tempfile::tempdir().unwrap();
+    // Another host may be between `create_dir` and the rename of its own snapshot dir.
+    dir_with_owner(root.path(), "young.tmp", None);
+    let now = SystemTime::now();
+    remove_stale_at(root.path(), |_| false, now);
+    assert_eq!(names(root.path()), ["young.tmp"]);
+    remove_stale_at(root.path(), |_| false, now + TMP_GRACE - Duration::from_secs(60));
+    assert_eq!(names(root.path()), ["young.tmp"]);
+    remove_stale_at(root.path(), |_| false, now + TMP_GRACE + Duration::from_secs(60));
+    assert!(names(root.path()).is_empty());
+}
+
+#[cfg(unix)]
+#[test]
+fn stale_scan_never_follows_a_symlink_out_of_the_root() {
+    let outside = tempfile::tempdir().unwrap();
+    std::fs::write(outside.path().join("precious"), b"x").unwrap();
+    let root = tempfile::tempdir().unwrap();
+    std::os::unix::fs::symlink(outside.path(), root.path().join("link")).unwrap();
+    remove_stale(root.path(), |_| false);
+    remove_stale_at(root.path(), |_| false, SystemTime::now() + 2 * TMP_GRACE);
+    assert_eq!(names(outside.path()), ["precious"]);
+}
@@ -0,0 +1,247 @@
+//! Dominator tree of the object graph, by Lengauer–Tarjan with path compression and no recursion:
+//! the DFS "stack" is the chain of DFS parents, and `eval` reverses the links of the path it
+//! compresses instead of keeping a stack.
+//!
+//! Between the DFS and the final translation every array is indexed by DFS number, so the root is
+//! 0 and a vertex's DFS ancestors all have smaller numbers.
+
+use ide_core::CancellationToken;
+
+use crate::column::{Column, NONE, Store};
+use crate::error::HeapError;
+use crate::files::IDOM_FILE;
+use crate::graph::accumulate;
+use crate::progress::{CHECK_EVERY, HeapPhase, Progress};
+
+const PHASE: HeapPhase = HeapPhase::Dominators;
+
+pub struct Dominators {
+    /// Immediate dominator of each node, saved as `idom.u32` in the store; [`NONE`] for
+    /// unreachable nodes, `root` for `root`.
+    pub idom: Column<u32>,
+    /// Nodes in DFS preorder from `root`, `reachable` entries.
+    pub preorder: Column<u32>,
+    pub reachable: u32,
+}
+
+/// The dominators of the graph whose node `v` has targets `out[out_start[v]..out_start[v + 1]]`,
+/// from `root` (which must be a node). `progress` gets `Dominators` from `(0, total)` to
+/// `(total, total)`; an `Err` from it stops the computation with that error.
+pub fn dominators(
+    out_start: &[u32],
+    out: &[u32],
+    root: u32,
+    store: &Store,
+    progress: &dyn Fn(HeapPhase, u64, u64) -> Result<(), HeapError>,
+    cancel: &CancellationToken,
+) -> Result<Dominators, HeapError> {
+    compute(out_start, out, root, store, progress, cancel).map(|(dominators, _)| dominators)
+}
+
+/// [`dominators`], plus the number of steps of work it took.
+fn compute(
+    out_start: &[u32],
+    out: &[u32],
+    root: u32,
+    store: &Store,
+    progress: &dyn Fn(HeapPhase, u64, u64) -> Result<(), HeapError>,
+    cancel: &CancellationToken,
+) -> Result<(Dominators, u64), HeapError> {
+    let nodes = out_start.len().saturating_sub(1);
+    if nodes >= NONE as usize {
+        return Err(HeapError::TooLarge);
+    }
+    assert!((root as usize) < nodes, "root {root} is not one of the {nodes} nodes");
+    // Three walks of at most `nodes` vertices each: DFS, semidominators, immediate dominators.
+    let span = nodes as u64;
+    let mut work = Work::new(Progress::new(progress, cancel), 3 * span);
+    work.report(0)?;
+
+    // DFS: `pre` maps nodes to DFS numbers and `vertex` back; `cursor[d]` is the next edge of
+    // DFS vertex d to follow.
+    let mut pre = store.scratch::<u32>(nodes, NONE)?;
+    let mut vertex = store.scratch::<u32>(nodes, 0)?;
+    let mut parent = store.scratch::<u32>(nodes, 0)?;
+    let mut cursor = store.scratch::<u32>(nodes, 0)?;
+    pre[root as usize] = 0;
+    vertex[0] = root;
+    cursor[0] = out_start[root as usize];
+    let (mut reachable, mut d) = (1u32, 0u32);
+    loop {
+        work.tick()?;
+        let edge = cursor[d as usize];
+        if edge < out_start[vertex[d as usize] as usize + 1] {
+            cursor[d as usize] = edge + 1;
+            let w = out[edge as usize] as usize;
+            if pre[w] == NONE {
+                let next = reachable as usize;
+                pre[w] = reachable;
+                vertex[next] = w as u32;
+                parent[next] = d;
+                cursor[next] = out_start[w];
+                d = reachable;
+                reachable += 1;
+                work.done = u64::from(reachable);
+            }
+        } else if d == 0 {
+            break;
+        } else {
+            d = parent[d as usize];
+        }
+    }
+    let r = reachable as usize;
+    work.report(span)?;
+
+    // Predecessors by DFS number, as CSR: counted into `starts[w + 1]`, then filled through
+    // `starts[w]` as a cursor, which leaves it at w's end until the column is shifted one slot.
+    let mut semi = cursor;
+    let mut label = store.scratch::<u32>(r, 0)?;
+    let mut starts = store.scratch::<u32>(r + 1, 0)?;
+    for d in 0..r {
+        work.tick()?;
+        semi[d] = d as u32;
+        label[d] = d as u32;
+        for &w in targets(out_start, out, vertex[d]) {
+            work.tick()?;
+            starts[pre[w as usize] as usize + 1] += 1;
+        }
+    }
+    let edges = accumulate(&mut starts, cancel)?;
+    let mut preds = store.scratch::<u32>(edges as usize, 0)?;
+    for d in 0..r {
+        work.tick()?;
+        for &w in targets(out_start, out, vertex[d]) {
+            work.tick()?;
+            let slot = &mut starts[pre[w as usize] as usize];
+            preds[*slot as usize] = d as u32;
+            *slot += 1;
+        }
+    }
+    starts.copy_within(0..r, 1);
+    starts[0] = 0;
+    drop(pre);
+    work.report(span)?;
+
+    // Semidominators in reverse preorder, linking each finished vertex to its parent. Vertex w
+    // waits in its semidominator's bucket until a child of that semidominator is linked; then
+    // `eval` gives w's idom, or a vertex whose idom is also w's, fixed up in preorder below.
+    // `idom[v]` is the next vertex in v's bucket until v leaves the bucket.
+    let mut ancestor = store.scratch::<u32>(r, NONE)?;
+    let mut bucket = store.scratch::<u32>(r, NONE)?;
+    let mut idom = store.scratch::<u32>(r, NONE)?;
+    for w in (1..r).rev() {
+        work.done = span + (r - w) as u64;
+        work.tick()?;
+        let mut s = semi[w];
+        for &v in &preds[starts[w] as usize..starts[w + 1] as usize] {
+            work.tick()?;
+            let u = eval(v, &mut ancestor, &mut label, &semi, &mut work)?;
+            s = s.min(semi[u as usize]);
+        }
+        semi[w] = s;
+        idom[w] = bucket[s as usize];
+        bucket[s as usize] = w as u32;
+        let p = parent[w];
+        ancestor[w] = p;
+        let mut v = std::mem::replace(&mut bucket[p as usize], NONE);
+        while v != NONE {
+            work.tick()?;
+            let next = idom[v as usize];
+            let u = eval(v, &mut ancestor, &mut label, &semi, &mut work)?;
+            idom[v as usize] = if semi[u as usize] < semi[v as usize] { u } else { p };
+            v = next;
+        }
+    }
+    drop((label, starts, preds, ancestor, bucket, parent));
+    work.report(2 * span)?;
+
+    // Immediate dominators, translated back to nodes; in preorder, so a deferred vertex's
+    // stand-in already has its final idom.
+    let mut node_idom = store.column::<u32>(IDOM_FILE, nodes, NONE)?;
+    let mut preorder = store.scratch::<u32>(r, 0)?;
+    idom[0] = 0;
+    node_idom[root as usize] = root;
+    preorder[0] = root;
+    for w in 1..r {
+        work.done = 2 * span + w as u64;
+        work.tick()?;
+        if idom[w] != semi[w] {
+            idom[w] = idom[idom[w] as usize];
+        }
+        node_idom[vertex[w] as usize] = vertex[idom[w] as usize];
+        preorder[w] = vertex[w];
+    }
+    work.report(3 * span)?;
+    Ok((Dominators { idom: node_idom, preorder, reachable }, work.steps))
+}
+
+fn targets<'a>(out_start: &[u32], out: &'a [u32], v: u32) -> &'a [u32] {
+    let v = v as usize;
+    &out[out_start[v] as usize..out_start[v + 1] as usize]
+}
+
+/// Counts steps of work and reports progress, which also looks at the cancellation token, at
+/// every phase boundary and after every [`CHECK_EVERY`] steps, whichever loop they are in.
+struct Work<'a> {
+    progress: Progress<'a>,
+    total: u64,
+    /// Progress to report at the next check; the loops keep it current.
+    done: u64,
+    steps: u64,
+    next_report: u64,
+}
+
+impl<'a> Work<'a> {
+    fn new(progress: Progress<'a>, total: u64) -> Self {
+        Self { progress, total, done: 0, steps: 0, next_report: CHECK_EVERY }
+    }
+
+    fn report(&mut self, done: u64) -> Result<(), HeapError> {
+        self.done = done;
+        self.next_report = self.steps + CHECK_EVERY;
+        self.progress.report(PHASE, done, self.total)
+    }
+
+    #[inline]
+    fn tick(&mut self) -> Result<(), HeapError> {
+        self.steps += 1;
+        if self.steps < self.next_report { Ok(()) } else { self.report(self.done) }
+    }
+}
+
+/// The vertex of smallest semidominator on the forest path from `v` up to, not including, its
+/// tree's root (`v` itself when it is a root), compressing that path so the root becomes the
+/// ancestor of every vertex on it. The walk up reverses the `ancestor` links so the walk down can
+/// fold labels nearest-root first, as the recursive compress does, without a stack.
+fn eval(v: u32, ancestor: &mut [u32], label: &mut [u32], semi: &[u32], work: &mut Work) -> Result<u32, HeapError> {
+    let at = |x: u32| x as usize;
+    if ancestor[at(v)] == NONE {
+        return Ok(v);
+    }
+    let (mut x, mut below) = (v, NONE);
+    while ancestor[at(ancestor[at(x)])] != NONE {
+        work.tick()?;
+        let up = ancestor[at(x)];
+        ancestor[at(x)] = below;
+        below = x;
+        x = up;
+    }
+    // `x` is the root's child, already compressed; `below` is the vertex under it.
+    let root = ancestor[at(x)];
+    let mut best = label[at(x)];
+    while below != NONE {
+        work.tick()?;
+        let y = at(below);
+        if semi[at(best)] < semi[at(label[y])] {
+            label[y] = best;
+        } else {
+            best = label[y];
+        }
+        below = ancestor[y];
+        ancestor[y] = root;
+    }
+    Ok(label[at(v)])
+}
+
+#[cfg(test)]
+mod tests;
@@ -0,0 +1,348 @@
+use std::cell::RefCell;
+use std::time::Instant;
+
+use proptest::collection::vec;
+use proptest::prelude::*;
+
+use super::*;
+use crate::NONE;
+use crate::graph::build_graph;
+use crate::testing::{XorShift, sample};
+
+fn no_progress(_: HeapPhase, _: u64, _: u64) -> Result<(), HeapError> {
+    Ok(())
+}
+
+/// CSR of `edges` over `n` nodes, targets in edge order.
+fn csr(n: usize, edges: &[(u32, u32)]) -> (Vec<u32>, Vec<u32>) {
+    let mut start = vec![0u32; n + 1];
+    for &(from, _) in edges {
+        start[from as usize + 1] += 1;
+    }
+    for v in 0..n {
+        start[v + 1] += start[v];
+    }
+    let mut cursor = start.clone();
+    let mut out = vec![0u32; edges.len()];
+    for &(from, to) in edges {
+        out[cursor[from as usize] as usize] = to;
+        cursor[from as usize] += 1;
+    }
+    (start, out)
+}
+
+fn run(n: usize, edges: &[(u32, u32)], root: u32) -> Dominators {
+    let (start, out) = csr(n, edges);
+    dominators(&start, &out, root, &Store::Ram, &no_progress, &CancellationToken::new()).unwrap()
+}
+
+fn preds(n: usize, edges: &[(u32, u32)]) -> Vec<Vec<u32>> {
+    let mut preds = vec![Vec::new(); n];
+    for &(from, to) in edges {
+        preds[to as usize].push(from);
+    }
+    preds
+}
+
+/// Immediate dominators from iterated `Dom` sets (one `u64` bitset per node, `n <= 64`).
+fn dataflow_idom(n: usize, edges: &[(u32, u32)], root: u32) -> Vec<u32> {
+    let (start, out) = csr(n, edges);
+    let mut reachable = vec![false; n];
+    let mut todo = vec![root];
+    reachable[root as usize] = true;
+    while let Some(v) = todo.pop() {
+        for &w in &out[start[v as usize] as usize..start[v as usize + 1] as usize] {
+            if !std::mem::replace(&mut reachable[w as usize], true) {
+                todo.push(w);
+            }
+        }
+    }
+    let preds = preds(n, edges);
+    let mut dom = vec![u64::MAX; n];
+    dom[root as usize] = 1 << root;
+    let mut changed = true;
+    while changed {
+        changed = false;
+        for v in (0..n).filter(|&v| reachable[v] && v != root as usize) {
+            let meet =
+                preds[v].iter().filter(|&&p| reachable[p as usize]).fold(u64::MAX, |acc, &p| acc & dom[p as usize]);
+            let next = meet | 1 << v;
+            if next != dom[v] {
+                dom[v] = next;
+                changed = true;
+            }
+        }
+    }
+    (0..n)
+        .map(|v| {
+            if !reachable[v] {
+                NONE
+            } else if v == root as usize {
+                root
+            } else {
+                // The strict dominator dominated by all the others has the most dominators itself.
+                let strict = dom[v] & !(1 << v);
+                (0..n as u32).filter(|&d| strict & 1 << d != 0).max_by_key(|&d| dom[d as usize].count_ones()).unwrap()
+            }
+        })
+        .collect()
+}
+
+/// Cooper–Harvey–Kennedy iteration over reverse postorder from an explicit-stack DFS.
+fn chk_idom(n: usize, edges: &[(u32, u32)], root: u32) -> Vec<u32> {
+    let (start, out) = csr(n, edges);
+    let mut post_number = vec![NONE; n];
+    let mut postorder = Vec::new();
+    let mut seen = vec![false; n];
+    let mut stack = vec![(root, start[root as usize])];
+    seen[root as usize] = true;
+    while let Some(&mut (v, ref mut next)) = stack.last_mut() {
+        if *next < start[v as usize + 1] {
+            let w = out[*next as usize];
+            *next += 1;
+            if !std::mem::replace(&mut seen[w as usize], true) {
+                stack.push((w, start[w as usize]));
+            }
+        } else {
+            post_number[v as usize] = postorder.len() as u32;
+            postorder.push(v);
+            stack.pop();
+        }
+    }
+    let preds = preds(n, edges);
+    let mut idom = vec![NONE; n];
+    idom[root as usize] = root;
+    let intersect = |idom: &[u32], mut a: u32, mut b: u32| {
+        while a != b {
+            while post_number[a as usize] < post_number[b as usize] {
+                a = idom[a as usize];
+            }
+            while post_number[b as usize] < post_number[a as usize] {
+                b = idom[b as usize];
+            }
+        }
+        a
+    };
+    let mut changed = true;
+    while changed {
+        changed = false;
+        for &v in postorder.iter().rev().filter(|&&v| v != root) {
+            let mut new = NONE;
+            for &p in &preds[v as usize] {
+                if idom[p as usize] != NONE {
+                    new = if new == NONE { p } else { intersect(&idom, p, new) };
+                }
+            }
+            if new != idom[v as usize] {
+                idom[v as usize] = new;
+                changed = true;
+            }
+        }
+    }
+    idom
+}
+
+#[test]
+fn diamond() {
+    let d = run(5, &[(0, 1), (0, 2), (1, 3), (2, 3), (3, 4)], 0);
+    assert_eq!(&*d.idom, &[0, 0, 0, 0, 3]);
+    assert_eq!(d.reachable, 5);
+    assert_eq!(&*d.preorder, &[0, 1, 3, 4, 2]);
+}
+
+#[test]
+fn unreachable_is_none() {
+    let d = run(6, &[(0, 1), (0, 2), (1, 3), (2, 3), (3, 4), (5, 3)], 0);
+    assert_eq!(&*d.idom, &[0, 0, 0, 0, 3, NONE]);
+    assert_eq!(d.reachable, 5);
+    assert_eq!(d.preorder.len(), 5);
+}
+
+#[test]
+fn cycle_back_to_root() {
+    let d = run(3, &[(0, 1), (1, 2), (2, 1), (2, 0)], 0);
+    assert_eq!(&*d.idom, &[0, 0, 1]);
+}
+
+#[test]
+fn root_need_not_be_node_zero() {
+    let d = run(4, &[(3, 1), (1, 0), (3, 2), (2, 0), (0, 3)], 3);
+    assert_eq!(&*d.idom, &[3, 3, 3, 3]);
+    assert_eq!(d.preorder[0], 3);
+}
+
+#[test]
+fn sample_heap_dominators() {
+    let bytes = sample().bytes();
+    let g = build_graph(&bytes, &Store::Ram, &no_progress, &CancellationToken::new()).unwrap();
+    let d = dominators(&g.out_start, &g.out, g.root, &Store::Ram, &no_progress, &CancellationToken::new()).unwrap();
+    let node = |id: u64| g.ids.rank(id).unwrap();
+    let idom_of = |id: u64| d.idom[node(id) as usize];
+    assert_eq!(idom_of(0x1100), node(0x1000), "N1 → H");
+    assert_eq!(idom_of(0x1200), node(0x1000), "N2 → H");
+    assert_eq!(idom_of(0x1300), g.root, "N3 → root");
+    assert_eq!(idom_of(0x1400), node(0x1300), "L → N3");
+    assert_eq!(idom_of(0x1500), NONE, "R is unreachable");
+    assert_eq!(idom_of(0x1700), NONE, "N4 only through the weak referent");
+    assert_eq!(d.idom[g.root as usize], g.root);
+}
+
+#[test]
+fn idom_is_written_to_the_store() {
+    let dir = tempfile::tempdir().unwrap();
+    let (start, out) = csr(3, &[(0, 1), (1, 2)]);
+    let store = Store::Dir(dir.path().to_path_buf());
+    let d = dominators(&start, &out, 0, &store, &no_progress, &CancellationToken::new()).unwrap();
+    drop(d);
+    assert_eq!(&*Column::<u32>::open(&dir.path().join("idom.u32")).unwrap(), &[0, 0, 1]);
+    let names: Vec<_> = std::fs::read_dir(dir.path()).unwrap().map(|e| e.unwrap().file_name()).collect();
+    assert_eq!(names, ["idom.u32"], "scratch columns leave no files");
+}
+
+#[test]
+fn reports_dominators_progress_and_stops_on_cancel() {
+    let (start, out) = csr(3, &[(0, 1), (1, 2)]);
+    let calls = RefCell::new(Vec::new());
+    let record = |phase, done, total| {
+        calls.borrow_mut().push((phase, done, total));
+        Ok(())
+    };
+    dominators(&start, &out, 0, &Store::Ram, &record, &CancellationToken::new()).unwrap();
+    let calls = calls.into_inner();
+    let total = calls[0].2;
+    assert_eq!(calls.first(), Some(&(HeapPhase::Dominators, 0, total)));
+    assert_eq!(calls.last(), Some(&(HeapPhase::Dominators, total, total)));
+    assert!(calls.windows(2).all(|w| w[0].1 <= w[1].1), "progress never goes back: {calls:?}");
+
+    let cancel = CancellationToken::new();
+    let cancel_on_first = |_, _, _| {
+        cancel.cancel();
+        Ok(())
+    };
+    let result = dominators(&start, &out, 0, &Store::Ram, &cancel_on_first, &cancel);
+    assert!(matches!(result, Err(HeapError::Cancelled)));
+
+    let refuse = |_, _, _| Err(HeapError::TooLarge);
+    let result = dominators(&start, &out, 0, &Store::Ram, &refuse, &CancellationToken::new());
+    assert!(matches!(result, Err(HeapError::TooLarge)));
+}
+
+#[test]
+fn cancel_during_idom_phase() {
+    // Long enough that the last phase alone passes a check interval.
+    const NODES: u32 = (CHECK_EVERY + CHECK_EVERY / 2) as u32;
+    let edges: Vec<_> = (1..NODES).map(|v| (v - 1, v)).collect();
+    let (start, out) = csr(NODES as usize, &edges);
+    let span = u64::from(NODES);
+    let cancel = CancellationToken::new();
+    let calls = RefCell::new(Vec::new());
+    let cancel_past_semidominators = |_, done, _| {
+        calls.borrow_mut().push(done);
+        if done > 2 * span {
+            cancel.cancel();
+        }
+        Ok(())
+    };
+    let result = dominators(&start, &out, 0, &Store::Ram, &cancel_past_semidominators, &cancel);
+    assert!(matches!(result, Err(HeapError::Cancelled)));
+    let calls = calls.into_inner();
+    assert!(calls.contains(&(2 * span)), "the semidominator phase finished: {calls:?}");
+    let last = *calls.last().unwrap();
+    assert!(last > 2 * span && last < 3 * span, "stopped inside the idom phase: {calls:?}");
+}
+
+proptest! {
+    #[test]
+    fn matches_dataflow_on_random_graphs(n in 2usize..64, edges in vec((0u32..64, 0u32..64), 0..192)) {
+        let edges: Vec<_> = edges.into_iter().map(|(a, b)| (a % n as u32, b % n as u32)).collect();
+        let d = run(n, &edges, 0);
+        prop_assert_eq!(d.idom.to_vec(), dataflow_idom(n, &edges, 0));
+        prop_assert_eq!(d.preorder.len(), d.reachable as usize);
+    }
+}
+
+#[test]
+fn matches_chk_on_a_large_random_graph() {
+    const NODES: u32 = 200_000;
+    const EXTRA_EDGES: u32 = 100_000;
+    let mut rng = XorShift::new(0x5EED_D0D0);
+    let mut edges: Vec<_> = (1..NODES).map(|v| (rng.below(v), v)).collect();
+    edges.extend((0..EXTRA_EDGES).map(|_| (rng.below(NODES), rng.below(NODES))));
+    // Visit edges in a scrambled order so the DFS tree differs from the generating tree.
+    for i in (1..edges.len()).rev() {
+        edges.swap(i, rng.below(i as u32 + 1) as usize);
+    }
+    let started = Instant::now();
+    let d = run(NODES as usize, &edges, 0);
+    let elapsed = started.elapsed();
+    let expected = chk_idom(NODES as usize, &edges, 0);
+    let mismatches = d.idom.iter().zip(&expected).filter(|(a, b)| a != b).count();
+    assert_eq!(mismatches, 0);
+    assert_eq!(d.reachable, NODES);
+    eprintln!("dominators of {NODES} random nodes: {elapsed:?}");
+}
+
+/// A doubly linked list whose items an array list also holds: super-root 0 → list 1 → node 0,
+/// 0 → array list 2 → element array 3 → every item; node j → item j, next, prev.
+fn shared_list_and_array(k: u32) -> (usize, Vec<(u32, u32)>) {
+    let node = |j: u32| 4 + 2 * j;
+    let item = |j: u32| 5 + 2 * j;
+    let mut edges = vec![(0, 1), (0, 2), (2, 3), (1, node(0))];
+    for j in 0..k {
+        edges.push((node(j), item(j)));
+        if j + 1 < k {
+            edges.push((node(j), node(j + 1)));
+        }
+        if j > 0 {
+            edges.push((node(j), node(j - 1)));
+        }
+        edges.push((3, item(j)));
+    }
+    ((4 + 2 * k) as usize, edges)
+}
+
+#[test]
+fn shared_list_and_array_is_near_linear() {
+    let (n, edges) = shared_list_and_array(29);
+    assert_eq!(run(n, &edges, 0).idom.to_vec(), dataflow_idom(n, &edges, 0));
+    let (n, edges) = shared_list_and_array(3_000);
+    assert_eq!(run(n, &edges, 0).idom.to_vec(), chk_idom(n, &edges, 0));
+
+    const K: u32 = 200_000;
+    let (n, edges) = shared_list_and_array(K);
+    let (start, out) = csr(n, &edges);
+    let started = Instant::now();
+    let (d, steps) = compute(&start, &out, 0, &Store::Ram, &no_progress, &CancellationToken::new()).unwrap();
+    let elapsed = started.elapsed();
+    let item = |j: u32| (5 + 2 * j) as usize;
+    assert!((0..K).all(|j| d.idom[item(j)] == 0), "every item is held by both collections");
+    let m = edges.len() as u64;
+    let bound = (n as u64 + m) * u64::from(n.ilog2());
+    eprintln!("shared list k={K}: {steps} steps (n={n}, m={m}, bound {bound}), {elapsed:?}");
+    assert!(steps <= bound, "{steps} steps for n={n}, m={m}");
+}
+
+#[test]
+fn deep_chain_has_linear_dominators() {
+    // A small stack proves the algorithm does not recurse along the chain.
+    std::thread::Builder::new()
+        .stack_size(256 << 10)
+        .spawn(|| {
+            const NODES: u32 = 1_000_000;
+            let mut edges: Vec<_> = (1..NODES).map(|v| (v - 1, v)).collect();
+            edges.push((0, NODES - 1));
+            // Makes `eval` compress the whole chain at once.
+            edges.push((NODES - 1, 1));
+            let started = Instant::now();
+            let d = run(NODES as usize, &edges, 0);
+            eprintln!("dominators of a {NODES}-node chain: {:?}", started.elapsed());
+            assert_eq!(d.reachable, NODES);
+            assert_eq!(d.idom[0], 0);
+            assert_eq!(d.idom[NODES as usize - 1], 0);
+            let wrong = (1..NODES - 1).filter(|&v| d.idom[v as usize] != v - 1).count();
+            assert_eq!(wrong, 0);
+        })
+        .unwrap()
+        .join()
+        .unwrap();
+}
@@ -0,0 +1,26 @@
+/// Offsets (`at`) are byte positions in the `.hprof` file.
+#[derive(Debug, thiserror::Error)]
+pub enum HeapError {
+    #[error("the dump ends early at byte {at}")]
+    Truncated { at: u64 },
+    #[error("not a heap dump (no JAVA PROFILE header)")]
+    NotHprof,
+    #[error("unsupported identifier size {0}")]
+    UnsupportedIdSize(u32),
+    #[error("unknown heap sub-record tag {tag:#04x} at byte {at}")]
+    UnknownSubRecord { tag: u8, at: u64 },
+    #[error("unknown value type {ty} at byte {at}")]
+    UnknownType { ty: u8, at: u64 },
+    #[error("class {id:#x} used at byte {at} is not in the dump")]
+    MissingClass { id: u64, at: u64 },
+    #[error("the heap has too many objects to analyze")]
+    TooLarge,
+    #[error("the dump's class and field names are too long; it is not a dump a JVM wrote")]
+    NamesTooLarge,
+    #[error("not enough disk space: {needed} bytes needed, {available} free")]
+    NotEnoughDiskSpace { needed: u64, available: u64 },
+    #[error("cancelled")]
+    Cancelled,
+    #[error("{0}")]
+    Io(#[from] std::io::Error),
+}
@@ -0,0 +1,34 @@
+//! Names of the files an analysis writes into its index directory. They live in one list so a
+//! failed analysis removes exactly these and never the dump or anything else sharing the directory.
+
+pub(crate) const IDS_BITS_FILE: &str = "ids.bits.u64";
+pub(crate) const IDS_WRANK_FILE: &str = "ids.wrank.u32";
+pub(crate) const IDS_TABLE_FILE: &str = "ids.table.u32";
+pub(crate) const IDS_CHUNKS_FILE: &str = "ids.chunks.u32";
+pub(crate) const IDS_SORTED_FILE: &str = "ids.sorted.u64";
+pub(crate) const TYPES_FILE: &str = "types.u32";
+pub(crate) const OFFSETS_FILE: &str = "offsets.u64";
+pub(crate) const IDOM_FILE: &str = "idom.u32";
+pub(crate) const SHALLOW8_FILE: &str = "shallow8.u32";
+pub(crate) const RETAINED_FILE: &str = "retained.u64";
+pub(crate) const KIDS_START_FILE: &str = "kids_start.u32";
+pub(crate) const KIDS_FILE: &str = "kids.u32";
+pub(crate) const GC_PARENT_FILE: &str = "gc_parent.u32";
+pub(crate) const SUMMARY_FILE: &str = "summary.json";
+
+pub(crate) const INDEX_FILES: &[&str] = &[
+    IDS_BITS_FILE,
+    IDS_WRANK_FILE,
+    IDS_TABLE_FILE,
+    IDS_CHUNKS_FILE,
+    IDS_SORTED_FILE,
+    TYPES_FILE,
+    OFFSETS_FILE,
+    IDOM_FILE,
+    SHALLOW8_FILE,
+    RETAINED_FILE,
+    KIDS_START_FILE,
+    KIDS_FILE,
+    GC_PARENT_FILE,
+    SUMMARY_FILE,
+];
@@ -0,0 +1,274 @@
+//! The object graph of a heap dump in CSR form: one node per object, plus a super-root.
+
+mod classes;
+mod link;
+
+use std::collections::hash_map::Entry;
+use std::collections::{HashMap, HashSet};
+
+use ide_core::CancellationToken;
+
+use self::classes::{ClassTable, IdHash};
+use self::link::Linker;
+use crate::column::{Column, Store};
+use crate::error::HeapError;
+use crate::files::{OFFSETS_FILE, TYPES_FILE};
+use crate::hprof::{BasicType, HeapRecord, HeapRootKind, Record, parse_header, scan, scan_segment};
+use crate::ids::{IdMap, IdMapBuilder};
+use crate::progress::{CHECK_EVERY, HeapPhase, Progress};
+
+/// Number of primitive array type slots, one per non-object [`BasicType`].
+pub const PRIM_SLOTS: u32 = 8;
+
+pub struct ClassInfo {
+    pub id: u64,
+    /// The hprof name with `/` turned into `.` (`java.lang.String`, `[Ljava.lang.Object;`).
+    pub name: String,
+    /// Index in [`HeapGraph::classes`]. Chains always end: a super cycle in the dump is cut where it closes.
+    pub super_index: Option<u32>,
+    /// This class's own instance fields, in dump order.
+    pub fields: Vec<(String, BasicType)>,
+    /// `(name, object id)` of reference statics; a null static has object id 0.
+    pub statics: Vec<(String, u64)>,
+    pub static_bytes: u64,
+    /// Index in `fields` of `java.lang.ref.Reference.referent`, on that class only.
+    pub weak_field: Option<usize>,
+}
+
+pub struct HeapGraph {
+    pub ids: IdMap,
+    /// Type slot of each object: class index for instances and object arrays,
+    /// [`Self::class_slot`] for class objects, [`Self::prim_slot`] for primitive arrays.
+    pub types: Column<u32>,
+    /// Array length, 0 for instances and classes.
+    pub lens: Column<u32>,
+    /// File offset of each object's record, for [`crate::record_at`].
+    pub offsets: Column<u64>,
+    /// `n + 2` entries: node `v`'s targets are `out[out_start[v]..out_start[v + 1]]`.
+    pub out_start: Column<u32>,
+    pub out: Column<u32>,
+    /// The super-root, node `n`, with an edge to every rooted object.
+    pub root: u32,
+    /// `(object, kind, thread serial)` of every root record whose object is in the dump.
+    pub roots: Vec<(u32, HeapRootKind, Option<u32>)>,
+    /// Class dumps in dump order, then a synthetic `java.lang.Class` when the dump has none.
+    pub classes: Vec<ClassInfo>,
+    /// Type slot of class objects (`java.lang.Class`).
+    pub class_slot: u32,
+    /// Thread serial → thread object, from `ROOT THREAD OBJECT` records.
+    pub thread_objects: HashMap<u32, u32>,
+    /// `Reference.referent` edges left out of the graph.
+    pub weak_edges_skipped: u64,
+    pub id_size: u8,
+    pub timestamp_ms: u64,
+}
+
+impl HeapGraph {
+    pub fn prim_slot(&self, ty: BasicType) -> u32 {
+        self.classes.len() as u32 + (ty as u32 - BasicType::Boolean as u32)
+    }
+
+    /// The element type of primitive array slot `slot`, or `None` for a class slot.
+    pub fn prim_type(&self, slot: u32) -> Option<BasicType> {
+        let offset = slot.checked_sub(self.classes.len() as u32).filter(|&o| o < PRIM_SLOTS)?;
+        BasicType::from_u8(offset as u8 + BasicType::Boolean as u8)
+    }
+
+    pub fn out_edges(&self, v: u32) -> &[u32] {
+        let v = v as usize;
+        &self.out[self.out_start[v] as usize..self.out_start[v + 1] as usize]
+    }
+}
+
+/// Builds the graph of the dump in `buf`. Strong edges only: `Reference.referent` is counted in
+/// [`HeapGraph::weak_edges_skipped`] instead. `progress` gets `Reading` by bytes, then
+/// `Linking` by objects, starting with `(Linking, 0, objects)` once the object count is known;
+/// an `Err` from it stops the build with that error.
+pub fn build_graph(
+    buf: &[u8],
+    store: &Store,
+    progress: &dyn Fn(HeapPhase, u64, u64) -> Result<(), HeapError>,
+    cancel: &CancellationToken,
+) -> Result<HeapGraph, HeapError> {
+    let progress = Progress::new(progress, cancel);
+    let header = parse_header(buf)?;
+    let id_size = header.id_size;
+    let len = buf.len() as u64;
+
+    // Pass 1: names, classes, roots and every object id.
+    progress.report(HeapPhase::Reading, 0, len)?;
+    let mut names: IdHash<&[u8]> = IdHash::default();
+    let mut class_names: IdHash<u64> = IdHash::default();
+    let mut dumps = Vec::new();
+    let mut class_by_id: IdHash<u32> = IdHash::default();
+    let mut raw_roots = Vec::new();
+    let mut segments = Vec::new();
+    let mut builder = IdMapBuilder::new();
+    let (mut step, mut pos) = (0, header.body_start as u64);
+    scan(buf, &header, &mut |record| {
+        progress.step(step, HeapPhase::Reading, pos, len)?;
+        step += 1;
+        match record {
+            Record::Utf8 { id, text } => {
+                names.insert(id, text);
+            }
+            Record::LoadClass { class_id, name_id } => {
+                class_names.insert(class_id, name_id);
+            }
+            Record::Segment(range) => {
+                pos = range.start as u64;
+                segments.push(range);
+            }
+            Record::Heap { at, record } => {
+                pos = at as u64;
+                match record {
+                    HeapRecord::Root { kind, id, thread_serial } => raw_roots.push((id, kind, thread_serial)),
+                    HeapRecord::Class(dump) => {
+                        builder.insert(dump.id);
+                        if let Entry::Vacant(slot) = class_by_id.entry(dump.id) {
+                            slot.insert(dumps.len() as u32);
+                            dumps.push(dump);
+                        }
+                    }
+                    HeapRecord::Instance { id, .. }
+                    | HeapRecord::ObjectArray { id, .. }
+                    | HeapRecord::PrimitiveArray { id, .. } => builder.insert(id),
+                }
+            }
+        }
+        Ok(())
+    })?;
+    progress.report(HeapPhase::Reading, len, len)?;
+
+    let ids = builder.build(store, cancel)?;
+    let table = classes::resolve(dumps, class_by_id, &names, &class_names, id_size, buf.len())?;
+    drop((names, class_names));
+    let n = ids.len();
+    let objects = u64::from(n);
+    progress.report(HeapPhase::Linking, 0, objects)?;
+
+    let mut roots = Vec::new();
+    let mut root_targets = Vec::new();
+    let mut thread_objects = HashMap::new();
+    let (mut seen_records, mut seen_targets) = (HashSet::new(), HashSet::new());
+    for (i, &(id, kind, serial)) in raw_roots.iter().enumerate() {
+        progress.step(i as u64, HeapPhase::Linking, 0, objects)?;
+        let Some(object) = ids.rank(id).filter(|_| id != 0) else { continue };
+        if seen_records.insert((object, kind as u8, serial)) {
+            roots.push((object, kind, serial));
+        }
+        if seen_targets.insert(object) {
+            root_targets.push(object);
+        }
+        if let (HeapRootKind::ThreadObject, Some(serial)) = (kind, serial) {
+            thread_objects.entry(serial).or_insert(object);
+        }
+    }
+    drop((raw_roots, seen_records, seen_targets));
+
+    let linker = Linker::new(&ids, &table, id_size);
+    let nodes = n as usize;
+    let mut types = store.column::<u32>(TYPES_FILE, nodes, 0)?;
+    let mut lens = store.scratch::<u32>(nodes, 0)?;
+    let mut offsets = store.column::<u64>(OFFSETS_FILE, nodes, 0)?;
+    let mut out_start = store.scratch::<u32>(nodes + 2, 0)?;
+    // Both passes visit every object record once; report them as one walk over the objects.
+    let mut visited = 0u64;
+    let tick = |visited: &mut u64| {
+        let result = progress.step(*visited, HeapPhase::Linking, (*visited / 2).min(objects), objects);
+        *visited += 1;
+        result
+    };
+
+    // Pass 2: node columns and out-degrees, counted into `out_start[v + 1]`.
+    let mut weak_edges_skipped = 0;
+    for segment in &segments {
+        scan_segment(buf, segment.clone(), id_size, &mut |at, record| {
+            let Some(node) = linker.node(at, &record)? else { return Ok(()) };
+            tick(&mut visited)?;
+            let v = node.index as usize;
+            types[v] = node.ty;
+            lens[v] = node.len;
+            offsets[v] = at as u64;
+            let mut degree = 0u64;
+            linker.edges(&record, &mut |_, weak| {
+                if weak {
+                    weak_edges_skipped += 1;
+                } else {
+                    degree += 1;
+                }
+            });
+            let count = &mut out_start[v + 1];
+            *count = u32::try_from(u64::from(*count) + degree).map_err(|_| HeapError::TooLarge)?;
+            Ok(())
+        })?;
+    }
+    out_start[nodes + 1] = u32::try_from(root_targets.len()).map_err(|_| HeapError::TooLarge)?;
+    let edges = accumulate(&mut out_start, cancel)?;
+
+    // Pass 3: `out_start[v]` is node v's write cursor; once filled it holds v's end, so the
+    // column is shifted one slot right to become the starts again.
+    let mut out = store.scratch::<u32>(edges as usize, 0)?;
+    for segment in &segments {
+        scan_segment(buf, segment.clone(), id_size, &mut |at, record| {
+            let Some(node) = linker.node(at, &record)? else { return Ok(()) };
+            tick(&mut visited)?;
+            let v = node.index as usize;
+            let mut cursor = out_start[v] as usize;
+            linker.edges(&record, &mut |target, weak| {
+                if !weak && let Some(slot) = out.get_mut(cursor) {
+                    *slot = target;
+                    cursor += 1;
+                }
+            });
+            out_start[v] = cursor as u32;
+            Ok(())
+        })?;
+    }
+    let first_root_edge = out_start[nodes] as usize;
+    for (slot, &target) in out[first_root_edge..].iter_mut().zip(&root_targets) {
+        *slot = target;
+    }
+    out_start[nodes] = edges;
+    out_start.copy_within(0..nodes + 1, 1);
+    out_start[0] = 0;
+    progress.report(HeapPhase::Linking, objects, objects)?;
+
+    drop(linker);
+    let ClassTable { classes, class_slot, .. } = table;
+    Ok(HeapGraph {
+        ids,
+        types,
+        lens,
+        offsets,
+        out_start,
+        out,
+        root: n,
+        roots,
+        classes,
+        class_slot,
+        thread_objects,
+        weak_edges_skipped,
+        id_size,
+        timestamp_ms: header.timestamp_ms,
+    })
+}
+
+/// Turns per-node counts into running totals in place (`counts[k]` becomes the sum of
+/// `counts[..=k]`) and returns the last one; past `u32::MAX` the graph is `TooLarge`.
+pub(crate) fn accumulate(counts: &mut [u32], cancel: &CancellationToken) -> Result<u32, HeapError> {
+    let mut sum = 0u32;
+    for chunk in counts.chunks_mut(CHECK_EVERY as usize) {
+        if cancel.is_cancelled() {
+            return Err(HeapError::Cancelled);
+        }
+        for count in chunk {
+            sum = sum.checked_add(*count).ok_or(HeapError::TooLarge)?;
+            *count = sum;
+        }
+    }
+    Ok(sum)
+}
+
+#[cfg(test)]
+mod tests;
@@ -0,0 +1,188 @@
+//! Class dumps resolved into [`ClassInfo`]s, plus where the references sit in instance data.
+
+use std::collections::HashMap;
+use std::hash::BuildHasherDefault;
+
+use super::{ClassInfo, PRIM_SLOTS};
+use crate::column::NONE;
+use crate::error::HeapError;
+use crate::hprof::{BasicType, ClassDump};
+use crate::ids::ChunkHasher;
+
+/// Keyed by hprof id (an address).
+pub(super) type IdHash<V> = HashMap<u64, V, BuildHasherDefault<ChunkHasher>>;
+
+const REFERENCE: &str = "java.lang.ref.Reference";
+const JAVA_LANG_CLASS: &str = "java.lang.Class";
+/// Not computed yet, in [`ClassTable::fielded`].
+const UNSET: u32 = NONE - 1;
+
+pub(super) struct ClassTable {
+    pub(super) classes: Vec<ClassInfo>,
+    /// Class id → class index.
+    pub(super) by_id: IdHash<u32>,
+    pub(super) class_slot: u32,
+    /// Per class: `(offset, is the referent)` of each reference field in the class's own part of
+    /// the instance data.
+    pub(super) refs: Vec<Vec<(usize, bool)>>,
+    /// Per class: bytes of its own part of the instance data.
+    pub(super) own_bytes: Vec<usize>,
+    /// Per class: the nearest class up its chain (itself included) whose own part is not empty, or
+    /// `NONE`. Walking these instead of every super keeps a walk bounded by the data it reads.
+    pub(super) fielded: Vec<u32>,
+}
+
+/// The longest name a JVM gives a class or field (a constant pool UTF8 has a `u2` length).
+const MAX_NAME_BYTES: usize = 65_535;
+/// Name bytes a dump may decode beyond 4 per byte of the file.
+const NAME_BUDGET_FLOOR: usize = 64 << 20;
+
+/// Names decoded from the UTF8 records within a budget: every field of every class may name the
+/// same record, so a small crafted file could otherwise ask for terabytes and abort the IDE.
+struct Names<'m, 'b> {
+    records: &'m IdHash<&'b [u8]>,
+    left: usize,
+}
+
+impl Names<'_, '_> {
+    /// Empty for an id with no record.
+    fn text(&mut self, id: u64) -> Result<String, HeapError> {
+        let Some(bytes) = self.records.get(&id) else { return Ok(String::new()) };
+        if bytes.len() > MAX_NAME_BYTES || bytes.len() > self.left {
+            return Err(HeapError::NamesTooLarge);
+        }
+        self.left -= bytes.len();
+        Ok(String::from_utf8_lossy(bytes).into_owned())
+    }
+}
+
+/// `dumps` holds one dump per class id, and `by_id` its position; `names` are the UTF8 records
+/// and `class_names` the LOAD CLASS class id → name id pairs. `file_len` bounds the name bytes.
+pub(super) fn resolve(
+    dumps: Vec<ClassDump>,
+    by_id: IdHash<u32>,
+    names: &IdHash<&[u8]>,
+    class_names: &IdHash<u64>,
+    id_size: u8,
+    file_len: usize,
+) -> Result<ClassTable, HeapError> {
+    // Room for the synthetic java.lang.Class and the primitive slots in a `u32` type id.
+    if dumps.len() > (u32::MAX - PRIM_SLOTS - 1) as usize {
+        return Err(HeapError::TooLarge);
+    }
+    let mut names = Names { records: names, left: file_len.saturating_mul(4).saturating_add(NAME_BUDGET_FLOOR) };
+    let mut supers: Vec<Option<u32>> =
+        dumps.iter().map(|d| if d.super_id == 0 { None } else { by_id.get(&d.super_id).copied() }).collect();
+    cut_super_cycles(&mut supers);
+
+    let mut classes = Vec::with_capacity(dumps.len() + 1);
+    let mut refs = Vec::with_capacity(dumps.len() + 1);
+    let mut own_bytes = Vec::with_capacity(dumps.len() + 1);
+    for (dump, super_index) in dumps.into_iter().zip(supers) {
+        let name = match class_names.get(&dump.id) {
+            Some(&name_id) if names.records.contains_key(&name_id) => names.text(name_id)?.replace('/', "."),
+            _ => format!("{:#x}", dump.id),
+        };
+        let fields =
+            dump.fields.iter().map(|&(n, ty)| Ok((names.text(n)?, ty))).collect::<Result<Vec<_>, HeapError>>()?;
+        let weak_field = if name == REFERENCE {
+            fields.iter().position(|(n, ty)| n == "referent" && *ty == BasicType::Object)
+        } else {
+            None
+        };
+        let mut offset = 0;
+        let mut class_refs = Vec::new();
+        for (k, &(_, ty)) in fields.iter().enumerate() {
+            if ty == BasicType::Object {
+                class_refs.push((offset, weak_field == Some(k)));
+            }
+            offset += ty.hprof_size(id_size);
+        }
+        refs.push(class_refs);
+        own_bytes.push(offset);
+        classes.push(ClassInfo {
+            id: dump.id,
+            name,
+            super_index,
+            fields,
+            statics: dump
+                .statics
+                .iter()
+                .map(|&(n, object)| Ok((names.text(n)?, object)))
+                .collect::<Result<_, HeapError>>()?,
+            static_bytes: dump.static_bytes,
+            weak_field,
+        });
+    }
+
+    let class_slot = match classes.iter().position(|c| c.name == JAVA_LANG_CLASS) {
+        Some(slot) => slot as u32,
+        None => {
+            classes.push(ClassInfo {
+                id: 0,
+                name: JAVA_LANG_CLASS.to_owned(),
+                super_index: None,
+                fields: Vec::new(),
+                statics: Vec::new(),
+                static_bytes: 0,
+                weak_field: None,
+            });
+            refs.push(Vec::new());
+            own_bytes.push(0);
+            classes.len() as u32 - 1
+        }
+    };
+    let fielded = nearest_fielded(&classes, &own_bytes);
+    Ok(ClassTable { classes, by_id, class_slot, refs, own_bytes, fielded })
+}
+
+/// A dump may claim `A extends B extends A`; the edge that closes a cycle is dropped so every
+/// walk up the chain ends. Iterative, so a long chain cannot overflow the stack.
+fn cut_super_cycles(supers: &mut [Option<u32>]) {
+    const NEW: u8 = 0;
+    const ON_PATH: u8 = 1;
+    const DONE: u8 = 2;
+    let mut state = vec![NEW; supers.len()];
+    let mut path = Vec::new();
+    for start in 0..supers.len() {
+        let mut c = start;
+        while state[c] == NEW {
+            state[c] = ON_PATH;
+            path.push(c);
+            match supers[c] {
+                Some(s) if state[s as usize] == ON_PATH => {
+                    supers[c] = None;
+                    break;
+                }
+                Some(s) => c = s as usize,
+                None => break,
+            }
+        }
+        for p in path.drain(..) {
+            state[p] = DONE;
+        }
+    }
+}
+
+fn nearest_fielded(classes: &[ClassInfo], own_bytes: &[usize]) -> Vec<u32> {
+    let mut fielded: Vec<u32> =
+        own_bytes.iter().enumerate().map(|(c, &b)| if b > 0 { c as u32 } else { UNSET }).collect();
+    let mut path = Vec::new();
+    for start in 0..classes.len() {
+        let mut c = start;
+        let found = loop {
+            if fielded[c] != UNSET {
+                break fielded[c];
+            }
+            path.push(c);
+            match classes[c].super_index {
+                Some(s) => c = s as usize,
+                None => break NONE,
+            }
+        };
+        for p in path.drain(..) {
+            fielded[p] = found;
+        }
+    }
+    fielded
+}
@@ -0,0 +1,107 @@
+//! Turns one heap sub-record into its node (index, type, length) and its outgoing edges. Both
+//! linking passes go through here, so the degrees counted in the first match the edges written
+//! in the second.
+
+use super::classes::ClassTable;
+use crate::column::NONE;
+use crate::error::HeapError;
+use crate::hprof::{BasicType, HeapRecord};
+use crate::ids::IdMap;
+
+pub(super) struct Node {
+    pub(super) index: u32,
+    pub(super) ty: u32,
+    pub(super) len: u32,
+}
+
+pub(super) struct Linker<'a> {
+    ids: &'a IdMap,
+    table: &'a ClassTable,
+    /// Per class: the node of its class object, `NONE` for the synthetic `java.lang.Class`.
+    class_objects: Vec<u32>,
+    id_size: u8,
+}
+
+impl<'a> Linker<'a> {
+    pub(super) fn new(ids: &'a IdMap, table: &'a ClassTable, id_size: u8) -> Self {
+        let class_objects =
+            table.classes.iter().map(|c| if c.id == 0 { NONE } else { ids.rank(c.id).unwrap_or(NONE) }).collect();
+        Self { ids, table, class_objects, id_size }
+    }
+
+    /// `None` for root records. `at` is the record's offset, for the error of an instance or array
+    /// whose class is not in the dump.
+    pub(super) fn node(&self, at: usize, record: &HeapRecord<'_>) -> Result<Option<Node>, HeapError> {
+        let class_index = |class_id: u64| {
+            self.table.by_id.get(&class_id).copied().ok_or(HeapError::MissingClass { id: class_id, at: at as u64 })
+        };
+        let (id, ty, len) = match record {
+            HeapRecord::Root { .. } => return Ok(None),
+            HeapRecord::Class(c) => (c.id, self.table.class_slot, 0),
+            HeapRecord::Instance { id, class_id, .. } => (*id, class_index(*class_id)?, 0),
+            HeapRecord::ObjectArray { id, class_id, len, .. } => (*id, class_index(*class_id)?, *len),
+            HeapRecord::PrimitiveArray { id, ty, len, .. } => {
+                let prim_base = self.table.classes.len() as u32;
+                (*id, prim_base + (*ty as u32 - BasicType::Boolean as u32), *len)
+            }
+        };
+        Ok(self.ids.rank(id).map(|index| Node { index, ty, len }))
+    }
+
+    /// Calls `edge(target, is_referent)` for every reference to an object in the dump, in field
+    /// order; `is_referent` marks `Reference.referent`, which callers leave out of the graph.
+    pub(super) fn edges(&self, record: &HeapRecord<'_>, edge: &mut impl FnMut(u32, bool)) {
+        let mut to = |id: u64, weak: bool| {
+            if let Some(target) = self.target(id) {
+                edge(target, weak);
+            }
+        };
+        match record {
+            HeapRecord::Root { .. } | HeapRecord::PrimitiveArray { .. } => {}
+            HeapRecord::Class(c) => {
+                to(c.super_id, false);
+                to(c.loader_id, false);
+                for &(_, object) in &c.statics {
+                    to(object, false);
+                }
+            }
+            HeapRecord::ObjectArray { data, .. } => {
+                for item in data.chunks_exact(usize::from(self.id_size)) {
+                    to(read_id(item, 0, self.id_size).unwrap_or(0), false);
+                }
+            }
+            HeapRecord::Instance { class_id, data, .. } => {
+                let Some(&class) = self.table.by_id.get(class_id) else { return };
+                let mut base = 0;
+                let mut next = self.table.fielded[class as usize];
+                'chain: while next != NONE && base < data.len() {
+                    let c = next as usize;
+                    for &(offset, weak) in &self.table.refs[c] {
+                        let Some(id) = read_id(data, base + offset, self.id_size) else { break 'chain };
+                        to(id, weak);
+                    }
+                    base += self.table.own_bytes[c];
+                    next = self.table.classes[c].super_index.map_or(NONE, |s| self.table.fielded[s as usize]);
+                }
+                let object = self.class_objects[class as usize];
+                if object != NONE {
+                    edge(object, false);
+                }
+            }
+        }
+    }
+
+    /// Id 0 is null; ids not in the dump have no node.
+    fn target(&self, id: u64) -> Option<u32> {
+        if id == 0 { None } else { self.ids.rank(id) }
+    }
+}
+
+/// The big-endian id at `at`, or `None` when `data` ends first.
+fn read_id(data: &[u8], at: usize, id_size: u8) -> Option<u64> {
+    let bytes = data.get(at..at.checked_add(usize::from(id_size))?)?;
+    Some(match *bytes {
+        [a, b, c, d] => u64::from(u32::from_be_bytes([a, b, c, d])),
+        _ => u64::from_be_bytes(bytes.try_into().ok()?),
+    })
+}
@@ -0,0 +1,479 @@
+use std::cell::RefCell;
+
+use proptest::prelude::*;
+
+use super::*;
+use crate::hprof::{HeapRecord, record_at};
+use crate::testing::{HprofWriter, MiniHeap, sample};
+
+const H: u64 = 0x1000;
+const N1: u64 = 0x1100;
+const N2: u64 = 0x1200;
+const N3: u64 = 0x1300;
+const L: u64 = 0x1400;
+const R: u64 = 0x1500;
+const W: u64 = 0x1600;
+const N4: u64 = 0x1700;
+
+fn no_progress(_: HeapPhase, _: u64, _: u64) -> Result<(), HeapError> {
+    Ok(())
+}
+
+fn build(bytes: &[u8]) -> Result<HeapGraph, HeapError> {
+    build_graph(bytes, &Store::Ram, &no_progress, &CancellationToken::new())
+}
+
+fn index(g: &HeapGraph, id: u64) -> u32 {
+    g.ids.rank(id).unwrap_or_else(|| panic!("{id:#x} is not in the graph"))
+}
+
+fn class(g: &HeapGraph, name: &str) -> (u32, u64) {
+    let slot = g.classes.iter().position(|c| c.name == name).unwrap_or_else(|| panic!("no class {name}"));
+    (slot as u32, g.classes[slot].id)
+}
+
+/// Targets of `id`'s edges, as ids, in edge order.
+fn out_of(g: &HeapGraph, id: u64) -> Vec<u64> {
+    g.out_edges(index(g, id)).iter().map(|&t| g.ids.id_at(t)).collect()
+}
+
+fn root_targets(g: &HeapGraph) -> Vec<u64> {
+    g.out_edges(g.root).iter().map(|&t| g.ids.id_at(t)).collect()
+}
+
+fn assert_csr(g: &HeapGraph) {
+    let n = g.ids.len();
+    assert_eq!(g.root, n);
+    assert_eq!(g.out_start.len(), n as usize + 2);
+    assert_eq!(g.out_start[0], 0);
+    assert!(g.out_start.windows(2).all(|w| w[0] <= w[1]), "out_start is not monotone");
+    assert_eq!(g.out_start[n as usize + 1] as usize, g.out.len());
+    assert!(g.out.iter().all(|&t| t < n), "edge to a node outside the objects");
+    assert_eq!((g.types.len(), g.lens.len(), g.offsets.len()), (n as usize, n as usize, n as usize));
+    let slots = g.classes.len() as u32 + PRIM_SLOTS;
+    assert!(g.types.iter().all(|&t| t < slots), "type outside the slots");
+    for c in &g.classes {
+        let mut steps = 0;
+        let mut cursor = c.super_index;
+        while let Some(s) = cursor {
+            steps += 1;
+            assert!(steps <= g.classes.len(), "super chain of {} does not end", c.name);
+            cursor = g.classes[s as usize].super_index;
+        }
+    }
+}
+
+#[test]
+fn edges_follow_fields_and_skip_weak_referents() {
+    let g = build(&sample().bytes()).unwrap();
+    assert_csr(&g);
+    let (_, holder) = class(&g, "Holder");
+    let (_, node) = class(&g, "Node");
+    let (_, weak) = class(&g, "java.lang.ref.WeakReference");
+    assert_eq!(out_of(&g, H), [N1, N2, holder]);
+    assert_eq!(out_of(&g, N1), [N3, node]);
+    assert_eq!(out_of(&g, N3), [L, node]);
+    assert_eq!(out_of(&g, W), [weak]);
+    assert_eq!(out_of(&g, N4), [node]);
+    assert_eq!(out_of(&g, L), Vec::<u64>::new());
+    assert_eq!(g.weak_edges_skipped, 1);
+    let (reference, _) = class(&g, "java.lang.ref.Reference");
+    assert_eq!(g.classes[reference as usize].weak_field, Some(0));
+    assert!(g.classes.iter().filter(|c| c.name != "java.lang.ref.Reference").all(|c| c.weak_field.is_none()));
+}
+
+#[test]
+fn object_arrays_skip_null_and_unknown() {
+    let mut heap = sample();
+    heap.array_of(0x1800, "[Ljava.lang.Object;", &[N2, 0, 0x9990, N1, 0xDEAD_BEEF]);
+    let g = build(&heap.bytes()).unwrap();
+    assert_csr(&g);
+    assert_eq!(out_of(&g, R), [N1]);
+    assert_eq!(out_of(&g, 0x1800), [N2, N1]);
+}
+
+#[test]
+fn super_root_points_at_each_root_once() {
+    let mut heap = sample();
+    heap.root(HeapRootKind::JniGlobal, H).root(HeapRootKind::MonitorUsed, H).root(HeapRootKind::JniLocal, 0x9990);
+    let g = build(&heap.bytes()).unwrap();
+    assert_csr(&g);
+    let targets = root_targets(&g);
+    assert_eq!(targets.iter().filter(|&&t| t == H).count(), 1);
+    assert!(targets.contains(&N3) && targets.contains(&W));
+    assert!(!targets.contains(&N1) && !targets.contains(&R) && !targets.contains(&N4));
+    let classes = g.classes.iter().filter(|c| c.id != 0).count();
+    assert_eq!(targets.len(), 3 + classes, "H, N3, W and every sticky class");
+    let mut sorted = targets.clone();
+    sorted.sort_unstable();
+    sorted.dedup();
+    assert_eq!(sorted.len(), targets.len());
+
+    let h = index(&g, H);
+    let of_h: Vec<_> = g.roots.iter().filter(|r| r.0 == h).map(|r| (r.1, r.2)).collect();
+    assert_eq!(of_h, [(HeapRootKind::JniGlobal, None), (HeapRootKind::MonitorUsed, None)]);
+    assert!(g.roots.contains(&(index(&g, N3), HeapRootKind::JavaFrame, Some(1))));
+    assert!(g.roots.iter().all(|r| r.0 < g.root));
+}
+
+#[test]
+fn class_dump_edges_cover_statics() {
+    let mut w = HprofWriter::new();
+    w.string(1, "java/lang/Object")
+        .load_class(0x100, 1)
+        .class(0x100, 0, &[], &[])
+        .string(2, "Config")
+        .string(3, "INSTANCE")
+        .string(4, "EMPTY")
+        .string(5, "LOST")
+        .load_class(0x200, 2)
+        .class_with_loader(0x200, 0x100, 0x1200, &[], &[(3, N1), (4, 0), (5, 0x9990)])
+        .instance(N1, 0x100, &[])
+        .instance(0x1200, 0x100, &[]);
+    let g = build(&w.finish()).unwrap();
+    assert_csr(&g);
+    assert_eq!(out_of(&g, 0x200), [0x100, 0x1200, N1]);
+    assert_eq!(out_of(&g, 0x100), Vec::<u64>::new());
+    let (config, _) = class(&g, "Config");
+    let info = &g.classes[config as usize];
+    let statics: Vec<_> = info.statics.iter().map(|(n, id)| (n.as_str(), *id)).collect();
+    assert_eq!(statics, [("INSTANCE", N1), ("EMPTY", 0), ("LOST", 0x9990)]);
+    assert_eq!(info.super_index, Some(class(&g, "java.lang.Object").0));
+}
+
+#[test]
+fn missing_class_is_an_error() {
+    let mut w = HprofWriter::new();
+    w.string(1, "java/lang/Object").load_class(0x100, 1).class(0x100, 0, &[], &[]).instance(N1, 0x999, &[]);
+    let bytes = w.finish();
+    let at = instance_offset(&bytes, N1);
+    let err = build(&bytes).err().unwrap();
+    assert!(matches!(err, HeapError::MissingClass { id: 0x999, at: a } if a == at as u64), "{err:?}");
+
+    let mut w = HprofWriter::new();
+    w.obj_array(0x10, 0x999, &[]);
+    assert!(matches!(build(&w.finish()), Err(HeapError::MissingClass { id: 0x999, .. })));
+}
+
+fn instance_offset(bytes: &[u8], id: u64) -> usize {
+    let header = crate::hprof::parse_header(bytes).unwrap();
+    let mut found = None;
+    crate::hprof::scan(bytes, &header, &mut |r| {
+        if let crate::hprof::Record::Heap { at, record: HeapRecord::Instance { id: i, .. } } = r
+            && i == id
+        {
+            found = Some(at);
+        }
+        Ok(())
+    })
+    .unwrap();
+    found.unwrap()
+}
+
+#[test]
+fn cancel_during_linking_returns_cancelled() {
+    let bytes = sample().bytes();
+    let cancelled = CancellationToken::new();
+    cancelled.cancel();
+    let result = build_graph(&bytes, &Store::Ram, &no_progress, &cancelled);
+    assert!(matches!(result, Err(HeapError::Cancelled)));
+
+    let cancel = CancellationToken::new();
+    let phases = RefCell::new(Vec::new());
+    let result = build_graph(
+        &bytes,
+        &Store::Ram,
+        &|phase, done, total| {
+            phases.borrow_mut().push((phase, done, total));
+            if phase == HeapPhase::Linking {
+                cancel.cancel();
+            }
+            Ok(())
+        },
+        &cancel,
+    );
+    assert!(matches!(result, Err(HeapError::Cancelled)));
+    let phases = phases.into_inner();
+    assert_eq!(phases.first(), Some(&(HeapPhase::Reading, 0, bytes.len() as u64)));
+    assert_eq!(phases.last(), Some(&(HeapPhase::Linking, 0, 15)), "stops at the first Linking report");
+}
+
+#[test]
+fn progress_error_stops_the_build() {
+    let bytes = sample().bytes();
+    let fail = |phase, _, total| {
+        if phase == HeapPhase::Linking {
+            Err(HeapError::NotEnoughDiskSpace { needed: total * 90, available: 0 })
+        } else {
+            Ok(())
+        }
+    };
+    let result = build_graph(&bytes, &Store::Ram, &fail, &CancellationToken::new());
+    assert!(matches!(result, Err(HeapError::NotEnoughDiskSpace { needed: 1350, available: 0 })));
+}
+
+#[test]
+fn progress_reads_bytes_then_links_objects() {
+    let bytes = sample().bytes();
+    let phases = RefCell::new(Vec::new());
+    let g = build_graph(
+        &bytes,
+        &Store::Ram,
+        &|phase, done, total| {
+            phases.borrow_mut().push((phase, done, total));
+            Ok(())
+        },
+        &CancellationToken::new(),
+    )
+    .unwrap();
+    let phases = phases.into_inner();
+    let len = bytes.len() as u64;
+    let objects = u64::from(g.root);
+    assert_eq!(objects, 15, "7 classes and 8 objects");
+    assert_eq!(phases.first(), Some(&(HeapPhase::Reading, 0, len)));
+    assert!(phases.contains(&(HeapPhase::Reading, len, len)));
+    let linking: Vec<_> = phases.iter().filter(|p| p.0 == HeapPhase::Linking).collect();
+    assert_eq!(linking.first(), Some(&&(HeapPhase::Linking, 0, objects)));
+    assert_eq!(linking.iter().filter(|p| ***p == (HeapPhase::Linking, 0, objects)).count(), 1, "{linking:?}");
+    assert_eq!(linking.last(), Some(&&(HeapPhase::Linking, objects, objects)));
+    assert!(phases.iter().all(|&(_, done, total)| done <= total));
+}
+
+#[test]
+fn types_lengths_and_offsets() {
+    let bytes = sample().bytes();
+    let g = build(&bytes).unwrap();
+    let (holder, holder_id) = class(&g, "Holder");
+    let (node, _) = class(&g, "Node");
+    let (array, _) = class(&g, "[Ljava.lang.Object;");
+    let (java_lang_class, _) = class(&g, "java.lang.Class");
+    assert_eq!(g.class_slot, java_lang_class);
+    let ty = |id| g.types[index(&g, id) as usize];
+    let len = |id| g.lens[index(&g, id) as usize];
+    assert_eq!([ty(H), ty(N1), ty(R), ty(holder_id)], [holder, node, array, java_lang_class]);
+    assert_eq!(ty(L), g.prim_slot(BasicType::Long));
+    assert_eq!(g.prim_type(ty(L)), Some(BasicType::Long));
+    assert_eq!(g.prim_type(holder), None);
+    assert_eq!(g.prim_type(g.classes.len() as u32 + PRIM_SLOTS), None);
+    assert_eq!(g.prim_slot(BasicType::Boolean), g.classes.len() as u32);
+    assert_eq!(g.prim_slot(BasicType::Long), g.classes.len() as u32 + PRIM_SLOTS - 1);
+    assert_eq!([len(H), len(L), len(R), len(holder_id)], [0, 2, 3, 0]);
+    for i in 0..g.root {
+        let id = match record_at(&bytes, g.offsets[i as usize] as usize, g.id_size).unwrap() {
+            HeapRecord::Class(c) => c.id,
+            HeapRecord::Instance { id, .. } | HeapRecord::ObjectArray { id, .. } => id,
+            HeapRecord::PrimitiveArray { id, .. } => id,
+            other => panic!("offset of object {i} points at {other:?}"),
+        };
+        assert_eq!(id, g.ids.id_at(i));
+    }
+    assert_eq!((g.id_size, g.timestamp_ms), (8, 1_700_000_000_000));
+    let holder_info = &g.classes[holder as usize];
+    let fields: Vec<_> = holder_info.fields.iter().map(|(n, t)| (n.as_str(), *t)).collect();
+    assert_eq!(fields, [("a", BasicType::Object), ("b", BasicType::Object)]);
+    assert_eq!(holder_info.super_index, Some(class(&g, "java.lang.Object").0));
+    assert_eq!(g.classes[class(&g, "java.lang.Object").0 as usize].super_index, None);
+}
+
+#[test]
+fn dump_without_java_lang_class_gets_a_synthetic_slot() {
+    let mut w = HprofWriter::new();
+    w.string(1, "java/lang/Object").load_class(0x100, 1).class(0x100, 0, &[], &[]).instance(N1, 0x100, &[]);
+    let g = build(&w.finish()).unwrap();
+    assert_csr(&g);
+    assert_eq!(g.classes.len(), 2);
+    let synthetic = &g.classes[g.class_slot as usize];
+    assert_eq!((synthetic.id, synthetic.name.as_str(), synthetic.super_index), (0, "java.lang.Class", None));
+    assert_eq!(g.types[index(&g, 0x100) as usize], g.class_slot);
+    assert_eq!(g.types[index(&g, N1) as usize], 0);
+}
+
+#[test]
+fn classes_without_a_name_record_get_their_address() {
+    let mut w = HprofWriter::new();
+    w.class(0x100, 0, &[(9, BasicType::Object)], &[])
+        .instance(N1, 0x100, &N2.to_be_bytes())
+        .instance(N2, 0x100, &[0; 8]);
+    let g = build(&w.finish()).unwrap();
+    assert_eq!(g.classes[0].name, "0x100");
+    assert_eq!(g.classes[0].fields, [(String::new(), BasicType::Object)]);
+    assert_eq!(out_of(&g, N1), [N2, 0x100]);
+}
+
+#[test]
+fn thread_objects_map_serials_to_threads() {
+    let mut heap = sample();
+    heap.class("java.lang.Thread", Some("java.lang.Object"), &[])
+        .object(0x2000, "java.lang.Thread", &[])
+        .object(0x2100, "java.lang.Thread", &[])
+        .root_in_thread(HeapRootKind::ThreadObject, 0x2000, 1)
+        .root_in_thread(HeapRootKind::ThreadObject, 0x2100, 7)
+        .root_in_thread(HeapRootKind::ThreadObject, 0x9990, 9);
+    let g = build(&heap.bytes()).unwrap();
+    let expected: HashMap<u32, u32> = [(1, index(&g, 0x2000)), (7, index(&g, 0x2100))].into();
+    assert_eq!(g.thread_objects, expected);
+    assert!(g.roots.contains(&(index(&g, 0x2100), HeapRootKind::ThreadObject, Some(7))));
+}
+
+#[test]
+fn inherited_fields_follow_the_class_first_layout() {
+    let mut heap = MiniHeap::new();
+    heap.class("A", Some("java.lang.Object"), &[("a", BasicType::Object), ("n", BasicType::Int)])
+        .class("Empty", Some("A"), &[])
+        .class("B", Some("Empty"), &[("flag", BasicType::Byte), ("b", BasicType::Object)])
+        .object(0x10, "B", &[("a", 0x20), ("b", 0x30), ("flag", 1)])
+        .object(0x20, "A", &[])
+        .object(0x30, "A", &[]);
+    let g = build(&heap.bytes()).unwrap();
+    assert_csr(&g);
+    assert_eq!(out_of(&g, 0x10), [0x30, 0x20, class(&g, "B").1]);
+}
+
+#[test]
+fn super_class_cycles_are_cut() {
+    let mut w = HprofWriter::new();
+    w.string(1, "A")
+        .string(2, "B")
+        .string(3, "S")
+        .string(4, "f")
+        .load_class(0x100, 1)
+        .load_class(0x200, 2)
+        .load_class(0x300, 3)
+        .class(0x100, 0x200, &[(4, BasicType::Object)], &[])
+        .class(0x200, 0x100, &[(4, BasicType::Object)], &[])
+        .class(0x300, 0x300, &[], &[])
+        .instance(0x10, 0x100, &[[0; 7].as_slice(), &[0x20], &[0; 7], &[0x30]].concat())
+        .instance(0x20, 0x300, &[])
+        .instance(0x30, 0x300, &[0; 64]);
+    let g = build(&w.finish()).unwrap();
+    assert_csr(&g);
+    assert_eq!(out_of(&g, 0x10), [0x20, 0x30, 0x100]);
+    assert_eq!(out_of(&g, 0x30), [0x300]);
+}
+
+#[test]
+fn short_instance_data_stops_at_the_last_whole_field() {
+    let mut w = HprofWriter::new();
+    w.string(1, "P")
+        .string(2, "x")
+        .load_class(0x100, 1)
+        .class(0x100, 0, &[(2, BasicType::Object), (2, BasicType::Object)], &[])
+        .instance(0x10, 0x100, &[[0; 7].as_slice(), &[0x20], &[0; 5]].concat())
+        .instance(0x20, 0x100, &[]);
+    let g = build(&w.finish()).unwrap();
+    assert_csr(&g);
+    assert_eq!(out_of(&g, 0x10), [0x20, 0x100]);
+}
+
+#[test]
+fn id_size_4_dump_links() {
+    let mut w = HprofWriter::with_id_size(4);
+    w.string(1, "Node")
+        .string(2, "next")
+        .load_class(0x100, 1)
+        .class(0x100, 0, &[(2, BasicType::Object)], &[(2, 0x20)])
+        .instance(0x10, 0x100, &0x20u32.to_be_bytes())
+        .instance(0x20, 0x100, &[0; 4])
+        .obj_array(0x30, 0x100, &[0x10, 0, 0x20])
+        .root(HeapRootKind::JniGlobal, 0x30);
+    let g = build(&w.finish()).unwrap();
+    assert_csr(&g);
+    assert_eq!(g.id_size, 4);
+    assert_eq!(out_of(&g, 0x10), [0x20, 0x100]);
+    assert_eq!(out_of(&g, 0x30), [0x10, 0x20]);
+    assert_eq!(out_of(&g, 0x100), [0x20]);
+    assert_eq!(root_targets(&g), [0x30]);
+}
+
+#[test]
+fn dir_store_keeps_types_and_offsets_only() {
+    let dir = tempfile::tempdir().unwrap();
+    // The id map's own files (`ids.*`) depend on its layout; MiniHeap's class ids are unaligned.
+    let names = || {
+        let mut names: Vec<_> = std::fs::read_dir(dir.path())
+            .unwrap()
+            .map(|e| e.unwrap().file_name().into_string().unwrap())
+            .filter(|name| !name.starts_with("ids."))
+            .collect();
+        names.sort();
+        names
+    };
+    let g =
+        build_graph(&sample().bytes(), &Store::Dir(dir.path().to_path_buf()), &no_progress, &CancellationToken::new())
+            .unwrap();
+    assert_eq!(out_of(&g, H).len(), 3);
+    let kept = ["offsets.u64", "types.u32"];
+    assert!(dir.path().join("ids.sorted.u64").exists());
+    #[cfg(unix)]
+    assert_eq!(names(), kept);
+    drop(g);
+    assert_eq!(names(), kept);
+}
+
+#[test]
+fn empty_dump_has_only_the_super_root() {
+    let g = build(&HprofWriter::new().finish()).unwrap();
+    assert_csr(&g);
+    assert_eq!((g.root, g.out.len(), g.classes.len()), (0, 0, 1));
+    assert_eq!(g.class_slot, 0);
+}
+
+#[test]
+fn edge_count_past_u32_is_too_large() {
+    let cancel = CancellationToken::new();
+    let mut counts = [0, 2, 0, 3, 1];
+    assert_eq!(accumulate(&mut counts, &cancel).unwrap(), 6);
+    assert_eq!(counts, [0, 2, 2, 5, 6]);
+    let mut full = [0, u32::MAX - 1, 1];
+    assert_eq!(accumulate(&mut full, &cancel).unwrap(), u32::MAX);
+    let mut over = [0, u32::MAX, 1];
+    assert!(matches!(accumulate(&mut over, &cancel), Err(HeapError::TooLarge)));
+    cancel.cancel();
+    assert!(matches!(accumulate(&mut [0, 1], &cancel), Err(HeapError::Cancelled)));
+}
+
+/// A class with `fields` instance fields, every one named by the same `name_len`-byte UTF8 record.
+fn shared_long_field_names(name_len: usize, fields: usize) -> Vec<u8> {
+    let mut w = HprofWriter::new();
+    let long = "f".repeat(name_len);
+    w.string(1, "java/lang/Object").load_class(0x100, 1).class(0x100, 0, &[], &[]);
+    w.string(2, "Wide").string(3, &long).load_class(0x200, 2);
+    w.class(0x200, 0x100, &vec![(3, BasicType::Int); fields], &[]);
+    w.finish()
+}
+
+#[test]
+fn names_that_would_decode_far_larger_than_the_file_are_refused() {
+    // 128 MiB of names from a file of about 70 KB.
+    let bytes = shared_long_field_names(32 << 10, 4000);
+    assert!(bytes.len() < 100 << 10, "{}", bytes.len());
+    let err = build(&bytes).err().expect("refused");
+    assert!(matches!(err, HeapError::NamesTooLarge), "{err:?}");
+}
+
+#[test]
+fn a_name_longer_than_the_jvm_allows_is_refused() {
+    let mut w = HprofWriter::new();
+    w.string(1, &"C".repeat(70_000)).load_class(0x100, 1).class(0x100, 0, &[], &[]);
+    assert!(matches!(build(&w.finish()), Err(HeapError::NamesTooLarge)));
+}
+
+#[test]
+fn real_sized_names_shared_by_many_fields_are_fine() {
+    let g = build(&shared_long_field_names(40, 4000)).unwrap();
+    assert_eq!(g.classes[class(&g, "Wide").0 as usize].fields.len(), 4000);
+}
+
+proptest! {
+    #[test]
+    fn build_graph_never_panics_on_mutated_dumps(flips in proptest::collection::vec((0usize..4096, any::<u8>()), 1..12)) {
+        let mut bytes = sample().bytes();
+        for (pos, value) in flips {
+            let at = pos % bytes.len();
+            bytes[at] = value;
+        }
+        if let Ok(g) = build(&bytes) {
+            assert_csr(&g);
+        }
+    }
+}
@@ -0,0 +1,945 @@
+//! Reader for HotSpot `.hprof` heap dumps (format 1.0.1 / 1.0.2, 4- or 8-byte ids).
+
+use std::ops::Range;
+
+use serde::{Deserialize, Serialize};
+
+use crate::error::HeapError;
+use crate::reader::Reader;
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+#[repr(u8)]
+pub enum BasicType {
+    Object = 2,
+    Boolean = 4,
+    Char = 5,
+    Float = 6,
+    Double = 7,
+    Byte = 8,
+    Short = 9,
+    Int = 10,
+    Long = 11,
+}
+
+impl BasicType {
+    pub fn from_u8(v: u8) -> Option<Self> {
+        Some(match v {
+            2 => Self::Object,
+            4 => Self::Boolean,
+            5 => Self::Char,
+            6 => Self::Float,
+            7 => Self::Double,
+            8 => Self::Byte,
+            9 => Self::Short,
+            10 => Self::Int,
+            11 => Self::Long,
+            _ => return None,
+        })
+    }
+
+    /// Bytes one value takes in the dump; `id_size` is the dump's identifier size.
+    pub fn hprof_size(self, id_size: u8) -> usize {
+        match self {
+            Self::Object => usize::from(id_size),
+            Self::Boolean | Self::Byte => 1,
+            Self::Char | Self::Short => 2,
+            Self::Float | Self::Int => 4,
+            Self::Double | Self::Long => 8,
+        }
+    }
+
+    /// Bytes one value takes in the JVM heap; `ref_size` is 4 with compressed oops, else 8.
+    pub fn heap_size(self, ref_size: u8) -> u64 {
+        match self {
+            Self::Object => u64::from(ref_size),
+            other => other.hprof_size(ref_size) as u64,
+        }
+    }
+
+    /// JVM class name of an array of this type (`[I`); `Object` arrays have no single name, so
+    /// they report the most general one.
+    pub fn array_name(self) -> &'static str {
+        match self {
+            Self::Object => "[Ljava.lang.Object;",
+            Self::Boolean => "[Z",
+            Self::Char => "[C",
+            Self::Float => "[F",
+            Self::Double => "[D",
+            Self::Byte => "[B",
+            Self::Short => "[S",
+            Self::Int => "[I",
+            Self::Long => "[J",
+        }
+    }
+}
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(rename_all = "camelCase")]
+pub enum HeapRootKind {
+    Unknown,
+    JniGlobal,
+    JniLocal,
+    JavaFrame,
+    NativeStack,
+    StickyClass,
+    ThreadBlock,
+    MonitorUsed,
+    ThreadObject,
+}
+
+#[derive(Clone, Debug, PartialEq, Eq)]
+pub struct HprofHeader {
+    pub version: String,
+    pub id_size: u8,
+    pub timestamp_ms: u64,
+    /// Offset of the first record.
+    pub body_start: usize,
+}
+
+#[derive(Clone, Debug, PartialEq, Eq)]
+pub struct ClassDump {
+    pub id: u64,
+    pub super_id: u64,
+    pub loader_id: u64,
+    /// `(name id, object id)` of reference statics; a null static has object id 0.
+    pub statics: Vec<(u64, u64)>,
+    /// Heap bytes taken by the primitive statics.
+    pub static_bytes: u64,
+    /// Instance fields in dump order, `(name id, type)`.
+    pub fields: Vec<(u64, BasicType)>,
+}
+
+#[derive(Clone, Debug, PartialEq, Eq)]
+pub enum HeapRecord<'a> {
+    /// `thread_serial` is present for the kinds that carry one.
+    Root {
+        kind: HeapRootKind,
+        id: u64,
+        thread_serial: Option<u32>,
+    },
+    Class(ClassDump),
+    /// `data` is the field values, class first, then each superclass.
+    Instance {
+        id: u64,
+        class_id: u64,
+        data: &'a [u8],
+    },
+    /// `data` is `len` ids.
+    ObjectArray {
+        id: u64,
+        class_id: u64,
+        len: u32,
+        data: &'a [u8],
+    },
+    /// `data` is `len` big-endian elements.
+    PrimitiveArray {
+        id: u64,
+        ty: BasicType,
+        len: u32,
+        data: &'a [u8],
+    },
+}
+
+#[derive(Clone, Debug, PartialEq, Eq)]
+pub enum Record<'a> {
+    Utf8 {
+        id: u64,
+        text: &'a [u8],
+    },
+    LoadClass {
+        class_id: u64,
+        name_id: u64,
+    },
+    /// Byte range of a heap-dump segment's sub-records; its contents follow as `Heap` records.
+    Segment(Range<usize>),
+    /// `at` is the offset of the sub-record's tag, for [`record_at`].
+    Heap {
+        at: usize,
+        record: HeapRecord<'a>,
+    },
+}
+
+const MAGIC_1_0_2: &[u8] = b"JAVA PROFILE 1.0.2\0";
+const MAGIC_1_0_1: &[u8] = b"JAVA PROFILE 1.0.1\0";
+
+const TAG_UTF8: u8 = 0x01;
+const TAG_LOAD_CLASS: u8 = 0x02;
+const TAG_HEAP_DUMP: u8 = 0x0C;
+const TAG_HEAP_DUMP_SEGMENT: u8 = 0x1C;
+const TAG_HEAP_DUMP_END: u8 = 0x2C;
+/// Tag (u1), timestamp (u4) and body length (u4).
+const RECORD_HEADER_LEN: usize = 9;
+
+fn check_id_size(id_size: u8) -> Result<(), HeapError> {
+    match id_size {
+        4 | 8 => Ok(()),
+        other => Err(HeapError::UnsupportedIdSize(u32::from(other))),
+    }
+}
+
+fn truncated(buf: &[u8]) -> HeapError {
+    HeapError::Truncated { at: buf.len() as u64 }
+}
+
+pub fn parse_header(buf: &[u8]) -> Result<HprofHeader, HeapError> {
+    let magic =
+        [MAGIC_1_0_2, MAGIC_1_0_1].into_iter().find(|magic| buf.starts_with(magic)).ok_or(HeapError::NotHprof)?;
+    let mut r = Reader::new(buf, magic.len(), 8);
+    let id_size = r.u4()?;
+    let id_size = u8::try_from(id_size).map_err(|_| HeapError::UnsupportedIdSize(id_size))?;
+    check_id_size(id_size)?;
+    let timestamp_ms = r.u8()?;
+    let version = String::from_utf8_lossy(&magic[..magic.len() - 1]).into_owned();
+    Ok(HprofHeader { version, id_size, timestamp_ms, body_start: r.pos() })
+}
+
+/// Walks every top-level record and, for heap-dump segments, the sub-records inside them.
+/// A record whose length runs past the end of `buf` is `Truncated`, and so are segments that no
+/// HEAP DUMP END follows: HotSpot writes whole segments, so a dump it did not finish ends after one.
+pub fn scan<'a>(
+    buf: &'a [u8],
+    header: &HprofHeader,
+    visit: &mut dyn FnMut(Record<'a>) -> Result<(), HeapError>,
+) -> Result<(), HeapError> {
+    let id_size = header.id_size;
+    check_id_size(id_size)?;
+    if header.body_start > buf.len() {
+        return Err(truncated(buf));
+    }
+    let mut pos = header.body_start;
+    let mut unended_segments = false;
+    while pos < buf.len() {
+        let mut head = Reader::new(buf, pos, id_size);
+        let tag = head.u1()?;
+        head.skip(4)?; // timestamp
+        let len = head.u4()? as usize;
+        let start = pos + RECORD_HEADER_LEN;
+        let end = start.checked_add(len).filter(|&end| end <= buf.len()).ok_or_else(|| truncated(buf))?;
+        let body = &buf[..end];
+        let mut r = Reader::new(body, start, id_size);
+        match tag {
+            TAG_UTF8 => {
+                let id = r.id()?;
+                let text = r.bytes(end - r.pos())?;
+                visit(Record::Utf8 { id, text })?;
+            }
+            TAG_LOAD_CLASS => {
+                r.skip(4)?; // class serial
+                let class_id = r.id()?;
+                r.skip(4)?; // stack trace serial
+                let name_id = r.id()?;
+                visit(Record::LoadClass { class_id, name_id })?;
+            }
+            TAG_HEAP_DUMP | TAG_HEAP_DUMP_SEGMENT => {
+                // A single HEAP DUMP (JDK 8, under 2 GB) has no end record.
+                unended_segments |= tag == TAG_HEAP_DUMP_SEGMENT;
+                visit(Record::Segment(start..end))?;
+                walk_segment(buf, start..end, id_size, &mut |at, record| visit(Record::Heap { at, record }))?;
+            }
+            TAG_HEAP_DUMP_END => unended_segments = false,
+            _ => {}
+        }
+        pos = end;
+    }
+    if unended_segments {
+        return Err(truncated(buf));
+    }
+    Ok(())
+}
+
+/// Visits the sub-records of one segment (the range from [`Record::Segment`]) with their offsets.
+/// The last sub-record must end exactly at the segment's end.
+pub fn scan_segment<'a>(
+    buf: &'a [u8],
+    segment: Range<usize>,
+    id_size: u8,
+    visit: &mut dyn FnMut(usize, HeapRecord<'a>) -> Result<(), HeapError>,
+) -> Result<(), HeapError> {
+    check_id_size(id_size)?;
+    walk_segment(buf, segment, id_size, visit)
+}
+
+fn walk_segment<'a>(
+    buf: &'a [u8],
+    segment: Range<usize>,
+    id_size: u8,
+    visit: &mut dyn FnMut(usize, HeapRecord<'a>) -> Result<(), HeapError>,
+) -> Result<(), HeapError> {
+    if segment.start > segment.end || segment.end > buf.len() {
+        return Err(truncated(buf));
+    }
+    let mut r = Reader::new(&buf[..segment.end], segment.start, id_size);
+    while r.pos() < segment.end {
+        let at = r.pos();
+        let record = read_sub_record(&mut r)?;
+        visit(at, record)?;
+    }
+    Ok(())
+}
+
+/// Reads the sub-record whose tag is at `at`, as given by [`Record::Heap`].
+pub fn record_at(buf: &[u8], at: usize, id_size: u8) -> Result<HeapRecord<'_>, HeapError> {
+    check_id_size(id_size)?;
+    read_sub_record(&mut Reader::new(buf, at, id_size))
+}
+
+fn read_sub_record<'a>(r: &mut Reader<'a>) -> Result<HeapRecord<'a>, HeapError> {
+    let at = r.pos();
+    let tag = r.u1()?;
+    // (kind, carries a thread serial, bytes after it)
+    let root = match tag {
+        0xFF => Some((HeapRootKind::Unknown, false, 0)),
+        0x01 => Some((HeapRootKind::JniGlobal, false, usize::from(r.id_size()))),
+        0x02 => Some((HeapRootKind::JniLocal, true, 4)),
+        0x03 => Some((HeapRootKind::JavaFrame, true, 4)),
+        0x04 => Some((HeapRootKind::NativeStack, true, 0)),
+        0x05 => Some((HeapRootKind::StickyClass, false, 0)),
+        0x06 => Some((HeapRootKind::ThreadBlock, true, 0)),
+        0x07 => Some((HeapRootKind::MonitorUsed, false, 0)),
+        0x08 => Some((HeapRootKind::ThreadObject, true, 4)),
+        _ => None,
+    };
+    if let Some((kind, has_serial, trailing)) = root {
+        let id = r.id()?;
+        let thread_serial = if has_serial { Some(r.u4()?) } else { None };
+        r.skip(trailing)?;
+        return Ok(HeapRecord::Root { kind, id, thread_serial });
+    }
+    match tag {
+        0x20 => read_class_dump(r).map(HeapRecord::Class),
+        0x21 => {
+            let id = r.id()?;
+            r.skip(4)?; // stack trace serial
+            let class_id = r.id()?;
+            let len = r.u4()? as usize;
+            Ok(HeapRecord::Instance { id, class_id, data: r.bytes(len)? })
+        }
+        0x22 => {
+            let id = r.id()?;
+            r.skip(4)?;
+            let len = r.u4()?;
+            let class_id = r.id()?;
+            let size = (len as usize).checked_mul(usize::from(r.id_size())).ok_or_else(|| truncated(r.buf()))?;
+            Ok(HeapRecord::ObjectArray { id, class_id, len, data: r.bytes(size)? })
+        }
+        0x23 => {
+            let id = r.id()?;
+            r.skip(4)?;
+            let len = r.u4()?;
+            let ty = read_type(r)?;
+            if ty == BasicType::Object {
+                return Err(HeapError::UnknownType { ty: ty as u8, at: (r.pos() - 1) as u64 });
+            }
+            let size = (len as usize).checked_mul(ty.hprof_size(r.id_size())).ok_or_else(|| truncated(r.buf()))?;
+            Ok(HeapRecord::PrimitiveArray { id, ty, len, data: r.bytes(size)? })
+        }
+        tag => Err(HeapError::UnknownSubRecord { tag, at: at as u64 }),
+    }
+}
+
+fn read_type(r: &mut Reader<'_>) -> Result<BasicType, HeapError> {
+    let at = r.pos();
+    let ty = r.u1()?;
+    BasicType::from_u8(ty).ok_or(HeapError::UnknownType { ty, at: at as u64 })
+}
+
+fn read_class_dump(r: &mut Reader<'_>) -> Result<ClassDump, HeapError> {
+    let id_size = r.id_size();
+    let id = r.id()?;
+    r.skip(4)?; // stack trace serial
+    let super_id = r.id()?;
+    let loader_id = r.id()?;
+    r.skip(4 * usize::from(id_size))?; // signers, protection domain, 2 reserved
+    r.skip(4)?; // instance size
+
+    for _ in 0..r.u2()? {
+        r.skip(2)?; // constant pool index
+        let ty = read_type(r)?;
+        r.skip(ty.hprof_size(id_size))?;
+    }
+
+    let mut statics = Vec::new();
+    let mut static_bytes = 0;
+    for _ in 0..r.u2()? {
+        let name = r.id()?;
+        let ty = read_type(r)?;
+        if ty == BasicType::Object {
+            statics.push((name, r.id()?));
+        } else {
+            r.skip(ty.hprof_size(id_size))?;
+            static_bytes += ty.heap_size(id_size);
+        }
+    }
+
+    let mut fields = Vec::new();
+    for _ in 0..r.u2()? {
+        let name = r.id()?;
+        fields.push((name, read_type(r)?));
+    }
+    Ok(ClassDump { id, super_id, loader_id, statics, static_bytes, fields })
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::testing::{HprofWriter, MiniHeap};
+    use proptest::prelude::*;
+
+    fn collect(bytes: &[u8]) -> Result<Vec<Record<'_>>, HeapError> {
+        let header = parse_header(bytes)?;
+        let mut out = Vec::new();
+        scan(bytes, &header, &mut |r| {
+            out.push(r);
+            Ok(())
+        })?;
+        Ok(out)
+    }
+
+    fn segment_of(bytes: &[u8]) -> Range<usize> {
+        collect(bytes)
+            .unwrap()
+            .into_iter()
+            .find_map(|r| if let Record::Segment(s) = r { Some(s) } else { None })
+            .expect("a segment")
+    }
+
+    fn all_kinds(w: &mut HprofWriter) {
+        w.string(1, "Node")
+            .string(2, "next")
+            .load_class(0x100, 1)
+            .class(0x100, 0, &[(2, BasicType::Object), (3, BasicType::Long)], &[(2, 0x10)])
+            .instance(0x10, 0x100, &[0u8; 16])
+            .obj_array(0x20, 0x100, &[0x10, 0])
+            .prim_array(0x30, BasicType::Int, 3)
+            .root(HeapRootKind::JavaFrame, 0x10)
+            .root(HeapRootKind::StickyClass, 0x100);
+    }
+
+    #[test]
+    fn parses_header() {
+        let header = parse_header(&MiniHeap::new().bytes()).unwrap();
+        assert_eq!((header.version.as_str(), header.id_size, header.body_start), ("JAVA PROFILE 1.0.2", 8, 31));
+
+        let mut old = b"JAVA PROFILE 1.0.1\0".to_vec();
+        old.extend_from_slice(&[0, 0, 0, 4, 0, 0, 0, 1, 0, 0, 0, 2]);
+        let header = parse_header(&old).unwrap();
+        assert_eq!(
+            (header.version.as_str(), header.id_size, header.timestamp_ms),
+            ("JAVA PROFILE 1.0.1", 4, (1 << 32) + 2)
+        );
+
+        let bad_size = b"JAVA PROFILE 1.0.2\0\0\0\0\x03\0\0\0\0\0\0\0\0";
+        assert!(matches!(parse_header(bad_size), Err(HeapError::UnsupportedIdSize(3))));
+        assert!(matches!(parse_header(b"GIF89a"), Err(HeapError::NotHprof)));
+        assert!(matches!(parse_header(b""), Err(HeapError::NotHprof)));
+        assert!(matches!(parse_header(b"JAVA PROFILE 1.0.3\0\0\0\0\x08"), Err(HeapError::NotHprof)));
+        assert!(matches!(parse_header(b"JAVA PROFILE 1.0.2\0\0\0"), Err(HeapError::Truncated { at: 21 })));
+    }
+
+    #[test]
+    fn scans_every_record_kind() {
+        let mut w = HprofWriter::new();
+        all_kinds(&mut w);
+        let bytes = w.finish();
+        let records = collect(&bytes).unwrap();
+
+        let (mut utf8, mut loads, mut segments) = (0, 0, 0);
+        let (mut classes, mut instances, mut obj_arrays, mut prim_arrays, mut roots) = (0, 0, 0, 0, 0);
+        for record in &records {
+            match record {
+                Record::Utf8 { .. } => utf8 += 1,
+                Record::LoadClass { class_id, name_id } => {
+                    loads += 1;
+                    assert_eq!((*class_id, *name_id), (0x100, 1));
+                }
+                Record::Segment(_) => segments += 1,
+                Record::Heap { record, .. } => match record {
+                    HeapRecord::Class(c) => {
+                        classes += 1;
+                        assert_eq!((c.id, c.super_id, c.loader_id), (0x100, 0, 0));
+                        assert_eq!(c.statics, [(2, 0x10)]);
+                        assert_eq!(c.fields, [(2, BasicType::Object), (3, BasicType::Long)]);
+                    }
+                    HeapRecord::Instance { id, class_id, data } => {
+                        instances += 1;
+                        assert_eq!((*id, *class_id, data.len()), (0x10, 0x100, 16));
+                    }
+                    HeapRecord::ObjectArray { id, class_id, len, data } => {
+                        obj_arrays += 1;
+                        assert_eq!((*id, *class_id, *len, data.len()), (0x20, 0x100, 2, 16));
+                    }
+                    HeapRecord::PrimitiveArray { id, ty, len, data } => {
+                        prim_arrays += 1;
+                        assert_eq!((*id, *ty, *len, data.len()), (0x30, BasicType::Int, 3, 12));
+                    }
+                    HeapRecord::Root { kind, id, thread_serial } => {
+                        roots += 1;
+                        match kind {
+                            HeapRootKind::JavaFrame => assert_eq!((*id, *thread_serial), (0x10, Some(1))),
+                            HeapRootKind::StickyClass => assert_eq!((*id, *thread_serial), (0x100, None)),
+                            other => panic!("unexpected root {other:?}"),
+                        }
+                    }
+                },
+            }
+        }
+        assert_eq!((utf8, loads, segments), (2, 1, 1));
+        assert_eq!((classes, instances, obj_arrays, prim_arrays, roots), (1, 1, 1, 1, 2));
+        assert!(matches!(&records[3], Record::Segment(s) if s.end <= bytes.len()), "segment precedes its contents");
+    }
+
+    #[test]
+    fn root_kinds_carry_the_thread_serial_they_have() {
+        let kinds = [
+            (HeapRootKind::Unknown, false),
+            (HeapRootKind::JniGlobal, false),
+            (HeapRootKind::JniLocal, true),
+            (HeapRootKind::JavaFrame, true),
+            (HeapRootKind::NativeStack, true),
+            (HeapRootKind::StickyClass, false),
+            (HeapRootKind::ThreadBlock, true),
+            (HeapRootKind::MonitorUsed, false),
+            (HeapRootKind::ThreadObject, true),
+        ];
+        let mut w = HprofWriter::new();
+        for (i, (kind, _)) in kinds.iter().enumerate() {
+            w.root_in_thread(*kind, 0x40 + i as u64, 7);
+            w.root(*kind, 0x80 + i as u64);
+        }
+        let bytes = w.finish();
+        let mut seen = Vec::new();
+        for r in collect(&bytes).unwrap() {
+            if let Record::Heap { record: HeapRecord::Root { kind, id, thread_serial }, .. } = r {
+                seen.push((kind, id, thread_serial));
+            }
+        }
+        assert_eq!(seen.len(), kinds.len() * 2);
+        for (i, (kind, carries)) in kinds.iter().enumerate() {
+            let explicit = seen[2 * i];
+            let default = seen[2 * i + 1];
+            assert_eq!(explicit, (*kind, 0x40 + i as u64, carries.then_some(7)));
+            assert_eq!(default, (*kind, 0x80 + i as u64, carries.then_some(1)));
+        }
+    }
+
+    #[test]
+    fn primitive_arrays_expose_their_contents() {
+        let mut w = HprofWriter::new();
+        w.prim_bytes(0x1, BasicType::Char, &[0, b'h', 0, 0xE9]).prim_bytes(0x2, BasicType::Byte, b"v42");
+        let bytes = w.finish();
+        let arrays: Vec<_> = collect(&bytes)
+            .unwrap()
+            .into_iter()
+            .filter_map(|r| match r {
+                Record::Heap { record: HeapRecord::PrimitiveArray { ty, len, data, .. }, .. } => {
+                    Some((ty, len, data.to_vec()))
+                }
+                _ => None,
+            })
+            .collect();
+        assert_eq!(arrays, [(BasicType::Char, 2, vec![0, b'h', 0, 0xE9]), (BasicType::Byte, 3, b"v42".to_vec())]);
+    }
+
+    #[test]
+    fn mini_heap_builds_strings_and_defines_object_and_class() {
+        let mut heap = MiniHeap::new();
+        heap.string(0x10, "v42", true).string(0x20, "hé", false);
+        let bytes = heap.bytes();
+        let records = collect(&bytes).unwrap();
+        let names: Vec<_> = records
+            .iter()
+            .filter_map(|r| {
+                if let Record::Utf8 { text, .. } = r { Some(String::from_utf8_lossy(text).into_owned()) } else { None }
+            })
+            .collect();
+        assert!(names.iter().any(|n| n == "java/lang/Object") && names.iter().any(|n| n == "java/lang/Class"));
+        let arrays: Vec<_> = records
+            .iter()
+            .filter_map(|r| match r {
+                Record::Heap { record: HeapRecord::PrimitiveArray { data, .. }, .. } => Some(data.to_vec()),
+                _ => None,
+            })
+            .collect();
+        assert_eq!(arrays, [b"v42".to_vec(), vec![b'h', 0, 0xE9, 0]]);
+        let coders: Vec<_> = records
+            .iter()
+            .filter_map(|r| match r {
+                Record::Heap { record: HeapRecord::Instance { id, data, .. }, .. } => Some((*id, data[8])),
+                _ => None,
+            })
+            .collect();
+        assert_eq!(coders, [(0x10, 0), (0x20, 1)]);
+    }
+
+    #[test]
+    fn mini_heap_lays_out_fields_class_first_then_super() {
+        let mut heap = MiniHeap::new();
+        heap.class("A", Some("java.lang.Object"), &[("a", BasicType::Int)])
+            .class("B", Some("A"), &[("b", BasicType::Object), ("c", BasicType::Byte)])
+            .object(0x10, "B", &[("a", 7), ("b", 0x99), ("c", 0x1FF)]);
+        let bytes = heap.bytes();
+        let data = collect(&bytes)
+            .unwrap()
+            .into_iter()
+            .find_map(|r| match r {
+                Record::Heap { record: HeapRecord::Instance { data, .. }, .. } => Some(data.to_vec()),
+                _ => None,
+            })
+            .unwrap();
+        assert_eq!(data, [0, 0, 0, 0, 0, 0, 0, 0x99, 0xFF, 0, 0, 0, 7]);
+    }
+
+    #[test]
+    fn record_at_reads_back_an_instance() {
+        let mut w = HprofWriter::new();
+        all_kinds(&mut w);
+        let bytes = w.finish();
+        let at = collect(&bytes)
+            .unwrap()
+            .into_iter()
+            .find_map(|r| match r {
+                Record::Heap { at, record: HeapRecord::Instance { .. } } => Some(at),
+                _ => None,
+            })
+            .unwrap();
+        match record_at(&bytes, at, 8).unwrap() {
+            HeapRecord::Instance { id, class_id, data } => assert_eq!((id, class_id, data.len()), (0x10, 0x100, 16)),
+            other => panic!("expected an instance, got {other:?}"),
+        }
+        assert!(matches!(record_at(&bytes, bytes.len(), 8), Err(HeapError::Truncated { .. })));
+        assert!(matches!(record_at(&bytes, at, 3), Err(HeapError::UnsupportedIdSize(3))));
+    }
+
+    #[test]
+    fn scan_segment_visits_the_same_records_scan_does() {
+        let mut w = HprofWriter::new();
+        all_kinds(&mut w);
+        let bytes = w.finish();
+        let from_scan: Vec<_> = collect(&bytes)
+            .unwrap()
+            .into_iter()
+            .filter_map(|r| if let Record::Heap { at, record } = r { Some((at, record)) } else { None })
+            .collect();
+        let mut from_segment = Vec::new();
+        scan_segment(&bytes, segment_of(&bytes), 8, &mut |at, record| {
+            from_segment.push((at, record));
+            Ok(())
+        })
+        .unwrap();
+        assert_eq!(from_scan.len(), 6);
+        assert_eq!(from_scan, from_segment);
+    }
+
+    #[test]
+    fn visitor_errors_stop_the_scan() {
+        let bytes = MiniHeap::new().bytes();
+        let header = parse_header(&bytes).unwrap();
+        let mut calls = 0;
+        let result = scan(&bytes, &header, &mut |_| {
+            calls += 1;
+            Err(HeapError::Cancelled)
+        });
+        assert!(matches!(result, Err(HeapError::Cancelled)));
+        assert_eq!(calls, 1);
+    }
+
+    #[test]
+    fn both_heap_dump_tags_are_segments() {
+        let bytes = MiniHeap::new().bytes();
+        let segment = segment_of(&bytes);
+        let mut old_style = bytes.clone();
+        old_style[segment.start - 9] = 0x0C;
+        assert_eq!(segment_of(&old_style), segment);
+    }
+
+    #[test]
+    fn id_size_4_dump_parses() {
+        let mut w = HprofWriter::with_id_size(4);
+        w.string(1, "Node")
+            .load_class(0x100, 1)
+            .class(0x100, 0, &[(2, BasicType::Object), (3, BasicType::Long)], &[(2, 0x10)])
+            .instance(0x10, 0x100, &[0u8; 12])
+            .obj_array(0x20, 0x100, &[0x10, 0, 0xFFFF_FFFF])
+            .prim_array(0x30, BasicType::Short, 5)
+            .root(HeapRootKind::ThreadObject, 0x10);
+        let bytes = w.finish();
+        let header = parse_header(&bytes).unwrap();
+        assert_eq!((header.id_size, header.body_start), (4, 31));
+        let records: Vec<_> = collect(&bytes)
+            .unwrap()
+            .into_iter()
+            .filter_map(|r| if let Record::Heap { record, .. } = r { Some(record) } else { None })
+            .collect();
+        assert_eq!(records.len(), 5);
+        match &records[0] {
+            HeapRecord::Class(c) => {
+                assert_eq!((c.id, c.statics.as_slice(), c.fields.len()), (0x100, &[(2, 0x10)][..], 2));
+            }
+            other => panic!("expected the class, got {other:?}"),
+        }
+        assert!(matches!(&records[1], HeapRecord::Instance { id: 0x10, class_id: 0x100, data } if data.len() == 12));
+        assert!(
+            matches!(&records[2], HeapRecord::ObjectArray { len: 3, data, .. } if data.len() == 12 && data[8..] == [0xFF; 4])
+        );
+        assert!(
+            matches!(&records[3], HeapRecord::PrimitiveArray { ty: BasicType::Short, len: 5, data, .. } if data.len() == 10)
+        );
+        assert!(matches!(
+            &records[4],
+            HeapRecord::Root { kind: HeapRootKind::ThreadObject, id: 0x10, thread_serial: Some(1) }
+        ));
+    }
+
+    fn push_id(out: &mut Vec<u8>, v: u64) {
+        out.extend_from_slice(&v.to_be_bytes());
+    }
+
+    /// A class dump written by hand: loader, a constant-pool entry, and statics of each shape.
+    fn class_dump_bytes(last_field_type: u8) -> Vec<u8> {
+        let mut b = vec![0x20];
+        push_id(&mut b, 0x500);
+        b.extend_from_slice(&0u32.to_be_bytes());
+        for id in [0x400, 0x77, 0, 0, 0, 0] {
+            push_id(&mut b, id); // super, loader, signers, domain, 2 reserved
+        }
+        b.extend_from_slice(&24u32.to_be_bytes());
+        b.extend_from_slice(&[0, 1, 0, 7, 10, 0, 0, 0, 99]); // constant pool: one int
+        b.extend_from_slice(&[0, 3]);
+        push_id(&mut b, 0xA);
+        b.push(2);
+        push_id(&mut b, 0xBEEF); // object static
+        push_id(&mut b, 0xB);
+        b.push(10);
+        b.extend_from_slice(&5u32.to_be_bytes()); // int static
+        push_id(&mut b, 0xC);
+        b.push(11);
+        b.extend_from_slice(&6u64.to_be_bytes()); // long static
+        b.extend_from_slice(&[0, 2]);
+        push_id(&mut b, 0xD);
+        b.push(2);
+        push_id(&mut b, 0xE);
+        b.push(last_field_type);
+        b
+    }
+
+    #[test]
+    fn class_dump_reads_loader_statics_and_skips_the_constant_pool() {
+        let bytes = class_dump_bytes(11);
+        let HeapRecord::Class(c) = record_at(&bytes, 0, 8).unwrap() else { panic!("expected a class") };
+        assert_eq!((c.id, c.super_id, c.loader_id), (0x500, 0x400, 0x77));
+        assert_eq!(c.statics, [(0xA, 0xBEEF)]);
+        assert_eq!(c.static_bytes, 12);
+        assert_eq!(c.fields, [(0xD, BasicType::Object), (0xE, BasicType::Long)]);
+    }
+
+    #[test]
+    fn unknown_value_type_reports_its_offset() {
+        let bytes = class_dump_bytes(0x63);
+        let err = record_at(&bytes, 0, 8).unwrap_err();
+        assert!(matches!(err, HeapError::UnknownType { ty: 0x63, at } if at == bytes.len() as u64 - 1), "{err:?}");
+    }
+
+    #[test]
+    fn truncated_dump_reports_offset() {
+        let mut bytes = MiniHeap::new().bytes();
+        let body_start = parse_header(&bytes).unwrap().body_start as u64;
+        bytes.truncate(bytes.len() - 5);
+        let err = collect(&bytes).unwrap_err();
+        assert!(matches!(err, HeapError::Truncated { at } if at > body_start && at == bytes.len() as u64), "{err:?}");
+        assert!(err.to_string().contains(&bytes.len().to_string()));
+    }
+
+    /// HotSpot flushes whole segments, so a JVM killed while dumping leaves a file that ends
+    /// right after one, without HEAP DUMP END.
+    #[test]
+    fn a_dump_the_jvm_did_not_finish_ends_early() {
+        let mut bytes = MiniHeap::new().bytes();
+        bytes.truncate(bytes.len() - RECORD_HEADER_LEN);
+        let err = collect(&bytes).unwrap_err();
+        assert!(matches!(err, HeapError::Truncated { at } if at == bytes.len() as u64), "{err:?}");
+        assert!(err.to_string().starts_with("the dump ends early"), "{err}");
+    }
+
+    #[test]
+    fn every_prefix_is_ok_or_truncated_at_its_length() {
+        let mut heap = MiniHeap::new();
+        heap.class("N", Some("java.lang.Object"), &[("next", BasicType::Object)])
+            .object(0x10, "N", &[("next", 0x20)])
+            .string(0x20, "x", true)
+            .root(HeapRootKind::ThreadObject, 0x10);
+        let bytes = heap.bytes();
+        let header = parse_header(&bytes).unwrap();
+        let segment = segment_of(&bytes);
+        for cut in header.body_start..bytes.len() {
+            let prefix = &bytes[..cut];
+            match scan(prefix, &header, &mut |_| Ok(())) {
+                // Only a prefix without heap data is a complete (empty) dump.
+                Ok(()) => assert!(cut < segment.start, "cut at {cut} has heap data but no end"),
+                Err(HeapError::Truncated { at }) => assert_eq!(at, cut as u64, "cut at {cut}"),
+                Err(other) => panic!("cut at {cut}: {other:?}"),
+            }
+        }
+        let past_end = HprofHeader { body_start: bytes.len() + 1, ..header };
+        assert!(matches!(scan(&bytes, &past_end, &mut |_| Ok(())), Err(HeapError::Truncated { .. })));
+    }
+
+    #[test]
+    fn sub_record_overrunning_its_segment_is_truncated() {
+        let mut bytes = MiniHeap::new().bytes();
+        let segment = segment_of(&bytes);
+        let len_at = segment.start - 4;
+        let shrunk = (segment.len() as u32 - 3).to_be_bytes();
+        bytes[len_at..segment.start].copy_from_slice(&shrunk);
+        let err = collect(&bytes).unwrap_err();
+        assert!(matches!(err, HeapError::Truncated { at } if at == segment.end as u64 - 3), "{err:?}");
+    }
+
+    #[test]
+    fn unknown_sub_record_is_an_error() {
+        let mut bytes = MiniHeap::new().bytes();
+        let segment = segment_of(&bytes);
+        bytes[segment.start] = 0x99;
+        let err = collect(&bytes).unwrap_err();
+        assert!(matches!(err, HeapError::UnknownSubRecord { tag: 0x99, at } if at == segment.start as u64), "{err:?}");
+        assert!(err.to_string().contains("0x99"));
+    }
+
+    #[test]
+    fn array_lengths_larger_than_the_dump_do_not_allocate_or_panic() {
+        let mut b = vec![0x23];
+        push_id(&mut b, 1);
+        b.extend_from_slice(&0u32.to_be_bytes());
+        b.extend_from_slice(&u32::MAX.to_be_bytes());
+        b.push(11);
+        assert!(matches!(record_at(&b, 0, 8), Err(HeapError::Truncated { .. })));
+        b[0] = 0x22;
+        assert!(matches!(record_at(&b, 0, 8), Err(HeapError::Truncated { .. })));
+    }
+
+    #[test]
+    fn primitive_array_of_objects_is_an_unknown_type() {
+        let mut b = vec![0x23];
+        push_id(&mut b, 1);
+        b.extend_from_slice(&[0, 0, 0, 0, 0, 0, 0, 0]);
+        b.push(2);
+        assert!(matches!(record_at(&b, 0, 8), Err(HeapError::UnknownType { ty: 2, .. })));
+    }
+
+    #[test]
+    fn basic_type_sizes_and_names() {
+        assert_eq!(BasicType::from_u8(10), Some(BasicType::Int));
+        assert_eq!([0, 1, 3, 12, 255].map(BasicType::from_u8), [None; 5]);
+        assert_eq!((BasicType::Object.hprof_size(4), BasicType::Object.hprof_size(8)), (4, 8));
+        assert_eq!((BasicType::Object.heap_size(4), BasicType::Long.heap_size(4)), (4, 8));
+        assert_eq!((BasicType::Char.hprof_size(8), BasicType::Boolean.heap_size(8)), (2, 1));
+        assert_eq!(
+            (BasicType::Int.array_name(), BasicType::Boolean.array_name(), BasicType::Long.array_name()),
+            ("[I", "[Z", "[J")
+        );
+    }
+
+    fn sample() -> Vec<u8> {
+        let mut heap = MiniHeap::new();
+        heap.class("Node", Some("java.lang.Object"), &[("next", BasicType::Object), ("v", BasicType::Long)])
+            .class("[LNode;", Some("java.lang.Object"), &[])
+            .object(0x10, "Node", &[("next", 0x20), ("v", 5)])
+            .object(0x20, "Node", &[])
+            .array_of(0x30, "[LNode;", &[0x10, 0x20, 0])
+            .prim(0x40, BasicType::Int, 3)
+            .string(0x50, "hello", true)
+            .root(HeapRootKind::ThreadObject, 0x10)
+            .root(HeapRootKind::JniGlobal, 0x30);
+        heap.bytes()
+    }
+
+    fn with_header(id_size: u8, body: &[u8]) -> Vec<u8> {
+        let mut bytes = MAGIC_1_0_2.to_vec();
+        bytes.extend_from_slice(&u32::from(id_size).to_be_bytes());
+        bytes.extend_from_slice(&1_700_000_000_000u64.to_be_bytes());
+        bytes.extend_from_slice(body);
+        bytes
+    }
+
+    proptest! {
+        #[test]
+        fn parser_never_panics(bytes in proptest::collection::vec(any::<u8>(), 0..4096)) {
+            let _ = parse_header(&bytes).and_then(|h| scan(&bytes, &h, &mut |_| Ok(())));
+        }
+
+        /// Random bytes alone fail the magic check, so this puts a valid header in front to make
+        /// `scan` and `scan_segment` run on arbitrary record streams.
+        #[test]
+        fn random_bytes_after_a_valid_header_never_panic(
+            id_size in prop_oneof![Just(4u8), Just(8u8)],
+            body in proptest::collection::vec(any::<u8>(), 0..4096),
+        ) {
+            let bytes = with_header(id_size, &body);
+            let header = parse_header(&bytes).unwrap();
+            prop_assert_eq!(header.id_size, id_size);
+            let _ = scan(&bytes, &header, &mut |_| Ok(()));
+            let _ = scan_segment(&bytes, header.body_start..bytes.len(), id_size, &mut |_, _| Ok(()));
+            for at in header.body_start..bytes.len() {
+                let _ = record_at(&bytes, at, id_size);
+            }
+        }
+
+        /// Same, but every record has a correct length so the random bytes reach the heap-dump
+        /// segments and the sub-record parsers instead of stopping at the first bad length.
+        #[test]
+        fn random_records_after_a_valid_header_never_panic(
+            id_size in prop_oneof![Just(4u8), Just(8u8)],
+            records in proptest::collection::vec(
+                (
+                    prop_oneof![Just(0x01u8), Just(0x02), Just(0x0C), Just(0x1C), Just(0x2C), any::<u8>()],
+                    prop_oneof![
+                        Just(0x20u8), Just(0x21), Just(0x22), Just(0x23), Just(0x01), Just(0x02), Just(0x03),
+                        Just(0x04), Just(0x05), Just(0x06), Just(0x07), Just(0x08), Just(0xFF), any::<u8>()
+                    ],
+                    proptest::collection::vec(any::<u8>(), 0..96),
+                ),
+                0..12,
+            ),
+        ) {
+            let mut body = Vec::new();
+            for (tag, first, rest) in records {
+                let mut record_body = vec![first];
+                record_body.extend_from_slice(&rest);
+                body.push(tag);
+                body.extend_from_slice(&0u32.to_be_bytes());
+                body.extend_from_slice(&(record_body.len() as u32).to_be_bytes());
+                body.extend_from_slice(&record_body);
+            }
+            let bytes = with_header(id_size, &body);
+            let header = parse_header(&bytes).unwrap();
+            let mut segments = Vec::new();
+            let _ = scan(&bytes, &header, &mut |r| {
+                if let Record::Segment(s) = r {
+                    segments.push(s);
+                }
+                Ok(())
+            });
+            for s in segments {
+                let _ = scan_segment(&bytes, s, id_size, &mut |_, _| Ok(()));
+            }
+        }
+
+        #[test]
+        fn mutated_dump_never_panics(flips in proptest::collection::vec((0usize..2048, any::<u8>()), 1..16)) {
+            let pristine = sample();
+            let header = parse_header(&pristine).unwrap();
+            let segment = segment_of(&pristine);
+            let mut bytes = pristine.clone();
+            for (pos, value) in flips {
+                let at = pos % bytes.len();
+                bytes[at] = value;
+            }
+            let _ = scan(&bytes, &header, &mut |_| Ok(()));
+            for id_size in [4, 8] {
+                let _ = scan_segment(&bytes, segment.clone(), id_size, &mut |_, _| Ok(()));
+            }
+            for at in 0..bytes.len() {
+                let _ = record_at(&bytes, at, 8);
+            }
+        }
+    }
+}
@@ -0,0 +1,327 @@
+//! Maps hprof object ids (addresses) to dense `u32` indices in ascending address order.
+//!
+//! Object ids are addresses and objects are at least 8 bytes apart, so one bit per 8-byte slot
+//! ranks ids at about a byte per object. Addresses are grouped in 1 MiB chunks of
+//! [`WORDS_PER_CHUNK`] words; only chunks holding an id get words, and a dense table maps a chunk
+//! to its first word. The rank of an id is the number of set bits before its word plus the set
+//! bits below it in the word. Ids that are not multiples of 8, or that span too wide an address
+//! range for the table, use a sorted array and binary search instead.
+
+mod builder;
+
+pub(crate) use builder::ChunkHasher;
+pub use builder::IdMapBuilder;
+
+use crate::column::{Column, NONE};
+
+const SLOT_SHIFT: u32 = 3;
+const CHUNK_SLOT_BITS: u32 = 17;
+const WORD_BITS: u64 = 64;
+const WORDS_PER_CHUNK: usize = (1 << CHUNK_SLOT_BITS) / WORD_BITS as usize;
+
+// The bit table is matched in hot paths; boxing the big variant would only add
+// an indirection to save stack space `IdMap` never holds by value in bulk.
+#[allow(clippy::large_enum_variant)]
+enum Repr {
+    Bits {
+        /// Chunk number of the first table entry.
+        min_chunk: u64,
+        words: Column<u64>,
+        /// Set bits before each word.
+        wrank: Column<u32>,
+        /// Per chunk from `min_chunk` up: index of its first word, or `NONE` when it has no id.
+        table: Column<u32>,
+        /// Per chunk that has words, in word order: its offset from `min_chunk`.
+        chunk_offsets: Column<u32>,
+        len: u32,
+    },
+    Sorted(Column<u64>),
+}
+
+/// Ids ranked in ascending address order: the index of an object is its position in the order.
+pub struct IdMap {
+    repr: Repr,
+}
+
+impl IdMap {
+    pub fn len(&self) -> u32 {
+        match &self.repr {
+            Repr::Bits { len, .. } => *len,
+            Repr::Sorted(ids) => ids.len() as u32,
+        }
+    }
+
+    pub fn is_empty(&self) -> bool {
+        self.len() == 0
+    }
+
+    /// The index of `id`, or `None` when it is not in the map.
+    pub fn rank(&self, id: u64) -> Option<u32> {
+        match &self.repr {
+            Repr::Sorted(ids) => ids.binary_search(&id).ok().map(|r| r as u32),
+            Repr::Bits { min_chunk, words, wrank, table, .. } => {
+                if id & 7 != 0 {
+                    return None;
+                }
+                let slot = id >> SLOT_SHIFT;
+                let offset = (slot >> CHUNK_SLOT_BITS).checked_sub(*min_chunk)?;
+                let first = *table.get(usize::try_from(offset).ok()?)?;
+                if first == NONE {
+                    return None;
+                }
+                let w = first as usize + (slot >> 6) as usize % WORDS_PER_CHUNK;
+                let bit = slot & 63;
+                let word = words[w];
+                if word >> bit & 1 == 0 {
+                    return None;
+                }
+                Some(wrank[w] + (word & ((1u64 << bit) - 1)).count_ones())
+            }
+        }
+    }
+
+    /// The id with index `rank`. Panics when `rank >= len()`.
+    pub fn id_at(&self, rank: u32) -> u64 {
+        match &self.repr {
+            Repr::Sorted(ids) => ids[rank as usize],
+            Repr::Bits { words, wrank, len, .. } => {
+                assert!(rank < *len, "rank {rank} out of range for {len} ids");
+                let w = wrank.partition_point(|&before| before <= rank) - 1;
+                let mut word = words[w];
+                for _ in 0..rank - wrank[w] {
+                    word &= word - 1;
+                }
+                (self.word_first_slot(w) + u64::from(word.trailing_zeros())) << SLOT_SHIFT
+            }
+        }
+    }
+
+    /// All ids in ascending order.
+    pub fn ids(&self) -> impl Iterator<Item = u64> + '_ {
+        Ids { map: self, next: 0, slot_base: 0, rest: 0 }
+    }
+
+    /// Bytes of all the columns, in RAM or on disk.
+    pub fn column_bytes(&self) -> u64 {
+        match &self.repr {
+            Repr::Sorted(ids) => std::mem::size_of_val(&**ids) as u64,
+            Repr::Bits { words, wrank, table, chunk_offsets, .. } => {
+                (std::mem::size_of_val(&**words)
+                    + std::mem::size_of_val(&**wrank)
+                    + std::mem::size_of_val(&**table)
+                    + std::mem::size_of_val(&**chunk_offsets)) as u64
+            }
+        }
+    }
+
+    /// Slot number of bit 0 of word `w` (bitmap layout only).
+    fn word_first_slot(&self, w: usize) -> u64 {
+        let Repr::Bits { min_chunk, chunk_offsets, .. } = &self.repr else {
+            unreachable!("sorted layout has no words")
+        };
+        let chunk = min_chunk + u64::from(chunk_offsets[w / WORDS_PER_CHUNK]);
+        (chunk << CHUNK_SLOT_BITS) + (w % WORDS_PER_CHUNK) as u64 * WORD_BITS
+    }
+}
+
+struct Ids<'a> {
+    map: &'a IdMap,
+    /// Next word (bitmap layout) or next id (sorted layout).
+    next: usize,
+    slot_base: u64,
+    /// Bits of the current word not yielded yet.
+    rest: u64,
+}
+
+impl Iterator for Ids<'_> {
+    type Item = u64;
+
+    fn next(&mut self) -> Option<u64> {
+        match &self.map.repr {
+            Repr::Sorted(ids) => {
+                let id = *ids.get(self.next)?;
+                self.next += 1;
+                Some(id)
+            }
+            Repr::Bits { words, .. } => loop {
+                if self.rest != 0 {
+                    let bit = u64::from(self.rest.trailing_zeros());
+                    self.rest &= self.rest - 1;
+                    return Some((self.slot_base + bit) << SLOT_SHIFT);
+                }
+                self.rest = *words.get(self.next)?;
+                self.slot_base = self.map.word_first_slot(self.next);
+                self.next += 1;
+            },
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use ide_core::CancellationToken;
+
+    use super::*;
+    use crate::column::Store;
+
+    /// Deterministic generator so failures replay; the crate has no `rand`.
+    struct XorShift(u64);
+
+    impl XorShift {
+        fn next(&mut self) -> u64 {
+            self.0 ^= self.0 << 13;
+            self.0 ^= self.0 >> 7;
+            self.0 ^= self.0 << 17;
+            self.0
+        }
+    }
+
+    fn build(ids: &[u64], store: &Store) -> IdMap {
+        let mut builder = IdMapBuilder::new();
+        for &id in ids {
+            builder.insert(id);
+        }
+        builder.build(store, &CancellationToken::new()).unwrap()
+    }
+
+    fn assert_matches_model(map: &IdMap, model: &[u64]) {
+        assert_eq!(map.len() as usize, model.len());
+        assert_eq!(map.ids().collect::<Vec<_>>(), model);
+        for (rank, &id) in model.iter().enumerate() {
+            assert_eq!(map.rank(id), Some(rank as u32), "rank of {id:#x}");
+            assert_eq!(map.id_at(rank as u32), id, "id at {rank}");
+            for near in [id.wrapping_sub(8), id.wrapping_add(8), id.wrapping_add(1), id.wrapping_add(4)] {
+                if model.binary_search(&near).is_err() {
+                    assert_eq!(map.rank(near), None, "{near:#x} was never inserted");
+                }
+            }
+        }
+    }
+
+    #[test]
+    fn rank_follows_address_order() {
+        let map = build(&[0x2000, 0x1000, 0x1010, 0x7_0000_0000], &Store::Ram);
+        assert_eq!(map.len(), 4);
+        assert_eq!(
+            [0x1000, 0x1010, 0x2000, 0x7_0000_0000].map(|id| map.rank(id)),
+            [Some(0), Some(1), Some(2), Some(3)]
+        );
+        assert_eq!(map.rank(0x1008), None);
+        assert_eq!(map.rank(0), None);
+        assert_eq!(map.id_at(2), 0x2000);
+        assert_eq!(map.ids().collect::<Vec<_>>(), [0x1000, 0x1010, 0x2000, 0x7_0000_0000]);
+    }
+
+    #[test]
+    fn unaligned_ids_use_sorted_fallback() {
+        let map = build(&[0x2000, 0x1004, 0x1000, 0x1010, 0x7_0000_0000], &Store::Ram);
+        assert_eq!(
+            [0x1000, 0x1004, 0x1010, 0x2000, 0x7_0000_0000].map(|id| map.rank(id)),
+            [Some(0), Some(1), Some(2), Some(3), Some(4)]
+        );
+        assert_eq!(map.rank(0x1008), None);
+        assert_eq!(map.id_at(1), 0x1004);
+    }
+
+    #[test]
+    fn sparse_wide_span_uses_fallback() {
+        let map = build(&[0x1000 + (1 << 50), 0x1000], &Store::Ram);
+        assert_eq!(map.rank(0x1000), Some(0));
+        assert_eq!(map.rank(0x1000 + (1 << 50)), Some(1));
+        assert_eq!(map.rank(0x1008), None);
+        assert!(map.column_bytes() < 64, "a two-id map must not allocate a chunk table");
+    }
+
+    #[test]
+    fn ten_million_ids_cost_about_a_byte_each() {
+        let mut builder = IdMapBuilder::new();
+        for i in 0..10_000_000u64 {
+            builder.insert(0x7_0000_0000 + i * 32);
+        }
+        let map = builder.build(&Store::Ram, &CancellationToken::new()).unwrap();
+        assert_eq!(map.len(), 10_000_000);
+        assert!(map.column_bytes() < 16_000_000, "{} bytes", map.column_bytes());
+        assert_eq!(map.rank(0x7_0000_0000 + 9_999_999 * 32), Some(9_999_999));
+        assert_eq!(map.id_at(5_000_000), 0x7_0000_0000 + 5_000_000 * 32);
+    }
+
+    #[test]
+    fn empty_map_and_duplicates() {
+        let map = build(&[], &Store::Ram);
+        assert!(map.is_empty());
+        assert_eq!(map.rank(0x1000), None);
+        assert_eq!(map.ids().count(), 0);
+        let map = build(&[0x1000, 0x1000, 0x1008, 0x1000], &Store::Ram);
+        assert_eq!(map.len(), 2);
+        assert_eq!(map.rank(0x1008), Some(1));
+    }
+
+    #[test]
+    fn chunk_boundaries_and_gaps_between_chunks() {
+        let ids = [0, 0xF_FFF8, 0x10_0000, 0x10_0008, 0x50_0000, 0x1_0000_0000];
+        let mut model = ids.to_vec();
+        model.sort_unstable();
+        let map = build(&ids, &Store::Ram);
+        assert_matches_model(&map, &model);
+    }
+
+    #[test]
+    fn ids_outside_the_populated_chunks_are_absent() {
+        let ids = [0x30_0000, 0x30_0008, 0x70_0000];
+        let map = build(&ids, &Store::Ram);
+        assert_matches_model(&map, &ids);
+        // Chunk 5 lies between the lowest and highest chunk but holds nothing.
+        assert_eq!(map.rank(0x50_0000), None);
+        // Chunk 1 is below the lowest populated chunk.
+        assert_eq!(map.rank(0x10_0000), None);
+        // Chunk 9 is past the last table entry.
+        assert_eq!(map.rank(0x900_0000), None);
+        assert_eq!(map.rank(u64::MAX - 7), None);
+    }
+
+    #[test]
+    fn highest_address_round_trips() {
+        let map = build(&[0xFFFF_FFFF_FFFF_FFF8], &Store::Ram);
+        assert_eq!(map.rank(0xFFFF_FFFF_FFFF_FFF8), Some(0));
+        assert_eq!(map.id_at(0), 0xFFFF_FFFF_FFFF_FFF8);
+        let map = build(&[0, 0xFFFF_FFFF_FFFF_FFF8], &Store::Ram);
+        assert_matches_model(&map, &[0, 0xFFFF_FFFF_FFFF_FFF8]);
+    }
+
+    #[test]
+    fn random_ids_match_a_sorted_model_in_ram_and_on_disk() {
+        for seed in 1..=8u64 {
+            let mut rng = XorShift(seed.wrapping_mul(0x9E37_79B9_7F4A_7C15) | 1);
+            let aligned = seed % 4 != 0;
+            let wide = seed % 3 == 0;
+            let ids: Vec<u64> = (0..3000)
+                .map(|_| {
+                    let r = rng.next();
+                    let base = if wide { (r >> 20) << 12 } else { 0x6_0000_0000 + (r % (6 << 20)) };
+                    if aligned { base & !7 } else { base }
+                })
+                .collect();
+            let mut model = ids.clone();
+            model.sort_unstable();
+            model.dedup();
+            let dir = tempfile::tempdir().unwrap();
+            for store in [Store::Ram, Store::Dir(dir.path().to_path_buf())] {
+                assert_matches_model(&build(&ids, &store), &model);
+            }
+        }
+    }
+
+    #[test]
+    fn dir_store_keeps_the_index_columns_under_stable_names() {
+        let dir = tempfile::tempdir().unwrap();
+        let map = build(&[0x1000, 0x2000], &Store::Dir(dir.path().to_path_buf()));
+        let mut names: Vec<_> =
+            std::fs::read_dir(dir.path()).unwrap().map(|e| e.unwrap().file_name().into_string().unwrap()).collect();
+        names.sort();
+        assert_eq!(names, ["ids.bits.u64", "ids.chunks.u32", "ids.table.u32", "ids.wrank.u32"]);
+        assert_eq!(map.rank(0x2000), Some(1));
+        let dir = tempfile::tempdir().unwrap();
+        build(&[0x1004], &Store::Dir(dir.path().to_path_buf()));
+        assert!(dir.path().join("ids.sorted.u64").exists());
+    }
+}
@@ -0,0 +1,409 @@
+//! Collects object ids in any order and lays them out as an [`IdMap`].
+
+use std::cmp::Reverse;
+use std::collections::{BinaryHeap, HashMap};
+use std::hash::{BuildHasherDefault, Hasher};
+
+use ide_core::CancellationToken;
+
+use super::{CHUNK_SLOT_BITS, IdMap, Repr, SLOT_SHIFT, WORD_BITS, WORDS_PER_CHUNK};
+use crate::column::{NONE, Store};
+use crate::error::HeapError;
+use crate::files::{IDS_BITS_FILE, IDS_CHUNKS_FILE, IDS_SORTED_FILE, IDS_TABLE_FILE, IDS_WRANK_FILE};
+
+/// Widest chunk range the dense table covers (256 MiB of table at most).
+const MAX_CHUNK_SPAN: u64 = 1 << 26;
+/// Chunks whose first word index still fits in the table's `u32`.
+const MAX_CHUNKS: usize = (NONE as usize - 1) / WORDS_PER_CHUNK;
+/// Largest object count: `NONE` and the one after it stay free as sentinels for the columns above.
+const MAX_IDS: u64 = NONE as u64 - 2;
+
+const CHUNK_BYTES: u64 = (WORDS_PER_CHUNK * size_of::<u64>()) as u64;
+/// The bitmaps may take this much before any id is inserted, then this many bytes per distinct id.
+/// A heap that fits in 4 GiB of address space never reaches the base allowance whatever the
+/// insertion order; sparse input (one id per chunk) is moved to plain `u64` ids, 8 bytes each,
+/// after at most `BITMAP_BASE_BYTES + BITMAP_BYTES_PER_ID * ids` of bitmaps, so builder memory is
+/// bounded by the number of ids rather than by the address range they spread over.
+const BITMAP_BASE_BYTES: u64 = 64 << 20;
+const BITMAP_BYTES_PER_ID: u64 = 32;
+
+/// Longest stretch of work between two looks at the cancellation token.
+const CHECK_EVERY: usize = 1 << 20;
+
+/// Chunk numbers are already well spread by a multiplicative hash; SipHash would dominate the
+/// per-insert cost on a 100M-object heap. The product keeps the low zero bits of its input, so
+/// the high half is folded down for the bucket index. The graph builder keys class and string
+/// ids (addresses) with it for the same reason.
+#[derive(Default)]
+pub(crate) struct ChunkHasher(u64);
+
+impl Hasher for ChunkHasher {
+    fn finish(&self) -> u64 {
+        self.0 ^ (self.0 >> 32)
+    }
+
+    fn write(&mut self, bytes: &[u8]) {
+        for &b in bytes {
+            self.write_u64(self.0.rotate_left(8) ^ u64::from(b));
+        }
+    }
+
+    fn write_u64(&mut self, n: u64) {
+        self.0 = n.wrapping_mul(0x9E37_79B9_7F4A_7C15);
+    }
+}
+
+struct BitChunks {
+    /// Chunk number → position in `words`.
+    index: HashMap<u64, usize, BuildHasherDefault<ChunkHasher>>,
+    words: Vec<Box<[u64]>>,
+    min: u64,
+    max: u64,
+    /// The chunk of the previous insert; ids usually arrive in runs.
+    last: Option<(u64, usize)>,
+    distinct: u64,
+}
+
+impl BitChunks {
+    fn new() -> Self {
+        Self { index: HashMap::default(), words: Vec::new(), min: u64::MAX, max: 0, last: None, distinct: 0 }
+    }
+
+    /// `false` when the id's chunk does not fit the dense table or the bitmap budget; the id is
+    /// then not recorded and the caller moves to plain ids.
+    fn insert(&mut self, id: u64) -> bool {
+        let slot = id >> SLOT_SHIFT;
+        let chunk = slot >> CHUNK_SLOT_BITS;
+        let at = match self.last {
+            Some((c, at)) if c == chunk => at,
+            _ => match self.index.get(&chunk) {
+                Some(&at) => at,
+                None => {
+                    let (min, max) = (self.min.min(chunk), self.max.max(chunk));
+                    let bitmap_bytes = (self.words.len() as u64 + 1) * CHUNK_BYTES;
+                    if self.words.len() >= MAX_CHUNKS
+                        || max - min >= MAX_CHUNK_SPAN
+                        || bitmap_bytes > BITMAP_BASE_BYTES + BITMAP_BYTES_PER_ID * self.distinct
+                    {
+                        return false;
+                    }
+                    (self.min, self.max) = (min, max);
+                    self.words.push(vec![0u64; WORDS_PER_CHUNK].into_boxed_slice());
+                    self.index.insert(chunk, self.words.len() - 1);
+                    self.words.len() - 1
+                }
+            },
+        };
+        self.last = Some((chunk, at));
+        let word = &mut self.words[at][(slot >> 6) as usize % WORDS_PER_CHUNK];
+        let bit = 1u64 << (slot & 63);
+        if *word & bit == 0 {
+            *word |= bit;
+            self.distinct += 1;
+        }
+        true
+    }
+
+    /// `(chunk number, position in words)` in ascending address order.
+    fn sorted_chunks(&self) -> Vec<(u64, usize)> {
+        let mut chunks: Vec<_> = self.index.iter().map(|(&chunk, &at)| (chunk, at)).collect();
+        chunks.sort_unstable();
+        chunks
+    }
+
+    /// The recorded ids, ascending.
+    fn ids(&self) -> BitIds<'_> {
+        BitIds { chunks: self.sorted_chunks(), words: &self.words, chunk: 0, word: 0, base: 0, rest: 0 }
+    }
+}
+
+struct BitIds<'a> {
+    chunks: Vec<(u64, usize)>,
+    words: &'a [Box<[u64]>],
+    chunk: usize,
+    word: usize,
+    /// Slot number of bit 0 of the word `rest` came from.
+    base: u64,
+    rest: u64,
+}
+
+impl Iterator for BitIds<'_> {
+    type Item = u64;
+
+    fn next(&mut self) -> Option<u64> {
+        loop {
+            if self.rest != 0 {
+                let bit = u64::from(self.rest.trailing_zeros());
+                self.rest &= self.rest - 1;
+                return Some((self.base + bit) << SLOT_SHIFT);
+            }
+            let &(chunk, at) = self.chunks.get(self.chunk)?;
+            self.rest = self.words[at][self.word];
+            self.base = (chunk << CHUNK_SLOT_BITS) + self.word as u64 * WORD_BITS;
+            self.word += 1;
+            if self.word == WORDS_PER_CHUNK {
+                self.word = 0;
+                self.chunk += 1;
+            }
+        }
+    }
+}
+
+pub struct IdMapBuilder {
+    bits: BitChunks,
+    /// Set once an id cannot go into `bits`; every later id goes here, and `bits` keeps what it
+    /// had. Unsorted, with duplicates.
+    plain: Option<Vec<u64>>,
+    max_ids: u64,
+}
+
+impl Default for IdMapBuilder {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl IdMapBuilder {
+    pub fn new() -> Self {
+        Self::with_limit(MAX_IDS)
+    }
+
+    /// `max_ids` is a parameter so tests can reach the too-large path without billions of inserts.
+    fn with_limit(max_ids: u64) -> Self {
+        Self { bits: BitChunks::new(), plain: None, max_ids }
+    }
+
+    /// Inserting an id twice is the same as once.
+    pub fn insert(&mut self, id: u64) {
+        match &mut self.plain {
+            Some(plain) => plain.push(id),
+            None => {
+                if id & 7 != 0 || !self.bits.insert(id) {
+                    self.plain = Some(vec![id]);
+                }
+            }
+        }
+    }
+
+    /// Fails with [`HeapError::TooLarge`] when there are more than `u32::MAX - 2` distinct ids,
+    /// and with [`HeapError::Cancelled`] when `cancel` fires (checked at least every `1 << 20`
+    /// steps).
+    pub fn build(self, store: &Store, cancel: &CancellationToken) -> Result<IdMap, HeapError> {
+        match self.plain {
+            None if self.bits.words.is_empty() => sorted_map(store, &[]),
+            None => bit_map(&self.bits, store, self.max_ids, cancel),
+            Some(plain) => merged_map(&self.bits, plain, store, self.max_ids, cancel),
+        }
+    }
+
+    #[cfg(test)]
+    fn allocated_bytes(&self) -> u64 {
+        self.bits.words.len() as u64 * CHUNK_BYTES
+            + self.plain.as_ref().map_or(0, |p| (p.capacity() * size_of::<u64>()) as u64)
+    }
+}
+
+fn check(cancel: &CancellationToken) -> Result<(), HeapError> {
+    if cancel.is_cancelled() { Err(HeapError::Cancelled) } else { Ok(()) }
+}
+
+fn sorted_map(store: &Store, ids: &[u64]) -> Result<IdMap, HeapError> {
+    let mut column = store.column(IDS_SORTED_FILE, ids.len(), 0u64)?;
+    column.copy_from_slice(ids);
+    Ok(IdMap { repr: Repr::Sorted(column) })
+}
+
+fn bit_map(bits: &BitChunks, store: &Store, max_ids: u64, cancel: &CancellationToken) -> Result<IdMap, HeapError> {
+    if bits.distinct > max_ids {
+        return Err(HeapError::TooLarge);
+    }
+    let chunks = bits.sorted_chunks();
+    let span = (bits.max - bits.min + 1) as usize;
+    let mut words = store.column(IDS_BITS_FILE, chunks.len() * WORDS_PER_CHUNK, 0u64)?;
+    let mut wrank = store.column(IDS_WRANK_FILE, chunks.len() * WORDS_PER_CHUNK, 0u32)?;
+    let mut table = store.column(IDS_TABLE_FILE, span, NONE)?;
+    let mut chunk_offsets = store.column(IDS_CHUNKS_FILE, chunks.len(), 0u32)?;
+    let mut before = 0u32;
+    for (ordinal, &(chunk, at)) in chunks.iter().enumerate() {
+        check(cancel)?;
+        let first = ordinal * WORDS_PER_CHUNK;
+        let offset = (chunk - bits.min) as usize;
+        table[offset] = first as u32;
+        chunk_offsets[ordinal] = offset as u32;
+        for (w, &word) in bits.words[at].iter().enumerate() {
+            words[first + w] = word;
+            wrank[first + w] = before;
+            before += word.count_ones();
+        }
+    }
+    Ok(IdMap { repr: Repr::Bits { min_chunk: bits.min, words, wrank, table, chunk_offsets, len: before } })
+}
+
+enum Source<'a> {
+    Bits(BitIds<'a>),
+    Run(std::iter::Copied<std::slice::Iter<'a, u64>>),
+}
+
+impl Iterator for Source<'_> {
+    type Item = u64;
+
+    fn next(&mut self) -> Option<u64> {
+        match self {
+            Source::Bits(it) => it.next(),
+            Source::Run(it) => it.next(),
+        }
+    }
+}
+
+/// Sorts `plain` in runs and merges the runs with the ids already in `bits` (itself a sorted
+/// source), dropping duplicates. A single `sort_unstable` of a very large vector could not be
+/// interrupted.
+fn merged_map(
+    bits: &BitChunks,
+    mut plain: Vec<u64>,
+    store: &Store,
+    max_ids: u64,
+    cancel: &CancellationToken,
+) -> Result<IdMap, HeapError> {
+    for run in plain.chunks_mut(CHECK_EVERY) {
+        check(cancel)?;
+        run.sort_unstable();
+    }
+    let mut sources = vec![Source::Bits(bits.ids())];
+    sources.extend(plain.chunks(CHECK_EVERY).map(|run| Source::Run(run.iter().copied())));
+    let mut heap = BinaryHeap::with_capacity(sources.len());
+    for (i, source) in sources.iter_mut().enumerate() {
+        if let Some(id) = source.next() {
+            heap.push(Reverse((id, i)));
+        }
+    }
+
+    let upper_bound = bits.distinct as usize + plain.len();
+    let mut merged = store.scratch::<u64>(upper_bound, 0)?;
+    let mut count = 0usize;
+    let mut steps = 0usize;
+    while let Some(Reverse((id, i))) = heap.pop() {
+        steps += 1;
+        if steps.is_multiple_of(CHECK_EVERY) {
+            check(cancel)?;
+        }
+        if let Some(next) = sources[i].next() {
+            heap.push(Reverse((next, i)));
+        }
+        if count > 0 && merged[count - 1] == id {
+            continue;
+        }
+        if count as u64 >= max_ids {
+            return Err(HeapError::TooLarge);
+        }
+        merged[count] = id;
+        count += 1;
+    }
+
+    let mut column = store.column(IDS_SORTED_FILE, count, 0u64)?;
+    for (to, from) in column.chunks_mut(CHECK_EVERY).zip(merged[..count].chunks(CHECK_EVERY)) {
+        check(cancel)?;
+        to.copy_from_slice(from);
+    }
+    Ok(IdMap { repr: Repr::Sorted(column) })
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn insert_all(builder: &mut IdMapBuilder, ids: &[u64]) {
+        for &id in ids {
+            builder.insert(id);
+        }
+    }
+
+    #[test]
+    fn too_many_ids_is_too_large() {
+        // Dense layout, then the merged layout (one unaligned id); the duplicate does not count.
+        for unaligned in [false, true] {
+            let filled = |limit| {
+                let mut builder = IdMapBuilder::with_limit(limit);
+                insert_all(&mut builder, &[0x1000, 0x1008, 0x1010, 0x1010]);
+                if unaligned {
+                    builder.insert(0x1_0004);
+                }
+                builder
+            };
+            let distinct = if unaligned { 4 } else { 3 };
+            let map = filled(distinct).build(&Store::Ram, &CancellationToken::new()).unwrap();
+            assert_eq!(u64::from(map.len()), distinct);
+            let err = filled(distinct - 1).build(&Store::Ram, &CancellationToken::new()).err().unwrap();
+            assert!(matches!(err, HeapError::TooLarge), "{err}");
+        }
+    }
+
+    #[test]
+    fn cancelled_build_returns_cancelled() {
+        let cancelled = CancellationToken::new();
+        cancelled.cancel();
+        let mut dense = IdMapBuilder::new();
+        insert_all(&mut dense, &[0x1000, 0x1008, 0x20_0000]);
+        assert!(matches!(dense.build(&Store::Ram, &cancelled), Err(HeapError::Cancelled)));
+
+        let mut merged = IdMapBuilder::new();
+        insert_all(&mut merged, &[0x1000, 0x1004, 0x20_0000]);
+        assert!(matches!(merged.build(&Store::Ram, &cancelled), Err(HeapError::Cancelled)));
+
+        let mut ok = IdMapBuilder::new();
+        insert_all(&mut ok, &[0x1000, 0x1004]);
+        assert_eq!(ok.build(&Store::Ram, &CancellationToken::new()).unwrap().len(), 2);
+    }
+
+    #[test]
+    fn sparse_ids_do_not_amplify_builder_memory() {
+        const IDS: u64 = 2_000_000;
+        let mut builder = IdMapBuilder::new();
+        let mut peak = 0;
+        for i in 0..IDS {
+            builder.insert(0x1_0000_0000 + (i << 20));
+            if i % 1024 == 0 {
+                peak = peak.max(builder.allocated_bytes());
+            }
+        }
+        peak = peak.max(builder.allocated_bytes());
+        // Bitmaps up to the budget, plus the plain ids' vector, which may have doubled its capacity.
+        let budget = BITMAP_BASE_BYTES + (BITMAP_BYTES_PER_ID + 2 * size_of::<u64>() as u64) * IDS;
+        assert!(peak <= budget, "peak {peak} bytes, budget {budget}");
+        // One bitmap per id would have taken 16 KiB each.
+        assert!(peak < IDS * CHUNK_BYTES / 100, "peak {peak} bytes");
+        assert!(builder.plain.is_some(), "sparse input must have left the bitmaps");
+
+        let map = builder.build(&Store::Ram, &CancellationToken::new()).unwrap();
+        assert_eq!(map.len() as u64, IDS);
+        assert_eq!(map.rank(0x1_0000_0000 + (1_234_567 << 20)), Some(1_234_567));
+        assert_eq!(map.rank(0x1_0000_0000 + (1_234_567 << 20) + 8), None);
+    }
+
+    #[test]
+    fn dense_input_in_any_order_stays_in_bitmaps() {
+        // 4 GiB of address space is the base allowance; random order must not trip the budget.
+        let mut state = 0x2545_F491_4F6C_DD1Du64;
+        let mut builder = IdMapBuilder::new();
+        for _ in 0..300_000 {
+            state ^= state << 13;
+            state ^= state >> 7;
+            state ^= state << 17;
+            builder.insert((0x7_0000_0000 + (state % (4 << 30))) & !7);
+        }
+        assert!(builder.plain.is_none());
+        assert!(builder.allocated_bytes() <= BITMAP_BASE_BYTES);
+    }
+
+    #[test]
+    fn chunk_hasher_spreads_chunks_that_share_low_zero_bits() {
+        let buckets: std::collections::HashSet<u64> = (0..1024u64)
+            .map(|i| {
+                let mut hasher = ChunkHasher::default();
+                hasher.write_u64(i << 12);
+                hasher.finish() & 1023
+            })
+            .collect();
+        assert!(buckets.len() > 500, "{} buckets for 1024 keys", buckets.len());
+    }
+}
@@ -0,0 +1,109 @@
+//! The result of analyzing a heap dump: per-object columns, the class table and the summary.
+
+mod fields;
+mod path;
+mod queries;
+mod rows;
+
+use std::collections::HashMap;
+use std::path::Path;
+
+use memmap2::Mmap;
+use serde::{Deserialize, Serialize};
+
+use crate::column::Column;
+use crate::error::HeapError;
+use crate::files::SUMMARY_FILE;
+use crate::graph::ClassInfo;
+use crate::hprof::HeapRootKind;
+use crate::ids::IdMap;
+use crate::shallow::SizeSource;
+
+pub(crate) use self::fields::{id_value, instance_fields};
+pub use self::rows::{
+    HeapClassRow, HeapEdge, HeapObjectPage, HeapObjectRef, HeapObjectRow, HeapPathStep, HeapRootPath, MAX_PAGE,
+};
+
+/// Counts over instances and arrays; class objects (class dumps) are left out.
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(rename_all = "camelCase")]
+pub struct HeapSummary {
+    /// `reachable_objects + unreachable_objects`.
+    pub objects: u64,
+    pub reachable_objects: u64,
+    pub reachable_bytes: u64,
+    pub unreachable_objects: u64,
+    pub unreachable_bytes: u64,
+    /// Class dumps in the dump.
+    pub classes: u32,
+    pub weak_edges_skipped: u64,
+    pub size_source: SizeSource,
+    pub analysis_ms: u32,
+}
+
+/// One row of the class table, for one type slot.
+#[derive(Clone, Debug, PartialEq, Eq)]
+pub struct ClassStat {
+    /// [`crate::display_name`] of the class (`long[]` for a primitive array slot).
+    pub name: String,
+    /// Reachable instances.
+    pub count: u64,
+    /// Shallow bytes of the reachable instances.
+    pub shallow: u64,
+    /// Bytes the reachable instances retain together: the sum of the retained sizes of those
+    /// with no instance of the same type above them in the dominator tree.
+    pub retained: u64,
+    pub unreachable_count: u64,
+}
+
+/// Columns are indexed by node: objects `0..root`, then the super-root `root`. Columns of the
+/// objects only (`types`, `offsets`) have no entry for the root.
+pub struct HeapIndex {
+    /// The dump, for [`crate::record_at`] at `offsets[v]`.
+    pub hprof: Mmap,
+    pub ids: IdMap,
+    /// Type slot of each object, as in [`crate::HeapGraph::types`].
+    pub types: Column<u32>,
+    pub offsets: Column<u64>,
+    /// Shallow size in units of 8 bytes, rounded up.
+    pub shallow8: Column<u32>,
+    /// Retained bytes; 0 for unreachable objects, every reachable byte for the root.
+    pub retained: Column<u64>,
+    /// Immediate dominator; [`crate::NONE`] for unreachable objects, `root` for the root.
+    pub idom: Column<u32>,
+    /// Children of node `v` in the dominator tree are `kids[kids_start[v]..kids_start[v + 1]]`,
+    /// by retained size descending, then by node.
+    pub kids_start: Column<u32>,
+    pub kids: Column<u32>,
+    /// Parent on a shortest path from the root (BFS over strong edges); [`crate::NONE`] for
+    /// unreachable objects, `root` for the root.
+    pub gc_parent: Column<u32>,
+    /// By type slot: class slots, then the primitive array slots.
+    pub classes: Vec<ClassStat>,
+    /// By class slot, as in [`crate::HeapGraph::classes`].
+    pub class_info: Vec<ClassInfo>,
+    /// Type slot of class objects.
+    pub class_slot: u32,
+    /// Object → kind and thread serial of its first root record.
+    pub roots: HashMap<u32, (HeapRootKind, Option<u32>)>,
+    /// Thread serial → thread object.
+    pub thread_objects: HashMap<u32, u32>,
+    pub id_size: u8,
+    pub summary: HeapSummary,
+}
+
+impl HeapIndex {
+    /// The super-root, whose children in both trees are the rooted objects.
+    pub fn root(&self) -> u32 {
+        self.ids.len()
+    }
+}
+
+pub(crate) fn write_summary(dir: &Path, summary: &HeapSummary) -> Result<(), HeapError> {
+    let json = serde_json::to_vec_pretty(summary).map_err(std::io::Error::from)?;
+    std::fs::write(dir.join(SUMMARY_FILE), json)?;
+    Ok(())
+}
+
+#[cfg(test)]
+mod tests;
@@ -0,0 +1,41 @@
+//! Named field values of an instance record.
+
+use super::HeapIndex;
+use crate::hprof::BasicType;
+
+pub(crate) struct FieldValue<'a> {
+    pub(crate) name: &'a str,
+    pub(crate) ty: BasicType,
+    /// Big-endian, as in the dump.
+    pub(crate) bytes: &'a [u8],
+    /// `java.lang.ref.Reference.referent`, which the graph leaves out.
+    pub(crate) weak: bool,
+}
+
+/// The fields of an instance of class slot `class` whose record holds `data`: the class's own,
+/// then each superclass's, as HotSpot lays them out. Stops where `data` ends.
+pub(crate) fn instance_fields<'a>(index: &'a HeapIndex, class: u32, data: &'a [u8]) -> Vec<FieldValue<'a>> {
+    let mut out = Vec::new();
+    let mut base = 0usize;
+    let mut cursor = Some(class);
+    // Super chains end (their cycles are cut), so this is only a bound on corrupt input.
+    for _ in 0..index.class_info.len() {
+        let Some(info) = cursor.and_then(|c| index.class_info.get(c as usize)) else { break };
+        for (k, (name, ty)) in info.fields.iter().enumerate() {
+            let size = ty.hprof_size(index.id_size);
+            let Some(bytes) = base.checked_add(size).and_then(|end| data.get(base..end)) else { return out };
+            out.push(FieldValue { name, ty: *ty, bytes, weak: info.weak_field == Some(k) });
+            base += size;
+        }
+        cursor = info.super_index;
+    }
+    out
+}
+
+/// A 4- or 8-byte big-endian id.
+pub(crate) fn id_value(bytes: &[u8]) -> Option<u64> {
+    match *bytes {
+        [a, b, c, d] => Some(u64::from(u32::from_be_bytes([a, b, c, d]))),
+        _ => Some(u64::from_be_bytes(bytes.try_into().ok()?)),
+    }
+}
@@ -0,0 +1,105 @@
+//! Paths to GC roots, along the BFS tree of `gc_parent`.
+
+use super::{HeapEdge, HeapIndex, HeapObjectRef, HeapPathStep, HeapRootPath, id_value, instance_fields};
+use crate::column::NONE;
+use crate::hprof::{BasicType, HeapRecord, HeapRootKind};
+use crate::strings::{char_array_text, string_preview};
+
+const THREAD_NAME_CHARS: usize = 100;
+
+/// Steps a long path keeps at each end: one deep in a long linked list would otherwise send
+/// every node over IPC.
+const PATH_END_STEPS: u32 = 500;
+
+impl HeapIndex {
+    /// From `object` up to its GC root, each step with how the next one holds it; past 1000
+    /// steps, only the 500 at each end. `None` for an unreachable object or a ref that names no
+    /// object.
+    pub fn path_to_root(&self, object: HeapObjectRef) -> Option<HeapRootPath> {
+        let root = self.root();
+        let mut v = object.0;
+        if v >= root || self.gc_parent[v as usize] == NONE {
+            return None;
+        }
+        let len = self.path_len(v)?;
+        let end = PATH_END_STEPS;
+        let cut = len > 2 * end;
+        let mut steps = Vec::with_capacity(len.min(2 * end) as usize);
+        for i in 0..len {
+            let parent = self.gc_parent[v as usize];
+            if !cut || i < end || i >= len - end {
+                let via = if parent == root { self.root_edge(v) } else { self.edge(parent, v) };
+                steps.push(HeapPathStep { object: self.object_row(HeapObjectRef(v))?, via });
+            }
+            v = parent;
+        }
+        let omitted = if cut { len - 2 * end } else { 0 };
+        Some(HeapRootPath { steps, omitted, omitted_after: if cut { end } else { 0 } })
+    }
+
+    /// Steps from `v` to the root; `None` when `gc_parent` leads nowhere.
+    fn path_len(&self, mut v: u32) -> Option<u32> {
+        let root = self.root();
+        // A BFS tree has no cycles; the bound only stops a corrupt column from looping.
+        for len in 1..=root {
+            let parent = self.gc_parent[v as usize];
+            if parent == root {
+                return Some(len);
+            }
+            if parent > root {
+                return None;
+            }
+            v = parent;
+        }
+        None
+    }
+
+    fn root_edge(&self, v: u32) -> HeapEdge {
+        let (kind, serial) = self.roots.get(&v).copied().unwrap_or((HeapRootKind::Unknown, None));
+        let thread = serial.and_then(|s| self.thread_objects.get(&s)).and_then(|&t| self.thread_name(t));
+        HeapEdge::Root { root: kind, thread }
+    }
+
+    /// `Thread.name`: a String, or a `char[]` before JDK 9.
+    fn thread_name(&self, thread: u32) -> Option<String> {
+        let Some(HeapRecord::Instance { data, .. }) = self.record(thread) else { return None };
+        let fields = instance_fields(self, *self.types.get(thread as usize)?, data);
+        let name = fields.iter().find(|f| f.name == "name" && f.ty == BasicType::Object)?;
+        let target = self.ids.rank(id_value(name.bytes)?)?;
+        string_preview(self, target, THREAD_NAME_CHARS).or_else(|| char_array_text(self, target, THREAD_NAME_CHARS))
+    }
+
+    /// How `parent` refers to `child`, checked in the order the graph's edges were made. A strong
+    /// edge from `parent` always exists; the empty field name only covers a dump that changed.
+    fn edge(&self, parent: u32, child: u32) -> HeapEdge {
+        self.find_edge(parent, self.ids.id_at(child)).unwrap_or(HeapEdge::Field { name: String::new() })
+    }
+
+    fn find_edge(&self, parent: u32, child_id: u64) -> Option<HeapEdge> {
+        match self.record(parent)? {
+            HeapRecord::Instance { data, .. } => {
+                let class = self.types[parent as usize];
+                let field = instance_fields(self, class, data)
+                    .into_iter()
+                    .find(|f| !f.weak && f.ty == BasicType::Object && id_value(f.bytes) == Some(child_id));
+                match field {
+                    Some(f) => Some(HeapEdge::Field { name: f.name.to_owned() }),
+                    None => (self.class_info.get(class as usize)?.id == child_id).then_some(HeapEdge::ClassOf),
+                }
+            }
+            HeapRecord::ObjectArray { data, .. } => {
+                let index =
+                    data.chunks_exact(usize::from(self.id_size)).position(|item| id_value(item) == Some(child_id))?;
+                Some(HeapEdge::Element { index: u32::try_from(index).ok()? })
+            }
+            HeapRecord::Class(dump) if dump.super_id == child_id => Some(HeapEdge::SuperClass),
+            HeapRecord::Class(dump) if dump.loader_id == child_id => Some(HeapEdge::ClassLoader),
+            HeapRecord::Class(_) => {
+                let info = self.class_info.get(self.class_of_object(parent)?)?;
+                let (name, _) = info.statics.iter().find(|(_, object)| *object == child_id)?;
+                Some(HeapEdge::Static { name: name.clone() })
+            }
+            HeapRecord::Root { .. } | HeapRecord::PrimitiveArray { .. } => None,
+        }
+    }
+}
@@ -0,0 +1,164 @@
+//! Class table rows, pages of the dominator tree and single object rows.
+
+use std::cmp::Reverse;
+use std::collections::{BinaryHeap, HashMap};
+
+use super::{HeapClassRow, HeapIndex, HeapObjectPage, HeapObjectRef, HeapObjectRow, HeapSummary, MAX_PAGE};
+use crate::column::NONE;
+use crate::hprof::HeapRecord;
+use crate::strings::string_preview;
+
+const PREVIEW_CHARS: usize = 100;
+
+impl HeapIndex {
+    pub fn summary(&self) -> &HeapSummary {
+        &self.summary
+    }
+
+    /// Types that have objects, by retained size descending, then by name.
+    pub fn class_rows(&self) -> Vec<HeapClassRow> {
+        let class_slots = &self.classes[..self.class_info.len().min(self.classes.len())];
+        let mut names: HashMap<&str, u32> = HashMap::with_capacity(class_slots.len());
+        for class in class_slots {
+            *names.entry(class.name.as_str()).or_default() += 1;
+        }
+        let mut rows: Vec<HeapClassRow> = self
+            .classes
+            .iter()
+            .enumerate()
+            .filter(|(_, c)| c.count > 0 || c.unreachable_count > 0)
+            .map(|(slot, c)| HeapClassRow {
+                class_index: slot as u32,
+                name: c.name.clone(),
+                count: c.count,
+                shallow: c.shallow,
+                retained: c.retained,
+                unreachable_count: c.unreachable_count,
+                // Primitive array slots have no class dump and so no second loader.
+                ambiguous: slot < class_slots.len() && names[c.name.as_str()] > 1,
+            })
+            .collect();
+        rows.sort_by(|a, b| b.retained.cmp(&a.retained).then_with(|| a.name.cmp(&b.name)));
+        rows
+    }
+
+    /// A page of objects by retained size descending, then by index:
+    ///
+    /// - no `parent`, no `class_index`: the children of the super-root, class objects left out;
+    /// - `parent`: its children in the dominator tree, of type `class_index` if given;
+    /// - `class_index` only: every reachable object of that type.
+    ///
+    /// `limit` is clamped to [`MAX_PAGE`]. A `parent` or `class_index` that names nothing gives an
+    /// empty page.
+    pub fn dominated(
+        &self,
+        parent: Option<HeapObjectRef>,
+        class_index: Option<u32>,
+        offset: u32,
+        limit: u32,
+    ) -> HeapObjectPage {
+        let limit = limit.min(MAX_PAGE);
+        let root = self.root();
+        if class_index.is_some_and(|c| c as usize >= self.classes.len()) {
+            return HeapObjectPage { rows: Vec::new(), total: 0 };
+        }
+        match (parent, class_index) {
+            (Some(HeapObjectRef(p)), _) if p >= root => HeapObjectPage { rows: Vec::new(), total: 0 },
+            (Some(HeapObjectRef(p)), class) => self.page(
+                self.children(p).filter(|&v| class.is_none_or(|c| self.types[v as usize] == c)),
+                offset,
+                limit,
+            ),
+            (None, None) => {
+                self.page(self.children(root).filter(|&v| self.types[v as usize] != self.class_slot), offset, limit)
+            }
+            (None, Some(class)) => self.largest_of(class, offset, limit),
+        }
+    }
+
+    /// `None` for a ref that names no object, the super-root included.
+    pub fn object_row(&self, object: HeapObjectRef) -> Option<HeapObjectRow> {
+        let v = object.0;
+        if v >= self.root() {
+            return None;
+        }
+        let i = v as usize;
+        let slot = self.types[i];
+        let preview = if slot == self.class_slot {
+            self.class_of_object(v).and_then(|c| self.classes.get(c)).map(|c| c.name.clone())
+        } else {
+            string_preview(self, v, PREVIEW_CHARS)
+        };
+        Some(HeapObjectRow {
+            object,
+            class_name: self.classes.get(slot as usize).map(|c| c.name.clone()).unwrap_or_default(),
+            address: format!("{:#x}", self.ids.id_at(v)),
+            shallow: u64::from(self.shallow8[i]) * 8,
+            retained: self.retained[i],
+            has_children: self.kids_start[i + 1] > self.kids_start[i],
+            preview,
+        })
+    }
+
+    /// The record of object `v`, or `None` when it cannot be read.
+    pub(crate) fn record(&self, v: u32) -> Option<HeapRecord<'_>> {
+        let at = usize::try_from(*self.offsets.get(v as usize)?).ok()?;
+        crate::hprof::record_at(&self.hprof, at, self.id_size).ok()
+    }
+
+    /// The class slot a class object stands for.
+    pub(crate) fn class_of_object(&self, v: u32) -> Option<usize> {
+        if v >= self.root() {
+            return None;
+        }
+        let id = self.ids.id_at(v);
+        self.class_info.iter().position(|c| c.id == id && c.id != 0)
+    }
+
+    /// Children of node `v` in the dominator tree, already in page order.
+    fn children(&self, v: u32) -> impl Iterator<Item = u32> + '_ {
+        let v = v as usize;
+        self.kids[self.kids_start[v] as usize..self.kids_start[v + 1] as usize].iter().copied()
+    }
+
+    fn page(&self, objects: impl Iterator<Item = u32>, offset: u32, limit: u32) -> HeapObjectPage {
+        let mut rows = Vec::new();
+        let mut total = 0u32;
+        for v in objects {
+            if total >= offset && total - offset < limit {
+                rows.extend(self.object_row(HeapObjectRef(v)));
+            }
+            total = total.saturating_add(1);
+        }
+        HeapObjectPage { rows, total }
+    }
+
+    /// Scans every object: the top `offset + limit` stay in a heap whose top is the smallest.
+    fn largest_of(&self, class: u32, offset: u32, limit: u32) -> HeapObjectPage {
+        let count = self.classes[class as usize].count;
+        let total = u32::try_from(count).unwrap_or(u32::MAX);
+        let keep = match offset.checked_add(limit) {
+            Some(keep) if offset < total && limit > 0 => keep.min(total) as usize,
+            _ => return HeapObjectPage { rows: Vec::new(), total },
+        };
+        let mut top: BinaryHeap<Reverse<(u64, Reverse<u32>)>> = BinaryHeap::with_capacity(keep + 1);
+        for v in 0..self.root() {
+            let i = v as usize;
+            if self.types[i] != class || self.idom[i] == NONE {
+                continue;
+            }
+            top.push(Reverse((self.retained[i], Reverse(v))));
+            if top.len() > keep {
+                top.pop();
+            }
+        }
+        // Ascending `Reverse` order is descending retained, then ascending index.
+        let rows = top
+            .into_sorted_vec()
+            .into_iter()
+            .skip(offset as usize)
+            .filter_map(|Reverse((_, Reverse(v)))| self.object_row(HeapObjectRef(v)))
+            .collect();
+        HeapObjectPage { rows, total }
+    }
+}
@@ -0,0 +1,95 @@
+//! What the index queries return over IPC.
+
+use serde::{Deserialize, Serialize};
+
+use crate::hprof::HeapRootKind;
+
+/// Most rows one page of [`crate::HeapIndex::dominated`] returns.
+pub const MAX_PAGE: u32 = 500;
+
+/// An object of one snapshot: its index in the [`crate::HeapIndex`] columns. Any value may
+/// arrive over IPC; queries answer an index that names no object with nothing.
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash, Serialize, Deserialize, specta::Type)]
+#[serde(transparent)]
+pub struct HeapObjectRef(pub u32);
+
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(rename_all = "camelCase")]
+pub struct HeapClassRow {
+    /// Type slot, as `classIndex` in [`crate::HeapIndex::dominated`].
+    pub class_index: u32,
+    pub name: String,
+    pub count: u64,
+    pub shallow: u64,
+    pub retained: u64,
+    pub unreachable_count: u64,
+    /// Another class has the same name (several class loaders): nothing joined by name, such as a
+    /// second snapshot, can tell them apart.
+    pub ambiguous: bool,
+}
+
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(rename_all = "camelCase")]
+pub struct HeapObjectRow {
+    pub object: HeapObjectRef,
+    pub class_name: String,
+    /// The object's hprof id in hex, `0x1300`.
+    pub address: String,
+    pub shallow: u64,
+    pub retained: u64,
+    /// Has children in the dominator tree.
+    pub has_children: bool,
+    /// The text of a `java.lang.String`, or the name of the class a class object stands for.
+    pub preview: Option<String>,
+}
+
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(rename_all = "camelCase")]
+pub struct HeapObjectPage {
+    pub rows: Vec<HeapObjectRow>,
+    /// Rows of every page together.
+    pub total: u32,
+}
+
+/// How an object is held by the next step of a path to a GC root.
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(tag = "kind", rename_all = "camelCase", rename_all_fields = "camelCase")]
+pub enum HeapEdge {
+    /// An instance field; the name is empty when the dump does not show which one.
+    Field {
+        name: String,
+    },
+    Element {
+        index: u32,
+    },
+    Static {
+        name: String,
+    },
+    /// From an instance to its class.
+    ClassOf,
+    SuperClass,
+    ClassLoader,
+    /// `thread` is the name of the thread whose root it is, when the dump has it.
+    Root {
+        root: HeapRootKind,
+        thread: Option<String>,
+    },
+}
+
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(rename_all = "camelCase")]
+pub struct HeapPathStep {
+    pub object: HeapObjectRow,
+    /// How the next step holds this object; on the last step, the root.
+    pub via: HeapEdge,
+}
+
+/// A path from an object up to its GC root. A long one keeps only the steps nearest each end.
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(rename_all = "camelCase")]
+pub struct HeapRootPath {
+    pub steps: Vec<HeapPathStep>,
+    /// Steps left out between `steps[omitted_after - 1]` and `steps[omitted_after]`; 0 for none.
+    pub omitted: u32,
+    pub omitted_after: u32,
+}
@@ -0,0 +1,336 @@
+use super::*;
+use crate::hprof::BasicType;
+use crate::test_index::{analyzed, analyzed_bytes, obj, slot};
+use crate::testing::{HprofWriter, MiniHeap, sample, sample_with_string};
+
+const H: u64 = 0x1000;
+const N1: u64 = 0x1100;
+const N3: u64 = 0x1300;
+const L: u64 = 0x1400;
+const W: u64 = 0x1600;
+const N4: u64 = 0x1700;
+
+fn addresses(page: &HeapObjectPage) -> Vec<&str> {
+    page.rows.iter().map(|r| r.address.as_str()).collect()
+}
+
+fn retained(page: &HeapObjectPage) -> Vec<u64> {
+    page.rows.iter().map(|r| r.retained).collect()
+}
+
+fn path(index: &HeapIndex, addr: u64) -> Option<Vec<(String, HeapEdge)>> {
+    let path = index.path_to_root(obj(index, addr))?;
+    assert_eq!((path.omitted, path.omitted_after), (0, 0));
+    Some(path.steps.into_iter().map(|s| (s.object.address, s.via)).collect())
+}
+
+fn field(name: &str) -> HeapEdge {
+    HeapEdge::Field { name: name.to_owned() }
+}
+
+fn root(root: HeapRootKind, thread: Option<&str>) -> HeapEdge {
+    HeapEdge::Root { root, thread: thread.map(str::to_owned) }
+}
+
+#[test]
+fn top_level_dominators_sorted_by_retained() {
+    let index = analyzed(&sample());
+    let page = index.dominated(None, None, 0, 10);
+    assert_eq!(addresses(&page), ["0x1000", "0x1300", "0x1600"]);
+    assert_eq!(retained(&page), [72, 56, 24]);
+    // The class objects, rooted as sticky classes, are left out.
+    assert_eq!(page.total, 3);
+    assert_eq!(addresses(&index.dominated(None, None, 1, 1)), ["0x1300"]);
+}
+
+#[test]
+fn children_of_holder() {
+    let index = analyzed(&sample());
+    let page = index.dominated(Some(obj(&index, H)), None, 0, 10);
+    assert_eq!(addresses(&page), ["0x1100", "0x1200"]);
+    assert_eq!(retained(&page), [24, 24]);
+    assert_eq!(page.total, 2);
+    assert!(page.rows.iter().all(|r| !r.has_children && r.class_name == "Node"));
+    let n3 = index.object_row(obj(&index, N3)).unwrap();
+    assert!(n3.has_children);
+    assert_eq!(index.dominated(Some(n3.object), None, 0, 10).rows[0].class_name, "long[]");
+}
+
+#[test]
+fn largest_of_class() {
+    let index = analyzed(&sample());
+    let node = slot(&index, "Node");
+    let page = index.dominated(None, Some(node), 0, 2);
+    assert_eq!(addresses(&page), ["0x1300", "0x1100"]);
+    assert_eq!(retained(&page), [56, 24]);
+    assert_eq!(page.total, 3);
+    assert_eq!(addresses(&index.dominated(None, Some(node), 2, 2)), ["0x1200"]);
+    assert!(index.dominated(None, Some(node), 3, 2).rows.is_empty());
+    // Within a parent's children.
+    assert_eq!(addresses(&index.dominated(Some(obj(&index, H)), Some(node), 1, 5)), ["0x1200"]);
+    assert_eq!(index.dominated(Some(obj(&index, H)), Some(slot(&index, "Holder")), 0, 5).total, 0);
+}
+
+#[test]
+fn object_row_describes_object() {
+    let index = analyzed(&sample());
+    let row = index.object_row(obj(&index, N3)).unwrap();
+    assert_eq!(
+        row,
+        HeapObjectRow {
+            object: obj(&index, N3),
+            class_name: "Node".to_owned(),
+            address: "0x1300".to_owned(),
+            shallow: 24,
+            retained: 56,
+            has_children: true,
+            preview: None,
+        }
+    );
+    let unreachable = index.object_row(obj(&index, N4)).unwrap();
+    assert_eq!((unreachable.retained, unreachable.has_children), (0, false));
+
+    let holder = &index.class_info[slot(&index, "Holder") as usize];
+    let class_object = obj(&index, holder.id);
+    let row = index.object_row(class_object).unwrap();
+    assert_eq!((row.class_name.as_str(), row.preview.as_deref()), ("java.lang.Class", Some("Holder")));
+}
+
+#[test]
+fn refs_that_name_no_object_answer_nothing() {
+    let index = analyzed(&sample());
+    let node = slot(&index, "Node");
+    for bad in [index.root(), index.root() + 1, u32::MAX] {
+        let bad = HeapObjectRef(bad);
+        assert_eq!(index.object_row(bad), None);
+        assert_eq!(index.path_to_root(bad), None);
+        assert_eq!(index.dominated(Some(bad), None, 0, 10), HeapObjectPage { rows: Vec::new(), total: 0 });
+        assert_eq!(index.dominated(Some(bad), Some(node), 0, 10).total, 0);
+    }
+    for bad in [index.classes.len() as u32, u32::MAX] {
+        assert_eq!(index.dominated(None, Some(bad), 0, 10).total, 0);
+    }
+}
+
+#[test]
+fn path_to_root_names_fields_and_root() {
+    let index = analyzed(&sample());
+    assert_eq!(
+        path(&index, L),
+        Some(vec![("0x1400".to_owned(), field("next")), ("0x1300".to_owned(), root(HeapRootKind::JavaFrame, None))])
+    );
+    assert_eq!(
+        path(&index, N1),
+        Some(vec![("0x1100".to_owned(), field("a")), ("0x1000".to_owned(), root(HeapRootKind::JniGlobal, None))])
+    );
+    assert_eq!(path(&index, W), Some(vec![("0x1600".to_owned(), root(HeapRootKind::JniGlobal, None))]));
+    assert_eq!(path(&index, N4), None);
+}
+
+/// A rooted linked list of `len` Nodes from `0x100000`, each held by the next one's `next`.
+fn chain(len: u64) -> HeapIndex {
+    let mut heap = sample();
+    for i in 0..len {
+        let next = if i == 0 { 0 } else { 0x10_0000 + (i - 1) * 0x20 };
+        heap.object(0x10_0000 + i * 0x20, "Node", &[("next", next)]);
+    }
+    heap.root(HeapRootKind::JniGlobal, 0x10_0000 + (len - 1) * 0x20);
+    analyzed(&heap)
+}
+
+#[test]
+fn path_of_an_object_deep_in_a_linked_list_keeps_both_ends() {
+    let index = chain(3000);
+    let path = index.path_to_root(obj(&index, 0x10_0000)).unwrap();
+    assert_eq!((path.steps.len(), path.omitted, path.omitted_after), (1000, 2000, 500));
+    let address = |i: usize| path.steps[i].object.address.clone();
+    assert_eq!([address(0), address(499)], ["0x100000", "0x103e60"]);
+    // The step after the gap is the one 2000 nodes further up.
+    assert_eq!([address(500), address(999)], ["0x113880", "0x1176e0"]);
+    assert_eq!(path.steps[999].via, root(HeapRootKind::JniGlobal, None));
+    assert!(path.steps[..999].iter().all(|s| s.via == field("next")));
+}
+
+#[test]
+fn path_of_exactly_a_thousand_steps_is_whole() {
+    let index = chain(1000);
+    let path = index.path_to_root(obj(&index, 0x10_0000)).unwrap();
+    assert_eq!((path.steps.len(), path.omitted, path.omitted_after), (1000, 0, 0));
+}
+
+#[test]
+fn path_skips_the_weak_referent() {
+    let mut heap = sample();
+    heap.object(0x1c00, "java.lang.ref.WeakReference", &[("referent", 0x1d00), ("queue", 0x1d00)])
+        .object(0x1d00, "Node", &[])
+        .root(HeapRootKind::JniGlobal, 0x1c00);
+    let index = analyzed(&heap);
+    assert_eq!(path(&index, 0x1d00).unwrap()[0].1, field("queue"));
+}
+
+/// Kid extends Base, loaded by loader `0x300`; Base's static `cache` holds X; K is a rooted Kid;
+/// `0x700` is a rooted `Object[] { null, Y }`. No class is rooted on its own.
+fn class_edges_heap() -> Vec<u8> {
+    let mut w = HprofWriter::new();
+    let names = [(1, "Base"), (2, "Kid"), (3, "Ldr"), (4, "[Ljava/lang/Object;"), (5, "cache")];
+    for (id, name) in names {
+        w.string(id, name);
+    }
+    for (class, name) in [(0x100, 1), (0x200, 2), (0x400, 3), (0x800, 4)] {
+        w.load_class(class, name);
+    }
+    w.class(0x100, 0, &[], &[(5, 0x500)])
+        .class_with_loader(0x200, 0x100, 0x300, &[], &[])
+        .class(0x400, 0, &[], &[])
+        .class(0x800, 0, &[], &[])
+        .instance(0x300, 0x400, &[])
+        .instance(0x500, 0x400, &[])
+        .instance(0x600, 0x200, &[])
+        .obj_array(0x700, 0x800, &[0, 0x900])
+        .instance(0x900, 0x400, &[])
+        .root(HeapRootKind::JniGlobal, 0x600)
+        .root(HeapRootKind::JniGlobal, 0x700);
+    w.finish()
+}
+
+#[test]
+fn path_names_statics_supers_loaders_classes_and_elements() {
+    let index = analyzed_bytes(&class_edges_heap());
+    let k = ("0x600".to_owned(), root(HeapRootKind::JniGlobal, None));
+    assert_eq!(
+        path(&index, 0x500),
+        Some(vec![
+            ("0x500".to_owned(), HeapEdge::Static { name: "cache".to_owned() }),
+            ("0x100".to_owned(), HeapEdge::SuperClass),
+            ("0x200".to_owned(), HeapEdge::ClassOf),
+            k.clone(),
+        ])
+    );
+    assert_eq!(
+        path(&index, 0x300),
+        Some(vec![("0x300".to_owned(), HeapEdge::ClassLoader), ("0x200".to_owned(), HeapEdge::ClassOf), k])
+    );
+    assert_eq!(
+        path(&index, 0x900),
+        Some(vec![
+            ("0x900".to_owned(), HeapEdge::Element { index: 1 }),
+            ("0x700".to_owned(), root(HeapRootKind::JniGlobal, None))
+        ])
+    );
+}
+
+fn with_main_thread(mut heap: MiniHeap, name: impl FnOnce(&mut MiniHeap, u64)) -> MiniHeap {
+    heap.class("java.lang.Thread", Some("java.lang.Object"), &[("name", BasicType::Object)]);
+    name(&mut heap, 0x2000);
+    heap.object(0x2100, "java.lang.Thread", &[("name", 0x2000)]).root_in_thread(HeapRootKind::ThreadObject, 0x2100, 1);
+    heap
+}
+
+#[test]
+fn thread_name_on_java_frame_root() {
+    let heap = with_main_thread(sample_with_string(), |h, at| {
+        h.string(at, "main", true);
+    });
+    let index = analyzed(&heap);
+    let steps = path(&index, L).unwrap();
+    assert_eq!(steps.last().unwrap().1, root(HeapRootKind::JavaFrame, Some("main")));
+    // A JNI global carries no thread.
+    assert_eq!(path(&index, H).unwrap()[0].1, root(HeapRootKind::JniGlobal, None));
+}
+
+#[test]
+fn jdk8_thread_name_is_a_char_array() {
+    let heap = with_main_thread(sample(), |h, at| {
+        let utf16: Vec<u8> = "main".encode_utf16().flat_map(u16::to_be_bytes).collect();
+        h.prim_bytes(at, BasicType::Char, &utf16);
+    });
+    let index = analyzed(&heap);
+    assert_eq!(path(&index, N3).unwrap()[0].1, root(HeapRootKind::JavaFrame, Some("main")));
+}
+
+#[test]
+fn page_limit_is_clamped() {
+    let mut heap = MiniHeap::new();
+    heap.class("Node", Some("java.lang.Object"), &[("next", BasicType::Object)]);
+    for k in 0..600u64 {
+        let addr = 0x10_0000 + k * 0x100;
+        heap.object(addr, "Node", &[]).root(HeapRootKind::JniGlobal, addr);
+    }
+    let index = analyzed(&heap);
+    let node = slot(&index, "Node");
+    let page = index.dominated(None, Some(node), 0, 10_000);
+    assert_eq!((page.rows.len(), page.total), (MAX_PAGE as usize, 600));
+    let top = index.dominated(None, None, 0, 10_000);
+    assert_eq!((top.rows.len(), top.total), (MAX_PAGE as usize, 600));
+    assert_eq!(index.dominated(None, None, 550, 10_000).rows.len(), 50);
+    for (offset, limit) in [(u32::MAX, u32::MAX), (u32::MAX - 10, 100), (599, u32::MAX)] {
+        let page = index.dominated(None, Some(node), offset, limit);
+        assert_eq!((page.rows.len(), page.total), (usize::from(offset == 599), 600), "{offset} {limit}");
+        assert!(index.dominated(None, None, offset, limit).rows.len() <= 1);
+    }
+}
+
+#[test]
+fn class_rows_skip_empty_slots() {
+    let index = analyzed(&sample());
+    let rows = index.class_rows();
+    let node = rows.iter().find(|r| r.name == "Node").unwrap();
+    assert_eq!(
+        (node.class_index, node.count, node.shallow, node.retained, node.unreachable_count, node.ambiguous),
+        (slot(&index, "Node"), 3, 72, 104, 1, false)
+    );
+    assert!(rows.iter().all(|r| r.count + r.unreachable_count > 0));
+    assert!(!rows.iter().any(|r| r.name == "boolean[]"));
+    assert!(rows.windows(2).all(|p| p[0].retained >= p[1].retained));
+    assert_eq!(index.summary().objects, 8);
+}
+
+#[test]
+fn class_rows_mark_names_of_several_classes() {
+    let mut heap = sample();
+    // `object` takes the class defined last under a name, so each Foo gets one instance.
+    heap.class("Foo", Some("java.lang.Object"), &[])
+        .object(0x3000, "Foo", &[])
+        .class("Foo", Some("java.lang.Object"), &[])
+        .object(0x3100, "Foo", &[])
+        .object(0x3200, "Foo", &[]);
+    let index = analyzed(&heap);
+    let rows = index.class_rows();
+    let foos: Vec<_> = rows.iter().filter(|r| r.name == "Foo").collect();
+    assert_eq!(foos.len(), 2);
+    assert!(foos.iter().all(|r| r.ambiguous));
+    let mut counts: Vec<u64> = foos.iter().map(|r| r.unreachable_count).collect();
+    counts.sort_unstable();
+    assert_eq!(counts, [1, 2]);
+    assert!(rows.iter().filter(|r| r.name != "Foo").all(|r| !r.ambiguous));
+}
+
+#[test]
+fn ipc_shapes() {
+    assert_eq!(json(&HeapObjectRef(7)), "7");
+    assert_eq!(json(&HeapEdge::ClassOf), r#"{"kind":"classOf"}"#);
+    assert_eq!(json(&HeapEdge::Element { index: 2 }), r#"{"kind":"element","index":2}"#);
+    assert_eq!(
+        json(&root(HeapRootKind::JavaFrame, Some("main"))),
+        r#"{"kind":"root","root":"javaFrame","thread":"main"}"#
+    );
+    let row = HeapClassRow {
+        class_index: 1,
+        name: "A".to_owned(),
+        count: 2,
+        shallow: 3,
+        retained: 4,
+        unreachable_count: 5,
+        ambiguous: false,
+    };
+    assert_eq!(
+        json(&row),
+        r#"{"classIndex":1,"name":"A","count":2,"shallow":3,"retained":4,"unreachableCount":5,"ambiguous":false}"#
+    );
+    let back: HeapObjectRef = serde_json::from_str("4294967295").unwrap();
+    assert_eq!(back, HeapObjectRef(u32::MAX));
+}
+
+fn json(value: &impl serde::Serialize) -> String {
+    serde_json::to_string(value).unwrap()
+}
@@ -0,0 +1,44 @@
+//! HotSpot `.hprof` heap-dump reading and analysis for the debugger's JVM Memory view.
+
+mod analysis;
+mod column;
+mod compare;
+mod disk;
+mod dominators;
+mod error;
+mod files;
+mod graph;
+mod hprof;
+mod ids;
+mod index;
+mod names;
+mod progress;
+mod reader;
+mod registry;
+mod shallow;
+mod strings;
+#[cfg(test)]
+mod test_index;
+/// Fixture builders shared by this crate's tests and by dependants' tests and benches; not API.
+#[doc(hidden)]
+pub mod testing;
+
+pub use analysis::{AnalyzeOptions, analyze};
+pub use column::{Column, NONE, Pod, Store};
+pub use compare::{HeapClassDiff, compare};
+pub use disk::{DISK_MARGIN, capture_need, create_snapshot_dir, free_bytes, index_need, remove_stale, snapshots_root};
+pub use dominators::{Dominators, dominators};
+pub use error::HeapError;
+pub use graph::{ClassInfo, HeapGraph, PRIM_SLOTS, build_graph};
+pub use hprof::{
+    BasicType, ClassDump, HeapRecord, HeapRootKind, HprofHeader, Record, parse_header, record_at, scan, scan_segment,
+};
+pub use ids::{IdMap, IdMapBuilder};
+pub use index::{
+    ClassStat, HeapClassRow, HeapEdge, HeapIndex, HeapObjectPage, HeapObjectRef, HeapObjectRow, HeapPathStep,
+    HeapRootPath, HeapSummary, MAX_PAGE,
+};
+pub use names::display_name;
+pub use progress::HeapPhase;
+pub use registry::{HeapOrigin, HeapRegistry, HeapSnapshotId, HeapSnapshotInfo, OpenSnapshot};
+pub use shallow::{HistogramEntry, ShallowModel, SizeSource, VmLayout};
@@ -0,0 +1,66 @@
+//! Class names in the form the JVM's class histogram and the UI use.
+
+/// The Java source form of an hprof class name (`java/util/HashMap$Node`, `[Ljava/lang/String;`),
+/// as `ide_jvm_attach::display_class_name` writes it, plus `+0x` → `/0x` for hidden classes,
+/// which the histogram spells with a slash. Names that already use dots pass through unchanged.
+pub fn display_name(hprof_name: &str) -> String {
+    let dotted = hprof_name.replace('/', ".");
+    let dims = dotted.bytes().take_while(|&b| b == b'[').count();
+    let shown = if dims == 0 { dotted } else { array_name(&dotted, dims) };
+    // After the slash replacement, or the new slash would become a dot.
+    shown.replace("+0x", "/0x")
+}
+
+/// `[[I` → `int[][]`; a descriptor that is not one stays as it is.
+fn array_name(dotted: &str, dims: usize) -> String {
+    let element = &dotted[dims..];
+    let base = match element {
+        "Z" => "boolean",
+        "B" => "byte",
+        "C" => "char",
+        "S" => "short",
+        "I" => "int",
+        "J" => "long",
+        "F" => "float",
+        "D" => "double",
+        _ => match element.strip_prefix('L').and_then(|e| e.strip_suffix(';')) {
+            Some(class) => class,
+            None => return dotted.to_owned(),
+        },
+    };
+    format!("{base}{}", "[]".repeat(dims))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn display_names() {
+        for (hprof, shown) in [
+            ("[Z", "boolean[]"),
+            ("[J", "long[]"),
+            ("[[D", "double[][]"),
+            ("[Ljava/lang/String;", "java.lang.String[]"),
+            ("java/util/HashMap$Node", "java.util.HashMap$Node"),
+            ("Gen$$Lambda+0x0000007800000a00", "Gen$$Lambda/0x0000007800000a00"),
+        ] {
+            assert_eq!(display_name(hprof), shown, "{hprof}");
+        }
+    }
+
+    #[test]
+    fn dotted_names_and_hidden_class_arrays() {
+        for (hprof, shown) in [
+            ("java.lang.String", "java.lang.String"),
+            ("[Ljava.lang.Object;", "java.lang.Object[]"),
+            ("[[Lpkg.Gen$$Lambda+0x0000007800000a00;", "pkg.Gen$$Lambda/0x0000007800000a00[][]"),
+            ("[Ljava.lang.String", "[Ljava.lang.String"),
+            ("[Q", "[Q"),
+            ("0x7f00", "0x7f00"),
+            ("", ""),
+        ] {
+            assert_eq!(display_name(hprof), shown, "{hprof}");
+        }
+    }
+}
@@ -0,0 +1,103 @@
+//! Phases of a heap analysis and the progress/cancellation checks every long pass makes.
+
+use ide_core::CancellationToken;
+use serde::{Deserialize, Serialize};
+
+use crate::error::HeapError;
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(rename_all = "camelCase")]
+pub enum HeapPhase {
+    Reading,
+    Linking,
+    Dominators,
+    Retained,
+    Paths,
+    Saving,
+}
+
+/// Longest stretch of work between two progress reports (and looks at the cancellation token).
+pub(crate) const CHECK_EVERY: u64 = 1 << 20;
+
+/// The caller's progress callback plus the token, looked at right after every report so a callback
+/// that cancels stops the work before the next step.
+pub(crate) struct Progress<'a> {
+    report: &'a dyn Fn(HeapPhase, u64, u64) -> Result<(), HeapError>,
+    cancel: &'a CancellationToken,
+}
+
+impl<'a> Progress<'a> {
+    pub(crate) fn new(
+        report: &'a dyn Fn(HeapPhase, u64, u64) -> Result<(), HeapError>,
+        cancel: &'a CancellationToken,
+    ) -> Self {
+        Self { report, cancel }
+    }
+
+    pub(crate) fn report(&self, phase: HeapPhase, done: u64, total: u64) -> Result<(), HeapError> {
+        (self.report)(phase, done, total)?;
+        self.check()
+    }
+
+    pub(crate) fn token(&self) -> &'a CancellationToken {
+        self.cancel
+    }
+
+    /// Looks at the token without reporting.
+    pub(crate) fn check(&self) -> Result<(), HeapError> {
+        if self.cancel.is_cancelled() { Err(HeapError::Cancelled) } else { Ok(()) }
+    }
+
+    /// Looks at the token at step 0 and reports every [`CHECK_EVERY`] steps after it. Step 0 does
+    /// not report: a loop starts right after its phase's own report.
+    pub(crate) fn step(&self, step: u64, phase: HeapPhase, done: u64, total: u64) -> Result<(), HeapError> {
+        if step == 0 {
+            self.check()
+        } else if step.is_multiple_of(CHECK_EVERY) {
+            self.report(phase, done, total)
+        } else {
+            Ok(())
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use std::cell::RefCell;
+
+    use super::*;
+
+    #[test]
+    fn steps_check_at_zero_and_report_every_check_interval() {
+        let calls = RefCell::new(Vec::new());
+        let report = |phase, done, total| {
+            calls.borrow_mut().push((phase, done, total));
+            Ok(())
+        };
+        let cancel = CancellationToken::new();
+        let progress = Progress::new(&report, &cancel);
+        for step in [0, 1, CHECK_EVERY - 1, CHECK_EVERY, CHECK_EVERY + 1, 3 * CHECK_EVERY] {
+            progress.step(step, HeapPhase::Linking, step, 9).unwrap();
+        }
+        assert_eq!(*calls.borrow(), [(HeapPhase::Linking, CHECK_EVERY, 9), (HeapPhase::Linking, 3 * CHECK_EVERY, 9)]);
+
+        cancel.cancel();
+        assert!(matches!(progress.step(0, HeapPhase::Linking, 0, 9), Err(HeapError::Cancelled)));
+        assert!(matches!(progress.report(HeapPhase::Saving, 1, 1), Err(HeapError::Cancelled)));
+        assert_eq!(calls.borrow().last(), Some(&(HeapPhase::Saving, 1, 1)), "reports before it looks at the token");
+    }
+
+    #[test]
+    fn report_errors_pass_through() {
+        let report = |_, _, _| Err(HeapError::NotEnoughDiskSpace { needed: 2, available: 1 });
+        let cancel = CancellationToken::new();
+        let progress = Progress::new(&report, &cancel);
+        assert!(matches!(progress.report(HeapPhase::Linking, 0, 1), Err(HeapError::NotEnoughDiskSpace { .. })));
+    }
+
+    #[test]
+    fn phases_serialize_in_camel_case() {
+        assert_eq!(serde_json::to_string(&HeapPhase::Dominators).unwrap(), "\"dominators\"");
+        assert_eq!(serde_json::from_str::<HeapPhase>("\"saving\"").unwrap(), HeapPhase::Saving);
+    }
+}
@@ -0,0 +1,92 @@
+use crate::error::HeapError;
+
+/// Big-endian cursor over a dump. Every read is bounds-checked; running off `buf` yields
+/// `Truncated` at `buf.len()`, so callers bound a record by slicing `buf` to its end.
+pub(crate) struct Reader<'a> {
+    buf: &'a [u8],
+    pos: usize,
+    id_size: u8,
+}
+
+impl<'a> Reader<'a> {
+    pub(crate) fn new(buf: &'a [u8], pos: usize, id_size: u8) -> Self {
+        Self { buf, pos, id_size }
+    }
+
+    pub(crate) fn pos(&self) -> usize {
+        self.pos
+    }
+
+    pub(crate) fn id_size(&self) -> u8 {
+        self.id_size
+    }
+
+    pub(crate) fn buf(&self) -> &'a [u8] {
+        self.buf
+    }
+
+    pub(crate) fn bytes(&mut self, n: usize) -> Result<&'a [u8], HeapError> {
+        let end = self.pos.checked_add(n).filter(|&end| end <= self.buf.len());
+        let Some(end) = end else {
+            return Err(HeapError::Truncated { at: self.buf.len() as u64 });
+        };
+        let slice = &self.buf[self.pos..end];
+        self.pos = end;
+        Ok(slice)
+    }
+
+    pub(crate) fn skip(&mut self, n: usize) -> Result<(), HeapError> {
+        self.bytes(n).map(|_| ())
+    }
+
+    fn array<const N: usize>(&mut self) -> Result<[u8; N], HeapError> {
+        let mut out = [0u8; N];
+        out.copy_from_slice(self.bytes(N)?);
+        Ok(out)
+    }
+
+    pub(crate) fn u1(&mut self) -> Result<u8, HeapError> {
+        Ok(self.array::<1>()?[0])
+    }
+
+    pub(crate) fn u2(&mut self) -> Result<u16, HeapError> {
+        Ok(u16::from_be_bytes(self.array()?))
+    }
+
+    pub(crate) fn u4(&mut self) -> Result<u32, HeapError> {
+        Ok(u32::from_be_bytes(self.array()?))
+    }
+
+    pub(crate) fn u8(&mut self) -> Result<u64, HeapError> {
+        Ok(u64::from_be_bytes(self.array()?))
+    }
+
+    /// `id_size` is 4 or 8; the public entry points reject anything else before building a reader.
+    pub(crate) fn id(&mut self) -> Result<u64, HeapError> {
+        if self.id_size == 4 { self.u4().map(u64::from) } else { self.u8() }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn reads_big_endian_and_ids_of_both_sizes() {
+        let buf = [1, 0, 2, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 4, 0, 0, 0, 5];
+        let mut r = Reader::new(&buf, 0, 8);
+        assert_eq!((r.u1().unwrap(), r.u2().unwrap(), r.u4().unwrap(), r.u8().unwrap()), (1, 2, 3, 4));
+        assert_eq!(r.pos(), 15);
+        assert_eq!(Reader::new(&buf[15..], 0, 4).id().unwrap(), 5);
+    }
+
+    #[test]
+    fn running_off_the_end_reports_the_buffer_end() {
+        let buf = [0u8; 6];
+        let mut r = Reader::new(&buf, 4, 8);
+        assert!(matches!(r.u4(), Err(HeapError::Truncated { at: 6 })));
+        assert_eq!(r.pos(), 4, "a failed read does not advance");
+        assert!(matches!(r.skip(usize::MAX), Err(HeapError::Truncated { at: 6 })));
+        assert!(matches!(Reader::new(&buf, 99, 8).u1(), Err(HeapError::Truncated { at: 6 })));
+    }
+}
@@ -0,0 +1,163 @@
+//! The heap snapshots that are open in this process.
+
+use std::collections::BTreeMap;
+use std::path::{Path, PathBuf};
+use std::sync::{Arc, Mutex, MutexGuard, PoisonError};
+
+use ide_core::process::process_alive;
+use ide_core::{DebugSessionId, IpcPath};
+use serde::{Deserialize, Serialize};
+
+use crate::disk::remove_stale;
+use crate::index::{HeapIndex, HeapSummary};
+
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash, Serialize, Deserialize, specta::Type)]
+#[serde(transparent)]
+pub struct HeapSnapshotId(pub u32);
+
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(tag = "kind", rename_all = "camelCase", rename_all_fields = "camelCase")]
+pub enum HeapOrigin {
+    /// Dumped from a live debug session.
+    Captured { session: DebugSessionId, pid: u32, java_version: String, taken_while_suspended: bool, dump_ms: u32 },
+    /// An `.hprof` the user opened; it is never deleted.
+    File { path: IpcPath },
+}
+
+impl HeapOrigin {
+    /// Text identifying the snapshot in the UI: the process id of a capture, the file name of a
+    /// file. The capture time is `created_ms`, which the UI formats in local time.
+    pub fn label(&self) -> String {
+        match self {
+            HeapOrigin::Captured { pid, .. } => pid.to_string(),
+            HeapOrigin::File { path } => path.file_name().unwrap_or(path.as_os_str()).to_string_lossy().into_owned(),
+        }
+    }
+}
+
+#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(rename_all = "camelCase")]
+pub struct HeapSnapshotInfo {
+    pub id: HeapSnapshotId,
+    pub label: String,
+    pub origin: HeapOrigin,
+    pub summary: HeapSummary,
+    /// Unix time in milliseconds when the snapshot was opened.
+    pub created_ms: u64,
+}
+
+/// An analyzed snapshot together with the directory that holds its files. Dropping it unmaps the
+/// index and then removes the directory, dump included for a capture; a dump opened from a file
+/// is outside the directory and stays.
+pub struct OpenSnapshot {
+    pub info: HeapSnapshotInfo,
+    /// `None` only while dropping, so the mappings are gone before the directory is deleted
+    /// (Windows cannot delete a mapped file).
+    index: Option<HeapIndex>,
+    /// Holds the index files and the dump of a capture.
+    pub dir: PathBuf,
+    pub dump: PathBuf,
+    /// Set by [`HeapRegistry::insert`] once `dir` is known to be one of the registry's own.
+    remove_dir: bool,
+}
+
+impl OpenSnapshot {
+    /// The directory is not removed on drop until the snapshot is in a [`HeapRegistry`] whose
+    /// root holds it.
+    pub fn new(info: HeapSnapshotInfo, index: HeapIndex, dir: PathBuf, dump: PathBuf) -> Self {
+        Self { info, index: Some(index), dir, dump, remove_dir: false }
+    }
+
+    pub fn index(&self) -> &HeapIndex {
+        self.index.as_ref().expect("the index is only taken while dropping")
+    }
+}
+
+impl Drop for OpenSnapshot {
+    fn drop(&mut self) {
+        drop(self.index.take());
+        if !self.remove_dir {
+            return;
+        }
+        // The user's own dump that happens to sit inside `dir` (an opened file is analyzed from a
+        // private copy, which goes with the directory).
+        if matches!(&self.info.origin, HeapOrigin::File { path } if **path == self.dump)
+            && self.dump.starts_with(&self.dir)
+        {
+            return;
+        }
+        // A link is not followed: only a real directory is deleted.
+        if std::fs::symlink_metadata(&self.dir).is_ok_and(|meta| meta.file_type().is_dir())
+            && let Err(err) = std::fs::remove_dir_all(&self.dir)
+        {
+            tracing::warn!(dir = %self.dir.display(), %err, "could not remove a heap snapshot directory");
+        }
+    }
+}
+
+struct State {
+    next_id: u32,
+    open: BTreeMap<u32, Arc<OpenSnapshot>>,
+}
+
+/// The open snapshots, shared between threads. Ids are never reused within a process.
+pub struct HeapRegistry {
+    root: PathBuf,
+    state: Mutex<State>,
+}
+
+impl HeapRegistry {
+    /// Registry for snapshot directories under `root`; first removes the directories there that
+    /// belong to processes that no longer exist.
+    pub fn new(root: PathBuf) -> Self {
+        remove_stale(&root, process_alive);
+        Self { root, state: Mutex::new(State { next_id: 1, open: BTreeMap::new() }) }
+    }
+
+    pub fn root(&self) -> &Path {
+        &self.root
+    }
+
+    fn state(&self) -> MutexGuard<'_, State> {
+        self.state.lock().unwrap_or_else(PoisonError::into_inner)
+    }
+
+    /// Registers the snapshot that `make` builds for a fresh id. `make` runs outside the lock.
+    pub fn insert(&self, make: impl FnOnce(HeapSnapshotId) -> OpenSnapshot) -> HeapSnapshotInfo {
+        let id = {
+            let mut state = self.state();
+            let id = state.next_id;
+            state.next_id = id.saturating_add(1);
+            HeapSnapshotId(id)
+        };
+        let mut snapshot = make(id);
+        snapshot.info.id = id;
+        snapshot.remove_dir = snapshot.dir.file_name().is_some() && snapshot.dir.parent() == Some(self.root.as_path());
+        if !snapshot.remove_dir {
+            tracing::warn!(dir = %snapshot.dir.display(), "heap snapshot directory is outside the registry root; keeping it");
+        }
+        let info = snapshot.info.clone();
+        self.state().open.insert(id.0, Arc::new(snapshot));
+        info
+    }
+
+    pub fn get(&self, id: HeapSnapshotId) -> Option<Arc<OpenSnapshot>> {
+        self.state().open.get(&id.0).cloned()
+    }
+
+    /// Forgets the snapshot; its directory goes once the last query using it lets go. `false` for
+    /// an id that is not open.
+    pub fn close(&self, id: HeapSnapshotId) -> bool {
+        // Bound first so the lock is released before the snapshot may be dropped: that deletes files.
+        let removed = self.state().open.remove(&id.0);
+        removed.is_some()
+    }
+
+    /// In the order the snapshots were opened.
+    pub fn list(&self) -> Vec<HeapSnapshotInfo> {
+        self.state().open.values().map(|snapshot| snapshot.info.clone()).collect()
+    }
+}
+
+#[cfg(test)]
+mod tests;
@@ -0,0 +1,265 @@
+use std::sync::Arc;
+
+use ide_core::{CancellationToken, DebugSessionId};
+
+use super::*;
+use crate::analysis::{AnalyzeOptions, analyze};
+use crate::disk::create_snapshot_dir;
+use crate::error::HeapError;
+use crate::progress::HeapPhase;
+use crate::testing::sample;
+
+fn no_progress(_: HeapPhase, _: u64, _: u64) -> Result<(), HeapError> {
+    Ok(())
+}
+
+fn captured() -> HeapOrigin {
+    HeapOrigin::Captured {
+        session: DebugSessionId(7),
+        pid: 4242,
+        java_version: "21.0.2".into(),
+        taken_while_suspended: true,
+        dump_ms: 35,
+    }
+}
+
+fn external(path: &Path) -> HeapOrigin {
+    HeapOrigin::File { path: IpcPath(path.to_path_buf()) }
+}
+
+/// A snapshot whose index files are mapped from `dir`, like a real one: `dump` is analyzed in
+/// place and `dir` receives the columns.
+fn open_in(dir: &Path, dump: &Path, origin: HeapOrigin) -> impl FnOnce(HeapSnapshotId) -> OpenSnapshot {
+    let dir = dir.to_path_buf();
+    let dump = dump.to_path_buf();
+    move |id| {
+        std::fs::write(&dump, sample().bytes()).unwrap();
+        let index = analyze(&dump, &dir, AnalyzeOptions::default(), &no_progress, &CancellationToken::new()).unwrap();
+        let info = HeapSnapshotInfo {
+            id,
+            label: origin.label(),
+            origin,
+            summary: index.summary.clone(),
+            created_ms: 1_700_000_000_000,
+        };
+        OpenSnapshot::new(info, index, dir, dump)
+    }
+}
+
+/// Inserts a captured snapshot with its own directory under the registry's root.
+fn insert_captured(registry: &HeapRegistry) -> (HeapSnapshotInfo, PathBuf) {
+    let dir = create_snapshot_dir(registry.root()).unwrap();
+    let dump = dir.join("dump.hprof");
+    let info = registry.insert(open_in(&dir, &dump, captured()));
+    (info, dir)
+}
+
+fn names(dir: &Path) -> Vec<String> {
+    let mut names: Vec<_> =
+        std::fs::read_dir(dir).unwrap().map(|e| e.unwrap().file_name().into_string().unwrap()).collect();
+    names.sort();
+    names
+}
+
+#[test]
+fn closing_snapshot_removes_dir() {
+    let root = tempfile::tempdir().unwrap();
+    let registry = HeapRegistry::new(root.path().to_path_buf());
+    let (info, dir) = insert_captured(&registry);
+    assert!(dir.join("dump.hprof").exists() && dir.join("summary.json").exists());
+    assert!(registry.close(info.id));
+    assert!(!dir.exists());
+    assert!(!registry.close(info.id));
+    assert!(registry.get(info.id).is_none());
+}
+
+#[test]
+fn external_dump_is_never_deleted() {
+    let root = tempfile::tempdir().unwrap();
+    let outside = tempfile::tempdir().unwrap();
+    let dump = outside.path().join("app.hprof");
+    let registry = HeapRegistry::new(root.path().to_path_buf());
+    let dir = create_snapshot_dir(registry.root()).unwrap();
+    let info = registry.insert(open_in(&dir, &dump, external(&dump)));
+    assert_eq!(info.label, "app.hprof");
+    assert!(dir.join("summary.json").exists());
+    assert!(registry.close(info.id));
+    assert!(!dir.exists());
+    assert!(dump.exists());
+}
+
+#[test]
+fn a_dump_inside_the_dir_of_a_file_snapshot_keeps_the_dir() {
+    let root = tempfile::tempdir().unwrap();
+    let registry = HeapRegistry::new(root.path().to_path_buf());
+    let dir = create_snapshot_dir(registry.root()).unwrap();
+    let dump = dir.join("opened.hprof");
+    let info = registry.insert(open_in(&dir, &dump, external(&dump)));
+    assert!(registry.close(info.id));
+    assert!(dump.exists());
+}
+
+#[test]
+fn a_dir_outside_the_root_is_never_deleted() {
+    let root = tempfile::tempdir().unwrap();
+    let elsewhere = tempfile::tempdir().unwrap();
+    let registry = HeapRegistry::new(root.path().to_path_buf());
+    let dump = elsewhere.path().join("dump.hprof");
+    let info = registry.insert(open_in(elsewhere.path(), &dump, captured()));
+    assert!(registry.close(info.id));
+    assert!(dump.exists());
+    // Neither the root itself nor a path that climbs out of it counts as a snapshot dir.
+    let sneaky = root.path().join("..").join(elsewhere.path().file_name().unwrap());
+    let info = registry.insert(open_in(&sneaky, &dump, captured()));
+    assert!(registry.close(info.id));
+    assert!(dump.exists());
+}
+
+#[cfg(unix)]
+#[test]
+fn a_symlinked_dir_is_not_followed() {
+    let root = tempfile::tempdir().unwrap();
+    let outside = tempfile::tempdir().unwrap();
+    let dump = outside.path().join("dump.hprof");
+    let link = root.path().join("link");
+    std::os::unix::fs::symlink(outside.path(), &link).unwrap();
+    let registry = HeapRegistry::new(root.path().to_path_buf());
+    let info = registry.insert(open_in(&link, &dump, captured()));
+    assert!(registry.close(info.id));
+    assert!(dump.exists());
+}
+
+#[test]
+fn ids_are_never_reused() {
+    let root = tempfile::tempdir().unwrap();
+    let registry = HeapRegistry::new(root.path().to_path_buf());
+    let (first, _) = insert_captured(&registry);
+    assert!(registry.close(first.id));
+    let (second, _) = insert_captured(&registry);
+    let (third, _) = insert_captured(&registry);
+    assert!(first.id.0 < second.id.0 && second.id.0 < third.id.0);
+}
+
+#[test]
+fn the_registry_decides_the_id_in_the_info() {
+    let root = tempfile::tempdir().unwrap();
+    let registry = HeapRegistry::new(root.path().to_path_buf());
+    let dir = create_snapshot_dir(registry.root()).unwrap();
+    let dump = dir.join("dump.hprof");
+    let make = open_in(&dir, &dump, captured());
+    let info = registry.insert(|id| {
+        let mut snapshot = make(id);
+        snapshot.info.id = HeapSnapshotId(u32::MAX);
+        snapshot
+    });
+    assert_ne!(info.id, HeapSnapshotId(u32::MAX));
+    assert_eq!(registry.get(info.id).unwrap().info.id, info.id);
+}
+
+#[test]
+fn list_is_in_opening_order_and_get_shares_the_snapshot() {
+    let root = tempfile::tempdir().unwrap();
+    let registry = HeapRegistry::new(root.path().to_path_buf());
+    let (a, _) = insert_captured(&registry);
+    let (b, _) = insert_captured(&registry);
+    let (c, _) = insert_captured(&registry);
+    assert!(registry.close(b.id));
+    assert_eq!(registry.list(), [a.clone(), c.clone()]);
+    let one = registry.get(a.id).unwrap();
+    let two = registry.get(a.id).unwrap();
+    assert!(Arc::ptr_eq(&one, &two));
+    assert_eq!(one.info, a);
+    assert_eq!(one.index().summary, a.summary);
+}
+
+#[test]
+fn a_snapshot_in_use_keeps_its_dir_until_the_last_holder_lets_go() {
+    let root = tempfile::tempdir().unwrap();
+    let registry = HeapRegistry::new(root.path().to_path_buf());
+    let (info, dir) = insert_captured(&registry);
+    let held = registry.get(info.id).unwrap();
+    assert!(registry.close(info.id));
+    assert!(registry.get(info.id).is_none() && registry.list().is_empty());
+    assert!(dir.exists());
+    drop(held);
+    assert!(!dir.exists());
+}
+
+#[test]
+fn dropping_the_registry_removes_the_open_snapshots() {
+    let root = tempfile::tempdir().unwrap();
+    let registry = HeapRegistry::new(root.path().to_path_buf());
+    let (_, dir) = insert_captured(&registry);
+    drop(registry);
+    assert!(!dir.exists());
+    assert!(names(root.path()).is_empty());
+}
+
+#[cfg(unix)]
+#[test]
+fn new_clears_dirs_whose_owner_died() {
+    let root = tempfile::tempdir().unwrap();
+    let mut child = std::process::Command::new("true").spawn().unwrap();
+    let dead = child.id();
+    child.wait().unwrap();
+    let dead_dir = root.path().join("dead");
+    std::fs::create_dir(&dead_dir).unwrap();
+    std::fs::write(dead_dir.join("owner"), dead.to_string()).unwrap();
+    let live_dir = create_snapshot_dir(root.path()).unwrap();
+    let registry = HeapRegistry::new(root.path().to_path_buf());
+    assert!(!dead_dir.exists());
+    assert!(live_dir.exists());
+    assert_eq!(registry.root(), root.path());
+}
+
+#[test]
+fn concurrent_inserts_get_distinct_ids() {
+    let root = tempfile::tempdir().unwrap();
+    let registry = Arc::new(HeapRegistry::new(root.path().to_path_buf()));
+    let handles: Vec<_> = (0..6)
+        .map(|_| {
+            let registry = registry.clone();
+            std::thread::spawn(move || (0..3).map(|_| insert_captured(&registry).0.id).collect::<Vec<_>>())
+        })
+        .collect();
+    let mut ids: Vec<_> = handles.into_iter().flat_map(|h| h.join().unwrap()).collect();
+    ids.sort_by_key(|id| id.0);
+    ids.dedup();
+    assert_eq!(ids.len(), 18);
+    assert_eq!(registry.list().len(), 18);
+    for id in ids {
+        assert!(registry.close(id));
+    }
+    assert!(names(root.path()).is_empty());
+}
+
+#[test]
+fn labels_name_the_pid_or_the_file() {
+    assert_eq!(captured().label(), "4242");
+    assert_eq!(external(Path::new("/tmp/dumps/app.hprof")).label(), "app.hprof");
+    assert_eq!(external(Path::new("/")).label(), "/");
+}
+
+#[test]
+fn origin_and_info_serialize_as_the_ui_expects() {
+    let value = serde_json::to_value(captured()).unwrap();
+    assert_eq!(
+        value,
+        serde_json::json!({
+            "kind": "captured", "session": 7, "pid": 4242, "javaVersion": "21.0.2",
+            "takenWhileSuspended": true, "dumpMs": 35
+        })
+    );
+    assert_eq!(serde_json::to_value(external(Path::new("/a/b.hprof"))).unwrap()["path"], "/a/b.hprof");
+    assert_eq!(serde_json::to_value(HeapSnapshotId(3)).unwrap(), serde_json::json!(3));
+    let back: HeapOrigin = serde_json::from_value(value).unwrap();
+    assert_eq!(back, captured());
+}
+
+// `HeapRegistry::get` hands out `Arc<OpenSnapshot>` to query threads.
+const _: fn() = || {
+    fn check<T: Send + Sync>() {}
+    check::<HeapIndex>();
+    check::<OpenSnapshot>();
+    check::<HeapRegistry>();
+};
@@ -0,0 +1,265 @@
+//! Shallow sizes: the bytes each object takes in the JVM heap, from the object layout rules, the
+//! JVM's own class histogram, or the distances between object addresses in the dump.
+
+mod layout;
+mod mirrors;
+
+use std::collections::HashMap;
+
+use ide_core::CancellationToken;
+use serde::{Deserialize, Serialize};
+
+pub use self::layout::VmLayout;
+use self::mirrors::{Mirrors, injected_by_table};
+use crate::error::HeapError;
+use crate::graph::{ClassInfo, HeapGraph};
+use crate::hprof::BasicType;
+use crate::names::display_name;
+use crate::progress::CHECK_EVERY;
+
+/// How far past the layout size an address gap may be and still count as an object size.
+const GAP_SLACK: u64 = 64;
+/// Share of the instance types that can have a gap (two or more instances), in tenths, that must
+/// take their size from address gaps for the sizes to be reported as coming from them.
+const GAP_TRUST_TENTHS: usize = 9;
+
+/// Where the sizes of instances came from.
+///
+/// Class objects (mirrors) are approximate in every case: HotSpot leaves the fields it injects
+/// into `java.lang.Class` out of the dump, so their layout size is short by a fixed amount per
+/// mirror. With a histogram that amount is fitted to its `java.lang.Class` row; otherwise (or when
+/// the fit is rejected) it comes from a table measured per JDK and reference size, within a few
+/// bytes per mirror, or is 32 when the JDK is unknown.
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
+#[serde(rename_all = "camelCase")]
+pub enum SizeSource {
+    /// The JVM's class histogram from the capture.
+    Jvm,
+    /// The smallest distance between neighbouring objects of a type, in a dump the IDE did not
+    /// capture.
+    AddressGaps,
+    Layout,
+}
+
+/// A row of the JVM's class histogram.
+#[derive(Clone, Debug, PartialEq, Eq)]
+pub struct HistogramEntry {
+    /// Display form: `java.lang.String`, `int[]`, `Gen$$Lambda/0x…`.
+    pub name: String,
+    pub instances: u64,
+    pub bytes: u64,
+}
+
+enum TypeSize {
+    Fixed(u64),
+    ObjectArray,
+    /// Class objects are sized one by one; this is for an instance of `java.lang.Class` that is
+    /// not a class object.
+    ClassObject(u64),
+}
+
+/// Shallow size of every object of a [`HeapGraph`]. Instances of a type share one size; arrays
+/// follow the layout; class objects add their statics to the size of `java.lang.Class`.
+pub struct ShallowModel {
+    pub source: SizeSource,
+    layout: VmLayout,
+    /// Per type slot of a class; primitive array slots follow and have no entry.
+    types: Vec<TypeSize>,
+    /// `(node, size)` of each class object, by node.
+    class_objects: Vec<(u32, u64)>,
+    /// Per class slot: another class has the same display name.
+    ambiguous: Vec<bool>,
+}
+
+impl ShallowModel {
+    /// `histogram` is the JVM's class histogram of the same stop as the dump, when the IDE captured
+    /// it. Without it, sizes come from address gaps where they agree with the layout.
+    ///
+    /// A name shared by several classes (several class loaders) never takes a histogram size,
+    /// since the name is the only link between the dump and the histogram; see
+    /// [`Self::is_ambiguous`]. `java.lang.Class` never does either, because mirror sizes vary with
+    /// their statics; the histogram only tells how many bytes HotSpot adds to each mirror.
+    pub fn new(
+        graph: &HeapGraph,
+        layout: VmLayout,
+        histogram: Option<&[HistogramEntry]>,
+        cancel: &CancellationToken,
+    ) -> Result<Self, HeapError> {
+        if cancel.is_cancelled() {
+            return Err(HeapError::Cancelled);
+        }
+        let classes = &graph.classes;
+        let field_bytes = field_bytes(classes, layout);
+        let by_layout: Vec<u64> = field_bytes.iter().map(|&bytes| layout.instance_size(bytes)).collect();
+        let names: Vec<String> = classes.iter().map(|c| display_name(&c.name)).collect();
+        let ambiguous = ambiguous_names(&names);
+
+        let class_slot = graph.class_slot as usize;
+        let mirrors = Mirrors::collect(graph, by_layout[class_slot], layout);
+        let mut fitted = None;
+        if let Some(rows) = histogram
+            && !ambiguous[class_slot]
+        {
+            let mut class_rows = rows.iter().filter(|row| row.name == names[class_slot]);
+            if let (Some(row), None) = (class_rows.next(), class_rows.next()) {
+                fitted = mirrors.fit_injected(graph, layout, by_layout[class_slot], row, cancel)?;
+            }
+        }
+        let injected = fitted.unwrap_or_else(|| injected_by_table(layout));
+
+        let mut types: Vec<TypeSize> = classes
+            .iter()
+            .enumerate()
+            .map(|(slot, class)| {
+                if class.name.starts_with('[') {
+                    TypeSize::ObjectArray
+                } else if slot == class_slot {
+                    TypeSize::ClassObject(layout.align(by_layout[slot] + injected))
+                } else {
+                    TypeSize::Fixed(by_layout[slot])
+                }
+            })
+            .collect();
+        let source = match histogram {
+            Some(rows) => {
+                apply_histogram(&mut types, &names, &ambiguous, rows);
+                SizeSource::Jvm
+            }
+            None => apply_address_gaps(&mut types, graph, &by_layout, cancel)?,
+        };
+        Ok(Self { source, layout, types, class_objects: mirrors.sizes(layout, injected), ambiguous })
+    }
+
+    /// Shallow size of `object` (a node of the graph); 0 for the super-root.
+    pub fn size_of(&self, graph: &HeapGraph, object: u32) -> u64 {
+        let Some(&slot) = graph.types.get(object as usize) else { return 0 };
+        match self.types.get(slot as usize) {
+            Some(&TypeSize::Fixed(size)) => size,
+            Some(TypeSize::ObjectArray) => self.array_size(BasicType::Object, graph.lens[object as usize]),
+            Some(&TypeSize::ClassObject(fallback)) => self
+                .class_objects
+                .binary_search_by_key(&object, |&(node, _)| node)
+                .map_or(fallback, |at| self.class_objects[at].1),
+            None => match graph.prim_type(slot) {
+                Some(ty) => self.array_size(ty, graph.lens[object as usize]),
+                None => 0,
+            },
+        }
+    }
+
+    /// Whether another class has the same display name as the class in `slot`. Sizes of such
+    /// classes come from the layout, and anything joined to them by name (histogram rows, a
+    /// second snapshot) cannot tell them apart.
+    pub fn is_ambiguous(&self, slot: u32) -> bool {
+        self.ambiguous.get(slot as usize).copied().unwrap_or(false)
+    }
+
+    fn array_size(&self, ty: BasicType, len: u32) -> u64 {
+        self.layout.array_size(ty, u64::from(len))
+    }
+}
+
+/// Bytes of instance fields per class, its superclasses included. Super chains always end
+/// (`ClassInfo::super_index` has its cycles cut).
+fn field_bytes(classes: &[ClassInfo], layout: VmLayout) -> Vec<u64> {
+    let mut total: Vec<Option<u64>> = vec![None; classes.len()];
+    let mut path = Vec::new();
+    for start in 0..classes.len() {
+        let mut cursor = Some(start);
+        let mut below = 0;
+        while let Some(c) = cursor {
+            if let Some(known) = total[c] {
+                below = known;
+                break;
+            }
+            path.push(c);
+            cursor = classes[c].super_index.map(|s| s as usize);
+        }
+        while let Some(c) = path.pop() {
+            let own: u64 = classes[c].fields.iter().map(|(_, ty)| ty.heap_size(layout.ref_size)).sum();
+            below += own;
+            total[c] = Some(below);
+        }
+    }
+    total.into_iter().map(Option::unwrap_or_default).collect()
+}
+
+fn ambiguous_names(names: &[String]) -> Vec<bool> {
+    let mut counts: HashMap<&str, u32> = HashMap::with_capacity(names.len());
+    for name in names {
+        *counts.entry(name).or_default() += 1;
+    }
+    names.iter().map(|name| counts[name.as_str()] > 1).collect()
+}
+
+/// `bytes / instances` for each plain class with a histogram row of its name. A name that is
+/// ambiguous in the dump or repeated in the histogram, or a row that is not a whole number of
+/// objects, keeps its layout size.
+fn apply_histogram(types: &mut [TypeSize], names: &[String], ambiguous: &[bool], rows: &[HistogramEntry]) {
+    let mut per_object: HashMap<&str, Option<u64>> = HashMap::with_capacity(rows.len());
+    for row in rows {
+        let size = row.bytes.checked_div(row.instances).filter(|&s| s > 0 && row.bytes % row.instances == 0);
+        per_object.entry(&row.name).and_modify(|seen| *seen = None).or_insert(size);
+    }
+    for (slot, ty) in types.iter_mut().enumerate() {
+        if let TypeSize::Fixed(size) = ty
+            && !ambiguous[slot]
+            && let Some(&Some(from_histogram)) = per_object.get(names[slot].as_str())
+        {
+            *size = from_histogram;
+        }
+    }
+}
+
+/// Takes the smallest distance from an instance to the next object in address order as the size
+/// of its type, for types with two or more instances where that distance is no smaller than the
+/// layout size and at most [`GAP_SLACK`] bigger. The result says [`SizeSource::AddressGaps`] when
+/// nine in ten of the types with two or more instances did; types with one instance have no gap
+/// to measure, so they neither count for nor against.
+fn apply_address_gaps(
+    types: &mut [TypeSize],
+    graph: &HeapGraph,
+    by_layout: &[u64],
+    cancel: &CancellationToken,
+) -> Result<SizeSource, HeapError> {
+    let slots = types.len();
+    let mut instances = vec![0u32; slots];
+    let mut smallest_gap = vec![u64::MAX; slots];
+    let mut ids = graph.ids.ids();
+    let mut current = ids.next();
+    let mut object = 0usize;
+    while let Some(id) = current {
+        if (object as u64).is_multiple_of(CHECK_EVERY) && cancel.is_cancelled() {
+            return Err(HeapError::Cancelled);
+        }
+        let next = ids.next();
+        let slot = graph.types[object] as usize;
+        if matches!(types.get(slot), Some(TypeSize::Fixed(_))) {
+            instances[slot] = instances[slot].saturating_add(1);
+            if let Some(next) = next.filter(|&n| n > id) {
+                smallest_gap[slot] = smallest_gap[slot].min(next - id);
+            }
+        }
+        current = next;
+        object += 1;
+    }
+
+    let (mut measurable, mut by_gap) = (0usize, 0usize);
+    for (slot, ty) in types.iter_mut().enumerate() {
+        let TypeSize::Fixed(size) = ty else { continue };
+        if instances[slot] < 2 {
+            continue;
+        }
+        measurable += 1;
+        let gap = smallest_gap[slot];
+        if (by_layout[slot]..=by_layout[slot] + GAP_SLACK).contains(&gap) {
+            *size = gap;
+            by_gap += 1;
+        }
+    }
+    let trusted = measurable > 0 && by_gap * 10 >= measurable * GAP_TRUST_TENTHS;
+    Ok(if trusted { SizeSource::AddressGaps } else { SizeSource::Layout })
+}
+
+#[cfg(test)]
+mod tests;
@@ -0,0 +1,113 @@
+//! The object layout rules of the JVM that wrote a dump.
+
+use std::collections::HashMap;
+
+use crate::hprof::BasicType;
+
+/// Object layout of the JVM that wrote the dump.
+#[derive(Clone, Copy, Debug, PartialEq)]
+pub struct VmLayout {
+    pub header: u8,
+    /// Bytes of a reference: 4 with compressed oops.
+    pub ref_size: u8,
+    /// Offset of the length field of an array.
+    pub length_offset: u8,
+    /// JDK 21 and older put array elements at the next 8-byte boundary after the length, later
+    /// JDKs at the next boundary of the element size.
+    pub legacy_array_base: bool,
+    pub alignment: u16,
+    /// The JDK the flags came from; `None` when nothing is known about the JVM.
+    pub java_major: Option<u32>,
+}
+
+impl VmLayout {
+    pub const DEFAULT: VmLayout = VmLayout {
+        header: 12,
+        ref_size: 4,
+        length_offset: 12,
+        legacy_array_base: false,
+        alignment: 8,
+        java_major: None,
+    };
+
+    /// `flags` is the output of `VM.flags`, which lists the flags set on this run. Compressed oops
+    /// are off by default and only switched on by ergonomics, so `-XX:+UseCompressedOops` is
+    /// printed exactly when references take 4 bytes; a heap too big for them prints no such flag.
+    /// Before JDK 15 compressed class pointers follow the same rule; with `java_major: None` (JDK
+    /// unknown) they follow the JDK 15+ rule and the array base that of the newest JDKs. Flags
+    /// without any `-XX:` option (an external dump) give [`Self::DEFAULT`] with the array base of
+    /// `java_major` and an unknown JDK, since the reference size is a guess.
+    /// An `ObjectAlignmentInBytes` that is not a power of two in `8..=256` is ignored.
+    pub fn from_vm_flags(flags: &str, java_major: Option<u32>) -> Self {
+        let legacy_array_base = java_major.map_or(Self::DEFAULT.legacy_array_base, |major| major <= 21);
+        let flags = parse_flags(flags);
+        if flags.is_empty() {
+            return VmLayout { legacy_array_base, ..Self::DEFAULT };
+        }
+        let on = |name: &str| flags.get(name) == Some(&"true");
+        let compressed_classes = if java_major.is_none_or(|major| major >= 15) {
+            flags.get("UseCompressedClassPointers") != Some(&"false")
+        } else {
+            on("UseCompressedClassPointers")
+        };
+        let (header, length_offset) = if on("UseCompactObjectHeaders") {
+            (8, 8)
+        } else if compressed_classes {
+            (12, 12)
+        } else {
+            (16, 16)
+        };
+        let alignment = flags
+            .get("ObjectAlignmentInBytes")
+            .and_then(|v| v.parse::<u16>().ok())
+            .filter(|a| (8..=256).contains(a) && a.is_power_of_two())
+            .unwrap_or(Self::DEFAULT.alignment);
+        VmLayout {
+            header,
+            ref_size: if on("UseCompressedOops") { 4 } else { 8 },
+            length_offset,
+            legacy_array_base,
+            alignment,
+            java_major,
+        }
+    }
+
+    /// Size of an instance whose fields (its class and every superclass) take `field_bytes`.
+    pub fn instance_size(&self, field_bytes: u64) -> u64 {
+        let smallest = if self.header == 8 { 8 } else { 16 };
+        self.align(u64::from(self.header) + field_bytes).max(smallest)
+    }
+
+    pub fn array_size(&self, ty: BasicType, len: u64) -> u64 {
+        let element = ty.heap_size(self.ref_size);
+        let base_alignment = if self.legacy_array_base { 8 } else { element };
+        let base = align_to(u64::from(self.length_offset) + 4, base_alignment);
+        self.align(base + element * len)
+    }
+
+    /// `value` rounded up to the object alignment.
+    pub(super) fn align(&self, value: u64) -> u64 {
+        align_to(value, u64::from(self.alignment))
+    }
+}
+
+fn align_to(value: u64, to: u64) -> u64 {
+    value.div_ceil(to.max(1)) * to.max(1)
+}
+
+/// `-XX:+Name` / `-XX:-Name` / `-XX:Name=value` tokens by name; booleans become `"true"` / `"false"`.
+/// A flag given twice keeps its last value, as in the JVM.
+fn parse_flags(flags: &str) -> HashMap<&str, &str> {
+    let mut parsed = HashMap::new();
+    for token in flags.split_whitespace() {
+        let Some(body) = token.strip_prefix("-XX:") else { continue };
+        if let Some(name) = body.strip_prefix('+') {
+            parsed.insert(name, "true");
+        } else if let Some(name) = body.strip_prefix('-') {
+            parsed.insert(name, "false");
+        } else if let Some((name, value)) = body.split_once('=') {
+            parsed.insert(name, value);
+        }
+    }
+    parsed
+}
@@ -0,0 +1,119 @@
+//! Sizes of class objects (mirrors): the `java.lang.Class` instance plus the class's statics, plus
+//! the fields HotSpot injects into every mirror and leaves out of the class dump.
+
+use ide_core::CancellationToken;
+
+use super::{HistogramEntry, VmLayout};
+use crate::error::HeapError;
+use crate::graph::HeapGraph;
+use crate::progress::CHECK_EVERY;
+
+/// Largest injected byte count (per mirror, a multiple of 4) the histogram fit tries.
+const MAX_INJECTED: u64 = 128;
+/// How far, in percent of the histogram's total, the best fit may be off before the row is taken
+/// for something else than the mirrors of this dump.
+const MAX_FIT_ERROR_PERCENT: u128 = 5;
+
+/// Bytes HotSpot injects into every mirror (`klass`, `array_klass`, `oop_size`,
+/// `static_oop_field_count`, and oops such as `protection_domain`) without listing them in the class
+/// dump, as measured by comparing the dump with `GC.class_histogram` on JDK 8, 11, 21, 23 and 25,
+/// with and without compressed oops. Each X is the best fit in steps of 4; the real value is
+/// within a few bytes (statics padding). `None` for a reference size the table does not cover.
+pub(super) fn injected_mirror_bytes(java_major: u32, ref_size: u8) -> Option<u64> {
+    match (ref_size, java_major) {
+        // 8, 11, 21 and 23 measure 36; 25 is the first JDK that shows 28.
+        (4, ..=24) => Some(36),
+        (4, 25..) => Some(28),
+        // 8, 11 and 21 measure 44; 23 is the first to show 40 and 25 the first to show 32.
+        (8, ..=22) => Some(44),
+        (8, 23..=24) => Some(40),
+        (8, 25..) => Some(32),
+        _ => None,
+    }
+}
+
+/// Used when the JVM is unknown (a dump without `VM.flags`): the midpoint of the measured values
+/// with 4-byte references, 36 and 28.
+const UNKNOWN_JVM_INJECTED: u64 = 32;
+
+/// The injected bytes per mirror the layout implies, without looking at a histogram.
+pub(super) fn injected_by_table(layout: VmLayout) -> u64 {
+    layout.java_major.and_then(|major| injected_mirror_bytes(major, layout.ref_size)).unwrap_or(UNKNOWN_JVM_INJECTED)
+}
+
+pub(super) struct Mirrors {
+    /// `(node, size before alignment)` of every class dump that is an object of the graph, by node.
+    dumped: Vec<(u32, u64)>,
+}
+
+impl Mirrors {
+    /// `instance` is the layout size of `java.lang.Class`, the base of every mirror.
+    pub(super) fn collect(graph: &HeapGraph, instance: u64, layout: VmLayout) -> Self {
+        let mut dumped: Vec<(u32, u64)> = graph
+            .classes
+            .iter()
+            .filter(|class| class.id != 0)
+            .filter_map(|class| {
+                let node = graph.ids.rank(class.id)?;
+                let references = class.statics.len() as u64 * u64::from(layout.ref_size);
+                Some((node, instance + class.static_bytes + references))
+            })
+            .collect();
+        dumped.sort_unstable_by_key(|&(node, _)| node);
+        Self { dumped }
+    }
+
+    /// `(node, size)` of each class object when HotSpot adds `injected` bytes to every mirror.
+    pub(super) fn sizes(&self, layout: VmLayout, injected: u64) -> Vec<(u32, u64)> {
+        self.dumped.iter().map(|&(node, bytes)| (node, layout.align(bytes + injected))).collect()
+    }
+
+    /// The injected bytes per mirror (a multiple of 4, at most 128) that make the mirrors of this
+    /// dump add up to `class_row`'s share of the histogram, or `None` when no value gets within 5%:
+    /// a histogram of other mirrors than these (a different JVM stop) must not skew the sizes.
+    ///
+    /// The fit compares averages, since the histogram also counts mirrors the dump has no class
+    /// dump for (primitive types, classes only archived by CDS). Every mirror still gets the same
+    /// extra bytes, never the average size, because statics make mirror sizes differ.
+    pub(super) fn fit_injected(
+        &self,
+        graph: &HeapGraph,
+        layout: VmLayout,
+        instance: u64,
+        class_row: &HistogramEntry,
+        cancel: &CancellationToken,
+    ) -> Result<Option<u64>, HeapError> {
+        if class_row.instances == 0 {
+            return Ok(None);
+        }
+        // Mirrors without a class dump (primitive types) have no statics.
+        let class_typed = count_slot(graph, graph.class_slot, cancel)?;
+        let bare = class_typed.saturating_sub(self.dumped.len() as u64);
+        let mirrors = self.dumped.len() as u64 + bare;
+        if mirrors == 0 {
+            return Ok(None);
+        }
+        let target = u128::from(class_row.bytes) * u128::from(mirrors) / u128::from(class_row.instances);
+        let total = |injected: u64| -> u128 {
+            let dumped: u128 = self.dumped.iter().map(|&(_, bytes)| u128::from(layout.align(bytes + injected))).sum();
+            dumped + u128::from(bare) * u128::from(layout.align(instance + injected))
+        };
+        let (best, error) = (0..=MAX_INJECTED)
+            .step_by(4)
+            .map(|injected| (injected, total(injected).abs_diff(target)))
+            .min_by_key(|&(injected, error)| (error, injected))
+            .unwrap_or((0, u128::MAX));
+        Ok((error * 100 <= target * MAX_FIT_ERROR_PERCENT).then_some(best))
+    }
+}
+
+fn count_slot(graph: &HeapGraph, slot: u32, cancel: &CancellationToken) -> Result<u64, HeapError> {
+    let mut count = 0;
+    for chunk in graph.types.chunks(CHECK_EVERY as usize) {
+        if cancel.is_cancelled() {
+            return Err(HeapError::Cancelled);
+        }
+        count += chunk.iter().filter(|&&ty| ty == slot).count() as u64;
+    }
+    Ok(count)
+}
@@ -0,0 +1,593 @@
+use super::*;
+use crate::column::Store;
+use crate::graph::build_graph;
+use crate::progress::HeapPhase;
+use crate::testing::{HprofWriter, MiniHeap, sample};
+
+const ROOT: Option<&str> = Some("java.lang.Object");
+
+fn no_progress(_: HeapPhase, _: u64, _: u64) -> Result<(), HeapError> {
+    Ok(())
+}
+
+fn graph_of(heap: &MiniHeap) -> HeapGraph {
+    build_graph(&heap.bytes(), &Store::Ram, &no_progress, &CancellationToken::new()).unwrap()
+}
+
+fn model(g: &HeapGraph, layout: VmLayout, histogram: Option<&[HistogramEntry]>) -> ShallowModel {
+    ShallowModel::new(g, layout, histogram, &CancellationToken::new()).unwrap()
+}
+
+fn size_at(g: &HeapGraph, m: &ShallowModel, addr: u64) -> u64 {
+    m.size_of(g, g.ids.rank(addr).unwrap_or_else(|| panic!("{addr:#x} is not in the graph")))
+}
+
+fn slot_at(g: &HeapGraph, addr: u64) -> u32 {
+    g.types[g.ids.rank(addr).unwrap() as usize]
+}
+
+fn entry(name: &str, instances: u64, bytes: u64) -> HistogramEntry {
+    HistogramEntry { name: name.to_owned(), instances, bytes }
+}
+
+fn flags(flags: &str, java_major: u32) -> VmLayout {
+    VmLayout::from_vm_flags(flags, Some(java_major))
+}
+
+const SHAPES: [&str; 9] = ["A", "B", "C", "D", "E", "F", "G", "H", "Node"];
+
+/// One instance of each shape, 0x100 apart so no address gap qualifies.
+fn shapes() -> MiniHeap {
+    use BasicType::{Byte, Int, Long, Object, Short};
+    let mut heap = MiniHeap::new();
+    heap.class("A", ROOT, &[("f", Byte)])
+        .class("B", ROOT, &[("f", Long)])
+        .class("C", ROOT, &[("i", Int), ("l", Long), ("b", Byte)])
+        .class("D", Some("C"), &[("s", Short), ("o", Object)])
+        .class("E", ROOT, &[("a", Object), ("b", Object), ("c", Object)])
+        .class("F", Some("A"), &[("g", Byte)])
+        .class("G", ROOT, &[])
+        .class("H", Some("B"), &[("i", Int)])
+        .class("Node", ROOT, &[("l", Long), ("a", Object), ("b", Object)]);
+    for (i, name) in SHAPES.iter().enumerate() {
+        heap.object(0x1000 + i as u64 * 0x100, name, &[]);
+    }
+    heap
+}
+
+fn shape_sizes(layout: VmLayout) -> Vec<u64> {
+    let g = graph_of(&shapes());
+    let m = model(&g, layout, None);
+    (0..SHAPES.len() as u64).map(|i| size_at(&g, &m, 0x1000 + i * 0x100)).collect()
+}
+
+// `jcmd <pid> VM.flags` of `-Xmx1g` and `-Xmx40g` runs (the flags that matter here).
+const J8_11_1G: &str = "-XX:MaxHeapSize=1073741824 -XX:+UseCompressedClassPointers -XX:+UseCompressedOops";
+const J8_11_40G: &str = "-XX:MaxHeapSize=42949672960";
+const J21_25_1G: &str = "-XX:MaxHeapSize=1073741824 -XX:SoftMaxHeapSize=1073741824 -XX:+UseCompressedOops";
+const J21_25_40G: &str = "-XX:MaxHeapSize=42949672960 -XX:SoftMaxHeapSize=42949672960";
+/// `-Xmx40g -XX:+UseCompressedOops`: the JVM warns and turns them off.
+const J21_40G_OFF: &str = "-XX:MaxHeapSize=42949672960 -XX:SoftMaxHeapSize=42949672960 -XX:-UseCompressedOops";
+const J25_COMPACT: &str = "-XX:MaxHeapSize=1073741824 -XX:+UseCompressedOops -XX:+UseCompactObjectHeaders";
+
+#[test]
+fn layout_from_flags() {
+    // The layout of a JVM of `major` with default flags otherwise.
+    let jvm = |major: u32, layout: VmLayout| VmLayout { java_major: Some(major), ..layout };
+    let legacy = VmLayout { legacy_array_base: true, ..VmLayout::DEFAULT };
+    assert_eq!(flags(J8_11_1G, 8), jvm(8, legacy));
+    assert_eq!(flags(J8_11_1G, 11), jvm(11, legacy));
+    assert_eq!(flags(J21_25_1G, 21), jvm(21, legacy));
+    assert_eq!(flags(J21_25_1G, 25), jvm(25, VmLayout::DEFAULT));
+    assert_eq!(flags(J25_COMPACT, 25), jvm(25, VmLayout { header: 8, length_offset: 8, ..VmLayout::DEFAULT }));
+    assert_eq!(flags(&format!("{J21_25_1G} -XX:+UseG1GC"), 21), jvm(21, legacy));
+    assert_eq!(
+        flags(&format!("{J21_25_1G} -XX:ObjectAlignmentInBytes=16"), 21),
+        jvm(21, VmLayout { alignment: 16, ..legacy })
+    );
+}
+
+#[test]
+fn heaps_too_big_for_compressed_oops_print_no_flag() {
+    let jvm = |major: u32, layout: VmLayout| VmLayout { java_major: Some(major), ..layout };
+    let wide_legacy =
+        VmLayout { header: 16, ref_size: 8, length_offset: 16, legacy_array_base: true, ..VmLayout::DEFAULT };
+    assert_eq!(flags(J8_11_40G, 8), jvm(8, wide_legacy));
+    assert_eq!(flags(J8_11_40G, 11), jvm(11, wide_legacy));
+    // From JDK 15 compressed class pointers stay on without compressed oops.
+    let wide = VmLayout { ref_size: 8, ..VmLayout::DEFAULT };
+    assert_eq!(flags(J21_25_40G, 21), jvm(21, VmLayout { legacy_array_base: true, ..wide }));
+    assert_eq!(flags(J21_25_40G, 25), jvm(25, wide));
+    assert_eq!(flags(J21_40G_OFF, 21), flags(J21_25_40G, 21));
+}
+
+#[test]
+fn flags_of_an_unknown_jdk_follow_the_jdk_15_class_pointer_rule() {
+    let unknown = |f: &str| VmLayout::from_vm_flags(f, None);
+    assert_eq!(unknown(J21_25_1G), VmLayout::DEFAULT);
+    assert_eq!(unknown(J8_11_40G), VmLayout { ref_size: 8, ..VmLayout::DEFAULT });
+    let no_ccp = unknown("-XX:+UseCompressedOops -XX:-UseCompressedClassPointers");
+    assert_eq!((no_ccp.header, no_ccp.length_offset, no_ccp.java_major), (16, 16, None));
+    assert_eq!(unknown(J25_COMPACT).header, 8);
+    // The mirror table has no row for an unknown JDK.
+    let (g, addrs) = mirror_heap(&MIRROR_STATICS);
+    assert_eq!(mirror_sizes(&g, &addrs, unknown(J21_25_1G), None), expected_mirrors(&MIRROR_STATICS, 32));
+}
+
+#[test]
+fn layout_flag_edge_cases() {
+    let legacy = VmLayout { legacy_array_base: true, ..VmLayout::DEFAULT };
+    // No VM.flags (an external dump): the default layout, of an unknown JVM.
+    assert_eq!(flags("", 25), VmLayout::DEFAULT);
+    assert_eq!(flags("", 21), legacy);
+    assert_eq!(flags("-Xmx1g --add-opens=x -XX:Foo", 25), VmLayout::DEFAULT);
+    // Before JDK 15 compressed class pointers are on only when the flags say so.
+    assert_eq!(flags("-XX:+UseCompressedOops", 11).header, 16);
+    assert_eq!(flags("-XX:+UseCompressedOops -XX:+UseCompressedClassPointers", 11).header, 12);
+    assert_eq!(flags("-XX:+UseCompressedOops -XX:-UseCompressedClassPointers", 11).header, 16);
+    assert_eq!(flags("-XX:+UseCompressedOops", 15).header, 12);
+    let no_ccp = flags("-XX:+UseCompressedOops -XX:-UseCompressedClassPointers", 21);
+    assert_eq!((no_ccp.header, no_ccp.length_offset, no_ccp.ref_size), (16, 16, 4));
+    // Compact headers win over the class pointer flag; the last mention of a flag wins.
+    assert_eq!(flags("-XX:-UseCompressedClassPointers -XX:+UseCompactObjectHeaders", 25).header, 8);
+    assert_eq!(flags("-XX:-UseCompressedOops -XX:+UseCompressedOops", 21).ref_size, 4);
+    assert_eq!(flags("-XX:+UseCompressedOops -XX:-UseCompressedOops", 21).ref_size, 8);
+}
+
+#[test]
+fn object_alignment_accepts_powers_of_two_from_8_to_256() {
+    for good in [8u16, 16, 32, 64, 128, 256] {
+        assert_eq!(flags(&format!("-XX:ObjectAlignmentInBytes={good}"), 25).alignment, good);
+    }
+    for bad in ["0", "4", "7", "12", "255", "512", "abc", "", "999999999999"] {
+        assert_eq!(flags(&format!("-XX:ObjectAlignmentInBytes={bad}"), 25).alignment, 8, "{bad:?}");
+    }
+    let wide = flags("-XX:+UseCompressedOops -XX:ObjectAlignmentInBytes=256", 21);
+    assert_eq!(wide.instance_size(1), 256);
+    assert_eq!(wide.instance_size(300), 512);
+    assert_eq!(wide.array_size(BasicType::Byte, 1), 256);
+}
+
+#[test]
+fn instance_sizes_match_the_jvm() {
+    let at = |sizes: &[u64], name: &str| sizes[SHAPES.iter().position(|n| *n == name).unwrap()];
+
+    let coops = shape_sizes(flags(J21_25_1G, 21));
+    for (name, size) in
+        [("A", 16), ("B", 24), ("C", 32), ("D", 32), ("E", 24), ("F", 16), ("G", 16), ("H", 24), ("Node", 32)]
+    {
+        assert_eq!(at(&coops, name), size, "{name} with compressed oops");
+    }
+    let wide = shape_sizes(flags(J21_25_40G, 21));
+    for (name, size) in [("D", 40), ("E", 40), ("Node", 40)] {
+        assert_eq!(at(&wide, name), size, "{name} without compressed oops");
+    }
+    let compact = shape_sizes(flags(J25_COMPACT, 25));
+    for (name, size) in [("G", 8), ("B", 16), ("C", 24), ("D", 32), ("Node", 24)] {
+        assert_eq!(at(&compact, name), size, "{name} with compact headers");
+    }
+}
+
+#[test]
+fn instance_size_bounds() {
+    assert_eq!(VmLayout::DEFAULT.instance_size(0), 16);
+    assert_eq!(flags("-XX:+UseCompactObjectHeaders", 25).instance_size(0), 8);
+    assert_eq!(flags("-XX:ObjectAlignmentInBytes=16", 21).instance_size(1), 16);
+    assert_eq!(flags("-XX:ObjectAlignmentInBytes=16", 21).instance_size(8), 32);
+}
+
+#[test]
+fn array_sizes() {
+    let d = VmLayout::DEFAULT;
+    assert_eq!(d.array_size(BasicType::Long, 2), 32);
+    assert_eq!(d.array_size(BasicType::Byte, 5), 24);
+    assert_eq!(d.array_size(BasicType::Object, 3), 32);
+    let compact = flags("-XX:+UseCompactObjectHeaders", 25);
+    assert_eq!(compact.array_size(BasicType::Byte, 5), 24);
+    assert_eq!(compact.array_size(BasicType::Int, 1), 16);
+    assert_eq!(compact.array_size(BasicType::Long, 1), 24);
+    assert_eq!(flags("-XX:-UseCompressedClassPointers", 21).array_size(BasicType::Byte, 1), 32);
+    assert_eq!(flags("-XX:-UseCompressedClassPointers", 25).array_size(BasicType::Byte, 1), 24);
+    assert_eq!(flags("-XX:-UseCompressedClassPointers", 25).array_size(BasicType::Long, 1), 32);
+    // Empty arrays and the largest length fit.
+    assert_eq!(d.array_size(BasicType::Int, 0), 16);
+    assert_eq!(d.array_size(BasicType::Long, u64::from(u32::MAX)), 16 + 8 * u64::from(u32::MAX));
+}
+
+#[test]
+fn arrays_in_the_graph_follow_the_layout() {
+    let g = graph_of(&sample());
+    let m = model(&g, VmLayout::DEFAULT, None);
+    assert_eq!(size_at(&g, &m, 0x1400), 32, "long[2]");
+    assert_eq!(size_at(&g, &m, 0x1500), 32, "Object[3]");
+    assert_eq!(size_at(&g, &m, 0x1100), 24, "Node");
+    let wide = model(&g, flags("-XX:-UseCompressedOops", 21), None);
+    assert_eq!(size_at(&g, &wide, 0x1500), 40, "Object[3] with 8-byte references");
+    assert_eq!(m.size_of(&g, g.root), 0, "the super-root has no size");
+    assert_eq!(m.source, SizeSource::Layout);
+}
+
+#[test]
+fn histogram_wins_for_instances() {
+    use BasicType::Int;
+    let fields: Vec<_> = (0..23).map(|i| (format!("f{i}"), Int)).collect();
+    let fields: Vec<(&str, BasicType)> = fields.iter().map(|(n, t)| (n.as_str(), *t)).collect();
+    let mut heap = MiniHeap::new();
+    heap.class("java.lang.Thread", ROOT, &fields)
+        .class("Plain", ROOT, &[("f", Int)])
+        .object(0x1000, "java.lang.Thread", &[])
+        .object(0x1100, "Plain", &[]);
+    let g = graph_of(&heap);
+
+    let without = model(&g, VmLayout::DEFAULT, None);
+    assert_eq!(size_at(&g, &without, 0x1000), 104);
+
+    let histogram = [entry("java.lang.Thread", 13, 1560), entry("Unrelated", 2, 64)];
+    let with = model(&g, VmLayout::DEFAULT, Some(&histogram));
+    assert_eq!(with.source, SizeSource::Jvm);
+    assert_eq!(size_at(&g, &with, 0x1000), 120);
+    assert_eq!(size_at(&g, &with, 0x1100), 16, "no row: layout");
+}
+
+#[test]
+fn histogram_rows_that_do_not_divide_or_are_empty_fall_back_to_layout() {
+    let mut heap = MiniHeap::new();
+    heap.class("Plain", ROOT, &[("f", BasicType::Int)]).object(0x1000, "Plain", &[]);
+    let g = graph_of(&heap);
+    for row in [entry("Plain", 3, 100), entry("Plain", 0, 0), entry("Plain", 0, 48), entry("Plain", 2, 0)] {
+        let m = model(&g, VmLayout::DEFAULT, Some(std::slice::from_ref(&row)));
+        assert_eq!(m.source, SizeSource::Jvm);
+        assert_eq!(size_at(&g, &m, 0x1000), 16, "{row:?}");
+    }
+    // The same name twice in the histogram cannot be told apart either.
+    let twice = [entry("Plain", 1, 48), entry("Plain", 1, 64)];
+    assert_eq!(size_at(&g, &model(&g, VmLayout::DEFAULT, Some(&twice)), 0x1000), 16);
+}
+
+#[test]
+fn histogram_matches_arrays_by_display_name_but_never_sizes_them() {
+    let g = graph_of(&sample());
+    let histogram = [entry("java.lang.Object[]", 1, 4096), entry("long[]", 1, 4096), entry("Node", 4, 160)];
+    let m = model(&g, VmLayout::DEFAULT, Some(&histogram));
+    assert_eq!(size_at(&g, &m, 0x1500), 32);
+    assert_eq!(size_at(&g, &m, 0x1400), 32);
+    assert_eq!(size_at(&g, &m, 0x1100), 40, "Node from the histogram");
+}
+
+#[test]
+fn a_name_shared_by_several_classes_never_takes_a_histogram_size() {
+    use BasicType::{Int, Long};
+    let mut heap = MiniHeap::new();
+    heap.class("dup.Foo", ROOT, &[("a", Int)])
+        .object(0x1000, "dup.Foo", &[])
+        .class("dup.Foo", ROOT, &[("a", Long), ("b", Long)])
+        .object(0x1100, "dup.Foo", &[])
+        .class("Solo", ROOT, &[("a", Int)])
+        .object(0x1200, "Solo", &[]);
+    let g = graph_of(&heap);
+    let histogram = [entry("dup.Foo", 2, 80), entry("Solo", 1, 48)];
+    let m = model(&g, VmLayout::DEFAULT, Some(&histogram));
+
+    assert_eq!(size_at(&g, &m, 0x1000), 16, "first dup.Foo uses its layout");
+    assert_eq!(size_at(&g, &m, 0x1100), 32, "second dup.Foo uses its layout");
+    assert_eq!(size_at(&g, &m, 0x1200), 48, "Solo still takes its histogram size");
+    let (first, second, solo) = (slot_at(&g, 0x1000), slot_at(&g, 0x1100), slot_at(&g, 0x1200));
+    assert_ne!(first, second);
+    assert!(m.is_ambiguous(first) && m.is_ambiguous(second));
+    assert!(!m.is_ambiguous(solo));
+    let ambiguous: Vec<_> = (0..g.classes.len() as u32).filter(|&s| m.is_ambiguous(s)).collect();
+    assert_eq!(ambiguous.len(), 2, "no other class is flagged");
+    assert!(!m.is_ambiguous(u32::MAX), "slots past the classes are never ambiguous");
+}
+
+#[test]
+fn ambiguity_covers_array_classes_and_ignores_the_source() {
+    let mut heap = MiniHeap::new();
+    heap.class("[Lx.Y;", ROOT, &[]).class("[Lx/Y;", ROOT, &[]).class("Solo", ROOT, &[]);
+    let g = graph_of(&heap);
+    let m = model(&g, VmLayout::DEFAULT, None);
+    let flagged: Vec<_> =
+        g.classes.iter().enumerate().filter(|(i, _)| m.is_ambiguous(*i as u32)).map(|(_, c)| c.name.as_str()).collect();
+    assert_eq!(flagged, ["[Lx.Y;", "[Lx.Y;"]);
+}
+
+/// A dump with three classes: `java.lang.Class` (three reference fields), `Statics` (two reference
+/// statics, one null) and `Plain`; `at` is where each class object lives.
+fn class_dump() -> Vec<u8> {
+    use BasicType::Object;
+    let mut w = HprofWriter::new();
+    w.string(1, "java/lang/Class").load_class(0x100, 1).class(
+        0x100,
+        0,
+        &[(10, Object), (11, Object), (12, Object)],
+        &[],
+    );
+    w.string(2, "Statics").load_class(0x200, 2).class(0x200, 0, &[], &[(13, 0x300), (13, 0)]);
+    w.string(3, "Plain").load_class(0x300, 3).class(0x300, 0, &[], &[]);
+    w.finish()
+}
+
+#[test]
+fn class_objects_use_the_layout_even_when_the_histogram_names_them() {
+    let g = build_graph(&class_dump(), &Store::Ram, &no_progress, &CancellationToken::new()).unwrap();
+    let histogram = [entry("java.lang.Class", 3, 3000)];
+    let by_histogram = model(&g, VmLayout::DEFAULT, Some(&histogram));
+    let by_layout = model(&g, VmLayout::DEFAULT, None);
+    assert_eq!(by_histogram.source, SizeSource::Jvm);
+    for m in [&by_histogram, &by_layout] {
+        // java.lang.Class has 12 bytes of fields: 24; Statics adds two references; every mirror
+        // gets the 32 bytes assumed for an unknown JVM (the histogram row does not fit).
+        assert_eq!(size_at(&g, m, 0x100), 56, "java.lang.Class itself");
+        assert_eq!(size_at(&g, m, 0x200), 64, "two reference statics");
+        assert_eq!(size_at(&g, m, 0x300), 56, "no statics");
+    }
+    // 8-byte references: 40 for java.lang.Class, 16 for the statics, 44 injected (JDK 21), aligned.
+    let wide = model(&g, flags("-XX:-UseCompressedOops", 21), None);
+    assert_eq!(size_at(&g, &wide, 0x200), 104);
+}
+
+#[test]
+fn primitive_statics_add_to_the_class_object() {
+    let mut g = build_graph(&class_dump(), &Store::Ram, &no_progress, &CancellationToken::new()).unwrap();
+    let statics = g.classes.iter().position(|c| c.name == "Statics").unwrap();
+    g.classes[statics].static_bytes = 12;
+    let m = model(&g, VmLayout::DEFAULT, None);
+    assert_eq!(size_at(&g, &m, 0x200), 80, "24 + 12 + 2 × 4 + 32 injected = 76, aligned");
+}
+
+#[test]
+fn a_dump_without_java_lang_class_sizes_class_objects_as_empty_mirrors() {
+    let mut w = HprofWriter::new();
+    w.string(1, "Statics").load_class(0x200, 1).class(0x200, 0, &[], &[(2, 0), (2, 0), (2, 0)]);
+    let g = build_graph(&w.finish(), &Store::Ram, &no_progress, &CancellationToken::new()).unwrap();
+    let m = model(&g, VmLayout::DEFAULT, None);
+    assert_eq!(size_at(&g, &m, 0x200), 64, "16 + 3 × 4 + 32 injected = 60, aligned");
+}
+
+fn one_class_two_instances(stride: u64) -> (HeapGraph, ShallowModel) {
+    let mut heap = MiniHeap::new();
+    heap.class("A", ROOT, &[("f", BasicType::Byte)]).object(0x1000, "A", &[]).object(0x1000 + stride, "A", &[]);
+    let g = graph_of(&heap);
+    let m = model(&g, VmLayout::DEFAULT, None);
+    (g, m)
+}
+
+#[test]
+fn address_gaps_for_external_dumps() {
+    let mut heap = MiniHeap::new();
+    heap.class("A", ROOT, &[("f", BasicType::Byte)])
+        .class("Wide", ROOT, &[("f", BasicType::Long)])
+        .class("Module", ROOT, &[("f", BasicType::Long)])
+        .object(0x1000, "A", &[])
+        .object(0x1018, "A", &[])
+        .object(0x1030, "A", &[])
+        .object(0x1048, "Module", &[])
+        .object(0x2000, "Wide", &[])
+        .object(0x3000, "Wide", &[]);
+    let g = graph_of(&heap);
+    let m = model(&g, VmLayout::DEFAULT, None);
+    assert_eq!(size_at(&g, &m, 0x1000), 24, "layout says 16, the smallest gap between As is 24");
+    assert_eq!(size_at(&g, &m, 0x1030), 24, "every A takes the type's size");
+    assert_eq!(size_at(&g, &m, 0x1048), 24, "a single instance has no gap to trust: layout");
+    assert_eq!(size_at(&g, &m, 0x2000), 24, "a gap beyond layout + 64 is not an object size: layout");
+    assert_eq!(m.source, SizeSource::Layout, "one of three types agrees");
+}
+
+#[test]
+fn address_gaps_are_taken_within_layout_and_layout_plus_64() {
+    for (stride, expected) in [(8, 16), (16, 16), (24, 24), (80, 80), (88, 16)] {
+        let (g, m) = one_class_two_instances(stride);
+        assert_eq!(size_at(&g, &m, 0x1000), expected, "stride {stride}");
+        assert_eq!(
+            m.source,
+            if expected == stride && stride >= 16 { SizeSource::AddressGaps } else { SizeSource::Layout }
+        );
+    }
+}
+
+/// `used` types with two instances 16 bytes apart (the layout size), `far` types with two
+/// instances 0x1000 apart (a gap that is no object size) and `single` types with one instance.
+fn types_by_gap_use(used: usize, far: usize, single: usize) -> SizeSource {
+    let mut heap = MiniHeap::new();
+    for i in 0..used + far + single {
+        let name = format!("T{i}");
+        heap.class(&name, ROOT, &[("f", BasicType::Byte)]);
+        let base = 0x10_0000 * (i as u64 + 1);
+        heap.object(base, &name, &[]);
+        if i < used {
+            heap.object(base + 16, &name, &[]);
+        } else if i < used + far {
+            heap.object(base + 0x1000, &name, &[]);
+        }
+    }
+    let g = graph_of(&heap);
+    model(&g, VmLayout::DEFAULT, None).source
+}
+
+#[test]
+fn address_gap_source_needs_ninety_percent_of_the_types_that_have_a_gap() {
+    assert_eq!(types_by_gap_use(10, 0, 0), SizeSource::AddressGaps);
+    assert_eq!(types_by_gap_use(9, 1, 0), SizeSource::AddressGaps);
+    assert_eq!(types_by_gap_use(8, 2, 0), SizeSource::Layout);
+    // Types with one instance have no gap: they count neither for nor against.
+    assert_eq!(types_by_gap_use(9, 1, 5), SizeSource::AddressGaps);
+    assert_eq!(types_by_gap_use(8, 2, 5), SizeSource::Layout);
+    assert_eq!(types_by_gap_use(10, 0, 400), SizeSource::AddressGaps);
+    assert_eq!(types_by_gap_use(0, 0, 3), SizeSource::Layout, "no type has a gap");
+    assert_eq!(types_by_gap_use(0, 2, 0), SizeSource::Layout);
+    assert_eq!(types_by_gap_use(0, 0, 0), SizeSource::Layout, "nothing to size");
+}
+
+/// A dump of `java.lang.Class` (three reference fields, so 24 bytes of layout) and one class per
+/// entry of `statics`: `(reference statics, primitive static bytes)`. Class `i` is at `0x1000 + 0x100 × i`.
+fn mirror_heap(statics: &[(usize, u64)]) -> (HeapGraph, Vec<u64>) {
+    use BasicType::Object;
+    let mut w = HprofWriter::new();
+    w.string(1, "java/lang/Class").load_class(0x100, 1).class(
+        0x100,
+        0,
+        &[(10, Object), (11, Object), (12, Object)],
+        &[],
+    );
+    let mut addrs = Vec::new();
+    for (i, &(refs, _)) in statics.iter().enumerate() {
+        let (addr, name_id) = (0x1000 + 0x100 * i as u64, 100 + i as u64);
+        w.string(name_id, &format!("C{i}")).load_class(addr, name_id).class(addr, 0, &[], &vec![(13, 0); refs]);
+        addrs.push(addr);
+    }
+    let mut g = build_graph(&w.finish(), &Store::Ram, &no_progress, &CancellationToken::new()).unwrap();
+    for (i, &(_, bytes)) in statics.iter().enumerate() {
+        let class = g.classes.iter().position(|c| c.name == format!("C{i}")).unwrap();
+        g.classes[class].static_bytes = bytes;
+    }
+    (g, addrs)
+}
+
+/// What HotSpot would make of those classes if it added `injected` bytes to every mirror.
+fn expected_mirrors(statics: &[(usize, u64)], injected: u64) -> Vec<u64> {
+    statics.iter().map(|&(refs, bytes)| (24 + bytes + 4 * refs as u64 + injected).next_multiple_of(8)).collect()
+}
+
+const MIRROR_STATICS: [(usize, u64); 8] = [(0, 0), (3, 0), (1, 12), (6, 8), (2, 0), (9, 24), (0, 4), (4, 1)];
+
+#[test]
+fn class_objects_get_the_injected_bytes_the_histogram_implies() {
+    let (g, addrs) = mirror_heap(&MIRROR_STATICS);
+    // java.lang.Class itself and the eight classes.
+    let mut sizes = expected_mirrors(&MIRROR_STATICS, 36);
+    let java_lang_class = 24 + 36;
+    let total = sizes.iter().sum::<u64>() + (java_lang_class as u64).next_multiple_of(8);
+    sizes.insert(0, (java_lang_class as u64).next_multiple_of(8));
+    let histogram = [entry("java.lang.Class", 9, total)];
+    let m = model(&g, VmLayout::DEFAULT, Some(&histogram));
+    assert_eq!(m.source, SizeSource::Jvm);
+    assert_eq!(size_at(&g, &m, 0x100), sizes[0]);
+    for (i, &addr) in addrs.iter().enumerate() {
+        assert_eq!(size_at(&g, &m, addr), sizes[i + 1], "class {i}");
+    }
+    let spread: Vec<_> = addrs.iter().map(|&a| size_at(&g, &m, a)).collect();
+    assert!(spread.iter().any(|&s| s != spread[0]), "statics still make the mirrors differ: {spread:?}");
+}
+
+#[test]
+fn injected_bytes_are_found_for_every_multiple_of_four() {
+    let (g, addrs) = mirror_heap(&MIRROR_STATICS);
+    for injected in (0..=128).step_by(4) {
+        let total =
+            expected_mirrors(&MIRROR_STATICS, injected).iter().sum::<u64>() + (24 + injected).next_multiple_of(8);
+        let histogram = [entry("java.lang.Class", 9, total)];
+        let m = model(&g, VmLayout::DEFAULT, Some(&histogram));
+        let got: Vec<_> = addrs.iter().map(|&a| size_at(&g, &m, a)).collect();
+        assert_eq!(got, expected_mirrors(&MIRROR_STATICS, injected), "injected {injected}");
+    }
+}
+
+#[test]
+fn the_fit_tolerates_mirrors_the_dump_has_no_class_for() {
+    let (g, addrs) = mirror_heap(&MIRROR_STATICS);
+    // The histogram counts the same average mirror 90 times more often (CDS-archived classes).
+    let total = expected_mirrors(&MIRROR_STATICS, 28).iter().sum::<u64>() + (24u64 + 28).next_multiple_of(8);
+    let histogram = [entry("java.lang.Class", 9 * 91, total * 91)];
+    let m = model(&g, VmLayout::DEFAULT, Some(&histogram));
+    let got: Vec<_> = addrs.iter().map(|&a| size_at(&g, &m, a)).collect();
+    assert_eq!(got, expected_mirrors(&MIRROR_STATICS, 28));
+}
+
+fn mirror_sizes(g: &HeapGraph, addrs: &[u64], layout: VmLayout, histogram: Option<&[HistogramEntry]>) -> Vec<u64> {
+    let m = model(g, layout, histogram);
+    addrs.iter().map(|&a| size_at(g, &m, a)).collect()
+}
+
+#[test]
+fn a_histogram_row_that_cannot_describe_these_mirrors_falls_back_to_the_table() {
+    let (g, addrs) = mirror_heap(&MIRROR_STATICS);
+    let rows = [
+        entry("java.lang.Class", 9, 9 * 5000),
+        entry("java.lang.Class", 9, 9),
+        entry("java.lang.Class", 0, 0),
+        entry("Something.Else", 9, 9 * 100),
+    ];
+    for row in &rows {
+        let one = std::slice::from_ref(row);
+        // Unknown JVM: the documented 32; JDK 11 with 4-byte references: 36.
+        assert_eq!(
+            mirror_sizes(&g, &addrs, VmLayout::DEFAULT, Some(one)),
+            expected_mirrors(&MIRROR_STATICS, 32),
+            "{row:?}"
+        );
+        assert_eq!(
+            mirror_sizes(&g, &addrs, flags(J8_11_1G, 11), Some(one)),
+            expected_mirrors(&MIRROR_STATICS, 36),
+            "{row:?}"
+        );
+    }
+    let twice = [entry("java.lang.Class", 9, 9 * 60), entry("java.lang.Class", 9, 9 * 60)];
+    assert_eq!(mirror_sizes(&g, &addrs, flags(J8_11_1G, 11), Some(&twice)), expected_mirrors(&MIRROR_STATICS, 36));
+}
+
+#[test]
+fn an_accepted_fit_beats_the_table() {
+    let (g, addrs) = mirror_heap(&MIRROR_STATICS);
+    let total = expected_mirrors(&MIRROR_STATICS, 20).iter().sum::<u64>() + 48;
+    let histogram = [entry("java.lang.Class", 9, total)];
+    // JDK 11's table says 36; the histogram says 20.
+    assert_eq!(mirror_sizes(&g, &addrs, flags(J8_11_1G, 11), Some(&histogram)), expected_mirrors(&MIRROR_STATICS, 20));
+}
+
+#[test]
+fn injected_mirror_bytes_table() {
+    // (JDK, 4-byte references, 8-byte references): the measured cells, then the JDKs between.
+    for (major, narrow, wide) in
+        [(8, 36, 44), (11, 36, 44), (21, 36, 44), (22, 36, 44), (23, 36, 40), (24, 36, 40), (25, 28, 32), (26, 28, 32)]
+    {
+        assert_eq!(mirrors::injected_mirror_bytes(major, 4), Some(narrow), "JDK {major}, compressed oops");
+        assert_eq!(mirrors::injected_mirror_bytes(major, 8), Some(wide), "JDK {major}, 8-byte references");
+    }
+    assert_eq!(mirrors::injected_mirror_bytes(21, 2), None);
+}
+
+#[test]
+fn without_a_histogram_class_objects_get_the_injected_bytes_of_their_jvm() {
+    let (g, addrs) = mirror_heap(&MIRROR_STATICS);
+    // The class dump of the fixture has 4-byte references; the layout under test decides the table
+    // cell, so use layouts whose reference size matches it.
+    for (layout, injected) in [
+        (flags(J8_11_1G, 8), 36),
+        (flags(J8_11_1G, 11), 36),
+        (flags(J21_25_1G, 21), 36),
+        (flags(J21_25_1G, 23), 36),
+        (flags(J21_25_1G, 25), 28),
+        (flags(J25_COMPACT, 25), 28),
+    ] {
+        assert_eq!(mirror_sizes(&g, &addrs, layout, None), expected_mirrors(&MIRROR_STATICS, injected), "{layout:?}");
+    }
+}
+
+#[test]
+fn eight_byte_references_use_their_own_cells() {
+    let g = build_graph(&class_dump(), &Store::Ram, &no_progress, &CancellationToken::new()).unwrap();
+    // java.lang.Class = 12 + 3 × 8 = 36 → 40; Plain has no statics: 40 + injected, aligned.
+    for (major, injected) in [(8, 44), (21, 44), (23, 40), (25, 32)] {
+        let m = model(&g, flags(J21_25_40G, major), None);
+        assert_eq!(size_at(&g, &m, 0x300), (40u64 + injected).next_multiple_of(8), "JDK {major}");
+    }
+}
+
+#[test]
+fn an_unknown_jvm_uses_the_midpoint_of_the_compressed_oop_cells() {
+    let (g, addrs) = mirror_heap(&MIRROR_STATICS);
+    assert_eq!(mirror_sizes(&g, &addrs, VmLayout::DEFAULT, None), expected_mirrors(&MIRROR_STATICS, 32));
+    // Flags without any -XX: option say nothing about the JVM either.
+    assert_eq!(mirror_sizes(&g, &addrs, flags("", 21), None), expected_mirrors(&MIRROR_STATICS, 32));
+    assert_eq!(VmLayout::DEFAULT.java_major, None);
+}
+
+#[test]
+fn cancelled_token_stops_the_model() {
+    let g = graph_of(&sample());
+    let cancel = CancellationToken::new();
+    cancel.cancel();
+    assert!(matches!(ShallowModel::new(&g, VmLayout::DEFAULT, None, &cancel), Err(HeapError::Cancelled)));
+    let histogram = [entry("Node", 1, 24)];
+    assert!(matches!(ShallowModel::new(&g, VmLayout::DEFAULT, Some(&histogram), &cancel), Err(HeapError::Cancelled)));
+}
@@ -0,0 +1,66 @@
+//! Text of `java.lang.String` objects.
+
+use crate::hprof::{BasicType, HeapRecord};
+use crate::index::{HeapIndex, id_value, instance_fields};
+
+const STRING: &str = "java.lang.String";
+const LATIN1: u8 = 0;
+const UTF16: u8 = 1;
+
+/// The text of String `object`, cut to `max_chars` chars plus `…`. `None` for anything that is
+/// not a String, or one whose `value` / `coder` the dump does not hold as expected.
+///
+/// JDK 9+ keeps a `byte[]` and a `coder`; UTF-16 bytes are in the JVM's native order, which
+/// hprof copies as is, read here as little-endian (x86-64, AArch64; a big-endian JVM's text would
+/// come out garbled). JDK 8 keeps a `char[]`, whose elements hprof writes big-endian.
+pub(crate) fn string_preview(index: &HeapIndex, object: u32, max_chars: usize) -> Option<String> {
+    let slot = *index.types.get(object as usize)?;
+    if index.class_info.get(slot as usize)?.name != STRING {
+        return None;
+    }
+    let Some(HeapRecord::Instance { data, .. }) = index.record(object) else { return None };
+    let fields = instance_fields(index, slot, data);
+    let value = fields.iter().find(|f| f.name == "value" && f.ty == BasicType::Object)?;
+    let array = index.ids.rank(id_value(value.bytes).filter(|&id| id != 0)?)?;
+    let coder = fields.iter().find(|f| f.name == "coder" && f.ty == BasicType::Byte).and_then(|f| f.bytes.first());
+    let Some(HeapRecord::PrimitiveArray { ty, data, .. }) = index.record(array) else { return None };
+    match (ty, coder) {
+        (BasicType::Byte, Some(&LATIN1)) => Some(cut(data.iter().map(|&b| char::from(b)), max_chars)),
+        (BasicType::Byte, Some(&UTF16)) => utf16(data, u16::from_le_bytes, max_chars),
+        (BasicType::Char, _) => utf16(data, u16::from_be_bytes, max_chars),
+        _ => None,
+    }
+}
+
+/// The text of `char[]` `object`, as [`string_preview`] cuts it.
+pub(crate) fn char_array_text(index: &HeapIndex, object: u32, max_chars: usize) -> Option<String> {
+    match index.record(object)? {
+        HeapRecord::PrimitiveArray { ty: BasicType::Char, data, .. } => utf16(data, u16::from_be_bytes, max_chars),
+        _ => None,
+    }
+}
+
+/// An odd byte count is `None`; a lone surrogate becomes U+FFFD.
+fn utf16(bytes: &[u8], unit: fn([u8; 2]) -> u16, max_chars: usize) -> Option<String> {
+    if !bytes.len().is_multiple_of(2) {
+        return None;
+    }
+    let units = bytes.as_chunks::<2>().0.iter().map(|&pair| unit(pair));
+    Some(cut(char::decode_utf16(units).map(|c| c.unwrap_or(char::REPLACEMENT_CHARACTER)), max_chars))
+}
+
+/// Chars are whole code points, so a cut never splits a surrogate pair.
+fn cut(chars: impl Iterator<Item = char>, max_chars: usize) -> String {
+    let mut out = String::new();
+    for (i, c) in chars.enumerate() {
+        if i == max_chars {
+            out.push('…');
+            break;
+        }
+        out.push(c);
+    }
+    out
+}
+
+#[cfg(test)]
+mod tests;
@@ -0,0 +1,113 @@
+use super::*;
+use crate::hprof::{BasicType, HeapRootKind};
+use crate::test_index::{analyzed, obj};
+use crate::testing::{MiniHeap, sample_with_string};
+
+const AT: u64 = 0x1000;
+const ARRAY: u64 = 0x2000;
+const JDK9: [(&str, BasicType); 2] = [("value", BasicType::Object), ("coder", BasicType::Byte)];
+
+fn preview(heap: &MiniHeap, addr: u64) -> Option<String> {
+    let index = analyzed(heap);
+    string_preview(&index, obj(&index, addr).0, 100)
+}
+
+fn text(text: &str, latin1: bool) -> Option<String> {
+    let mut heap = MiniHeap::new();
+    heap.string(AT, text, latin1).root(HeapRootKind::JniGlobal, AT);
+    preview(&heap, AT)
+}
+
+/// A `java.lang.String` class with `fields`, and one String at [`AT`] with `values`.
+fn custom(fields: &[(&str, BasicType)], values: &[(&str, u64)], array: impl FnOnce(&mut MiniHeap)) -> Option<String> {
+    let mut heap = MiniHeap::new();
+    heap.class("java.lang.String", Some("java.lang.Object"), fields);
+    array(&mut heap);
+    heap.object(AT, "java.lang.String", values);
+    preview(&heap, AT)
+}
+
+#[test]
+fn string_preview_latin1_and_utf16() {
+    assert_eq!(preview(&sample_with_string(), 0x1800).as_deref(), Some("v42"));
+    assert_eq!(text("hé", false).as_deref(), Some("hé"));
+    assert_eq!(text("ÿ é", true).as_deref(), Some("ÿ é"));
+    assert_eq!(text("", true).as_deref(), Some(""));
+
+    let long = "a".repeat(150);
+    assert_eq!(text(&long, true), Some(format!("{}…", "a".repeat(100))));
+    assert_eq!(text(&long, false), Some(format!("{}…", "a".repeat(100))));
+    let exactly = "b".repeat(100);
+    assert_eq!(text(&exactly, true), Some(exactly));
+}
+
+#[test]
+fn truncation_keeps_surrogate_pairs_whole() {
+    let s = format!("{}😀{}", "a".repeat(99), "b".repeat(50));
+    assert_eq!(text(&s, false), Some(format!("{}😀…", "a".repeat(99))));
+    // A lone surrogate becomes the replacement character.
+    let lone: Vec<u8> = [0x68u16, 0xD800, 0x69].iter().flat_map(|u| u.to_le_bytes()).collect();
+    let got = custom(&JDK9, &[("value", ARRAY), ("coder", 1)], |h| {
+        h.prim_bytes(ARRAY, BasicType::Byte, &lone);
+    });
+    assert_eq!(got.as_deref(), Some("h\u{FFFD}i"));
+}
+
+#[test]
+fn jdk8_strings_hold_big_endian_chars() {
+    let chars: Vec<u8> = "hé".encode_utf16().flat_map(u16::to_be_bytes).collect();
+    let fields = [("value", BasicType::Object), ("hash", BasicType::Int)];
+    let got = custom(&fields, &[("value", ARRAY)], |h| {
+        h.prim_bytes(ARRAY, BasicType::Char, &chars);
+    });
+    assert_eq!(got.as_deref(), Some("hé"));
+}
+
+#[test]
+fn malformed_strings_have_no_preview() {
+    let odd = custom(&JDK9, &[("value", ARRAY), ("coder", 1)], |h| {
+        h.prim_bytes(ARRAY, BasicType::Byte, &[0x68, 0, 0x69]);
+    });
+    assert_eq!(odd, None);
+    let bad_coder = custom(&JDK9, &[("value", ARRAY), ("coder", 2)], |h| {
+        h.prim_bytes(ARRAY, BasicType::Byte, b"hi");
+    });
+    assert_eq!(bad_coder, None);
+    let no_value = custom(&[("coder", BasicType::Byte)], &[], |_| {});
+    assert_eq!(no_value, None);
+    let no_coder = custom(&[("value", BasicType::Object)], &[("value", ARRAY)], |h| {
+        h.prim_bytes(ARRAY, BasicType::Byte, b"hi");
+    });
+    assert_eq!(no_coder, None);
+    let null_value = custom(&JDK9, &[], |_| {});
+    assert_eq!(null_value, None);
+    let int_array = custom(&JDK9, &[("value", ARRAY)], |h| {
+        h.prim(ARRAY, BasicType::Int, 2);
+    });
+    assert_eq!(int_array, None);
+    let not_an_array = custom(&JDK9, &[("value", ARRAY)], |h| {
+        h.object(ARRAY, "java.lang.Object", &[]);
+    });
+    assert_eq!(not_an_array, None);
+    // `value` stored as a long instead of a reference.
+    let wrong_type = custom(&[("value", BasicType::Long), ("coder", BasicType::Byte)], &[("value", ARRAY)], |h| {
+        h.prim_bytes(ARRAY, BasicType::Byte, b"hi");
+    });
+    assert_eq!(wrong_type, None);
+}
+
+#[test]
+fn only_strings_have_a_preview() {
+    let mut heap = MiniHeap::new();
+    heap.class("Text", Some("java.lang.Object"), &JDK9).prim_bytes(ARRAY, BasicType::Byte, b"hi").object(
+        AT,
+        "Text",
+        &[("value", ARRAY)],
+    );
+    assert_eq!(preview(&heap, AT), None);
+    assert_eq!(preview(&heap, ARRAY), None);
+    let index = analyzed(&heap);
+    for bad in [index.root(), u32::MAX] {
+        assert_eq!(string_preview(&index, bad, 100), None);
+    }
+}
@@ -0,0 +1,35 @@
+//! Analyzed fixtures for the query tests.
+
+use ide_core::CancellationToken;
+
+use crate::analysis::{AnalyzeOptions, analyze};
+use crate::error::HeapError;
+use crate::index::{HeapIndex, HeapObjectRef};
+use crate::progress::HeapPhase;
+use crate::testing::MiniHeap;
+
+fn no_progress(_: HeapPhase, _: u64, _: u64) -> Result<(), HeapError> {
+    Ok(())
+}
+
+/// `heap` analyzed in memory, with layout sizes.
+pub(crate) fn analyzed(heap: &MiniHeap) -> HeapIndex {
+    analyzed_bytes(&heap.bytes())
+}
+
+pub(crate) fn analyzed_bytes(hprof: &[u8]) -> HeapIndex {
+    let dir = tempfile::tempdir().unwrap();
+    let dump = dir.path().join("dump.hprof");
+    std::fs::write(&dump, hprof).unwrap();
+    let opts = AnalyzeOptions { in_memory: true, ..AnalyzeOptions::default() };
+    analyze(&dump, dir.path(), opts, &no_progress, &CancellationToken::new()).unwrap()
+}
+
+pub(crate) fn obj(index: &HeapIndex, addr: u64) -> HeapObjectRef {
+    HeapObjectRef(index.ids.rank(addr).unwrap_or_else(|| panic!("{addr:#x} is not in the dump")))
+}
+
+/// The slot of the class named `name`.
+pub(crate) fn slot(index: &HeapIndex, name: &str) -> u32 {
+    index.classes.iter().position(|c| c.name == name).unwrap_or_else(|| panic!("no class {name}")) as u32
+}
@@ -0,0 +1,430 @@
+//! Builders for `.hprof` fixtures. They panic on misuse (unknown class name, text that does not
+//! fit the requested encoding): they are test helpers, not input handling.
+
+use std::collections::HashMap;
+use std::path::Path;
+
+use crate::hprof::{BasicType, HeapRootKind};
+
+const TAG_UTF8: u8 = 0x01;
+const TAG_LOAD_CLASS: u8 = 0x02;
+const TAG_HEAP_SEGMENT: u8 = 0x1C;
+const TAG_HEAP_DUMP_END: u8 = 0x2C;
+const TIMESTAMP_MS: u64 = 1_700_000_000_000;
+
+fn put_id(out: &mut Vec<u8>, id_size: u8, id: u64) {
+    if id_size == 4 {
+        out.extend_from_slice(&(id as u32).to_be_bytes());
+    } else {
+        out.extend_from_slice(&id.to_be_bytes());
+    }
+}
+
+/// Writes records one by one; heap sub-records are collected into a single heap-dump segment that
+/// `finish` places after the UTF8 / LOAD CLASS records, followed by HEAP DUMP END.
+pub struct HprofWriter {
+    id_size: u8,
+    top: Vec<u8>,
+    heap: Vec<u8>,
+    class_serial: u32,
+}
+
+impl Default for HprofWriter {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl HprofWriter {
+    pub fn new() -> Self {
+        Self::with_id_size(8)
+    }
+
+    /// `id_size` is 4 or 8; ids are truncated to the width.
+    pub fn with_id_size(id_size: u8) -> Self {
+        assert!(id_size == 4 || id_size == 8, "hprof ids are 4 or 8 bytes");
+        let mut top = b"JAVA PROFILE 1.0.2\0".to_vec();
+        top.extend_from_slice(&u32::from(id_size).to_be_bytes());
+        top.extend_from_slice(&TIMESTAMP_MS.to_be_bytes());
+        Self { id_size, top, heap: Vec::new(), class_serial: 0 }
+    }
+
+    fn top_record(&mut self, tag: u8, body: &[u8]) {
+        self.top.push(tag);
+        self.top.extend_from_slice(&0u32.to_be_bytes());
+        self.top.extend_from_slice(&(body.len() as u32).to_be_bytes());
+        self.top.extend_from_slice(body);
+    }
+
+    fn heap_id(&mut self, id: u64) {
+        put_id(&mut self.heap, self.id_size, id);
+    }
+
+    fn heap_u4(&mut self, v: u32) {
+        self.heap.extend_from_slice(&v.to_be_bytes());
+    }
+
+    pub fn string(&mut self, id: u64, s: &str) -> &mut Self {
+        let mut body = Vec::new();
+        put_id(&mut body, self.id_size, id);
+        body.extend_from_slice(s.as_bytes());
+        self.top_record(TAG_UTF8, &body);
+        self
+    }
+
+    pub fn load_class(&mut self, class_id: u64, name_id: u64) -> &mut Self {
+        self.class_serial += 1;
+        let mut body = self.class_serial.to_be_bytes().to_vec();
+        put_id(&mut body, self.id_size, class_id);
+        body.extend_from_slice(&0u32.to_be_bytes());
+        put_id(&mut body, self.id_size, name_id);
+        self.top_record(TAG_LOAD_CLASS, &body);
+        self
+    }
+
+    /// `statics` are `(name id, object id)` reference statics.
+    pub fn class(&mut self, id: u64, super_id: u64, fields: &[(u64, BasicType)], statics: &[(u64, u64)]) -> &mut Self {
+        self.class_with_loader(id, super_id, 0, fields, statics)
+    }
+
+    pub fn class_with_loader(
+        &mut self,
+        id: u64,
+        super_id: u64,
+        loader_id: u64,
+        fields: &[(u64, BasicType)],
+        statics: &[(u64, u64)],
+    ) -> &mut Self {
+        self.heap.push(0x20);
+        self.heap_id(id);
+        self.heap_u4(0);
+        self.heap_id(super_id);
+        self.heap_id(loader_id);
+        for _ in 0..4 {
+            self.heap_id(0); // signers, protection domain, 2 reserved
+        }
+        let instance_size: usize = fields.iter().map(|(_, ty)| ty.hprof_size(self.id_size)).sum();
+        self.heap_u4(instance_size as u32);
+        self.heap.extend_from_slice(&0u16.to_be_bytes()); // constant pool
+        self.heap.extend_from_slice(&(statics.len() as u16).to_be_bytes());
+        for &(name, object) in statics {
+            self.heap_id(name);
+            self.heap.push(BasicType::Object as u8);
+            self.heap_id(object);
+        }
+        self.heap.extend_from_slice(&(fields.len() as u16).to_be_bytes());
+        for &(name, ty) in fields {
+            self.heap_id(name);
+            self.heap.push(ty as u8);
+        }
+        self
+    }
+
+    pub fn instance(&mut self, id: u64, class_id: u64, data: &[u8]) -> &mut Self {
+        self.heap.push(0x21);
+        self.heap_id(id);
+        self.heap_u4(0);
+        self.heap_id(class_id);
+        self.heap_u4(data.len() as u32);
+        self.heap.extend_from_slice(data);
+        self
+    }
+
+    pub fn obj_array(&mut self, id: u64, class_id: u64, items: &[u64]) -> &mut Self {
+        self.heap.push(0x22);
+        self.heap_id(id);
+        self.heap_u4(0);
+        self.heap_u4(items.len() as u32);
+        self.heap_id(class_id);
+        for &item in items {
+            self.heap_id(item);
+        }
+        self
+    }
+
+    /// An array of `len` zeroed elements.
+    pub fn prim_array(&mut self, id: u64, ty: BasicType, len: u32) -> &mut Self {
+        let bytes = vec![0u8; len as usize * ty.hprof_size(self.id_size)];
+        self.prim_bytes(id, ty, &bytes)
+    }
+
+    /// An array whose elements are `bytes` (big-endian, as stored in the dump).
+    pub fn prim_bytes(&mut self, id: u64, ty: BasicType, bytes: &[u8]) -> &mut Self {
+        let size = ty.hprof_size(self.id_size);
+        assert!(ty != BasicType::Object && bytes.len().is_multiple_of(size), "{ty:?} array needs whole elements");
+        self.heap.push(0x23);
+        self.heap_id(id);
+        self.heap_u4(0);
+        self.heap_u4((bytes.len() / size) as u32);
+        self.heap.push(ty as u8);
+        self.heap.extend_from_slice(bytes);
+        self
+    }
+
+    /// Kinds that carry a thread serial get serial 1; see [`Self::root_in_thread`].
+    pub fn root(&mut self, kind: HeapRootKind, id: u64) -> &mut Self {
+        self.root_in_thread(kind, id, 1)
+    }
+
+    /// `serial` is ignored for kinds that do not carry one.
+    pub fn root_in_thread(&mut self, kind: HeapRootKind, id: u64, serial: u32) -> &mut Self {
+        let (tag, has_serial, trailing) = match kind {
+            HeapRootKind::Unknown => (0xFF, false, Trailing::None),
+            HeapRootKind::JniGlobal => (0x01, false, Trailing::Id),
+            HeapRootKind::JniLocal => (0x02, true, Trailing::U4),
+            HeapRootKind::JavaFrame => (0x03, true, Trailing::U4),
+            HeapRootKind::NativeStack => (0x04, true, Trailing::None),
+            HeapRootKind::StickyClass => (0x05, false, Trailing::None),
+            HeapRootKind::ThreadBlock => (0x06, true, Trailing::None),
+            HeapRootKind::MonitorUsed => (0x07, false, Trailing::None),
+            HeapRootKind::ThreadObject => (0x08, true, Trailing::U4),
+        };
+        self.heap.push(tag);
+        self.heap_id(id);
+        if has_serial {
+            self.heap_u4(serial);
+        }
+        match trailing {
+            Trailing::None => {}
+            Trailing::U4 => self.heap_u4(0),
+            Trailing::Id => self.heap_id(0),
+        }
+        self
+    }
+
+    pub fn finish(&self) -> Vec<u8> {
+        let mut out = self.top.clone();
+        out.push(TAG_HEAP_SEGMENT);
+        out.extend_from_slice(&0u32.to_be_bytes());
+        let heap_len = u32::try_from(self.heap.len()).expect("fixture heap segment exceeds 4 GiB");
+        out.extend_from_slice(&heap_len.to_be_bytes());
+        out.extend_from_slice(&self.heap);
+        out.push(TAG_HEAP_DUMP_END);
+        out.extend_from_slice(&0u32.to_be_bytes());
+        out.extend_from_slice(&0u32.to_be_bytes());
+        out
+    }
+}
+
+enum Trailing {
+    None,
+    U4,
+    Id,
+}
+
+struct MiniClass {
+    id: u64,
+    super_name: Option<String>,
+    fields: Vec<(String, BasicType)>,
+}
+
+/// Ids for classes, names and string backing arrays come from here, above any address a test
+/// would pick by hand.
+const GENERATED_ID_BASE: u64 = 1 << 32;
+
+/// Heap fixtures by class and field name on top of [`HprofWriter`] (id size 8).
+///
+/// Class names are written in the HotSpot form (`.` becomes `/`); look-ups use the name as given.
+pub struct MiniHeap {
+    w: HprofWriter,
+    next_id: u64,
+    classes: HashMap<String, MiniClass>,
+}
+
+impl Default for MiniHeap {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl MiniHeap {
+    /// Starts with `java.lang.Object` and `java.lang.Class` already defined.
+    pub fn new() -> Self {
+        let mut heap = Self { w: HprofWriter::new(), next_id: GENERATED_ID_BASE, classes: HashMap::new() };
+        heap.class("java.lang.Object", None, &[]);
+        heap.class("java.lang.Class", Some("java.lang.Object"), &[]);
+        heap
+    }
+
+    fn fresh_id(&mut self) -> u64 {
+        self.next_id += 1;
+        self.next_id
+    }
+
+    fn class_id(&self, name: &str) -> u64 {
+        self.classes.get(name).unwrap_or_else(|| panic!("MiniHeap: class {name} is not defined")).id
+    }
+
+    /// `super_name: None` writes super id 0.
+    pub fn class(&mut self, name: &str, super_name: Option<&str>, fields: &[(&str, BasicType)]) -> &mut Self {
+        let super_id = super_name.map_or(0, |sup| self.class_id(sup));
+        let id = self.fresh_id();
+        let name_id = self.fresh_id();
+        let mut field_ids = Vec::with_capacity(fields.len());
+        for &(field, ty) in fields {
+            let field_id = self.fresh_id();
+            self.w.string(field_id, field);
+            field_ids.push((field_id, ty));
+        }
+        self.w.string(name_id, &name.replace('.', "/"));
+        self.w.load_class(id, name_id);
+        self.w.class(id, super_id, &field_ids, &[]);
+        self.w.root(HeapRootKind::StickyClass, id);
+        let fields = fields.iter().map(|&(field, ty)| (field.to_owned(), ty)).collect();
+        self.classes.insert(name.to_owned(), MiniClass { id, super_name: super_name.map(str::to_owned), fields });
+        self
+    }
+
+    /// Fields are laid out class first, then superclass, as HotSpot does. A field missing from
+    /// `values` is 0; narrower types keep the low bytes of the value.
+    pub fn object(&mut self, addr: u64, class: &str, values: &[(&str, u64)]) -> &mut Self {
+        let class_id = self.class_id(class);
+        let mut data = Vec::new();
+        let mut cursor = Some(class);
+        while let Some(name) = cursor {
+            let c = &self.classes[name];
+            for (field, ty) in &c.fields {
+                let value = values.iter().find(|(n, _)| *n == field.as_str()).map_or(0, |&(_, v)| v);
+                let width = ty.hprof_size(8);
+                data.extend_from_slice(&value.to_be_bytes()[8 - width..]);
+            }
+            cursor = c.super_name.as_deref();
+        }
+        self.w.instance(addr, class_id, &data);
+        self
+    }
+
+    pub fn array_of(&mut self, addr: u64, class: &str, items: &[u64]) -> &mut Self {
+        let class_id = self.class_id(class);
+        self.w.obj_array(addr, class_id, items);
+        self
+    }
+
+    /// A primitive array of `len` zeroed elements.
+    pub fn prim(&mut self, addr: u64, ty: BasicType, len: u32) -> &mut Self {
+        self.w.prim_array(addr, ty, len);
+        self
+    }
+
+    /// A primitive array holding `bytes` (big-endian elements).
+    pub fn prim_bytes(&mut self, addr: u64, ty: BasicType, bytes: &[u8]) -> &mut Self {
+        self.w.prim_bytes(addr, ty, bytes);
+        self
+    }
+
+    /// A `java.lang.String` (JDK 9+ layout: `value` byte[] + `coder`) at `addr`. `latin1` stores
+    /// one byte per char (coder 0, every char must be ≤ U+00FF); otherwise UTF-16LE (coder 1).
+    pub fn string(&mut self, addr: u64, text: &str, latin1: bool) -> &mut Self {
+        if !self.classes.contains_key("java.lang.String") {
+            let fields = [("value", BasicType::Object), ("coder", BasicType::Byte)];
+            self.class("java.lang.String", Some("java.lang.Object"), &fields);
+        }
+        let bytes: Vec<u8> = if latin1 {
+            text.chars()
+                .map(|c| u8::try_from(u32::from(c)).unwrap_or_else(|_| panic!("{c:?} is not Latin-1")))
+                .collect()
+        } else {
+            text.encode_utf16().flat_map(u16::to_le_bytes).collect()
+        };
+        let array = self.fresh_id();
+        self.w.prim_bytes(array, BasicType::Byte, &bytes);
+        self.object(addr, "java.lang.String", &[("value", array), ("coder", u64::from(!latin1))])
+    }
+
+    /// Kinds that carry a thread serial get serial 1.
+    pub fn root(&mut self, kind: HeapRootKind, addr: u64) -> &mut Self {
+        self.w.root(kind, addr);
+        self
+    }
+
+    pub fn root_in_thread(&mut self, kind: HeapRootKind, addr: u64, serial: u32) -> &mut Self {
+        self.w.root_in_thread(kind, addr, serial);
+        self
+    }
+
+    pub fn bytes(&self) -> Vec<u8> {
+        self.w.finish()
+    }
+
+    pub fn write_to(&self, path: &Path) {
+        std::fs::write(path, self.bytes()).unwrap_or_else(|e| panic!("MiniHeap: writing {}: {e}", path.display()));
+    }
+}
+
+/// The heap most analysis tests share:
+///
+/// - `Holder { a: Object, b: Object }`, `Node { next: Object, v: long }`,
+///   `java.lang.ref.Reference { referent: Object, queue: Object }`,
+///   `java.lang.ref.WeakReference extends Reference`, `[Ljava.lang.Object;`
+/// - H `0x1000` Holder { a: N1, b: N2 }; N1 `0x1100` Node { next: N3 }; N2 `0x1200` Node { next: N3 };
+///   N3 `0x1300` Node { next: L }; L `0x1400` long[2]; R `0x1500` Object[] { N1, null, null };
+///   W `0x1600` WeakReference { referent: N4 }; N4 `0x1700` Node {}
+/// - roots: JNI global H, Java frame N3 (thread serial 1), JNI global W
+///
+/// R and N4 are unreachable (N4 only through the weak referent).
+pub fn sample() -> MiniHeap {
+    let mut heap = MiniHeap::new();
+    heap.class("Holder", Some("java.lang.Object"), &[("a", BasicType::Object), ("b", BasicType::Object)])
+        .class("Node", Some("java.lang.Object"), &[("next", BasicType::Object), ("v", BasicType::Long)])
+        .class(
+            "java.lang.ref.Reference",
+            Some("java.lang.Object"),
+            &[("referent", BasicType::Object), ("queue", BasicType::Object)],
+        )
+        .class("java.lang.ref.WeakReference", Some("java.lang.ref.Reference"), &[])
+        .class("[Ljava.lang.Object;", Some("java.lang.Object"), &[])
+        .object(0x1000, "Holder", &[("a", 0x1100), ("b", 0x1200)])
+        .object(0x1100, "Node", &[("next", 0x1300)])
+        .object(0x1200, "Node", &[("next", 0x1300)])
+        .object(0x1300, "Node", &[("next", 0x1400)])
+        .prim(0x1400, BasicType::Long, 2)
+        .array_of(0x1500, "[Ljava.lang.Object;", &[0x1100, 0, 0])
+        .object(0x1600, "java.lang.ref.WeakReference", &[("referent", 0x1700)])
+        .object(0x1700, "Node", &[])
+        .root(HeapRootKind::JniGlobal, 0x1000)
+        .root(HeapRootKind::JavaFrame, 0x1300)
+        .root(HeapRootKind::JniGlobal, 0x1600);
+    heap
+}
+
+/// [`sample`] plus S `0x1800` String `"v42"` (Latin-1) held as `a` of a second Holder `0x1900`,
+/// rooted as a JNI global. That Holder retains 72 bytes, as much as H.
+pub fn sample_with_string() -> MiniHeap {
+    let mut heap = sample();
+    heap.string(0x1800, "v42", true).object(0x1900, "Holder", &[("a", 0x1800)]).root(HeapRootKind::JniGlobal, 0x1900);
+    heap
+}
+
+/// [`sample`] plus two Nodes `0x1a00` and `0x1b00`, each rooted as a JNI global.
+pub fn sample_with_two_more_nodes() -> MiniHeap {
+    let mut heap = sample();
+    heap.object(0x1a00, "Node", &[])
+        .object(0x1b00, "Node", &[])
+        .root(HeapRootKind::JniGlobal, 0x1a00)
+        .root(HeapRootKind::JniGlobal, 0x1b00);
+    heap
+}
+
+/// Seeded xorshift64 numbers for reproducible random test data (the workspace has no `rand`).
+pub struct XorShift(u64);
+
+impl XorShift {
+    pub fn new(seed: u64) -> Self {
+        // Zero is xorshift's one fixed point.
+        Self(seed.max(1))
+    }
+
+    pub fn next_u64(&mut self) -> u64 {
+        let mut x = self.0;
+        x ^= x << 13;
+        x ^= x >> 7;
+        x ^= x << 17;
+        self.0 = x;
+        x
+    }
+
+    /// A number in `0..bound`; `bound` must not be 0.
+    pub fn below(&mut self, bound: u32) -> u32 {
+        (self.next_u64() % u64::from(bound)) as u32
+    }
+}
@@ -27,6 +27,7 @@ ide-search.workspace = true
 ide-lsp.workspace = true
 ide-vcs.workspace = true
 ide-dap.workspace = true
+ide-heap.workspace = true
 ide-jvm-attach.workspace = true
 ide-build.workspace = true
 ide-analysis.workspace = true
@@ -22,7 +22,7 @@
 mod templates;

 use ide_extension::{Manifest, validate_plugin_id};
-use ide_host::plugins::{PluginHost, plugin_icon, read_market_url, resolve_market_href};
+use ide_host::plugins::{PluginHost, market_href_reachable_from, plugin_icon, read_market_url, resolve_market_href};
 use ide_plugin::{Limits, PluginEngine};
 use std::path::{Path, PathBuf};
 use std::process::{Command, ExitCode};
@@ -591,7 +591,7 @@ fn cmd_index(args: &[String]) -> Result<(), String> {
    let base = a.value("download-base").map(|b| b.trim_end_matches('/'));
    // Revocations and other publishers of an existing index are kept.
    let mut index = match std::fs::read_to_string(&out) {
-        Ok(text) => current_format(Index::parse(&text)?, &out.to_string_lossy())?,
+        Ok(text) => parse_index(&text, &out.to_string_lossy())?,
        Err(_) => Index { format: package::INDEX_FORMAT, ..Index::default() },
    };
    let publisher = match (a.value("publisher"), a.value("key")) {
@@ -653,6 +653,11 @@ fn cmd_index(args: &[String]) -> Result<(), String> {
                engine: package::engine_requirement(&m.engine, built_for.as_ref()),
                categories: m.categories(),
                icon: plugin_icon(&ide_extension::Package::new(m.clone(), scratch.clone()))?,
+                homepage: m.homepage.clone().filter(|h| !h.trim().is_empty()),
+                notes: m.change_notes.clone().filter(|n| !n.trim().is_empty()),
+                downloads: None,
+                featured: false,
+                suggest: Vec::new(),
            })
        })();
        let entry = entry.map_err(|e| format!("{}: {e}", path.display()))?;
@@ -717,14 +722,22 @@ fn register_key(
    Ok(publishers)
 }

-/// `index`, unless a newer `openidea-plugin` wrote it (rewriting it would drop what this one can't read).
-fn current_format(index: Index, file: &str) -> Result<Index, String> {
+/// The index in `text` (read from `file`), unless a newer `openidea-plugin` wrote it (rewriting it
+/// would drop what this one can't read). Says which entries it does not keep: no IDE offers them.
+fn parse_index(text: &str, file: &str) -> Result<Index, String> {
+    let (index, dropped) = Index::parse_dropping(text)?;
    if index.is_newer() {
        return Err(format!(
            "{file}: index format {} is newer than this tool writes; update openidea-plugin",
            index.format
        ));
    }
+    for e in &dropped {
+        eprintln!(
+            "warning: {file}: dropped {:?} {:?}: its id or version is not one a manifest may carry",
+            e.id, e.version
+        );
+    }
    Ok(index)
 }

@@ -735,14 +748,15 @@ fn cmd_merge(args: &[String]) -> Result<(), String> {
    };
    let keep = a.value("keep").ok_or("--keep is required")?;
    let out = a.value("out").unwrap_or(base);
-    let mut index =
-        current_format(Index::parse(&std::fs::read_to_string(base).map_err(|e| format!("{base}: {e}"))?)?, base)?;
+    let mut index = parse_index(&std::fs::read_to_string(base).map_err(|e| format!("{base}: {e}"))?, base)?;
    let bytes = read_market_url(other, 16 << 20)?;
-    let theirs = Index::parse(&String::from_utf8(bytes).map_err(|_| format!("{other}: not UTF-8"))?)?;
-    let mut theirs = current_format(theirs, other)?;
+    let mut theirs = parse_index(&String::from_utf8(bytes).map_err(|_| format!("{other}: not UTF-8"))?, other)?;
    // Their downloads are relative to their index, not to ours.
    for e in &mut theirs.plugins {
        e.download = resolve_market_href(other, &e.download);
+        if !market_href_reachable_from(other, &e.download) {
+            return Err(format!("{other}: the download of {} {} is not on the network", e.id, e.version));
+        }
    }
    let count = theirs.plugins.len();
    index.include(theirs, &[keep]).map_err(|e| format!("{other}: {e}"))?;
@@ -942,6 +956,47 @@ mod tests {
        assert!(err.contains("unknown publisher"), "{err}");
    }

+    /// An index read over the network is not merged when it names a download on this machine:
+    /// the merged index is a local one, which may.
+    #[test]
+    fn an_index_read_over_the_network_is_not_merged_with_local_downloads() {
+        use std::io::{BufRead, BufReader, Write};
+        let tmp = tempfile::tempdir().unwrap();
+        let base = tmp.path().join("index.json");
+        write_index(&Index { format: package::INDEX_FORMAT, ..Index::default() }, &base).unwrap();
+        let local = tmp.path().join("alice.dawn-1.0.0.oiplugin").to_string_lossy().into_owned();
+        let theirs = serde_json::json!({
+            "format": package::INDEX_FORMAT,
+            "publishers": [{ "id": "alice", "name": "Alice", "keys": [] }],
+            "plugins": [{
+                "id": "alice.dawn", "name": "Dawn", "version": "1.0.0", "publisher": "alice",
+                "download": local, "digest": "d", "engine": "^1.0",
+            }],
+        })
+        .to_string();
+        let listener = std::net::TcpListener::bind("127.0.0.1:0").unwrap();
+        let other = format!("http://127.0.0.1:{}/index.json", listener.local_addr().unwrap().port());
+        std::thread::spawn(move || {
+            for mut stream in listener.incoming().flatten() {
+                let mut reader = BufReader::new(stream.try_clone().unwrap());
+                let mut line = String::new();
+                while reader.read_line(&mut line).unwrap_or(0) > 0 && line != "\r\n" {
+                    line.clear();
+                }
+                let _ = write!(
+                    stream,
+                    "HTTP/1.1 200 OK\r\nContent-Length: {}\r\nConnection: close\r\n\r\n{theirs}",
+                    theirs.len()
+                );
+            }
+        });
+
+        let err = cmd_merge(&strings(&[base.to_str().unwrap(), &other, "--keep", "openidea"])).unwrap_err();
+        assert!(err.contains("is not on the network"), "{err}");
+        let merged = Index::parse(&std::fs::read_to_string(&base).unwrap()).unwrap();
+        assert!(merged.plugins.is_empty(), "{:?}", merged.plugins);
+    }
+
    #[test]
    fn the_index_carries_plugin_icons() {
        let tmp = tempfile::tempdir().unwrap();
@@ -9,6 +9,14 @@ use std::path::{Path, PathBuf};
 /// configuration and roaming data keep following the OS.
 pub const LOCAL_DATA_ENV: &str = "OPENIDEA_LOCAL_DATA_DIR";

+/// A custom local-data root chosen in Settings › System Settings › Caches,
+/// stored in the configuration directory. The environment variable still wins.
+pub const OVERRIDE_FILE: &str = "local-data-dir.txt";
+
+/// A pending move of the local data to a newly chosen directory, carried out
+/// at the next start (before any project opens), like File › Invalidate Caches.
+const MIGRATION_FILE: &str = "local-data-migration.json";
+
 /// `$OPENIDEA_LOCAL_DATA_DIR/<identifier>` when set, else the OS local data directory
 /// (Tauri's `app_local_data_dir`). The identifier keeps release and per-worktree
 /// debug builds apart under one root. A set but unusable path is an error, never a
@@ -17,6 +25,203 @@ pub fn local_data_dir(identifier: &str) -> Result<PathBuf, String> {
    resolve_local(std::env::var_os(LOCAL_DATA_ENV), dirs::data_local_dir(), identifier)
 }

+/// The directory to actually start with: the environment override, else a valid
+/// custom directory from Settings, else the OS default. A stored but unusable
+/// custom directory is an error, never a silent fallback.
+pub fn startup_local_data_dir(identifier: &str) -> Result<PathBuf, String> {
+    startup_resolve(std::env::var_os(LOCAL_DATA_ENV), stored_override(identifier), dirs::data_local_dir(), identifier)
+}
+
+fn startup_resolve(
+    var: Option<OsString>,
+    stored: Option<PathBuf>,
+    os: Option<PathBuf>,
+    identifier: &str,
+) -> Result<PathBuf, String> {
+    if var.as_ref().is_some_and(|v| !v.is_empty()) {
+        return resolve_local(var, os, identifier);
+    }
+    let Some(root) = stored else { return resolve_local(None, os, identifier) };
+    if !root.is_absolute() {
+        return Err(format!("custom local data directory must be an absolute path: {}", root.display()));
+    }
+    resolve_root(root, identifier, "custom local data directory")
+}
+
+/// The file holding the custom local-data root, if the platform exposes its
+/// configuration directory. Both startup and Settings use this one path.
+pub fn override_path(identifier: &str) -> Option<PathBuf> {
+    dirs::config_dir().map(|dir| dir.join(identifier).join(OVERRIDE_FILE))
+}
+
+fn migration_path(identifier: &str) -> Option<PathBuf> {
+    dirs::config_dir().map(|dir| dir.join(identifier).join(MIGRATION_FILE))
+}
+
+/// The custom root stored by Settings, if any (validated when it is used).
+pub fn stored_override(identifier: &str) -> Option<PathBuf> {
+    stored_override_in(&override_path(identifier)?)
+}
+
+fn stored_override_in(path: &Path) -> Option<PathBuf> {
+    let text = fs::read_to_string(path).ok()?;
+    let trimmed = text.trim();
+    (!trimmed.is_empty()).then(|| PathBuf::from(trimmed))
+}
+
+/// The OS default local data directory (what clearing the custom directory
+/// returns to), ignoring any stored override. The environment still applies.
+pub fn default_local_data_dir(identifier: &str) -> Result<PathBuf, String> {
+    local_data_dir(identifier)
+}
+
+/// Stores (`Some`) or clears (`None`) the custom local-data root, returning the
+/// directory that takes effect after a restart. A pending custom migration to
+/// anywhere else is dropped: only the caller schedules the matching one.
+pub fn set_override(identifier: &str, root: Option<&Path>) -> Result<PathBuf, String> {
+    let Some(path) = override_path(identifier) else {
+        return Err("cannot find the configuration directory".into());
+    };
+    set_override_in(&path, &migration_path(identifier), root, identifier)
+}
+
+fn set_override_in(
+    path: &Path,
+    migration: &Option<PathBuf>,
+    root: Option<&Path>,
+    identifier: &str,
+) -> Result<PathBuf, String> {
+    if let Some(migration) = migration {
+        let _ = fs::remove_file(migration);
+    }
+    let Some(root) = root else {
+        if let Err(error) = fs::remove_file(path)
+            && error.kind() != io::ErrorKind::NotFound
+        {
+            return Err(format!("cannot clear the custom local data directory: {error}"));
+        }
+        return local_data_dir(identifier);
+    };
+    if !root.is_absolute() {
+        return Err(format!("custom local data directory must be an absolute path: {}", root.display()));
+    }
+    let dir = resolve_root(root.to_path_buf(), identifier, "custom local data directory")?;
+    if let Some(parent) = path.parent()
+        && let Err(error) = fs::create_dir_all(parent)
+    {
+        return Err(format!("cannot store the custom local data directory: {error}"));
+    }
+    if let Err(error) = fs::write(path, format!("{}\n", root.display())) {
+        return Err(format!("cannot store the custom local data directory: {error}"));
+    }
+    Ok(dir)
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
+struct CustomMigration {
+    from: PathBuf,
+    to: PathBuf,
+}
+
+/// Schedules a move of the local data from `from` to `to` at the next start.
+/// Returns false when there is nothing to move. The caller restarts the IDE.
+pub fn schedule_custom_migration(identifier: &str, from: &Path, to: &Path) -> Result<bool, String> {
+    let Some(path) = migration_path(identifier) else {
+        return Err("cannot find the configuration directory".into());
+    };
+    schedule_custom_migration_in(&path, from, to)
+}
+
+fn schedule_custom_migration_in(path: &Path, from: &Path, to: &Path) -> Result<bool, String> {
+    if from == to {
+        return Ok(false);
+    }
+    if let Some(parent) = path.parent()
+        && let Err(error) = fs::create_dir_all(parent)
+    {
+        return Err(format!("cannot schedule the data move: {error}"));
+    }
+    let json = serde_json::to_vec(&CustomMigration { from: from.into(), to: to.into() })
+        .map_err(|error| format!("cannot schedule the data move: {error}"))?;
+    if let Err(error) = fs::write(path, json) {
+        return Err(format!("cannot schedule the data move: {error}"));
+    }
+    Ok(true)
+}
+
+/// Carries out a scheduled custom migration aimed at `local` (call at start-up,
+/// before projects open). Entries that appear in the meantime are never
+/// overwritten; a partially moved tree is retried at the next start.
+pub fn apply_custom_migration(identifier: &str, local: &Path) {
+    let Some(path) = migration_path(identifier) else { return };
+    apply_custom_migration_in(&path, local);
+}
+
+fn apply_custom_migration_in(path: &Path, local: &Path) {
+    let Ok(bytes) = fs::read(path) else { return };
+    let Ok(job) = serde_json::from_slice::<CustomMigration>(&bytes) else {
+        let _ = fs::remove_file(path);
+        return;
+    };
+    if job.to != local || job.from == local {
+        let _ = fs::remove_file(path);
+        return;
+    }
+    move_entries(&job.from, local, &custom_entries(&job.from));
+    let leftover = custom_entries(&job.from).into_iter().any(|entry| job.from.join(entry).exists());
+    if !leftover {
+        let _ = fs::remove_file(path);
+    }
+}
+
+/// Entries of a local-data tree that move to a newly chosen directory.
+/// Non-relocatable tool installs (virtual environments with absolute interpreter
+/// paths) stay behind and are reinstalled on demand, as in `migrate_entries`.
+fn custom_entries(root: &Path) -> Vec<PathBuf> {
+    let mut entries = local_entries(root);
+    for extra in ["logs", "agents/tools"] {
+        let entry = PathBuf::from(extra);
+        if !entries.contains(&entry) {
+            entries.push(entry);
+        }
+    }
+    entries
+}
+
+/// Moves the local-data tree from `from` to `to`, entry by entry. Same-volume
+/// entries rename at once; cross-volume copies run in the background. Targets
+/// created in the meantime are never merged into or overwritten.
+fn move_entries(from: &Path, to: &Path, entries: &[PathBuf]) {
+    if from == to {
+        return;
+    }
+    let mut copies = Vec::new();
+    for entry in entries {
+        let source = from.join(entry);
+        let target = to.join(entry);
+        match try_rename(&source, &target) {
+            Ok(true) => copies.push((source, target)),
+            Ok(false) => {}
+            Err(error) => {
+                tracing::warn!(?source, ?target, %error, "data move failed; keeping old data, using new location")
+            }
+        }
+    }
+    if !copies.is_empty() {
+        let result = std::thread::Builder::new().name("openidea-data-migration".into()).spawn(move || {
+            for (source, target) in copies {
+                tracing::info!(?source, ?target, "copying data to the new location in background");
+                if let Err(error) = copy_then_remove(&source, &target) {
+                    tracing::warn!(?source, ?target, %error, "data copy failed; keeping old data");
+                }
+            }
+        });
+        if let Err(error) = result {
+            tracing::warn!(%error, "cannot start data migration worker; keeping old data");
+        }
+    }
+}
+
 fn resolve_local(var: Option<OsString>, os: Option<PathBuf>, identifier: &str) -> Result<PathBuf, String> {
    let Some(root) = var.filter(|v| !v.is_empty()).map(PathBuf::from) else {
        return os.map(|dir| dir.join(identifier)).ok_or_else(|| "cannot find the local data directory".into());
@@ -25,10 +230,14 @@ fn resolve_local(var: Option<OsString>, os: Option<PathBuf>, identifier: &str) -
    if !root.is_absolute() {
        return Err(format!("{LOCAL_DATA_ENV} must be an absolute path: {}", root.display()));
    }
+    resolve_root(root, identifier, LOCAL_DATA_ENV)
+}
+
+fn resolve_root(root: PathBuf, identifier: &str, what: &str) -> Result<PathBuf, String> {
    let dir = root.join(identifier);
    fs::create_dir_all(&dir)
        .and_then(|()| tempfile::NamedTempFile::new_in(&dir).map(drop))
-        .map_err(|error| format!("{LOCAL_DATA_ENV}: cannot write to {}: {error}", dir.display()))?;
+        .map_err(|error| format!("{what}: cannot write to {}: {error}", dir.display()))?;
    Ok(dir)
 }

@@ -77,6 +286,11 @@ pub fn migrate(data: &Path, local: &Path) {
 }

 fn migrate_entries(data: &Path, local: &Path) {
+    move_entries(data, local, &local_entries(data));
+}
+
+/// The rebuildable entries of the legacy roaming tree that move to Local.
+fn local_entries(data: &Path) -> Vec<PathBuf> {
    let mut entries: Vec<PathBuf> = [
        "language-server-runtimes",
        "index",
@@ -118,31 +332,7 @@ fn migrate_entries(data: &Path, local: &Path) {
        Err(error) if error.kind() == io::ErrorKind::NotFound => {}
        Err(error) => tracing::warn!(%error, "cannot enumerate legacy tools; keeping old data, using Local"),
    }
-    let mut copies = Vec::new();
-    for entry in entries {
-        let source = data.join(&entry);
-        let target = data_path(data, local, &entry);
-        match try_rename(&source, &target) {
-            Ok(true) => copies.push((source, target)),
-            Ok(false) => {}
-            Err(error) => {
-                tracing::warn!(?source, ?target, %error, "data migration failed; keeping old data, using Local")
-            }
-        }
-    }
-    if !copies.is_empty() {
-        let result = std::thread::Builder::new().name("openidea-data-migration".into()).spawn(move || {
-            for (source, target) in copies {
-                tracing::info!(?source, ?target, "copying legacy data in background");
-                if let Err(error) = copy_then_remove(&source, &target) {
-                    tracing::warn!(?source, ?target, %error, "data copy failed; keeping old data, using Local");
-                }
-            }
-        });
-        if let Err(error) = result {
-            tracing::warn!(%error, "cannot start data migration worker; keeping old data, using Local");
-        }
-    }
+    entries
 }

 /// Returns true when a cross-volume copy is needed.
@@ -597,4 +787,108 @@ mod tests {
                .any(|e| e.file_name().to_string_lossy().starts_with(".migration-"))
        );
    }
+
+    #[test]
+    fn custom_override_round_trips_and_validates() {
+        let tmp = tempfile::tempdir().unwrap();
+        let file = tmp.path().join("local-data-dir.txt");
+        let migration = tmp.path().join("local-data-migration.json");
+        let id = "ai.test.openidea";
+        assert_eq!(stored_override_in(&file), None);
+
+        let root = tmp.path().join("custom-root");
+        let dir = set_override_in(&file, &Some(migration.clone()), Some(&root), id).unwrap();
+        assert_eq!(dir, root.join(id));
+        assert!(dir.is_dir());
+        assert_eq!(stored_override_in(&file), Some(root.clone()));
+        assert_eq!(startup_resolve(None, stored_override_in(&file), Some(tmp.path().join("os")), id).unwrap(), dir);
+
+        // A relative root is rejected before anything is written.
+        let before = fs::read_to_string(&file).unwrap();
+        let error = set_override_in(&file, &Some(migration.clone()), Some(Path::new("relative")), id).unwrap_err();
+        assert!(error.contains("absolute"), "{error}");
+        assert_eq!(fs::read_to_string(&file).unwrap(), before);
+
+        // An unwritable root (an existing file) is rejected too.
+        let blocker = tmp.path().join("blocker");
+        fs::write(&blocker, "").unwrap();
+        let error = set_override_in(&file, &Some(migration.clone()), Some(&blocker), id).unwrap_err();
+        assert!(error.contains("cannot write"), "{error}");
+
+        // Clearing removes the file and returns the default.
+        let dir = set_override_in(&file, &Some(migration), None, id).unwrap();
+        assert!(!file.exists());
+        assert_eq!(dir, local_data_dir(id).unwrap());
+        assert_eq!(stored_override_in(&file), None);
+    }
+
+    #[test]
+    fn startup_prefers_the_environment_then_the_override() {
+        let tmp = tempfile::tempdir().unwrap();
+        let os = tmp.path().join("os");
+        let custom = tmp.path().join("custom");
+        let env = tmp.path().join("env");
+        let id = "ai.test.openidea";
+
+        let error = startup_resolve(None, Some(PathBuf::from("relative")), Some(os.clone()), id).unwrap_err();
+        assert!(error.contains("absolute"), "{error}");
+
+        // The environment wins over a stored override.
+        let dir = startup_resolve(Some(env.clone().into()), Some(custom.clone()), Some(os.clone()), id).unwrap();
+        assert_eq!(dir, env.join(id));
+
+        // Without the environment the override wins over the OS default.
+        let dir = startup_resolve(None, Some(custom.clone()), Some(os.clone()), id).unwrap();
+        assert_eq!(dir, custom.join(id));
+
+        // And without either the OS default applies.
+        let dir = startup_resolve(None, None, Some(os.clone()), id).unwrap();
+        assert_eq!(dir, os.join(id));
+    }
+
+    #[test]
+    fn custom_migration_moves_the_tree_and_clears_itself() {
+        let tmp = tempfile::tempdir().unwrap();
+        let marker = tmp.path().join("local-data-migration.json");
+        let from = tmp.path().join("old-local");
+        let to = tmp.path().join("new-local");
+        fs::create_dir_all(from.join("index/p1")).unwrap();
+        fs::write(from.join("index/p1/symbols"), "index").unwrap();
+        fs::create_dir_all(from.join("cache/p1")).unwrap();
+        fs::write(from.join("cache/p1/build"), "cache").unwrap();
+        fs::create_dir_all(from.join("tools/demo/bin")).unwrap();
+        fs::write(from.join("tools/demo/bin/demo.cmd"), "payload").unwrap();
+        fs::write(from.join("history"), "roaming stays").unwrap();
+
+        // Nothing to move: no marker is written.
+        assert!(!schedule_custom_migration_in(&marker, &from, &from).unwrap());
+        assert!(!marker.exists());
+
+        assert!(schedule_custom_migration_in(&marker, &from, &to).unwrap());
+        apply_custom_migration_in(&marker, &to);
+        assert!(!marker.exists());
+        assert_eq!(fs::read_to_string(to.join("index/p1/symbols")).unwrap(), "index");
+        assert_eq!(fs::read_to_string(to.join("cache/p1/build")).unwrap(), "cache");
+        assert!(to.join("tools/demo/bin/demo.cmd").exists());
+        assert!(!from.join("index").exists());
+        // Roaming content is not local data and stays behind.
+        assert_eq!(fs::read_to_string(from.join("history")).unwrap(), "roaming stays");
+
+        // A migration aimed elsewhere is dropped without touching anything.
+        fs::create_dir_all(from.join("lsp")).unwrap();
+        assert!(schedule_custom_migration_in(&marker, &from, &tmp.path().join("elsewhere")).unwrap());
+        apply_custom_migration_in(&marker, &to);
+        assert!(!marker.exists());
+        assert!(from.join("lsp").exists());
+        assert!(!to.join("lsp").exists());
+    }
+
+    #[test]
+    fn custom_entries_cover_logs_and_agent_tools() {
+        let tmp = tempfile::tempdir().unwrap();
+        let entries = custom_entries(tmp.path());
+        for expected in ["logs", "agents/tools", "index", "cache", "lsp", "agents/registry.json"] {
+            assert!(entries.contains(&PathBuf::from(expected)), "{entries:?}");
+        }
+    }
 }
@@ -73,6 +73,11 @@ pub struct Host {
    pub processes: ProcessManager,
    /// Debug sessions (adapters run on this machine, next to the project).
    pub debugger: Arc<ide_dap::DebugManager>,
+    /// Heap snapshots open in any window, captured from a debug session or opened from a file.
+    pub heap: Arc<ide_heap::HeapRegistry>,
+    /// The window that owns each open heap snapshot; its project's close closes them.
+    pub(crate) heap_windows: Mutex<HashMap<ide_heap::HeapSnapshotId, String>>,
+    pub(crate) heap_requests: ops::heap::HeapRequests,
    /// SSH connections of Settings › SSH Configurations.
    pub ssh: Arc<ide_ssh::SshManager>,
    /// SFTP deployment, remote file editing and runs on run targets.
@@ -143,6 +148,9 @@ impl Host {
            terminals: TerminalManager::new(),
            processes: ProcessManager::new(),
            debugger: ide_dap::DebugManager::new(languages.clone()),
+            heap: Arc::new(ide_heap::HeapRegistry::new(ide_heap::snapshots_root(&local_data_dir))),
+            heap_windows: Mutex::default(),
+            heap_requests: Default::default(),
            languages,
            syntax,
            config_dir,
@@ -255,6 +263,8 @@ impl Host {
        for request in self.project_requests.write().remove(self.owner_window(window)).unwrap_or_default() {
            self.cancel_request(request);
        }
+        // After the cancels: a capture or open still running then discards what it registers.
+        ops::heap::close_window_snapshots(self, window);
        let project = self.projects.write().remove(window)?;
        if self.windows_for_root(&project.root).is_empty()
            && let Some(plugins) = self.plugin_host()
@@ -405,9 +415,12 @@ impl Host {
        }
    }

-    /// Stops what this host started: notebook kernels, language servers, agents, runs and terminals.
+    /// Stops what this host started: heap snapshots, notebook kernels, language servers, agents,
+    /// runs and terminals.
    /// For a process that exits without dropping the host (the remote server).
    pub async fn shutdown(&self) {
+        // A capture's dump may hold secrets from the debuggee's memory: delete it before exiting.
+        ops::heap::shutdown(self).await;
        self.environment.shutdown();
        self.processes.kill_all();
        self.terminals.kill_all();
@@ -51,7 +51,12 @@ impl Call {
    pub async fn ask(&self, request: ide_core::event::McpUiRequest) -> IdeResult<()> {
        self.host.mcp_requests.ask(self, request).await
    }
+    /// Asks the user before a tool changes the project or starts a process, unless brave mode
+    /// is on — read from the IDE's own settings only, which a project's settings can't set.
    pub async fn confirm(&self, subject: &str, detail: Option<String>) -> IdeResult<()> {
+        if self.host.global_settings.effective().mcp_server.run_without_confirmation {
+            return self.project.require_trust();
+        }
        self.ask(ide_core::event::McpUiRequest::Confirm {
            client: self.client.clone(),
            tool: self.tool.clone(),
@@ -45,26 +45,12 @@ fn innermost_repo<T>(repos: Vec<(PathBuf, T)>, path: &Path) -> Option<(PathBuf,
 // Read tools must never invoke repository-configured executables, including in Restricted Mode.
 fn read_command(git: &str, root: &Path) -> std::process::Command {
    let mut command = std::process::Command::new(git);
+    ide_vcs::restrict(&mut command);
    command
        .current_dir(root)
-        .args([
-            "-c",
-            "core.fsmonitor=false",
-            "-c",
-            "core.hooksPath=",
-            "-c",
-            "diff.external=",
-            "-c",
-            "core.attributesFile=",
-            "-c",
-            "submodule.recurse=false",
-            "-c",
-            "color.ui=false",
-        ])
-        .env("GIT_NO_LAZY_FETCH", "1")
+        .args(["-c", "color.ui=false"])
        .env("GIT_TERMINAL_PROMPT", "0")
        .env("GIT_OPTIONAL_LOCKS", "0")
-        .env_remove("GIT_EXTERNAL_DIFF")
        .env_remove("GIT_DIR")
        .env_remove("GIT_WORK_TREE")
        .env_remove("GIT_INDEX_FILE");
@@ -72,6 +58,32 @@ fn read_command(git: &str, root: &Path) -> std::process::Command {
    command
 }

+/// `-c` arguments that empty the clean and process filters the repository's own config names:
+/// git runs them to compare a changed file with the index. Filters of the user's config stay
+/// (Git LFS), as they are not the repository's choice.
+fn filter_overrides(git: &str, root: &Path) -> IdeResult<Vec<String>> {
+    let mut cmd = read_command(git, root);
+    cmd.args(["config", "--null", "--list", "--show-scope"]);
+    let out = cmd.output().map_err(|e| IdeError::unavailable(format!("cannot run git: {e}")))?;
+    if !out.status.success() {
+        return Err(IdeError::internal(String::from_utf8_lossy(&out.stderr).trim().to_owned()));
+    }
+    repository_filter_overrides(&out.stdout)
+}
+
+/// [`filter_overrides`] out of `listing`, the output of `git config --null --list --show-scope`.
+fn repository_filter_overrides(listing: &[u8]) -> IdeResult<Vec<String>> {
+    let mut fields = listing.split(|b| *b == 0);
+    let mut own = Vec::new();
+    while let (Some(scope), Some(record)) = (fields.next(), fields.next()) {
+        if matches!(scope, b"local" | b"worktree") {
+            own.extend_from_slice(record);
+            own.push(0);
+        }
+    }
+    ide_vcs::filter_overrides_from(&own)
+}
+
 /// The branch HEAD is on (unborn too); `None` when HEAD is detached or git fails.
 fn read_branch(git: &str, root: &Path) -> Option<String> {
    let mut cmd = read_command(git, root);
@@ -167,7 +179,10 @@ fn git_executable(call: &Call) -> String {
 /// `git status` of the repository at `root`, paths relative to it.
 fn read_status(git: &str, root: &Path, untracked: bool, ignored: bool) -> IdeResult<Vec<StatusEntry>> {
    let mut cmd = read_command(git, root);
+    cmd.args(filter_overrides(git, root)?);
    cmd.args(["-c", "core.quotepath=false", "status", "--porcelain", "-z", "--find-renames"]);
+    // git asks a submodule with changes for its own status, which runs under the submodule's config.
+    cmd.arg("--ignore-submodules=dirty");
    // git refuses `--ignored=matching` with `--untracked-files=no`: untracked files are dropped below.
    cmd.arg(if untracked || ignored { "--untracked-files=all" } else { "--untracked-files=no" });
    if ignored {
@@ -183,6 +198,39 @@ fn read_status(git: &str, root: &Path, untracked: bool, ignored: bool) -> IdeRes
    Ok(entries)
 }

+/// `git diff` of the repository at `root` (of `file` alone, when given): the index against HEAD
+/// when `staged`, else disk against the index.
+fn read_diff(
+    git: &str,
+    root: &Path,
+    file: Option<&Path>,
+    staged: bool,
+    cancel: &ide_core::CancellationToken,
+) -> IdeResult<String> {
+    let mut cmd = read_command(git, root);
+    cmd.args(filter_overrides(git, root)?);
+    cmd.args(["--no-pager", "diff", "--no-ext-diff", "--no-textconv"]);
+    // git asks a submodule with changes for its own status, and for its own diff when the
+    // repository's `diff.submodule` says so: both run under the submodule's config.
+    cmd.args(["--ignore-submodules=dirty", "--submodule=short"]);
+    if staged {
+        cmd.arg("--cached");
+    }
+    cmd.arg("--");
+    if let Some(file) = file {
+        cmd.arg(file.strip_prefix(root).map_err(|e| IdeError::invalid(e.to_string()))?);
+    }
+    ide_core::process::prepare(&mut cmd);
+    if cancel.is_cancelled() {
+        return Err(IdeError::cancelled());
+    }
+    let out = cmd.output()?;
+    if !out.status.success() {
+        return Err(IdeError::unavailable(String::from_utf8_lossy(&out.stderr).trim()));
+    }
+    Ok(String::from_utf8_lossy(&out.stdout).into_owned())
+}
+
 /// A git repository in the project, for paths outside the repositories IDEA knows: the
 /// closest folder with `.git` from `start` up to the project root.
 fn find_git_root(root: &Path, start: &Path) -> Option<PathBuf> {
@@ -307,18 +355,7 @@ fn git_diff() -> Tool {
        let staged = call.flag("staged", false)?;
        let git = git_executable(&call);
        let cancel = call.cancel.clone();
-        let text = call.host.blocking(move || {
-            let mut cmd = read_command(&git, &root);
-            cmd.args(["--no-pager", "diff", "--no-ext-diff", "--no-textconv"]);
-            if staged { cmd.arg("--cached"); }
-            cmd.arg("--");
-            if let Some(file) = file { cmd.arg(file.strip_prefix(&root).map_err(|e| IdeError::invalid(e.to_string()))?); }
-            ide_core::process::prepare(&mut cmd);
-            if cancel.is_cancelled() { return Err(IdeError::cancelled()); }
-            let out = cmd.output()?;
-            if !out.status.success() { return Err(IdeError::unavailable(String::from_utf8_lossy(&out.stderr).trim())); }
-            Ok(String::from_utf8_lossy(&out.stdout).into_owned())
-        }).await?;
+        let text = call.host.blocking(move || read_diff(&git, &root, file.as_deref(), staged, &cancel)).await?;
        Ok(Output::text(text))
    })
    .param(Param::optional("repositoryPathRelativeToProject", ParamType::String, "Select the containing repository"))
@@ -342,6 +379,252 @@ mod tests {
        assert!(e[3].conflicted() && !e[3].staged() && !e[3].unstaged());
    }

+    /// Security audit lead 2 (variant): reading status or a diff must not run the repository's filters.
+    #[test]
+    fn status_and_diff_do_not_run_repository_filters() {
+        let dir = tempfile::tempdir().unwrap();
+        let root = dunce::canonicalize(dir.path()).unwrap();
+        let git = |args: &[&str]| {
+            let out = std::process::Command::new("git").current_dir(&root).args(args).output().unwrap();
+            assert!(out.status.success(), "git {args:?}: {}", String::from_utf8_lossy(&out.stderr));
+        };
+        git(&["init", "-q"]);
+        git(&["config", "user.email", "[email protected]"]);
+        git(&["config", "user.name", "t"]);
+        git(&["config", "commit.gpgsign", "false"]);
+        std::fs::write(root.join(".gitattributes"), "*.txt filter=marker\n").unwrap();
+        std::fs::write(root.join("a.txt"), "one\n").unwrap();
+        git(&["add", "."]);
+        git(&["commit", "-qm", "init"]);
+        git(&["config", "filter.marker.clean", "echo x > executed-marker; cat"]);
+        git(&["config", "filter.marker.process", "echo x > executed-marker; cat"]);
+        git(&["config", "filter.marker.required", "true"]);
+        let marker = root.join("executed-marker");
+        let mut ran = Vec::new();
+        // The size it has in the index, so git has to read the file to tell whether it changed.
+        std::fs::write(root.join("a.txt"), "two\n").unwrap();
+        let status = read_status("git", &root, false, false);
+        if marker.exists() {
+            ran.push("status");
+        }
+        let _ = std::fs::remove_file(&marker);
+        std::fs::write(root.join("a.txt"), "one\ntwo\nthree\n").unwrap();
+        let diff = read_diff("git", &root, None, false, &ide_core::CancellationToken::new());
+        if marker.exists() {
+            ran.push("diff");
+        }
+        // Control: the fixture's filter really runs when git is used directly.
+        let _ = std::fs::remove_file(&marker);
+        std::fs::write(root.join("a.txt"), "six\n").unwrap();
+        let _ = std::process::Command::new("git").current_dir(&root).args(["status", "--porcelain"]).output();
+        assert!(marker.exists(), "control: plain `git status` did not run the filter, fixture is not live");
+        assert!(ran.is_empty(), "a read tool ran the repository's filter via: {ran:?}");
+        assert_eq!(status.unwrap().len(), 1);
+        let diff = diff.unwrap();
+        assert!(diff.contains("+three"), "{diff}");
+    }
+
+    #[test]
+    fn only_filters_of_the_repository_s_own_config_are_emptied() {
+        let listing = b"system\0filter.lfs.clean\ngit-lfs clean -- %f\0\
+            global\0filter.lfs.process\ngit-lfs filter-process\0\
+            global\0filter.lfs.required\ntrue\0\
+            local\0core.bare\nfalse\0\
+            local\0filter.a.clean\nx\0\
+            worktree\0filter.b.process\ny\0\
+            local\0filter.a.required\ntrue\0\
+            command\0filter.c.clean\nz\0";
+        assert_eq!(
+            repository_filter_overrides(listing).unwrap(),
+            ["-c", "filter.a.clean=", "-c", "filter.b.process=", "-c", "filter.a.required=false"]
+        );
+    }
+
+    fn git(dir: &Path, args: &[&str]) {
+        let out = std::process::Command::new("git").current_dir(dir).args(args).output().unwrap();
+        assert!(out.status.success(), "git {args:?}: {}", String::from_utf8_lossy(&out.stderr));
+    }
+
+    /// A repository at `dir` with `a.txt` committed.
+    fn repository(dir: &Path, attributes: &[u8]) {
+        std::fs::create_dir_all(dir).unwrap();
+        git(dir, &["init", "-q"]);
+        git(dir, &["config", "user.email", "[email protected]"]);
+        git(dir, &["config", "user.name", "t"]);
+        git(dir, &["config", "commit.gpgsign", "false"]);
+        std::fs::write(dir.join(".gitattributes"), attributes).unwrap();
+        std::fs::write(dir.join("a.txt"), "one\n").unwrap();
+        git(dir, &["add", "."]);
+        git(dir, &["commit", "-qm", "init"]);
+    }
+
+    /// A shell command that leaves `marker` behind and passes its input on.
+    fn leaves(marker: &Path) -> String {
+        format!("echo x > '{}'; cat", marker.to_string_lossy().replace('\\', "/"))
+    }
+
+    /// Whether a program of the fixture left `marker` behind; removes it.
+    fn left(marker: &Path) -> bool {
+        let was = marker.exists();
+        let _ = std::fs::remove_file(marker);
+        was
+    }
+
+    /// Reads the status and then the diff of `root` after rewriting `file`, then has plain git
+    /// read the status as a control. Each write keeps the size the file has in the index, so git
+    /// has to read it to tell whether it changed.
+    fn read_both(root: &Path, file: &Path, marker: &Path) -> (IdeResult<Vec<StatusEntry>>, IdeResult<String>) {
+        let mut ran = Vec::new();
+        std::fs::write(file, "two\n").unwrap();
+        let status = read_status("git", root, false, false);
+        if left(marker) {
+            ran.push("status");
+        }
+        std::fs::write(file, "six\n").unwrap();
+        let diff = read_diff("git", root, None, false, &ide_core::CancellationToken::new());
+        if left(marker) {
+            ran.push("diff");
+        }
+        std::fs::write(file, "ten\n").unwrap();
+        let _ = std::process::Command::new("git").current_dir(root).args(["status", "--porcelain"]).output();
+        assert!(left(marker), "control: plain `git status` ran no program of the fixture, it is not live");
+        assert!(ran.is_empty(), "a read tool ran a program of the repository via: {ran:?}");
+        (status, diff)
+    }
+
+    #[test]
+    fn status_and_diff_do_not_run_filters_of_any_repository_config() {
+        type Configure = fn(&Path, &str);
+        let cases: [(&str, Configure); 4] = [
+            ("clean", |root, command| git(root, &["config", "filter.marker.clean", command])),
+            ("process", |root, command| git(root, &["config", "filter.marker.process", command])),
+            ("included file", |root, command| {
+                let included = format!("[filter \"marker\"]\n\tclean = \"{command}\"\n");
+                std::fs::write(root.join("extra.gitconfig"), included).unwrap();
+                git(root, &["config", "include.path", "../extra.gitconfig"]);
+            }),
+            ("worktree config", |root, command| {
+                git(root, &["config", "extensions.worktreeConfig", "true"]);
+                git(root, &["config", "--worktree", "filter.marker.clean", command]);
+            }),
+        ];
+        for (case, configure) in cases {
+            let dir = tempfile::tempdir().unwrap();
+            let root = dunce::canonicalize(dir.path()).unwrap().join("repo");
+            let marker = root.with_file_name("marker");
+            repository(&root, b"*.txt filter=marker\n");
+            configure(&root, &leaves(&marker));
+            let (status, diff) = read_both(&root, &root.join("a.txt"), &marker);
+            assert_eq!(status.unwrap().len(), 1, "{case}");
+            let diff = diff.unwrap();
+            assert!(diff.contains("+six"), "{case}: {diff}");
+        }
+    }
+
+    /// git splits `-c name=value` at the first `=` and takes no name that is not UTF-8 on every
+    /// platform, so such a filter cannot be emptied: the tools read nothing instead.
+    #[test]
+    fn status_and_diff_refuse_a_repository_filter_git_cannot_be_told_to_skip() {
+        for name in [&b"x=y"[..], &[0xE9]] {
+            let dir = tempfile::tempdir().unwrap();
+            let root = dunce::canonicalize(dir.path()).unwrap().join("repo");
+            let marker = root.with_file_name("marker");
+            repository(&root, &[b"*.txt filter=", name, b"\n"].concat());
+            let section =
+                [b"[filter \"", name, format!("\"]\n\tclean = \"{}\"\n", leaves(&marker)).as_bytes()].concat();
+            let config = root.join(".git").join("config");
+            std::fs::write(&config, [std::fs::read(&config).unwrap(), section].concat()).unwrap();
+            let (status, diff) = read_both(&root, &root.join("a.txt"), &marker);
+            assert!(status.is_err() && diff.is_err(), "{name:?}");
+        }
+    }
+
+    /// git asks a submodule for its own status to tell whether it is dirty, under the
+    /// submodule's config.
+    #[test]
+    fn status_and_diff_do_not_run_filters_of_a_submodule() {
+        let dir = tempfile::tempdir().unwrap();
+        let root = dunce::canonicalize(dir.path()).unwrap().join("repo");
+        let (sub, marker) = (root.join("sub"), root.with_file_name("marker"));
+        repository(&root, b"");
+        repository(&sub, b"*.txt filter=marker\n");
+        git(&root, &["add", "sub"]);
+        git(&root, &["commit", "-qm", "submodule"]);
+        git(&sub, &["config", "filter.marker.clean", &leaves(&marker)]);
+        git(&root, &["config", "diff.ignoreSubmodules", "none"]);
+        git(&root, &["config", "submodule.sub.ignore", "none"]);
+        let (status, diff) = read_both(&root, &sub.join("a.txt"), &marker);
+        status.unwrap();
+        diff.unwrap();
+    }
+
+    /// `git diff` writes the index back when it finds a file whose stat changed and whose content
+    /// did not, and git runs the hooks a config names for `post-index-change` on that write.
+    #[test]
+    fn status_and_diff_do_not_run_hooks_of_the_repository_s_config() {
+        let dir = tempfile::tempdir().unwrap();
+        let root = dunce::canonicalize(dir.path()).unwrap().join("repo");
+        let marker = root.with_file_name("marker");
+        repository(&root, b"");
+        git(&root, &["config", "hook.marker.event", "post-index-change"]);
+        let command = format!("echo x > '{}'", marker.to_string_lossy().replace('\\', "/"));
+        git(&root, &["config", "hook.marker.command", &command]);
+        let listed = std::process::Command::new("git")
+            .current_dir(&root)
+            .args(["hook", "list", "post-index-change"])
+            .output()
+            .unwrap();
+        if !String::from_utf8_lossy(&listed.stdout).contains("marker") {
+            return; // This git has no hooks named by a config.
+        }
+        // The content it has in the index, with a time of its own that is not the index's.
+        let touch = |seconds: u64| {
+            let file = std::fs::File::options().write(true).open(root.join("a.txt")).unwrap();
+            file.set_modified(std::time::SystemTime::now() - std::time::Duration::from_secs(seconds)).unwrap();
+        };
+        let mut ran = Vec::new();
+        touch(60);
+        let status = read_status("git", &root, false, false);
+        if left(&marker) {
+            ran.push("status");
+        }
+        touch(120);
+        let diff = read_diff("git", &root, None, false, &ide_core::CancellationToken::new());
+        if left(&marker) {
+            ran.push("diff");
+        }
+        touch(180);
+        let _ = std::process::Command::new("git").current_dir(&root).args(["--no-pager", "diff"]).output();
+        assert!(left(&marker), "control: plain `git diff` did not run the hook, fixture is not live");
+        assert!(ran.is_empty(), "a read tool ran a hook of the repository's config via: {ran:?}");
+        assert!(status.unwrap().is_empty());
+        assert_eq!(diff.unwrap(), "");
+    }
+
+    /// `diff.submodule=diff` has git run `git diff` in the submodule, under the submodule's config.
+    #[test]
+    fn diff_does_not_run_a_diff_driver_of_a_submodule() {
+        let dir = tempfile::tempdir().unwrap();
+        let root = dunce::canonicalize(dir.path()).unwrap().join("repo");
+        let (sub, marker) = (root.join("sub"), root.with_file_name("marker"));
+        repository(&root, b"");
+        repository(&sub, b"*.txt diff=marker\n");
+        git(&root, &["add", "sub"]);
+        git(&root, &["commit", "-qm", "submodule"]);
+        std::fs::write(sub.join("a.txt"), "one\ntwo\n").unwrap();
+        git(&sub, &["commit", "-qam", "second"]);
+        git(&sub, &["config", "diff.marker.command", &leaves(&marker)]);
+        git(&root, &["config", "diff.submodule", "diff"]);
+        let diff = read_diff("git", &root, None, false, &ide_core::CancellationToken::new());
+        let ran = left(&marker);
+        let _ = std::process::Command::new("git").current_dir(&root).args(["--no-pager", "diff"]).output();
+        assert!(left(&marker), "control: plain `git diff` did not run the diff driver, fixture is not live");
+        assert!(!ran, "git_diff ran the submodule's diff driver");
+        let diff = diff.unwrap();
+        assert!(diff.contains("Subproject commit"), "{diff}");
+        assert_eq!(read_status("git", &root, false, false).unwrap().len(), 1);
+    }
+
    #[cfg(unix)]
    #[test]
    fn paths_through_a_symlinked_root_compare_canonically() {
@@ -5,8 +5,9 @@ use crate::Host;
 use crate::rpc::Dispatcher;
 use ide_agent::registry::{AgentRegistry, RegistryPaths};
 use ide_agent::{
-    AgentChange, AgentCommand, AgentEntry, AgentEvent, AgentProbe, AgentPrompt, AgentProvider, AgentQueued, AgentTask,
-    ExternalSession, McpScope, McpServer, McpServerInput, NewAgentTask,
+    AcpImportOutcome, AgentAcceptOutcome, AgentChange, AgentCommand, AgentEntry, AgentEvent, AgentProbe, AgentPrompt,
+    AgentProvider, AgentQueued, AgentTask, CustomAgentInput, ExternalSession, McpScope, McpServer, McpServerInput,
+    NewAgentTask,
 };
 use ide_core::error::ErrorKind;
 use ide_core::{IdeError, IdeEvent, IdeResult, IpcPath, RequestId, SharedSink, TaskId};
@@ -44,6 +45,24 @@ pub fn set_env(
    host.project(window)?.agents.set_builtin_env(&id, env)
 }

+/// Saves a new custom ACP agent through its agent file.
+pub fn save_custom_agent(host: &Host, window: &str, input: CustomAgentInput) -> IdeResult<()> {
+    host.require_trust(window)?;
+    host.project(window)?.agents.save_custom_agent(input)
+}
+
+/// Removes a custom agent's file (registry installs go through `registry_remove`).
+pub fn remove_custom_agent(host: &Host, window: &str, id: String) -> IdeResult<()> {
+    host.require_trust(window)?;
+    host.project(window)?.agents.remove_custom_agent(&id)
+}
+
+/// Imports a JetBrains `acp.json` file's `agent_servers` entries as custom agents.
+pub fn import_acp_agents(host: &Host, window: &str, text: String) -> IdeResult<Vec<AcpImportOutcome>> {
+    host.require_trust(window)?;
+    host.project(window)?.agents.import_acp_agents(&text)
+}
+
 /// Where ACP Registry agents are saved (`<config>/agents`, like the user's own) and installed.
 pub(crate) fn registry_paths(host: &Host) -> RegistryPaths {
    RegistryPaths::new(&host.config_dir, &host.local_data_dir)
@@ -181,15 +200,18 @@ pub fn entries(host: &Host, window: &str, task: String, subagent: Option<String>
    host.project(window)?.agents.entries(&task, subagent)
 }

-/// Sessions on this machine that no task holds yet, newest first (#312).
-pub fn external_sessions(host: &Host, window: &str) -> IdeResult<Vec<ExternalSession>> {
-    Ok(host.project(window)?.agents.external_sessions())
+/// Sessions of the project on this machine that no task holds yet, newest first. Reads
+/// transcripts from disk on the blocking pool.
+pub async fn external_sessions(host: &Host, window: &str) -> IdeResult<Vec<ExternalSession>> {
+    let agents = host.project(window)?.agents.clone();
+    tokio::task::spawn_blocking(move || agents.external_sessions()).await.map_err(join_err)
 }

-/// Imports an external session as a task: its first turn loads and replays it (#312).
-pub fn import_session(host: &Host, window: &str, provider: String, session_id: String) -> IdeResult<AgentTask> {
+/// Imports an external session as a task: its first turn loads and replays it.
+pub async fn import_session(host: &Host, window: &str, provider: String, session_id: String) -> IdeResult<AgentTask> {
    host.require_trust(window)?;
-    host.project(window)?.agents.import_session(&provider, &session_id)
+    let agents = host.project(window)?.agents.clone();
+    tokio::task::spawn_blocking(move || agents.import_session(&provider, &session_id)).await.map_err(join_err)?
 }

 pub async fn create(host: &Host, window: &str, mut request: NewAgentTask) -> IdeResult<AgentTask> {
@@ -294,6 +316,18 @@ pub async fn rollback_changes(host: &Host, window: &str, task: String, paths: Op
    host.project(window)?.agents.rollback_changes(&task, paths).await
 }

+/// Accept: copies a worktree task's changed files among `paths` (all without) into the
+/// local checkout, uncommitted; files the checkout changed itself are left alone and reported.
+pub async fn accept_changes(
+    host: &Host,
+    window: &str,
+    task: String,
+    paths: Option<Vec<String>>,
+) -> IdeResult<AgentAcceptOutcome> {
+    host.require_trust(window)?;
+    host.project(window)?.agents.accept_changes(&task, paths).await
+}
+
 type McpServerMap = std::collections::BTreeMap<String, ide_core::settings::AgentMcpServer>;

 fn mcp_maps(host: &Host, window: &str) -> (McpServerMap, McpServerMap, Option<std::sync::Arc<crate::Project>>) {
@@ -409,9 +443,9 @@ pub(crate) fn register(d: &mut Dispatcher) {
    d.add("agent_commands", |c| async move { commands(&c.host, &c.window, c.arg("provider")?, c.arg("task")?).await });
    d.add("agent_entries", |c| async move { entries(&c.host, &c.window, c.arg("task")?, c.arg("subagent")?) });
    d.add("agent_create", |c| async move { create(&c.host, &c.window, c.arg("request")?).await });
-    d.add("agent_external_sessions", |c| async move { external_sessions(&c.host, &c.window) });
+    d.add("agent_external_sessions", |c| async move { external_sessions(&c.host, &c.window).await });
    d.add("agent_import_session", |c| async move {
-        import_session(&c.host, &c.window, c.arg("provider")?, c.arg("sessionId")?)
+        import_session(&c.host, &c.window, c.arg("provider")?, c.arg("sessionId")?).await
    });
    d.add("agent_prompt", |c| async move {
        prompt(&c.host, &c.window, c.arg("task")?, c.arg("prompt")?, c.arg("now")?).await
@@ -446,6 +480,9 @@ pub(crate) fn register(d: &mut Dispatcher) {
    d.add("agent_rollback_changes", |c| async move {
        rollback_changes(&c.host, &c.window, c.arg("task")?, c.arg("paths")?).await
    });
+    d.add("agent_accept_changes", |c| async move {
+        accept_changes(&c.host, &c.window, c.arg("task")?, c.arg("paths")?).await
+    });
 }

 fn validate_project_root(root: &std::path::Path, requested: Option<&std::path::Path>) -> IdeResult<std::path::PathBuf> {
@@ -17,9 +17,11 @@ pub async fn fs_read_range(_host: &Host, _window: &str, path: PathBuf, offset: u
    blocking(move || ide_vfs::read_range(&path, offset, len)).await
 }

-/// An image file as a `data:` URL.
-pub async fn fs_read_image(_host: &Host, _window: &str, path: PathBuf) -> IdeResult<String> {
-    blocking(move || ide_vfs::read_data_url(&path)).await
+/// An image file as a `data:` URL. A network path is read only from a share an open project is
+/// on: the path may come from Markdown, and opening a share signs in to its server.
+pub async fn fs_read_image(host: &Host, _window: &str, path: PathBuf) -> IdeResult<String> {
+    let opened: Vec<PathBuf> = host.projects().iter().map(|project| project.root.clone()).collect();
+    blocking(move || ide_vfs::read_data_url(&path, &opened)).await
 }

 /// Commands of this module the remote server answers.
@@ -1,3 +1,6 @@
+mod kotlin;
+#[cfg(test)]
+mod kotlin_tests;
 mod output;

 use crate::Host;
@@ -41,6 +44,7 @@ pub async fn debug_start(host: &Host, window: &str, config: LaunchConfig) -> Ide
            })
            .await?;
    }
+    config = kotlin::choose_kotlin_debugger(host, window, config).await?;
    if config.adapter == ide_dap::kotlin::ADAPTER {
        let data_dir = host.local_data_dir.clone();
        let runtime_root = config.cwd.clone().map(PathBuf::from).unwrap_or_default();
@@ -0,0 +1,415 @@
+//! Kotlin debugging: kotlin-lsp's debugger when the project's kotlin-lsp can serve it, else
+//! kotlin-debug-adapter with a notice saying why.
+
+use crate::Host;
+use ide_core::event::NotifyLevel;
+use ide_core::task::CancelHandle;
+use ide_core::{CancellationToken, IdeEvent, IdeResult, SharedSink, TaskId};
+use ide_dap::LaunchConfig;
+use ide_lsp::{KotlinDebugServer, KotlinDebugUnavailable};
+use parking_lot::Mutex;
+use std::collections::HashSet;
+use std::future::Future;
+use std::path::PathBuf;
+use std::time::Duration;
+
+pub(super) const KOTLIN_IMPORT_WAIT: Duration = Duration::from_secs(120);
+/// A ready kotlin-lsp answers well within this; only a longer wait shows a task.
+const TASK_DELAY: Duration = Duration::from_millis(500);
+
+// Catalogued as written (`{detail}` replaced at runtime): the text catalog test counts these
+// literals as the use of its entries.
+const TASK_TITLE: &str = "Waiting for kotlin-lsp to import the project";
+const NOTICE_TITLE: &str = "Debugging Kotlin with kotlin-debug-adapter";
+const NOT_CONFIGURED: &str = "kotlin-lsp is not the Kotlin language server of this project.";
+const NOT_INSTALLED: &str = "kotlin-lsp is not installed.";
+const NOT_STARTED: &str = "kotlin-lsp did not start: {detail}";
+const STILL_IMPORTING: &str =
+    "kotlin-lsp is still importing the project. Debug again once the import has finished to use its debugger.";
+const IMPORT_FAILED: &str = "kotlin-lsp could not import the project.";
+const FAILED: &str = "kotlin-lsp could not start its debugger: {detail}";
+
+/// `config` for kotlin-lsp's debug server on `port`; the rest of the launch stays as it is.
+pub(super) fn use_kotlin_lsp(mut config: LaunchConfig, port: u16) -> IdeResult<LaunchConfig> {
+    let mut extra = extra_object(&config)?;
+    extra.insert("debugServer".into(), port.into());
+    config.adapter = ide_dap::kotlin_lsp::ADAPTER.into();
+    config.extra_json = Some(serde_json::Value::Object(extra).to_string());
+    Ok(config)
+}
+
+/// The dedupe key of `reason` and the notice body (English, translated by the UI's catalog).
+pub(super) fn fallback_notice(reason: &KotlinDebugUnavailable) -> (&'static str, String) {
+    match reason {
+        KotlinDebugUnavailable::NotConfigured => ("notConfigured", NOT_CONFIGURED.into()),
+        KotlinDebugUnavailable::NotInstalled => ("notInstalled", NOT_INSTALLED.into()),
+        KotlinDebugUnavailable::NotStarted(detail) => ("notStarted", NOT_STARTED.replace("{detail}", detail)),
+        KotlinDebugUnavailable::StillImporting => ("stillImporting", STILL_IMPORTING.into()),
+        KotlinDebugUnavailable::ImportFailed => ("importFailed", IMPORT_FAILED.into()),
+        KotlinDebugUnavailable::Failed(detail) => ("failed", FAILED.replace("{detail}", detail)),
+    }
+}
+
+/// A kotlin-debug-adapter launch becomes a kotlin-lsp one when the project's kotlin-lsp has
+/// imported the module and started its debug server; otherwise it stays on
+/// kotlin-debug-adapter and the window is told why (once per reason).
+pub(super) async fn choose_kotlin_debugger(host: &Host, window: &str, config: LaunchConfig) -> IdeResult<LaunchConfig> {
+    if config.adapter == ide_dap::kotlin_lsp::ADAPTER {
+        require_debug_server(&config)?;
+        return Ok(config);
+    }
+    if config.adapter != ide_dap::kotlin::ADAPTER {
+        return Ok(config);
+    }
+    let Ok(project) = host.project(window) else {
+        tracing::info!(
+            "debugging Kotlin with kotlin-debug-adapter: {}",
+            fallback_notice(&KotlinDebugUnavailable::NotConfigured).1
+        );
+        return Ok(config);
+    };
+    let path = debug_path(&config).unwrap_or_else(|| project.root.clone());
+    let lsp = project.lsp.clone();
+    let chosen = wait_for_debug_server(&project.sink, |cancel| async move {
+        lsp.kotlin_debug_server(&path, KOTLIN_IMPORT_WAIT, &cancel).await
+    })
+    .await;
+    match chosen {
+        Ok(server) => use_kotlin_lsp(config, server.port),
+        Err(reason) => {
+            report_fallback(&project.kotlin_debug_notices, &project.sink, &reason);
+            Ok(config)
+        }
+    }
+}
+
+/// kotlin-lsp is only reached through the port its language server opened; without one
+/// ide-dap would try to spawn a `kotlin-lsp` adapter that does not exist.
+fn require_debug_server(config: &LaunchConfig) -> IdeResult<()> {
+    match extra_object(config)?.get("debugServer") {
+        None | Some(serde_json::Value::Null) => Err(ide_core::IdeError::invalid(
+            "A kotlin-lsp debug configuration needs \"debugServer\": the port of kotlin-lsp's debug server. \
+             Use kotlin-debug-adapter to let the IDE start it.",
+        )),
+        Some(_) => Ok(()),
+    }
+}
+
+fn extra_object(config: &LaunchConfig) -> IdeResult<serde_json::Map<String, serde_json::Value>> {
+    match config.extra_json.as_deref().map(serde_json::from_str).transpose() {
+        Ok(None) => Ok(serde_json::Map::new()),
+        Ok(Some(serde_json::Value::Object(extra))) => Ok(extra),
+        Ok(Some(other)) => Err(ide_core::IdeError::invalid(format!("launch arguments are not an object: {other}"))),
+        Err(e) => Err(ide_core::IdeError::invalid(e.to_string())),
+    }
+}
+
+/// The module to debug: the launch's `projectRoot`, else its working directory.
+fn debug_path(config: &LaunchConfig) -> Option<PathBuf> {
+    let extra: Option<serde_json::Value> = config.extra_json.as_deref().and_then(|e| serde_json::from_str(e).ok());
+    extra
+        .as_ref()
+        .and_then(|e| e.get("projectRoot")?.as_str())
+        .filter(|root| !root.is_empty())
+        .map(PathBuf::from)
+        .or_else(|| config.cwd.as_deref().map(PathBuf::from))
+}
+
+/// Runs `debug_server` with a token the user can cancel; a wait longer than [`TASK_DELAY`]
+/// shows as a cancellable task, which ends however the wait does (also when dropped).
+async fn wait_for_debug_server<F, Fut>(
+    sink: &SharedSink,
+    debug_server: F,
+) -> Result<KotlinDebugServer, KotlinDebugUnavailable>
+where
+    F: FnOnce(CancellationToken) -> Fut,
+    Fut: Future<Output = Result<KotlinDebugServer, KotlinDebugUnavailable>>,
+{
+    let cancel = CancellationToken::new();
+    let id = TaskId::next();
+    let handle = ide_core::task::on_cancel(id, {
+        let cancel = cancel.clone();
+        move || cancel.cancel()
+    });
+    let wait = debug_server(cancel);
+    tokio::pin!(wait);
+    if let Ok(answer) = tokio::time::timeout(TASK_DELAY, &mut wait).await {
+        return answer;
+    }
+    let _task = WaitTask::start(sink.clone(), id, handle);
+    wait.await
+}
+
+/// The visible import wait; dropping it ends the task.
+struct WaitTask {
+    sink: SharedSink,
+    id: TaskId,
+    _cancel: CancelHandle,
+}
+
+impl WaitTask {
+    fn start(sink: SharedSink, id: TaskId, cancel: CancelHandle) -> Self {
+        let task = Self { sink, id, _cancel: cancel };
+        task.emit(false);
+        task
+    }
+
+    fn emit(&self, done: bool) {
+        self.sink.emit(IdeEvent::Task {
+            id: self.id,
+            title: TASK_TITLE.into(),
+            message: None,
+            fraction: None,
+            done,
+            cancellable: !done,
+        });
+    }
+}
+
+impl Drop for WaitTask {
+    fn drop(&mut self) {
+        self.emit(true);
+    }
+}
+
+/// Logs every fallback; notifies the window once per reason.
+fn report_fallback(notices: &Mutex<HashSet<&'static str>>, sink: &SharedSink, reason: &KotlinDebugUnavailable) {
+    let (key, body) = fallback_notice(reason);
+    tracing::info!("debugging Kotlin with kotlin-debug-adapter: {body}");
+    if notices.lock().insert(key) {
+        sink.emit(IdeEvent::Notify { level: NotifyLevel::Info, title: NOTICE_TITLE.into(), body: Some(body) });
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::path::Path;
+    use std::sync::Arc;
+
+    fn launch(adapter: &str, extra: serde_json::Value) -> LaunchConfig {
+        LaunchConfig {
+            name: "AppKt".into(),
+            adapter: adapter.into(),
+            request: "launch".into(),
+            program: None,
+            args: vec![],
+            cwd: Some("/cwd".into()),
+            env: Default::default(),
+            extra_json: Some(extra.to_string()),
+        }
+    }
+
+    fn extra(config: &LaunchConfig) -> serde_json::Value {
+        serde_json::from_str(config.extra_json.as_deref().unwrap()).unwrap()
+    }
+
+    fn reasons() -> Vec<KotlinDebugUnavailable> {
+        vec![
+            KotlinDebugUnavailable::NotConfigured,
+            KotlinDebugUnavailable::NotInstalled,
+            KotlinDebugUnavailable::NotStarted("needs JDK 21".into()),
+            KotlinDebugUnavailable::StillImporting,
+            KotlinDebugUnavailable::ImportFailed,
+            KotlinDebugUnavailable::Failed("boom".into()),
+        ]
+    }
+
+    fn recording_sink() -> (SharedSink, Arc<Mutex<Vec<IdeEvent>>>) {
+        let events = Arc::new(Mutex::new(Vec::new()));
+        let recorded = events.clone();
+        (Arc::new(move |event| recorded.lock().push(event)), events)
+    }
+
+    /// `(done, cancellable)` of each task event, with the task id.
+    fn tasks(events: &Mutex<Vec<IdeEvent>>) -> Vec<(ide_core::TaskId, String, bool, bool)> {
+        events
+            .lock()
+            .iter()
+            .filter_map(|e| match e {
+                IdeEvent::Task { id, title, done, cancellable, .. } => Some((*id, title.clone(), *done, *cancellable)),
+                _ => None,
+            })
+            .collect()
+    }
+
+    fn server() -> KotlinDebugServer {
+        KotlinDebugServer { port: 4711, root: PathBuf::from("/p") }
+    }
+
+    #[test]
+    fn kotlin_lsp_takes_the_debug_server_port() {
+        let config = launch(ide_dap::kotlin::ADAPTER, serde_json::json!({"mainClass": "a.AppKt", "projectRoot": "/p"}));
+        let c = use_kotlin_lsp(config, 4711).unwrap();
+        assert_eq!(c.adapter, ide_dap::kotlin_lsp::ADAPTER);
+        let args = extra(&c);
+        assert_eq!(args["debugServer"], 4711);
+        assert_eq!(args["mainClass"], "a.AppKt");
+        assert_eq!(args["projectRoot"], "/p");
+        assert!(args.get("__adapterJavaHome").is_none());
+        assert_eq!(
+            (c.name.as_str(), c.request.as_str(), c.cwd.as_deref()),
+            ("AppKt", "launch", Some(Path::new("/cwd")))
+        );
+        let mut bare = launch(ide_dap::kotlin::ADAPTER, serde_json::json!({}));
+        bare.extra_json = None;
+        assert_eq!(extra(&use_kotlin_lsp(bare, 4711).unwrap())["debugServer"], 4711);
+    }
+
+    #[test]
+    fn every_fallback_reason_has_a_catalogued_text() {
+        let catalogs: [(&str, serde_json::Value); 2] = [
+            ("en", serde_json::from_str(include_str!("../../../../../src/platform/locales/text/en.json")).unwrap()),
+            ("zh", serde_json::from_str(include_str!("../../../../../src/platform/locales/text/zh.json")).unwrap()),
+        ];
+        let templates = [NOT_CONFIGURED, NOT_INSTALLED, NOT_STARTED, STILL_IMPORTING, IMPORT_FAILED, FAILED];
+        for reason in reasons() {
+            let (_, body) = fallback_notice(&reason);
+            let detail = match &reason {
+                KotlinDebugUnavailable::NotStarted(d) | KotlinDebugUnavailable::Failed(d) => d.as_str(),
+                _ => "",
+            };
+            assert!(
+                templates.iter().any(|t| t.replace("{detail}", detail) == body),
+                "{reason:?}: {body:?} is not built from a catalogued template"
+            );
+        }
+        for text in templates.iter().chain([&NOTICE_TITLE, &TASK_TITLE]) {
+            for (locale, catalog) in &catalogs {
+                let translated = catalog[*text].as_str().unwrap_or_else(|| panic!("{locale}.json lacks {text:?}"));
+                if *locale == "zh" {
+                    assert_ne!(translated, *text, "zh.json leaves {text:?} untranslated");
+                }
+            }
+        }
+    }
+
+    #[test]
+    fn fallback_reasons_have_distinct_keys() {
+        let keys: HashSet<_> = reasons().iter().map(|r| fallback_notice(r).0).collect();
+        assert_eq!(keys.len(), reasons().len());
+        // The detail does not make another reason.
+        assert_eq!(
+            fallback_notice(&KotlinDebugUnavailable::Failed("a".into())).0,
+            fallback_notice(&KotlinDebugUnavailable::Failed("b".into())).0
+        );
+    }
+
+    #[test]
+    fn a_kotlin_lsp_config_without_a_debug_server_is_refused() {
+        let refused = require_debug_server(&launch(ide_dap::kotlin_lsp::ADAPTER, serde_json::json!({}))).unwrap_err();
+        assert_eq!(refused.kind, ide_core::error::ErrorKind::InvalidInput);
+        assert!(refused.message.contains("debugServer"), "{}", refused.message);
+        let mut bare = launch(ide_dap::kotlin_lsp::ADAPTER, serde_json::json!({}));
+        bare.extra_json = None;
+        assert!(require_debug_server(&bare).is_err());
+        assert!(
+            require_debug_server(&launch(ide_dap::kotlin_lsp::ADAPTER, serde_json::json!({"debugServer": null})))
+                .is_err()
+        );
+        for port in [serde_json::json!(4711), serde_json::json!("10.0.0.5:4711")] {
+            require_debug_server(&launch(ide_dap::kotlin_lsp::ADAPTER, serde_json::json!({"debugServer": port})))
+                .unwrap();
+        }
+    }
+
+    #[test]
+    fn the_module_is_the_project_root_else_the_working_directory() {
+        let with_root = launch(ide_dap::kotlin::ADAPTER, serde_json::json!({"projectRoot": "/p/app"}));
+        assert_eq!(debug_path(&with_root), Some(PathBuf::from("/p/app")));
+        assert_eq!(debug_path(&launch(ide_dap::kotlin::ADAPTER, serde_json::json!({}))), Some(PathBuf::from("/cwd")));
+        let mut neither = launch(ide_dap::kotlin::ADAPTER, serde_json::json!({}));
+        neither.cwd = None;
+        assert_eq!(debug_path(&neither), None);
+    }
+
+    #[tokio::test(start_paused = true)]
+    async fn a_quick_answer_shows_no_task() {
+        let (sink, events) = recording_sink();
+        assert_eq!(wait_for_debug_server(&sink, |_| async { Ok(server()) }).await, Ok(server()));
+        assert!(events.lock().is_empty());
+    }
+
+    #[tokio::test(start_paused = true)]
+    async fn a_longer_wait_shows_a_task_that_ends_on_every_outcome() {
+        for outcome in [Ok(server()), Err(KotlinDebugUnavailable::ImportFailed)] {
+            let (sink, events) = recording_sink();
+            let answer = outcome.clone();
+            let result = wait_for_debug_server(&sink, |_| async move {
+                tokio::time::sleep(Duration::from_secs(5)).await;
+                answer
+            })
+            .await;
+            assert_eq!(result, outcome);
+            let tasks = tasks(&events);
+            assert_eq!(tasks.len(), 2, "{tasks:?}");
+            assert_eq!(tasks[0].0, tasks[1].0);
+            assert_eq!(tasks[0].1, TASK_TITLE);
+            assert_eq!((tasks[0].2, tasks[0].3), (false, true));
+            assert_eq!((tasks[1].2, tasks[1].3), (true, false));
+        }
+    }
+
+    #[tokio::test(start_paused = true)]
+    async fn cancelling_the_task_stops_the_wait() {
+        let (sink, events) = recording_sink();
+        let wait = tokio::spawn(async move {
+            wait_for_debug_server(&sink, |cancel| async move {
+                cancel.cancelled().await;
+                Err(KotlinDebugUnavailable::StillImporting)
+            })
+            .await
+        });
+        tokio::time::sleep(Duration::from_secs(1)).await;
+        let id = tasks(&events)[0].0;
+        assert!(ide_core::task::cancel(id));
+        assert_eq!(wait.await.unwrap(), Err(KotlinDebugUnavailable::StillImporting));
+        assert_eq!(tasks(&events).last().map(|t| t.2), Some(true));
+        assert!(!ide_core::task::cancel(id), "an ended wait is no longer cancellable");
+    }
+
+    #[tokio::test(start_paused = true)]
+    async fn a_dropped_wait_ends_its_task() {
+        let (sink, events) = recording_sink();
+        let wait = tokio::spawn(async move {
+            wait_for_debug_server(&sink, |_| std::future::pending::<Result<KotlinDebugServer, _>>()).await
+        });
+        tokio::time::sleep(Duration::from_secs(1)).await;
+        wait.abort();
+        let _ = wait.await;
+        assert_eq!(tasks(&events).iter().map(|t| t.2).collect::<Vec<_>>(), [false, true]);
+    }
+
+    #[test]
+    fn the_notice_shows_once_per_reason() {
+        let (sink, events) = recording_sink();
+        let notices = Mutex::new(HashSet::new());
+        for reason in [
+            KotlinDebugUnavailable::StillImporting,
+            KotlinDebugUnavailable::StillImporting,
+            KotlinDebugUnavailable::NotStarted("needs JDK 21".into()),
+            KotlinDebugUnavailable::NotStarted("crashed".into()),
+        ] {
+            report_fallback(&notices, &sink, &reason);
+        }
+        let notes: Vec<_> = events
+            .lock()
+            .iter()
+            .map(|e| match e {
+                IdeEvent::Notify { level, title, body } => (*level, title.clone(), body.clone()),
+                other => panic!("{other:?}"),
+            })
+            .collect();
+        assert_eq!(
+            notes,
+            [
+                (NotifyLevel::Info, NOTICE_TITLE.to_string(), Some(STILL_IMPORTING.to_string())),
+                (
+                    NotifyLevel::Info,
+                    NOTICE_TITLE.to_string(),
+                    Some("kotlin-lsp did not start: needs JDK 21".to_string())
+                ),
+            ]
+        );
+    }
+}