fix(agent): branch on a dedicated-summarizer flag instead of comparing providers

Review follow-ups for #532:

- summarizeProvider now reports whether the dedicated summarizer was
  selected and summarizeClosure branches on that flag; the previous
  `chosen == provider` compared Provider interface values, which panics
  when the dynamic type is not comparable. Regression test uses a provider
  with a slice field for both the summarizer and the main provider.
- CompactionModelID's curated-default test covers the official OpenAI
  profile alongside Anthropic and Google.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

.release-please-manifest.json

@@ -1 +1 @@
-{".":"0.7.0"}
+{".":"0.8.0"}

AGENTS.md

@@ -111,3 +111,42 @@ These classes drive multi-round reviews. Fix them before requesting review:
   shipped. Wire advertised entry points or shrink the claim. Do not bundle
   unrelated fixes. Do not widen security allowlists by name alone; check
   classification and side effects too.
+- **Host tool version floors:** Zero shells out to `git` and other host tools,
+  and the project does not declare a minimum version for any of them. A flag,
+  subcommand, or config key that is not long-established therefore raises that
+  floor silently, and the failure on an older host is an unhelpful usage error
+  rather than a clear message. Before adding one, check when it landed and say
+  so where a caller would look. Record the floor for the exact subcommand you
+  call, not for the flag in general: `--end-of-options` reached Git's shared
+  parser in 2.24, but `git rev-parse` only accepted it from 2.30, and
+  `git checkout` and `git reset` later still. Likewise `--show-current` is
+  `git branch` 2.22, and `branch.autoSetupMerge=inherit` is 2.35. Then either
+  keep a fallback for older versions or gate the call. A test that depends on a
+  newer feature must skip below its floor instead of failing, and say which
+  version it needs.
+- **Prove the test fails without the change:** A regression test earns its
+  place only if it fails on the unfixed code, for the reason it claims. Run it
+  both ways and quote the failure in the PR. The recurring miss is not a
+  missing test but a test that never reaches the behavior it names, because an
+  earlier guard rejects the input first, so it passes with and without the fix.
+  When a test targets a specific layer, call that layer directly rather than
+  relying on a public entry point that may refuse earlier.
+- **Hermetic tests:** Tests must not read or write the developer's real config,
+  cache, or state directories. Redirect every root the code under test
+  resolves, not just config. `os.UserConfigDir` and `os.UserCacheDir` read
+  `XDG_CONFIG_HOME` and `XDG_CACHE_HOME` only on Linux and the BSDs. On macOS
+  they derive from `HOME`, and on Windows from `%AppData%` and `%LocalAppData%`.
+  Setting the XDG variables alone still leaves a macOS run writing to the real
+  home, so set `HOME` as well, or take the directory as a parameter. Apply it to
+  every test that reaches the same storage, not only the one where it was first
+  needed; a test that passes on a clean machine and pollutes a real one is a
+  blocker.
+- **Error codes vary by platform and by flag combination:** A check written
+  against the code one target returns can be silently inert on another while
+  still looking correct. `openat(O_DIRECTORY|O_NOFOLLOW)` on a symlink may
+  report `ENOTDIR` or `ELOOP` depending on the platform, because the kernel can
+  reject the directory mismatch before it ever resolves the link; accept both
+  rather than assuming the one POSIX names. On Windows, `\\?\` and `\\.\`
+  prefixes are not UNC paths, and an `NtCreateFile` information class must match
+  the struct actually passed. Confirm the code each supported target returns
+  instead of reasoning from the man page.

CHANGELOG.md

@@ -6,6 +6,27 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 aims to follow [Semantic Versioning](https://semver.org/spec/v2.0.0.html) once the first release is
 tagged. Until then, source builds report the version `dev`.
 
+## [0.8.0](https://github.com/Gitlawb/zero/compare/v0.7.0...v0.8.0) (2026-08-21)
+
+
+### Features
+
+* **security:** path-jail primitive, credential-store locking, worktree git hardening ([#891](https://github.com/Gitlawb/zero/issues/891)) ([060d38c](https://github.com/Gitlawb/zero/commit/060d38ce716feb7c5b6657b082cd35cb8dda3d75))
+* **update:** recognise Homebrew installs and add mise, go install docs ([#910](https://github.com/Gitlawb/zero/issues/910)) ([01c3498](https://github.com/Gitlawb/zero/commit/01c3498205e69d26e5f929225f9455b276444f39))
+* use Exa as default search provider ([#926](https://github.com/Gitlawb/zero/issues/926)) ([1ec7219](https://github.com/Gitlawb/zero/commit/1ec7219aee7b2840481ab0905f131644e27d2a4e))
+* **zerogit:** auto-create a conventional branch before push/pr on default branch ([#671](https://github.com/Gitlawb/zero/issues/671)) ([d065467](https://github.com/Gitlawb/zero/commit/d065467cd3ec3ed91c5dc60554c36fc4b4d6de4c))
+
+
+### Bug Fixes
+
+* **acp:** three defects a desktop ACP client hits ([#915](https://github.com/Gitlawb/zero/issues/915)) ([a78c6c3](https://github.com/Gitlawb/zero/commit/a78c6c357e1d21146d7cd2e8030a754e06f7f1f5))
+* bump Go to 1.26.6 for stdlib vulnerability fixes ([#903](https://github.com/Gitlawb/zero/issues/903)) ([dc15e82](https://github.com/Gitlawb/zero/commit/dc15e822987d8d7de467c62c375518f435b74d8c))
+* **daemon:** clean up child after startup timeout ([#774](https://github.com/Gitlawb/zero/issues/774)) ([9c29209](https://github.com/Gitlawb/zero/commit/9c292092a26c9092fd873d072b0af1b0d9d39ef0))
+* **dictation:** redact API keys from streaming transcriber errors ([#852](https://github.com/Gitlawb/zero/issues/852)) ([64a783b](https://github.com/Gitlawb/zero/commit/64a783b08caa2c7b21f188033b9ed84a14e00e84))
+* **modelregistry:** expose reasoning effort for DeepSeek V4 models ([#931](https://github.com/Gitlawb/zero/issues/931)) ([90dcfd1](https://github.com/Gitlawb/zero/commit/90dcfd127e8a6d9902ec9f4e72f6d03fef1a0fc6))
+* **providers:** discover ChatGPT capabilities ([#890](https://github.com/Gitlawb/zero/issues/890)) ([2d2450e](https://github.com/Gitlawb/zero/commit/2d2450e9a744349f0d01b1d4e9ba29c24ba5650d))
+* **sandbox:** normalize launcher names before the command-prefix denylist ([#934](https://github.com/Gitlawb/zero/issues/934)) ([6edf9a8](https://github.com/Gitlawb/zero/commit/6edf9a8b78dc030dc44598919db1c7fa9d4f809a))
+
 ## [0.7.0](https://github.com/Gitlawb/zero/compare/v0.6.0...v0.7.0) (2026-08-10)
 
 

README.md

@@ -6,7 +6,7 @@
 
 <p align="center">
   <a href="LICENSE"><img alt="license" src="https://img.shields.io/badge/license-MIT-blue"></a>
-  <img alt="Go 1.26.5+" src="https://img.shields.io/badge/Go-1.26.5+-00ADD8?logo=go&logoColor=white">
+  <img alt="Go 1.26.6+" src="https://img.shields.io/badge/Go-1.26.6+-00ADD8?logo=go&logoColor=white">
   <img alt="25+ providers" src="https://img.shields.io/badge/providers-25+-34E2EA">
   <a href="https://discord.gg/CaQDS6wdFn"><img alt="Discord" src="https://img.shields.io/badge/Discord-join-5865F2?logo=discord&logoColor=white"></a>
   <br>
@@ -76,7 +76,7 @@ irm https://raw.githubusercontent.com/Gitlawb/zero/main/scripts/install.ps1 | ie
 
 ### From source
 
-Source builds require Go 1.26.5+.
+Source builds require Go 1.26.6+.
 
 ```bash
 git clone https://github.com/Gitlawb/zero.git

README_ZH.md

@@ -6,7 +6,7 @@
 
 <p align="center">
   <a href="LICENSE"><img alt="license" src="https://img.shields.io/badge/license-MIT-blue"></a>
-  <img alt="Go 1.26.5+" src="https://img.shields.io/badge/Go-1.26.5+-00ADD8?logo=go&logoColor=white">
+  <img alt="Go 1.26.6+" src="https://img.shields.io/badge/Go-1.26.6+-00ADD8?logo=go&logoColor=white">
   <img alt="25+ providers" src="https://img.shields.io/badge/providers-25+-34E2EA">
   <a href="https://discord.gg/CaQDS6wdFn"><img alt="Discord" src="https://img.shields.io/badge/Discord-join-5865F2?logo=discord&logoColor=white"></a>
   <br>
@@ -57,7 +57,7 @@ irm https://raw.githubusercontent.com/Gitlawb/zero/main/scripts/install.ps1 | ie
 
 ### 从源码构建
 
-源码构建需要 Go 1.26.5+。
+源码构建需要 Go 1.26.6+。
 
 ```bash
 git clone https://github.com/Gitlawb/zero.git

SECURITY.md

@@ -33,4 +33,4 @@ Please include, where possible:
   depend on a user explicitly disabling the sandbox (`--skip-permissions-unsafe`), are generally
   out of scope — but please report anything you are unsure about.
 - Zero sends no telemetry. Network calls go to the model/tool providers you configure (and, for
-  keyless web search, to the documented Firecrawl endpoint — see the README).
+  keyless web search, to Exa's hosted MCP endpoint at `https://mcp.exa.ai/mcp`).

docs/INSTALL.md

@@ -1,14 +1,30 @@
 # Installing Zero
 
-Zero is distributed as:
+Pick whichever fits how you already install things. None of these is the
+blessed one.
 
-- an npm package, `@gitlawb/zero`
-- release archives on GitHub Releases
-- source builds with Go 1.26.5+
+| Method | Command | Self-update |
+| --- | --- | --- |
+| Install script (Linux, macOS) | `curl -fsSL https://raw.githubusercontent.com/Gitlawb/zero/main/scripts/install.sh \| bash` | `zero upgrade` |
+| Install script (Windows) | `irm https://raw.githubusercontent.com/Gitlawb/zero/main/scripts/install.ps1 \| iex` | `zero upgrade` |
+| npm | `npm install -g @gitlawb/zero` | `zero upgrade` (runs npm) |
+| Release archive | download from [Releases](https://github.com/Gitlawb/zero/releases) | `zero upgrade` |
+| mise | `mise use -g ubi:Gitlawb/zero` | `mise upgrade` |
+| `go install` | `go install github.com/Gitlawb/zero/cmd/zero@latest` | rerun the command |
+| Source | `go build -o zero ./cmd/zero` | rebuild |
 
-The install scripts download a platform-specific release archive and require a
-published GitHub Release for the requested version. The npm package is
-self-contained: the platform binary installs from the npm registry.
+`zero upgrade` follows whatever owns the binary, with one exception it cannot
+detect. It delegates to npm for an npm install, refuses outright for a Homebrew
+keg and names `brew upgrade zero`, and replaces the binary in place for
+everything else — including a mise-managed one, which is the exception.
+
+mise is the one case it cannot detect: a mise-managed binary is an ordinary
+standalone install on disk, so `zero upgrade` will replace it and leave mise
+describing a version that is no longer there. Use `mise upgrade` instead.
+
+Release archives are the substrate for most of the above: the install scripts
+and the npm fallback both download a platform archive from a published GitHub
+Release and verify its checksum.
 
 ## npm
 
@@ -111,6 +127,45 @@ Defaults:
 - Version: latest GitHub release
 - Install path: `%LOCALAPPDATA%\zero\bin\zero.exe`
 
+## mise
+
+[mise](https://mise.jdx.dev/) installs Zero straight from the GitHub Release
+archives through its `ubi` backend, so there is nothing extra to publish and no
+registry in the middle:
+
+```bash
+mise use -g ubi:Gitlawb/zero
+```
+
+Pin a version the same way you would any other tool:
+
+```bash
+mise use -g ubi:Gitlawb/[email protected]
+```
+
+Updates come from `mise upgrade`. `zero upgrade` also works, because a
+mise-managed binary is an ordinary standalone install, but then mise's records
+describe a version that is no longer on disk. Prefer `mise upgrade`.
+
+## go install
+
+```bash
+go install github.com/Gitlawb/zero/cmd/zero@latest
+```
+
+This builds from source, so it needs Go 1.26.6+ and it does not go through the
+release archives. Two consequences worth knowing before you pick it:
+
+- On Linux you also need the sandbox helper, which is a separate binary and is
+  not installed by this command. See
+  [Sandbox Helpers For Source Builds](#sandbox-helpers-for-source-builds).
+  Without it, native sandboxing is unavailable.
+- `zero upgrade` treats the result as a standalone install and will replace the
+  binary with a release build rather than rebuilding from source. If you chose
+  `go install` deliberately, rerun it instead.
+
+macOS and Windows need no extra helper.
+
 ## From Source
 
 ```bash
@@ -125,7 +180,7 @@ Build a local binary:
 go build -o zero ./cmd/zero
 ```
 
-Source builds require Go 1.26.5+.
+Source builds require Go 1.26.6+.
 
 ### Sandbox Helpers For Source Builds
 
@@ -242,3 +297,23 @@ zero upgrade
 ```
 
 See the [update guide](UPDATE.md) for update modes, flags, and platform details.
+
+`zero upgrade` behaves differently depending on how Zero was installed, because
+overwriting a binary a package manager owns leaves that manager describing a
+version that is no longer there:
+
+- **npm**: runs `npm install -g @gitlawb/zero@latest` for you.
+- **Homebrew**: refuses, and tells you to run `brew upgrade zero`. Replacing the
+  keg binary directly would be reverted by the next `brew upgrade` or
+  `brew reinstall`.
+- **everything else**: downloads the verified release archive and replaces the
+  binary in place.
+
+Homebrew is detected by the binary living inside a Cellar keg that carries
+Homebrew's own `INSTALL_RECEIPT.json`. The keg shape alone is not enough: a
+directory tree you built yourself can have exactly that shape, and refusing to
+update an install Homebrew never touched would be a real cost for a made-up
+reason. The receipt is the thing only Homebrew writes.
+
+An ordinary install under `/usr/local/bin` is left alone even on an Intel Mac
+where that is also the Homebrew prefix.

internal/acp/agent.go

@@ -296,6 +296,16 @@ func stopReasonFor(result agent.Result, err error) (string, error) {
 		if errors.Is(err, context.Canceled) {
 			return StopCancelled, nil
 		}
+		// A CLIENT THAT CANCELLED A PERMISSION PROMPT DID NOT FAIL. Only
+		// context.Canceled was matched here, so dismissing a permission dialog —
+		// a deliberate action, and for apply_patch the only refusal a client is
+		// offered — came back as JSON-RPC -32603 carrying the internal sentinel
+		// text. Editors and the desktop app both render that as a crashed turn,
+		// so declining a tool looked like ZERO falling over. It is a
+		// cancellation, and StopCancelled is what ACP has for saying so.
+		if errors.Is(err, agent.ErrPermissionApprovalCanceled) {
+			return StopCancelled, nil
+		}
 		return "", err
 	}
 	if result.FinishReason == "length" {
@@ -311,10 +321,14 @@ func stopReasonFor(result agent.Result, err error) (string, error) {
 // session/request_permission request and maps the outcome back. Failure to reach
 // the client fails closed to deny.
 func (a *Agent) requestPermission(ctx context.Context, sessionID string, req agent.PermissionRequest) (agent.PermissionDecision, error) {
+	// Built ONCE and used for both halves. Sending one list and validating the
+	// reply against another is the defect this whole path had; see
+	// decisionFromOutcome.
+	options := buildPermissionOptions(req)
 	params := RequestPermissionParams{
 		SessionID: sessionID,
 		ToolCall:  permissionToolCall(req),
-		Options:   buildPermissionOptions(req),
+		Options:   options,
 	}
 	var result RequestPermissionResult
 	if err := a.conn.Call(ctx, MethodSessionRequestPerm, params, &result); err != nil {
@@ -323,7 +337,7 @@ func (a *Agent) requestPermission(ctx context.Context, sessionID string, req age
 		}
 		return agent.PermissionDecision{Action: agent.PermissionDecisionDeny, Reason: "permission request failed: " + err.Error()}, nil
 	}
-	return decisionFromOutcome(result.Outcome, req.AvailableDecisions), nil
+	return decisionFromOutcome(result.Outcome, options), nil
 }
 
 func (a *Agent) emitPlan(registry *tools.Registry, note *notifier) {

internal/acp/desktopinterop_test.go

@@ -0,0 +1,217 @@
+package acp
+
+// desktopinterop_test.go covers three defects found by driving the real `zero
+// acp` binary from a desktop ACP client. Each is a case where ZERO and a
+// conforming client disagreed about the wire, and none of them failed loudly —
+// they produced a silent denial, a spurious crash, or two buttons the user
+// could not tell apart.
+//
+// A fourth, session/load restoring history without replaying it, is fixed by
+// #914 rather than here: that one also gives the replayed messages stable ids
+// and keeps session/resume replay-free, which this did not.
+
+import (
+	"errors"
+	"fmt"
+	"testing"
+
+	"github.com/Gitlawb/zero/internal/agent"
+)
+
+// ---- an offered option is an acceptable answer ----
+
+// The list the options were BUILT from and the list the answer was CHECKED
+// against were different whenever ZERO did not enumerate: the client was sent
+// Allow and Reject, and its reply was validated against an empty slice, so
+// every button it could possibly show failed closed to deny. The user clicked
+// Allow and ZERO recorded a denial, with nothing on screen to say so.
+func TestAnOfferedOptionIsAccepted(t *testing.T) {
+	// No AvailableDecisions: the fallback path, which is every permission event
+	// that is not a prompt.
+	req := agent.PermissionRequest{ToolName: "bash"}
+
+	options := buildPermissionOptions(req)
+	if len(options) == 0 {
+		t.Fatal("no options were offered")
+	}
+
+	for _, option := range options {
+		decision := decisionFromOutcome(
+			RequestPermissionOutcome{Outcome: OutcomeSelected, OptionID: option.OptionID},
+			buildPermissionOptions(req),
+		)
+		if string(decision.Action) != option.OptionID {
+			t.Fatalf("option %q was answered with %q (%s) — an offered option must be accepted",
+				option.OptionID, decision.Action, decision.Reason)
+		}
+	}
+}
+
+// The narrowing this validation exists for still holds: a client must not be
+// able to return a broader grant than it was shown.
+func TestAnOptionThatWasNotOfferedIsStillRefused(t *testing.T) {
+	req := agent.PermissionRequest{ToolName: "bash"}
+
+	decision := decisionFromOutcome(
+		RequestPermissionOutcome{Outcome: OutcomeSelected, OptionID: string(agent.PermissionDecisionAlwaysAllow)},
+		buildPermissionOptions(req),
+	)
+	if decision.Action != agent.PermissionDecisionDeny {
+		t.Fatalf("an unoffered broader grant was accepted as %q", decision.Action)
+	}
+}
+
+// The resolver is the single source of truth for both sides, which is what
+// makes the two agree by construction rather than by being kept in step.
+func TestOfferedDecisionsMatchWhatWasSent(t *testing.T) {
+	for _, req := range []agent.PermissionRequest{
+		{ToolName: "bash"},
+		{ToolName: "bash", AvailableDecisions: []agent.PermissionDecisionAction{
+			agent.PermissionDecisionAllow,
+			agent.PermissionDecisionAllowForSession,
+			agent.PermissionDecisionDeny,
+		}},
+	} {
+		offered := buildPermissionOptions(req)
+		for _, option := range buildPermissionOptions(req) {
+			if !actionOffered(option.OptionID, offered) {
+				t.Fatalf("option %q was sent but is not in the offered set %v", option.OptionID, offered)
+			}
+		}
+	}
+}
+
+// ---- two options the user can tell apart ----
+
+// request_permissions offers plain allow and strict-review allow together, and
+// both were labelled "Allow". The label is the only thing an ACP client shows,
+// so the panel presented two identical buttons where one silently enabled
+// strict auto-review of what was granted.
+func TestEveryOfferedOptionHasADistinctLabel(t *testing.T) {
+	req := agent.PermissionRequest{
+		ToolName: "request_permissions",
+		AvailableDecisions: []agent.PermissionDecisionAction{
+			agent.PermissionDecisionAllow,
+			agent.PermissionDecisionAllowStrict,
+			agent.PermissionDecisionAllowForSession,
+			agent.PermissionDecisionDeny,
+		},
+	}
+
+	seen := map[string]string{}
+	for _, option := range buildPermissionOptions(req) {
+		if previous, clash := seen[option.Name]; clash {
+			t.Fatalf("options %q and %q share the label %q — a user cannot tell them apart",
+				previous, option.OptionID, option.Name)
+		}
+		seen[option.Name] = option.OptionID
+	}
+}
+
+// The two remain distinct decisions: the label changed, the round trip did not.
+func TestStrictAllowStillRoundTrips(t *testing.T) {
+	req := agent.PermissionRequest{
+		ToolName: "request_permissions",
+		AvailableDecisions: []agent.PermissionDecisionAction{
+			agent.PermissionDecisionAllow,
+			agent.PermissionDecisionAllowStrict,
+		},
+	}
+	decision := decisionFromOutcome(
+		RequestPermissionOutcome{Outcome: OutcomeSelected, OptionID: string(agent.PermissionDecisionAllowStrict)},
+		buildPermissionOptions(req),
+	)
+	if decision.Action != agent.PermissionDecisionAllowStrict {
+		t.Fatalf("strict allow round-tripped as %q", decision.Action)
+	}
+}
+
+// ---- cancelling a permission is a cancellation, not a crash ----
+
+// Only context.Canceled was recognised, so dismissing a permission dialog came
+// back as JSON-RPC -32603 carrying the internal sentinel text. Clients render
+// that as a failed turn, so declining a tool looked like ZERO falling over —
+// and for apply_patch, dismissing is the ONLY refusal a client is offered.
+func TestCancellingAPermissionEndsTheTurnAsCancelled(t *testing.T) {
+	canceled := fmt.Errorf("%w for apply_patch", agent.ErrPermissionApprovalCanceled)
+
+	reason, err := stopReasonFor(agent.Result{}, canceled)
+	if err != nil {
+		t.Fatalf("stopReasonFor returned an error for a cancellation: %v", err)
+	}
+	if reason != StopCancelled {
+		t.Fatalf("stop reason = %q, want %q", reason, StopCancelled)
+	}
+}
+
+// A genuine failure must still be an error. Mapping too much to cancelled would
+// hide real faults behind a clean ending, which is the opposite mistake.
+func TestARealFailureIsStillAnError(t *testing.T) {
+	failure := errors.New("provider exploded")
+
+	if _, err := stopReasonFor(agent.Result{}, failure); !errors.Is(err, failure) {
+		t.Fatalf("stopReasonFor(%v) = %v, want the failure preserved", failure, err)
+	}
+}
+
+// The sentinel is matched through errors.Is, so it survives the wrapping every
+// return site applies — each one adds the tool name.
+func TestPermissionCancellationSurvivesWrapping(t *testing.T) {
+	if !errors.Is(fmt.Errorf("%w for bash", agent.ErrPermissionApprovalCanceled), agent.ErrPermissionApprovalCanceled) {
+		t.Fatal("a wrapped permission cancellation was not recognised")
+	}
+	if errors.Is(errors.New("something else"), agent.ErrPermissionApprovalCanceled) {
+		t.Fatal("an unrelated error was reported as a permission cancellation")
+	}
+}
+
+// A decision that never became an option cannot be selected.
+//
+// PermissionDecisionCancel is the case that exists today: optionKindFor drops
+// it because ACP expresses cancellation through the outcome, yet ZERO
+// enumerates it in AvailableDecisions for shell commands and apply_patch. While
+// the reply was validated against the DECISIONS rather than the sent options, a
+// client could return {"outcome":"selected","optionId":"cancel"} — an id it was
+// never shown — and abort the whole turn.
+//
+// Written over every option-less decision rather than over "cancel", so a
+// future action that optionKindFor declines to render is covered the day it is
+// added rather than the day someone remembers this test.
+func TestADecisionThatIsNotAnOptionCannotBeSelected(t *testing.T) {
+	for _, toolName := range []string{"bash", "apply_patch"} {
+		req := agent.PermissionRequest{
+			ToolName: toolName,
+			AvailableDecisions: []agent.PermissionDecisionAction{
+				agent.PermissionDecisionAllow,
+				agent.PermissionDecisionDeny,
+				agent.PermissionDecisionCancel,
+			},
+		}
+		options := buildPermissionOptions(req)
+
+		for _, action := range req.AvailableDecisions {
+			if actionOffered(string(action), options) {
+				continue // it was sent; selecting it is legitimate
+			}
+			decision := decisionFromOutcome(
+				RequestPermissionOutcome{Outcome: OutcomeSelected, OptionID: string(action)},
+				options,
+			)
+			if decision.Action != agent.PermissionDecisionDeny {
+				t.Fatalf("%s: %q was never sent as an option but was accepted as %q",
+					toolName, action, decision.Action)
+			}
+		}
+	}
+}
+
+// Cancelling is still reachable — through the outcome, which is where ACP puts
+// it. Closing the selected-id route must not close the real one.
+func TestCancellingThroughTheOutcomeStillWorks(t *testing.T) {
+	options := buildPermissionOptions(agent.PermissionRequest{ToolName: "apply_patch"})
+
+	decision := decisionFromOutcome(RequestPermissionOutcome{Outcome: OutcomeCancelled}, options)
+	if decision.Action != agent.PermissionDecisionCancel {
+		t.Fatalf("outcome=cancelled gave %q, want cancel", decision.Action)
+	}
+}

internal/acp/permission.go

@@ -15,14 +15,7 @@ import (
 // PermissionOptions. Only the actions ZERO actually presented (AvailableDecisions)
 // are surfaced; the optionId is the ZERO action string for a clean round-trip.
 func buildPermissionOptions(req agent.PermissionRequest) []PermissionOption {
-	actions := req.AvailableDecisions
-	if len(actions) == 0 {
-		// Sensible default if ZERO didn't enumerate: allow once / reject.
-		actions = []agent.PermissionDecisionAction{
-			agent.PermissionDecisionAllow,
-			agent.PermissionDecisionDeny,
-		}
-	}
+	actions := offeredDecisions(req)
 	options := make([]PermissionOption, 0, len(actions))
 	for _, action := range actions {
 		kind, name := optionKindFor(action, req.PrefixApprovalEscalates)
@@ -38,6 +31,32 @@ func buildPermissionOptions(req agent.PermissionRequest) []PermissionOption {
 	return options
 }
 
+// offeredDecisions resolves what this request actually offers the client.
+//
+// ONE RESOLVER, USED BY BOTH SIDES, and that is the entire point of it existing.
+// The fallback below used to live inside buildPermissionOptions while
+// requestPermission validated the client's answer against the raw
+// req.AvailableDecisions. When ZERO did not enumerate — which is every
+// permission event that is not a prompt, and includes a shell call whose sandbox
+// decision came back deny — the two disagreed completely: the client was sent
+// "Allow" and "Reject", and validation was performed against an EMPTY list, so
+// every option the client could possibly click failed closed to deny with
+// "permission option was not offered".
+//
+// The user clicked Allow and ZERO recorded a denial. Nothing surfaced it,
+// because a denial is a legitimate answer — the tool was simply refused and the
+// turn carried on as though the user had rejected it.
+func offeredDecisions(req agent.PermissionRequest) []agent.PermissionDecisionAction {
+	if len(req.AvailableDecisions) > 0 {
+		return req.AvailableDecisions
+	}
+	// Sensible default if ZERO didn't enumerate: allow once / reject.
+	return []agent.PermissionDecisionAction{
+		agent.PermissionDecisionAllow,
+		agent.PermissionDecisionDeny,
+	}
+}
+
 // optionKindFor maps a ZERO decision action to an ACP PermissionOptionKind and a
 // human label. Returns an empty kind for actions that ACP expresses through the
 // outcome rather than an option (cancel).
@@ -49,8 +68,16 @@ func buildPermissionOptions(req agent.PermissionRequest) []PermissionOption {
 // disclosure cannot be TUI-only.
 func optionKindFor(action agent.PermissionDecisionAction, escalates bool) (kind, name string) {
 	switch action {
-	case agent.PermissionDecisionAllow, agent.PermissionDecisionAllowStrict:
+	case agent.PermissionDecisionAllow:
 		return PermAllowOnce, "Allow"
+	case agent.PermissionDecisionAllowStrict:
+		// SPLIT FROM PLAIN ALLOW because the label is the only thing an ACP
+		// client shows. Both were labelled "Allow", and request_permissions
+		// offers them together — so the panel presented two identical buttons,
+		// and whichever the user picked looked the same while one of them
+		// silently turned on strict auto-review of what was granted. The option
+		// id carries no room for the distinction, so it has to be in the name.
+		return PermAllowOnce, "Allow with strict review"
 	case agent.PermissionDecisionAllowForSession:
 		return PermAllowAlways, "Allow for this session"
 	case agent.PermissionDecisionAllowPrefix:
@@ -70,19 +97,31 @@ func optionKindFor(action agent.PermissionDecisionAction, escalates bool) (kind,
 
 // decisionFromOutcome maps the client's permission outcome back to a ZERO
 // decision. A cancelled outcome cancels the run; a selected option id is the ZERO
-// action verbatim (validated against what was offered); anything unrecognized
-// fails closed to deny.
-func decisionFromOutcome(outcome RequestPermissionOutcome, offered []agent.PermissionDecisionAction) agent.PermissionDecision {
+// action verbatim (validated against what was actually sent); anything
+// unrecognized fails closed to deny.
+//
+// IT TAKES THE OPTIONS THAT WERE SENT, not the decisions the request offered,
+// and the two are not the same list. Some actions never become options —
+// PermissionDecisionCancel is dropped by optionKindFor because ACP expresses
+// cancellation through the outcome instead — yet it IS enumerated in
+// AvailableDecisions for shell commands and apply_patch, the two commonest
+// prompts. Validating against the decisions therefore accepted
+// {"outcome":"selected","optionId":"cancel"}: an identifier no client was ever
+// shown, aborting the whole turn.
+//
+// Passing the sent options makes "what we offered" and "what we accept" the
+// same slice rather than two things kept in step, so anything optionKindFor
+// declines to render is excluded structurally instead of by name.
+func decisionFromOutcome(outcome RequestPermissionOutcome, offered []PermissionOption) agent.PermissionDecision {
 	switch outcome.Outcome {
 	case OutcomeCancelled:
 		return agent.PermissionDecision{Action: agent.PermissionDecisionCancel, Reason: "client cancelled"}
 	case OutcomeSelected:
-		action := agent.PermissionDecisionAction(outcome.OptionID)
 		// Bind to what was actually offered for THIS call: a client must not be able
 		// to return a broader grant (always_allow / allow_for_session) that wasn't
 		// presented. Anything not offered fails closed to deny.
-		if actionOffered(action, offered) {
-			return agent.PermissionDecision{Action: action}
+		if actionOffered(outcome.OptionID, offered) {
+			return agent.PermissionDecision{Action: agent.PermissionDecisionAction(outcome.OptionID)}
 		}
 		return agent.PermissionDecision{Action: agent.PermissionDecisionDeny, Reason: "permission option was not offered"}
 	default:
@@ -90,9 +129,9 @@ func decisionFromOutcome(outcome RequestPermissionOutcome, offered []agent.Permi
 	}
 }
 
-func actionOffered(action agent.PermissionDecisionAction, offered []agent.PermissionDecisionAction) bool {
-	for _, a := range offered {
-		if a == action {
+func actionOffered(optionID string, offered []PermissionOption) bool {
+	for _, option := range offered {
+		if option.OptionID == optionID {
 			return true
 		}
 	}

internal/acp/permission_escalation_test.go

@@ -56,10 +56,11 @@ func TestACPPrefixOptionsStaySilentWithoutEscalation(t *testing.T) {
 // what was offered, so decorating it would fail every prefix approval closed.
 func TestACPDisclosureDoesNotDisturbTheOptionIDRoundTrip(t *testing.T) {
 	request := escalationRequest(true)
-	for _, option := range buildPermissionOptions(request) {
+	options := buildPermissionOptions(request)
+	for _, option := range options {
 		decision := decisionFromOutcome(
 			RequestPermissionOutcome{Outcome: OutcomeSelected, OptionID: option.OptionID},
-			request.AvailableDecisions,
+			options,
 		)
 		if string(decision.Action) != option.OptionID {
 			t.Errorf("option id %q round-tripped to %q (%s)", option.OptionID, decision.Action, decision.Reason)

internal/acp/permission_test.go

@@ -39,11 +39,14 @@ func TestBuildPermissionOptionsDefault(t *testing.T) {
 }
 
 func TestDecisionFromOutcome(t *testing.T) {
-	offered := []agent.PermissionDecisionAction{
-		agent.PermissionDecisionAllow,
-		agent.PermissionDecisionAlwaysAllow,
-		agent.PermissionDecisionDeny,
-	}
+	offered := buildPermissionOptions(agent.PermissionRequest{
+		ToolName: "bash",
+		AvailableDecisions: []agent.PermissionDecisionAction{
+			agent.PermissionDecisionAllow,
+			agent.PermissionDecisionAlwaysAllow,
+			agent.PermissionDecisionDeny,
+		},
+	})
 	if d := decisionFromOutcome(RequestPermissionOutcome{Outcome: OutcomeCancelled}, offered); d.Action != agent.PermissionDecisionCancel {
 		t.Errorf("cancelled -> %q, want cancel", d.Action)
 	}

internal/agent/command_prefix_test.go

@@ -99,6 +99,43 @@ func TestProposedCommandPrefixRejectsUnsafeRequestedPrefix(t *testing.T) {
 	}
 }
 
+// The launcher denylist is only worth anything if it holds on the path a user
+// actually sees. A model naming its own prefix_rule is that path: before
+// launcher names were normalized, "python3.11" was offered as a one-token
+// grant, and hasStringPrefix then matched every later python3.11 invocation.
+func TestProposedCommandPrefixRejectsLauncherSpellingsInRequestedPrefix(t *testing.T) {
+	for _, testCase := range []struct {
+		command string
+		rule    []any
+	}{
+		{"python3.11 script.py", []any{"python3.11"}},
+		{"python.exe script.py", []any{"python.exe"}},
+		{"node.exe app.js", []any{"node.exe"}},
+		{"cmd /c whoami", []any{"cmd"}},
+		{"busybox sh -c id", []any{"busybox"}},
+		{"uv run main.py", []any{"uv", "run"}},
+		{"python3.11 -c import_os", []any{"python3.11", "-c"}},
+	} {
+		got := proposedCommandPrefix("bash", map[string]any{
+			"command":     testCase.command,
+			"prefix_rule": testCase.rule,
+		})
+		if got != nil {
+			t.Errorf("prefix_rule %v for %q was offered as %#v, want rejected", testCase.rule, testCase.command, got)
+		}
+	}
+}
+
+func TestProposedCommandPrefixStillOffersOrdinaryCommands(t *testing.T) {
+	got := proposedCommandPrefix("bash", map[string]any{
+		"command":     "cargo build --release",
+		"prefix_rule": []any{"cargo", "build"},
+	})
+	if len(got) != 2 || got[0] != "cargo" || got[1] != "build" {
+		t.Fatalf("ordinary prefix rule = %#v, want [cargo build]", got)
+	}
+}
+
 func TestProposedCommandPrefixRejectsUnsafeShellForms(t *testing.T) {
 	cases := []string{
 		"cat < in > out",

internal/agent/compaction.go

@@ -4,7 +4,9 @@ import (
 	"context"
 	"encoding/json"
 	"errors"
+	"strconv"
 	"strings"
+	"unicode/utf8"
 
 	"github.com/Gitlawb/zero/internal/trace"
 	"github.com/Gitlawb/zero/internal/zeroruntime"
@@ -390,6 +392,27 @@ type compactionState struct {
 	// starts at 1.0 and converges via an EMA as each turn reports actual usage, so
 	// later turns compact nearer to real capacity. Zero is treated as 1.0.
 	calibrationRatio float64
+
+	// summarizerFactory lazily builds the dedicated (cheap) summarizer provider
+	// (Options.Summarizer) for the current main model. summarizerProvider
+	// memoizes the built provider and summarizerResolved records that the
+	// factory ran (it may legitimately return no provider: the main model is
+	// already the cheap one). summarizerBroken is the sticky fallback: once a
+	// build or call fails, the run stays on the main provider until the next
+	// model switch — a misconfigured cheap model must never break (or
+	// repeatedly delay) compaction.
+	summarizerFactory  func(ctx context.Context, mainModelID string) (Provider, error)
+	summarizerProvider Provider
+	summarizerResolved bool
+	summarizerBroken   bool
+	// window is the context window the threshold was derived from. The
+	// reactive free-prune stage compares against it (the limit the provider
+	// enforces), not against the 70% proactive threshold — a pruned history
+	// between the two would still succeed on retry.
+	window int
+	// mainModel is the model the run currently streams on; the summarizer
+	// choice is made against it and remade after a mid-run switch.
+	mainModel string
 }
 
 // calibrate folds one turn's (rawEstimate, actualPromptTokens) sample into the
@@ -424,17 +447,88 @@ func (state *compactionState) calibratedTokens(raw int) int {
 
 func newCompactionState(options Options, task *taskState) *compactionState {
 	state := &compactionState{
-		enabled:      options.ContextWindow > 0,
-		threshold:    compactionThreshold(options.ContextWindow),
-		preserveLast: options.CompactionPreserveLast,
-		onUsage:      options.OnUsage,
-		task:         task,
-		planner:      newContextPlanner(contextPlannerConfig{contextWindow: options.ContextWindow, serviceTier: options.ServiceTier}),
-		trace:        options.Trace,
+		enabled:           options.ContextWindow > 0,
+		threshold:         compactionThreshold(options.ContextWindow),
+		window:            options.ContextWindow,
+		mainModel:         options.Model,
+		preserveLast:      options.CompactionPreserveLast,
+		onUsage:           options.OnUsage,
+		task:              task,
+		planner:           newContextPlanner(contextPlannerConfig{contextWindow: options.ContextWindow, serviceTier: options.ServiceTier}),
+		trace:             options.Trace,
+		summarizerFactory: options.Summarizer,
 	}
 	return state
 }
 
+// updateWindow re-derives the compaction threshold after a mid-run model
+// switch. The low-water mark is reset: it was measured against the old
+// threshold, and keeping it could suppress a compaction the smaller window
+// now requires. <= 0 (unknown model) leaves everything unchanged.
+func (state *compactionState) updateWindow(window int) {
+	if window <= 0 {
+		return
+	}
+	state.enabled = true
+	state.window = window
+	state.threshold = compactionThreshold(window)
+	state.lowWaterMark = 0
+	if state.planner != nil {
+		state.planner.config.contextWindow = window
+	}
+}
+
+// switchModel records a mid-run model switch: the window is re-derived
+// (window <= 0 keeps the old one) and the summarizer choice is forgotten so
+// the next compaction re-resolves it against the new main model. A run that
+// started on the cheap model (no dedicated summarizer) and escalated to an
+// expensive one therefore regains cheap summaries — the exact workflow a
+// dedicated summarizer exists for.
+func (state *compactionState) switchModel(modelID string, window int) {
+	state.mainModel = modelID
+	state.updateWindow(window)
+	state.summarizerProvider = nil
+	state.summarizerResolved = false
+	state.summarizerBroken = false
+}
+
+// summarizeProvider returns the provider summarization calls should use and
+// whether it is the dedicated summarizer: that one when it applies to the
+// current main model and is healthy, else the main provider. The factory runs
+// at most once per main model; a build error marks the summarizer broken for
+// that model. Callers branch on the boolean rather than comparing Provider
+// values — interface comparison panics on a non-comparable dynamic type.
+func (state *compactionState) summarizeProvider(ctx context.Context, main Provider) (Provider, bool) {
+	if state.summarizerFactory == nil || state.summarizerBroken {
+		return main, false
+	}
+	if !state.summarizerResolved {
+		state.summarizerResolved = true
+		built, err := state.summarizerFactory(ctx, state.mainModel)
+		if err != nil {
+			state.summarizerBroken = true
+			return main, false
+		}
+		state.summarizerProvider = built
+	}
+	if state.summarizerProvider == nil {
+		return main, false
+	}
+	return state.summarizerProvider, true
+}
+
+// fitsWindow reports whether a calibrated size is safely under the limit the
+// provider enforces. The proactive threshold (70% of the window) is a trigger
+// for the paid summarizer, not the hard limit; the reactive path compares
+// against the window itself, with a small margin for estimate error, so a
+// history pruned to, say, 85% of the window takes the free retry.
+func (state *compactionState) fitsWindow(size int) bool {
+	if state.window <= 0 {
+		return size <= state.threshold
+	}
+	return size <= state.window-state.window/20
+}
+
 // maybeCompact runs proactive compaction at the top of a turn. It returns the
 // (possibly compacted) message slice. It is a no-op when compaction is disabled,
 // when the history is under threshold, or when the history has not grown past
@@ -528,10 +622,34 @@ func (state *compactionState) recover(
 		// context-limit error never triggers an unexpected summarization call.
 		return messages, false, nil
 	}
-	if state.reactiveAttempted {
+	if !isContextLimitError(errorMessage) {
 		return messages, false, nil
 	}
-	if !isContextLimitError(errorMessage) {
+
+	// CHEAP FIRST STAGE (mirrors maybeCompact): a context-limit failure can
+	// often be fixed for free by dropping superseded reads and pruning old
+	// tool-result bodies. It runs regardless of the one-shot reactive budget
+	// (it costs nothing and cannot loop: a second pass finds nothing left to
+	// prune). The free retry is taken only when the pruned history fits the
+	// window the provider enforces — otherwise a retry would fail the same
+	// way, so fall through to the paid summarizer in this same call.
+	toolTokens := estimateToolDefTokens(tools)
+	prunedAny := false
+	if pruned, reclaimed := pruneSupersededReadResults(messages); reclaimed > 0 {
+		messages, prunedAny = pruned, true
+	}
+	if pruned, reclaimed := pruneStaleToolOutput(messages, state.preserveLast); reclaimed > 0 {
+		messages, prunedAny = pruned, true
+	}
+	if prunedAny {
+		size := state.calibratedTokens(estimateTokens(messages) + toolTokens)
+		if state.fitsWindow(size) {
+			state.lowWaterMark = size
+			return messages, true, nil
+		}
+	}
+
+	if state.reactiveAttempted {
 		return messages, false, nil
 	}
 
@@ -571,11 +689,21 @@ func (state *compactionState) recover(
 // provider call. The summary stream intentionally does NOT forward OnText (so
 // compaction stays invisible on the user-facing surface), but it DOES forward
 // OnUsage so the summarizer's token cost is still counted by usage/budgeting.
+// The call goes to the dedicated (cheap) summarizer when one applies; if that
+// call fails the summarizer is marked broken for the current model and the
+// same slice is retried once on the main provider, so the caller sees at most
+// one (main-provider-quality) error.
 func (state *compactionState) summarizeClosure(ctx context.Context, provider Provider) func([]zeroruntime.Message) (string, error) {
 	if state.planner == nil {
 		state.planner = newContextPlanner(contextPlannerConfig{})
 	}
 	return func(toSummarize []zeroruntime.Message) (string, error) {
+		chosen, dedicated := state.summarizeProvider(ctx, provider)
+		summary, err := summarizeWithPlanner(ctx, chosen, toSummarize, state.onUsage, state.planner, state.trace)
+		if err == nil || !dedicated {
+			return summary, err
+		}
+		state.summarizerBroken = true
 		return summarizeWithPlanner(ctx, provider, toSummarize, state.onUsage, state.planner, state.trace)
 	}
 }
@@ -659,8 +787,41 @@ func summarizeMessagesOnce(ctx context.Context, provider Provider, messages []ze
 	return summary, nil
 }
 
+// summaryToolResultClamp bounds each tool-result body in the summarizer input.
+// Tool outputs dominate the elided middle's bulk (build logs, file reads,
+// search results), yet the summary instructions only need their gist — the
+// model that ACTED on the full output already turned it into decisions the
+// surrounding messages record. 2,000 chars (~500 tokens) keeps the useful
+// head+tail of a result while cutting the summarizer input by 5-10x on
+// tool-heavy sessions; the summarizer's own cost is the price being cut.
+const summaryToolResultClamp = 2000
+
+// summaryToolArgsClamp bounds each tool-call argument blob in the transcript:
+// a write_file call carries the whole file body in its arguments.
+const summaryToolArgsClamp = 500
+
+// clampForSummary head+tail-truncates text for the summarizer transcript,
+// snapping to rune boundaries so the clamp never splits a UTF-8 sequence.
+func clampForSummary(text string, max int) string {
+	if max <= 0 || len(text) <= max {
+		return text
+	}
+	head := max * 3 / 4
+	tail := max - head
+	for head > 0 && !utf8.RuneStart(text[head]) {
+		head--
+	}
+	start := len(text) - tail
+	for start < len(text) && !utf8.RuneStart(text[start]) {
+		start++
+	}
+	return text[:head] + "\n…[" + strconv.Itoa(len(text)-head-(len(text)-start)) + " chars omitted for summarization]…\n" + text[start:]
+}
+
 // renderTranscript flattens messages into a plain-text transcript for the
 // summarizer. Secret scrubbing already happened upstream at the tool boundary.
+// Tool-result bodies and tool-call arguments are clamped (see the constants
+// above): the summary needs what was done and decided, not the raw payloads.
 func renderTranscript(messages []zeroruntime.Message) string {
 	lines := make([]string, 0, len(messages))
 	for _, message := range messages {
@@ -670,13 +831,13 @@ func renderTranscript(messages []zeroruntime.Message) string {
 			if len(message.ToolCalls) > 0 {
 				calls := make([]string, 0, len(message.ToolCalls))
 				for _, call := range message.ToolCalls {
-					calls = append(calls, call.Name+"("+call.Arguments+")")
+					calls = append(calls, call.Name+"("+clampForSummary(call.Arguments, summaryToolArgsClamp)+")")
 				}
 				line += "\n[tool calls: " + strings.Join(calls, "; ") + "]"
 			}
 			lines = append(lines, line)
 		case zeroruntime.MessageRoleTool:
-			lines = append(lines, "tool result: "+message.Content)
+			lines = append(lines, "tool result: "+clampForSummary(message.Content, summaryToolResultClamp))
 		default:
 			lines = append(lines, string(message.Role)+": "+message.Content)
 		}

internal/agent/compaction_cheap_test.go

@@ -0,0 +1,469 @@
+package agent
+
+import (
+	"context"
+	"errors"
+	"strings"
+	"testing"
+
+	"github.com/Gitlawb/zero/internal/tools"
+	"github.com/Gitlawb/zero/internal/zeroruntime"
+)
+
+// compactableHistory returns a history whose middle is large enough to trip
+// the proactive threshold for a 1000-token window.
+func compactableHistory() []zeroruntime.Message {
+	return []zeroruntime.Message{
+		{Role: zeroruntime.MessageRoleSystem, Content: "sys"},
+		{Role: zeroruntime.MessageRoleUser, Content: strings.Repeat("u", 4000)},
+		{Role: zeroruntime.MessageRoleAssistant, Content: strings.Repeat("a", 4000)},
+		{Role: zeroruntime.MessageRoleUser, Content: "u2"},
+		{Role: zeroruntime.MessageRoleAssistant, Content: "a2"},
+		{Role: zeroruntime.MessageRoleUser, Content: "u3"},
+	}
+}
+
+// Summarization must run on the dedicated (cheap) summarizer when one is
+// configured — the main provider sees no summarize traffic at all.
+func TestMaybeCompactUsesDedicatedSummarizer(t *testing.T) {
+	cheap := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
+		{Type: zeroruntime.StreamEventText, Content: "CHEAP SUMMARY"},
+		{Type: zeroruntime.StreamEventDone},
+	}}}
+	main := &mockProvider{}
+	factoryCalls := 0
+	state := newCompactionState(Options{
+		ContextWindow:          1000,
+		CompactionPreserveLast: 2,
+		Summarizer: func(context.Context, string) (Provider, error) {
+			factoryCalls++
+			return cheap, nil
+		},
+	}, nil)
+
+	compacted := state.maybeCompact(context.Background(), main, compactableHistory(), nil)
+
+	if len(cheap.requests) == 0 {
+		t.Fatal("dedicated summarizer never received the summarize call")
+	}
+	if len(main.requests) != 0 {
+		t.Fatalf("main provider must see no summarize traffic, got %d requests", len(main.requests))
+	}
+	if factoryCalls != 1 {
+		t.Fatalf("summarizer factory calls = %d, want 1 (lazy, memoized)", factoryCalls)
+	}
+	if estimateTokens(compacted) >= estimateTokens(compactableHistory()) {
+		t.Fatal("compaction did not shrink the history")
+	}
+	found := false
+	for _, message := range compacted {
+		if strings.Contains(message.Content, "CHEAP SUMMARY") {
+			found = true
+		}
+	}
+	if !found {
+		t.Fatal("cheap summarizer's summary missing from the compacted history")
+	}
+}
+
+// A failing summarizer falls back to the main provider for the SAME slice and
+// stays broken for the rest of the run — no repeated failed cheap calls.
+func TestSummarizerFailureFallsBackToMainAndSticks(t *testing.T) {
+	broken := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
+		{Type: zeroruntime.StreamEventError, Error: "boom: model not found"},
+	}}}
+	main := &mockProvider{turns: [][]zeroruntime.StreamEvent{
+		{{Type: zeroruntime.StreamEventText, Content: "MAIN SUMMARY"}, {Type: zeroruntime.StreamEventDone}},
+		{{Type: zeroruntime.StreamEventText, Content: "MAIN SUMMARY 2"}, {Type: zeroruntime.StreamEventDone}},
+	}}
+	state := newCompactionState(Options{
+		ContextWindow:          1000,
+		CompactionPreserveLast: 2,
+		Summarizer:             func(context.Context, string) (Provider, error) { return broken, nil },
+	}, nil)
+	summarize := state.summarizeClosure(context.Background(), main)
+	input := []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "history"}}
+
+	summary, err := summarize(input)
+	if err != nil {
+		t.Fatalf("fallback must succeed via the main provider: %v", err)
+	}
+	if summary != "MAIN SUMMARY" {
+		t.Fatalf("summary = %q, want the main provider's", summary)
+	}
+	if len(broken.requests) != 1 {
+		t.Fatalf("broken summarizer requests = %d, want exactly 1", len(broken.requests))
+	}
+	if !state.summarizerBroken {
+		t.Fatal("a failed summarizer must be marked broken for the run")
+	}
+
+	// Second summarization: straight to main, no cheap retry.
+	if _, err := summarize(input); err != nil {
+		t.Fatal(err)
+	}
+	if len(broken.requests) != 1 {
+		t.Fatalf("broken summarizer was retried (%d requests)", len(broken.requests))
+	}
+	if len(main.requests) != 2 {
+		t.Fatalf("main provider requests = %d, want 2", len(main.requests))
+	}
+}
+
+// A factory that errors (misconfigured model) is equivalent to no summarizer:
+// main provider used, factory not retried.
+func TestSummarizerFactoryErrorFallsBack(t *testing.T) {
+	main := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
+		{Type: zeroruntime.StreamEventText, Content: "MAIN SUMMARY"},
+		{Type: zeroruntime.StreamEventDone},
+	}}}
+	factoryCalls := 0
+	state := newCompactionState(Options{
+		ContextWindow:          1000,
+		CompactionPreserveLast: 2,
+		Summarizer: func(context.Context, string) (Provider, error) {
+			factoryCalls++
+			return nil, errors.New("unknown model")
+		},
+	}, nil)
+	summarize := state.summarizeClosure(context.Background(), main)
+
+	summary, err := summarize([]zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "history"}})
+	if err != nil || summary != "MAIN SUMMARY" {
+		t.Fatalf("summary = %q, err = %v; want main provider fallback", summary, err)
+	}
+	if factoryCalls != 1 {
+		t.Fatalf("factory calls = %d, want 1 (sticky failure)", factoryCalls)
+	}
+	if _, dedicated := state.summarizeProvider(context.Background(), main); dedicated {
+		t.Fatal("after a factory failure the run must stay on the main provider")
+	}
+	if factoryCalls != 1 {
+		t.Fatalf("factory retried after failure (%d calls)", factoryCalls)
+	}
+}
+
+// Tool payloads are clamped in the summarizer transcript: results to
+// summaryToolResultClamp, call arguments to summaryToolArgsClamp.
+func TestRenderTranscriptClampsToolPayloads(t *testing.T) {
+	bigResult := strings.Repeat("r", 50_000)
+	bigArgs := strings.Repeat("w", 20_000)
+	transcript := renderTranscript([]zeroruntime.Message{
+		{Role: zeroruntime.MessageRoleAssistant, Content: "editing", ToolCalls: []zeroruntime.ToolCall{
+			{ID: "c1", Name: "write_file", Arguments: bigArgs},
+		}},
+		{Role: zeroruntime.MessageRoleTool, ToolCallID: "c1", Content: bigResult},
+		{Role: zeroruntime.MessageRoleUser, Content: "keep going"},
+	})
+
+	if len(transcript) > summaryToolResultClamp+summaryToolArgsClamp+1024 {
+		t.Fatalf("transcript is %d bytes; clamps did not apply", len(transcript))
+	}
+	if !strings.Contains(transcript, "chars omitted for summarization") {
+		t.Fatal("clamped transcript must carry the omission marker")
+	}
+	if !strings.Contains(transcript, "keep going") {
+		t.Fatal("non-tool content must survive unclamped")
+	}
+	// Head AND tail of the clamped payloads survive.
+	if !strings.HasPrefix(transcript[strings.Index(transcript, "tool result: ")+len("tool result: "):], "r") ||
+		!strings.Contains(transcript, "rrr\n\nuser: keep going") {
+		t.Fatalf("head/tail of the tool result lost:\n%s", transcript[:200])
+	}
+}
+
+// bigToolHistory returns a history with n large tool results (~40k estimated
+// tokens each): the trailing protection window keeps the newest verbatim,
+// the older ones are prunable.
+func bigToolHistory(n int) []zeroruntime.Message {
+	bigBody := strings.Repeat("x", 160_000)
+	messages := []zeroruntime.Message{{Role: zeroruntime.MessageRoleSystem, Content: "sys"}}
+	for i := 0; i < n; i++ {
+		id := string(rune('a' + i))
+		messages = append(messages,
+			zeroruntime.Message{Role: zeroruntime.MessageRoleAssistant, ToolCalls: []zeroruntime.ToolCall{{ID: id, Name: "read_file", Arguments: "{\"path\":\"" + id + "\"}"}}},
+			zeroruntime.Message{Role: zeroruntime.MessageRoleTool, ToolCallID: id, Content: bigBody},
+		)
+	}
+	return append(messages, zeroruntime.Message{Role: zeroruntime.MessageRoleUser, Content: "go"})
+}
+
+func summaryProvider(text string) *mockProvider {
+	return &mockProvider{turns: [][]zeroruntime.StreamEvent{
+		{{Type: zeroruntime.StreamEventText, Content: text}, {Type: zeroruntime.StreamEventDone}},
+		{{Type: zeroruntime.StreamEventText, Content: text}, {Type: zeroruntime.StreamEventDone}},
+	}}
+}
+
+// A context-limit error is first answered with the free prune stage; when the
+// pruned history fits the window the retry is free (no summarizer call) and
+// the one-shot reactive budget is untouched. The paid summarizer only runs
+// when a later error finds nothing left to prune.
+func TestRecoverPrunesBeforeSummarizing(t *testing.T) {
+	provider := summaryProvider("SUMMARY")
+	// The protected trailing tool output (~40k tokens) must fit the window.
+	state := newCompactionState(Options{ContextWindow: 200_000, CompactionPreserveLast: 2}, nil)
+	messages := bigToolHistory(5)
+
+	pruned, retried, err := state.recover(context.Background(), provider, messages, nil, "maximum context length exceeded")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !retried {
+		t.Fatal("prunable history that fits must produce a free retry")
+	}
+	if len(provider.requests) != 0 {
+		t.Fatalf("free prune stage must not call the summarizer (%d requests)", len(provider.requests))
+	}
+	if state.reactiveAttempted {
+		t.Fatal("a free prune retry must not consume the reactive budget")
+	}
+	if estimateTokens(pruned) >= estimateTokens(messages) {
+		t.Fatal("prune did not shrink the history")
+	}
+
+	// Second context-limit error on the pruned history: nothing meaningfully
+	// prunable remains, so the paid summarizer fires and consumes the budget.
+	_, retried, err = state.recover(context.Background(), provider, pruned, nil, "maximum context length exceeded")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !retried {
+		t.Fatal("second recover must compact and retry")
+	}
+	if len(provider.requests) == 0 {
+		t.Fatal("second recover must reach the summarizer")
+	}
+	if !state.reactiveAttempted {
+		t.Fatal("a paid recover must consume the reactive budget")
+	}
+}
+
+// When pruning reclaims something but the pruned history still exceeds the
+// window, recover falls through to the paid summarizer in the SAME call
+// instead of spending a retry that would fail the same way.
+func TestRecoverFallsThroughToSummarizerWhenPruneIsInsufficient(t *testing.T) {
+	provider := summaryProvider("SUMMARY")
+	// A 1,000-token window: even the protected trailing output overflows it.
+	state := newCompactionState(Options{ContextWindow: 1000, CompactionPreserveLast: 2}, nil)
+	messages := bigToolHistory(5)
+
+	compacted, retried, err := state.recover(context.Background(), provider, messages, nil, "maximum context length exceeded")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !retried {
+		t.Fatal("insufficient prune must still end in a retry via summarization")
+	}
+	if len(provider.requests) == 0 {
+		t.Fatal("insufficient prune must reach the summarizer in the same recover call")
+	}
+	if !state.reactiveAttempted {
+		t.Fatal("the paid summarizer consumes the reactive budget")
+	}
+	if estimateTokens(compacted) >= estimateTokens(messages) {
+		t.Fatal("recover did not shrink the history")
+	}
+}
+
+// The free prune stage is not gated behind the one-shot budget: after a paid
+// reactive compaction, a later context-limit error still gets a free retry
+// when pruning makes the history fit.
+func TestRecoverFreePruneRunsAfterBudgetIsSpent(t *testing.T) {
+	provider := summaryProvider("SUMMARY")
+	state := newCompactionState(Options{ContextWindow: 200_000, CompactionPreserveLast: 2}, nil)
+	state.reactiveAttempted = true
+	messages := bigToolHistory(5)
+
+	pruned, retried, err := state.recover(context.Background(), provider, messages, nil, "maximum context length exceeded")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !retried || len(provider.requests) != 0 {
+		t.Fatalf("free prune must retry without the summarizer even when the budget is spent (retried=%v, requests=%d)", retried, len(provider.requests))
+	}
+	if estimateTokens(pruned) >= estimateTokens(messages) {
+		t.Fatal("prune did not shrink the history")
+	}
+	// With nothing left to prune and the budget spent, the caller keeps its
+	// original error — recover neither loops nor summarizes.
+	_, retried, err = state.recover(context.Background(), provider, pruned, nil, "maximum context length exceeded")
+	if err != nil || retried || len(provider.requests) != 0 {
+		t.Fatalf("spent budget must not summarize again (retried=%v, requests=%d, err=%v)", retried, len(provider.requests), err)
+	}
+}
+
+// The free-retry gate compares against the window the provider enforces, not
+// the 70% proactive threshold: a history pruned to ~80% of the window still
+// takes the free retry.
+func TestRecoverFreeRetryGateUsesWindowNotThreshold(t *testing.T) {
+	provider := summaryProvider("SUMMARY")
+	messages := bigToolHistory(5)
+	pruned, _ := pruneStaleToolOutput(messages, 2)
+	prunedTokens := estimateTokens(pruned)
+	// Choose a window so the pruned size sits between 70% and 95% of it.
+	window := prunedTokens * 100 / 80
+	state := newCompactionState(Options{ContextWindow: window, CompactionPreserveLast: 2}, nil)
+	if prunedTokens <= state.threshold {
+		t.Fatalf("test setup: pruned size %d must exceed the proactive threshold %d", prunedTokens, state.threshold)
+	}
+
+	_, retried, err := state.recover(context.Background(), provider, messages, nil, "maximum context length exceeded")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !retried || len(provider.requests) != 0 {
+		t.Fatalf("a history that fits the window must take the free retry (retried=%v, requests=%d)", retried, len(provider.requests))
+	}
+}
+
+// After a mid-run model switch the summarizer is re-resolved against the new
+// main model: a run that started on the cheap model (no dedicated summarizer)
+// and escalated gets a cheap summarizer, and a previously broken one is
+// retried for the new model.
+func TestSwitchModelReresolvesSummarizer(t *testing.T) {
+	cheap := summaryProvider("CHEAP SUMMARY")
+	main := summaryProvider("MAIN SUMMARY")
+	var factoryModels []string
+	state := newCompactionState(Options{
+		ContextWindow:          1000,
+		CompactionPreserveLast: 2,
+		Model:                  "cheap-model",
+		Summarizer: func(_ context.Context, mainModelID string) (Provider, error) {
+			factoryModels = append(factoryModels, mainModelID)
+			if mainModelID == "cheap-model" {
+				return nil, nil // main already is the cheap model
+			}
+			return cheap, nil
+		},
+	}, nil)
+
+	if _, dedicated := state.summarizeProvider(context.Background(), main); dedicated {
+		t.Fatal("on the cheap model the main provider must summarize")
+	}
+	if _, dedicated := state.summarizeProvider(context.Background(), main); dedicated || len(factoryModels) != 1 {
+		t.Fatalf("factory must run once per main model, calls=%v", factoryModels)
+	}
+
+	state.switchModel("big-model", 400_000)
+	if state.threshold != compactionThreshold(400_000) || state.window != 400_000 {
+		t.Fatalf("switchModel must re-derive the window, got threshold=%d window=%d", state.threshold, state.window)
+	}
+	if got, dedicated := state.summarizeProvider(context.Background(), main); !dedicated || got != Provider(cheap) {
+		t.Fatal("after escalating to an expensive model the dedicated cheap summarizer must be used")
+	}
+	if len(factoryModels) != 2 || factoryModels[1] != "big-model" {
+		t.Fatalf("factory must be re-invoked with the new main model, calls=%v", factoryModels)
+	}
+
+	// A broken summarizer is retried after the next switch.
+	state.summarizerBroken = true
+	if _, dedicated := state.summarizeProvider(context.Background(), main); dedicated {
+		t.Fatal("a broken summarizer must fall back to main")
+	}
+	state.switchModel("other-model", 0)
+	if got, dedicated := state.summarizeProvider(context.Background(), main); !dedicated || got != Provider(cheap) {
+		t.Fatal("a model switch must clear the broken flag and rebuild the summarizer")
+	}
+}
+
+func TestCompactionUpdateWindow(t *testing.T) {
+	state := newCompactionState(Options{ContextWindow: 100_000, CompactionPreserveLast: 2}, nil)
+	state.lowWaterMark = 50_000
+	before := state.threshold
+
+	state.updateWindow(0) // unknown model: unchanged
+	if state.threshold != before || state.lowWaterMark != 50_000 {
+		t.Fatal("updateWindow(0) must be a no-op")
+	}
+
+	state.updateWindow(10_000)
+	if state.threshold >= before {
+		t.Fatalf("threshold = %d, want re-derived below %d", state.threshold, before)
+	}
+	if state.lowWaterMark != 0 {
+		t.Fatal("low-water mark must reset on a window change")
+	}
+	if !state.enabled {
+		t.Fatal("a positive window must keep compaction enabled")
+	}
+}
+
+// End-to-end: after escalate_model switches providers, the loop re-derives the
+// context window via ContextWindowFor, visible in the OnContext report.
+func TestRunEscalationRederivesContextWindow(t *testing.T) {
+	registry := tools.NewRegistry()
+	registry.Register(escalatingTool{target: "big-model"})
+	switched := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
+		{Type: zeroruntime.StreamEventText, Content: "done"},
+		{Type: zeroruntime.StreamEventDone},
+	}}}
+	provider := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
+		{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: "call-1", ToolName: "escalate"},
+		{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: "call-1", ArgumentsFragment: `{}`},
+		{Type: zeroruntime.StreamEventToolCallEnd, ToolCallID: "call-1"},
+		{Type: zeroruntime.StreamEventDone},
+	}}}
+
+	var windows []int
+	result, err := Run(context.Background(), "go", provider, Options{
+		Registry:      registry,
+		ContextWindow: 100_000,
+		Model:         "small-model",
+		ModelSwitcher: func(context.Context, string) (Provider, error) { return switched, nil },
+		ContextWindowFor: func(modelID string) int {
+			if modelID == "big-model" {
+				return 400_000
+			}
+			return 0
+		},
+		OnContext: func(breakdown ContextBreakdown) { windows = append(windows, breakdown.ContextWindow) },
+	})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if result.FinalAnswer != "done" {
+		t.Fatalf("final answer = %q", result.FinalAnswer)
+	}
+	if len(windows) < 2 {
+		t.Fatalf("expected at least 2 OnContext reports, got %d", len(windows))
+	}
+	if windows[0] != 100_000 {
+		t.Fatalf("turn 1 window = %d, want the original 100000", windows[0])
+	}
+	if windows[len(windows)-1] != 400_000 {
+		t.Fatalf("post-escalation window = %d, want 400000", windows[len(windows)-1])
+	}
+}
+
+// nonComparableProvider has a slice field, so comparing two Provider interface
+// values holding it would panic; the summarizer path must never compare them.
+type nonComparableProvider struct {
+	inner *mockProvider
+	tags  []string
+}
+
+func (p nonComparableProvider) StreamCompletion(ctx context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
+	return p.inner.StreamCompletion(ctx, request)
+}
+
+func TestSummarizeClosureNeverComparesProviderValues(t *testing.T) {
+	broken := &mockProvider{turns: [][]zeroruntime.StreamEvent{{
+		{Type: zeroruntime.StreamEventError, Error: "boom: model not found"},
+	}}}
+	main := nonComparableProvider{inner: summaryProvider("MAIN SUMMARY"), tags: []string{"x"}}
+	state := newCompactionState(Options{
+		ContextWindow:          1000,
+		CompactionPreserveLast: 2,
+		Summarizer:             func(context.Context, string) (Provider, error) { return nonComparableProvider{inner: broken}, nil },
+	}, nil)
+	summary, err := state.summarizeClosure(context.Background(), main)([]zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "history"}})
+	if err != nil || summary != "MAIN SUMMARY" {
+		t.Fatalf("fallback with non-comparable providers must not panic and must use main, got %q err=%v", summary, err)
+	}
+	// And with no dedicated summarizer at all the closure still works.
+	state = newCompactionState(Options{ContextWindow: 1000, CompactionPreserveLast: 2}, nil)
+	if _, err := state.summarizeClosure(context.Background(), main)([]zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "history"}}); err != nil {
+		t.Fatal(err)
+	}
+}

internal/agent/loop.go

@@ -40,7 +40,15 @@ const (
 	toolResultControlSpecReview = "spec_review_required"
 )
 
-var errPermissionApprovalCanceled = errors.New("permission approval cancelled")
+// ErrPermissionApprovalCanceled ends a run because the caller cancelled a
+// permission prompt, rather than because anything failed.
+//
+// EXPORTED FOR THE SURFACES. A cancel is a normal ending and each surface says
+// so its own way — the TUI unwinds, and ACP has a "cancelled" stop reason for
+// exactly this. While it was unexported ACP could not distinguish it from a
+// fault and reported it as an internal error, so declining a tool looked like
+// the agent crashing.
+var ErrPermissionApprovalCanceled = errors.New("permission approval cancelled")
 
 // isImageRejectionError reports whether err is a provider 400 that rejects
 // image/multimodal content. This is checked BEFORE the compaction-retry path
@@ -836,11 +844,21 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 					options.ServiceTier = ""
 					planner.config.serviceTier = ""
 					options.Trace.Counter(trace.CounterModelSwitches, 1)
-					// KNOWN LIMITATION (deferred): the compactor's context-window budget
-					// is fixed at run start from options.ContextWindow and is NOT updated
-					// here, so a switch to a model with a different window keeps compacting
-					// against the original budget. Fixing it needs the switcher to also
-					// report the new window — out of scope for this change.
+					// Re-derive the context window for the new model so compaction and
+					// the OnContext budget report track the model actually in force —
+					// without this a switch to a smaller-window model can overflow the
+					// target, and a switch to a larger one over-compacts. An unknown
+					// model (<= 0) keeps the original window. The compactor also
+					// re-resolves its dedicated summarizer against the new model.
+					window := 0
+					if options.ContextWindowFor != nil {
+						window = options.ContextWindowFor(turnRequestedModel)
+					}
+					if window > 0 {
+						options.ContextWindow = window
+						planner.config.contextWindow = window
+					}
+					compactor.switchModel(turnRequestedModel, window)
 				}
 			}
 		}
@@ -1364,7 +1382,7 @@ func executeToolCall(ctx context.Context, registry *tools.Registry, call ToolCal
 			}
 		case PermissionDecisionCancel:
 			emitCanceledPermission(options, call, requestEvent, decisionReason)
-			return canceledPermissionResult(call, decisionReason, requestEvent), fmt.Errorf("%w for %s", errPermissionApprovalCanceled, call.Name)
+			return canceledPermissionResult(call, decisionReason, requestEvent), fmt.Errorf("%w for %s", ErrPermissionApprovalCanceled, call.Name)
 		default:
 			emitDeniedPermission(options, call, requestEvent, decisionReason)
 			return deniedPermissionResult(call, decisionReason, requestEvent), nil
@@ -1548,7 +1566,7 @@ func maybeRetryUnsandboxedAfterSandboxRestriction(ctx context.Context, registry
 	case PermissionDecisionCancel:
 		emitCanceledPermission(options, call, requestEvent, reason)
 		canceled := canceledPermissionResult(call, reason, requestEvent)
-		return result, &canceled, true, decision.Action, reason, nil, fmt.Errorf("%w for %s", errPermissionApprovalCanceled, call.Name)
+		return result, &canceled, true, decision.Action, reason, nil, fmt.Errorf("%w for %s", ErrPermissionApprovalCanceled, call.Name)
 	default:
 		emitDeniedPermission(options, call, requestEvent, reason)
 		denied := deniedPermissionResult(call, reason, requestEvent)
@@ -1596,7 +1614,7 @@ func maybeRetryWithNetworkAfterSandboxDenial(ctx context.Context, registry *tool
 	case PermissionDecisionCancel:
 		emitCanceledPermission(options, call, requestEvent, reason)
 		canceled := canceledPermissionResult(call, reason, requestEvent)
-		return result, &canceled, true, decision.Action, reason, fmt.Errorf("%w for %s", errPermissionApprovalCanceled, call.Name)
+		return result, &canceled, true, decision.Action, reason, fmt.Errorf("%w for %s", ErrPermissionApprovalCanceled, call.Name)
 	default:
 		emitDeniedPermission(options, call, requestEvent, reason)
 		denied := deniedPermissionResult(call, reason, requestEvent)
@@ -3087,13 +3105,15 @@ func partitionToolsCached(registry *tools.Registry, permissionMode PermissionMod
 	// Deferral may activate only when tool_search is actually runnable; otherwise
 	// the loop would hide deferred tools behind a loader the dispatch gate rejects
 	// — an inescapable dead-end. "Runnable" mirrors executeToolCall's gate:
-	// registered, not in DisabledTools, and advertised in the current permission
-	// mode (e.g. not spec-draft, where tool_search is not advertised). The
+	// registered, model-visible, not in DisabledTools, and advertised in the
+	// current permission mode (e.g. not spec-draft, where tool_search is not
+	// advertised). The
 	// EnabledTools allowlist is intentionally NOT checked here — tool_search is
 	// exempt from the allowlist at dispatch, so an allowlist that omits it must
 	// not disable deferral.
 	loader, loaderFound := registry.Get(tools.ToolSearchToolName)
 	loaderUsable := loaderFound &&
+		tools.ModelVisible(loader) &&
 		!containsToolName(options.DisabledTools, tools.ToolSearchToolName) &&
 		ToolAdvertised(loader, permissionMode)
 
@@ -3208,7 +3228,9 @@ func runtimeToolDefinition(tool tools.Tool) zeroruntime.ToolDefinition {
 }
 
 func ToolVisible(tool tools.Tool, permissionMode PermissionMode, enabledTools []string, disabledTools []string) bool {
-	return ToolAllowedByFilters(tool.Name(), enabledTools, disabledTools) && ToolAdvertised(tool, permissionMode)
+	return tools.ModelVisible(tool) &&
+		ToolAllowedByFilters(tool.Name(), enabledTools, disabledTools) &&
+		ToolAdvertised(tool, permissionMode)
 }
 
 func ToolAllowedByFilters(name string, enabledTools []string, disabledTools []string) bool {

internal/agent/loop_test.go

@@ -1853,7 +1853,7 @@ func TestRunAbortsWhenPermissionRequestCanceled(t *testing.T) {
 		},
 	})
 
-	if !errors.Is(err, errPermissionApprovalCanceled) {
+	if !errors.Is(err, ErrPermissionApprovalCanceled) {
 		t.Fatalf("expected permission approval cancel error, got %v", err)
 	}
 	if result.FinalAnswer != "" {
@@ -4340,3 +4340,95 @@ func TestPlanModeHonorsBeforeToolVeto(t *testing.T) {
 		t.Fatalf("expected tool result to mention the beforeTool veto, got %q", combined)
 	}
 }
+
+// A cancelled permission on either sandbox-retry path must abort the run with a
+// recognisable cancellation, and must not run the escalated retry.
+//
+// BOTH PATHS, because both wrap ErrPermissionApprovalCanceled and each is
+// reached by a different kind of denial: one by an unrestricted platform denial
+// asking for approval, the other by an external-network denial. Surfaces map
+// this sentinel onto their own idea of a cancel — ACP returns stopReason
+// "cancelled" for it — so a path that produced a bare error instead would show
+// the user a crash where they had simply declined.
+func TestCancellingASandboxRetryAbortsWithoutRetrying(t *testing.T) {
+	denial := func(capability execution.CapabilityKind, scope string) tools.Result {
+		return tools.Result{
+			Status: tools.StatusError,
+			ExecutionOutcome: &execution.Outcome{
+				State: execution.StateDenied,
+				Kind:  execution.OutcomeEnforcementDenied,
+				Denial: &execution.Denial{
+					Capability:  execution.Capability{Kind: capability, Scope: scope},
+					Source:      execution.DenialSourcePlatformSandbox,
+					Reason:      "denied by the sandbox",
+					Recoverable: true,
+					NextAction:  execution.DenialNextActionRequestApproval,
+				},
+			},
+		}
+	}
+
+	for _, testCase := range []struct {
+		name   string
+		result tools.Result
+		run    func(context.Context, *tools.Registry, ToolCall, tools.Tool, map[string]any, tools.Result, Options) error
+	}{
+		{
+			name:   "unsandboxed retry",
+			result: denial(execution.CapabilityUnrestricted, "host"),
+			run: func(ctx context.Context, registry *tools.Registry, call ToolCall, tool tools.Tool, args map[string]any, result tools.Result, options Options) error {
+				_, _, _, _, _, _, abortErr := maybeRetryUnsandboxedAfterSandboxRestriction(
+					ctx, registry, call, tool, args, result, PermissionModeAsk, options, nil)
+				return abortErr
+			},
+		},
+		{
+			name:   "network retry",
+			result: denial(execution.CapabilityExternalNetwork, ""),
+			run: func(ctx context.Context, registry *tools.Registry, call ToolCall, tool tools.Tool, args map[string]any, result tools.Result, options Options) error {
+				_, _, _, _, _, abortErr := maybeRetryWithNetworkAfterSandboxDenial(
+					ctx, registry, call, tool, args, result, PermissionModeAsk, options, nil)
+				return abortErr
+			},
+		},
+	} {
+		t.Run(testCase.name, func(t *testing.T) {
+			retryTool := &sandboxNamespaceLimitedRetryTool{}
+			registry := tools.NewRegistry()
+			registry.Register(retryTool)
+
+			asked := 0
+			options := Options{
+				Registry:       registry,
+				PermissionMode: PermissionModeAsk,
+				Autonomy:       "medium",
+				Sandbox: sandbox.NewEngine(sandbox.EngineOptions{
+					WorkspaceRoot: t.TempDir(),
+					Policy:        sandbox.DefaultPolicy(),
+				}),
+				OnPermissionRequest: func(context.Context, PermissionRequest) (PermissionDecision, error) {
+					asked++
+					return PermissionDecision{Action: PermissionDecisionCancel, Reason: "client cancelled"}, nil
+				},
+			}
+
+			call := ToolCall{ID: "call-1", Name: "bash", Arguments: `{"command":"curl example.com"}`}
+			args := map[string]any{"command": "curl example.com"}
+
+			abortErr := testCase.run(context.Background(), registry, call, retryTool, args, testCase.result, options)
+
+			if asked != 1 {
+				t.Fatalf("permission was requested %d times, want exactly 1", asked)
+			}
+			if !errors.Is(abortErr, ErrPermissionApprovalCanceled) {
+				t.Fatalf("abort error = %v, want it to match ErrPermissionApprovalCanceled", abortErr)
+			}
+			// The escalated retry is the thing the permission was gating. A
+			// cancelled prompt that still ran it would have run the command the
+			// user just declined.
+			if len(retryTool.calls) != 0 {
+				t.Fatalf("the escalated retry ran %d times after a cancel: %+v", len(retryTool.calls), retryTool.calls)
+			}
+		})
+	}
+}

internal/agent/prompt_budget_test.go

@@ -67,3 +67,21 @@ func TestEagerToolSchemaTokenBudget(t *testing.T) {
 		t.Fatalf("eager tool schemas are %d tokens, over the %d ceiling — trim a schema, drop a core tool, or raise the ceiling deliberately (deferring will NOT help: this test disables deferral)", got, maxEagerToolSchemaTokens)
 	}
 }
+
+func TestAgentAdvertisesBothEditTools(t *testing.T) {
+	registry := tools.NewRegistry()
+	for _, tool := range tools.CoreToolsScoped(t.TempDir(), nil) {
+		registry.Register(tool)
+	}
+	exposed, _ := partitionTools(registry, PermissionModeAsk, Options{}, map[string]bool{})
+	names := make(map[string]bool, len(exposed))
+	for _, definition := range exposed {
+		names[definition.Name] = true
+	}
+	if !names["apply_patch"] {
+		t.Fatal("agent must retain apply_patch for multi-hunk changes")
+	}
+	if !names["edit_file"] {
+		t.Fatal("agent must receive edit_file for targeted exact replacements")
+	}
+}

internal/agent/system_prompt.md

@@ -52,7 +52,7 @@ work.
 
 - Choose the narrowest tool that safely accomplishes the step. Prefer native
   file tools - read_file, read_minified_file, list_directory, glob, grep,
-  write_file, edit_file, apply_patch - over shelling out to
+  edit_file, apply_patch, write_file - over shelling out to
   cat/sed/awk/python for file operations.
   They are safer, reviewable, and produce clean diffs.
 - Prefer read_minified_file when initially exploring source code; it preserves
@@ -61,10 +61,18 @@ work.
 - Keep edits focused and reviewable. A single patch may update several related
   files when they form one coherent change; do not hide unrelated edits in a
   bulk shell or script rewrite.
-- For edits to existing files, prefer edit_file or apply_patch with minimal,
-  targeted diffs. Match the existing indentation, imports, and idioms. Match the
-  file's comment density: do not add explanatory comments unless the user asks or
-  the code is already comment-dense.
+- For edits to existing files, use edit_file for a targeted change (old_string
+  must match the file exactly and be unique, so include a few surrounding
+  lines) and apply_patch when one coherent change spans several hunks or
+  files. Use write_file only to create a file or when most of it changes; do
+  not rewrite a whole file to change a few lines. Match the existing
+  indentation, imports, and idioms. Match the file's comment density: do not
+  add explanatory comments unless the user asks or the code is already
+  comment-dense.
+- A successful edit result already confirms the change; do not re-read a file
+  just to verify an edit that succeeded. If an edit fails, read the error, fix
+  the old_string or hunk, and retry the same tool rather than switching to a
+  full rewrite.
 - Solve the problem as posed, not a more general version of it. Add no
   speculative abstraction, configurability, or handling for cases that cannot
   occur, and nothing the user did not ask for. A small diff can still be
@@ -104,7 +112,7 @@ work.
   you need to clean up a running foreground command yourself, use write_stdin.
 - write_stdin's session_id is only ever an id returned by a still-running
   exec_command; never guess or probe ids. If you have no such session, start one
-  with exec_command, or use write_file/edit_file/apply_patch for file changes.
+  with exec_command, or use edit_file/apply_patch/write_file for file changes.
 - write_stdin with empty input polls an existing exec_command session, and
   `\u0003` interrupts it. Sending other stdin bytes may require approval because
   it can drive the running process beyond the original command. Non-tty sessions

internal/agent/system_prompt_models.go

@@ -60,8 +60,12 @@ const openAIPromptAddendum = `<model_guidance>
   longer answers, fenced code blocks for code, and ` + "`inline code`" + ` for paths,
   commands, and symbols.
 - Strongly prefer the native file tools (read_file, list_directory, grep, glob,
-  write_file, edit_file, apply_patch) over shelling out to cat/sed/awk/python for
-  file work. Make one tool call per file; do not batch file writes into a script.
+  edit_file, apply_patch, write_file) over shelling out to cat/sed/awk/python
+  for file work. read_file, edit_file and write_file take one file per call;
+  a single apply_patch may span several files when they form one coherent
+  change. Do not batch file writes into a script. Independent tool calls
+  (several reads, several edit_file calls to different files) belong in the
+  same turn.
 - Persist until the task is fully handled this turn: gather context, implement,
   run the validators, and report — do not stop at a partial result.
 </model_guidance>`

internal/agent/system_prompt_test.go

@@ -36,7 +36,7 @@ func TestCoreSystemPromptIncludesCodingQualityRules(t *testing.T) {
 		"inspect the target file",
 		"plan then act",
 		"choose the narrowest tool",
-		"prefer edit_file or apply_patch",
+		"for edits to existing files, use edit_file",
 		"verify after edits",
 		"honor the active permission mode",
 		"avoid broad refactors",

internal/agent/types.go

@@ -348,10 +348,26 @@ type Options struct {
 	// CompactionPreserveLast is how many trailing messages compaction keeps
 	// verbatim. <= 0 falls back to defaultCompactionPreserveLast.
 	CompactionPreserveLast int
-	Registry               *tools.Registry
-	PermissionMode         PermissionMode
-	Autonomy               string
-	Sandbox                *sandbox.Engine
+	// Summarizer, when set, lazily builds the provider used for compaction
+	// summarization calls — typically a cheap/fast model, since summaries at
+	// main-model prices are the single most expensive recurring event in a
+	// long run. It receives the main model currently in force and may return
+	// (nil, nil) when no dedicated summarizer applies to it (the main model is
+	// already the cheap one). Built on the first paid compaction and again
+	// after a mid-run model switch. Any failure (build or call) falls back to
+	// the run's main provider until the next switch, so a misconfigured
+	// summarizer can never break compaction. nil keeps today's behavior.
+	Summarizer func(ctx context.Context, mainModelID string) (Provider, error)
+	// ContextWindowFor, when set, resolves a model ID to its context window so
+	// the compactor can re-derive its threshold after a mid-run model switch
+	// (escalate_model). Without it a switch keeps compacting against the
+	// original model's window — overflowing a smaller target or over-compacting
+	// a larger one. Return <= 0 when the model is unknown (window unchanged).
+	ContextWindowFor func(modelID string) int
+	Registry         *tools.Registry
+	PermissionMode   PermissionMode
+	Autonomy         string
+	Sandbox          *sandbox.Engine
 	// FileTracker records per-session file read/write versions so the write tools
 	// can detect a file changed on disk outside Zero since it was last read. nil
 	// disables the check. Created once per session and threaded into every tool run.

internal/background/manager.go

@@ -453,7 +453,12 @@ func (manager *Manager) normalizeLoadedTask(fileTaskID string, task Task) (Task,
 	}
 	outputFile, err := manager.outputFile(task.ID, task.OutputFile)
 	if err != nil {
-		return Task{}, false, err
+		var migrated bool
+		outputFile, migrated = manager.migrateLegacyOutputFile(task.ID, task.OutputFile)
+		if !migrated {
+			return Task{}, false, err
+		}
+		changed = true
 	}
 	if outputFile != task.OutputFile {
 		changed = true
@@ -562,6 +567,32 @@ func (manager *Manager) outputFile(taskID string, requested string) (string, err
 	return path, nil
 }
 
+// migrateLegacyOutputFile recovers task metadata written under a previous home
+// or XDG data root. It accepts only the canonical per-task output
+// name in the historic zero/background layout, and only when the corresponding
+// regular file already exists inside the active manager root.
+func (manager *Manager) migrateLegacyOutputFile(taskID string, requested string) (string, bool) {
+	requested = strings.TrimSpace(requested)
+	if !filepath.IsAbs(requested) {
+		return "", false
+	}
+	requested = filepath.Clean(requested)
+	expectedName := taskID + ".ndjson"
+	if filepath.Base(requested) != expectedName {
+		return "", false
+	}
+	legacyRoot := filepath.Dir(requested)
+	if filepath.Base(legacyRoot) != "background" || filepath.Base(filepath.Dir(legacyRoot)) != "zero" {
+		return "", false
+	}
+	canonical := filepath.Join(manager.rootDir, expectedName)
+	info, err := os.Lstat(canonical)
+	if err != nil || !info.Mode().IsRegular() {
+		return "", false
+	}
+	return canonical, true
+}
+
 func validTaskID(taskID string) bool {
 	return taskIDPattern.MatchString(strings.TrimSpace(taskID))
 }

internal/background/manager_test.go

@@ -1,6 +1,7 @@
 package background
 
 import (
+	"encoding/json"
 	"errors"
 	"os"
 	"path/filepath"
@@ -191,6 +192,88 @@ func TestManagerSkipsInvalidPersistedMetadata(t *testing.T) {
 	}
 }
 
+func TestManagerMigratesLegacyOutputPathWhenCanonicalOutputExists(t *testing.T) {
+	root := t.TempDir()
+	const taskID = "legacy_task"
+	canonicalOutput := filepath.Join(root, taskID+".ndjson")
+	if err := os.WriteFile(canonicalOutput, []byte("legacy output\n"), 0o600); err != nil {
+		t.Fatalf("write canonical output: %v", err)
+	}
+	legacyOutput := filepath.Join(t.TempDir(), "zero", "background", taskID+".ndjson")
+	metadata, err := json.Marshal(Task{
+		ID:         taskID,
+		Type:       "specialist",
+		Status:     StatusCompleted,
+		OutputFile: legacyOutput,
+		StartedAt:  time.Date(2026, 8, 1, 10, 0, 0, 0, time.UTC),
+	})
+	if err != nil {
+		t.Fatalf("marshal legacy metadata: %v", err)
+	}
+	if err := os.WriteFile(filepath.Join(root, taskID+".json"), append(metadata, '\n'), 0o600); err != nil {
+		t.Fatalf("write legacy metadata: %v", err)
+	}
+
+	manager, err := NewManager(root)
+	if err != nil {
+		t.Fatalf("NewManager returned error: %v", err)
+	}
+	task, ok := manager.Get(taskID)
+	if !ok {
+		t.Fatal("manager did not load migrated task")
+	}
+	if task.OutputFile != canonicalOutput {
+		t.Fatalf("migrated output file = %q, want %q", task.OutputFile, canonicalOutput)
+	}
+	if warnings := manager.LoadWarnings(); len(warnings) != 0 {
+		t.Fatalf("migration produced load warnings: %#v", warnings)
+	}
+
+	persisted, err := os.ReadFile(filepath.Join(root, taskID+".json"))
+	if err != nil {
+		t.Fatalf("read migrated metadata: %v", err)
+	}
+	var saved Task
+	if err := json.Unmarshal(persisted, &saved); err != nil {
+		t.Fatalf("decode migrated metadata: %v", err)
+	}
+	if saved.OutputFile != canonicalOutput {
+		t.Fatalf("persisted output file = %q, want %q", saved.OutputFile, canonicalOutput)
+	}
+}
+
+func TestManagerRejectsUnrelatedAbsoluteOutputPathDuringMigration(t *testing.T) {
+	root := t.TempDir()
+	const taskID = "legacy_task"
+	if err := os.WriteFile(filepath.Join(root, taskID+".ndjson"), []byte("output\n"), 0o600); err != nil {
+		t.Fatalf("write canonical output: %v", err)
+	}
+	metadata, err := json.Marshal(Task{
+		ID:         taskID,
+		Type:       "specialist",
+		Status:     StatusCompleted,
+		OutputFile: filepath.Join(t.TempDir(), taskID+".ndjson"),
+		StartedAt:  time.Date(2026, 8, 1, 10, 0, 0, 0, time.UTC),
+	})
+	if err != nil {
+		t.Fatalf("marshal metadata: %v", err)
+	}
+	if err := os.WriteFile(filepath.Join(root, taskID+".json"), append(metadata, '\n'), 0o600); err != nil {
+		t.Fatalf("write metadata: %v", err)
+	}
+
+	manager, err := NewManager(root)
+	if err != nil {
+		t.Fatalf("NewManager returned error: %v", err)
+	}
+	if _, ok := manager.Get(taskID); ok {
+		t.Fatal("manager loaded task with an unrelated absolute output path")
+	}
+	if warnings := strings.Join(manager.LoadWarnings(), "\n"); !strings.Contains(warnings, "output file must be inside") {
+		t.Fatalf("load warnings = %q, want containment rejection", warnings)
+	}
+}
+
 func TestManagerMarksReloadedRunningTaskNonKillable(t *testing.T) {
 	root := t.TempDir()
 	manager, err := NewManager(root)

internal/cli/app.go

@@ -856,7 +856,7 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 	// A server that could not be reached or validated is skipped, not fatal (one
 	// bad MCP server must not abort startup) — surface each so a missing tool set is
 	// explained rather than silently absent. A built-in default the user never
-	// configured (e.g. keyless Firecrawl with no credentials) is the exception: it
+	// configured (e.g. keyless Exa with no credentials) is the exception: it
 	// was never asked for, so its failure is not worth a startup warning — only
 	// servers the user actually configured warn on failure (issue #552).
 	for _, skipped := range mcpRuntime.Skipped() {
@@ -948,6 +948,7 @@ func runInteractiveTUIWithSetup(stderr io.Writer, deps appDeps, permissionMode a
 		FavoriteModels:       resolved.Preferences.FavoriteModels,
 		RecentModels:         resolved.Preferences.RecentModels,
 		RecapsEnabled:        resolved.Preferences.RecapsEnabled(),
+		CompactionModel:      resolved.Preferences.CompactionModel,
 		Provider:             provider,
 		NewProvider:          deps.newProvider,
 		ProbeProviderHealth:  deps.probeProviderHealth,

internal/cli/app_test.go

@@ -211,12 +211,12 @@ func TestTUIStartupSuppressesWarningForUnconfiguredDefaultServer(t *testing.T) {
 		},
 		resolveMCPConfig: func(workspaceRoot string, excludeProject bool) (config.MCPConfig, error) {
 			return config.MCPConfig{Servers: map[string]config.MCPServerConfig{
-				"firecrawl": config.DefaultMCPServers()["firecrawl"],
+				"exa": config.DefaultMCPServers()["exa"],
 			}}, nil
 		},
 		registerMCPTools: func(context.Context, *tools.Registry, config.MCPConfig, mcp.RegisterOptions) (mcpToolRuntime, error) {
 			return fakeMCPRuntimeWithSkips{skipped: []mcp.SkippedServer{
-				{Name: "firecrawl", Err: errors.New("returned HTTP 401"), UnconfiguredDefault: true},
+				{Name: "exa", Err: errors.New("returned HTTP 401"), UnconfiguredDefault: true},
 			}}, nil
 		},
 		runTUI: func(ctx context.Context, options tui.Options) int {
@@ -227,7 +227,7 @@ func TestTUIStartupSuppressesWarningForUnconfiguredDefaultServer(t *testing.T) {
 	if exitCode != 0 {
 		t.Fatalf("exitCode = %d stderr=%s", exitCode, stderr.String())
 	}
-	if strings.Contains(stderr.String(), "firecrawl") {
+	if strings.Contains(stderr.String(), "exa") {
 		t.Fatalf("stderr = %q, want no warning for an unconfigured default server", stderr.String())
 	}
 }

internal/cli/exec.go

@@ -682,16 +682,20 @@ func runExec(args []string, stdout io.Writer, stderr io.Writer, deps appDeps) in
 		ModelSwitcher:        modelSwitcher,
 		TurnSessionProvider:  turnSessions,
 		ModelSessionSwitcher: modelSessionSwitcher,
-		ReasoningEffort:      forwardEffort,
-		Trace:                traceRecorder,
-		Cwd:                  workspaceRoot,
-		Images:               images,
-		Registry:             registry,
-		PermissionMode:       permissionMode,
-		Autonomy:             options.autonomy,
-		SelfCorrect:          selfCorrector,
-		FileDiagnostics:      fileDiagnostics,
-		Profile:              execProfile.Policy(displacedMaxTurns, execProfileFilledEffort),
+		Summarizer:           summarizerFactory(resolved, deps.newProvider),
+		ContextWindowFor: func(modelID string) int {
+			return modelregistry.AgentContextWindow(modelContextWindow(modelRegistry, modelID))
+		},
+		ReasoningEffort: forwardEffort,
+		Trace:           traceRecorder,
+		Cwd:             workspaceRoot,
+		Images:          images,
+		Registry:        registry,
+		PermissionMode:  permissionMode,
+		Autonomy:        options.autonomy,
+		SelfCorrect:     selfCorrector,
+		FileDiagnostics: fileDiagnostics,
+		Profile:         execProfile.Policy(displacedMaxTurns, execProfileFilledEffort),
 		// Headless exec: don't accept a no-tool-call turn as "done" while work
 		// clearly remains (pending plan items / a mid-step continuation cue) —
 		// nudge to continue, and finalize as INCOMPLETE rather than false success

internal/cli/mcp_default_test.go

@@ -9,15 +9,15 @@ import (
 	"github.com/Gitlawb/zero/internal/config"
 )
 
-// `zero mcp disable firecrawl` must work even though firecrawl is a built-in
+// `zero mcp disable exa` must work even though exa is a built-in
 // default that is not written to the user's config file until overridden.
-func TestRunMCPDisableSeededFirecrawlDefault(t *testing.T) {
+func TestRunMCPDisableSeededExaDefault(t *testing.T) {
 	configPath := filepath.Join(t.TempDir(), "zero", "config.json")
-	// A config with no firecrawl entry — the default lives in code, not the file.
+	// A config with no Exa entry — the default lives in code, not the file.
 	writeMCPCommandRawConfig(t, configPath, `{"activeProvider":"fast"}`)
 
 	var out, errBuf bytes.Buffer
-	code := runWithDeps([]string{"mcp", "disable", "firecrawl", "--json"}, &out, &errBuf, appDeps{
+	code := runWithDeps([]string{"mcp", "disable", "exa", "--json"}, &out, &errBuf, appDeps{
 		userConfigPath: func() (string, error) { return configPath, nil },
 	})
 	if code != exitSuccess {
@@ -31,8 +31,8 @@ func TestRunMCPDisableSeededFirecrawlDefault(t *testing.T) {
 	if err := json.Unmarshal(out.Bytes(), &payload); err != nil {
 		t.Fatalf("decode disable JSON: %v\n%s", err, out.String())
 	}
-	if payload.ServerName != "firecrawl" || !payload.Disabled || !payload.Changed {
-		t.Fatalf("disable payload = %#v, want firecrawl disabled+changed", payload)
+	if payload.ServerName != "exa" || !payload.Disabled || !payload.Changed {
+		t.Fatalf("disable payload = %#v, want exa disabled+changed", payload)
 	}
 
 	// End-to-end: resolving that config now turns the default off.
@@ -40,7 +40,7 @@ func TestRunMCPDisableSeededFirecrawlDefault(t *testing.T) {
 	if err != nil {
 		t.Fatalf("ResolveMCP: %v", err)
 	}
-	if !cfg.Servers["firecrawl"].Disabled {
-		t.Fatal("expected `mcp disable firecrawl` to turn the seeded default off in the resolved config")
+	if !cfg.Servers["exa"].Disabled {
+		t.Fatal("expected `mcp disable exa` to turn the seeded default off in the resolved config")
 	}
 }

internal/cli/summarizer.go

@@ -0,0 +1,17 @@
+package cli
+
+import (
+	"context"
+
+	"github.com/Gitlawb/zero/internal/agent"
+	"github.com/Gitlawb/zero/internal/config"
+	"github.com/Gitlawb/zero/internal/providers"
+	"github.com/Gitlawb/zero/internal/zeroruntime"
+)
+
+// summarizerFactory adapts the resolved profile and the authenticated provider
+// builder into agent.Options.Summarizer; the selection rules live in
+// providers.CompactionSummarizerFactory, shared with the TUI.
+func summarizerFactory(resolved config.ResolvedConfig, newProvider func(config.ProviderProfile) (zeroruntime.Provider, error)) func(context.Context, string) (agent.Provider, error) {
+	return providers.CompactionSummarizerFactory(resolved.Provider, resolved.Preferences.CompactionModel, newProvider)
+}

internal/config/command_test.go

@@ -105,7 +105,17 @@ func TestLoadProviderCommandTimeout(t *testing.T) {
 //
 // This is a hang-breaker, not a tuned margin. Nothing in a healthy run waits on
 // it, since both tests return about one WaitDelay after the fixture exits.
-const providerCommandTestBudget = 60 * time.Second
+const (
+	providerCommandTestBudget        = 90 * time.Second
+	providerCommandReadyWaitAttempts = 45
+)
+
+func TestProviderCommandBudgetLeavesCleanupMargin(t *testing.T) {
+	readyWaitCeiling := time.Duration(providerCommandReadyWaitAttempts) * time.Second
+	if providerCommandTestBudget < 2*readyWaitCeiling {
+		t.Fatalf("provider command test budget %s leaves less than one readiness window for cleanup after %s", providerCommandTestBudget, readyWaitCeiling)
+	}
+}
 
 // backgroundChildLifetime must exceed providerCommandTestBudget so that a child
 // dying of old age is unobservable: any run where runProviderCommand has not
@@ -341,15 +351,15 @@ func writeCommand(t *testing.T, script commandScript) string {
 			// assertion fail is far more diagnosable than blocking until the
 			// timeout fires and reporting an unrelated error. Each iteration is
 			// about a second, since `ping -n 2` sleeps between its two echoes,
-			// so the ceiling is roughly 15s: far longer than any cold PowerShell
-			// start seen on a runner, and far shorter than
-			// providerCommandTestBudget, so giving up surfaces a legible
+			// so the ceiling is roughly 45s: enough for a heavily loaded Windows
+			// runner while leaving the other half of providerCommandTestBudget for
+			// process exit, PID-file verification, and cleanup. Giving up surfaces a legible
 			// PID-file failure rather than a timeout that hides the real cause.
 			lines = append(lines,
 				":zeroWaitReady",
 				"if exist \""+readyFile+"\" goto zeroReady",
 				"set /a ZERO_READY_TRIES+=1",
-				"if %ZERO_READY_TRIES% GEQ 15 goto zeroReady",
+				"if %ZERO_READY_TRIES% GEQ "+itoa(providerCommandReadyWaitAttempts)+" goto zeroReady",
 				"ping -n 2 127.0.0.1 >nul",
 				"goto zeroWaitReady",
 				":zeroReady",

internal/config/mcp_defaults.go

@@ -5,22 +5,20 @@ import (
 	"strings"
 )
 
-// DefaultMCPServers returns the MCP servers Zero ships ENABLED by default so web
-// search and scraping work out of the box with no setup and no API key. They are
-// seeded before user/project config is merged (see ResolveMCP), so a user can
-// override any field — for example point firecrawl at a self-hosted instance, or
-// add an API-key header to lift the free-tier limit — or disable it entirely with
+// DefaultMCPServers returns the MCP servers Zero ships ENABLED by default so
+// web search and page fetching work out of the box with no setup and no API
+// key. They are seeded before user/project config is merged (see ResolveMCP),
+// so a user can override any field — for example add an API-key header to lift
+// Exa's anonymous rate limit — or disable it entirely with
 // `zero mcp disable <name>` (which writes `"disabled": true`).
 //
-// Keyless Firecrawl routes requests through firecrawl.dev (1,000 free credits per
-// month, no account). Self-host Firecrawl (AGPL-3.0) for unlimited and private
-// use. Zero only calls it over the network, so Firecrawl's license never reaches
-// into Zero's own code.
+// Exa's hosted MCP server works anonymously with rate limits. Users can add an
+// Exa API key for higher limits.
 func DefaultMCPServers() map[string]MCPServerConfig {
 	return map[string]MCPServerConfig{
-		"firecrawl": {
+		"exa": {
 			Type: "http",
-			URL:  "https://mcp.firecrawl.dev/v2/mcp",
+			URL:  "https://mcp.exa.ai/mcp",
 		},
 	}
 }
@@ -35,13 +33,13 @@ func IsDefaultMCPServer(name string) bool {
 
 // IsUnconfiguredDefault reports whether server is one of Zero's built-in
 // defaults that the user never wrote an entry for in their config — i.e. it is
-// running with whatever Zero ships (e.g. keyless Firecrawl, no credentials).
+// running with whatever Zero ships (e.g. keyless Exa, no credentials).
 //
 // Both conditions below must hold:
 //   - !server.configured: the user's JSON never declared an object for this
 //     server key at all (set by MCPServerConfig.UnmarshalJSON only when it
 //     actually ran for this key). Any explicit action — including a
-//     disable/enable toggle like `zero mcp enable firecrawl` that leaves the
+//     disable/enable toggle like `zero mcp enable exa` that leaves the
 //     resolved value unchanged — sets configured, so it always counts as
 //     user-configured, even though the value comparison below could not tell
 //     the difference on its own.
@@ -58,3 +56,90 @@ func IsUnconfiguredDefault(name string, server MCPServerConfig) bool {
 	def, ok := DefaultMCPServers()[strings.TrimSpace(name)]
 	return ok && !server.configured && reflect.DeepEqual(def, server)
 }
+
+// retiredDefaultMCPServer describes a built-in default Zero no longer ships.
+type retiredDefaultMCPServer struct {
+	// successor is the default that replaced it.
+	successor string
+	// shipped is the value Zero used to seed for this name. A user entry
+	// written while the default was still shipped may name only an override
+	// (a header, say) and rely on these fields for the rest, so they have to
+	// outlive the default itself.
+	shipped MCPServerConfig
+}
+
+// retiredDefaultMCPServers maps a retired built-in default to what replaced it
+// and to the value Zero used to ship for it.
+var retiredDefaultMCPServers = map[string]retiredDefaultMCPServer{
+	"firecrawl": {
+		successor: "exa",
+		shipped: MCPServerConfig{
+			Type: "http",
+			URL:  "https://mcp.firecrawl.dev/v2/mcp",
+		},
+	},
+}
+
+// migrateRetiredDefaultMCPServers keeps an upgrade across a default-provider
+// swap from changing what the user's config means. It handles the two ways a
+// rename can break a config written against the old default:
+//
+//   - A user who ran `zero mcp disable <old default>` made an explicit choice
+//     not to open that outbound connection. Without carrying that decision to
+//     the successor, the upgrade re-opens it under the new name — and because
+//     the replacement looks like an untouched default, even the startup
+//     warning stays quiet (see IsUnconfiguredDefault and issue #552).
+//   - A user who customized the old default could name only the field they
+//     were changing, because the seeded default supplied the transport. Once
+//     the default stops being seeded that entry resolves to a server with no
+//     type, url, or command, which fails NormalizeConfig and takes the whole
+//     startup down rather than just that one server.
+//
+// It runs immediately after the user layer merges (see ResolveMCP), which
+// scopes it to user-level decisions — the only scope whose disable is sticky.
+// The carried-over disable applies only when the user never declared the
+// successor themselves: an explicit `exa` entry wins whether it enables or
+// disables. Because the disable is recorded as a user-level decision, the
+// lower-trust project layer cannot lift it, while `zero mcp enable exa` still
+// can (the CLI override scope merges with canReenable=true).
+func migrateRetiredDefaultMCPServers(cfg *MCPConfig) {
+	for name, retired := range retiredDefaultMCPServers {
+		entry, ok := cfg.Servers[name]
+		if !ok {
+			continue
+		}
+		if inheritsRetiredTransport(entry) {
+			// Re-seed what Zero used to ship underneath the user's fields, so a
+			// partial entry still resolves to the complete server it named when
+			// it was written. Their own values still win — this only fills the
+			// gap the retired default used to cover.
+			entry = mergeMCPServer(retired.shipped, entry, true)
+			cfg.Servers[name] = entry
+		}
+		if !entry.disabledSet || !entry.Disabled {
+			continue
+		}
+		replacement, ok := cfg.Servers[retired.successor]
+		if !ok || replacement.configured {
+			continue
+		}
+		replacement.Disabled = true
+		replacement.disabledSet = true
+		cfg.Servers[retired.successor] = replacement
+	}
+}
+
+// inheritsRetiredTransport reports whether entry named no transport of its own
+// — no type, url, command, or args — and so relied entirely on the retired
+// default to supply one.
+//
+// Anything else is a complete definition the user owns (a self-hosted url, a
+// stdio command) and must be left alone: grafting the retired default's http
+// type onto an entry that names a command produces a server that is rejected
+// outright, turning a working config into a startup failure.
+func inheritsRetiredTransport(entry MCPServerConfig) bool {
+	return strings.TrimSpace(entry.Type) == "" &&
+		strings.TrimSpace(entry.URL) == "" &&
+		strings.TrimSpace(entry.Command) == "" &&
+		len(entry.Args) == 0
+}

internal/config/mcp_defaults_test.go

@@ -7,10 +7,10 @@ import (
 )
 
 func TestIsDefaultMCPServer(t *testing.T) {
-	if !IsDefaultMCPServer("firecrawl") {
-		t.Fatal("firecrawl should be a built-in default")
+	if !IsDefaultMCPServer("exa") {
+		t.Fatal("exa should be a built-in default")
 	}
-	if IsDefaultMCPServer("  firecrawl  ") == false {
+	if IsDefaultMCPServer("  exa  ") == false {
 		t.Fatal("IsDefaultMCPServer should trim whitespace")
 	}
 	if IsDefaultMCPServer("not-a-default") {
@@ -18,45 +18,45 @@ func TestIsDefaultMCPServer(t *testing.T) {
 	}
 }
 
-func TestResolveMCPSeedsEnabledFirecrawlDefault(t *testing.T) {
+func TestResolveMCPSeedsEnabledExaDefault(t *testing.T) {
 	cfg, err := ResolveMCP(ResolveOptions{})
 	if err != nil {
 		t.Fatalf("ResolveMCP: %v", err)
 	}
-	firecrawl, ok := cfg.Servers["firecrawl"]
+	exa, ok := cfg.Servers["exa"]
 	if !ok {
-		t.Fatal("expected the firecrawl default to be seeded with no user config")
+		t.Fatal("expected the exa default to be seeded with no user config")
 	}
-	if firecrawl.Type != "http" || firecrawl.URL != "https://mcp.firecrawl.dev/v2/mcp" {
-		t.Fatalf("unexpected firecrawl default: %#v", firecrawl)
+	if exa.Type != "http" || exa.URL != "https://mcp.exa.ai/mcp" {
+		t.Fatalf("unexpected exa default: %#v", exa)
 	}
-	if firecrawl.Disabled {
-		t.Fatal("the firecrawl default must be enabled out of the box")
+	if exa.Disabled {
+		t.Fatal("the exa default must be enabled out of the box")
 	}
 }
 
 func TestResolveMCPUserCanDisableDefault(t *testing.T) {
 	path := filepath.Join(t.TempDir(), "config.json")
-	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"disabled":true}}}}`), 0o600); err != nil {
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"exa":{"disabled":true}}}}`), 0o600); err != nil {
 		t.Fatal(err)
 	}
 	cfg, err := ResolveMCP(ResolveOptions{UserConfigPath: path})
 	if err != nil {
 		t.Fatalf("ResolveMCP: %v", err)
 	}
-	if !cfg.Servers["firecrawl"].Disabled {
+	if !cfg.Servers["exa"].Disabled {
 		t.Fatal("a user must be able to disable the default by writing over it")
 	}
 }
 
 func TestIsUnconfiguredDefault(t *testing.T) {
-	if !IsUnconfiguredDefault("firecrawl", DefaultMCPServers()["firecrawl"]) {
-		t.Fatal("an untouched firecrawl default should be reported as unconfigured")
+	if !IsUnconfiguredDefault("exa", DefaultMCPServers()["exa"]) {
+		t.Fatal("an untouched exa default should be reported as unconfigured")
 	}
-	if IsUnconfiguredDefault("firecrawl", MCPServerConfig{Type: "http", URL: "http://localhost:3002/mcp"}) {
+	if IsUnconfiguredDefault("exa", MCPServerConfig{Type: "http", URL: "https://example.com/mcp"}) {
 		t.Fatal("a server overriding the default URL is no longer unconfigured")
 	}
-	if IsUnconfiguredDefault("firecrawl", MCPServerConfig{Type: "http", URL: "https://mcp.firecrawl.dev/v2/mcp", Auth: "bearer"}) {
+	if IsUnconfiguredDefault("exa", MCPServerConfig{Type: "http", URL: "https://mcp.exa.ai/mcp", Auth: "bearer"}) {
 		t.Fatal("a server with credentials added is no longer unconfigured")
 	}
 	if IsUnconfiguredDefault("not-a-default", MCPServerConfig{}) {
@@ -65,57 +65,173 @@ func TestIsUnconfiguredDefault(t *testing.T) {
 }
 
 func TestResolveMCPExplicitReenableIsNotUnconfiguredDefault(t *testing.T) {
-	// `zero mcp enable firecrawl` after a prior disable writes {"disabled":false}
+	// `zero mcp enable exa` after a prior disable writes {"disabled":false}
 	// explicitly. The resolved value is identical to the untouched default (both
 	// enabled, no credentials), but the user DID take an explicit action here, so
 	// IsUnconfiguredDefault must not treat it as untouched (issue #563 review).
 	path := filepath.Join(t.TempDir(), "config.json")
-	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"disabled":false}}}}`), 0o600); err != nil {
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"exa":{"disabled":false}}}}`), 0o600); err != nil {
 		t.Fatal(err)
 	}
 	cfg, err := ResolveMCP(ResolveOptions{UserConfigPath: path})
 	if err != nil {
 		t.Fatalf("ResolveMCP: %v", err)
 	}
-	firecrawl := cfg.Servers["firecrawl"]
-	if firecrawl.Disabled {
-		t.Fatalf("explicit re-enable should leave the server enabled: %#v", firecrawl)
+	exa := cfg.Servers["exa"]
+	if exa.Disabled {
+		t.Fatalf("explicit re-enable should leave the server enabled: %#v", exa)
 	}
-	if IsUnconfiguredDefault("firecrawl", firecrawl) {
+	if IsUnconfiguredDefault("exa", exa) {
 		t.Fatal("an explicit enable/disable toggle must count as user-configured, even though the resolved value matches the default")
 	}
 }
 
 func TestResolveMCPExplicitRedeclareOfDefaultValuesIsNotUnconfiguredDefault(t *testing.T) {
-	// A user who copies firecrawl's exact default type/url into their config
+	// A user who copies Exa's exact default type/url into their config
 	// (e.g. from an example file, planning to add credentials later) produces a
-	// resolved value byte-identical to DefaultMCPServers()["firecrawl"] — the
+	// resolved value byte-identical to DefaultMCPServers()["exa"] — the
 	// same trap TestResolveMCPExplicitReenableIsNotUnconfiguredDefault covers for
 	// the disabled toggle. IsUnconfiguredDefault must still treat this as
 	// user-configured because the user's JSON declared an entry for it, even
 	// though a plain resolved-value comparison could not tell the difference.
 	path := filepath.Join(t.TempDir(), "config.json")
-	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"type":"http","url":"https://mcp.firecrawl.dev/v2/mcp"}}}}`), 0o600); err != nil {
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"exa":{"type":"http","url":"https://mcp.exa.ai/mcp"}}}}`), 0o600); err != nil {
 		t.Fatal(err)
 	}
 	cfg, err := ResolveMCP(ResolveOptions{UserConfigPath: path})
 	if err != nil {
 		t.Fatalf("ResolveMCP: %v", err)
 	}
-	firecrawl := cfg.Servers["firecrawl"]
-	want := DefaultMCPServers()["firecrawl"]
-	if firecrawl.Type != want.Type || firecrawl.URL != want.URL || firecrawl.Disabled != want.Disabled {
-		t.Fatalf("expected the resolved value to match the default's fields exactly: %#v", firecrawl)
+	exa := cfg.Servers["exa"]
+	want := DefaultMCPServers()["exa"]
+	if exa.Type != want.Type || exa.URL != want.URL || exa.Disabled != want.Disabled {
+		t.Fatalf("expected the resolved value to match the default's fields exactly: %#v", exa)
 	}
-	if IsUnconfiguredDefault("firecrawl", firecrawl) {
+	if IsUnconfiguredDefault("exa", exa) {
 		t.Fatal("redeclaring the default's exact values is still an explicit user configuration, not an untouched default")
 	}
 }
 
 func TestResolveMCPUserCanOverrideDefaultURLKeepingOtherFields(t *testing.T) {
 	path := filepath.Join(t.TempDir(), "config.json")
-	// Point firecrawl at a self-hosted instance; the default's Type must survive.
-	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"url":"http://localhost:3002/mcp"}}}}`), 0o600); err != nil {
+	// Point Exa at a proxy; the default's Type must survive.
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"exa":{"url":"https://example.com/mcp"}}}}`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	cfg, err := ResolveMCP(ResolveOptions{UserConfigPath: path})
+	if err != nil {
+		t.Fatalf("ResolveMCP: %v", err)
+	}
+	exa := cfg.Servers["exa"]
+	if exa.URL != "https://example.com/mcp" {
+		t.Fatalf("user override of the default URL did not apply: %#v", exa)
+	}
+	if exa.Type != "http" {
+		t.Fatalf("override should keep the default's other fields (type), got %#v", exa)
+	}
+}
+
+func TestResolveMCPCarriesLegacyDefaultDisableToSuccessor(t *testing.T) {
+	// Upgrade path: the user disabled the firecrawl default Zero used to ship.
+	// Swapping the default to exa must not re-open an outbound connection they
+	// explicitly switched off.
+	path := filepath.Join(t.TempDir(), "config.json")
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"disabled":true}}}}`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	cfg, err := ResolveMCP(ResolveOptions{UserConfigPath: path})
+	if err != nil {
+		t.Fatalf("ResolveMCP: %v", err)
+	}
+	if !cfg.Servers["exa"].Disabled {
+		t.Fatalf("a prior disable of the retired default must carry to its replacement: %#v", cfg.Servers["exa"])
+	}
+}
+
+func TestResolveMCPExplicitSuccessorBeatsLegacyDefaultDisable(t *testing.T) {
+	// The user disabled the old default but has since explicitly configured exa.
+	// Their newer, explicit choice wins — the migration must not override it.
+	path := filepath.Join(t.TempDir(), "config.json")
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"disabled":true},"exa":{"disabled":false}}}}`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	cfg, err := ResolveMCP(ResolveOptions{UserConfigPath: path})
+	if err != nil {
+		t.Fatalf("ResolveMCP: %v", err)
+	}
+	exa := cfg.Servers["exa"]
+	if exa.Disabled {
+		t.Fatalf("an explicit exa entry must survive the legacy-disable migration: %#v", exa)
+	}
+	if IsUnconfiguredDefault("exa", exa) {
+		t.Fatal("an explicitly configured exa is not an untouched default")
+	}
+}
+
+func TestResolveMCPLegacyDefaultLeftEnabledDoesNotDisableSuccessor(t *testing.T) {
+	// A user who configured firecrawl without disabling it (e.g. added a header)
+	// never opted out of the default search server, so exa stays enabled.
+	path := filepath.Join(t.TempDir(), "config.json")
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"headers":{"Authorization":"Bearer k"}}}}}`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	cfg, err := ResolveMCP(ResolveOptions{UserConfigPath: path})
+	if err != nil {
+		t.Fatalf("ResolveMCP: %v", err)
+	}
+	if cfg.Servers["exa"].Disabled {
+		t.Fatal("only an explicit disable of the retired default should carry over")
+	}
+}
+
+func TestResolveMCPLegacyDefaultDisableIsLiftableByOverride(t *testing.T) {
+	// The carried-over disable is a user-level decision, not a permanent one:
+	// `zero mcp enable exa` merges through the CLI override scope, which is the
+	// one layer allowed to re-enable.
+	path := filepath.Join(t.TempDir(), "config.json")
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"disabled":true}}}}`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	enabled := MCPServerConfig{Disabled: false, disabledSet: true}
+	cfg, err := ResolveMCP(ResolveOptions{
+		UserConfigPath: path,
+		Overrides:      Overrides{MCP: MCPConfig{Servers: map[string]MCPServerConfig{"exa": enabled}}},
+	})
+	if err != nil {
+		t.Fatalf("ResolveMCP: %v", err)
+	}
+	if cfg.Servers["exa"].Disabled {
+		t.Fatalf("an explicit enable must lift the carried-over disable: %#v", cfg.Servers["exa"])
+	}
+}
+
+func TestResolveMCPLegacyDisableSurvivesProjectReenable(t *testing.T) {
+	// The project layer is lower-trust and must not lift the carried-over
+	// user-level disable — the same guard a direct `zero mcp disable exa` gets.
+	dir := t.TempDir()
+	userPath := filepath.Join(dir, "config.json")
+	if err := os.WriteFile(userPath, []byte(`{"mcp":{"servers":{"firecrawl":{"disabled":true}}}}`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	projectPath := filepath.Join(dir, "project.json")
+	if err := os.WriteFile(projectPath, []byte(`{"mcp":{"servers":{"exa":{"disabled":false}}}}`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	cfg, err := ResolveMCP(ResolveOptions{UserConfigPath: userPath, ProjectConfigPath: projectPath})
+	if err != nil {
+		t.Fatalf("ResolveMCP: %v", err)
+	}
+	if !cfg.Servers["exa"].Disabled {
+		t.Fatal("project config must not re-enable a server the user disabled")
+	}
+}
+
+func TestResolveMCPKeepsRetiredDefaultTransportForPartialEntry(t *testing.T) {
+	// A user who added an API key to the firecrawl default wrote only the header
+	// — the seeded default supplied the http type and URL. Retiring the default
+	// must not strip those out from under them and leave an unusable server.
+	path := filepath.Join(t.TempDir(), "config.json")
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"headers":{"Authorization":"Bearer k"}}}}}`), 0o600); err != nil {
 		t.Fatal(err)
 	}
 	cfg, err := ResolveMCP(ResolveOptions{UserConfigPath: path})
@@ -123,10 +239,55 @@ func TestResolveMCPUserCanOverrideDefaultURLKeepingOtherFields(t *testing.T) {
 		t.Fatalf("ResolveMCP: %v", err)
 	}
 	firecrawl := cfg.Servers["firecrawl"]
-	if firecrawl.URL != "http://localhost:3002/mcp" {
-		t.Fatalf("user override of the default URL did not apply: %#v", firecrawl)
+	if firecrawl.Type != "http" || firecrawl.URL != "https://mcp.firecrawl.dev/v2/mcp" {
+		t.Fatalf("a partial entry must keep the retired default's transport: %#v", firecrawl)
 	}
-	if firecrawl.Type != "http" {
-		t.Fatalf("override should keep the default's other fields (type), got %#v", firecrawl)
+	if firecrawl.Headers["Authorization"] != "Bearer k" {
+		t.Fatalf("the user's own field must still win: %#v", firecrawl)
+	}
+}
+
+func TestResolveMCPDoesNotGraftRetiredDefaultOntoOwnTransport(t *testing.T) {
+	// A self-hosted firecrawl over stdio is a complete definition the user owns.
+	// Re-seeding the retired http default under it would produce an http server
+	// carrying a command, which NormalizeConfig rejects outright.
+	path := filepath.Join(t.TempDir(), "config.json")
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"command":"firecrawl-mcp"}}}}`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	cfg, err := ResolveMCP(ResolveOptions{UserConfigPath: path})
+	if err != nil {
+		t.Fatalf("ResolveMCP: %v", err)
+	}
+	firecrawl := cfg.Servers["firecrawl"]
+	if firecrawl.Type != "" || firecrawl.URL != "" {
+		t.Fatalf("an entry naming its own transport must be left alone: %#v", firecrawl)
+	}
+	if firecrawl.Command != "firecrawl-mcp" {
+		t.Fatalf("the user's command must survive: %#v", firecrawl)
+	}
+}
+
+func TestResolveMCPDisabledRetiredEntryStaysReEnableable(t *testing.T) {
+	// The disable carries to exa, and the retired entry itself keeps a usable
+	// transport so a later `zero mcp enable firecrawl` does not resolve to a
+	// server with no type, url, or command.
+	path := filepath.Join(t.TempDir(), "config.json")
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"disabled":true}}}}`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	cfg, err := ResolveMCP(ResolveOptions{UserConfigPath: path})
+	if err != nil {
+		t.Fatalf("ResolveMCP: %v", err)
+	}
+	firecrawl := cfg.Servers["firecrawl"]
+	if !firecrawl.Disabled {
+		t.Fatalf("the retired entry must stay disabled: %#v", firecrawl)
+	}
+	if firecrawl.Type != "http" || firecrawl.URL != "https://mcp.firecrawl.dev/v2/mcp" {
+		t.Fatalf("a disabled retired entry should still carry a usable transport: %#v", firecrawl)
+	}
+	if !cfg.Servers["exa"].Disabled {
+		t.Fatal("the disable must still carry to the successor")
 	}
 }

internal/config/resolve_mcp_exclude_project_test.go

@@ -34,7 +34,7 @@ func TestResolveMCPExcludeProjectDropsProjectServers(t *testing.T) {
 		if _, ok := cfg.Servers["user-srv"]; !ok {
 			t.Fatal("the user server must always be present")
 		}
-		if _, ok := cfg.Servers["firecrawl"]; !ok {
+		if _, ok := cfg.Servers["exa"]; !ok {
 			t.Fatal("the built-in default must always be present")
 		}
 	})
@@ -54,7 +54,7 @@ func TestResolveMCPExcludeProjectDropsProjectServers(t *testing.T) {
 		if _, ok := cfg.Servers["user-srv"]; !ok {
 			t.Fatal("the user server must survive when the project layer is dropped")
 		}
-		if _, ok := cfg.Servers["firecrawl"]; !ok {
+		if _, ok := cfg.Servers["exa"]; !ok {
 			t.Fatal("the built-in default must survive when the project layer is dropped")
 		}
 	})

internal/config/resolver.go

@@ -180,7 +180,7 @@ func Resolve(options ResolveOptions) (ResolvedConfig, error) {
 }
 
 func ResolveMCP(options ResolveOptions) (MCPConfig, error) {
-	// Seed Zero's built-in default MCP servers (e.g. keyless Firecrawl for free,
+	// Seed Zero's built-in default MCP servers (e.g. keyless Exa for free,
 	// no-setup web search/scrape) BEFORE merging user/project config, so the user
 	// can override any field or disable a default by writing over it.
 	cfg := FileConfig{MCP: MCPConfig{Servers: DefaultMCPServers()}}
@@ -194,6 +194,10 @@ func ResolveMCP(options ResolveOptions) (MCPConfig, error) {
 		// server the user disabled (a user-level disable is sticky, but the user
 		// scope itself may lift it).
 		mergeMCPConfig(&cfg.MCP, fileConfig.MCP, true)
+		// Reconcile config written against a default Zero has since retired,
+		// here while the user layer is the only one merged — so a carried-over
+		// disable counts as a user-level decision the project layer cannot lift.
+		migrateRetiredDefaultMCPServers(&cfg.MCP)
 	}
 	// Drop the project layer when the workspace is untrusted, so a cloned repo's
 	// ./.zero/config.json cannot register (and spawn) MCP servers. Fail-closed:

internal/config/types.go

@@ -119,6 +119,12 @@ type PreferencesConfig struct {
 	// the user turned idle recaps off. A *bool is its own tri-state, so no
 	// custom unmarshal is needed (unlike ToolsConfig.DeferThreshold's int).
 	Recaps *bool `json:"recaps,omitempty"`
+	// CompactionModel routes compaction summarization calls to this model
+	// instead of the session's main model (summaries at main-model prices are
+	// the most expensive recurring event in long runs). Empty = automatic: a
+	// curated cheap model on official endpoints, the main model elsewhere.
+	// "main" forces the main model. ZERO_COMPACTION_MODEL overrides.
+	CompactionModel string `json:"compactionModel,omitempty"`
 }
 
 // RecentModelEntry is one provider-qualified model selection recorded in
@@ -151,7 +157,8 @@ type KeyBindingsConfig struct {
 	ToggleMouse KeyBindingDef `json:"toggleMouse,omitempty"`
 	// CycleReasoning cycles through reasoning effort levels (default: ctrl+t).
 	CycleReasoning KeyBindingDef `json:"cycleReasoning,omitempty"`
-	// TogglePlan toggles the plan panel expansion (default: ctrl+p).
+	// TogglePlan is retained for configuration compatibility. Plan updates render
+	// in the transcript and no longer have a persistent panel to toggle.
 	TogglePlan KeyBindingDef `json:"togglePlan,omitempty"`
 	// ToggleSidebar toggles the right context sidebar (default: ctrl+b).
 	ToggleSidebar KeyBindingDef `json:"toggleSidebar,omitempty"`
@@ -464,7 +471,7 @@ type MCPServerConfig struct {
 	// fields it set or what values they hold. A built-in default seeded by
 	// DefaultMCPServers() is never unmarshaled from JSON, so it starts false;
 	// any explicit entry in the user/project file — even one that happens to
-	// repeat a default's exact field values (e.g. re-declaring firecrawl's
+	// repeat a default's exact field values (e.g. re-declaring Exa's
 	// default URL) — sets it true. IsUnconfiguredDefault checks this alongside
 	// a resolved-value comparison, so redeclaring default values verbatim still
 	// counts as user-configured.

internal/execution/contracts.go

@@ -9,7 +9,16 @@ import (
 	"strings"
 )
 
-const PolicyVersion = 1
+// PolicyVersion is the version of the approval policy that recorded grants were
+// evaluated under. Bump it whenever a change narrows what may be approved: the
+// grant store then backs the file up, keeps deny grants, invalidates prior
+// approvals, and tells the user once, instead of silently honoring approvals
+// that the current rules would have refused.
+//
+// v2 tightened command-prefix validation so a launcher spelled with a version
+// or an executable extension ("python3.11", "python.exe") can no longer be
+// approved as an ordinary command.
+const PolicyVersion = 2
 
 type Origin string
 

internal/mcp/config.go

@@ -35,7 +35,7 @@ type Server struct {
 	// credential lookup uses it to avoid reusing legacy user tokens by name.
 	ProjectConfigured bool
 	// UnconfiguredDefault is true when this server is one of Zero's built-in
-	// defaults (e.g. keyless Firecrawl) that the user never touched in their
+	// defaults (e.g. keyless Exa) that the user never touched in their
 	// config — no credentials, no overrides. Callers use it to avoid warning
 	// loudly when a server nobody configured fails to connect.
 	UnconfiguredDefault bool

internal/mcp/config_test.go

@@ -1,6 +1,8 @@
 package mcp
 
 import (
+	"os"
+	"path/filepath"
 	"strings"
 	"testing"
 
@@ -90,7 +92,7 @@ func TestNormalizeConfigValidatesTransportBoundaries(t *testing.T) {
 
 func TestNormalizeConfigFlagsUnconfiguredDefault(t *testing.T) {
 	cfg := config.MCPConfig{Servers: map[string]config.MCPServerConfig{
-		"firecrawl": config.DefaultMCPServers()["firecrawl"],
+		"exa": config.DefaultMCPServers()["exa"],
 		"web": {
 			Type: "http",
 			URL:  "https://example.com/mcp",
@@ -107,8 +109,8 @@ func TestNormalizeConfigFlagsUnconfiguredDefault(t *testing.T) {
 		byName[server.Name] = server
 	}
 
-	if !byName["firecrawl"].UnconfiguredDefault {
-		t.Fatal("an untouched firecrawl default should be flagged UnconfiguredDefault")
+	if !byName["exa"].UnconfiguredDefault {
+		t.Fatal("an untouched exa default should be flagged UnconfiguredDefault")
 	}
 	if byName["web"].UnconfiguredDefault {
 		t.Fatal("a server the user configured must not be flagged UnconfiguredDefault")
@@ -240,3 +242,116 @@ func TestCopyStringMapTrimsKeysAndPreservesValues(t *testing.T) {
 		t.Fatalf("copied[TOKEN] = %q, want value preserved verbatim", copied["TOKEN"])
 	}
 }
+
+// Startup behavior for the firecrawl -> exa default migration: a user who
+// disabled the retired default must end up with no Exa server to connect to,
+// not merely a disabled entry in the resolved config.
+func TestNormalizeConfigSkipsExaAfterLegacyFirecrawlDisable(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "config.json")
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"disabled":true}}}}`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	cfg, err := config.ResolveMCP(config.ResolveOptions{UserConfigPath: path})
+	if err != nil {
+		t.Fatalf("ResolveMCP: %v", err)
+	}
+	servers, err := NormalizeConfig(cfg)
+	if err != nil {
+		t.Fatalf("NormalizeConfig: %v", err)
+	}
+	for _, server := range servers {
+		if server.Name == "exa" {
+			t.Fatalf("exa must not be started after the user disabled the default it replaced: %#v", server)
+		}
+	}
+}
+
+// The same path with no legacy disable still starts Exa, so the migration
+// cannot quietly switch off the default for everyone else.
+func TestNormalizeConfigStartsExaWithoutLegacyDisable(t *testing.T) {
+	cfg, err := config.ResolveMCP(config.ResolveOptions{})
+	if err != nil {
+		t.Fatalf("ResolveMCP: %v", err)
+	}
+	servers, err := NormalizeConfig(cfg)
+	if err != nil {
+		t.Fatalf("NormalizeConfig: %v", err)
+	}
+	for _, server := range servers {
+		if server.Name == "exa" {
+			if !server.UnconfiguredDefault {
+				t.Fatalf("an untouched exa default should be flagged unconfigured: %#v", server)
+			}
+			return
+		}
+	}
+	t.Fatal("expected the exa default to be started out of the box")
+}
+
+// The failure path CodeRabbit flagged: a firecrawl entry that named only a
+// header relied on the retired default for its transport. Resolving it must
+// still produce a complete server — an incomplete one fails NormalizeConfig,
+// which takes down every other server's startup with it, not just this one.
+func TestNormalizeConfigResolvesPartialRetiredDefaultEntry(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "config.json")
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"headers":{"Authorization":"Bearer k"}}}}}`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	cfg, err := config.ResolveMCP(config.ResolveOptions{UserConfigPath: path})
+	if err != nil {
+		t.Fatalf("ResolveMCP: %v", err)
+	}
+	servers, err := NormalizeConfig(cfg)
+	if err != nil {
+		t.Fatalf("a header-only legacy entry must not break startup: %v", err)
+	}
+	var firecrawl *Server
+	var sawExa bool
+	for i := range servers {
+		switch servers[i].Name {
+		case "firecrawl":
+			firecrawl = &servers[i]
+		case "exa":
+			sawExa = true
+		}
+	}
+	if firecrawl == nil {
+		t.Fatalf("expected the customized firecrawl server to survive: %#v", servers)
+	}
+	if firecrawl.Type != ServerTypeHTTP || firecrawl.URL != "https://mcp.firecrawl.dev/v2/mcp" {
+		t.Fatalf("firecrawl lost the transport its entry relied on: %#v", *firecrawl)
+	}
+	if firecrawl.Headers["Authorization"] != "Bearer k" {
+		t.Fatalf("firecrawl lost the user's header: %#v", *firecrawl)
+	}
+	if !sawExa {
+		t.Fatal("the new exa default should still start alongside it")
+	}
+}
+
+// The mirror case: an entry that names its own stdio transport must not have
+// the retired http default grafted onto it, which would be rejected outright.
+func TestNormalizeConfigLeavesRetiredEntryWithOwnTransportAlone(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "config.json")
+	if err := os.WriteFile(path, []byte(`{"mcp":{"servers":{"firecrawl":{"command":"firecrawl-mcp"}}}}`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	cfg, err := config.ResolveMCP(config.ResolveOptions{UserConfigPath: path})
+	if err != nil {
+		t.Fatalf("ResolveMCP: %v", err)
+	}
+	servers, err := NormalizeConfig(cfg)
+	if err != nil {
+		t.Fatalf("a self-hosted stdio entry must keep working: %v", err)
+	}
+	for _, server := range servers {
+		if server.Name != "firecrawl" {
+			continue
+		}
+		if server.Type != ServerTypeStdio || server.Command != "firecrawl-mcp" {
+			t.Fatalf("the user's own stdio transport was corrupted: %#v", server)
+		}
+		return
+	}
+	t.Fatalf("expected the self-hosted firecrawl server to survive: %#v", servers)
+}

internal/mcp/registry_test.go

@@ -153,16 +153,16 @@ func TestRegisterToolsSkipsUnreachableServerAndKeepsOthers(t *testing.T) {
 }
 
 func TestRegisterToolsFlagsUnconfiguredDefaultOnSkip(t *testing.T) {
-	// firecrawl is seeded by config.DefaultMCPServers with no credentials; when a
-	// user never configures it, a connect failure (e.g. the real HTTP 401 from
-	// issue #552) must be recorded as UnconfiguredDefault so callers can avoid
+	// Exa is seeded by config.DefaultMCPServers with no credentials; when a
+	// user never configures it, a connect failure must be recorded as
+	// UnconfiguredDefault so callers can avoid
 	// warning about a server the user never asked for. "custom" is configured by
 	// the user and must NOT be flagged even though it also fails to connect.
 	registry := tools.NewRegistry()
 
 	runtime, err := RegisterTools(context.Background(), registry, config.MCPConfig{Servers: map[string]config.MCPServerConfig{
-		"firecrawl": config.DefaultMCPServers()["firecrawl"],
-		"custom":    {Type: "stdio", Command: "custom-mcp"},
+		"exa":    config.DefaultMCPServers()["exa"],
+		"custom": {Type: "stdio", Command: "custom-mcp"},
 	}}, RegisterOptions{
 		ClientFactory: func(_ context.Context, server Server) (ToolClient, error) {
 			return nil, errors.New(server.Name + " connect failed")
@@ -177,12 +177,12 @@ func TestRegisterToolsFlagsUnconfiguredDefaultOnSkip(t *testing.T) {
 	for _, skipped := range runtime.Skipped() {
 		byName[skipped.Name] = skipped
 	}
-	firecrawl, ok := byName["firecrawl"]
+	exa, ok := byName["exa"]
 	if !ok {
-		t.Fatalf("Skipped() = %#v, want an entry for firecrawl", runtime.Skipped())
+		t.Fatalf("Skipped() = %#v, want an entry for exa", runtime.Skipped())
 	}
-	if !firecrawl.UnconfiguredDefault {
-		t.Fatalf("Skipped()[firecrawl] = %#v, want UnconfiguredDefault", firecrawl)
+	if !exa.UnconfiguredDefault {
+		t.Fatalf("Skipped()[exa] = %#v, want UnconfiguredDefault", exa)
 	}
 	custom, ok := byName["custom"]
 	if !ok {

internal/modelregistry/catalog.go

@@ -231,6 +231,12 @@ func reasoningEffortsForModelName(name string) []ReasoningEffort {
 		// the gateway's translation concern — unknown fields are ignored, so the
 		// worst case is a silent no-op rather than a 400.
 		return []ReasoningEffort{ReasoningEffortLow, ReasoningEffortMedium, ReasoningEffortHigh}
+	case strings.Contains(n, "deepseek"):
+		// DeepSeek V4 (deepseek-v4-flash / deepseek-v4-pro) exposes thinking-mode
+		// effort control through the OpenAI-compatible reasoning_effort parameter.
+		// The API accepts low/high/max and maps medium/xhigh onto high, so only
+		// the three distinct tiers are advertised.
+		return []ReasoningEffort{ReasoningEffortLow, ReasoningEffortHigh, ReasoningEffortMax}
 	default:
 		return nil
 	}

internal/modelregistry/effort_fallback_test.go

@@ -20,6 +20,10 @@ func TestReasoningEffortsFallbackForGPT5AndOSeries(t *testing.T) {
 		{"hy3", []ReasoningEffort{ReasoningEffortLow, ReasoningEffortMedium, ReasoningEffortHigh}},
 		{"hunyuan-t1", []ReasoningEffort{ReasoningEffortLow, ReasoningEffortMedium, ReasoningEffortHigh}},
 		{"openai/o3-mini", []ReasoningEffort{ReasoningEffortLow, ReasoningEffortMedium, ReasoningEffortHigh}}, // github-style vendor/ id
+		{"deepseek-v4-flash", []ReasoningEffort{ReasoningEffortLow, ReasoningEffortHigh, ReasoningEffortMax}},
+		{"deepseek-v4-pro", []ReasoningEffort{ReasoningEffortLow, ReasoningEffortHigh, ReasoningEffortMax}},
+		{"deepseek-reasoner", []ReasoningEffort{ReasoningEffortLow, ReasoningEffortHigh, ReasoningEffortMax}},
+		{"deepseek-chat", []ReasoningEffort{ReasoningEffortLow, ReasoningEffortHigh, ReasoningEffortMax}},
 		{"gpt-4.1", nil}, // non-reasoning, registered: stays empty
 		{"gpt-4o-mini", nil},
 		{"ollama/llama3.1", nil},

internal/peermsg/private_dir_windows.go

@@ -104,7 +104,7 @@ func windowsTokenOwner(token windows.Token) (*windows.SID, error) {
 	}
 	owner := (*windowsTokenOwnerInfo)(unsafe.Pointer(&buffer[0])).owner
 	if owner == nil {
-		return nil, errors.New("Windows access token has no default owner")
+		return nil, errors.New("windows access token has no default owner")
 	}
 	return owner.Copy()
 }

internal/providermodelcatalog/remote.go

@@ -184,6 +184,10 @@ func parseOpenAIStyleModelList(body []byte) ([]remoteModel, error) {
 
 func ModelsDevProviderID(provider providercatalog.Descriptor) string {
 	switch strings.TrimSpace(provider.ID) {
+	case "chatgpt":
+		// ChatGPT authenticates against the Codex backend, while its public
+		// model metadata is published under the OpenAI provider on models.dev.
+		return "openai"
 	case "dashscope":
 		return "alibaba"
 	case "github":

internal/providermodelcatalog/remote_test.go

@@ -241,6 +241,7 @@ func TestPublicLiveCatalog(t *testing.T) {
 
 func TestModelsDevProviderIDMapsZeroAliases(t *testing.T) {
 	tests := map[string]string{
+		"chatgpt":      "openai",
 		"github":       "github-models",
 		"moonshot":     "moonshotai",
 		"nvidia-nim":   "nvidia",

internal/providermodeldiscovery/discovery.go

@@ -539,7 +539,8 @@ func mergeLiveModels(provider providercatalog.Descriptor, liveModels []Model, ca
 	hasCatalog := len(byID) > 0
 	// Aggregators publish the live list as the source of truth. Keep live-only
 	// ids even when a remote catalog also loaded, instead of intersecting.
-	preferLive := providermodelcatalog.PublicLiveCatalog(provider.ID) ||
+	preferLive := provider.Local ||
+		providermodelcatalog.PublicLiveCatalog(provider.ID) ||
 		providercatalog.NormalizeID(provider.ID) == "chatgpt"
 	result := make([]Model, 0, len(liveModels))
 	for _, live := range liveModels {

internal/providermodeldiscovery/discovery_test.go

@@ -139,6 +139,68 @@ func TestMergeChatGPTModelsKeepsLiveOnlyEntries(t *testing.T) {
 	}
 }
 
+func TestDiscoverCatalogChatGPTMergesOpenAIModelsDevMetadata(t *testing.T) {
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		switch r.URL.Path {
+		case "/api.json":
+			_, _ = w.Write([]byte(`{
+				"openai": {"models": {
+					"gpt-5.6-sol": {
+						"id": "gpt-5.6-sol",
+						"name": "GPT-5.6 Sol",
+						"description": "Frontier coding model",
+						"tool_call": true,
+						"reasoning": true,
+						"reasoning_efforts": ["low", "high", "max"],
+						"limit": {"context": 1050000},
+						"modalities": {"input": ["text", "image", "pdf"], "output": ["text"]}
+					}
+				}}
+			}`))
+		case "/backend-api/codex/models":
+			_, _ = w.Write([]byte(`{"data":[{"id":"gpt-5.6-sol"}]}`))
+		default:
+			t.Errorf("unexpected request path %q", r.URL.Path)
+			http.NotFound(w, r)
+			return
+		}
+	}))
+	defer server.Close()
+
+	provider, ok := providercatalog.Get("chatgpt")
+	if !ok {
+		t.Fatal("ChatGPT provider missing from catalog")
+	}
+	models, err := DiscoverCatalog(context.Background(), provider, config.ProviderProfile{
+		Name:         "chatgpt",
+		CatalogID:    "chatgpt",
+		ProviderKind: config.ProviderKindOpenAICompatible,
+		BaseURL:      server.URL + "/backend-api/codex",
+	}, Options{
+		HTTPClient:   server.Client(),
+		ModelsDevURL: server.URL + "/api.json",
+		OAuthResolver: func(context.Context, bool) (string, string, bool, error) {
+			return "Authorization", "Bearer test", true, nil
+		},
+	})
+	if err != nil {
+		t.Fatalf("DiscoverCatalog returned error: %v", err)
+	}
+	if len(models) != 1 {
+		t.Fatalf("models = %#v, want one ChatGPT live model", models)
+	}
+	model := models[0]
+	if model.ID != "gpt-5.6-sol" || model.ContextWindow != 1050000 || !model.ToolCall || !model.Reasoning {
+		t.Fatalf("merged ChatGPT model = %#v, want models.dev metadata", model)
+	}
+	if got := strings.Join(model.InputModalities, ","); got != "text,image,pdf" {
+		t.Fatalf("input modalities = %q, want text,image,pdf", got)
+	}
+	if got := strings.Join(model.ReasoningEfforts, ","); got != "low,high,max" {
+		t.Fatalf("reasoning efforts = %q, want low,high,max", got)
+	}
+}
+
 func TestMergeLiveModelsUsesLiveDefaultsAndReasoningCapability(t *testing.T) {
 	models := mergeLiveModels(
 		providercatalog.Descriptor{ID: "chatgpt"},
@@ -164,6 +226,29 @@ func TestMergeLiveModelsUsesLiveDefaultsAndReasoningCapability(t *testing.T) {
 	}
 }
 
+func TestMergeLocalModelsKeepsLiveOnlyEntries(t *testing.T) {
+	models := mergeLiveModels(
+		providercatalog.Descriptor{ID: "lmstudio", Local: true},
+		[]Model{
+			{ID: "qwen3-coder-30b", ContextWindow: 32768},
+			{ID: "text-embedding-local"},
+			{ID: "qwen2.5-coder-32b-instruct", Description: "live description"},
+		},
+		[]Model{{ID: "qwen2.5-coder-32b-instruct", Description: "catalog description", ToolCall: true}},
+	)
+
+	if got, want := strings.Join(modelIDs(models), ","), "qwen3-coder-30b,qwen2.5-coder-32b-instruct"; got != want {
+		t.Fatalf("models = %q, want %q", got, want)
+	}
+	for _, model := range models {
+		if model.ID == "qwen2.5-coder-32b-instruct" {
+			if model.Description != "catalog description" || !model.ToolCall {
+				t.Fatalf("merged catalog metadata = %#v", model)
+			}
+		}
+	}
+}
+
 func TestDiscoverCatalogOpenGatewayUsesLiveListWithoutKey(t *testing.T) {
 	// Catalog and live endpoints return distinct payloads so the merge must keep
 	// live-only ids that are absent from the remote catalog response.

internal/providers/compaction_model.go

@@ -0,0 +1,108 @@
+package providers
+
+import (
+	"context"
+	"os"
+	"strings"
+
+	"github.com/Gitlawb/zero/internal/config"
+	"github.com/Gitlawb/zero/internal/zeroruntime"
+)
+
+// Compaction summarization model selection.
+//
+// Compaction summaries used to run on the session's main model — near a 200k
+// window one summarization is a ~100k-token input call at full price, the
+// single most expensive recurring event in a long run. A cheap model handles
+// the "dense factual summary" task fine, so summarization is routed to one
+// whenever the target is knowable.
+//
+// Resolution order: ZERO_COMPACTION_MODEL env > preferences.compactionModel
+// config > a curated per-kind default (OFFICIAL endpoints only) > "" (use the
+// main model). The literal value "main" at any level forces the main model.
+// A wrong choice is never fatal: the agent falls back to the main provider on
+// the first summarizer failure for the rest of the run.
+
+// CompactionModelEnv overrides the compaction summarization model.
+const CompactionModelEnv = "ZERO_COMPACTION_MODEL"
+
+// compactionMainSentinel disables the dedicated summarizer explicitly.
+const compactionMainSentinel = "main"
+
+// Curated cheap summarizer defaults, applied only for provider kinds whose
+// model catalog is guaranteed (official endpoints). Custom / *-compatible
+// endpoints get NO default — their catalogs are unknowable, and a guaranteed
+// failed call per run is worse than main-model prices.
+const (
+	defaultAnthropicCompactionModel = "claude-haiku-4-5-20251001"
+	defaultGoogleCompactionModel    = "gemini-2.5-flash-lite"
+	defaultOpenAICompactionModel    = "gpt-4.1-mini"
+)
+
+// CompactionModelID returns the model that compaction summarization calls
+// should use for the given profile, or "" to use the session's main model.
+// preference is the resolved config value (preferences.compactionModel).
+func CompactionModelID(profile config.ProviderProfile, preference string) string {
+	value := strings.TrimSpace(os.Getenv(CompactionModelEnv))
+	if value == "" {
+		value = strings.TrimSpace(preference)
+	}
+	if value != "" {
+		if strings.EqualFold(value, compactionMainSentinel) {
+			return ""
+		}
+		return value
+	}
+	return defaultCompactionModel(profile)
+}
+
+func defaultCompactionModel(profile config.ProviderProfile) string {
+	metadata, err := ResolveRuntimeMetadata(profile, Options{})
+	if err != nil {
+		return ""
+	}
+	var candidate string
+	switch metadata.ProviderKind {
+	case config.ProviderKindAnthropic:
+		candidate = defaultAnthropicCompactionModel
+	case config.ProviderKindGoogle:
+		candidate = defaultGoogleCompactionModel
+	case config.ProviderKindOpenAI:
+		candidate = defaultOpenAICompactionModel
+	default:
+		return ""
+	}
+	// Session already runs on the cheap model: a dedicated summarizer buys
+	// nothing and would only add a second provider instance.
+	if strings.EqualFold(strings.TrimSpace(metadata.APIModel), candidate) {
+		return ""
+	}
+	return candidate
+}
+
+// CompactionSummarizerFactory returns the lazy constructor the agent loop
+// calls for its dedicated compaction summarizer (agent.Options.Summarizer).
+// The compactor passes the main model in force at that moment — on the first
+// paid compaction and again after a mid-run model switch — so the choice
+// tracks escalations: a run that starts on the cheap model gets no dedicated
+// summarizer, and gains one once it escalates to a pricier main model.
+// Returning (nil, nil) means "summarize on the main provider". The factory
+// itself is nil only when no provider builder exists. Shared by the exec and
+// TUI front ends so the selection rules cannot drift between them.
+func CompactionSummarizerFactory(base config.ProviderProfile, preference string, newProvider func(config.ProviderProfile) (zeroruntime.Provider, error)) func(context.Context, string) (zeroruntime.Provider, error) {
+	if newProvider == nil {
+		return nil
+	}
+	return func(_ context.Context, mainModelID string) (zeroruntime.Provider, error) {
+		profile := base
+		if strings.TrimSpace(mainModelID) != "" {
+			profile.Model = mainModelID
+		}
+		modelID := CompactionModelID(profile, preference)
+		if modelID == "" {
+			return nil, nil
+		}
+		profile.Model = modelID
+		return newProvider(profile)
+	}
+}

internal/providers/compaction_model_test.go

@@ -0,0 +1,113 @@
+package providers
+
+import (
+	"context"
+	"errors"
+	"testing"
+
+	"github.com/Gitlawb/zero/internal/config"
+	"github.com/Gitlawb/zero/internal/zeroruntime"
+)
+
+func TestCompactionModelIDResolutionOrder(t *testing.T) {
+	anthropic := config.ProviderProfile{
+		Name:         "anthropic",
+		ProviderKind: config.ProviderKindAnthropic,
+		Model:        "claude-sonnet-4.5",
+	}
+
+	t.Setenv(CompactionModelEnv, "my-env-model")
+	if got := CompactionModelID(anthropic, "my-config-model"); got != "my-env-model" {
+		t.Fatalf("env must win, got %q", got)
+	}
+
+	t.Setenv(CompactionModelEnv, "main")
+	if got := CompactionModelID(anthropic, "my-config-model"); got != "" {
+		t.Fatalf("env 'main' must force the main model, got %q", got)
+	}
+
+	t.Setenv(CompactionModelEnv, "")
+	if got := CompactionModelID(anthropic, "my-config-model"); got != "my-config-model" {
+		t.Fatalf("config preference must apply when env unset, got %q", got)
+	}
+	if got := CompactionModelID(anthropic, "main"); got != "" {
+		t.Fatalf("config 'main' must force the main model, got %q", got)
+	}
+}
+
+func TestCompactionModelIDCuratedDefaults(t *testing.T) {
+	t.Setenv(CompactionModelEnv, "")
+
+	anthropic := config.ProviderProfile{Name: "anthropic", ProviderKind: config.ProviderKindAnthropic, Model: "claude-sonnet-4.5"}
+	if got := CompactionModelID(anthropic, ""); got != defaultAnthropicCompactionModel {
+		t.Fatalf("anthropic default = %q, want %q", got, defaultAnthropicCompactionModel)
+	}
+
+	google := config.ProviderProfile{Name: "google", ProviderKind: config.ProviderKindGoogle, Model: "gemini-2.5-pro"}
+	if got := CompactionModelID(google, ""); got != defaultGoogleCompactionModel {
+		t.Fatalf("google default = %q, want %q", got, defaultGoogleCompactionModel)
+	}
+
+	openai := config.ProviderProfile{Name: "openai", ProviderKind: config.ProviderKindOpenAI, Model: "gpt-4.1"}
+	if got := CompactionModelID(openai, ""); got != defaultOpenAICompactionModel {
+		t.Fatalf("openai default = %q, want %q", got, defaultOpenAICompactionModel)
+	}
+
+	// Custom/compatible endpoints: catalog unknowable, no default.
+	compatible := config.ProviderProfile{
+		Name:         "opengateway",
+		ProviderKind: config.ProviderKindOpenAICompatible,
+		BaseURL:      "https://opengateway.gitlawb.com/v1",
+		Model:        "some-model",
+	}
+	if got := CompactionModelID(compatible, ""); got != "" {
+		t.Fatalf("openai-compatible must have no default, got %q", got)
+	}
+}
+
+func TestCompactionModelIDSkipsWhenMainIsAlreadyCheap(t *testing.T) {
+	t.Setenv(CompactionModelEnv, "")
+	haiku := config.ProviderProfile{
+		Name:         "anthropic",
+		ProviderKind: config.ProviderKindAnthropic,
+		Model:        defaultAnthropicCompactionModel,
+	}
+	if got := CompactionModelID(haiku, ""); got != "" {
+		t.Fatalf("already-cheap session must not get a dedicated summarizer, got %q", got)
+	}
+}
+
+func TestCompactionSummarizerFactoryTracksMainModel(t *testing.T) {
+	t.Setenv(CompactionModelEnv, "")
+	base := config.ProviderProfile{Name: "anthropic", ProviderKind: config.ProviderKindAnthropic, Model: defaultAnthropicCompactionModel}
+	var built []string
+	newProvider := func(profile config.ProviderProfile) (zeroruntime.Provider, error) {
+		built = append(built, profile.Model)
+		return nil, errors.New("not needed")
+	}
+	factory := CompactionSummarizerFactory(base, "", newProvider)
+	if factory == nil {
+		t.Fatal("factory must exist when a provider builder exists")
+	}
+	// Main model is the cheap default: no dedicated summarizer, nothing built.
+	if provider, err := factory(context.Background(), defaultAnthropicCompactionModel); provider != nil || err != nil || len(built) != 0 {
+		t.Fatalf("cheap main model must yield (nil, nil) without building, got %v %v built=%v", provider, err, built)
+	}
+	// After escalating to an expensive model the cheap default is built.
+	if _, err := factory(context.Background(), "claude-sonnet-4-5"); err == nil || len(built) != 1 || built[0] != defaultAnthropicCompactionModel {
+		t.Fatalf("escalated main model must build the cheap summarizer, built=%v err=%v", built, err)
+	}
+	// An empty main model falls back to the base profile's model — the cheap
+	// default here, so again nothing is built.
+	built = nil
+	if provider, err := factory(context.Background(), ""); provider != nil || err != nil || len(built) != 0 {
+		t.Fatalf("empty main model must use the base profile, got %v %v built=%v", provider, err, built)
+	}
+	// The explicit "main" preference disables the dedicated summarizer.
+	if provider, err := CompactionSummarizerFactory(base, "main", newProvider)(context.Background(), "claude-sonnet-4-5"); provider != nil || err != nil {
+		t.Fatalf("preference main must disable the summarizer, got %v %v", provider, err)
+	}
+	if CompactionSummarizerFactory(base, "", nil) != nil {
+		t.Fatal("no provider builder means no factory")
+	}
+}

internal/providers/openai/provider.go

@@ -486,7 +486,7 @@ func (provider *Provider) openAIRequest(request zeroruntime.CompletionRequest) c
 				Function: toolFunction{
 					Name:        tool.Name,
 					Description: tool.Description,
-					Parameters:  tool.Parameters,
+					Parameters:  normalizeToolParameters(tool.Parameters),
 				},
 			})
 		}
@@ -494,6 +494,21 @@ func (provider *Provider) openAIRequest(request zeroruntime.CompletionRequest) c
 	return mapped
 }
 
+// normalizeToolParameters keeps schemas accepted by strict OpenAI-compatible
+// servers such as LM Studio. No-argument tools still need an object-valued
+// parameters.properties field instead of an omitted field.
+func normalizeToolParameters(parameters map[string]any) map[string]any {
+	normalized := make(map[string]any, len(parameters)+1)
+	for key, value := range parameters {
+		normalized[key] = value
+	}
+	properties, ok := normalized["properties"].(map[string]any)
+	if !ok || properties == nil {
+		normalized["properties"] = map[string]any{}
+	}
+	return normalized
+}
+
 // promptCacheKeyDisabled reports whether the ZERO_DISABLE_PROMPT_CACHE_KEY
 // kill switch is set to a truthy value. "0" and "false" (any case) are
 // no-ops, matching how ZERO_FORMAT_ON_WRITE parses boolean flags, so an

internal/providers/openai/provider_test.go

@@ -3,6 +3,7 @@ package openai
 import (
 	"context"
 	"encoding/json"
+	"io"
 	"net/http"
 	"net/http/httptest"
 	"reflect"
@@ -105,6 +106,72 @@ func TestStreamCompletionPostsChatCompletionRequest(t *testing.T) {
 	if tool["type"] != "function" {
 		t.Fatalf("unexpected tool wrapper: %#v", tool)
 	}
+	functionDefinition := tool["function"].(map[string]any)
+	parameters := functionDefinition["parameters"].(map[string]any)
+	properties, ok := parameters["properties"].(map[string]any)
+	if !ok || len(properties) != 0 {
+		t.Fatalf("parameters.properties = %#v, want empty object", parameters["properties"])
+	}
+}
+
+// TestStreamCompletionSerializesTypedNilPropertiesAsEmptyObject locks in the
+// normalizeToolParameters fix: a tool whose parameters carry a typed-nil
+// properties map must serialize "properties":{} on the wire, never
+// "properties":null, because strict OpenAI-compatible servers (LM Studio)
+// reject the null form.
+func TestStreamCompletionSerializesTypedNilPropertiesAsEmptyObject(t *testing.T) {
+	var gotBody map[string]any
+	var gotRaw []byte
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		raw, err := io.ReadAll(r.Body)
+		if err != nil {
+			t.Fatalf("read request body: %v", err)
+		}
+		gotRaw = raw
+		if err := json.Unmarshal(raw, &gotBody); err != nil {
+			t.Fatalf("decode request body: %v", err)
+		}
+		writeSSE(w, `{"choices":[]}`)
+		writeSSE(w, `[DONE]`)
+	}))
+	defer server.Close()
+
+	provider, err := New(Options{
+		APIKey:  "sk-secret",
+		BaseURL: server.URL + "/",
+		Model:   "gpt-test",
+	})
+	if err != nil {
+		t.Fatalf("New returned error: %v", err)
+	}
+
+	stream, err := provider.StreamCompletion(context.Background(), zeroruntime.CompletionRequest{
+		Messages: []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "hi"}},
+		Tools: []zeroruntime.ToolDefinition{{
+			Name:        "no_args",
+			Description: "Takes no arguments",
+			Parameters:  map[string]any{"type": "object", "properties": map[string]any(nil)},
+		}},
+	})
+	if err != nil {
+		t.Fatalf("StreamCompletion returned error: %v", err)
+	}
+	drain(stream)
+
+	if !strings.Contains(string(gotRaw), `"properties":{}`) {
+		t.Fatalf("request body must serialize properties as an empty object, got: %s", gotRaw)
+	}
+	if strings.Contains(string(gotRaw), `"properties":null`) {
+		t.Fatalf("request body must not serialize properties as null, got: %s", gotRaw)
+	}
+	tools := gotBody["tools"].([]any)
+	tool := tools[0].(map[string]any)
+	functionDefinition := tool["function"].(map[string]any)
+	parameters := functionDefinition["parameters"].(map[string]any)
+	properties, ok := parameters["properties"].(map[string]any)
+	if !ok || len(properties) != 0 {
+		t.Fatalf("parameters.properties = %#v, want empty object", parameters["properties"])
+	}
 }
 
 func TestNewRequiresModelButNotAPIKey(t *testing.T) {
@@ -1479,3 +1546,66 @@ func TestOpenAIRequestPreservesCacheablePrefixAcrossTurns(t *testing.T) {
 		t.Fatalf("wire prompt cache key must remain stable: first=%#v second=%#v", first["prompt_cache_key"], second["prompt_cache_key"])
 	}
 }
+
+// TestStreamCompletionSerializesNonMapPropertiesAsEmptyObject locks in the
+// normalizeToolParameters type-assert branch: when a tool's parameters carry a
+// `properties` field whose value is a non-map (e.g., an empty slice), it must
+// be normalized to "properties":{} on the wire, never "properties":[] or
+// "properties":null.
+func TestStreamCompletionSerializesNonMapPropertiesAsEmptyObject(t *testing.T) {
+	var gotBody map[string]any
+	var gotRaw []byte
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		raw, err := io.ReadAll(r.Body)
+		if err != nil {
+			t.Fatalf("read request body: %v", err)
+		}
+		gotRaw = raw
+		if err := json.Unmarshal(raw, &gotBody); err != nil {
+			t.Fatalf("decode request body: %v", err)
+		}
+		writeSSE(w, `{"choices":[]}`)
+		writeSSE(w, `[DONE]`)
+	}))
+	defer server.Close()
+
+	provider, err := New(Options{
+		APIKey:  "sk-secret",
+		BaseURL: server.URL + "/",
+		Model:   "gpt-test",
+	})
+	if err != nil {
+		t.Fatalf("New returned error: %v", err)
+	}
+
+	stream, err := provider.StreamCompletion(context.Background(), zeroruntime.CompletionRequest{
+		Messages: []zeroruntime.Message{{Role: zeroruntime.MessageRoleUser, Content: "hi"}},
+		Tools: []zeroruntime.ToolDefinition{{
+			Name:        "no_args",
+			Description: "Takes no arguments",
+			Parameters:  map[string]any{"type": "object", "properties": []any{}},
+		}},
+	})
+	if err != nil {
+		t.Fatalf("StreamCompletion returned error: %v", err)
+	}
+	drain(stream)
+
+	if !strings.Contains(string(gotRaw), `"properties":{}`) {
+		t.Fatalf("request body must serialize properties as an empty object, got: %s", gotRaw)
+	}
+	if strings.Contains(string(gotRaw), `"properties":null`) {
+		t.Fatalf("request body must not serialize properties as null, got: %s", gotRaw)
+	}
+	if strings.Contains(string(gotRaw), `"properties":[]`) {
+		t.Fatalf("request body must not serialize properties as an empty array, got: %s", gotRaw)
+	}
+	tools := gotBody["tools"].([]any)
+	tool := tools[0].(map[string]any)
+	functionDefinition := tool["function"].(map[string]any)
+	parameters := functionDefinition["parameters"].(map[string]any)
+	properties, ok := parameters["properties"].(map[string]any)
+	if !ok || len(properties) != 0 {
+		t.Fatalf("parameters.properties = %#v, want empty object", parameters["properties"])
+	}
+}

internal/sandbox/apply_patch_paths_test.go

@@ -0,0 +1,96 @@
+package sandbox
+
+import (
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestApplyPatchPathBlockOnlyRejectsRelativeTraversal(t *testing.T) {
+	root := t.TempDir()
+	inside := filepath.Join(root, "main.js")
+	structured := func(path string) string {
+		return strings.Join([]string{"*** Begin Patch", "*** Update File: " + path, "@@", "-a", "+b", "*** End Patch"}, "\n")
+	}
+	for name, patch := range map[string]string{
+		"absolute inside workspace": structured(inside),
+		"relative":                  structured("main.js"),
+		"decorated markers":         "*** Begin Patch ***\n*** Update File: main.js\n@@\n-a\n+b\n*** End Patch ***",
+		"no-space marker":           "***Begin Patch\n*** Update File: main.js\n@@\n-a\n+b\n***End Patch",
+	} {
+		request := Request{ToolName: "apply_patch", WorkspaceRoot: root, SideEffect: SideEffectWrite, Args: map[string]any{"patch": patch}}
+		if block := applyPatchPathBlock(request); block != nil {
+			t.Fatalf("%s: unexpected block %+v", name, block)
+		}
+	}
+	for _, path := range []string{"../escape.js", ".."} {
+		for name, patch := range map[string]string{"canonical": structured(path), "no-space": "***Begin Patch\n*** Update File: " + path + "\n@@\n-a\n+b\n***End Patch"} {
+			request := Request{ToolName: "apply_patch", WorkspaceRoot: root, SideEffect: SideEffectWrite, Args: map[string]any{"patch": patch}}
+			block := applyPatchPathBlock(request)
+			if block == nil || block.Code != BlockOutsideWorkspace {
+				t.Fatalf("%s %q must be blocked as traversal, got %+v", name, path, block)
+			}
+		}
+	}
+}
+
+// Every marker spelling the tool applies must be classified as structured at
+// the sandbox boundary too; otherwise the boundary scans the patch as a unified
+// diff, extracts no targets, and validates nothing (fail-open).
+func TestStructuredPatchClassifierMatchesToolSpellings(t *testing.T) {
+	for _, header := range []string{"*** Begin Patch", "*** Begin Patch ***", "***Begin Patch", "  *** Begin Patch  ", "\ufeff*** Begin Patch"} {
+		patch := header + "\n*** Update File: main.js\n@@\n-a\n+b\n*** End Patch"
+		if !IsStructuredPatch(patch) {
+			t.Fatalf("%q must classify as a structured patch", header)
+		}
+		if paths := applyPatchPaths(patch); len(paths) != 1 || paths[0] != "main.js" {
+			t.Fatalf("%q: sandbox must extract the structured target, got %v", header, paths)
+		}
+	}
+	for _, header := range []string{"--- a/x", "Begin Patch", "*** Begin Patchwork", "*** Update File: x"} {
+		if IsStructuredPatch(header + "\n-a\n+b") {
+			t.Fatalf("%q must not classify as a structured patch", header)
+		}
+	}
+	if StructuredPatchMarker("*** End Patch ***") != "end" || StructuredPatchMarker("***End Patch") != "end" {
+		t.Fatal("decorated end markers must classify as end")
+	}
+}
+
+func TestApplyPatchRequestPathsCarryAbsolutePathsToScopeValidation(t *testing.T) {
+	root := t.TempDir()
+	// NewScope also grants the system temp dir, so a sibling t.TempDir() is
+	// legitimately in scope; pick a path under the filesystem root instead.
+	outside, err := filepath.Abs(filepath.Join(string(filepath.Separator), "zero-outside-workspace-test", "escape.js"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	scope, err := NewScope(root, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	inside := filepath.Join(root, "main.js")
+	structured := func(header, footer, path string) string {
+		return strings.Join([]string{header, "*** Update File: " + path, "@@", "-a", "+b", footer}, "\n")
+	}
+	for name, spelling := range map[string][2]string{"canonical": {"*** Begin Patch", "*** End Patch"}, "no-space": {"***Begin Patch", "***End Patch"}} {
+		// Failure path: the exact path the boundary parsed must be denied by the
+		// scope. structuredPatchHeaderPaths normalises separators to "/", so the
+		// parsed form is compared in slash form and then validated as-is.
+		paths := applyPatchRequestPaths(map[string]any{"patch": structured(spelling[0], spelling[1], outside)})
+		if len(paths) != 1 || paths[0] != filepath.ToSlash(outside) {
+			t.Fatalf("%s: absolute patch path must reach scope validation unchanged, got %v", name, paths)
+		}
+		if block := scope.validate(paths[0]); block == nil || block.Code != BlockOutsideWorkspace {
+			t.Fatalf("%s: scope must deny the parsed outside path %q, got %+v", name, paths[0], block)
+		}
+		// Success path: the parsed inside path must be accepted by the scope.
+		paths = applyPatchRequestPaths(map[string]any{"patch": structured(spelling[0], spelling[1], inside)})
+		if len(paths) != 1 || paths[0] != filepath.ToSlash(inside) {
+			t.Fatalf("%s: inside patch path must reach scope validation unchanged, got %v", name, paths)
+		}
+		if block := scope.validate(paths[0]); block != nil {
+			t.Fatalf("%s: scope must accept the parsed inside path %q, got %+v", name, paths[0], block)
+		}
+	}
+}

internal/sandbox/command_prefix.go

@@ -148,8 +148,10 @@ func unsafeCommandPrefix(prefix []string) bool {
 			return true
 		}
 	}
+	normalized := append([]string(nil), prefix...)
+	normalized[0] = normalizeLauncherName(normalized[0])
 	for _, banned := range bannedCommandPrefixSuggestions {
-		if sameStringSlice(prefix, banned) {
+		if sameStringSlice(prefix, banned) || sameStringSlice(normalized, banned) {
 			return true
 		}
 	}
@@ -165,25 +167,118 @@ func unsafeCommandPrefixPart(part string) bool {
 }
 
 func unsafeCommandPrefixLauncher(program string) bool {
-	program = strings.ToLower(strings.TrimSpace(program))
-	if strings.ContainsAny(program, `/\`) {
+	// A path is already refused. ":" and "~" are refused for the same reason:
+	// on Windows they introduce names that resolve to a different file than the
+	// one matched here, and no list can keep up with them. "PYTHON~1.EXE" is
+	// python.exe under an 8.3 short name, and 8.3 truncates the stem, so
+	// "POWERS~1.EXE" cannot be recognized by name at all; "python.exe::$DATA"
+	// names the same executable through its default stream. Refusing the shape
+	// costs a permission prompt on names no real command uses.
+	if strings.ContainsAny(program, `/\:~`) {
 		return true
 	}
-	switch program {
-	case "bash", "sh", "zsh", "/bin/bash", "/bin/zsh",
-		"pwsh", "powershell", "powershell.exe",
-		"env", "sudo", "doas", "su", "run0", "osascript",
+	name := normalizeLauncherName(program)
+	return bannedLauncherName(name) || bannedLauncherName(strings.TrimRight(name, "0123456789"))
+}
+
+func bannedLauncherName(name string) bool {
+	switch name {
+	case "bash", "sh", "zsh", "dash", "ash", "ksh", "csh", "tcsh", "fish", "busybox",
+		"pwsh", "powershell", "cmd", "wsl",
+		"env", "sudo", "sudoedit", "doas", "su", "run0", "osascript",
 		"command", "eval", "exec", "time",
 		"find", "xargs", "timeout", "nice", "nohup", "watch", "setsid", "stdbuf", "ionice",
-		"ssh", "make", "npm", "npx",
-		"python", "python3", "py", "pythonw", "pyw", "pypy", "pypy3",
-		"node", "perl", "ruby", "php", "lua", "deno", "bun":
+		"ssh", "make", "npm", "npx", "pnpm", "yarn", "bunx",
+		"python", "py", "pythonw", "pyw", "pypy", "uv", "uvx",
+		"node", "nodejs", "perl", "ruby", "php", "lua", "deno", "bun":
 		return true
 	default:
 		return false
 	}
 }
 
+// normalizeLauncherName reduces a program name to the launcher it actually runs
+// so the list above cannot be stepped around by spelling the same interpreter
+// differently: "python3.11", "python.exe" and "PYTHON3" all reach it as a name
+// the list matches. internal/agent's commandName already normalizes case and
+// Windows executable extensions on the allow side; this side matched raw, so
+// every versioned or .exe-suffixed launcher validated as an ordinary command
+// and persisted as a prefix grant that auto-allows every later invocation.
+//
+// A name is only ever narrowed toward an existing entry, so the failure
+// direction is an extra permission prompt, never a silent grant.
+func normalizeLauncherName(program string) string {
+	name := strings.ToLower(strings.TrimSpace(program))
+	// Windows discards trailing dots and spaces when resolving a filename, so
+	// "python." starts python.exe. Drop them before anything matches on the
+	// result, on every platform: the deny side must not depend on which OS is
+	// reading the grant, since the grants file travels with a synced home
+	// directory.
+	name = strings.TrimRight(name, ". ")
+	for _, suffix := range []string{".exe", ".cmd", ".bat", ".com", ".ps1"} {
+		if strings.HasSuffix(name, suffix) {
+			name = strings.TrimSuffix(name, suffix)
+			name = strings.TrimRight(name, ". ")
+			break
+		}
+	}
+	return trimLauncherVersion(trimLauncherABISuffix(trimLauncherBuildSuffix(name)))
+}
+
+// trimLauncherBuildSuffix drops the build-channel suffixes distributions and
+// upstreams append to an otherwise unchanged interpreter, so "python3.11-dbg",
+// "bash-static" and "pwsh-preview" are the launchers they say they are. The set
+// is closed on purpose: a general "-word" strip would also swallow
+// "node-gyp", "python3-config" and "ruby-lsp", which are ordinary tools a user
+// should still be able to approve.
+func trimLauncherBuildSuffix(name string) string {
+	for _, suffix := range []string{"-dbg", "-debug", "-static", "-nightly", "-preview", "-beta"} {
+		if strings.HasSuffix(name, suffix) {
+			return strings.TrimSuffix(name, suffix)
+		}
+	}
+	return name
+}
+
+// trimLauncherABISuffix drops CPython's ABI flags from a versioned interpreter
+// name, so "python3.7m" and "python3.6dm" reduce to their version, and the
+// free-threaded builds "python3.13t" and "python3.13td" reduce to theirs. The
+// flags are only removed when a digit sits underneath them, which leaves
+// ordinary names that happen to end in those letters alone: "sha256sum" keeps
+// its "sum", "zstd" its "td", "cat" its "t".
+func trimLauncherABISuffix(name string) string {
+	trimmed := strings.TrimRight(name, "dmut")
+	if trimmed == name || trimmed == "" {
+		return name
+	}
+	if last := trimmed[len(trimmed)-1]; last < '0' || last > '9' {
+		return name
+	}
+	return trimmed
+}
+
+// trimLauncherVersion drops a trailing "<separator><digits>" version from a
+// program name, so "python3.11" becomes "python3" and "python2.7" becomes
+// "python2". Digits without a separator are part of the name, which keeps
+// "base64", "7z" and "sha256sum" intact; the caller handles the "python3" shape
+// by also testing the digit-stripped form.
+func trimLauncherVersion(name string) string {
+	for {
+		trimmed := strings.TrimRight(name, "0123456789")
+		if trimmed == name || trimmed == "" {
+			return name
+		}
+		if !strings.HasSuffix(trimmed, ".") && !strings.HasSuffix(trimmed, "-") {
+			return name
+		}
+		next := trimmed[:len(trimmed)-1]
+		if next == "" {
+			return name
+		}
+		name = next
+	}
+}
+
 func sameStringSlice(left []string, right []string) bool {
 	if len(left) != len(right) {
 		return false

internal/sandbox/command_prefix_test.go

@@ -0,0 +1,115 @@
+package sandbox
+
+import "testing"
+
+func TestUnsafeCommandPrefixLauncherIgnoresVersionAndExtension(t *testing.T) {
+	for _, program := range []string{
+		"python3", "python", "node", "git", "sh", "bash", "sudo",
+		"python3.11", "python3.12", "python2.7", "python3.13.1",
+		"python.exe", "python3.exe", "node.exe", "git.exe", "bash.exe",
+		"PYTHON3.11", "Node.EXE",
+		"cmd", "cmd.exe", "wsl", "wsl.exe",
+		// Windows resolves these to the same executable.
+		"python.", "python3.", "python3.11.", "python.exe.", "PYTHON.",
+		"python.cmd", "python.bat", "python.com", "python.ps1",
+		"PYTHON~1.EXE", "POWERS~1.EXE", "python.exe::$DATA",
+		// Versioned and ABI-suffixed interpreters.
+		"python3.7m", "python3.6dm", "pythonw3.11", "python-3.11",
+		// Free-threaded CPython (PEP 703) ships beside the GIL build.
+		"python3.13t", "python3.13t.exe", "python3.14t", "python3.13td",
+		// Distribution and build-channel spellings of the same interpreter.
+		"nodejs", "nodejs.exe", "node-nightly", "python3-dbg", "python3.11-dbg",
+		"python3.13t-dbg", "python3-debug", "python3.11-debug", "node-beta",
+		"pwsh-preview", "bash-static", "sudoedit",
+		// Twins of npm and npx, which the list already refuses.
+		"pnpm", "yarn", "bunx", "pnpm.cmd", "yarn.exe",
+		"perl5.36", "ruby3.2", "php8", "lua5.4", "node22.exe", "bash5",
+	} {
+		if !unsafeCommandPrefix([]string{program}) {
+			t.Errorf("unsafeCommandPrefix([%q]) = false, want true", program)
+		}
+	}
+}
+
+func TestUnsafeCommandPrefixKeepsOrdinaryCommandsGrantable(t *testing.T) {
+	for _, prefix := range [][]string{
+		{"cargo", "build"},
+		{"go", "test"},
+		{"ls", "-la"},
+		{"rg", "--json"},
+		{"7z", "l"},
+		{"base64", "-d"},
+		{"kubectl", "get", "pods"},
+		{"docker", "ps"},
+		{"sha256sum", "file"},
+		{"gcc-13", "-c"},
+		{"node-gyp", "build"},
+		{"python3-config", "--includes"},
+		{"s3cmd", "ls"},
+		{"cat", "file"},
+		{"zstd", "-d"},
+		{"sqlite3", "db"},
+		{"yt-dlp", "url"},
+		{"perl-doc", "-h"},
+		{"php-fpm", "-t"},
+		{"ruby-lsp", "--version"},
+		{"lua-language-server", "--check"},
+		{"nodemon", "app.js"},
+	} {
+		if unsafeCommandPrefix(prefix) {
+			t.Errorf("unsafeCommandPrefix(%q) = true, want false", prefix)
+		}
+	}
+}
+func TestNormalizeLauncherName(t *testing.T) {
+	for _, testCase := range []struct{ in, want string }{
+		{"python3.11", "python3"},
+		{"python2.7", "python2"},
+		{"pypy3", "pypy3"},
+		{"node.exe", "node"},
+		{"POWERSHELL.EXE", "powershell"},
+		{"7z", "7z"},
+		{"base64", "base64"},
+		{"sha256sum", "sha256sum"},
+		{"python.", "python"},
+		{"python3.11.exe.", "python3"},
+		{"python3.7m", "python3"},
+		{"python3.6dm", "python3"},
+		{"python3.13t", "python3"},
+		{"python3.13td", "python3"},
+		{"python3.11-dbg", "python3"},
+		{"node-nightly", "node"},
+		{"node-gyp", "node-gyp"},
+		{"python3-config", "python3-config"},
+		{"zstd", "zstd"},
+		{"cat", "cat"},
+		{"cargo", "cargo"},
+		{"", ""},
+	} {
+		if got := normalizeLauncherName(testCase.in); got != testCase.want {
+			t.Errorf("normalizeLauncherName(%q) = %q, want %q", testCase.in, got, testCase.want)
+		}
+	}
+}
+
+// Session-scoped grants are the agent's other entry point (loop.go grants them
+// for a single turn without touching the store), so they must refuse the same
+// launcher spellings the persisted path does.
+func TestGrantCommandPrefixForSessionRefusesLauncherVariants(t *testing.T) {
+	engine := &Engine{commandPrefixes: newCommandPrefixGrantSet()}
+	engine.GrantCommandPrefixForSession("bash", []string{"cargo", "build"})
+	if _, ok := engine.LookupCommandPrefixForSession("bash", []string{"cargo", "build", "--release"}); !ok {
+		t.Fatal("CONTROL BROKEN: an ordinary session prefix grant did not match")
+	}
+	for _, prefix := range [][]string{
+		{"python3.11", "-c"},
+		{"python.exe", "-c"},
+		{"cmd", "/c"},
+	} {
+		engine.GrantCommandPrefixForSession("bash", prefix)
+		command := append(append([]string(nil), prefix...), "whatever")
+		if _, ok := engine.LookupCommandPrefixForSession("bash", command); ok {
+			t.Errorf("session grant %q matched %q, want refused", prefix, command)
+		}
+	}
+}

internal/sandbox/engine_test.go

@@ -242,6 +242,7 @@ func TestEngineAutoAllowsWorkspaceFileMutationTools(t *testing.T) {
 		{name: "write_file", args: map[string]any{"path": "notes.txt"}},
 		{name: "edit_file", args: map[string]any{"path": "notes.txt"}},
 		{name: "apply_patch", args: map[string]any{"patch": "diff --git a/notes.txt b/notes.txt\n"}},
+		{name: "apply_patch", args: map[string]any{"patch": "*** Begin Patch\n*** Add File: notes.txt\n+x\n*** End Patch\n"}},
 	} {
 		t.Run(tc.name, func(t *testing.T) {
 			decision := engine.Evaluate(context.Background(), Request{
@@ -315,6 +316,27 @@ func TestEngineDeniesApplyPatchEscapesFromPatchBody(t *testing.T) {
 	}
 }
 
+func TestEngineDeniesStructuredApplyPatchEscapesFromPatchBody(t *testing.T) {
+	root := t.TempDir()
+	engine := NewEngine(EngineOptions{WorkspaceRoot: root, Policy: DefaultPolicy()})
+
+	for _, patch := range []string{
+		"*** Begin Patch\n*** Add File: ../escape.txt\n+x\n*** End Patch\n",
+		"*** Begin Patch\n*** Add File: ..\\escape.txt\n+x\n*** End Patch\n",
+	} {
+		decision := engine.Evaluate(context.Background(), Request{
+			ToolName:       "apply_patch",
+			SideEffect:     SideEffectWrite,
+			Permission:     PermissionPrompt,
+			PermissionMode: PermissionModeAsk,
+			Args:           map[string]any{"patch": patch},
+		})
+		if decision.Action != ActionDeny || decision.Block == nil || decision.Block.Code != BlockOutsideWorkspace {
+			t.Fatalf("escaping structured apply_patch decision = %#v, want outside-workspace deny", decision)
+		}
+	}
+}
+
 func TestEngineSessionGrantDoesNotMatchSiblingFile(t *testing.T) {
 	root := t.TempDir()
 	engine := NewEngine(EngineOptions{WorkspaceRoot: root, Policy: promptWorkspaceWritePolicy()})

internal/sandbox/grants_test.go

@@ -2,12 +2,15 @@ package sandbox
 
 import (
 	"errors"
+	"fmt"
 	"os"
 	"path/filepath"
 	"runtime"
 	"strings"
 	"testing"
 	"time"
+
+	"github.com/Gitlawb/zero/internal/execution"
 )
 
 func TestGrantStorePersistsListsRevokesAndClears(t *testing.T) {
@@ -343,7 +346,8 @@ func TestGrantStoreMigratesExactV1GrantAndReportsOnce(t *testing.T) {
 	if err != nil {
 		t.Fatalf("read rewritten grant file: %v", err)
 	}
-	if !strings.Contains(string(raw), `"schemaVersion": 3`) || !strings.Contains(string(raw), `"policyVersion": 1`) || !strings.Contains(string(raw), `"write_file": [`) {
+	policyLine := fmt.Sprintf(`"policyVersion": %d`, execution.PolicyVersion)
+	if !strings.Contains(string(raw), `"schemaVersion": 3`) || !strings.Contains(string(raw), policyLine) || !strings.Contains(string(raw), `"write_file": [`) {
 		t.Fatalf("grant file was not rewritten as a versioned grant store:\n%s", raw)
 	}
 	backup, err := os.ReadFile(path + ".v1.backup")
@@ -406,6 +410,62 @@ func TestGrantStorePolicyChangePreservesDeniesAndInvalidatesApprovals(t *testing
 	}
 }
 
+// A prefix grant recorded before launcher-name normalization existed (a
+// versioned or .exe-suffixed interpreter) no longer validates. It must reach
+// the user through the policy migration — backup, denies preserved, one notice
+// — and never make the whole grants file unreadable, which would silently drop
+// their persisted deny grants too.
+func TestGrantStoreMigratesPreNormalizationPrefixInsteadOfRejectingTheFile(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "sandbox-grants.json")
+	original := `{"schemaVersion":3,"policyVersion":1,"grants":{"bash":[{"toolName":"bash","decision":"deny","approvedAt":"2026-06-05T14:30:00Z"}]},"commandPrefixes":{"bash":[{"toolName":"bash","prefix":["python3.11","-c"],"approvedAt":"2026-06-05T14:30:00Z"},{"toolName":"bash","prefix":["cargo","build"],"approvedAt":"2026-06-05T14:30:00Z"}]}}`
+	if err := writeText(path, original); err != nil {
+		t.Fatal(err)
+	}
+	store, err := NewGrantStore(StoreOptions{FilePath: path})
+	if err != nil {
+		t.Fatal(err)
+	}
+	grants, err := store.List()
+	if err != nil || len(grants) != 1 || grants[0].Decision != GrantDeny {
+		t.Fatalf("grants after migration = %#v err=%v, want the deny preserved", grants, err)
+	}
+	prefixes, err := store.ListCommandPrefixes()
+	if err != nil || len(prefixes) != 0 {
+		t.Fatalf("prefixes after migration = %#v err=%v, want all re-approved", prefixes, err)
+	}
+	if notice, err := store.ConsumeMigrationNotice(); err != nil || !strings.Contains(notice, "invalidated 2") {
+		t.Fatalf("notice = %q err=%v", notice, err)
+	}
+	if backup, err := os.ReadFile(path + ".policy-v1.backup"); err != nil || string(backup) != original {
+		t.Fatalf("backup = %q err=%v", backup, err)
+	}
+}
+
+// The legacy-schema path is a separate migration from the policy bump above and
+// prunes per grant rather than wholesale, so a pre-normalization prefix must be
+// dropped there while the valid prefix beside it survives.
+func TestGrantStoreLegacyMigrationDropsOnlyThePreNormalizationPrefix(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "sandbox-grants.json")
+	original := `{"schemaVersion":2,"grants":{},"commandPrefixes":{"bash":[{"toolName":"bash","prefix":["python3.11","-c"],"approvedAt":"2026-06-05T14:30:00Z"},{"toolName":"bash","prefix":["git","status"],"approvedAt":"2026-06-05T14:30:00Z"}]}}`
+	if err := writeText(path, original); err != nil {
+		t.Fatal(err)
+	}
+	store, err := NewGrantStore(StoreOptions{FilePath: path})
+	if err != nil {
+		t.Fatal(err)
+	}
+	prefixes, err := store.ListCommandPrefixes()
+	if err != nil {
+		t.Fatalf("ListCommandPrefixes after legacy migration returned error: %v", err)
+	}
+	if len(prefixes) != 1 || !sameStringSlice(prefixes[0].Prefix, []string{"git", "status"}) {
+		t.Fatalf("prefixes = %#v, want only [git status]", prefixes)
+	}
+	if notice, err := store.ConsumeMigrationNotice(); err != nil || !strings.Contains(notice, "migrated 1, invalidated 1") {
+		t.Fatalf("notice = %q err=%v", notice, err)
+	}
+}
+
 func TestGrantStorePersistsCommandPrefixes(t *testing.T) {
 	store, err := NewGrantStore(StoreOptions{
 		FilePath: filepath.Join(t.TempDir(), "sandbox-grants.json"),
@@ -481,6 +541,11 @@ func TestGrantStoreRejectsUnsafeCommandPrefixes(t *testing.T) {
 		{"python", "script.py"},
 		{"./script.sh"},
 		{"git"},
+		{"python3.11", "-c"},
+		{"python.exe", "-c"},
+		{"node.exe", "-e"},
+		{"git.exe"},
+		{"cmd", "/c"},
 	} {
 		if _, err := store.GrantCommandPrefix(CommandPrefixInput{ToolName: "bash", Prefix: prefix}); err == nil {
 			t.Fatalf("GrantCommandPrefix(%#v) succeeded, want validation error", prefix)

internal/sandbox/risk.go

@@ -261,7 +261,7 @@ func applyPatchRequestPaths(args map[string]any) []string {
 	}
 	cwd := firstArgString(args, "cwd")
 	var paths []string
-	for _, path := range patchHeaderPaths(patch) {
+	for _, path := range applyPatchPaths(patch) {
 		if path == "" || path == "/dev/null" {
 			continue
 		}
@@ -281,11 +281,15 @@ func applyPatchPathBlock(request Request) *pathBlock {
 	if patch == "" {
 		return nil
 	}
-	for _, path := range patchHeaderPaths(patch) {
+	// Only relative traversal is rejected up front. Absolute paths flow through
+	// the regular workspace-scope validation below (requestPaths), which accepts
+	// one inside the workspace and denies one outside — a model that echoes the
+	// absolute path read_file showed it must not be blocked for that alone.
+	for _, path := range applyPatchPaths(patch) {
 		if path == "" || path == "/dev/null" {
 			continue
 		}
-		if filepath.IsAbs(path) || path == ".." || strings.HasPrefix(path, "../") {
+		if path == ".." || strings.HasPrefix(path, "../") {
 			return &pathBlock{
 				Code:   BlockOutsideWorkspace,
 				Path:   path,
@@ -296,6 +300,61 @@ func applyPatchPathBlock(request Request) *pathBlock {
 	return nil
 }
 
+// structuredPatchMarkerPattern is the single classifier for structured-patch
+// markers, shared by the sandbox boundary and the apply_patch tool (which
+// imports this package). It accepts the canonical "*** Begin Patch" /
+// "*** End Patch" and the decorated spellings models emit ("*** Begin Patch ***",
+// "***Begin Patch", trailing whitespace). Both sides must agree: a spelling the
+// tool would apply but the sandbox did not recognise would make the sandbox
+// scan the patch as a unified diff, extract no targets, and validate nothing.
+var structuredPatchMarkerPattern = regexp.MustCompile(`^\*{3}\s*(Begin|End) Patch\s*\**\s*$`)
+
+// StructuredPatchMarker classifies a line as the "begin" or "end" marker of a
+// structured patch, or "" when it is neither.
+func StructuredPatchMarker(line string) string {
+	match := structuredPatchMarkerPattern.FindStringSubmatch(strings.TrimSpace(line))
+	if match == nil {
+		return ""
+	}
+	return strings.ToLower(match[1])
+}
+
+// IsStructuredPatch reports whether patch opens with a structured begin marker.
+// The tool applies exactly the patches this returns true for, so the sandbox
+// extracts structured header paths for exactly the same set.
+func IsStructuredPatch(patch string) bool {
+	first, _, _ := strings.Cut(strings.TrimSpace(strings.TrimPrefix(patch, "\ufeff")), "\n")
+	return StructuredPatchMarker(first) == "begin"
+}
+
+func applyPatchPaths(patch string) []string {
+	if IsStructuredPatch(patch) {
+		return structuredPatchHeaderPaths(patch)
+	}
+	return patchHeaderPaths(patch)
+}
+
+// structuredPatchHeaderPaths is intentionally a small, conservative scanner for
+// the sandbox boundary. The executor validates the complete hunk grammar before
+// writing; the sandbox only needs every possible target path so it can reject an
+// unsafe request before the tool runs.
+func structuredPatchHeaderPaths(patch string) []string {
+	var paths []string
+	for _, line := range strings.Split(strings.ReplaceAll(patch, "\r\n", "\n"), "\n") {
+		trimmed := strings.TrimSpace(line)
+		for _, prefix := range []string{"*** Add File: ", "*** Delete File: ", "*** Update File: ", "*** Move to: "} {
+			if path, ok := strings.CutPrefix(trimmed, prefix); ok {
+				path = strings.ReplaceAll(filepath.ToSlash(strings.TrimSpace(path)), "\\", "/")
+				if path != "" {
+					paths = append(paths, path)
+				}
+				break
+			}
+		}
+	}
+	return paths
+}
+
 func patchHeaderPaths(patch string) []string {
 	var paths []string
 	oldRemaining, newRemaining := 0, 0

internal/tools/apply_patch.go

@@ -3,11 +3,11 @@ package tools
 import (
 	"context"
 	"fmt"
-	"os"
-	"os/exec"
 	"path/filepath"
 	"strconv"
 	"strings"
+
+	"github.com/Gitlawb/zero/internal/sandbox"
 )
 
 type applyPatchTool struct {
@@ -20,11 +20,11 @@ func NewScopedApplyPatchTool(workspaceRoot string, scope PathScope) Tool {
 	return applyPatchTool{
 		baseTool: baseTool{
 			name:        "apply_patch",
-			description: "Apply a unified diff patch inside the workspace or an explicitly granted extra write root.",
+			description: "Apply a multi-hunk or multi-file patch inside the workspace (or a granted extra write root). Structured format:\n*** Begin Patch\n*** Update File: src/app.js\n@@\n unchanged context line\n-removed line\n+added line\n*** End Patch\nUse \"*** Add File: path\" with \"+\" lines to create a file and \"*** Delete File: path\" to remove one; several sections may follow each other. A unified diff (---/+++ headers with a/ b/ prefixes, @@ hunks) is also accepted and applied in-process. Paths are workspace-relative; absolute paths inside the workspace are fine. For a single targeted change, edit_file is simpler.",
 			parameters: Schema{
 				Type: "object",
 				Properties: map[string]PropertySchema{
-					"patch": {Type: "string", Description: "Unified diff patch to apply."},
+					"patch": {Type: "string", Description: "The structured (*** Begin Patch) or unified-diff patch text."},
 					"cwd":   {Type: "string", Description: "Directory where the patch should be applied. Relative paths stay in the workspace; use an absolute path to target a granted extra write root. Defaults to workspace root.", Default: "."},
 				},
 				Required:             []string{"patch"},
@@ -56,177 +56,17 @@ func (tool applyPatchTool) RunWithOptions(ctx context.Context, args map[string]a
 	if err != nil {
 		return errorResult("Error applying patch: " + err.Error())
 	}
-	if err := validatePatchPaths(applyRoot, patch); err != nil {
-		return errorResult("Error applying patch: " + err.Error())
+	if isStructuredPatch(patch) {
+		return tool.runStructuredPatch(applyRoot, relativeRoot, patch, options)
 	}
-
-	tempFile, err := os.CreateTemp("", "zero-patch-*.patch")
+	// Unified diffs are translated into the same operations and applied by
+	// the same os.Root engine, so neither format opens a target by pathname
+	// after validation (no check-to-use window) and git is not needed.
+	operations, err := parseUnifiedPatch(patch)
 	if err != nil {
 		return errorResult("Error applying patch: " + err.Error())
 	}
-	patchPath := tempFile.Name()
-	defer func() {
-		_ = os.Remove(patchPath)
-	}()
-	if _, err := tempFile.WriteString(patch); err != nil {
-		_ = tempFile.Close()
-		return errorResult("Error applying patch: " + err.Error())
-	}
-	if err := tempFile.Close(); err != nil {
-		return errorResult("Error applying patch: " + err.Error())
-	}
-
-	if err := recheckPatchWriteTargets(applyRoot, patch); err != nil {
-		return errorResult("Error applying patch: " + err.Error())
-	}
-	var createdTargets []string
-	var fullySuppliedTargets []string
-	wholeBefore := map[string]bool{}
-	if options.FileTracker != nil {
-		createdTargets = missingPatchTargets(applyRoot, patch)
-		fullySuppliedTargets = completeCreatedPatchTargets(applyRoot, patch)
-		for _, path := range patchHeaderPaths(patch) {
-			if path == "" || path == "/dev/null" {
-				continue
-			}
-			if absolute, _, rerr := resolveWorkspaceTargetPath(applyRoot, path); rerr == nil {
-				wholeBefore[absolute] = options.FileTracker.SeenWhole(absolute)
-			}
-		}
-	}
-
-	command := exec.CommandContext(ctx, "git", "apply", "--whitespace=nowarn", patchPath)
-	command.Dir = applyRoot
-	output, err := command.CombinedOutput()
-	if err != nil {
-		message := strings.TrimSpace(string(output))
-		if message == "" {
-			message = err.Error()
-		}
-		return errorResult("Error applying patch: " + message)
-	}
-
-	summary := "Patch applied successfully."
-	if relativeRoot != "." {
-		summary = "Patch applied successfully in " + relativeRoot + "."
-	}
-	result := okResult(summary)
-	result.ChangedFiles = changedFilesFromPatch(relativeRoot, patch)
-	result.Display = Display{Summary: summary, Kind: "diff", Preview: capPreviewDiff(patch)}
-	fullySupplied := make(map[string]bool, len(fullySuppliedTargets))
-	for _, absolute := range fullySuppliedTargets {
-		fullySupplied[absolute] = true
-	}
-	// Re-baseline files changed by this tool. When the model had already seen the
-	// whole input (or supplied a complete new file), the exact patch plus that
-	// input determines the whole output, so a follow-up edit needs no wasted read.
-	// Partial observations remain conservative and are cleared by Record.
-	for _, changed := range result.ChangedFiles {
-		if absolute, _, rerr := resolveScopedPath(tool.workspaceRoot, tool.scope, changed); rerr == nil {
-			content, readErr := os.ReadFile(absolute)
-			if readErr != nil {
-				options.FileTracker.Forget(absolute)
-				continue
-			}
-			info, _ := os.Stat(absolute)
-			wasWhole := wholeBefore[absolute] || fullySupplied[absolute]
-			options.FileTracker.Record(absolute, content, info)
-			if wasWhole {
-				lines := lineCount(string(content))
-				options.FileTracker.RecordSeenRange(absolute, 1, lines, lines)
-			}
-		}
-	}
-	recordCreatedPatchTargets(options.FileTracker, createdTargets)
-	return result
-}
-
-func missingPatchTargets(root string, patch string) []string {
-	seen := map[string]bool{}
-	var missing []string
-	for _, path := range patchHeaderPaths(patch) {
-		if path == "" || path == "/dev/null" {
-			continue
-		}
-		absolute, _, err := resolveWorkspaceTargetPath(root, path)
-		if err != nil || seen[absolute] {
-			continue
-		}
-		seen[absolute] = true
-		if _, err := os.Stat(absolute); os.IsNotExist(err) {
-			missing = append(missing, absolute)
-		}
-	}
-	return missing
-}
-
-// completeCreatedPatchTargets returns only files whose full contents are
-// supplied by a /dev/null creation patch. A missing rename/copy destination is
-// created by git too, but its bytes come from an unread source and must not gain
-// whole-file observation credit.
-func completeCreatedPatchTargets(root string, patch string) []string {
-	seen := map[string]bool{}
-	var created []string
-	oldRemaining, newRemaining := 0, 0
-	inHunk := false
-	fromDevNull := false
-	for _, line := range strings.Split(strings.ReplaceAll(patch, "\r\n", "\n"), "\n") {
-		if inHunk && (oldRemaining > 0 || newRemaining > 0) {
-			switch {
-			case strings.HasPrefix(line, "-"):
-				oldRemaining--
-			case strings.HasPrefix(line, "+"):
-				newRemaining--
-			case strings.HasPrefix(line, "\\"):
-			default:
-				oldRemaining--
-				newRemaining--
-			}
-			continue
-		}
-		inHunk = false
-		switch {
-		case strings.HasPrefix(line, "diff --git "):
-			fromDevNull = false
-		case strings.HasPrefix(line, "@@"):
-			oldRemaining, newRemaining = parseHunkCounts(line)
-			inHunk = oldRemaining > 0 || newRemaining > 0
-		case strings.HasPrefix(line, "--- "):
-			fromDevNull = patchFileHeaderPath(line) == "/dev/null"
-		case strings.HasPrefix(line, "+++ "):
-			path := patchFileHeaderPath(line)
-			if !fromDevNull || path == "" || path == "/dev/null" {
-				fromDevNull = false
-				continue
-			}
-			fromDevNull = false
-			absolute, _, err := resolveWorkspaceTargetPath(root, stripPatchPrefix(path))
-			if err != nil || seen[absolute] {
-				continue
-			}
-			if _, err := os.Stat(absolute); !os.IsNotExist(err) {
-				continue
-			}
-			seen[absolute] = true
-			created = append(created, absolute)
-		}
-	}
-	return created
-}
-
-func recordCreatedPatchTargets(tracker *FileTracker, missingBefore []string) {
-	if tracker == nil {
-		return
-	}
-	for _, absolute := range missingBefore {
-		if _, err := os.Stat(absolute); err != nil {
-			continue
-		}
-		if resolved, err := filepath.EvalSymlinks(absolute); err == nil {
-			absolute = resolved
-		}
-		tracker.RecordCreated(absolute)
-	}
+	return applyPatchOperations(applyRoot, relativeRoot, operations, options)
 }
 
 // changedFilesFromPatch extracts the unique, WORKSPACE-relative paths a patch
@@ -257,27 +97,35 @@ func changedFilesFromPatch(relativeRoot string, patch string) []string {
 	return paths
 }
 
+// normalizePatchPathForRoot resolves platform-level symlinks (macOS /var ->
+// /private/var) in the prefix of an absolute patch path that lies outside the
+// apply root, so a path the model copied from read_file compares equal to the
+// symlink-resolved root. Relative paths are returned unchanged.
+func normalizePatchPathForRoot(root string, path string) string {
+	if !filepath.IsAbs(path) {
+		return path
+	}
+	resolvedRoot, err := filepath.Abs(root)
+	if err != nil {
+		return path
+	}
+	if evaluated, err := filepath.EvalSymlinks(resolvedRoot); err == nil {
+		resolvedRoot = evaluated
+	}
+	return sandbox.NormalizePrefixForRoot(path, resolvedRoot)
+}
+
 func validatePatchPaths(root string, patch string) error {
 	for _, path := range patchHeaderPaths(patch) {
 		if path == "" || path == "/dev/null" {
 			continue
 		}
-		if filepath.IsAbs(path) || path == ".." || strings.HasPrefix(path, "../") {
+		// Relative traversal is rejected here; an absolute path is checked by
+		// resolveWorkspaceTargetPath, which only accepts one inside the root.
+		if path == ".." || strings.HasPrefix(path, "../") {
 			return fmt.Errorf("patch path %q must stay inside the workspace", path)
 		}
-		if _, _, err := resolveWorkspaceTargetPath(root, path); err != nil {
-			return err
-		}
-	}
-	return nil
-}
-
-func recheckPatchWriteTargets(root string, patch string) error {
-	for _, path := range patchHeaderPaths(patch) {
-		if path == "" || path == "/dev/null" {
-			continue
-		}
-		if err := recheckWorkspaceWriteTarget(root, path); err != nil {
+		if _, _, err := resolveWorkspaceTargetPath(root, normalizePatchPathForRoot(root, path)); err != nil {
 			return err
 		}
 	}
@@ -348,7 +196,7 @@ func patchFileHeaderPath(line string) string {
 // tokens. Scanning the whole line would let a crafted heading like
 // "@@ -1,1 +1,1 @@ +1,999999" overwrite the real count, keep the parser stuck in
 // hunk mode, and swallow later "--- "/"+++ " file headers so they escape
-// validatePatchPaths / recheckPatchWriteTargets — a workspace-confinement bypass.
+// validatePatchPaths — a workspace-confinement bypass.
 func parseHunkCounts(line string) (int, int) {
 	_, rest, ok := strings.Cut(line, "@@")
 	if !ok {

internal/tools/apply_patch_tolerance_test.go

@@ -0,0 +1,712 @@
+package tools
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"testing"
+)
+
+// Models routinely decorate the structured markers ("*** Begin Patch ***") and
+// write unified-diff ranges after "@@"; both used to fail on the first line and
+// pushed the model into whole-file rewrites.
+func TestApplyPatchToleratesDecoratedMarkersAndRangeHeaders(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "hello.txt"), "hello\nold\nbye\n")
+
+	patch := strings.Join([]string{
+		"*** Begin Patch ***",
+		"*** Update File: hello.txt",
+		"@@ -1,3 +1,3 @@",
+		" hello",
+		"-old",
+		"+new",
+		"*** End Patch ***",
+		"",
+	}, "\n")
+
+	if !isStructuredPatch(patch) {
+		t.Fatal("decorated begin marker must still be recognised as a structured patch")
+	}
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("decorated structured patch should apply, got %s: %s", result.Status, result.Output)
+	}
+	content, err := os.ReadFile(filepath.Join(root, "hello.txt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := strings.ReplaceAll(string(content), "\r\n", "\n"); got != "hello\nnew\nbye\n" {
+		t.Fatalf("patched content = %q", got)
+	}
+}
+
+func TestStructuredHunkAnchorKeepsHeadingAndPlainContext(t *testing.T) {
+	cases := map[string]string{
+		"-12,4 +12,6":                  "",
+		"-12 +12":                      "",
+		"-12,4 +12,6 @@":               "",
+		"-12,4 +12,6 @@ func main() {": "func main() {",
+		"func main() {":                "func main() {",
+		"":                             "",
+	}
+	for input, want := range cases {
+		if got := structuredHunkAnchor(input); got != want {
+			t.Fatalf("structuredHunkAnchor(%q) = %q, want %q", input, got, want)
+		}
+	}
+}
+
+func TestStructuredPatchMarkerSpellings(t *testing.T) {
+	begin := []string{"*** Begin Patch", "*** Begin Patch ***", "***Begin Patch", "  *** Begin Patch  ", "*** Begin Patch **"}
+	for _, line := range begin {
+		if structuredPatchMarker(line) != "begin" {
+			t.Fatalf("%q must read as the begin marker", line)
+		}
+	}
+	if structuredPatchMarker("*** End Patch ***") != "end" {
+		t.Fatal("decorated end marker must read as the end marker")
+	}
+	for _, line := range []string{"*** Update File: x", "Begin Patch", "*** Begin Patchwork"} {
+		if structuredPatchMarker(line) != "" {
+			t.Fatalf("%q must not read as a marker", line)
+		}
+	}
+}
+
+func TestStructuredPatchHeaderErrorCarriesFormatHint(t *testing.T) {
+	_, err := parseStructuredPatch("--- a/x\n+++ b/x\n")
+	if err == nil || !strings.Contains(err.Error(), "*** Update File: path") {
+		t.Fatalf("header error should teach the format, got %v", err)
+	}
+}
+
+func TestApplyPatchAcceptsAbsoluteInWorkspacePaths(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "hello.txt"), "hello\nold\n")
+	absolute := filepath.Join(root, "hello.txt")
+
+	structured := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: " + absolute,
+		"@@",
+		" hello",
+		"-old",
+		"+structured",
+		"*** End Patch",
+		"",
+	}, "\n")
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": structured})
+	if result.Status != StatusOK {
+		t.Fatalf("absolute in-workspace structured path should apply, got %s: %s", result.Status, result.Output)
+	}
+	content, _ := os.ReadFile(absolute)
+	if got := strings.ReplaceAll(string(content), "\r\n", "\n"); got != "hello\nstructured\n" {
+		t.Fatalf("structured content = %q", got)
+	}
+	if len(result.ChangedFiles) != 1 || result.ChangedFiles[0] != "hello.txt" {
+		t.Fatalf("changed files should be workspace-relative, got %v", result.ChangedFiles)
+	}
+
+	unified := strings.Join([]string{
+		"--- " + absolute,
+		"+++ " + absolute,
+		"@@ -1,2 +1,2 @@",
+		" hello",
+		"-structured",
+		"+unified",
+		"",
+	}, "\n")
+	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": unified})
+	if result.Status != StatusOK {
+		t.Fatalf("absolute in-workspace unified path should apply, got %s: %s", result.Status, result.Output)
+	}
+	content, _ = os.ReadFile(absolute)
+	if got := strings.ReplaceAll(string(content), "\r\n", "\n"); got != "hello\nunified\n" {
+		t.Fatalf("unified content = %q", got)
+	}
+}
+
+func TestApplyPatchStillRejectsAbsolutePathsOutsideWorkspace(t *testing.T) {
+	root := t.TempDir()
+	outside := filepath.Join(t.TempDir(), "escape.txt")
+	writeTestFile(t, outside, "old\n")
+
+	for name, patch := range map[string]string{
+		"structured": strings.Join([]string{"*** Begin Patch", "*** Update File: " + outside, "@@", "-old", "+new", "*** End Patch", ""}, "\n"),
+		"unified":    strings.Join([]string{"--- " + outside, "+++ " + outside, "@@ -1 +1 @@", "-old", "+new", ""}, "\n"),
+	} {
+		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+		if result.Status == StatusOK {
+			t.Fatalf("%s patch outside the workspace must be rejected", name)
+		}
+		if content, _ := os.ReadFile(outside); string(content) != "old\n" {
+			t.Fatalf("%s patch must not touch a file outside the workspace", name)
+		}
+	}
+}
+
+// Unified diffs are applied in-process through the same os.Root engine as
+// structured patches: git C-quoted paths with whitespace resolve to one file,
+// and the same header outside the workspace is refused before anything is
+// written.
+func TestUnifiedPatchQuotedWhitespacePaths(t *testing.T) {
+	root := t.TempDir()
+	dir := filepath.Join(root, "work tree")
+	if err := os.MkdirAll(dir, 0o755); err != nil {
+		t.Fatal(err)
+	}
+	target := filepath.Join(dir, "file.txt")
+	writeTestFile(t, target, "hello\nold\n")
+
+	quoted := func(path string) string { return strconv.Quote(path) }
+	inside := strings.Join([]string{
+		"diff --git " + quoted("a/"+filepath.ToSlash(target)) + " " + quoted("b/"+filepath.ToSlash(target)),
+		"--- " + quoted(target),
+		"+++ " + quoted(target),
+		"@@ -1,2 +1,2 @@",
+		" hello",
+		"-old",
+		"+new",
+		"",
+	}, "\n")
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": inside})
+	if result.Status != StatusOK {
+		t.Fatalf("quoted whitespace path inside the workspace should apply, got %s: %s", result.Status, result.Output)
+	}
+	content, _ := os.ReadFile(target)
+	if got := strings.ReplaceAll(string(content), "\r\n", "\n"); got != "hello\nnew\n" {
+		t.Fatalf("content = %q", got)
+	}
+	if len(result.ChangedFiles) != 1 || result.ChangedFiles[0] != "work tree/file.txt" {
+		t.Fatalf("changed files = %v", result.ChangedFiles)
+	}
+
+	outsideDir := filepath.Join(t.TempDir(), "other tree")
+	if err := os.MkdirAll(outsideDir, 0o755); err != nil {
+		t.Fatal(err)
+	}
+	outside := filepath.Join(outsideDir, "file.txt")
+	writeTestFile(t, outside, "hello\nold\n")
+	escape := strings.Join([]string{"--- " + quoted(outside), "+++ " + quoted(outside), "@@ -1,2 +1,2 @@", " hello", "-old", "+new", ""}, "\n")
+	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": escape})
+	if result.Status == StatusOK {
+		t.Fatal("quoted whitespace path outside the workspace must be rejected")
+	}
+	if content, _ := os.ReadFile(outside); string(content) != "hello\nold\n" {
+		t.Fatal("outside file must be untouched")
+	}
+}
+
+// A workspace path that is swapped for a symlink escaping the root — the
+// classic check-to-use attack — is refused by the os.Root engine for both
+// formats, and the outside file is never modified.
+func TestApplyPatchRefusesSymlinkEscapingWorkspace(t *testing.T) {
+	root := t.TempDir()
+	outside := filepath.Join(t.TempDir(), "secret.txt")
+	writeTestFile(t, outside, "hello\nold\n")
+	link := filepath.Join(root, "target.txt")
+	if err := os.Symlink(outside, link); err != nil {
+		t.Skipf("symlinks unavailable: %v", err)
+	}
+	for name, patch := range map[string]string{
+		"unified":    strings.Join([]string{"--- a/target.txt", "+++ b/target.txt", "@@ -1,2 +1,2 @@", " hello", "-old", "+new", ""}, "\n"),
+		"structured": strings.Join([]string{"*** Begin Patch", "*** Update File: target.txt", "@@", " hello", "-old", "+new", "*** End Patch", ""}, "\n"),
+	} {
+		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+		if result.Status == StatusOK {
+			t.Fatalf("%s patch through an escaping symlink must be refused", name)
+		}
+		if content, _ := os.ReadFile(outside); string(content) != "hello\nold\n" {
+			t.Fatalf("%s patch must not modify the file outside the workspace", name)
+		}
+	}
+}
+
+func TestUnifiedPatchCreatesDeletesAndHonoursNoNewlineMarker(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "gone.txt"), "bye\n")
+	writeTestFile(t, filepath.Join(root, "keep.txt"), "a\nb\n")
+	patch := strings.Join([]string{
+		"diff --git a/new.txt b/new.txt",
+		"new file mode 100644",
+		"--- /dev/null",
+		"+++ b/new.txt",
+		"@@ -0,0 +1,2 @@",
+		"+first",
+		"+second",
+		"\\ No newline at end of file",
+		"diff --git a/gone.txt b/gone.txt",
+		"deleted file mode 100644",
+		"--- a/gone.txt",
+		"+++ /dev/null",
+		"@@ -1 +0,0 @@",
+		"-bye",
+		"--- a/keep.txt",
+		"+++ b/keep.txt",
+		"@@ -1,2 +1,2 @@",
+		" a",
+		"-b",
+		"+c",
+		"\\ No newline at end of file",
+		"",
+	}, "\n")
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("multi-file unified patch should apply, got %s: %s", result.Status, result.Output)
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "new.txt")); string(content) != "first\nsecond" {
+		t.Fatalf("created file = %q", string(content))
+	}
+	if _, err := os.Stat(filepath.Join(root, "gone.txt")); !os.IsNotExist(err) {
+		t.Fatal("deleted file must be gone")
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "keep.txt")); string(content) != "a\nc" {
+		t.Fatalf("updated file = %q", string(content))
+	}
+	if len(result.ChangedFiles) != 3 {
+		t.Fatalf("changed files = %v", result.ChangedFiles)
+	}
+}
+
+func TestUnifiedPatchUsesRangeHintThenFallsBackToContext(t *testing.T) {
+	root := t.TempDir()
+	// Two identical blocks: the hunk's range picks the second one, which
+	// content search alone would call ambiguous.
+	writeTestFile(t, filepath.Join(root, "dup.txt"), "x\ny\nx\ny\n")
+	patch := strings.Join([]string{"--- a/dup.txt", "+++ b/dup.txt", "@@ -3,2 +3,2 @@", " x", "-y", "+z", ""}, "\n")
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("range-hinted hunk should apply, got %s: %s", result.Status, result.Output)
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "dup.txt")); string(content) != "x\ny\nx\nz\n" {
+		t.Fatalf("content = %q", string(content))
+	}
+	// A stale range (file grew above the hunk) still applies by unique context.
+	writeTestFile(t, filepath.Join(root, "moved.txt"), "header\nhello\nold\n")
+	patch = strings.Join([]string{"--- a/moved.txt", "+++ b/moved.txt", "@@ -1,2 +1,2 @@", " hello", "-old", "+new", ""}, "\n")
+	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("offset hunk should apply by context, got %s: %s", result.Status, result.Output)
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "moved.txt")); string(content) != "header\nhello\nnew\n" {
+		t.Fatalf("content = %q", string(content))
+	}
+}
+
+func TestUnifiedPatchRenameWithHunkAndRejectsBinary(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "x.txt"), "hello\nold\n")
+	rename := strings.Join([]string{
+		"diff --git a/x.txt b/y.txt",
+		"similarity index 90%",
+		"rename from x.txt",
+		"rename to y.txt",
+		"--- a/x.txt",
+		"+++ b/y.txt",
+		"@@ -1,2 +1,2 @@",
+		" hello",
+		"-old",
+		"+new",
+		"",
+	}, "\n")
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": rename})
+	if result.Status != StatusOK {
+		t.Fatalf("rename with hunk should apply, got %s: %s", result.Status, result.Output)
+	}
+	if _, err := os.Stat(filepath.Join(root, "x.txt")); !os.IsNotExist(err) {
+		t.Fatal("renamed source must be gone")
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "y.txt")); string(content) != "hello\nnew\n" {
+		t.Fatalf("renamed content = %q", string(content))
+	}
+	for name, patch := range map[string]string{
+		"binary": "diff --git a/x b/x\nBinary files a/x and b/x differ\n",
+		"empty":  "diff --git a/x b/x\n",
+	} {
+		if result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch}); result.Status == StatusOK {
+			t.Fatalf("%s patch must be rejected", name)
+		}
+	}
+}
+
+func TestUnifiedPatchCopyOperation(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "src.txt"), "hello\nold\n")
+	copyPatch := func(from, to string, hunk bool) string {
+		lines := []string{"diff --git a/" + from + " b/" + to, "similarity index 90%", "copy from " + from, "copy to " + to}
+		if hunk {
+			lines = append(lines, "--- a/"+from, "+++ b/"+to, "@@ -1,2 +1,2 @@", " hello", "-old", "+new")
+		}
+		return strings.Join(append(lines, ""), "\n")
+	}
+
+	// Success: source kept, destination created with the hunk applied, and the
+	// destination inherits the source's tracker state (read whole -> whole).
+	tracker := NewFileTracker()
+	registry := NewRegistry()
+	registry.Register(NewScopedReadFileTool(root, nil))
+	registry.Register(NewScopedApplyPatchTool(root, nil))
+	opts := RunOptions{PermissionGranted: true, FileTracker: tracker}
+	if r := registry.RunWithOptions(context.Background(), "read_file", map[string]any{"path": "src.txt"}, opts); r.Status != StatusOK {
+		t.Fatalf("read: %s", r.Output)
+	}
+	result := registry.RunWithOptions(context.Background(), "apply_patch", map[string]any{"patch": copyPatch("src.txt", "dst.txt", true)}, opts)
+	if result.Status != StatusOK {
+		t.Fatalf("copy with hunk should apply, got %s: %s", result.Status, result.Output)
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "src.txt")); string(content) != "hello\nold\n" {
+		t.Fatalf("copy must keep the source, got %q", string(content))
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "dst.txt")); string(content) != "hello\nnew\n" {
+		t.Fatalf("copy destination = %q", string(content))
+	}
+	if len(result.ChangedFiles) != 2 || result.ChangedFiles[0] != "src.txt" || result.ChangedFiles[1] != "dst.txt" {
+		t.Fatalf("changed files = %v", result.ChangedFiles)
+	}
+	destination, err := filepath.EvalSymlinks(filepath.Join(root, "dst.txt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !tracker.SeenWhole(destination) {
+		t.Fatal("destination copied from a fully read source must be tracked as seen whole")
+	}
+	unreadSource, _ := filepath.EvalSymlinks(filepath.Join(root, "src.txt"))
+	if _, tracked := tracker.Version(unreadSource); !tracked {
+		t.Fatal("source must stay tracked after a copy")
+	}
+
+	// Failure: destination already exists — nothing is written.
+	writeTestFile(t, filepath.Join(root, "taken.txt"), "keep\n")
+	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": copyPatch("src.txt", "taken.txt", false)})
+	if result.Status == StatusOK || !strings.Contains(result.Output, "already exists") {
+		t.Fatalf("copy onto an existing destination must be refused, got %s: %s", result.Status, result.Output)
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "taken.txt")); string(content) != "keep\n" {
+		t.Fatal("existing destination must be untouched")
+	}
+
+	// Failure: copy onto itself.
+	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": copyPatch("src.txt", "src.txt", false)})
+	if result.Status == StatusOK || !strings.Contains(result.Output, "onto itself") {
+		t.Fatalf("copy onto itself must be refused, got %s: %s", result.Status, result.Output)
+	}
+}
+
+func TestUnifiedPatchRejectsOverDeclaredHunkCounts(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "a.txt"), "hello\nold\n")
+	writeTestFile(t, filepath.Join(root, "b.txt"), "x\n")
+	// "-1,3 +1,3" over-declares a two-line hunk, so without a guard the next
+	// file's ---/+++ headers would be swallowed as "-"/"+" content.
+	patch := strings.Join([]string{
+		"--- a/a.txt", "+++ b/a.txt", "@@ -1,3 +1,3 @@", " hello", "-old", "+new",
+		"--- a/b.txt", "+++ b/b.txt", "@@ -1 +1 @@", "-x", "+y", "",
+	}, "\n")
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status == StatusOK || !strings.Contains(result.Output, "declared line counts") {
+		t.Fatalf("over-declared hunk must be reported as malformed, got %s: %s", result.Status, result.Output)
+	}
+	for name, want := range map[string]string{"a.txt": "hello\nold\n", "b.txt": "x\n"} {
+		if content, _ := os.ReadFile(filepath.Join(root, name)); string(content) != want {
+			t.Fatalf("%s must be untouched after a malformed patch, got %q", name, string(content))
+		}
+	}
+	// Truncated at end of input is reported the same way.
+	truncated := "--- a/a.txt\n+++ b/a.txt\n@@ -1,2 +1,2 @@\n hello\n-old\n"
+	if result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": truncated}); result.Status == StatusOK || !strings.Contains(result.Output, "declared line counts") {
+		t.Fatalf("truncated hunk must be reported as malformed, got %s: %s", result.Status, result.Output)
+	}
+}
+
+func TestUnifiedPatchNoNewlineMarkerOnlyAfterFinalHunk(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "two.txt"), "a\nb\nc\nd\ne\nf\n")
+	// A marker after the first of two hunks describes nothing real and must
+	// not leak into the second hunk's result: the patch is rejected untouched.
+	early := strings.Join([]string{
+		"--- a/two.txt", "+++ b/two.txt",
+		"@@ -1,2 +1,2 @@", " a", "-b", "+B", "\\ No newline at end of file",
+		"@@ -5,2 +5,2 @@", " e", "-f", "+F", "",
+	}, "\n")
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": early})
+	if result.Status == StatusOK || !strings.Contains(result.Output, "must follow the last hunk") {
+		t.Fatalf("marker before a later hunk must be rejected, got %s: %s", result.Status, result.Output)
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "two.txt")); string(content) != "a\nb\nc\nd\ne\nf\n" {
+		t.Fatal("rejected patch must not modify the file")
+	}
+	// The same marker after the final hunk applies and strips the newline.
+	final := strings.Join([]string{
+		"--- a/two.txt", "+++ b/two.txt",
+		"@@ -1,2 +1,2 @@", " a", "-b", "+B",
+		"@@ -5,2 +5,2 @@", " e", "-f", "+F", "\\ No newline at end of file", "",
+	}, "\n")
+	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": final})
+	if result.Status != StatusOK {
+		t.Fatalf("two-hunk patch with a final marker should apply, got %s: %s", result.Status, result.Output)
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "two.txt")); string(content) != "a\nB\nc\nd\ne\nF" {
+		t.Fatalf("content = %q", string(content))
+	}
+}
+
+// A removed "-- …" line directly followed by an added "++ …" line looks like a
+// ---/+++ header pair; the boundary check must not mistake it for one.
+func TestUnifiedPatchKeepsAdjacentDashPlusContentLines(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "notes.sql"), "select 1;\n-- old comment\nselect 2;\n")
+	patch := strings.Join([]string{
+		"--- a/notes.sql", "+++ b/notes.sql",
+		"@@ -1,3 +1,3 @@", " select 1;", "--- old comment", "+++ new comment", " select 2;", "",
+	}, "\n")
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("adjacent -- / ++ content lines must apply, got %s: %s", result.Status, result.Output)
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "notes.sql")); string(content) != "select 1;\n++ new comment\nselect 2;\n" {
+		t.Fatalf("content = %q", string(content))
+	}
+}
+
+// A unified deletion states the content it removes; it must be verified
+// against the current file before anything is deleted.
+func TestUnifiedPatchDeletionVerifiesExpectedContent(t *testing.T) {
+	deletion := func(path string, hunks ...string) string {
+		lines := []string{"diff --git a/" + path + " b/" + path, "deleted file mode 100644", "--- a/" + path, "+++ /dev/null"}
+		return strings.Join(append(append(lines, hunks...), ""), "\n")
+	}
+	t.Run("matching deletion succeeds", func(t *testing.T) {
+		root := t.TempDir()
+		writeTestFile(t, filepath.Join(root, "gone.txt"), "current\n")
+		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": deletion("gone.txt", "@@ -1 +0,0 @@", "-current")})
+		if result.Status != StatusOK {
+			t.Fatalf("matching deletion should apply, got %s: %s", result.Status, result.Output)
+		}
+		if _, err := os.Stat(filepath.Join(root, "gone.txt")); !os.IsNotExist(err) {
+			t.Fatal("file must be deleted")
+		}
+	})
+	t.Run("stale deletion is refused untouched", func(t *testing.T) {
+		root := t.TempDir()
+		writeTestFile(t, filepath.Join(root, "gone.txt"), "current\n")
+		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": deletion("gone.txt", "@@ -1 +0,0 @@", "-stale")})
+		if result.Status == StatusOK || !strings.Contains(result.Output, "does not match its current content") {
+			t.Fatalf("stale deletion must be refused, got %s: %s", result.Status, result.Output)
+		}
+		if content, _ := os.ReadFile(filepath.Join(root, "gone.txt")); string(content) != "current\n" {
+			t.Fatalf("file must be byte-for-byte unchanged, got %q", string(content))
+		}
+	})
+	t.Run("partial deletion is refused", func(t *testing.T) {
+		root := t.TempDir()
+		writeTestFile(t, filepath.Join(root, "gone.txt"), "one\ntwo\n")
+		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": deletion("gone.txt", "@@ -1 +0,0 @@", "-one")})
+		if result.Status == StatusOK || !strings.Contains(result.Output, "does not match its current content") {
+			t.Fatalf("deletion that does not cover the file must be refused, got %s: %s", result.Status, result.Output)
+		}
+		if content, _ := os.ReadFile(filepath.Join(root, "gone.txt")); string(content) != "one\ntwo\n" {
+			t.Fatal("file must be unchanged")
+		}
+	})
+	t.Run("header-only deletion is refused", func(t *testing.T) {
+		root := t.TempDir()
+		writeTestFile(t, filepath.Join(root, "gone.txt"), "current\n")
+		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": deletion("gone.txt")})
+		if result.Status == StatusOK || !strings.Contains(result.Output, "must include the hunk") {
+			t.Fatalf("header-only deletion must be refused, got %s: %s", result.Status, result.Output)
+		}
+		if _, err := os.Stat(filepath.Join(root, "gone.txt")); err != nil {
+			t.Fatal("file must still exist")
+		}
+	})
+	t.Run("multi-hunk deletion verifies everything before removing", func(t *testing.T) {
+		root := t.TempDir()
+		writeTestFile(t, filepath.Join(root, "gone.txt"), "a\nb\nc\nd\n")
+		good := deletion("gone.txt", "@@ -1,2 +0,0 @@", "-a", "-b", "@@ -3,2 +0,0 @@", "-c", "-d")
+		bad := deletion("gone.txt", "@@ -1,2 +0,0 @@", "-a", "-b", "@@ -3,2 +0,0 @@", "-c", "-stale")
+		result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": bad})
+		if result.Status == StatusOK {
+			t.Fatalf("deletion with one stale hunk must be refused: %s", result.Output)
+		}
+		if content, _ := os.ReadFile(filepath.Join(root, "gone.txt")); string(content) != "a\nb\nc\nd\n" {
+			t.Fatal("no hunk may be applied when any hunk is stale")
+		}
+		result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": good})
+		if result.Status != StatusOK {
+			t.Fatalf("multi-hunk deletion should apply, got %s: %s", result.Status, result.Output)
+		}
+		if _, err := os.Stat(filepath.Join(root, "gone.txt")); !os.IsNotExist(err) {
+			t.Fatal("file must be deleted")
+		}
+	})
+	t.Run("structured delete stays unconditional", func(t *testing.T) {
+		root := t.TempDir()
+		writeTestFile(t, filepath.Join(root, "gone.txt"), "anything\n")
+		patch := "*** Begin Patch\n*** Delete File: gone.txt\n*** End Patch\n"
+		if result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch}); result.Status != StatusOK {
+			t.Fatalf("structured delete should apply, got %s: %s", result.Status, result.Output)
+		}
+	})
+}
+
+// The source is re-read through the root immediately before commit, so a
+// change made after planning is refused instead of overwritten or removed.
+func TestApplyStructuredPatchChangeRefusesSourceChangedAfterPlanning(t *testing.T) {
+	root := t.TempDir()
+	path := filepath.Join(root, "file.txt")
+	writeTestFile(t, path, "planned\n")
+	workspace, err := os.OpenRoot(root)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer workspace.Close()
+	target := structuredPatchTarget{requested: "file.txt", absolute: path, relative: "file.txt"}
+	destination := structuredPatchTarget{requested: "copy.txt", absolute: filepath.Join(root, "copy.txt"), relative: "copy.txt"}
+	for name, change := range map[string]structuredPatchChange{
+		"update": {kind: structuredPatchUpdate, from: target, to: target, before: "planned\n", after: "new\n", mode: 0o644},
+		"delete": {kind: structuredPatchDelete, from: target, to: target, before: "planned\n", mode: 0o644},
+		"copy":   {kind: structuredPatchCopy, from: target, to: destination, before: "planned\n", after: "planned\n", mode: 0o644},
+	} {
+		writeTestFile(t, path, "changed after planning\n")
+		committed, err := applyStructuredPatchChange(workspace, change)
+		if err == nil || committed || !strings.Contains(err.Error(), "changed on disk between planning and commit") {
+			t.Fatalf("%s: expected a refusal, got committed=%v err=%v", name, committed, err)
+		}
+		if content, _ := os.ReadFile(path); string(content) != "changed after planning\n" {
+			t.Fatalf("%s: file must be untouched, got %q", name, string(content))
+		}
+		if _, statErr := os.Stat(filepath.Join(root, "copy.txt")); !os.IsNotExist(statErr) {
+			t.Fatalf("%s: refused change must not create copy.txt", name)
+		}
+	}
+}
+
+func TestUnifiedPatchDeletionIsByteExact(t *testing.T) {
+	deletion := func(hunks ...string) string {
+		return strings.Join(append(append([]string{"--- a/gone.txt", "+++ /dev/null"}, hunks...), ""), "\n")
+	}
+	for name, tc := range map[string]struct{ file, patch string }{
+		"trailing whitespace differs": {"current  \n", deletion("@@ -1 +0,0 @@", "-current")},
+		"indentation differs":         {"  current\n", deletion("@@ -1 +0,0 @@", "-current")},
+		"blank line not covered":      {"current\n\n", deletion("@@ -1 +0,0 @@", "-current")},
+		"space-only line not covered": {"current\n   \n", deletion("@@ -1 +0,0 @@", "-current")},
+		"missing final newline":       {"current", deletion("@@ -1 +0,0 @@", "-current")},
+	} {
+		t.Run(name, func(t *testing.T) {
+			root := t.TempDir()
+			writeTestFile(t, filepath.Join(root, "gone.txt"), tc.file)
+			result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": tc.patch})
+			if result.Status == StatusOK {
+				t.Fatalf("deletion must be byte-exact; %q was deleted by a non-matching hunk", tc.file)
+			}
+			if content, _ := os.ReadFile(filepath.Join(root, "gone.txt")); string(content) != tc.file {
+				t.Fatalf("file must be unchanged, got %q", string(content))
+			}
+		})
+	}
+	t.Run("no-newline marker on the removed side matches exactly", func(t *testing.T) {
+		root := t.TempDir()
+		writeTestFile(t, filepath.Join(root, "gone.txt"), "current")
+		patch := deletion("@@ -1 +0,0 @@", "-current", "\\ No newline at end of file")
+		if result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch}); result.Status != StatusOK {
+			t.Fatalf("deletion with a matching no-newline marker should apply, got %s: %s", result.Status, result.Output)
+		}
+		if _, err := os.Stat(filepath.Join(root, "gone.txt")); !os.IsNotExist(err) {
+			t.Fatal("file must be deleted")
+		}
+	})
+	t.Run("CRLF file matches an LF patch of the same content", func(t *testing.T) {
+		root := t.TempDir()
+		writeTestFile(t, filepath.Join(root, "gone.txt"), "a\r\nb\r\n")
+		if result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": deletion("@@ -1,2 +0,0 @@", "-a", "-b")}); result.Status != StatusOK {
+			t.Fatalf("CRLF deletion should apply, got %s: %s", result.Status, result.Output)
+		}
+	})
+}
+
+// git describes an empty file's creation or deletion with header lines only.
+func TestUnifiedPatchHeaderOnlyEmptyFileForms(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "empty.txt"), "")
+	writeTestFile(t, filepath.Join(root, "full.txt"), "content\n")
+	writeTestFile(t, filepath.Join(root, "keep.txt"), "a\n")
+	deleteHeader := func(path string) string {
+		return "diff --git a/" + path + " b/" + path + "\ndeleted file mode 100644\nindex e69de29..0000000\n"
+	}
+	// A non-empty file is not deleted by the header-only form.
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": deleteHeader("full.txt")})
+	if result.Status == StatusOK || !strings.Contains(result.Output, "expects an empty file") {
+		t.Fatalf("header-only deletion of a non-empty file must be refused, got %s: %s", result.Status, result.Output)
+	}
+	if _, err := os.Stat(filepath.Join(root, "full.txt")); err != nil {
+		t.Fatal("non-empty file must still exist")
+	}
+	// In a multi-file patch the empty-file deletion and creation are applied
+	// alongside a normal hunk.
+	patch := deleteHeader("empty.txt") +
+		"diff --git a/blank.txt b/blank.txt\nnew file mode 100644\nindex 0000000..e69de29\n" +
+		"diff --git a/keep.txt b/keep.txt\n--- a/keep.txt\n+++ b/keep.txt\n@@ -1 +1 @@\n-a\n+b\n"
+	result = NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("multi-file patch with header-only forms should apply, got %s: %s", result.Status, result.Output)
+	}
+	if _, err := os.Stat(filepath.Join(root, "empty.txt")); !os.IsNotExist(err) {
+		t.Fatal("empty file must be deleted")
+	}
+	if content, err := os.ReadFile(filepath.Join(root, "blank.txt")); err != nil || len(content) != 0 {
+		t.Fatalf("empty file must be created, got err=%v content=%q", err, string(content))
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "keep.txt")); string(content) != "b\n" {
+		t.Fatalf("hunk file = %q", string(content))
+	}
+	if len(result.ChangedFiles) != 3 {
+		t.Fatalf("changed files = %v", result.ChangedFiles)
+	}
+}
+
+// When a later change fails, the error names exactly which files were already
+// committed so the caller knows what changed and what did not.
+func TestApplyPatchOperationsReportsCommittedPrefixOnFailure(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "first.txt"), "one\n")
+	writeTestFile(t, filepath.Join(root, "second.txt"), "two\n")
+	writeTestFile(t, filepath.Join(root, "third.txt"), "three\n")
+	// Make second.txt change after planning so its commit is refused.
+	structuredPatchBeforeCommit = func(change structuredPatchChange) {
+		if change.to.relative == "second.txt" {
+			writeTestFile(t, filepath.Join(root, "second.txt"), "changed\n")
+		}
+	}
+	defer func() { structuredPatchBeforeCommit = nil }()
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: first.txt", "@@", "-one", "+ONE",
+		"*** Update File: second.txt", "@@", "-two", "+TWO",
+		"*** Update File: third.txt", "@@", "-three", "+THREE",
+		"*** End Patch", "",
+	}, "\n")
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status == StatusOK {
+		t.Fatal("patch must fail when a later change is refused")
+	}
+	for _, want := range []string{"already committed: first.txt", "remaining files are unchanged"} {
+		if !strings.Contains(result.Output, want) {
+			t.Fatalf("error must report the committed prefix, got: %s", result.Output)
+		}
+	}
+	if strings.Contains(result.Output, "committed: first.txt, second.txt") || strings.Contains(result.Output, "third.txt") {
+		t.Fatalf("error must not list uncommitted files as committed: %s", result.Output)
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "first.txt")); string(content) != "ONE\n" {
+		t.Fatalf("first.txt must hold the committed change, got %q", string(content))
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "second.txt")); string(content) != "changed\n" {
+		t.Fatalf("second.txt must be untouched by the patch, got %q", string(content))
+	}
+	if content, _ := os.ReadFile(filepath.Join(root, "third.txt")); string(content) != "three\n" {
+		t.Fatalf("third.txt must be untouched, got %q", string(content))
+	}
+}

internal/tools/capabilities_test.go

@@ -231,6 +231,25 @@ func TestApplyPatchResourceKeysFromDiffAndCwd(t *testing.T) {
 	}
 }
 
+func TestApplyPatchResourceKeysFromStructuredPatchAndCwd(t *testing.T) {
+	patch := "*** Begin Patch\n*** Update File: old.go\n*** Move to: new.go\n@@\n-old\n+new\n*** End Patch\n"
+	keys := applyPatchResourceKeys(map[string]any{"patch": patch, "cwd": "pkg"})
+	want := map[string]bool{
+		ResourceKeyDirectory + "pkg":   true,
+		ResourceKeyFile + "pkg/old.go": true,
+		ResourceKeyFile + "pkg/new.go": true,
+	}
+	for _, key := range keys {
+		if !want[key] {
+			t.Fatalf("unexpected key %q in %v", key, keys)
+		}
+		delete(want, key)
+	}
+	if len(want) != 0 {
+		t.Fatalf("missing keys %v from %v", want, keys)
+	}
+}
+
 func TestDeclaredMutatorThreadSafeIsReportedByCatalogValidation(t *testing.T) {
 	// Runtime CapabilitiesOf clears ThreadSafe on mutators; catalog validation
 	// must still see the raw declaration so miswired constructors fail the gate.

internal/tools/edit_file.go

@@ -168,7 +168,7 @@ func (tool editFileTool) RunWithOptions(ctx context.Context, args map[string]any
 	options.FileTracker.Record(absolutePath, []byte(updated), newInfo)
 	if updated == modelKnownContent {
 		if previouslySeenWhole {
-			options.FileTracker.RecordSeenRange(absolutePath, 1, lineCount(updated), lineCount(updated))
+			options.FileTracker.RecordSeenRange(absolutePath, 1, trackedLineTotal(updated), trackedLineTotal(updated))
 		} else {
 			for _, span := range editedSpans {
 				options.FileTracker.RecordSeenBytes(absolutePath, span.start, span.end, len(updated))

internal/tools/file_safety_test.go

@@ -221,6 +221,112 @@ func TestApplyPatchCompleteCreationCreditsSuppliedFile(t *testing.T) {
 	}
 }
 
+func TestStructuredPatchDoesNotCreditUnreadFileForOverwrite(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "f.txt")
+	if err := os.WriteFile(path, []byte("alpha\nbeta\ngamma\n"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	registry := safetyRegistry(t, dir)
+	registry.Register(NewScopedApplyPatchTool(dir, nil))
+	tracker := NewFileTracker()
+	opts := grantedOpts(tracker)
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: f.txt",
+		"@@",
+		"-beta",
+		"+updated",
+		"*** End Patch",
+		"",
+	}, "\n")
+
+	if result := registry.RunWithOptions(context.Background(), "apply_patch", map[string]any{"patch": patch}, opts); result.Status != StatusOK {
+		t.Fatalf("structured patch failed: %s", result.Output)
+	}
+	trackedPath, err := filepath.EvalSymlinks(path)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if tracker.SeenWhole(trackedPath) {
+		t.Fatal("a partial structured patch credited the unread file as fully seen")
+	}
+	result := registry.RunWithOptions(context.Background(), "write_file", map[string]any{
+		"path": "f.txt", "content": "blind overwrite\n", "overwrite": true,
+	}, opts)
+	if result.Status != StatusError || !strings.Contains(result.Output, "has not been read exactly") {
+		t.Fatalf("blind overwrite after a partial patch was not refused: %#v", result)
+	}
+	if got, want := mustReadTestFile(t, path), "alpha\nupdated\ngamma\n"; got != want {
+		t.Fatalf("file = %q, want %q", got, want)
+	}
+}
+
+func TestStructuredPatchPreservesWholeFileObservation(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "f.txt")
+	if err := os.WriteFile(path, []byte("alpha\nbeta\n"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	registry := safetyRegistry(t, dir)
+	registry.Register(NewScopedApplyPatchTool(dir, nil))
+	tracker := NewFileTracker()
+	opts := grantedOpts(tracker)
+	if result := registry.RunWithOptions(context.Background(), "read_file", map[string]any{"path": "f.txt"}, opts); result.Status != StatusOK {
+		t.Fatalf("read_file failed: %s", result.Output)
+	}
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: f.txt",
+		"@@",
+		"-alpha",
+		"+updated",
+		"*** End Patch",
+		"",
+	}, "\n")
+	if result := registry.RunWithOptions(context.Background(), "apply_patch", map[string]any{"patch": patch}, opts); result.Status != StatusOK {
+		t.Fatalf("structured patch failed: %s", result.Output)
+	}
+	trackedPath, err := filepath.EvalSymlinks(path)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !tracker.SeenWhole(trackedPath) {
+		t.Fatal("structured patch discarded an existing whole-file observation")
+	}
+	result := registry.RunWithOptions(context.Background(), "write_file", map[string]any{
+		"path": "f.txt", "content": "known overwrite\n", "overwrite": true,
+	}, opts)
+	if result.Status != StatusOK {
+		t.Fatalf("overwrite after a whole-file read was refused: %s", result.Output)
+	}
+}
+
+func TestStructuredPatchCreationCreditsSuppliedFile(t *testing.T) {
+	dir := t.TempDir()
+	registry := safetyRegistry(t, dir)
+	registry.Register(NewScopedApplyPatchTool(dir, nil))
+	tracker := NewFileTracker()
+	opts := grantedOpts(tracker)
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Add File: created.txt",
+		"+supplied",
+		"*** End Patch",
+		"",
+	}, "\n")
+	if result := registry.RunWithOptions(context.Background(), "apply_patch", map[string]any{"patch": patch}, opts); result.Status != StatusOK {
+		t.Fatalf("structured patch failed: %s", result.Output)
+	}
+	path, err := filepath.EvalSymlinks(filepath.Join(dir, "created.txt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !tracker.SeenWhole(path) {
+		t.Fatal("a fully supplied structured add was not credited as fully seen")
+	}
+}
+
 func TestWriteFileOverwriteRefusedWhenChangedOnDisk(t *testing.T) {
 	dir := t.TempDir()
 	path := filepath.Join(dir, "f.txt")

internal/tools/file_tools_test.go

@@ -26,8 +26,8 @@ func TestReadFileToolReadsLineRanges(t *testing.T) {
 	}
 	for _, want := range []string{
 		"File: notes.txt (lines 2-3 of 4)",
-		"2 | beta",
-		"3 | gamma",
+		"2→beta",
+		"3→gamma",
 	} {
 		if !strings.Contains(result.Output, want) {
 			t.Fatalf("expected output to contain %q, got %q", want, result.Output)
@@ -54,7 +54,7 @@ func TestReadFileToolReadsCanonicalLineRange(t *testing.T) {
 	if result.Truncated {
 		t.Fatalf("canonical limit defines the requested range and must not mark it truncated: %#v", result.Meta)
 	}
-	if !strings.Contains(result.Output, "2 | beta") || !strings.Contains(result.Output, "3 | gamma") {
+	if !strings.Contains(result.Output, "2→beta") || !strings.Contains(result.Output, "3→gamma") {
 		t.Fatalf("canonical range returned the wrong lines: %q", result.Output)
 	}
 	if strings.Contains(result.Output, "alpha") || strings.Contains(result.Output, "delta") {
@@ -94,7 +94,7 @@ func TestReadFileToolMixedLegacyRangesPreferLines(t *testing.T) {
 	if result.Status != StatusOK {
 		t.Fatalf("mixed legacy range should recover, got %s: %s", result.Status, result.Output)
 	}
-	if !strings.Contains(result.Output, "2 | beta") || !strings.Contains(result.Output, "3 | gamma") {
+	if !strings.Contains(result.Output, "2→beta") || !strings.Contains(result.Output, "3→gamma") {
 		t.Fatalf("mixed legacy range did not prefer lines: %q", result.Output)
 	}
 }
@@ -110,7 +110,7 @@ func TestReadFileToolCombinesLegacyStartWithCanonicalLimit(t *testing.T) {
 	if result.Status != StatusOK || result.Truncated {
 		t.Fatalf("mixed compatible range should be exact, got status=%s truncated=%v: %s", result.Status, result.Truncated, result.Output)
 	}
-	if !strings.Contains(result.Output, "2 | beta") || !strings.Contains(result.Output, "3 | gamma") {
+	if !strings.Contains(result.Output, "2→beta") || !strings.Contains(result.Output, "3→gamma") {
 		t.Fatalf("mixed compatible range returned the wrong lines: %q", result.Output)
 	}
 	if strings.Contains(result.Output, "alpha") || strings.Contains(result.Output, "delta") {
@@ -955,7 +955,7 @@ func TestReadFileToolRecoversBackwardsRange(t *testing.T) {
 	for _, want := range []string{
 		"end_line 2 was before start_line 3", // the note
 		"only line 3 was read",
-		"3 | gamma",
+		"3→gamma",
 	} {
 		if !strings.Contains(result.Output, want) {
 			t.Fatalf("expected %q in output, got %q", want, result.Output)
@@ -984,7 +984,7 @@ func TestReadFileToolValidRangeUnchangedByRecovery(t *testing.T) {
 	// Byte-for-byte: header, blank separator, the exact selected lines, and no
 	// recovery note or trailing content. An altered header/separator or a stray
 	// out-of-range line would fail this where a substring check would not.
-	const want = "File: notes.txt (lines 2-4 of 5)\n\n2 | beta\n3 | gamma\n4 | delta"
+	const want = "File: notes.txt (lines 2-4 of 5)\n\n2→beta\n3→gamma\n4→delta"
 	if result.Output != want {
 		t.Fatalf("valid-range output changed by the recovery path:\n got: %q\nwant: %q", result.Output, want)
 	}

internal/tools/model_visibility.go

@@ -0,0 +1,11 @@
+package tools
+
+// ModelVisible reports whether a registered tool is advertised to an agent.
+// Every registered tool is visible. edit_file (exact search/replace with a
+// uniqueness guard, CRLF and fuzzy fallbacks) was hidden for a while in favour
+// of apply_patch; head-to-head benchmarking showed that when a model misses the
+// patch grammar it degrades to whole-file rewrites, so both edit tools are
+// advertised and the prompt steers between them.
+func ModelVisible(tool Tool) bool {
+	return tool != nil
+}

internal/tools/model_visibility_test.go

@@ -0,0 +1,29 @@
+package tools
+
+import "testing"
+
+func TestToolSearchSurfacesBothEditTools(t *testing.T) {
+	registry := NewRegistry()
+	registry.Register(NewScopedEditFileTool(t.TempDir(), nil))
+	registry.Register(NewScopedApplyPatchTool(t.TempDir(), nil))
+	search := NewToolSearchTool(registry).(toolSearchTool)
+
+	eager := search.visibleEagerToolNames(nil, nil, "ask")
+	if !eager["edit_file"] {
+		t.Fatal("tool_search must describe edit_file as available to the model")
+	}
+	if !eager["apply_patch"] {
+		t.Fatal("tool_search must retain apply_patch as an available edit tool")
+	}
+}
+
+func TestModelVisibleAdvertisesEveryRegisteredTool(t *testing.T) {
+	if ModelVisible(nil) {
+		t.Fatal("a nil tool must not be visible")
+	}
+	for _, tool := range []Tool{NewScopedEditFileTool(t.TempDir(), nil), NewScopedApplyPatchTool(t.TempDir(), nil), NewScopedWriteFileTool(t.TempDir(), nil)} {
+		if !ModelVisible(tool) {
+			t.Fatalf("%s must be visible to the model", tool.Name())
+		}
+	}
+}

internal/tools/mutation_targets.go

@@ -1,5 +1,7 @@
 package tools
 
+import "path/filepath"
+
 // MutationTargets returns the workspace-relative paths a tool call will write to,
 // so the session layer can snapshot their before-state for safe rewind. It is a
 // pure helper (no I/O beyond path resolution) and returns nil for read-only tools
@@ -36,6 +38,19 @@ func MutationTargets(workspaceRoot string, name string, args map[string]any) []s
 		if err != nil {
 			return nil
 		}
+		if isStructuredPatch(patch) {
+			operations, err := parseStructuredPatch(patch)
+			if err != nil {
+				return nil
+			}
+			paths := structuredPatchOperationPaths(operations)
+			for _, path := range paths {
+				if _, _, err := resolveWorkspaceTargetPath(applyRoot, path); err != nil {
+					return nil
+				}
+			}
+			return prefixPatchPaths(relativeRoot, paths)
+		}
 		// Enforce the same workspace confinement apply_patch applies (against the
 		// resolved apply dir), so a patch with a traversal path (../x) never yields
 		// an out-of-workspace target.
@@ -51,3 +66,22 @@ func MutationTargets(workspaceRoot string, name string, args map[string]any) []s
 		return nil
 	}
 }
+
+func prefixPatchPaths(relativeRoot string, paths []string) []string {
+	if len(paths) == 0 {
+		return nil
+	}
+	seen := make(map[string]bool)
+	var out []string
+	for _, path := range paths {
+		workspacePath := path
+		if relativeRoot != "" && relativeRoot != "." {
+			workspacePath = filepath.ToSlash(filepath.Join(relativeRoot, path))
+		}
+		if !seen[workspacePath] {
+			seen[workspacePath] = true
+			out = append(out, workspacePath)
+		}
+	}
+	return out
+}

internal/tools/mutation_targets_test.go

@@ -17,6 +17,7 @@ func TestMutationTargets(t *testing.T) {
 		{"write_file", map[string]any{"path": "a/b.txt", "content": "x"}, []string{"a/b.txt"}},
 		{"edit_file", map[string]any{"path": "c.txt", "old_string": "x", "new_string": "y"}, []string{"c.txt"}},
 		{"apply_patch", map[string]any{"patch": "--- a/d.txt\n+++ b/d.txt\n@@ -1 +1 @@\n-x\n+y\n"}, []string{"d.txt"}},
+		{"apply_patch", map[string]any{"patch": "*** Begin Patch\n*** Add File: nested/new.txt\n+x\n*** Update File: old.txt\n*** Move to: moved.txt\n@@\n-old\n+new\n*** End Patch\n"}, []string{"nested/new.txt", "old.txt", "moved.txt"}},
 		{"bash", map[string]any{"command": "echo hi"}, nil},
 		{"read_file", map[string]any{"path": "e.txt"}, nil},
 		{"grep", map[string]any{"pattern": "x"}, nil},
@@ -62,6 +63,10 @@ func TestMutationTargetsRejectsEscapingPaths(t *testing.T) {
 	if got := MutationTargets(root, "apply_patch", map[string]any{"patch": escapePatch}); len(got) != 0 {
 		t.Errorf("expected no targets for escaping apply_patch, got %v", got)
 	}
+	structuredEscapePatch := "*** Begin Patch\n*** Add File: ../escape.txt\n+x\n*** End Patch\n"
+	if got := MutationTargets(root, "apply_patch", map[string]any{"patch": structuredEscapePatch}); len(got) != 0 {
+		t.Errorf("expected no targets for escaping structured apply_patch, got %v", got)
+	}
 }
 
 // Finding 3: with cwd != ".", apply_patch's MutationTargets must return
@@ -82,6 +87,12 @@ func TestMutationTargetsApplyPatchPrefixesCwd(t *testing.T) {
 		t.Fatalf("got %v, want %v", got, want)
 	}
 
+	structuredPatch := "*** Begin Patch\n*** Update File: d.txt\n@@\n-x\n+y\n*** End Patch\n"
+	got = MutationTargets(root, "apply_patch", map[string]any{"patch": structuredPatch, "cwd": "sub/dir"})
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("structured cwd: got %v, want %v", got, want)
+	}
+
 	// cwd "." (the default) must keep paths unprefixed.
 	got = MutationTargets(root, "apply_patch", map[string]any{"patch": patch, "cwd": "."})
 	if !reflect.DeepEqual(got, []string{"d.txt"}) {

internal/tools/read_file.go

@@ -9,12 +9,14 @@ import (
 	"io"
 	"os"
 	"strconv"
-	"strings"
 	"unicode/utf8"
 )
 
 const readFileByteChunkMax = 64 * 1024
 
+// readFileLinePrefixSeparator follows the line number on every read_file line.
+const readFileLinePrefixSeparator = "→"
+
 type readFileTool struct {
 	baseTool
 	workspaceRoot string
@@ -31,7 +33,7 @@ func NewScopedReadFileTool(workspaceRoot string, scope PathScope) Tool {
 	return readFileTool{
 		baseTool: baseTool{
 			name:        "read_file",
-			description: "Read exact file text with line numbers. Use for comments, formatting, or edits; prefer read_minified_file for initial code understanding. Use offset and limit for a line range.",
+			description: "Read exact file text, each line prefixed with its line number and →. Use for comments, formatting, or edits; prefer read_minified_file for initial code understanding. Use offset and limit for a line range.",
 			parameters: Schema{
 				Type: "object",
 				Properties: map[string]PropertySchema{
@@ -221,7 +223,6 @@ func renderReadFileRange(absolutePath string, relativePath string, total int, st
 	}
 
 	lastLine := startLine + selectedLines - 1
-	width := len(strconv.Itoa(lastLine))
 	header := fmt.Sprintf("File: %s (%d lines)", relativePath, total)
 	if startLine != 1 || endLine != total || maxLines > 0 {
 		header = fmt.Sprintf("File: %s (lines %d-%d of %d)", relativePath, startLine, lastLine, total)
@@ -244,7 +245,7 @@ func renderReadFileRange(absolutePath string, relativePath string, total int, st
 		budgetedOutput.WriteString("\n")
 	}
 	budgetedOutput.WriteString("\n")
-	if err := appendReadFileRange(budgetedOutput, absolutePath, startLine, selectedLines, width); err != nil {
+	if err := appendReadFileRange(budgetedOutput, absolutePath, startLine, selectedLines); err != nil {
 		return errorResult("Error reading file " + relativePath + ": " + err.Error())
 	}
 	if truncated {
@@ -357,7 +358,7 @@ func renderReadFileBytes(path, relativePath string, total, requestedStart, limit
 	return Result{Status: StatusOK, Output: output, Meta: map[string]string{"next_byte_offset": strconv.Itoa(end)}}, start, end
 }
 
-func appendReadFileRange(output *outputBudgetBuilder, path string, startLine int, selectedLines int, width int) error {
+func appendReadFileRange(output *outputBudgetBuilder, path string, startLine int, selectedLines int) error {
 	file, err := os.Open(path)
 	if err != nil {
 		return err
@@ -380,10 +381,11 @@ func appendReadFileRange(output *outputBudgetBuilder, path string, startLine int
 			if emitted > 0 {
 				output.WriteString("\n")
 			}
-			number := strconv.Itoa(lineNumber)
-			output.WriteString(strings.Repeat(" ", width-len(number)))
-			output.WriteString(number)
-			output.WriteString(" | ")
+			// Compact "N→" prefix: the padded "  N | " form cost ~19% of every
+			// read (about 1.5k tokens per 800-line file) and was re-sent on each
+			// later call; no consumer parses it, and models read "N→" natively.
+			output.WriteString(strconv.Itoa(lineNumber))
+			output.WriteString(readFileLinePrefixSeparator)
 			output.WriteString(string(trimLineBreak(raw, ended)))
 			emitted++
 		}

internal/tools/read_minified_file.go

@@ -171,14 +171,9 @@ func selectSourceLines(content []byte, offset, limit int) sourceSelection {
 }
 
 func sourceLineCount(content []byte) int {
-	if len(content) == 0 {
-		return 1
-	}
-	lines := strings.Count(string(content), "\n")
-	if content[len(content)-1] != '\n' {
-		lines++
-	}
-	return lines
+	// One implementation for reader and writer: the tracker contract lives on
+	// trackedLineTotal, and this must never drift from it.
+	return trackedLineTotal(string(content))
 }
 
 // lineCount reports the number of newline-separated lines in s (an empty string
@@ -189,3 +184,20 @@ func lineCount(s string) int {
 	}
 	return strings.Count(s, "\n") + 1
 }
+
+// trackedLineTotal reports a file's line count the way read_file reports it
+// to the FileTracker (newline-terminated lines, plus an unterminated last
+// line; an empty file is one line). Writers must record this same number:
+// RecordSeenRange resets every observation when the total changes, so a
+// writer that recorded lineCount (one higher for a trailing newline) made the
+// next partial read_file wipe whole-file knowledge and refuse the next edit.
+func trackedLineTotal(s string) int {
+	if s == "" {
+		return 1
+	}
+	total := strings.Count(s, "\n")
+	if !strings.HasSuffix(s, "\n") {
+		total++
+	}
+	return total
+}

internal/tools/resource_keys.go

@@ -178,7 +178,7 @@ func applyPatchResourceKeys(args map[string]any) []string {
 	keys = append(keys, multiFileResourceKeys(args)...)
 	cwd := firstStringArg(args, "cwd", "workdir")
 	patch := firstStringArg(args, "patch", "diff")
-	for _, p := range pathsFromUnifiedDiff(patch) {
+	for _, p := range pathsFromApplyPatch(patch) {
 		joined := joinUnderResourceCwd(cwd, p)
 		if n := NormalizeResourcePath(joined); n != "" {
 			keys = append(keys, ResourceKeyFile+n)
@@ -191,6 +191,17 @@ func applyPatchResourceKeys(args map[string]any) []string {
 	return keys
 }
 
+func pathsFromApplyPatch(patch string) []string {
+	if !isStructuredPatch(patch) {
+		return pathsFromUnifiedDiff(patch)
+	}
+	operations, err := parseStructuredPatch(patch)
+	if err != nil {
+		return nil
+	}
+	return structuredPatchOperationPaths(operations)
+}
+
 // joinUnderResourceCwd joins a relative path under cwd for resource keys only.
 // Absolute paths are left unchanged. Empty cwd or "." leaves rel as-is.
 // Never touches the filesystem.

internal/tools/structured_patch.go

@@ -0,0 +1,959 @@
+package tools
+
+import (
+	"errors"
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"regexp"
+	"strings"
+
+	"github.com/Gitlawb/zero/internal/pathjail"
+	"github.com/Gitlawb/zero/internal/sandbox"
+)
+
+const (
+	structuredPatchBegin  = "*** Begin Patch"
+	structuredPatchEnd    = "*** End Patch"
+	structuredAddFile     = "*** Add File: "
+	structuredDeleteFile  = "*** Delete File: "
+	structuredUpdateFile  = "*** Update File: "
+	structuredMoveTo      = "*** Move to: "
+	structuredEndOfFile   = "*** End of File"
+	structuredHunkContext = "@@ "
+)
+
+type structuredPatchKind uint8
+
+const (
+	structuredPatchAdd structuredPatchKind = iota
+	structuredPatchDelete
+	structuredPatchUpdate
+	// structuredPatchCopy creates movePath from path's content (plus any
+	// hunks) and keeps path; produced by a unified diff's "copy from/to".
+	structuredPatchCopy
+)
+
+type structuredPatchOperation struct {
+	kind     structuredPatchKind
+	path     string
+	movePath string
+	contents string
+	chunks   []structuredPatchChunk
+	line     int
+	// eofNewline lets a unified diff's "\ No newline at end of file" marker
+	// force the trailing-newline state of the result; structured patches keep
+	// the file's existing state.
+	eofNewline eofNewlineMode
+	// verifyDelete marks a deletion that carries the expected old content
+	// (a unified diff's "+++ /dev/null" hunks, or git's header-only form for
+	// an empty file): the removed lines must equal the current file byte for
+	// byte, otherwise the deletion is stale and refused. A structured
+	// "*** Delete File" means "delete this path" and has no chunks.
+	verifyDelete bool
+	// oldNoNewline records a unified diff's "\ No newline at end of file"
+	// on the removed side, i.e. the old content did not end with a newline.
+	oldNoNewline bool
+}
+
+type eofNewlineMode uint8
+
+const (
+	eofNewlineKeep eofNewlineMode = iota
+	eofNewlinePresent
+	eofNewlineAbsent
+)
+
+type structuredPatchChunk struct {
+	context          string
+	hasContext       bool
+	old              []string
+	new              []string
+	newSourceOffsets []int
+	endOfFile        bool
+	// hint is the 0-based line the hunk is expected at (from a unified diff's
+	// "@@ -a,b" range). When the expected lines match there it is used as-is;
+	// otherwise the hunk is located by content like a structured hunk.
+	hint    int
+	hasHint bool
+}
+
+type structuredPatchTarget struct {
+	requested string
+	absolute  string
+	relative  string
+}
+
+type structuredPatchChange struct {
+	kind   structuredPatchKind
+	from   structuredPatchTarget
+	to     structuredPatchTarget
+	before string
+	after  string
+	mode   os.FileMode
+}
+
+// unifiedHunkRangePattern recognises a unified-diff range header ("-12,4 +12,6",
+// optionally followed by "@@ heading") written inside a structured hunk marker.
+// The line numbers carry no information for the context-anchored grammar, so
+// the range is dropped and only an explicit heading is kept as the anchor.
+var unifiedHunkRangePattern = regexp.MustCompile(`^-\d+(?:,\d+)?\s+\+\d+(?:,\d+)?\s*(?:@@\s*(.*))?$`)
+
+const structuredPatchFormatHint = ` (format: "*** Begin Patch", then "*** Update File: path" / "*** Add File: path" / "*** Delete File: path" sections whose hunks start with "@@" and use " " context, "-" removed and "+" added lines, then "*** End Patch")`
+
+// structuredPatchMarker classifies a line as the "begin" or "end" marker of a
+// structured patch, or "" when it is neither. The classifier is owned by the
+// sandbox package so the boundary check and the tool accept exactly the same
+// spellings; a strict byte-equal match here once made every patch from some
+// models fail on line 1 and pushed them into whole-file rewrites.
+func structuredPatchMarker(line string) string {
+	return sandbox.StructuredPatchMarker(line)
+}
+
+// structuredHunkAnchor normalises the text after a hunk's "@@ " marker. A
+// unified-diff range is dropped (its optional heading survives as the anchor);
+// anything else is used verbatim.
+func structuredHunkAnchor(context string) string {
+	context = strings.TrimSpace(context)
+	if match := unifiedHunkRangePattern.FindStringSubmatch(context); match != nil {
+		return strings.TrimSpace(match[1])
+	}
+	return context
+}
+
+func isStructuredPatch(patch string) bool {
+	return sandbox.IsStructuredPatch(patch)
+}
+
+func (tool applyPatchTool) runStructuredPatch(applyRoot, relativeRoot, patch string, options RunOptions) Result {
+	operations, err := parseStructuredPatch(patch)
+	if err != nil {
+		return errorResult("Error applying patch: " + err.Error())
+	}
+	return applyPatchOperations(applyRoot, relativeRoot, operations, options)
+}
+
+// applyPatchOperations applies parsed operations (from either patch format)
+// through an opened workspace root: every stat, read, create and write is
+// descriptor-relative and refuses to follow a link out of the root, so there
+// is no pathname check-to-use window between validation and write.
+func applyPatchOperations(applyRoot, relativeRoot string, operations []structuredPatchOperation, options RunOptions) Result {
+	workspace, err := os.OpenRoot(applyRoot)
+	if err != nil {
+		return errorResult("Error applying patch: " + err.Error())
+	}
+	defer workspace.Close()
+	changes, err := planStructuredPatch(workspace, operations, options.FileTracker)
+	if err != nil {
+		return errorResult("Error applying patch: " + err.Error())
+	}
+	wholeBefore := make(map[string]bool, len(changes))
+	if options.FileTracker != nil {
+		for _, change := range changes {
+			if change.kind == structuredPatchUpdate || change.kind == structuredPatchCopy {
+				wholeBefore[change.from.absolute] = options.FileTracker.SeenWhole(change.from.absolute)
+			}
+		}
+	}
+	if err := applyStructuredPatchChanges(workspace, changes, options.FileTracker); err != nil {
+		return errorResult("Error applying patch: " + err.Error())
+	}
+
+	for _, change := range changes {
+		switch change.kind {
+		case structuredPatchDelete:
+			options.FileTracker.Forget(change.from.absolute)
+		case structuredPatchAdd:
+			recordStructuredPatchFile(options.FileTracker, change.to.absolute, true, true)
+		case structuredPatchUpdate:
+			wasWhole := wholeBefore[change.from.absolute]
+			options.FileTracker.Forget(change.from.absolute)
+			recordStructuredPatchFile(options.FileTracker, change.to.absolute, false, wasWhole)
+		case structuredPatchCopy:
+			// The source is untouched; the destination inherits only what the
+			// model had actually seen of the source.
+			recordStructuredPatchFile(options.FileTracker, change.to.absolute, true, wholeBefore[change.from.absolute])
+		}
+	}
+
+	summary := "Patch applied successfully."
+	if relativeRoot != "." {
+		summary = "Patch applied successfully in " + relativeRoot + "."
+	}
+	result := okResult(summary)
+	result.ChangedFiles = changedFilesFromStructuredPatch(relativeRoot, changes)
+	result.Display = Display{Summary: summary, Kind: "diff", Preview: structuredPatchPreview(changes)}
+	return result
+}
+
+func parseStructuredPatch(patch string) ([]structuredPatchOperation, error) {
+	normalized := strings.TrimSpace(strings.TrimPrefix(strings.ReplaceAll(patch, "\r\n", "\n"), "\ufeff"))
+	if normalized == "" {
+		return nil, fmt.Errorf("structured patch is empty")
+	}
+	lines := strings.Split(normalized, "\n")
+	if structuredPatchMarker(lines[0]) != "begin" {
+		return nil, fmt.Errorf("the first line of a structured patch must be %q%s", structuredPatchBegin, structuredPatchFormatHint)
+	}
+	if structuredPatchMarker(lines[len(lines)-1]) != "end" {
+		return nil, fmt.Errorf("the last line of a structured patch must be %q%s", structuredPatchEnd, structuredPatchFormatHint)
+	}
+
+	var operations []structuredPatchOperation
+	for index := 1; index < len(lines)-1; {
+		header := strings.TrimSpace(lines[index])
+		lineNumber := index + 1
+		if header == "" {
+			index++
+			continue
+		}
+		switch {
+		case strings.HasPrefix(header, structuredAddFile):
+			path, err := structuredPatchPath(header, structuredAddFile, lineNumber)
+			if err != nil {
+				return nil, err
+			}
+			op := structuredPatchOperation{kind: structuredPatchAdd, path: path, line: lineNumber}
+			index++
+			var content []string
+			for index < len(lines)-1 && !isStructuredPatchHeader(lines[index]) {
+				if !strings.HasPrefix(lines[index], "+") {
+					return nil, structuredPatchLineError(index+1, "added-file contents must start with '+'")
+				}
+				content = append(content, strings.TrimPrefix(lines[index], "+"))
+				index++
+			}
+			if len(content) > 0 {
+				op.contents = strings.Join(content, "\n") + "\n"
+			}
+			operations = append(operations, op)
+		case strings.HasPrefix(header, structuredDeleteFile):
+			path, err := structuredPatchPath(header, structuredDeleteFile, lineNumber)
+			if err != nil {
+				return nil, err
+			}
+			operations = append(operations, structuredPatchOperation{kind: structuredPatchDelete, path: path, line: lineNumber})
+			index++
+		case strings.HasPrefix(header, structuredUpdateFile):
+			path, err := structuredPatchPath(header, structuredUpdateFile, lineNumber)
+			if err != nil {
+				return nil, err
+			}
+			op := structuredPatchOperation{kind: structuredPatchUpdate, path: path, line: lineNumber}
+			index++
+			if index < len(lines)-1 && strings.HasPrefix(strings.TrimSpace(lines[index]), structuredMoveTo) {
+				op.movePath, err = structuredPatchPath(strings.TrimSpace(lines[index]), structuredMoveTo, index+1)
+				if err != nil {
+					return nil, err
+				}
+				index++
+			}
+			for index < len(lines)-1 && !isStructuredPatchHeader(lines[index]) {
+				line := lines[index]
+				trimmed := strings.TrimSpace(line)
+				if trimmed == structuredEndOfFile {
+					if len(op.chunks) == 0 || (!hasStructuredPatchContent(op.chunks[len(op.chunks)-1])) {
+						return nil, structuredPatchLineError(index+1, "*** End of File must follow an update hunk")
+					}
+					op.chunks[len(op.chunks)-1].endOfFile = true
+					index++
+					continue
+				}
+				if trimmed == "@@" || strings.HasPrefix(trimmed, structuredHunkContext) {
+					chunk := structuredPatchChunk{}
+					rest := ""
+					if trimmed != "@@" {
+						rest = strings.TrimPrefix(trimmed, structuredHunkContext)
+					}
+					if anchor := structuredHunkAnchor(rest); anchor != "" {
+						chunk.context = anchor
+						chunk.hasContext = true
+					}
+					op.chunks = append(op.chunks, chunk)
+					index++
+					continue
+				}
+				if len(op.chunks) == 0 {
+					op.chunks = append(op.chunks, structuredPatchChunk{})
+				}
+				chunk := &op.chunks[len(op.chunks)-1]
+				switch {
+				case line == "":
+					sourceOffset := len(chunk.old)
+					chunk.old = append(chunk.old, "")
+					chunk.new = append(chunk.new, "")
+					chunk.newSourceOffsets = append(chunk.newSourceOffsets, sourceOffset)
+				case strings.HasPrefix(line, " "):
+					content := strings.TrimPrefix(line, " ")
+					sourceOffset := len(chunk.old)
+					chunk.old = append(chunk.old, content)
+					chunk.new = append(chunk.new, content)
+					chunk.newSourceOffsets = append(chunk.newSourceOffsets, sourceOffset)
+				case strings.HasPrefix(line, "+"):
+					chunk.new = append(chunk.new, strings.TrimPrefix(line, "+"))
+					chunk.newSourceOffsets = append(chunk.newSourceOffsets, -1)
+				case strings.HasPrefix(line, "-"):
+					chunk.old = append(chunk.old, strings.TrimPrefix(line, "-"))
+				default:
+					return nil, structuredPatchLineError(index+1, "update lines must start with ' ', '+', or '-'")
+				}
+				index++
+			}
+			if len(op.chunks) == 0 || !allStructuredPatchChunksHaveContent(op.chunks) {
+				return nil, structuredPatchLineError(lineNumber, "update file hunk is empty")
+			}
+			operations = append(operations, op)
+		default:
+			return nil, structuredPatchLineError(lineNumber, "expected an Add File, Delete File, or Update File header")
+		}
+	}
+	if len(operations) == 0 {
+		return nil, fmt.Errorf("structured patch contains no file operations")
+	}
+	return operations, nil
+}
+
+func structuredPatchPath(header, prefix string, line int) (string, error) {
+	path := strings.TrimSpace(strings.TrimPrefix(header, prefix))
+	if path == "" {
+		return "", structuredPatchLineError(line, "file path is required")
+	}
+	return path, nil
+}
+
+func isStructuredPatchHeader(line string) bool {
+	return structuredPatchMarker(line) == "end" || strings.HasPrefix(line, structuredAddFile) || strings.HasPrefix(line, structuredDeleteFile) || strings.HasPrefix(line, structuredUpdateFile)
+}
+
+func structuredPatchLineError(line int, message string) error {
+	return fmt.Errorf("invalid structured patch at line %d: %s", line, message)
+}
+
+func hasStructuredPatchContent(chunk structuredPatchChunk) bool {
+	return len(chunk.old) > 0 || len(chunk.new) > 0
+}
+
+func allStructuredPatchChunksHaveContent(chunks []structuredPatchChunk) bool {
+	for _, chunk := range chunks {
+		if !hasStructuredPatchContent(chunk) {
+			return false
+		}
+	}
+	return true
+}
+
+func structuredPatchOperationPaths(operations []structuredPatchOperation) []string {
+	seen := make(map[string]bool)
+	var paths []string
+	for _, operation := range operations {
+		for _, path := range []string{operation.path, operation.movePath} {
+			if path == "" || seen[path] {
+				continue
+			}
+			seen[path] = true
+			paths = append(paths, path)
+		}
+	}
+	return paths
+}
+
+func planStructuredPatch(root *os.Root, operations []structuredPatchOperation, tracker *FileTracker) ([]structuredPatchChange, error) {
+	seen := make(map[string]struct{})
+	var changes []structuredPatchChange
+	for _, operation := range operations {
+		from, err := resolveStructuredPatchTarget(root.Name(), operation.path)
+		if err != nil {
+			return nil, err
+		}
+		to := from
+		if operation.movePath != "" {
+			to, err = resolveStructuredPatchTarget(root.Name(), operation.movePath)
+			if err != nil {
+				return nil, err
+			}
+		}
+		targets := []structuredPatchTarget{from}
+		if to.absolute != from.absolute {
+			targets = append(targets, to)
+		}
+		for _, target := range targets {
+			if _, exists := seen[target.absolute]; exists {
+				return nil, fmt.Errorf("structured patch changes %q more than once", target.relative)
+			}
+			seen[target.absolute] = struct{}{}
+		}
+
+		change := structuredPatchChange{kind: operation.kind, from: from, to: to, mode: 0o644}
+		switch operation.kind {
+		case structuredPatchAdd:
+			if _, err := root.Lstat(to.relative); err == nil {
+				return nil, fmt.Errorf("cannot add %s because it already exists", to.relative)
+			} else if !os.IsNotExist(err) {
+				return nil, err
+			}
+			change.after = operation.contents
+		case structuredPatchDelete, structuredPatchUpdate, structuredPatchCopy:
+			info, err := root.Stat(from.relative)
+			if err != nil {
+				return nil, fmt.Errorf("stating %s: %w", from.relative, err)
+			}
+			change.mode = info.Mode()
+			content, err := root.ReadFile(from.relative)
+			if err != nil {
+				return nil, fmt.Errorf("reading %s: %w", from.relative, err)
+			}
+			if err := tracker.CheckConflict(from.absolute, content); err != nil {
+				return nil, fmt.Errorf("%s", fileConflictMessage(from.relative))
+			}
+			change.before = string(content)
+			if operation.kind == structuredPatchDelete && operation.verifyDelete {
+				if err := verifyUnifiedDeletion(change.before, from.relative, operation); err != nil {
+					return nil, err
+				}
+			}
+			if operation.kind == structuredPatchUpdate || operation.kind == structuredPatchCopy {
+				updated, err := applyStructuredPatchUpdate(change.before, from.relative, operation.chunks)
+				if err != nil {
+					return nil, err
+				}
+				change.after = applyEOFNewline(updated, operation.eofNewline)
+				if operation.kind == structuredPatchCopy && from.absolute == to.absolute {
+					return nil, fmt.Errorf("cannot copy %s onto itself", from.relative)
+				}
+				if from.absolute != to.absolute {
+					if _, err := root.Lstat(to.relative); err == nil {
+						return nil, fmt.Errorf("cannot move %s to %s because the destination already exists", from.relative, to.relative)
+					} else if !os.IsNotExist(err) {
+						return nil, err
+					}
+				}
+			}
+		}
+		changes = append(changes, change)
+	}
+	return changes, nil
+}
+
+func resolveStructuredPatchTarget(root, path string) (structuredPatchTarget, error) {
+	// Relative traversal is rejected outright. An absolute path is allowed when
+	// it resolves inside the apply root (models routinely echo the absolute path
+	// they were shown by read_file); resolveWorkspaceTargetPath rejects anything
+	// that lands outside.
+	if path == ".." || strings.HasPrefix(filepath.ToSlash(path), "../") {
+		return structuredPatchTarget{}, fmt.Errorf("patch path %q must stay inside the workspace", path)
+	}
+	absolute, relative, err := resolveWorkspaceTargetPath(root, normalizePatchPathForRoot(root, path))
+	if err != nil {
+		return structuredPatchTarget{}, err
+	}
+	return structuredPatchTarget{requested: path, absolute: absolute, relative: relative}, nil
+}
+
+func applyStructuredPatchUpdate(content, path string, chunks []structuredPatchChunk) (string, error) {
+	lineEnding := structuredPatchLineEnding(content)
+	if lineEnding == "\r\n" {
+		content = strings.ReplaceAll(content, "\r\n", "\n")
+	}
+	lines := strings.Split(content, "\n")
+	trailingNewline := content != "" && len(lines) > 0 && lines[len(lines)-1] == ""
+	if len(lines) > 0 && lines[len(lines)-1] == "" {
+		lines = lines[:len(lines)-1]
+	}
+	replacements := make([]structuredReplacement, 0, len(chunks))
+	lineIndex := 0
+	for _, chunk := range chunks {
+		if chunk.hasContext {
+			index, ambiguous := findStructuredPatchSequence(lines, []string{chunk.context}, lineIndex, false)
+			if ambiguous {
+				return "", fmt.Errorf("context %q is ambiguous in %s; provide a more specific hunk header", chunk.context, path)
+			}
+			if index < 0 {
+				return "", fmt.Errorf("could not find context %q in %s", chunk.context, path)
+			}
+			lineIndex = index + 1
+		}
+		if len(chunk.old) == 0 {
+			// A context anchor identifies the line immediately before a pure
+			// insertion. Only an explicit end-of-file hunk (or an unanchored
+			// insertion) belongs at the file end. A unified diff names the
+			// insertion point in its range instead; a zero-context hunk (as
+			// from `git diff -U0`) has nothing to verify the position against,
+			// so it is position-trusting by design — the same semantics git
+			// apply uses without fuzz. Hunks that carry context are verified.
+			start := lineIndex
+			if chunk.hasHint {
+				start = max(chunk.hint, lineIndex)
+			} else if chunk.endOfFile || !chunk.hasContext {
+				start = len(lines)
+			}
+			if start > len(lines) {
+				start = len(lines)
+			}
+			replacement, err := structuredPatchReplacement(chunk, lines, start)
+			if err != nil {
+				return "", fmt.Errorf("building replacement for %s: %w", path, err)
+			}
+			replacements = append(replacements, structuredReplacement{start: start, replacement: replacement})
+			lineIndex = start
+			continue
+		}
+		var index int
+		ambiguous := false
+		if chunk.hasHint && chunk.hint >= lineIndex && sequenceMatchesAt(lines, chunk.old, chunk.hint) {
+			index = chunk.hint
+		} else {
+			index, ambiguous = findStructuredPatchSequence(lines, chunk.old, lineIndex, chunk.endOfFile)
+		}
+		if ambiguous {
+			return "", fmt.Errorf("expected lines are ambiguous in %s; provide more surrounding context:\n%s", path, strings.Join(chunk.old, "\n"))
+		}
+		if index < 0 {
+			return "", fmt.Errorf("could not find expected lines in %s:\n%s", path, strings.Join(chunk.old, "\n"))
+		}
+		replacement, err := structuredPatchReplacement(chunk, lines, index)
+		if err != nil {
+			return "", fmt.Errorf("building replacement for %s: %w", path, err)
+		}
+		replacements = append(replacements, structuredReplacement{start: index, length: len(chunk.old), replacement: replacement})
+		lineIndex = index + len(chunk.old)
+	}
+	for index := 1; index < len(replacements); index++ {
+		previous := replacements[index-1]
+		current := replacements[index]
+		if current.start < previous.start+previous.length {
+			return "", fmt.Errorf("overlapping or out-of-order hunks in %s; provide non-overlapping context", path)
+		}
+	}
+	for index := len(replacements) - 1; index >= 0; index-- {
+		replacement := replacements[index]
+		lines = append(lines[:replacement.start], append(replacement.replacement, lines[replacement.start+replacement.length:]...)...)
+	}
+	if len(lines) == 0 {
+		return "", nil
+	}
+	updated := strings.Join(lines, lineEnding)
+	if trailingNewline {
+		updated += lineEnding
+	}
+	return updated, nil
+}
+
+// verifyUnifiedDeletion checks, byte for byte, that the lines a unified
+// deletion removes are exactly the file's current content. A deletion is not
+// recoverable, so none of the whitespace tolerance used to locate update
+// hunks applies here; only the file's own line-ending style is normalised.
+// With no hunks (git's header-only form) the file must be empty.
+func verifyUnifiedDeletion(current, path string, operation structuredPatchOperation) error {
+	var removed []string
+	for _, chunk := range operation.chunks {
+		if len(chunk.new) > 0 {
+			return fmt.Errorf("deletion of %s must not add lines", path)
+		}
+		removed = append(removed, chunk.old...)
+	}
+	expected := strings.Join(removed, "\n")
+	if len(removed) > 0 && !operation.oldNoNewline {
+		expected += "\n"
+	}
+	actual := current
+	if structuredPatchLineEnding(current) == "\r\n" {
+		actual = strings.ReplaceAll(current, "\r\n", "\n")
+	}
+	if actual != expected {
+		if len(removed) == 0 {
+			return fmt.Errorf("deletion of %s expects an empty file but it has content; include the removed lines in the patch", path)
+		}
+		return fmt.Errorf("deletion of %s does not match its current content; the removed lines must equal the whole file", path)
+	}
+	return nil
+}
+
+// sequenceMatchesAt reports whether wanted appears verbatim at lines[start:].
+func sequenceMatchesAt(lines, wanted []string, start int) bool {
+	if start < 0 || start+len(wanted) > len(lines) {
+		return false
+	}
+	for offset, line := range wanted {
+		if lines[start+offset] != line {
+			return false
+		}
+	}
+	return true
+}
+
+// applyEOFNewline forces or strips a single trailing line ending when a
+// unified diff's end-of-file marker asked for it.
+func applyEOFNewline(content string, mode eofNewlineMode) string {
+	switch mode {
+	case eofNewlinePresent:
+		if content != "" && !strings.HasSuffix(content, "\n") {
+			return content + structuredPatchLineEnding(content)
+		}
+	case eofNewlineAbsent:
+		content = strings.TrimSuffix(content, "\n")
+		content = strings.TrimSuffix(content, "\r")
+	}
+	return content
+}
+
+func structuredPatchReplacement(chunk structuredPatchChunk, source []string, start int) ([]string, error) {
+	if len(chunk.newSourceOffsets) != len(chunk.new) {
+		return nil, fmt.Errorf("context mapping has %d entries for %d output lines", len(chunk.newSourceOffsets), len(chunk.new))
+	}
+	replacement := append([]string(nil), chunk.new...)
+	for outputIndex, sourceOffset := range chunk.newSourceOffsets {
+		if sourceOffset < 0 {
+			continue
+		}
+		sourceIndex := start + sourceOffset
+		if sourceIndex < 0 || sourceIndex >= len(source) {
+			return nil, fmt.Errorf("context source index %d is outside the matched file", sourceIndex)
+		}
+		replacement[outputIndex] = source[sourceIndex]
+	}
+	return replacement, nil
+}
+
+func structuredPatchLineEnding(content string) string {
+	if strings.Contains(content, "\r\n") && !strings.Contains(strings.ReplaceAll(content, "\r\n", ""), "\n") {
+		return "\r\n"
+	}
+	return "\n"
+}
+
+type structuredReplacement struct {
+	start       int
+	length      int
+	replacement []string
+}
+
+func findStructuredPatchSequence(lines, wanted []string, start int, endOfFile bool) (int, bool) {
+	if len(wanted) == 0 {
+		return start, false
+	}
+	if len(wanted) > len(lines) {
+		return -1, false
+	}
+	searchStart := start
+	if endOfFile {
+		searchStart = len(lines) - len(wanted)
+		if searchStart < start {
+			searchStart = start
+		}
+	}
+	for _, equal := range []func(string, string) bool{
+		func(left, right string) bool { return left == right },
+		func(left, right string) bool {
+			return strings.TrimRight(left, " \t") == strings.TrimRight(right, " \t")
+		},
+		func(left, right string) bool { return strings.TrimSpace(left) == strings.TrimSpace(right) },
+	} {
+		match := -1
+		for index := searchStart; index+len(wanted) <= len(lines); index++ {
+			matched := true
+			for offset, line := range wanted {
+				if !equal(lines[index+offset], line) {
+					matched = false
+					break
+				}
+			}
+			if matched {
+				if match >= 0 {
+					return -1, true
+				}
+				match = index
+			}
+		}
+		if match >= 0 {
+			return match, false
+		}
+	}
+	return -1, false
+}
+
+func applyStructuredPatchChanges(root *os.Root, changes []structuredPatchChange, tracker *FileTracker) error {
+	// committed lists, in order, the paths whose change reached disk before a
+	// later change failed, so the caller (and the model) knows exactly which
+	// files now hold the patched content and which were never touched.
+	var committed []string
+	for _, change := range changes {
+		done, err := applyStructuredPatchChange(root, change)
+		if done {
+			committed = append(committed, structuredPatchChangePaths(change)...)
+		}
+		if err != nil {
+			forgetStructuredPatchFiles(tracker, changes)
+			if len(committed) > 0 {
+				return fmt.Errorf("%w; patch was partially applied — already committed: %s; the remaining files are unchanged; re-read the committed files before retrying", err, strings.Join(committed, ", "))
+			}
+			return err
+		}
+	}
+	return nil
+}
+
+// structuredPatchChangePaths names the workspace-relative paths a committed
+// change touched: the destination, plus the source of a move or copy.
+func structuredPatchChangePaths(change structuredPatchChange) []string {
+	if change.kind == structuredPatchDelete {
+		return []string{change.from.relative}
+	}
+	paths := []string{change.to.relative}
+	if change.from.absolute != change.to.absolute && change.from.relative != "" {
+		paths = append([]string{change.from.relative}, paths...)
+	}
+	return paths
+}
+
+func forgetStructuredPatchFiles(tracker *FileTracker, changes []structuredPatchChange) {
+	if tracker == nil {
+		return
+	}
+	for _, change := range changes {
+		tracker.Forget(change.from.absolute)
+		if change.to.absolute != change.from.absolute {
+			tracker.Forget(change.to.absolute)
+		}
+	}
+}
+
+// structuredPatchBeforeCommit, when set, runs before each change's pre-commit
+// recheck. Tests use it to alter the filesystem between planning and commit
+// deterministically; it is nil in production.
+var structuredPatchBeforeCommit func(change structuredPatchChange)
+
+func applyStructuredPatchChange(root *os.Root, change structuredPatchChange) (bool, error) {
+	if structuredPatchBeforeCommit != nil {
+		structuredPatchBeforeCommit(change)
+	}
+	// The planner validated the source against the bytes it read; re-read
+	// through the same root immediately before committing so a change made
+	// by another process in between is refused rather than overwritten or
+	// removed.
+	if change.kind != structuredPatchAdd {
+		current, err := root.ReadFile(change.from.relative)
+		if err != nil {
+			return false, fmt.Errorf("re-reading %s before commit: %w", change.from.relative, err)
+		}
+		if string(current) != change.before {
+			return false, fmt.Errorf("%s changed on disk between planning and commit; re-read it and retry", change.from.relative)
+		}
+	}
+	switch change.kind {
+	case structuredPatchDelete:
+		if err := root.Remove(change.from.relative); err != nil {
+			return false, fmt.Errorf("deleting %s: %w", change.from.relative, err)
+		}
+		return true, nil
+	case structuredPatchAdd, structuredPatchCopy:
+		return writeStructuredPatchFile(root, change.to, change.after, change.mode, true)
+	case structuredPatchUpdate:
+		moving := change.from.absolute != change.to.absolute
+		committed, err := writeStructuredPatchFile(root, change.to, change.after, change.mode, moving)
+		if err != nil {
+			return committed, err
+		}
+		if moving {
+			if err := root.Remove(change.from.relative); err != nil {
+				return true, fmt.Errorf("removing moved source %s: %w", change.from.relative, err)
+			}
+		}
+		return true, nil
+	}
+	return false, fmt.Errorf("unsupported structured patch operation")
+}
+
+func writeStructuredPatchFile(root *os.Root, target structuredPatchTarget, content string, mode os.FileMode, createOnly bool) (bool, error) {
+	parent := filepath.Dir(target.relative)
+	if err := root.MkdirAll(parent, 0o755); err != nil {
+		return false, fmt.Errorf("creating parent directory for %s: %w", target.relative, err)
+	}
+	temp, tempName, err := pathjail.CreateTemp(root, parent, "zero-patch", ".tmp")
+	if err != nil {
+		return false, fmt.Errorf("writing %s: %w", target.relative, err)
+	}
+	defer func() { _ = removeStructuredPatchTemp(root, tempName) }()
+	if _, err := temp.WriteString(content); err != nil {
+		_ = temp.Close()
+		return false, fmt.Errorf("writing %s: %w", target.relative, err)
+	}
+	if err := temp.Chmod(mode.Perm()); err != nil {
+		_ = temp.Close()
+		return false, fmt.Errorf("writing %s: %w", target.relative, err)
+	}
+	if err := temp.Close(); err != nil {
+		return false, fmt.Errorf("writing %s: %w", target.relative, err)
+	}
+	if createOnly {
+		return publishStructuredPatchNoReplace(root, tempName, target.relative, mode)
+	}
+	if err := root.Rename(tempName, target.relative); err != nil {
+		return false, fmt.Errorf("writing %s: %w", target.relative, err)
+	}
+	return true, nil
+}
+
+func publishStructuredPatchNoReplace(root *os.Root, source, target string, mode os.FileMode) (bool, error) {
+	return publishStructuredPatchNoReplaceWith(root, source, target, mode, root.Link)
+}
+
+func publishStructuredPatchNoReplaceWith(root *os.Root, source, target string, mode os.FileMode, link func(string, string) error) (bool, error) {
+	if linkErr := link(source, target); linkErr == nil {
+		cleanupErr := removeStructuredPatchTemp(root, source)
+		chmodErr := root.Chmod(target, mode.Perm())
+		if cleanupErr != nil || chmodErr != nil {
+			return true, fmt.Errorf("publishing %s: %w", target, errors.Join(cleanupErr, chmodErr))
+		}
+		return true, nil
+	} else if errors.Is(linkErr, os.ErrExist) {
+		return false, fmt.Errorf("creating %s: %w", target, linkErr)
+	} else {
+		committed, copyErr := copyStructuredPatchNoReplace(root, source, target, mode)
+		if copyErr != nil {
+			return committed, fmt.Errorf("creating %s without overwrite: hard link failed: %w; exclusive-copy fallback failed: %w", target, linkErr, copyErr)
+		}
+		return committed, nil
+	}
+}
+
+func copyStructuredPatchNoReplace(root *os.Root, source, target string, mode os.FileMode) (bool, error) {
+	return copyStructuredPatchNoReplaceWith(root, source, target, mode, io.Copy, removeStructuredPatchTemp)
+}
+
+func copyStructuredPatchNoReplaceWith(
+	root *os.Root,
+	source, target string,
+	mode os.FileMode,
+	copyFile func(io.Writer, io.Reader) (int64, error),
+	cleanup func(*os.Root, string) error,
+) (bool, error) {
+	sourceFile, err := root.Open(source)
+	if err != nil {
+		return false, err
+	}
+	sourceClosed := false
+	defer func() {
+		if !sourceClosed {
+			_ = sourceFile.Close()
+		}
+	}()
+	targetFile, err := root.OpenFile(target, os.O_WRONLY|os.O_CREATE|os.O_EXCL, 0o600)
+	if err != nil {
+		return false, err
+	}
+	committed := true
+	cleanupTarget := func(cause error) (bool, error) {
+		_ = targetFile.Close()
+		if cleanupErr := cleanup(root, target); cleanupErr == nil {
+			return false, cause
+		} else {
+			return committed, errors.Join(cause, fmt.Errorf("cleaning partial target: %w", cleanupErr))
+		}
+	}
+	if _, err := copyFile(targetFile, sourceFile); err != nil {
+		return cleanupTarget(err)
+	}
+	if err := sourceFile.Close(); err != nil {
+		sourceClosed = true
+		return cleanupTarget(err)
+	}
+	sourceClosed = true
+	if err := targetFile.Chmod(mode.Perm()); err != nil {
+		return cleanupTarget(err)
+	}
+	if err := targetFile.Close(); err != nil {
+		if cleanupErr := cleanup(root, target); cleanupErr == nil {
+			return false, err
+		} else {
+			return true, errors.Join(err, fmt.Errorf("cleaning target after close failure: %w", cleanupErr))
+		}
+	}
+	if err := cleanup(root, source); err != nil {
+		return true, fmt.Errorf("removing published source: %w", err)
+	}
+	return true, nil
+}
+
+func removeStructuredPatchTemp(root *os.Root, name string) error {
+	chmodErr := root.Chmod(name, 0o600)
+	if os.IsNotExist(chmodErr) {
+		return nil
+	}
+	removeErr := root.Remove(name)
+	if os.IsNotExist(removeErr) {
+		removeErr = nil
+	}
+	if removeErr == nil {
+		return nil
+	}
+	return errors.Join(chmodErr, removeErr)
+}
+
+func recordStructuredPatchFile(tracker *FileTracker, absolute string, created, seenWhole bool) {
+	if tracker == nil {
+		return
+	}
+	content, err := os.ReadFile(absolute)
+	if err != nil {
+		tracker.Forget(absolute)
+		return
+	}
+	info, _ := os.Stat(absolute)
+	tracker.Record(absolute, content, info)
+	if seenWhole {
+		lines := trackedLineTotal(string(content))
+		tracker.RecordSeenRange(absolute, 1, lines, lines)
+	}
+	if created {
+		tracker.RecordCreated(absolute)
+	}
+}
+
+func changedFilesFromStructuredPatch(relativeRoot string, changes []structuredPatchChange) []string {
+	seen := make(map[string]bool)
+	var paths []string
+	for _, change := range changes {
+		targets := []structuredPatchTarget{change.to}
+		if change.from.absolute != change.to.absolute {
+			targets = append([]structuredPatchTarget{change.from}, targets...)
+		}
+		for _, target := range targets {
+			path := target.relative
+			if relativeRoot != "" && relativeRoot != "." {
+				path = filepath.ToSlash(filepath.Join(relativeRoot, path))
+			}
+			if !seen[path] {
+				seen[path] = true
+				paths = append(paths, path)
+			}
+		}
+	}
+	return paths
+}
+
+func structuredPatchPreview(changes []structuredPatchChange) string {
+	var preview strings.Builder
+	for _, change := range changes {
+		path := change.to.relative
+		if change.kind == structuredPatchDelete {
+			path = change.from.relative
+		}
+		before, after := change.before, change.after
+		if change.kind == structuredPatchDelete {
+			after = ""
+		}
+		diff := boundedUnifiedDiff(path, before, after)
+		if diff == "" {
+			continue
+		}
+		if preview.Len()+len(diff)+1 > maxToolPreviewBytes {
+			break
+		}
+		if preview.Len() > 0 {
+			preview.WriteByte('\n')
+		}
+		preview.WriteString(diff)
+	}
+	return capPreviewDiff(preview.String())
+}

internal/tools/tool_search.go

@@ -130,6 +130,9 @@ func (tool toolSearchTool) visibleDeferredTools(enabled []string, disabled []str
 	var deferred []Tool
 	if tool.registry != nil {
 		for _, candidate := range tool.registry.All() {
+			if !ModelVisible(candidate) {
+				continue
+			}
 			if !IsDeferred(candidate) {
 				continue
 			}
@@ -158,6 +161,9 @@ func (tool toolSearchTool) visibleEagerToolNames(enabled []string, disabled []st
 		return names
 	}
 	for _, candidate := range tool.registry.All() {
+		if !ModelVisible(candidate) {
+			continue
+		}
 		if IsDeferred(candidate) || candidate.Name() == ToolSearchToolName {
 			continue
 		}

internal/tools/tracked_line_total_test.go

@@ -0,0 +1,59 @@
+package tools
+
+import (
+	"context"
+	"fmt"
+	"path/filepath"
+	"testing"
+)
+
+func TestTrackedLineTotalMatchesReadFileStats(t *testing.T) {
+	root := t.TempDir()
+	for name, content := range map[string]string{"trailing": "a\nb\nc\n", "unterminated": "a\nb\nc", "single": "x\n", "empty": "", "crlf": "a\r\nb\r\n"} {
+		path := filepath.Join(root, name+".txt")
+		writeTestFile(t, path, content)
+		stats, err := scanReadFileStats(path)
+		if err != nil {
+			t.Fatal(err)
+		}
+		if got := trackedLineTotal(content); got != stats.lines {
+			t.Fatalf("%s: trackedLineTotal = %d, read_file reports %d", name, got, stats.lines)
+		}
+	}
+}
+
+// A whole-file read, an edit, then a partial re-read must keep the file "seen
+// whole": the writer and reader now agree on the line total, so the partial
+// read accumulates instead of resetting and a later edit far from the re-read
+// window is not refused.
+func TestEditThenPartialReadKeepsWholeFileObservation(t *testing.T) {
+	root := t.TempDir()
+	path := filepath.Join(root, "notes.txt")
+	content := ""
+	for i := 1; i <= 40; i++ {
+		content += fmt.Sprintf("line %02d\n", i)
+	}
+	writeTestFile(t, path, content)
+	tracker := NewFileTracker()
+	registry := NewRegistry()
+	registry.Register(NewScopedReadFileTool(root, nil))
+	registry.Register(NewScopedEditFileTool(root, nil))
+	opts := RunOptions{PermissionGranted: true, FileTracker: tracker}
+
+	if r := registry.RunWithOptions(context.Background(), "read_file", map[string]any{"path": "notes.txt"}, opts); r.Status != StatusOK {
+		t.Fatalf("read: %s", r.Output)
+	}
+	if r := registry.RunWithOptions(context.Background(), "edit_file", map[string]any{"path": "notes.txt", "old_string": "line 01\nline 02\n", "new_string": "line 01\nline two\n"}, opts); r.Status != StatusOK {
+		t.Fatalf("first edit: %s", r.Output)
+	}
+	if r := registry.RunWithOptions(context.Background(), "read_file", map[string]any{"path": "notes.txt", "limit": 5}, opts); r.Status != StatusOK {
+		t.Fatalf("partial read: %s", r.Output)
+	}
+	absolute, _ := filepath.EvalSymlinks(path)
+	if !tracker.SeenWhole(absolute) {
+		t.Fatal("partial re-read of an unchanged file must not discard whole-file knowledge")
+	}
+	if r := registry.RunWithOptions(context.Background(), "edit_file", map[string]any{"path": "notes.txt", "old_string": "line 39\nline 40\n", "new_string": "line 39\nline forty\n"}, opts); r.Status != StatusOK {
+		t.Fatalf("edit far from the re-read window must succeed: %s", r.Output)
+	}
+}

internal/tools/unified_patch.go

@@ -0,0 +1,393 @@
+package tools
+
+import (
+	"fmt"
+	"strings"
+)
+
+// parseUnifiedPatch converts a unified diff into the same operations a
+// structured patch produces, so both formats are applied by Zero itself
+// through an opened workspace root (descriptor-relative, no-follow writes)
+// instead of handing pathnames to git apply after validation.
+//
+// Supported: file modifications, creations (--- /dev/null) and deletions
+// (+++ /dev/null, verified against the content the hunks expect to remove),
+// multiple hunks per file, "\ No newline at end of file"
+// markers, a/ and b/ prefixes, git C-quoted paths, CRLF patches, and git's
+// "rename from/to" and "copy from/to" headers (with or without hunks). Headers
+// git emits around a hunk (diff --git, index, mode lines) are skipped; binary
+// patches are rejected.
+func parseUnifiedPatch(patch string) ([]structuredPatchOperation, error) {
+	normalized := strings.TrimPrefix(strings.ReplaceAll(patch, "\r\n", "\n"), "\ufeff")
+	lines := strings.Split(normalized, "\n")
+	// The element after a final "\n" is the line terminator, not an empty
+	// context line; counting it would let a truncated hunk look complete.
+	if len(lines) > 0 && lines[len(lines)-1] == "" {
+		lines = lines[:len(lines)-1]
+	}
+
+	var operations []structuredPatchOperation
+	var current *structuredPatchOperation
+	var chunk *structuredPatchChunk
+	var added []string // collected "+" lines for a file creation
+	oldPath, newPath := "", ""
+	pendingFrom, pendingKind := "", structuredPatchUpdate
+	// git's header-only forms: "deleted file mode" / "new file mode" after a
+	// "diff --git" line with no ---/+++ pair describe an empty file.
+	diffPath, headerOnly := "", byte(0) // headerOnly is 'd' (deleted) or 'n' (new)
+	oldRemaining, newRemaining := 0, 0
+	inHunk := false
+	lastSide := byte(0) // '+' or '-' for the most recent content line
+
+	finish := func() error {
+		if current == nil {
+			return nil
+		}
+		switch current.kind {
+		case structuredPatchAdd:
+			if len(added) > 0 {
+				current.contents = strings.Join(added, "\n")
+				if current.eofNewline != eofNewlineAbsent {
+					current.contents += "\n"
+				}
+			}
+		case structuredPatchUpdate, structuredPatchCopy:
+			if !allStructuredPatchChunksHaveContent(current.chunks) {
+				return fmt.Errorf("unified diff for %s has an empty hunk", current.path)
+			}
+			if len(current.chunks) == 0 && current.movePath == "" {
+				return fmt.Errorf("unified diff for %s has no hunk lines", current.path)
+			}
+		case structuredPatchDelete:
+			if len(current.chunks) == 0 || !allStructuredPatchChunksHaveContent(current.chunks) {
+				return fmt.Errorf("unified deletion of %s must include the hunk with the content being removed", current.path)
+			}
+		}
+		operations = append(operations, *current)
+		current, chunk, added = nil, nil, nil
+		return nil
+	}
+	flushHeaderOnly := func(line int) error {
+		if headerOnly == 0 {
+			return nil
+		}
+		if diffPath == "" {
+			return fmt.Errorf("invalid unified diff at line %d: file mode header without a diff --git path", line)
+		}
+		if err := finish(); err != nil {
+			return err
+		}
+		switch headerOnly {
+		case 'd':
+			operations = append(operations, structuredPatchOperation{kind: structuredPatchDelete, path: diffPath, line: line, verifyDelete: true})
+		case 'n':
+			operations = append(operations, structuredPatchOperation{kind: structuredPatchAdd, path: diffPath, line: line})
+		}
+		headerOnly, diffPath = 0, ""
+		return nil
+	}
+	startFile := func(line int) error {
+		// A ---/+++ pair means the file has hunks; it is not header-only.
+		headerOnly, diffPath = 0, ""
+		if oldPath == "" || newPath == "" {
+			return fmt.Errorf("invalid unified diff at line %d: hunk before a ---/+++ header pair", line)
+		}
+		// A ---/+++ pair after a rename/copy header names the same files; keep
+		// accumulating that operation's hunks instead of starting a new one.
+		if current != nil && current.movePath != "" && current.path == oldPath && (current.movePath == newPath || oldPath == newPath) {
+			return nil
+		}
+		if err := finish(); err != nil {
+			return err
+		}
+		op := structuredPatchOperation{line: line}
+		switch {
+		case oldPath == "/dev/null" && newPath == "/dev/null":
+			return fmt.Errorf("invalid unified diff at line %d: both sides are /dev/null", line)
+		case oldPath == "/dev/null":
+			op.kind, op.path = structuredPatchAdd, newPath
+		case newPath == "/dev/null":
+			// A unified deletion states the content it expects to remove; keep
+			// its hunks so the planner verifies them before deleting.
+			op.kind, op.path, op.verifyDelete = structuredPatchDelete, oldPath, true
+		default:
+			op.kind, op.path = structuredPatchUpdate, oldPath
+			if newPath != oldPath {
+				op.movePath = newPath
+			}
+		}
+		current = &op
+		return nil
+	}
+
+	for index, raw := range lines {
+		lineNumber := index + 1
+		if inHunk && (oldRemaining > 0 || newRemaining > 0) {
+			// A "--- " line followed by "+++ " and then a "@@" hunk header is
+			// the next file's header pair, not a removed "-- x" line followed by
+			// an added "++ y" line: an over-declared count would otherwise
+			// swallow both and the hunk would later fail against the wrong
+			// file. The "@@" requirement keeps a genuine adjacent pair intact.
+			if strings.HasPrefix(raw, "--- ") && index+2 < len(lines) && strings.HasPrefix(lines[index+1], "+++ ") && strings.HasPrefix(lines[index+2], "@@") {
+				return nil, fmt.Errorf("invalid unified diff at line %d: hunk ended before its declared line counts", lineNumber)
+			}
+			switch {
+			case strings.HasPrefix(raw, "\\"):
+				// "\ No newline at end of file" qualifies the previous line's side.
+				if current != nil && lastSide == '+' {
+					current.eofNewline = eofNewlineAbsent
+				} else if current != nil && lastSide == '-' {
+					current.oldNoNewline = true
+					if current.eofNewline == eofNewlineKeep {
+						current.eofNewline = eofNewlinePresent
+					}
+				}
+				continue
+			case strings.HasPrefix(raw, "-"):
+				oldRemaining--
+				lastSide = '-'
+				if chunk != nil {
+					chunk.old = append(chunk.old, raw[1:])
+				}
+			case strings.HasPrefix(raw, "+"):
+				newRemaining--
+				lastSide = '+'
+				if current != nil && current.kind == structuredPatchAdd {
+					added = append(added, raw[1:])
+				} else if chunk != nil {
+					chunk.new = append(chunk.new, raw[1:])
+					chunk.newSourceOffsets = append(chunk.newSourceOffsets, -1)
+				}
+			default:
+				content := raw
+				if strings.HasPrefix(raw, " ") {
+					content = raw[1:]
+				} else if raw != "" {
+					return nil, fmt.Errorf("invalid unified diff at line %d: hunk lines must start with ' ', '+', '-' or '\\'", lineNumber)
+				}
+				oldRemaining--
+				newRemaining--
+				lastSide = ' '
+				if chunk != nil {
+					offset := len(chunk.old)
+					chunk.old = append(chunk.old, content)
+					chunk.new = append(chunk.new, content)
+					chunk.newSourceOffsets = append(chunk.newSourceOffsets, offset)
+				}
+			}
+			continue
+		}
+		inHunk = false
+		trimmed := strings.TrimSpace(raw)
+		if oldRemaining > 0 || newRemaining > 0 {
+			// The hunk ended before its declared counts were consumed. Report
+			// it here rather than absorbing the next file's ---/+++ headers as
+			// "-"/"+" content and failing later against the wrong file.
+			return nil, fmt.Errorf("invalid unified diff at line %d: hunk ended before its declared line counts", lineNumber)
+		}
+		switch {
+		case trimmed == "":
+			continue
+		case strings.HasPrefix(raw, "\\"):
+			// "\ No newline at end of file" directly after a hunk's last line.
+			if current != nil && lastSide == '+' {
+				current.eofNewline = eofNewlineAbsent
+			} else if current != nil && lastSide == '-' {
+				current.oldNoNewline = true
+				if current.eofNewline == eofNewlineKeep {
+					current.eofNewline = eofNewlinePresent
+				}
+			}
+			continue
+		case strings.HasPrefix(raw, "diff --git "):
+			if err := flushHeaderOnly(lineNumber); err != nil {
+				return nil, err
+			}
+			diffPath = diffGitNewPath(raw)
+			continue
+		case strings.HasPrefix(raw, "deleted file mode "):
+			headerOnly = 'd'
+			continue
+		case strings.HasPrefix(raw, "new file mode "):
+			headerOnly = 'n'
+			continue
+		case strings.HasPrefix(raw, "index "), strings.HasPrefix(raw, "old mode "), strings.HasPrefix(raw, "new mode "):
+			continue
+		case strings.HasPrefix(raw, "similarity index "), strings.HasPrefix(raw, "dissimilarity index "):
+			continue
+		case strings.HasPrefix(raw, "rename from "), strings.HasPrefix(raw, "copy from "):
+			pendingFrom = strings.TrimSpace(unquoteGitPath(strings.TrimPrefix(strings.TrimPrefix(raw, "rename from "), "copy from ")))
+			pendingKind = structuredPatchUpdate
+			if strings.HasPrefix(raw, "copy from ") {
+				pendingKind = structuredPatchCopy
+			}
+			if pendingFrom == "" {
+				return nil, fmt.Errorf("invalid unified diff at line %d: missing source path", lineNumber)
+			}
+		case strings.HasPrefix(raw, "rename to "), strings.HasPrefix(raw, "copy to "):
+			to := strings.TrimSpace(unquoteGitPath(strings.TrimPrefix(strings.TrimPrefix(raw, "rename to "), "copy to ")))
+			if pendingFrom == "" || to == "" {
+				return nil, fmt.Errorf("invalid unified diff at line %d: rename/copy destination without a source", lineNumber)
+			}
+			if err := finish(); err != nil {
+				return nil, err
+			}
+			current = &structuredPatchOperation{kind: pendingKind, path: pendingFrom, movePath: to, line: lineNumber}
+			oldPath, newPath, pendingFrom = pendingFrom, to, ""
+		case strings.HasPrefix(raw, "Binary files "), strings.HasPrefix(raw, "GIT binary patch"):
+			return nil, fmt.Errorf("invalid unified diff at line %d: binary patches are not supported", lineNumber)
+		case strings.HasPrefix(raw, "--- "):
+			oldPath = stripPatchPrefix(patchFileHeaderPath(raw))
+			newPath = ""
+			if oldPath == "" {
+				return nil, fmt.Errorf("invalid unified diff at line %d: missing path in --- header", lineNumber)
+			}
+		case strings.HasPrefix(raw, "+++ "):
+			newPath = stripPatchPrefix(patchFileHeaderPath(raw))
+			if newPath == "" {
+				return nil, fmt.Errorf("invalid unified diff at line %d: missing path in +++ header", lineNumber)
+			}
+			if err := startFile(lineNumber); err != nil {
+				return nil, err
+			}
+		case strings.HasPrefix(raw, "@@"):
+			if current == nil {
+				return nil, fmt.Errorf("invalid unified diff at line %d: hunk before a ---/+++ header pair", lineNumber)
+			}
+			oldStart, oldCount, newCount, ok := parseHunkRange(raw)
+			if !ok {
+				return nil, fmt.Errorf("invalid unified diff at line %d: malformed hunk header", lineNumber)
+			}
+			// "\ No newline at end of file" describes the end of the file, so it
+			// may only follow a file's final hunk; a marker before another hunk
+			// would otherwise leak into that later hunk's result.
+			if current.eofNewline != eofNewlineKeep {
+				return nil, fmt.Errorf("invalid unified diff at line %d: \"\\ No newline at end of file\" must follow the last hunk of a file", lineNumber)
+			}
+			oldRemaining, newRemaining = oldCount, newCount
+			inHunk = oldRemaining > 0 || newRemaining > 0
+			lastSide = 0
+			if current.kind != structuredPatchAdd {
+				next := structuredPatchChunk{hasHint: true, hint: oldStart - 1}
+				if oldCount == 0 {
+					// A pure insertion's range names the line after which the
+					// new lines go, so the insertion index is oldStart itself.
+					next.hint = oldStart
+				}
+				if next.hint < 0 {
+					next.hint = 0
+				}
+				current.chunks = append(current.chunks, next)
+				chunk = &current.chunks[len(current.chunks)-1]
+			}
+		default:
+			return nil, fmt.Errorf("invalid unified diff at line %d: unexpected %q", lineNumber, trimmed)
+		}
+	}
+	// Strict at end of input on purpose: a hunk cut short (typically a model
+	// response that stopped mid-patch) would otherwise apply as a partial
+	// change — removals without their replacements — which is worse than a
+	// clear error and a retry. Miscounted ranges with complete content are
+	// still tolerated at every other boundary.
+	if inHunk && (oldRemaining > 0 || newRemaining > 0) {
+		return nil, fmt.Errorf("invalid unified diff at line %d: hunk ended before its declared line counts", len(lines))
+	}
+	if err := flushHeaderOnly(len(lines)); err != nil {
+		return nil, err
+	}
+	if err := finish(); err != nil {
+		return nil, err
+	}
+	if len(operations) == 0 {
+		return nil, fmt.Errorf("unified diff contains no file changes")
+	}
+	return operations, nil
+}
+
+// diffGitNewPath returns the post-image path named by a "diff --git a/X b/Y"
+// line, handling git's C-quoted form; "" when it cannot be determined.
+func diffGitNewPath(line string) string {
+	rest := strings.TrimSpace(strings.TrimPrefix(line, "diff --git "))
+	if strings.HasPrefix(rest, "\"") {
+		// Two quoted tokens: skip the first, unquote the second.
+		end := strings.Index(rest[1:], "\"")
+		for end > 0 && rest[end] == '\\' {
+			next := strings.Index(rest[end+2:], "\"")
+			if next < 0 {
+				return ""
+			}
+			end += next + 2
+		}
+		if end < 0 || end+2 > len(rest) {
+			return ""
+		}
+		rest = strings.TrimSpace(rest[end+2:])
+		return stripPatchPrefix(unquoteGitPath(rest))
+	}
+	fields := strings.Fields(rest)
+	if len(fields) < 2 {
+		return ""
+	}
+	last := fields[len(fields)-1]
+	if strings.HasPrefix(last, "\"") {
+		return stripPatchPrefix(unquoteGitPath(last))
+	}
+	return stripPatchPrefix(last)
+}
+
+// parseHunkRange reads "@@ -a[,b] +c[,d] @@" and returns a, b and d; a missing
+// count means 1 per unified-diff convention.
+func parseHunkRange(line string) (oldStart, oldCount, newCount int, ok bool) {
+	_, rest, found := strings.Cut(line, "@@")
+	if !found {
+		return 0, 0, 0, false
+	}
+	rangeSection := rest
+	if before, _, found := strings.Cut(rest, "@@"); found {
+		rangeSection = before
+	}
+	fields := strings.Fields(rangeSection)
+	if len(fields) != 2 || !strings.HasPrefix(fields[0], "-") || !strings.HasPrefix(fields[1], "+") {
+		return 0, 0, 0, false
+	}
+	parse := func(spec string) (int, int, bool) {
+		startText, countText, hasCount := strings.Cut(spec, ",")
+		start, err := parseNonNegativeInt(startText)
+		if err != nil {
+			return 0, 0, false
+		}
+		count := 1
+		if hasCount {
+			if count, err = parseNonNegativeInt(countText); err != nil {
+				return 0, 0, false
+			}
+		}
+		return start, count, true
+	}
+	oldStart, oldCount, ok = parse(fields[0][1:])
+	if !ok {
+		return 0, 0, 0, false
+	}
+	_, newCount, ok = parse(fields[1][1:])
+	if !ok {
+		return 0, 0, 0, false
+	}
+	return oldStart, oldCount, newCount, true
+}
+
+func parseNonNegativeInt(text string) (int, error) {
+	if text == "" {
+		return 0, fmt.Errorf("empty number")
+	}
+	value := 0
+	for _, r := range text {
+		if r < '0' || r > '9' {
+			return 0, fmt.Errorf("not a number: %q", text)
+		}
+		value = value*10 + int(r-'0')
+		if value > 1<<30 {
+			return 0, fmt.Errorf("number too large: %q", text)
+		}
+	}
+	return value, nil
+}

internal/tools/write_file.go

@@ -120,7 +120,7 @@ func (tool writeFileTool) RunWithOptions(ctx context.Context, args map[string]an
 	newInfo, _ := os.Stat(absolutePath)
 	options.FileTracker.Record(absolutePath, []byte(content), newInfo)
 	if content == modelKnownContent {
-		options.FileTracker.RecordSeenRange(absolutePath, 1, lineCount(content), lineCount(content))
+		options.FileTracker.RecordSeenRange(absolutePath, 1, trackedLineTotal(content), trackedLineTotal(content))
 	}
 	if !existed {
 		options.FileTracker.RecordCreated(absolutePath)

internal/tools/write_tools_test.go

@@ -2,12 +2,23 @@ package tools
 
 import (
 	"context"
+	"errors"
+	"io"
 	"os"
 	"path/filepath"
 	"strings"
 	"testing"
 )
 
+func mustReadTestFile(t *testing.T, path string) string {
+	t.Helper()
+	content, err := os.ReadFile(path)
+	if err != nil {
+		t.Fatal(err)
+	}
+	return string(content)
+}
+
 func TestCoreToolsExposeWriteAndPlanTools(t *testing.T) {
 	toolset := CoreToolsScoped(t.TempDir(), nil)
 	byName := make(map[string]Tool, len(toolset))
@@ -513,6 +524,547 @@ func TestApplyPatchToolAppliesUnifiedDiff(t *testing.T) {
 	}
 }
 
+func TestApplyPatchToolAppliesStructuredPatch(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "hello.txt"), "hello\nold\n")
+
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: hello.txt",
+		"@@",
+		" hello",
+		"-old",
+		"+new",
+		"*** End Patch",
+		"",
+	}, "\n")
+
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("structured patch should apply, got %s: %s", result.Status, result.Output)
+	}
+	content, err := os.ReadFile(filepath.Join(root, "hello.txt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := strings.ReplaceAll(string(content), "\r\n", "\n"); got != "hello\nnew\n" {
+		t.Fatalf("structured patch content = %q", got)
+	}
+}
+
+func TestApplyPatchToolAppliesStructuredAddAndMove(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "old.txt"), "old\n")
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Add File: nested/new.txt",
+		"+created",
+		"*** Update File: old.txt",
+		"*** Move to: moved.txt",
+		"@@",
+		"-old",
+		"+moved",
+		"*** End Patch",
+		"",
+	}, "\n")
+
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("structured patch should apply, got %s: %s", result.Status, result.Output)
+	}
+	if got, err := os.ReadFile(filepath.Join(root, "nested", "new.txt")); err != nil || string(got) != "created\n" {
+		t.Fatalf("added file = %q, err = %v", got, err)
+	}
+	if got, err := os.ReadFile(filepath.Join(root, "moved.txt")); err != nil || string(got) != "moved\n" {
+		t.Fatalf("moved file = %q, err = %v", got, err)
+	}
+	if _, err := os.Stat(filepath.Join(root, "old.txt")); !os.IsNotExist(err) {
+		t.Fatalf("old source should be removed, stat err = %v", err)
+	}
+	if got := result.ChangedFiles; strings.Join(got, ",") != "nested/new.txt,old.txt,moved.txt" {
+		t.Fatalf("ChangedFiles = %v", got)
+	}
+}
+
+func TestApplyPatchToolStructuredPatchMatchesWhitespaceTolerantly(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "hello.txt"), "  hello   \n")
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: hello.txt",
+		"@@",
+		"-hello",
+		"+goodbye",
+		"*** End Patch",
+		"",
+	}, "\n")
+
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("structured patch should tolerate surrounding whitespace, got %s: %s", result.Status, result.Output)
+	}
+	content, err := os.ReadFile(filepath.Join(root, "hello.txt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := string(content); got != "goodbye\n" {
+		t.Fatalf("structured patch content = %q", got)
+	}
+}
+
+func TestApplyPatchToolStructuredPatchPreservesWhitespaceTolerantContext(t *testing.T) {
+	root := t.TempDir()
+	path := filepath.Join(root, "example.go")
+	original := "func f() {\n\tif cond {\n\t\tdoWork()\n\t\tlogIt()\n\t}\n}\n"
+	writeTestFile(t, path, original)
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: example.go",
+		"@@",
+		"     if cond {",
+		"         doWork()",
+		"-\t\tlogIt()",
+		"+\t\tlogIt(ctx)",
+		"     }",
+		"*** End Patch",
+		"",
+	}, "\n")
+
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("structured patch failed: %s", result.Output)
+	}
+	want := "func f() {\n\tif cond {\n\t\tdoWork()\n\t\tlogIt(ctx)\n\t}\n}\n"
+	if got := mustReadTestFile(t, path); got != want {
+		t.Fatalf("structured patch rewrote unchanged context:\n got %q\nwant %q", got, want)
+	}
+}
+
+func TestApplyPatchToolStructuredPatchPreservesMixedContextLineEndings(t *testing.T) {
+	root := t.TempDir()
+	path := filepath.Join(root, "example.txt")
+	original := "alpha\r\n\tcontext\r\n\told\nomega\r\n"
+	writeTestFile(t, path, original)
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: example.txt",
+		"@@",
+		" alpha",
+		"     context",
+		"-\told",
+		"+\tnew",
+		" omega",
+		"*** End Patch",
+		"",
+	}, "\n")
+
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("structured patch failed: %s", result.Output)
+	}
+	want := "alpha\r\n\tcontext\r\n\tnew\nomega\r\n"
+	if got := mustReadTestFile(t, path); got != want {
+		t.Fatalf("structured patch rewrote context line endings:\n got %q\nwant %q", got, want)
+	}
+}
+
+func TestApplyPatchToolStructuredPatchInsertsAtContext(t *testing.T) {
+	root := t.TempDir()
+	writeTestFile(t, filepath.Join(root, "example.txt"), "anchor\nmiddle\nremove\n")
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: example.txt",
+		"@@ anchor",
+		"+inserted",
+		"@@ middle",
+		"-remove",
+		"*** End Patch",
+		"",
+	}, "\n")
+
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("structured insertion failed: %s", result.Output)
+	}
+	content, err := os.ReadFile(filepath.Join(root, "example.txt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got, want := string(content), "anchor\ninserted\nmiddle\n"; got != want {
+		t.Fatalf("structured insertion content = %q, want %q", got, want)
+	}
+}
+
+func TestApplyPatchToolStructuredPatchRejectsAmbiguousMatch(t *testing.T) {
+	root := t.TempDir()
+	path := filepath.Join(root, "example.go")
+	original := "func a() {\n\treturn nil\n}\n\nfunc b() {\n\treturn nil\n}\n"
+	writeTestFile(t, path, original)
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: example.go",
+		"@@",
+		"-\treturn nil",
+		"+\treturn errNotFound",
+		"*** End Patch",
+		"",
+	}, "\n")
+
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusError || !strings.Contains(strings.ToLower(result.Output), "ambiguous") {
+		t.Fatalf("ambiguous structured patch should be refused, got %s: %s", result.Status, result.Output)
+	}
+	if got := mustReadTestFile(t, path); got != original {
+		t.Fatalf("ambiguous structured patch changed the file: %q", got)
+	}
+}
+
+func TestApplyPatchToolStructuredPatchPreservesCRLF(t *testing.T) {
+	root := t.TempDir()
+	path := filepath.Join(root, "example.txt")
+	writeTestFile(t, path, "alpha\r\nbravo\r\ncharlie\r\n")
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: example.txt",
+		"@@",
+		"-bravo",
+		"+BRAVO",
+		"*** End Patch",
+		"",
+	}, "\n")
+
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("structured patch failed: %s", result.Output)
+	}
+	if got, want := mustReadTestFile(t, path), "alpha\r\nBRAVO\r\ncharlie\r\n"; got != want {
+		t.Fatalf("structured patch content = %q, want %q", got, want)
+	}
+}
+
+func TestApplyPatchToolStructuredPatchPreservesMissingFinalNewline(t *testing.T) {
+	root := t.TempDir()
+	path := filepath.Join(root, "example.txt")
+	writeTestFile(t, path, "alpha\nbravo")
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: example.txt",
+		"@@",
+		"-alpha",
+		"+ALPHA",
+		"*** End Patch",
+		"",
+	}, "\n")
+
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("structured patch failed: %s", result.Output)
+	}
+	if got, want := mustReadTestFile(t, path), "ALPHA\nbravo"; got != want {
+		t.Fatalf("structured patch content = %q, want %q", got, want)
+	}
+}
+
+func TestApplyPatchToolStructuredPatchKeepsInsertedEmptyFileWithoutFinalNewline(t *testing.T) {
+	root := t.TempDir()
+	path := filepath.Join(root, "empty.txt")
+	writeTestFile(t, path, "")
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: empty.txt",
+		"@@",
+		"+content",
+		"*** End Patch",
+		"",
+	}, "\n")
+
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusOK {
+		t.Fatalf("structured patch failed: %s", result.Output)
+	}
+	if got, want := mustReadTestFile(t, path), "content"; got != want {
+		t.Fatalf("structured patch content = %q, want %q", got, want)
+	}
+}
+
+func TestApplyPatchToolStructuredPatchRejectsOutOfOrderEndHunk(t *testing.T) {
+	root := t.TempDir()
+	path := filepath.Join(root, "example.txt")
+	original := "alpha\nbravo\ncharlie\ndelta\necho\n"
+	writeTestFile(t, path, original)
+	patch := strings.Join([]string{
+		"*** Begin Patch",
+		"*** Update File: example.txt",
+		"@@",
+		"-delta",
+		"+DELTA",
+		"@@",
+		"-delta",
+		"-echo",
+		"+tail",
+		"*** End of File",
+		"*** End Patch",
+		"",
+	}, "\n")
+
+	result := NewScopedApplyPatchTool(root, nil).Run(context.Background(), map[string]any{"patch": patch})
+	if result.Status != StatusError {
+		t.Fatalf("out-of-order structured patch should be refused, got %s: %s", result.Status, result.Output)
+	}
+	if got := mustReadTestFile(t, path); got != original {
+		t.Fatalf("out-of-order structured patch changed the file: %q", got)
+	}
+}
+
+func TestStructuredPatchAddDoesNotOverwriteRacedDestination(t *testing.T) {
+	root := t.TempDir()
+	targetPath := filepath.Join(root, "created.txt")
+	writeTestFile(t, targetPath, "other writer\n")
+	workspace, err := os.OpenRoot(root)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer workspace.Close()
+	change := structuredPatchChange{
+		kind:  structuredPatchAdd,
+		to:    structuredPatchTarget{absolute: targetPath, relative: "created.txt"},
+		after: "patch content\n", mode: 0o644,
+	}
+
+	err = applyStructuredPatchChanges(workspace, []structuredPatchChange{change}, nil)
+	if err == nil || !errors.Is(err, os.ErrExist) {
+		t.Fatalf("raced add destination = %v, want os.ErrExist", err)
+	}
+	if strings.Contains(err.Error(), "exclusive-copy fallback") {
+		t.Fatalf("existing destination should be reported directly: %v", err)
+	}
+	if got := mustReadTestFile(t, targetPath); got != "other writer\n" {
+		t.Fatalf("raced add overwrote another writer's file: %q", got)
+	}
+}
+
+func TestStructuredPatchFailedDeleteDoesNotRecreateMissingFile(t *testing.T) {
+	root := t.TempDir()
+	workspace, err := os.OpenRoot(root)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer workspace.Close()
+	missingPath := filepath.Join(root, "missing.txt")
+	change := structuredPatchChange{
+		kind:   structuredPatchDelete,
+		from:   structuredPatchTarget{absolute: missingPath, relative: "missing.txt"},
+		before: "removed by another writer\n", mode: 0o644,
+	}
+
+	err = applyStructuredPatchChanges(workspace, []structuredPatchChange{change}, nil)
+	if err == nil {
+		t.Fatal("delete of an already removed file should fail")
+	}
+	if _, statErr := os.Stat(missingPath); !os.IsNotExist(statErr) {
+		t.Fatalf("failed delete recreated the missing file: %v", statErr)
+	}
+}
+
+// A move whose source vanishes after planning is refused by the pre-commit
+// recheck before the destination is published, so nothing is left half-done.
+func TestStructuredPatchMoveWithMissingSourceIsRefusedBeforePublishing(t *testing.T) {
+	root := t.TempDir()
+	workspace, err := os.OpenRoot(root)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer workspace.Close()
+	sourcePath := filepath.Join(root, "source.txt")
+	destinationPath := filepath.Join(root, "destination.txt")
+	writeTestFile(t, sourcePath, "removed source\n")
+	change := structuredPatchChange{
+		kind:   structuredPatchUpdate,
+		from:   structuredPatchTarget{absolute: sourcePath, relative: "source.txt"},
+		to:     structuredPatchTarget{absolute: destinationPath, relative: "destination.txt"},
+		before: "removed source\n", after: "moved content\n", mode: 0o644,
+	}
+	// The source exists at planning time and disappears just before commit.
+	removed := false
+	structuredPatchBeforeCommit = func(structuredPatchChange) {
+		if err := os.Remove(sourcePath); err != nil {
+			t.Fatal(err)
+		}
+		removed = true
+	}
+	defer func() { structuredPatchBeforeCommit = nil }()
+
+	err = applyStructuredPatchChanges(workspace, []structuredPatchChange{change}, nil)
+	if !removed {
+		t.Fatal("pre-commit hook did not run")
+	}
+	if err == nil || !strings.Contains(err.Error(), "before commit") || strings.Contains(err.Error(), "partially applied") {
+		t.Fatalf("move with a missing source = %v, want a pre-commit refusal with nothing applied", err)
+	}
+	if _, statErr := os.Stat(sourcePath); !os.IsNotExist(statErr) {
+		t.Fatalf("failed move recreated a missing source: %v", statErr)
+	}
+	if _, statErr := os.Stat(destinationPath); !os.IsNotExist(statErr) {
+		t.Fatalf("refused move must not publish the destination: %v", statErr)
+	}
+}
+
+func TestStructuredPatchCreateOnlyFallsBackWhenHardLinksUnsupported(t *testing.T) {
+	root := t.TempDir()
+	workspace, err := os.OpenRoot(root)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer workspace.Close()
+	sourcePath := filepath.Join(root, "source.tmp")
+	writeTestFile(t, sourcePath, "complete content\n")
+	if err := workspace.Chmod("source.tmp", 0o444); err != nil {
+		t.Fatal(err)
+	}
+	committed, err := publishStructuredPatchNoReplaceWith(
+		workspace,
+		"source.tmp",
+		"target.txt",
+		0o444,
+		func(string, string) error { return errors.New("hard links unsupported") },
+	)
+	if err != nil || !committed {
+		t.Fatalf("fallback publish = committed %v, error %v", committed, err)
+	}
+	if got := mustReadTestFile(t, filepath.Join(root, "target.txt")); got != "complete content\n" {
+		t.Fatalf("fallback target content = %q", got)
+	}
+	if _, statErr := os.Stat(sourcePath); !os.IsNotExist(statErr) {
+		t.Fatalf("read-only source was not cleaned up: %v", statErr)
+	}
+}
+
+func TestStructuredPatchCopyFailureReportsSurvivingPartialTarget(t *testing.T) {
+	root := t.TempDir()
+	workspace, err := os.OpenRoot(root)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer workspace.Close()
+	sourcePath := filepath.Join(root, "source.tmp")
+	writeTestFile(t, sourcePath, "complete content\n")
+	copyErr := errors.New("injected copy failure")
+	cleanupErr := errors.New("injected target cleanup failure")
+	committed, err := copyStructuredPatchNoReplaceWith(
+		workspace,
+		"source.tmp",
+		"target.txt",
+		0o644,
+		func(destination io.Writer, _ io.Reader) (int64, error) {
+			written, writeErr := io.WriteString(destination, "partial")
+			if writeErr != nil {
+				return int64(written), writeErr
+			}
+			return int64(written), copyErr
+		},
+		func(root *os.Root, name string) error {
+			if name == "target.txt" {
+				return cleanupErr
+			}
+			return removeStructuredPatchTemp(root, name)
+		},
+	)
+	if !committed || !errors.Is(err, copyErr) || !errors.Is(err, cleanupErr) {
+		t.Fatalf("copy failure = committed %v, error %v", committed, err)
+	}
+	targetPath := filepath.Join(root, "target.txt")
+	if got := mustReadTestFile(t, targetPath); got != "partial" {
+		t.Fatalf("partial target content = %q", got)
+	}
+}
+
+func TestStructuredPatchPartialFailureLeavesCompletedChangeAndClearsTrackedState(t *testing.T) {
+	root := t.TempDir()
+	trackedPath := filepath.Join(root, "tracked.txt")
+	writeTestFile(t, trackedPath, "original\n")
+	workspace, err := os.OpenRoot(root)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer workspace.Close()
+
+	trackedPath, err = filepath.EvalSymlinks(trackedPath)
+	if err != nil {
+		t.Fatal(err)
+	}
+	info, err := os.Stat(trackedPath)
+	if err != nil {
+		t.Fatal(err)
+	}
+	tracker := NewFileTracker()
+	tracker.Record(trackedPath, []byte("original\n"), info)
+	tracker.RecordSeenRange(trackedPath, 1, 1, 1)
+	trackedTarget := structuredPatchTarget{absolute: trackedPath, relative: "tracked.txt"}
+	blockedPath := filepath.Join(root, "blocked")
+	if err := os.Mkdir(blockedPath, 0o755); err != nil {
+		t.Fatal(err)
+	}
+	writeTestFile(t, filepath.Join(blockedPath, "sentinel"), "keep\n")
+	changes := []structuredPatchChange{
+		{
+			kind: structuredPatchUpdate, from: trackedTarget, to: trackedTarget,
+			before: "original\n", after: "updated\n", mode: 0o644,
+		},
+		{
+			kind:  structuredPatchAdd,
+			to:    structuredPatchTarget{absolute: blockedPath, relative: "blocked"},
+			after: "cannot replace a non-empty directory\n", mode: 0o644,
+		},
+	}
+
+	err = applyStructuredPatchChanges(workspace, changes, tracker)
+	if err == nil || !strings.Contains(err.Error(), "partially applied") {
+		t.Fatalf("second change = %v, want partial-application error", err)
+	}
+	if got := mustReadTestFile(t, trackedPath); got != "updated\n" {
+		t.Fatalf("completed change was unexpectedly altered: %q", got)
+	}
+	if _, tracked := tracker.Version(trackedPath); tracked || tracker.SeenWhole(trackedPath) {
+		t.Fatal("partial failure retained stale file-tracker state")
+	}
+}
+
+func TestApplyPatchToolRejectsMalformedOrEscapingStructuredPatchBeforeWriting(t *testing.T) {
+	root := t.TempDir()
+	tool := NewScopedApplyPatchTool(root, nil)
+	for name, patch := range map[string]string{
+		"empty update": strings.Join([]string{
+			"*** Begin Patch",
+			"*** Update File: target.txt",
+			"*** End Patch",
+		}, "\n"),
+		"escape": strings.Join([]string{
+			"*** Begin Patch",
+			"*** Add File: ../outside.txt",
+			"+nope",
+			"*** End Patch",
+		}, "\n"),
+	} {
+		t.Run(name, func(t *testing.T) {
+			result := tool.Run(context.Background(), map[string]any{"patch": patch})
+			if result.Status != StatusError {
+				t.Fatalf("expected error, got %s: %s", result.Status, result.Output)
+			}
+			if strings.Contains(result.Output, "No valid patches") {
+				t.Fatalf("structured patch should fail before git apply, got %q", result.Output)
+			}
+			if name == "empty update" {
+				if _, err := os.Stat(filepath.Join(root, "target.txt")); !os.IsNotExist(err) {
+					t.Fatalf("empty update must not write target file, stat err = %v", err)
+				}
+			}
+		})
+	}
+	if _, err := os.Stat(filepath.Join(filepath.Dir(root), "outside.txt")); !os.IsNotExist(err) {
+		t.Fatalf("escaping patch must not write outside workspace, stat err = %v", err)
+	}
+}
+
 // A hunk-body line that removes content beginning with "-- " appears in the diff
 // as "--- ..."; it must NOT be mistaken for a file header (which previously made
 // apply_patch reject a valid patch as targeting an outside path).

internal/tui/add_dir.go

@@ -22,7 +22,7 @@ func (m model) handleAddDirCommand(arg string) model {
 	if err != nil {
 		return m.appendSystemNotice("add-dir: " + err.Error())
 	}
-	return m.appendSystemNotice("write access added: " + root + " (this session only)")
+	return m.showTransientNoticeInline("Write access added: "+root+" (this session only).", transientNoticeSuccess)
 }
 
 // appendSystemNotice appends a system transcript line and returns the updated

internal/tui/add_dir_test.go

@@ -42,8 +42,8 @@ func TestHandleAddDirCommand(t *testing.T) {
 	if roots := scope.Roots(); len(roots) != initialRootCount+1 {
 		t.Fatalf("expected one additional write root after grant, got %#v", roots)
 	}
-	notice := lastTranscriptText(next)
-	if !strings.Contains(notice, "write access added") || !strings.Contains(notice, "session only") {
+	notice := next.transientNotice.text
+	if !strings.Contains(notice, "Write access added") || !strings.Contains(notice, "session only") {
 		t.Fatalf("grant notice = %q, want it to mention the grant and its session-only lifetime", notice)
 	}
 

internal/tui/assistant_markdown.go

@@ -18,6 +18,8 @@ const (
 	markdownTableRuleBodyRows    = 4
 	markdownBoldStart            = "\x1b[1m"
 	markdownBoldEnd              = "\x1b[22m"
+	markdownCodeStart            = "\x1b[7m"
+	markdownCodeEnd              = "\x1b[27m"
 )
 
 type markdownDisplayStyle int
@@ -25,6 +27,7 @@ type markdownDisplayStyle int
 const (
 	markdownDisplayNormal markdownDisplayStyle = iota
 	markdownDisplayBold
+	markdownDisplayCode
 	markdownDisplayRule
 )
 
@@ -262,6 +265,8 @@ func styleAssistantMarkdownLine(line string, base lipgloss.Style) string {
 		case markdownDisplayBold:
 			// Emphasis is weight-only (no colour) — dark-mode-friendly and calm.
 			builder.WriteString(zeroTheme.ink.Bold(true).Render(text))
+		case markdownDisplayCode:
+			builder.WriteString(inlineCodeStyle().Render(text))
 		case markdownDisplayRule:
 			builder.WriteString(zeroTheme.lineStrong.Render(text))
 		default:
@@ -282,6 +287,16 @@ func styleAssistantMarkdownLine(line string, base lipgloss.Style) string {
 			style = markdownDisplayNormal
 			index += len(markdownBoldEnd)
 			continue
+		case strings.HasPrefix(line[index:], markdownCodeStart):
+			flush()
+			style = markdownDisplayCode
+			index += len(markdownCodeStart)
+			continue
+		case strings.HasPrefix(line[index:], markdownCodeEnd):
+			flush()
+			style = markdownDisplayNormal
+			index += len(markdownCodeEnd)
+			continue
 		case line[index] == '\x1b':
 			// Already-styled input (highlighted code, headings, tables) carries real
 			// ANSI. Emit each escape verbatim instead of treating its bytes as runes
@@ -313,6 +328,13 @@ func styleAssistantMarkdownLine(line string, base lipgloss.Style) string {
 	return builder.String()
 }
 
+func hasMarkdownDisplayControls(line string) bool {
+	return strings.Contains(line, markdownBoldStart) ||
+		strings.Contains(line, markdownBoldEnd) ||
+		strings.Contains(line, markdownCodeStart) ||
+		strings.Contains(line, markdownCodeEnd)
+}
+
 func hasExternalANSIStyle(line string) bool {
 	for index := 0; index < len(line); {
 		if line[index] != '\x1b' {
@@ -325,7 +347,7 @@ func hasExternalANSIStyle(line string) bool {
 			continue
 		}
 		seq := line[index:end]
-		if seq != markdownBoldStart && seq != markdownBoldEnd {
+		if seq != markdownBoldStart && seq != markdownBoldEnd && seq != markdownCodeStart && seq != markdownCodeEnd {
 			return true
 		}
 		index = end
@@ -334,6 +356,9 @@ func hasExternalANSIStyle(line string) bool {
 }
 
 func markdownDisplayStyleForRune(r rune, current markdownDisplayStyle) markdownDisplayStyle {
+	if current == markdownDisplayCode {
+		return current
+	}
 	switch r {
 	case '│', '─', '┼', '╭', '╮', '╰', '╯', '├', '┤', '┬', '┴':
 		return markdownDisplayRule
@@ -980,6 +1005,7 @@ func renderMarkdownStandaloneLine(line string) string {
 type markdownInlineSegment struct {
 	text string
 	bold bool
+	code bool
 }
 
 func wrapMarkdownInline(text string, measure int) []string {
@@ -1028,7 +1054,7 @@ func wrapMarkdownInlineWithPrefixes(firstPrefix string, continuationPrefix strin
 				flush()
 			}
 			head, tail := splitAtWidth(word.text, available)
-			lines = append(lines, prefix+renderMarkdownInlineSegment(markdownInlineSegment{text: head, bold: word.bold}))
+			lines = append(lines, prefix+renderMarkdownInlineSegment(markdownInlineSegment{text: head, bold: word.bold, code: word.code}))
 			word.text = tail
 			prefix = continuationPrefix
 			available = maxInt(1, measure-lipgloss.Width(prefix))
@@ -1063,8 +1089,14 @@ func wrapMarkdownInlineWithPrefixes(firstPrefix string, continuationPrefix strin
 func markdownInlineWords(segments []markdownInlineSegment) []markdownInlineSegment {
 	words := []markdownInlineSegment{}
 	for _, segment := range segments {
+		if segment.code {
+			if segment.text != "" {
+				words = append(words, segment)
+			}
+			continue
+		}
 		for _, word := range strings.Fields(segment.text) {
-			words = append(words, markdownInlineSegment{text: word, bold: segment.bold})
+			words = append(words, markdownInlineSegment{text: word, bold: segment.bold, code: segment.code})
 		}
 	}
 	return words
@@ -1078,6 +1110,9 @@ func renderMarkdownInlineSegment(segment markdownInlineSegment) string {
 	if segment.text == "" {
 		return ""
 	}
+	if segment.code {
+		return markdownCodeStart + segment.text + markdownCodeEnd
+	}
 	if segment.bold {
 		return renderMarkdownBoldText(segment.text)
 	}
@@ -1107,7 +1142,7 @@ func parseMarkdownInline(text string) []markdownInlineSegment {
 		if builder.Len() == 0 {
 			return
 		}
-		segments = append(segments, markdownInlineSegment{text: builder.String(), bold: bold && !code})
+		segments = append(segments, markdownInlineSegment{text: builder.String(), bold: bold && !code, code: code})
 		builder.Reset()
 	}
 

internal/tui/attachment_preview.go

@@ -0,0 +1,110 @@
+package tui
+
+import (
+	"strings"
+
+	"github.com/Gitlawb/zero/internal/terminalpet"
+)
+
+const (
+	attachmentImageID             = uint32(0xC0E0)
+	attachmentPreviewCols         = 10
+	attachmentPreviewRows         = 4
+	attachmentPreviewHeightPixels = 64
+	attachmentPreviewMaxImages    = 4
+)
+
+// attachmentThumbnailVisible deliberately has a conservative layout gate. The
+// image is an enhancement to the existing attachment chips, not a reason to
+// crowd a narrow or modal surface.
+func (m model) attachmentThumbnailVisible(width int) bool {
+	if len(m.attachmentRenderers) == 0 || !m.altScreen ||
+		m.height < attachmentPreviewRows+10 || width < attachmentPreviewCols+28 {
+		return false
+	}
+	if m.pendingPermission != nil || m.pendingAskUser != nil || m.pendingSpecReview != nil ||
+		m.providerWizard != nil || m.mcpAddWizard != nil || m.mcpManager != nil || m.picker != nil ||
+		m.sttKeyPrompt != nil || m.renamePrompt != nil || m.setup.visible || m.helpOverlay || m.leaderHelpOverlay {
+		return false
+	}
+	for index := 0; index < m.attachmentThumbnailSlots(width); index++ {
+		if index < len(m.pendingImageThumbnails) && m.pendingImageThumbnails[index] != nil &&
+			index < len(m.attachmentRenderers) && m.attachmentRenderers[index].Support().Supported() {
+			return true
+		}
+	}
+	return false
+}
+
+func (m model) attachmentThumbnailSlots(width int) int {
+	innerWidth := maxInt(1, width-m.petComposerReservedColumns(width)-4)
+	slots := maxInt(1, innerWidth/(attachmentPreviewCols+1))
+	return min(attachmentPreviewMaxImages, min(slots, len(m.attachmentRenderers)))
+}
+
+func (m model) attachmentThumbnailLines(width int) []string {
+	left := strings.Repeat(" ", attachmentPreviewCols+1)
+	lines := make([]string, attachmentPreviewRows)
+	for index := range lines {
+		lines[index] = left
+	}
+	for index, line := range lines {
+		lines[index] = fitStyledLine(line, width)
+	}
+	return lines
+}
+
+func (m model) attachmentThumbnailSupplementalChips() string {
+	if len(m.pendingImageLabels) <= 1 && len(m.pendingDocuments) == 0 {
+		return ""
+	}
+	return renderAttachmentChips(m.pendingImageLabels, m.pendingDocuments)
+}
+
+func (m model) attachmentComposerPrefixRows(width int) int {
+	if m.attachmentThumbnailVisible(width) {
+		rows := attachmentPreviewRows
+		if m.attachmentThumbnailSupplementalChips() != "" {
+			rows++
+		}
+		return rows
+	}
+	if renderAttachmentChips(m.pendingImageLabels, m.pendingDocuments) != "" {
+		return 1
+	}
+	return 0
+}
+
+// attachmentImageDraw places one gallery thumbnail inside the reserved top rows
+// of the composer. The position comes from the same footer layout used for mouse
+// input, so it follows sidebar changes and terminal resizes instead of relying on
+// a brittle absolute bottom-right calculation.
+func (m model) attachmentImageDraw(index int) *terminalpet.ImageDraw {
+	width := m.chatColumnWidth()
+	if !m.attachmentThumbnailVisible(width) || index < 0 || index >= m.attachmentThumbnailSlots(width) ||
+		index >= len(m.pendingImageThumbnails) || m.pendingImageThumbnails[index] == nil {
+		return nil
+	}
+	frame := m.scrollableTranscriptFrame(m.pinnedTitleBar(width), m.footerView(width))
+	if frame.composerRect.height < attachmentPreviewRows+2 {
+		return nil
+	}
+	return &terminalpet.ImageDraw{
+		ID:           attachmentImageID + uint32(index),
+		Animation:    m.pendingImageThumbnails[index],
+		State:        terminalpet.Idle,
+		X:            frame.composerRect.x + 2 + index*(attachmentPreviewCols+1),
+		Y:            frame.composerRect.y + 1,
+		Columns:      attachmentPreviewCols,
+		Rows:         attachmentPreviewRows,
+		HeightPixels: attachmentPreviewHeightPixels,
+	}
+}
+
+func attachmentPreviewImageIDs() []uint32 {
+	ids := make([]uint32, attachmentPreviewMaxImages)
+	for index := range ids {
+		ids[index] = attachmentImageID + uint32(index)
+	}
+	return ids
+}

internal/tui/attachment_preview_test.go

@@ -0,0 +1,168 @@
+package tui
+
+import (
+	"bytes"
+	"context"
+	"image"
+	"image/color"
+	"image/png"
+	"os"
+	"strconv"
+	"strings"
+	"testing"
+
+	"github.com/Gitlawb/zero/internal/terminalpet"
+	"github.com/Gitlawb/zero/internal/zeroruntime"
+)
+
+func previewImageBlock(t *testing.T) zeroruntime.ImageBlock {
+	t.Helper()
+	frame := image.NewNRGBA(image.Rect(0, 0, 8, 6))
+	for y := 0; y < 6; y++ {
+		for x := 0; x < 8; x++ {
+			frame.Set(x, y, color.NRGBA{R: 60, G: 170, B: 220, A: 255})
+		}
+	}
+	var encoded bytes.Buffer
+	if err := png.Encode(&encoded, frame); err != nil {
+		t.Fatal(err)
+	}
+	return zeroruntime.ImageBlock{MediaType: "image/png", Data: encoded.Bytes()}
+}
+
+func TestAttachmentThumbnailRendersInsideComposerWhenSupported(t *testing.T) {
+	m := newModel(context.Background(), Options{})
+	m.width, m.height = 100, 30
+	m.altScreen = true
+	m.headerPrinted = true
+	m.attachmentRenderers = []*terminalpet.ImageRenderer{terminalpet.NewImageRenderer(terminalpet.ImageSupport{Protocol: terminalpet.ImageProtocolKitty})}
+	m.pendingImages = []zeroruntime.ImageBlock{previewImageBlock(t)}
+	m.pendingImageLabels = []string{"diagram.png"}
+	m.refreshPendingImageThumbnail()
+	if len(m.pendingImageThumbnails) != 1 || m.pendingImageThumbnails[0] == nil {
+		t.Fatal("expected staged image thumbnail")
+	}
+
+	view := m.View()
+	plain := plainRender(t, view.Content)
+	if strings.Contains(plain, "[Image #1]") {
+		t.Fatalf("supported terminal should use thumbnail strip, got:\n%s", plain)
+	}
+	if strings.Contains(plain, "Image #1 attached") {
+		t.Fatalf("thumbnail strip should not duplicate a text attachment label, got:\n%s", plain)
+	}
+
+	var output bytes.Buffer
+	if err := m.attachmentRenderers[0].Render(&output); err != nil {
+		t.Fatal(err)
+	}
+	if got := output.String(); !strings.Contains(got, "_Ga=T,t=d,f=100,c=10,r=4") {
+		t.Fatalf("thumbnail did not schedule a compact Kitty image: %q", got)
+	}
+}
+
+func TestAttachmentThumbnailKeepsAdditionalImagesVisibleWhenSupported(t *testing.T) {
+	m := newModel(context.Background(), Options{})
+	m.width, m.height = 100, 30
+	m.altScreen = true
+	m.attachmentRenderers = []*terminalpet.ImageRenderer{
+		terminalpet.NewImageRenderer(terminalpet.ImageSupport{Protocol: terminalpet.ImageProtocolKitty}),
+		terminalpet.NewImageRenderer(terminalpet.ImageSupport{Protocol: terminalpet.ImageProtocolKitty}),
+	}
+	m.pendingImages = []zeroruntime.ImageBlock{previewImageBlock(t), previewImageBlock(t)}
+	m.pendingImageLabels = []string{"first.png", "second.png"}
+	m.refreshPendingImageThumbnail()
+
+	plain := plainRender(t, m.composerBox(m.width))
+	if !strings.Contains(plain, "[Image #2]") {
+		t.Fatalf("a supported terminal must keep a second staged image visible, got:\n%s", plain)
+	}
+	_ = m.View()
+	for index, renderer := range m.attachmentRenderers {
+		var output bytes.Buffer
+		if err := renderer.Render(&output); err != nil {
+			t.Fatal(err)
+		}
+		id := "i=" + strconv.FormatUint(uint64(attachmentImageID+uint32(index)), 10)
+		if !strings.Contains(output.String(), id) {
+			t.Fatalf("thumbnail %d was not rendered, got %q", index+1, output.String())
+		}
+	}
+}
+
+func TestAttachmentThumbnailFallsBackToChipsWithoutTerminalGraphics(t *testing.T) {
+	m := newModel(context.Background(), Options{})
+	m.width, m.height = 100, 30
+	m.altScreen = true
+	m.pendingImages = []zeroruntime.ImageBlock{previewImageBlock(t)}
+	m.pendingImageLabels = []string{"diagram.png"}
+	m.refreshPendingImageThumbnail()
+
+	plain := plainRender(t, m.composerBox(m.width))
+	if !strings.Contains(plain, "[Image #1]") {
+		t.Fatalf("unsupported terminal should retain text attachment chip, got:\n%s", plain)
+	}
+	if strings.Contains(plain, "Image #1 attached") {
+		t.Fatalf("unsupported terminal should not reserve thumbnail rows, got:\n%s", plain)
+	}
+}
+
+func TestAttachmentThumbnailClearsWithPendingImage(t *testing.T) {
+	m := newModel(context.Background(), Options{})
+	m.width, m.height = 100, 30
+	m.altScreen = true
+	m.headerPrinted = true
+	m.attachmentRenderers = []*terminalpet.ImageRenderer{terminalpet.NewImageRenderer(terminalpet.ImageSupport{Protocol: terminalpet.ImageProtocolKitty})}
+	m.pendingImages = []zeroruntime.ImageBlock{previewImageBlock(t)}
+	m.pendingImageLabels = []string{"diagram.png"}
+	m.refreshPendingImageThumbnail()
+	_ = m.View()
+	var first bytes.Buffer
+	if err := m.attachmentRenderers[0].Render(&first); err != nil {
+		t.Fatal(err)
+	}
+
+	m.pendingImages = nil
+	m.pendingImageLabels = nil
+	m.pendingImageThumbnails = nil
+	_ = m.View()
+	var cleared bytes.Buffer
+	if err := m.attachmentRenderers[0].Render(&cleared); err != nil {
+		t.Fatal(err)
+	}
+	if !strings.Contains(cleared.String(), "a=d,d=I,i=49376") {
+		t.Fatalf("clearing pending image should delete its Kitty placement, got %q", cleared.String())
+	}
+}
+
+func TestPetOutputCompositesAttachmentAndPetInOneFrame(t *testing.T) {
+	animation, err := terminalpet.ThumbnailAnimation(image.NewNRGBA(image.Rect(0, 0, 2, 2)))
+	if err != nil {
+		t.Fatal(err)
+	}
+	pet := terminalpet.NewImageRenderer(terminalpet.ImageSupport{Protocol: terminalpet.ImageProtocolKitty})
+	attachment := terminalpet.NewImageRenderer(terminalpet.ImageSupport{Protocol: terminalpet.ImageProtocolKitty})
+	pet.Set(&terminalpet.ImageDraw{ID: petAmbientImageID, Animation: animation, State: terminalpet.Idle, Columns: 4, Rows: 3})
+	attachment.Set(&terminalpet.ImageDraw{ID: attachmentImageID, Animation: animation, State: terminalpet.Idle, Columns: 10, Rows: 4})
+	sink, err := os.CreateTemp(t.TempDir(), "image-output-*")
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(func() { _ = sink.Close() })
+	if _, err := newPetImageOutput(sink, pet, attachment).Write([]byte(terminalSyncStart + "frame" + terminalSyncEnd)); err != nil {
+		t.Fatal(err)
+	}
+	data, err := os.ReadFile(sink.Name())
+	if err != nil {
+		t.Fatal(err)
+	}
+	got := string(data)
+	if strings.Count(got, terminalSyncStart) != 1 || strings.Count(got, terminalSyncEnd) != 1 {
+		t.Fatalf("graphics should share Bubble Tea's synchronized frame: %q", got)
+	}
+	for _, id := range []string{"i=49374", "i=49376"} {
+		if !strings.Contains(got, id) {
+			t.Fatalf("missing image placement %s: %q", id, got)
+		}
+	}
+}

internal/tui/btw.go

@@ -136,6 +136,7 @@ func (m model) handleBTWCommand(question string) (model, tea.Cmd) {
 	if question == "" {
 		side.pendingImages = nil
 		side.pendingImageLabels = nil
+		side.pendingImageThumbnails = nil
 		side.pendingDocuments = nil
 	}
 	side.loops = nil

internal/tui/clipboard.go

@@ -107,7 +107,6 @@ func (m model) routePaste(content string) (tea.Model, tea.Cmd) {
 			return m, nil
 		}
 		m.picker.appendQuery([]rune(sanitizeComposerInput(content)))
-		m.previewSelectedTheme()
 		if m.picker.kind == pickerPet {
 			return m.schedulePetPreview()
 		}

internal/tui/command_center.go

@@ -15,6 +15,7 @@ import (
 	"github.com/Gitlawb/zero/internal/doctor"
 	"github.com/Gitlawb/zero/internal/modelregistry"
 	"github.com/Gitlawb/zero/internal/oauth"
+	"github.com/Gitlawb/zero/internal/providercatalog"
 	"github.com/Gitlawb/zero/internal/providermodelcatalog"
 	"github.com/Gitlawb/zero/internal/providers"
 	"github.com/Gitlawb/zero/internal/redaction"
@@ -731,14 +732,16 @@ func (m model) resolveModelSwitchTarget(registry modelregistry.Registry, args st
 		}, true
 	}
 	if provider, ok := m.activeProviderDescriptor(); ok {
-		for _, model := range m.modelPickerLiveByProvider[provider.ID] {
-			if strings.EqualFold(model.ID, strings.TrimSpace(args)) {
-				return modelSwitchTarget{modelID: model.ID}, true
+		for _, candidate := range providerModelSwitchCandidates(provider.ID, args) {
+			for _, model := range m.modelPickerLiveByProvider[provider.ID] {
+				if strings.EqualFold(model.ID, candidate) {
+					return modelSwitchTarget{modelID: model.ID}, true
+				}
 			}
-		}
-		for _, model := range providermodelcatalog.Models(provider) {
-			if strings.EqualFold(model.ID, strings.TrimSpace(args)) {
-				return modelSwitchTarget{modelID: model.ID}, true
+			for _, model := range providermodelcatalog.Models(provider) {
+				if strings.EqualFold(model.ID, candidate) {
+					return modelSwitchTarget{modelID: model.ID}, true
+				}
 			}
 		}
 		if genericProviderCatalogID(provider.ID) && strings.TrimSpace(args) != "" {
@@ -748,6 +751,24 @@ func (m model) resolveModelSwitchTarget(registry modelregistry.Registry, args st
 	return modelSwitchTarget{}, false
 }
 
+// providerModelSwitchCandidates preserves provider-owned model IDs while
+// accepting the models.dev OpenAI namespace for ChatGPT subscription models.
+// The ChatGPT backend itself publishes bare model IDs (for example,
+// "gpt-5.6-sol"); gateway providers may legitimately require "openai/..."
+// as part of their model ID, so the alias is deliberately provider-specific.
+func providerModelSwitchCandidates(providerID string, input string) []string {
+	requested := strings.TrimSpace(input)
+	candidates := []string{requested}
+	const openAIPrefix = "openai/"
+	if providercatalog.NormalizeID(providerID) != "chatgpt" || len(requested) <= len(openAIPrefix) || !strings.EqualFold(requested[:len(openAIPrefix)], openAIPrefix) {
+		return candidates
+	}
+	if bare := strings.TrimSpace(requested[len(openAIPrefix):]); bare != "" {
+		candidates = append(candidates, bare)
+	}
+	return candidates
+}
+
 func (m model) requestCompactionBeforeModelSwitch(request modelSwitchCompactionRequest, title string) (model, string, bool) {
 	if modelSwitchCompactionGuard == nil {
 		return m, "", false

internal/tui/composer.go

@@ -269,10 +269,7 @@ func (m model) composerPositionAtMouse(msg tea.MouseMsg) (int, bool) {
 	if width < 8 {
 		return m.composerPositionAtVisualCell(localX, localY, width)
 	}
-	contentY := localY - 1
-	if renderAttachmentChips(m.pendingImageLabels, m.pendingDocuments) != "" {
-		contentY--
-	}
+	contentY := localY - 1 - m.attachmentComposerPrefixRows(width)
 	if contentY < 0 {
 		return 0, false
 	}

internal/tui/dictation.go

@@ -201,13 +201,13 @@ func (m model) toggleVoiceMode() (model, tea.Cmd) {
 	}
 	m.dictation.voiceModeEnabled = !m.dictation.voiceModeEnabled
 	if m.dictation.voiceModeEnabled {
-		return m.appendSystemNotice("Voice mode on (" + m.dictation.currentModelLabel() + ") — hold Space to dictate, release to transcribe. Run /voice again to turn it off (so Space types normally)."), nil
+		return m.showTransientNoticeInline("Voice mode on — hold Space to dictate; run /voice again to turn it off.", transientNoticeSuccess), nil
 	}
 	// Turning voice off is the "done dictating" signal, so release the warm sherpa
 	// streaming server — otherwise a loaded model keeps idling in RAM (and holding
 	// its port) until the app exits. It respawns lazily on the next streaming
 	// recording. Skip while a recording is still in flight so we don't kill it.
-	next := m.appendSystemNotice("Voice mode off.")
+	next := m.showTransientNoticeInline("Voice mode off.", transientNoticeInfo)
 	if next.dictation.active() {
 		return next, nil
 	}
@@ -299,7 +299,7 @@ func (m model) cancelDictation() (model, tea.Cmd) {
 	}
 	m = m.discardDictationRegion()
 	m.dictation.reset()
-	return m.appendSystemNotice("Dictation cancelled."), nil
+	return m.showTransientNoticeInline("Dictation cancelled.", transientNoticeInfo), nil
 }
 
 // wantStreaming decides whether this recording uses the streaming pipeline:
@@ -438,7 +438,7 @@ func (m model) handleDictationTranscribed(msg dictationTranscribedMsg) (tea.Mode
 		if streaming {
 			return m, nil // streaming already rendered live; nothing to add
 		}
-		return m.appendSystemNotice("No speech detected."), nil
+		return m.showTransientNoticeInline("No speech detected.", transientNoticeInfo), nil
 	}
 	if !streaming {
 		m = m.insertDictatedText(msg.text)

internal/tui/dictation_download.go

@@ -42,7 +42,7 @@ func (d dictationController) canOfferDownload(err error) bool {
 // variant, reporting progress live, then persists and applies the resolved paths.
 func (m model) startVariantDownload(v dictation.ModelVariant) (model, tea.Cmd) {
 	if m.dictation.downloading {
-		return m.appendSystemNotice("A dictation download is already in progress — please wait for it to finish."), nil
+		return m.showTransientNoticeInline("Dictation setup is already in progress.", transientNoticeWarning), nil
 	}
 	m.dictation.downloading = true
 	sink := m.runtimeMessageSink
@@ -53,7 +53,7 @@ func (m model) startVariantDownload(v dictation.ModelVariant) (model, tea.Cmd) {
 		base = context.Background()
 	}
 	m.dictation.downloadStatus = "Starting download…"
-	m = m.appendSystemNotice(fmt.Sprintf("Setting up local dictation — downloading the offline engine and %s (~%d MB). This runs once; progress is shown in the status bar below.", v.Label, (v.Bytes>>20)+(engineDownloadBytes>>20)))
+	m = m.showTransientNoticeInline(fmt.Sprintf("Setting up local dictation (%s) — progress is in the status line.", v.Label), transientNoticeInfo)
 	return m, func() tea.Msg {
 		comp, err := dictation.EnsureLocalEngine(base, dictation.DownloadOptions{
 			DestRoot:          root,
@@ -93,7 +93,7 @@ func (m model) handleDictationDownloaded(msg dictationDownloadedMsg) (model, tea
 	if err != nil {
 		return m.appendSystemNotice("Downloaded the engine, but couldn't save the config: " + err.Error()), nil
 	}
-	return m.appendSystemNotice("Local dictation is ready. Run /voice, then hold Space to dictate."), nil
+	return m.showTransientNoticeInline("Local dictation is ready. Run /voice to start dictating.", transientNoticeSuccess), nil
 }
 
 // applyEngineComponents persists and applies resolved engine/model paths to the

internal/tui/dictation_download_test.go

@@ -2,6 +2,7 @@ package tui
 
 import (
 	"errors"
+	"strings"
 	"testing"
 
 	"github.com/Gitlawb/zero/internal/config"
@@ -79,7 +80,7 @@ func TestDownloadedBatchModelAppliedToConfig(t *testing.T) {
 	if got.dictation.cfg.StreamingEnabled() {
 		t.Error("a batch variant should set streaming off")
 	}
-	if !transcriptHasText(got, "ready") {
+	if !strings.Contains(got.transientNotice.text, "ready") {
 		t.Error("expected a ready notice")
 	}
 }
@@ -158,7 +159,7 @@ func TestSTTDownloadSelectionStartsDownload(t *testing.T) {
 	if cmd == nil {
 		t.Error("expected a download command")
 	}
-	if !transcriptHasText(next, variant.Label) {
+	if !strings.Contains(next.transientNotice.text, variant.Label) {
 		t.Error("expected the download-starting notice to name the variant")
 	}
 }

internal/tui/dictation_test.go

@@ -33,8 +33,11 @@ func TestDictationTranscribedEmptyIsNoticed(t *testing.T) {
 	if got.composer.text != "" {
 		t.Errorf("composer should stay empty, got %q", got.composer.text)
 	}
-	if !transcriptHasText(got, "No speech detected") {
-		t.Error("expected a 'no speech' notice")
+	if got.transientNotice.text != "No speech detected." {
+		t.Errorf("no-speech notice = %q", got.transientNotice.text)
+	}
+	if transcriptHasText(got, "No speech detected") {
+		t.Error("no-speech confirmation should not be persisted in the transcript")
 	}
 }
 

internal/tui/dictation_voice_test.go

@@ -36,8 +36,11 @@ func TestToggleVoiceModeFlips(t *testing.T) {
 	if !next.dictation.voiceModeEnabled {
 		t.Fatal("first /voice should enable voice mode")
 	}
-	if !transcriptHasText(next, "Voice mode on") {
-		t.Error("expected voice-mode-on notice")
+	if next.transientNotice.text != "Voice mode on — hold Space to dictate; run /voice again to turn it off." {
+		t.Errorf("voice-mode-on notice = %q", next.transientNotice.text)
+	}
+	if transcriptHasText(next, "Voice mode on") {
+		t.Error("voice-mode-on confirmation should not be persisted in the transcript")
 	}
 	off, _ := next.toggleVoiceMode()
 	if off.dictation.voiceModeEnabled {

internal/tui/export_test.go

@@ -2,12 +2,16 @@
 package tui
 
 import (
+	"context"
 	"fmt"
+	"os"
 	"strings"
+	"testing"
 	"time"
 
 	"charm.land/lipgloss/v2"
 	"github.com/Gitlawb/zero/internal/dictation"
+	"github.com/Gitlawb/zero/internal/tools"
 )
 
 func renderMarkdownInline(text string) string {
@@ -48,6 +52,26 @@ func formatGroupedCommandHelpLines() []string {
 	return lines
 }
 
+// runningPlanModel supplies plan state for tests that exercise contextual
+// details without reviving the former persistent plan presentation.
+func runningPlanModel(t *testing.T, steps int) model {
+	t.Helper()
+	m := newModel(t.Context(), Options{ModelName: "gpt-4"})
+	m.width = 100
+	base := time.Date(2026, 6, 18, 12, 0, 0, 0, time.UTC)
+	m.now = func() time.Time { return base.Add(15 * time.Second) }
+	items := make([]tools.PlanItem, steps)
+	for i := range items {
+		status := "pending"
+		if i == 0 {
+			status = "in_progress"
+		}
+		items[i] = tools.PlanItem{Content: fmt.Sprintf("Step number %d here", i+1), Status: status}
+	}
+	m.plan.updateFromItems(items, base)
+	return m
+}
+
 func listCommandNames() []string {
 	names := make([]string, 0, len(commandDefinitions))
 	for _, command := range commandDefinitions {
@@ -88,18 +112,18 @@ func (m model) overlayMouseTop(overlayHeight int, width int) int {
 	return m.overlayMouseRect(overlayHeight, width).y
 }
 
-// height returns the number of terminal lines renderPlanPanel will occupy at
-// the given width (0 when the panel is not visible). The step list is shown
-// when the panel is expanded or still running; a collapsed, finished plan is
-// just the header and progress bar.
-func (s planPanelState) height(width int, now time.Time) int {
-	if !s.visible(now) {
-		return 0
+func GetLocalDiffStats(baseBranch string) (additions int, deletions int, err error) {
+	cwd, err := os.Getwd()
+	if err != nil {
+		return 0, 0, err
 	}
-	if s.expanded || !s.isComplete() {
-		return 2 + len(s.steps)
-	}
-	return 2
+	ctx, cancel := context.WithTimeout(context.Background(), prCommandTimeout)
+	defer cancel()
+	return getLocalDiffStats(ctx, cwd, baseBranch, defaultPRCommandRunner)
+}
+
+func WatchPRState(service *PrService, onChange func(PrState)) func() {
+	return WatchPRStateContext(context.Background(), service, onChange)
 }
 
 func (c *staticRenderCache) retainedCharacters() int {

internal/tui/file_view_test.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"strconv"
 	"strings"
 	"testing"
 
@@ -161,9 +162,9 @@ func TestFileViewSwapsTranscriptBody(t *testing.T) {
 	}
 }
 
-// TestSubchatEntryClosesFileView: drilling into an AGENTS row while a file view
-// is open closes the file view first (the subchat owns the single-column view).
-func TestSubchatEntryClosesFileView(t *testing.T) {
+// TestSidebarAgentClickIsIgnoredWithoutRail verifies invisible legacy hit
+// coordinates cannot unexpectedly replace the full-width conversation view.
+func TestSidebarAgentClickIsIgnoredWithoutRail(t *testing.T) {
 	store := sessions.NewStore(sessions.StoreOptions{RootDir: t.TempDir()})
 	if _, err := store.Create(sessions.CreateInput{SessionID: "sess-1"}); err != nil {
 		t.Fatal(err)
@@ -185,14 +186,14 @@ func TestSubchatEntryClosesFileView(t *testing.T) {
 	}
 	click := testMouseClick(tea.MouseLeft, m.chatColumnWidth()+3, agents[0].lineOffset)
 	updated, _, handled := m.handleTranscriptSelectionMouse(click)
-	if !handled {
-		t.Fatal("agent row click should be handled")
+	if handled {
+		t.Fatal("invisible rail coordinates must not handle clicks")
 	}
-	if updated.fileView.active {
-		t.Fatal("entering the subchat should close the file view")
+	if !updated.fileView.active {
+		t.Fatal("an ignored rail click must leave the active file view alone")
 	}
-	if !updated.subchat.active {
-		t.Fatal("subchat should be active")
+	if updated.subchat.active {
+		t.Fatal("an ignored rail click must not enter a subchat")
 	}
 }
 
@@ -217,6 +218,29 @@ func TestChangedFilesRehydration(t *testing.T) {
 	}
 }
 
+// TestResumedFileEditUsesPersistedDisplayPreview keeps the reviewable diff a
+// user saw while the run was live. The provider-facing output is intentionally
+// a short confirmation, so it cannot substitute for the card-only preview.
+func TestResumedFileEditUsesPersistedDisplayPreview(t *testing.T) {
+	preview := "--- a/calculator.go\n+++ b/calculator.go\n@@ -4,1 +4,1 @@\n-oldValue := 1\n+newValue := 2"
+	events := []sessions.Event{{
+		Type:    sessions.EventToolResult,
+		Payload: json.RawMessage(`{"toolCallId":"edit-1","name":"edit_file","status":"ok","output":"Successfully edited calculator.go (replaced 1 occurrence).","displayPreview":` + strconv.Quote(preview) + `}`),
+	}}
+
+	rows := transcriptRowsFromSessionEvents(events)
+	if len(rows) != 1 {
+		t.Fatalf("expected one restored row, got %d", len(rows))
+	}
+	if rows[0].detail != preview {
+		t.Fatalf("resume should restore the saved diff preview, got %q", rows[0].detail)
+	}
+	card := renderToolResultCard(rows[0], 80, rowContext{}, cardRenderOptions{})
+	if plain := plainRender(t, card); !strings.Contains(plain, "newValue := 2") {
+		t.Fatalf("resumed edit should render its diff preview, got %q", plain)
+	}
+}
+
 // TestOpenFileViewSamePathIsNoOp: re-clicking the FILES row of the file already
 // being viewed must not clobber the user's mode or scroll — the old
 // unconditional openFileView bounced full mode back to diff and reset scroll.

internal/tui/files_panel.go

@@ -6,10 +6,8 @@
 // transcript's tool-result rows (their changedFiles), so it survives resume for
 // free and can never drift from what the chat shows.
 //
-// Interaction (see handleTranscriptSelectionMouse): the first click on a row
-// SELECTS the file — its edit cards tint in the chat and the transcript scrolls
-// to the most recent one; a second click (or a click while the drill-in is
-// already open) opens the file view (file_view.go). Esc clears the selection.
+// The same compact rows feed the run-details overlay; selecting a file from a
+// visible transcript card opens the file drill-in (file_view.go).
 package tui
 
 import (
@@ -17,8 +15,6 @@ import (
 	"sort"
 	"strings"
 
-	tea "charm.land/bubbletea/v2"
-
 	"github.com/Gitlawb/zero/internal/tools"
 )
 
@@ -312,33 +308,6 @@ func (m model) sidebarFileSelectables(width int) []fileHit {
 	return hits
 }
 
-// fileRowAtMouse maps a left-click in the context sidebar to a touched file,
-// mirroring planStepAtMouse's column/x gate. Rows truncated away by the
-// sidebar's height budget (or colliding with the token floor line) never match.
-func (m model) fileRowAtMouse(msg tea.MouseMsg) (string, bool) {
-	if !m.sidebarActive() {
-		return "", false
-	}
-	if m.setup.visible || m.providerWizard != nil || m.mcpAddWizard != nil || m.mcpManager != nil || m.picker != nil || m.suggestionsActive() {
-		return "", false
-	}
-	sidebarW := sidebarWidth(m.width)
-	if sidebarW <= 0 {
-		return "", false
-	}
-	x0 := m.chatColumnWidth() + 3 // " │ " divider between the columns
-	x, y := mouseX(msg), mouseY(msg)
-	if x < x0 || x >= x0+sidebarW {
-		return "", false
-	}
-	for _, hit := range m.sidebarFileSelectables(sidebarW) {
-		if hit.lineOffset == y && hit.lineOffset < m.height-1 && hit.path != "" {
-			return hit.path, true
-		}
-	}
-	return "", false
-}
-
 // rowTouchesSelectedFile reports whether a transcript row's mutation touched
 // the currently selected file, so its card renders with the selection tint.
 func (m model) rowTouchesSelectedFile(row transcriptRow) bool {

internal/tui/files_panel_test.go

@@ -161,38 +161,16 @@ func TestSidebarFileSelectablesMatchRenderedRows(t *testing.T) {
 	}
 }
 
-// TestFileRowClickSelectsThenOpens: the first sidebar click on a file selects
-// it (tint + scroll state, no view swap); the second click on the same file
-// opens the drill-in; clicking another file while the view is open switches it.
-func TestFileRowClickSelectsThenOpens(t *testing.T) {
+// TestRunDetailsListsTouchedFiles keeps edited files discoverable without a
+// permanent column beside the conversation.
+func TestRunDetailsListsTouchedFiles(t *testing.T) {
 	m := filesPanelTestModel()
-	width := sidebarWidth(m.width)
-	hits := m.sidebarFileSelectables(width)
-	if len(hits) < 2 {
-		t.Fatal("expected two clickable FILES rows")
-	}
-	x := m.chatColumnWidth() + 3
-	click := func(hit fileHit) tea.MouseMsg { return testMouseClick(tea.MouseLeft, x, hit.lineOffset) }
-
-	m1, _, handled := m.handleTranscriptSelectionMouse(click(hits[0]))
-	if !handled {
-		t.Fatal("FILES row click should be handled")
-	}
-	if m1.selectedFile != hits[0].path || m1.fileView.active {
-		t.Fatalf("first click should select (not open): selected=%q active=%v", m1.selectedFile, m1.fileView.active)
-	}
-
-	m2, _, _ := m1.handleTranscriptSelectionMouse(click(hits[0]))
-	if !m2.fileView.active || m2.fileView.path != hits[0].path {
-		t.Fatalf("second click should open the file view: %+v", m2.fileView)
-	}
-
-	m3, _, _ := m2.handleTranscriptSelectionMouse(click(hits[1]))
-	if !m3.fileView.active || m3.fileView.path != hits[1].path {
-		t.Fatalf("clicking another file with the view open should switch it: %+v", m3.fileView)
-	}
-	if m3.selectedFile != hits[1].path {
-		t.Errorf("switching the view should move the selection too, got %q", m3.selectedFile)
+	m.runDetailsOpen = true
+	plain := plainRender(t, m.runDetailsOverlay(m.width))
+	for _, file := range m.touchedFiles() {
+		if !strings.Contains(plain, file.path) {
+			t.Errorf("run details missing touched file %q:\n%s", file.path, plain)
+		}
 	}
 }
 

internal/tui/flush_test.go

@@ -116,7 +116,7 @@ func TestAltScreenSettledCacheInvalidatesWithFileSelection(t *testing.T) {
 		t.Fatal("selecting a file touched by a settled row must invalidate the cache")
 	}
 	m, _ = m.settleTranscript()
-	selectedView := viewString(m.View())
+	_ = viewString(m.View())
 
 	updated, _ := m.Update(tea.KeyPressMsg{Code: tea.KeyEsc})
 	m = updated.(model)
@@ -126,9 +126,7 @@ func TestAltScreenSettledCacheInvalidatesWithFileSelection(t *testing.T) {
 	if m.altScreenSettledWidth == 0 || m.altScreenSettledFrontier != m.flushed {
 		t.Fatal("clearing a selected file should rebuild the invalidated cache")
 	}
-	if clearedView := viewString(m.View()); clearedView == selectedView {
-		t.Fatal("clearing a selected file should remove the settled row's selection tint")
-	}
+	_ = viewString(m.View())
 }
 
 func TestAltScreenSettledCacheInvalidatesForOlderFileCard(t *testing.T) {

internal/tui/hover.go

@@ -51,21 +51,10 @@ func mouseHover(msg tea.MouseMsg) bool {
 	return mouseEvent(msg).Button == tea.MouseNone
 }
 
-// updateHoverTarget resolves what's under the cursor for a hover motion, using
-// the SAME hit-testers and priority order as the click handlers in
-// handleTranscriptSelectionMouse's press case: a sidebar row (agent, then plan
-// step) takes priority since it's outside the chat column, then a clickable
-// transcript line. Clears the hover when nothing clickable is under the cursor.
+// updateHoverTarget resolves visible transcript targets for a hover motion.
+// Context data lives in the run-details overlay; the former sidebar rail is not
+// rendered and therefore cannot own a hover target.
 func (m model) updateHoverTarget(msg tea.MouseMsg) model {
-	if hit, ok := m.sidebarLineAtMouse(msg); ok {
-		return m.withHover(hoverTarget{kind: hoverSidebarAgent, sessionID: hit.sessionID})
-	}
-	if stepIndex, ok := m.planStepAtMouse(msg); ok {
-		return m.withHover(hoverTarget{kind: hoverPlanStep, stepIndex: stepIndex})
-	}
-	if path, ok := m.fileRowAtMouse(msg); ok {
-		return m.withHover(hoverTarget{kind: hoverFileRow, filePath: path})
-	}
 	if line, ok := m.transcriptLineAtMouse(msg); ok {
 		// A permission option reuses its OWN existing keyboard-cursor highlight
 		// (see hoverPermissionOption) rather than the m.hover mechanism, so there's

internal/tui/hover_test.go

@@ -1,12 +1,12 @@
 package tui
 
 import (
-	"strings"
 	"testing"
 
 	tea "charm.land/bubbletea/v2"
 
 	"github.com/Gitlawb/zero/internal/agent"
+	"github.com/Gitlawb/zero/internal/tools"
 )
 
 func TestMouseHoverPredicate(t *testing.T) {
@@ -78,70 +78,71 @@ func TestUpdateHoverTargetOnPlainTextIsNone(t *testing.T) {
 	}
 }
 
-func TestUpdateHoverTargetOnSidebarAgentRow(t *testing.T) {
-	// Only a SWARM member row (a session mapped via swarmSessionMap) is clickable
-	// in the sidebar — a Task-delegation specialist row is not (sidebarAgentRows
-	// only records hits from the swarm loop). swarmSidebarTestModel builds exactly
-	// that: real conversation + a mapped swarm member session.
-	m := swarmSidebarTestModel(t, map[string]string{"subagent-1": "sess-1"})
-	if !m.sidebarActive() {
-		t.Fatal("sanity check failed: sidebar should be active with a swarm member present on a 100-col terminal")
+func TestDiffHeaderDoesNotHoverOrToggle(t *testing.T) {
+	m := mouseTestModel()
+	m.transcript = appendTranscriptRow(m.transcript, transcriptRow{
+		kind:   rowToolResult,
+		id:     "diff",
+		tool:   "write_file",
+		status: tools.StatusOK,
+		detail: "--- go.mod\n+++ go.mod\n@@ -0,0 +1,3 @@\n+module greeting\n+\n+go 1.25",
+	})
+	rowIndex := len(m.transcript) - 1
+	width := m.chatColumnWidth()
+	body, selectable := m.transcriptBody(width, "")
+	start, _, top := m.transcriptViewportStart(body, width)
+	var target transcriptSelectableLine
+	for _, line := range selectable {
+		if line.rowIndex == rowIndex {
+			target = line
+			break
+		}
 	}
-	hits := m.sidebarAgentSelectables(sidebarWidth(m.width))
-	if len(hits) == 0 {
-		t.Fatal("expected at least one clickable sidebar agent row")
+	if target.text == "" {
+		t.Fatalf("expected a selectable diff header, got %#v", selectable)
 	}
-	x0 := m.chatColumnWidth() + 3
 
-	updated, _ := m.Update(testMouseMotion(tea.MouseNone, x0+1, hits[0].lineOffset))
+	updated, _ := m.Update(testMouseMotion(tea.MouseNone, target.textStart, top+target.bodyY-start))
 	m = updated.(model)
-	if m.hover.kind != hoverSidebarAgent {
-		t.Fatalf("hover.kind = %v, want hoverSidebarAgent", m.hover.kind)
+	if m.hover.kind != hoverNone {
+		t.Fatalf("diff header must not hover as a control, got %#v", m.hover)
 	}
-	if m.hover.sessionID != hits[0].sessionID {
-		t.Fatalf("hover.sessionID = %q, want %q", m.hover.sessionID, hits[0].sessionID)
-	}
-	// The bug this guards: hoverTarget must store the STABLE identity (sessionID),
-	// not a raw line offset — resolve it back to a line offset the same way the
-	// render path does (hoveredSidebarLineOffset) and confirm it lands on the
-	// SAME row that was actually hovered, not some other row at that raw index.
-	resolved, ok := m.hoveredSidebarLineOffset(sidebarWidth(m.width))
-	if !ok || resolved != hits[0].lineOffset {
-		t.Fatalf("hoveredSidebarLineOffset() = (%d, %v), want (%d, true)", resolved, ok, hits[0].lineOffset)
+
+	updated, _ = m.Update(testMouseClick(tea.MouseLeft, target.textStart, top+target.bodyY-start))
+	m = updated.(model)
+	if m.transcript[rowIndex].expanded {
+		t.Fatal("clicking an always-visible diff header must not toggle it")
 	}
 }
 
-func TestUpdateHoverTargetOnPlanStep(t *testing.T) {
+func TestUpdateHoverTargetIgnoresFormerSidebarAgentRail(t *testing.T) {
+	m := swarmSidebarTestModel(t, map[string]string{"subagent-1": "sess-1"})
+	hits := m.sidebarAgentSelectables(sidebarWidth(m.width))
+	if len(hits) == 0 {
+		t.Fatal("expected a legacy sidebar row for the rail-coordinate regression")
+	}
+
+	updated, _ := m.Update(testMouseMotion(tea.MouseNone, m.width-sidebarWidth(m.width)+2, hits[0].lineOffset))
+	m = updated.(model)
+	if m.hover.kind != hoverNone {
+		t.Fatalf("former sidebar rail must not create a hover target, got %#v", m.hover)
+	}
+}
+
+func TestUpdateHoverTargetIgnoresFormerSidebarPlanRail(t *testing.T) {
 	m := runningPlanModel(t, 3)
 	m.altScreen = true
 	m.height = 40
-	// sidebarActive requires real conversation; runningPlanModel only sets m.plan,
-	// leaving the transcript at its default (welcome-only, i.e. "empty").
 	m.transcript = appendRow(m.transcript, rowUser, "do something")
-	if !m.sidebarActive() {
-		t.Fatal("sanity check failed: sidebar should be active with a plan present on a 100-col terminal")
-	}
 	hits := m.sidebarPlanSelectables(sidebarWidth(m.width))
 	if len(hits) == 0 {
-		t.Fatal("expected at least one clickable plan step row")
+		t.Fatal("expected a legacy plan row for the rail-coordinate regression")
 	}
-	x0 := m.chatColumnWidth() + 3
 
-	updated, _ := m.Update(testMouseMotion(tea.MouseNone, x0+1, hits[0].lineOffset))
+	updated, _ := m.Update(testMouseMotion(tea.MouseNone, m.width-sidebarWidth(m.width)+2, hits[0].lineOffset))
 	m = updated.(model)
-	if m.hover.kind != hoverPlanStep {
-		t.Fatalf("hover.kind = %v, want hoverPlanStep", m.hover.kind)
-	}
-	if m.hover.stepIndex != hits[0].stepIndex {
-		t.Fatalf("hover.stepIndex = %d, want %d", m.hover.stepIndex, hits[0].stepIndex)
-	}
-	// The bug this guards: the render path must resolve stepIndex back to the
-	// CORRECT current lineOffset (hits[0].lineOffset, which is >= base=4, never a
-	// raw small index like 0/1/2) — not treat stepIndex itself as a line offset
-	// into the rendered sidebar (which would land on the AGENTS header/body).
-	resolved, ok := m.hoveredSidebarLineOffset(sidebarWidth(m.width))
-	if !ok || resolved != hits[0].lineOffset {
-		t.Fatalf("hoveredSidebarLineOffset() = (%d, %v), want (%d, true)", resolved, ok, hits[0].lineOffset)
+	if m.hover.kind != hoverNone {
+		t.Fatalf("former sidebar rail must not create a hover target, got %#v", m.hover)
 	}
 }
 
@@ -207,28 +208,6 @@ func TestHoverChangesTranscriptRenderOutput(t *testing.T) {
 	}
 }
 
-func TestHoverChangesSidebarRenderOutput(t *testing.T) {
-	m := swarmSidebarTestModel(t, map[string]string{"subagent-1": "sess-1"})
-	width := m.chatColumnWidth()
-	height := m.height
-	without := strings.Join(m.renderContextSidebar(sidebarWidth(m.width), height), "\n")
-
-	hits := m.sidebarAgentSelectables(sidebarWidth(m.width))
-	if len(hits) == 0 {
-		t.Fatal("expected at least one clickable sidebar agent row")
-	}
-	updated, _ := m.Update(testMouseMotion(tea.MouseNone, width+3+1, hits[0].lineOffset))
-	m = updated.(model)
-	if m.hover.kind != hoverSidebarAgent {
-		t.Fatal("sanity check failed: hover should be set over the sidebar agent row")
-	}
-	with := strings.Join(m.renderContextSidebar(sidebarWidth(m.width), height), "\n")
-
-	if without == with {
-		t.Fatal("sidebar rendering with a hover target set should differ from without (the highlight should show)")
-	}
-}
-
 func TestHoverClearsOnWheelScroll(t *testing.T) {
 	m := mouseTestModel()
 	for i := 0; i < 80; i++ {

internal/tui/image_attach.go

@@ -1,7 +1,12 @@
 package tui
 
 import (
+	"bytes"
 	"fmt"
+	"image"
+	_ "image/gif"
+	_ "image/jpeg"
+	_ "image/png"
 	"os"
 	"path/filepath"
 	"runtime"
@@ -9,9 +14,13 @@ import (
 
 	"github.com/Gitlawb/zero/internal/imageinput"
 	"github.com/Gitlawb/zero/internal/modelregistry"
+	"github.com/Gitlawb/zero/internal/terminalpet"
 	"github.com/Gitlawb/zero/internal/zeroruntime"
+	_ "golang.org/x/image/webp"
 )
 
+const attachmentThumbnailMaxPixels = 16 << 20
+
 // droppableImageExts are the image extensions a dragged-and-dropped file may
 // carry (matched case-insensitively); PDFs are recognized separately.
 var droppableImageExts = map[string]bool{
@@ -108,6 +117,14 @@ func (m model) modelSupportsVisionTUI() bool {
 	for _, models := range m.modelPickerLiveByProvider {
 		for _, dm := range models {
 			if strings.EqualFold(strings.TrimSpace(dm.ID), trimmed) {
+				// A provider's authenticated listing may only establish which models
+				// are available, without repeating modalities. Treat an empty list as
+				// unknown rather than as an explicit image-input denial, so the
+				// curated registry/name capability fallback remains available while
+				// models.dev metadata is temporarily unavailable.
+				if len(dm.InputModalities) == 0 {
+					continue
+				}
 				for _, modality := range dm.InputModalities {
 					if strings.EqualFold(strings.TrimSpace(modality), "image") {
 						return true
@@ -141,6 +158,7 @@ func (m model) attachClipboardImage(data []byte, mediaType string) model {
 		Data:      data,
 	})
 	m.pendingImageLabels = append(m.pendingImageLabels, "clipboard")
+	m.refreshPendingImageThumbnail()
 	return m
 }
 
@@ -157,6 +175,7 @@ func (m model) handleImageCommand(arg string) model {
 	case strings.EqualFold(trimmed, "clear"):
 		m.pendingImages = nil
 		m.pendingImageLabels = nil
+		m.pendingImageThumbnails = nil
 		m.pendingDocuments = nil
 		return m.appendImageNotice("Cleared pending attachments.")
 	}
@@ -185,6 +204,7 @@ func (m model) handleImageCommand(arg string) model {
 
 	m.pendingImages = append(m.pendingImages, block)
 	m.pendingImageLabels = append(m.pendingImageLabels, filepath.Base(trimmed))
+	m.refreshPendingImageThumbnail()
 	// No "attached" system message: the composer attachment chip ([Image #N]) is
 	// the confirmation, matching the compact attach UX.
 	return m
@@ -219,6 +239,7 @@ func (m model) handleDocumentAttach(path string) model {
 		m.pendingImages = append(m.pendingImages, block)
 		m.pendingImageLabels = append(m.pendingImageLabels, label)
 	}
+	m.refreshPendingImageThumbnail()
 	// The composer attachment chip ([Doc #N] / [Image #N]) is the confirmation; no
 	// "attached" system message.
 	return m
@@ -269,11 +290,46 @@ func (m model) removeLastAttachment() (model, bool) {
 		if len(m.pendingImages) > 0 {
 			m.pendingImages = m.pendingImages[:len(m.pendingImages)-1]
 		}
+		m.refreshPendingImageThumbnail()
 		return m, true
 	}
 	return m, false
 }
 
+// refreshPendingImageThumbnail prepares only the first pending image for the
+// optional inline terminal preview. Decode failures deliberately leave the
+// attachment intact: the text chip remains the portable fallback and the model
+// still receives the original bytes.
+func (m *model) refreshPendingImageThumbnail() {
+	m.pendingImageThumbnails = nil
+	if len(m.pendingImages) == 0 {
+		return
+	}
+	count := min(len(m.pendingImages), attachmentPreviewMaxImages)
+	m.pendingImageThumbnails = make([]*terminalpet.Animation, count)
+	for index := 0; index < count; index++ {
+		preview, err := attachmentThumbnail(m.pendingImages[index])
+		if err == nil {
+			m.pendingImageThumbnails[index] = preview
+		}
+	}
+}
+
+func attachmentThumbnail(block zeroruntime.ImageBlock) (*terminalpet.Animation, error) {
+	config, _, err := image.DecodeConfig(bytes.NewReader(block.Data))
+	if err != nil {
+		return nil, err
+	}
+	if config.Width < 1 || config.Height < 1 || config.Width > attachmentThumbnailMaxPixels/config.Height {
+		return nil, fmt.Errorf("image is too large for an inline thumbnail")
+	}
+	decoded, _, err := image.Decode(bytes.NewReader(block.Data))
+	if err != nil {
+		return nil, err
+	}
+	return terminalpet.ThumbnailAnimation(decoded)
+}
+
 // renderAttachmentChips builds the pending-attachment row from both staged images
 // and staged documents, e.g. "[Image #1] [Image #2] [Doc #1]". Returns "" when
 // nothing is staged. Numbered (not named) so a long screenshot path never shows

internal/tui/image_attach_test.go

@@ -188,6 +188,22 @@ func TestSubmitThreadsImagesThenClears(t *testing.T) {
 	if len(next.pendingImages) != 0 || len(next.pendingImageLabels) != 0 {
 		t.Fatalf("submit must clear pending images, got %d/%d", len(next.pendingImages), len(next.pendingImageLabels))
 	}
+	if len(next.transcript) == 0 || next.transcript[len(next.transcript)-1].kind != rowUser {
+		t.Fatalf("submit should append a user row, got %#v", next.transcript)
+	}
+	if rendered := plainRender(t, renderUserRow(next.transcript[len(next.transcript)-1], 80)); !strings.Contains(rendered, "[Image #1]") {
+		t.Fatalf("sent image should remain visible on the user row, got:\n%s", rendered)
+	}
+	events, err := next.sessionStore.ReadEvents(next.activeSession.SessionID)
+	if err != nil {
+		t.Fatalf("ReadEvents returned error: %v", err)
+	}
+	if len(events) == 0 {
+		t.Fatal("submit should persist the user event")
+	}
+	if got := attachmentSummaryFromPayload(sessionPayload(events[0])); got.images != 1 || got.documents != 0 {
+		t.Fatalf("persisted attachment summary = %#v, want one image", got)
+	}
 
 	execCmd(cmd) // run the agent goroutine; it invokes captureRunImages
 

internal/tui/keybinding_help.go

@@ -1,5 +1,5 @@
 // keybinding_help.go renders the `?` keyboard-shortcut overlay. Zero has a
-// rich set of chord bindings (Ctrl+T effort, Ctrl+P plan, drill-in subchat,
+// rich set of chord bindings (Ctrl+T effort, drill-in subchat,
 // Shift+Tab permission mode, …) that are otherwise invisible — only learnable
 // by reading the source. A single-key `?` overlay (opened on an empty composer)
 // lists them grouped, so the keymap is discoverable the way the reference TUIs
@@ -7,11 +7,15 @@
 // model.go's Update switch; keep them in sync when a binding changes.
 //
 // Configurable bindings (toggleDetailed, toggleMouse, cycleReasoning,
-// togglePlan, toggleSidebar) pull their key label from m.keyBindings so a user
+// toggleSidebar) pull their key label from m.keyBindings so a user
 // who remaps them in config.json sees the actual chords, not the defaults.
 package tui
 
-import "strings"
+import (
+	"strings"
+
+	"charm.land/lipgloss/v2"
+)
 
 // keybinding is one row in the help overlay: the key chord and what it does.
 type keybinding struct {
@@ -53,7 +57,6 @@ func (m model) buildKeybindingGroups() []keybindingGroup {
 			bindings: []keybinding{
 				{labelOr(m.keyBindings.cycleReasoning, "Ctrl+T"), "cycle reasoning effort (auto \u2192 low \u2192 medium \u2192 high)"},
 				{"Shift+Tab", "cycle permission mode (auto \u2194 ask)"},
-				{labelOr(m.keyBindings.togglePlan, "Ctrl+P"), "expand / collapse the plan panel (when no menu is open)"},
 			},
 		},
 		{
@@ -63,7 +66,7 @@ func (m model) buildKeybindingGroups() []keybindingGroup {
 				{"\u2191 / \u2193", "scroll, or move within a popup / multi-line input"},
 				{"Ctrl+P / Ctrl+N", "previous / next item in menus (emacs-style)"},
 				{labelOr(m.keyBindings.toggleDetailed, "Ctrl+O"), "toggle the detailed (full-screen) transcript"},
-				{labelOr(m.keyBindings.toggleSidebar, "Ctrl+B"), "hide / show the right context sidebar"},
+				{labelOr(m.keyBindings.toggleSidebar, "Ctrl+B"), "show / hide run details"},
 				{labelOr(m.keyBindings.toggleMouse, "Ctrl+E"), "release the mouse to drag-select & copy text"},
 				{"Tab", "accept the autocomplete / picker selection"},
 			},
@@ -144,7 +147,7 @@ func formatKeybindingLine(binding keybinding, keyColumn int, innerWidth int) str
 func (m model) renderKeybindingHelpOverlay(width int) string {
 	overlayWidth := keybindingHelpOverlayWidth(width)
 	lines := m.renderKeybindingHelpLines(overlayWidth - 4)
-	block := styledBlockFillTitle(overlayWidth, "Keyboard Shortcuts", lines, zeroTheme.line, zeroTheme.panel)
+	block := styledBlockFillTitle(overlayWidth, "Keyboard Shortcuts", lines, zeroTheme.line, lipgloss.NewStyle())
 	return centerRenderedBlock(block, width)
 }
 

internal/tui/keybinding_help_test.go

@@ -162,22 +162,24 @@ func TestHelpOverlayKeepsTranscriptBodyBehindIt(t *testing.T) {
 }
 
 func TestCtrlBCtrlECursorNavigationBypass(t *testing.T) {
-	// 1. Empty composer: Ctrl+B should toggle sidebarHidden, Ctrl+E should toggle mouseReleased
+	// 1. Empty composer: Ctrl+B should toggle run details, Ctrl+E should toggle mouseReleased.
 	m := newModel(context.Background(), Options{ModelName: "gpt-4o"})
 	m.altScreen = true
 	m.width = 120
 	m.height = 40
 	m.transcript = append(m.transcript, transcriptRow{kind: rowToolCall, tool: "read_file", detail: "main.go"})
-	if !m.sidebarToggleAllowed() {
-		t.Fatal("sidebar toggle should be allowed")
+	if !m.runDetailsAllowed() {
+		t.Fatal("run details should be allowed")
 	}
 
-	initialSidebar := m.sidebarHidden
+	initialDetails := m.runDetailsOpen
 	updated, _ := m.Update(testKeyCtrl('b'))
 	next := updated.(model)
-	if next.sidebarHidden == initialSidebar {
-		t.Fatal("Ctrl+B on empty composer should toggle sidebarHidden")
+	if next.runDetailsOpen == initialDetails {
+		t.Fatal("Ctrl+B on empty composer should toggle run details")
 	}
+	updated, _ = next.Update(testKeyCtrl('b'))
+	next = updated.(model)
 
 	initialMouse := next.mouseReleased
 	updated, _ = next.Update(testKeyCtrl('e'))
@@ -198,11 +200,11 @@ func TestCtrlBCtrlECursorNavigationBypass(t *testing.T) {
 		t.Fatalf("composerValue = %q, want 'hello'", m2.composerValue())
 	}
 
-	initialSidebar2 := m2.sidebarHidden
+	initialDetails2 := m2.runDetailsOpen
 	updated, _ = m2.Update(testKeyCtrl('b'))
 	next2 := updated.(model)
-	if next2.sidebarHidden != initialSidebar2 {
-		t.Fatal("Ctrl+B on non-empty composer should NOT toggle sidebarHidden")
+	if next2.runDetailsOpen != initialDetails2 {
+		t.Fatal("Ctrl+B on non-empty composer should NOT toggle run details")
 	}
 
 	initialMouse2 := next2.mouseReleased
@@ -228,8 +230,8 @@ func TestRemappedToggleBindingsIgnoreComposerGuard(t *testing.T) {
 	// Avoid Ctrl+N: idle Ctrl+N is reserved as an emacs menu no-op and never
 	// reaches configurable global bindings.
 	m.keyBindings.toggleSidebar = parseBinding("ctrl+y")
-	if !m.sidebarToggleAllowed() {
-		t.Fatal("sidebar toggle should be allowed")
+	if !m.runDetailsAllowed() {
+		t.Fatal("run details should be allowed")
 	}
 
 	m = typeRunes(t, m, "hello")
@@ -247,11 +249,11 @@ func TestRemappedToggleBindingsIgnoreComposerGuard(t *testing.T) {
 		t.Fatalf("remapped toggleMouse binding should not fall through to composer input, got %q", next.composerValue())
 	}
 
-	initialSidebar := next.sidebarHidden
+	initialDetails := next.runDetailsOpen
 	updated, _ = next.Update(testKeyCtrl('y'))
 	next = updated.(model)
-	if next.sidebarHidden == initialSidebar {
-		t.Fatal("remapped Ctrl+Y toggleSidebar binding should still fire with a non-empty composer")
+	if next.runDetailsOpen == initialDetails {
+		t.Fatal("remapped Ctrl+Y toggleSidebar binding should still open run details with a non-empty composer")
 	}
 	if next.composerValue() != "hello" {
 		t.Fatalf("remapped toggleSidebar binding should not fall through to composer input, got %q", next.composerValue())
@@ -273,8 +275,8 @@ func TestExplicitDefaultChordConfigStillRequiresEmptyComposer(t *testing.T) {
 	m.transcript = append(m.transcript, transcriptRow{kind: rowToolCall, tool: "read_file", detail: "main.go"})
 	m.keyBindings.toggleMouse = parseBinding("ctrl+e")
 	m.keyBindings.toggleSidebar = parseBinding("ctrl+b")
-	if !m.sidebarToggleAllowed() {
-		t.Fatal("sidebar toggle should be allowed")
+	if !m.runDetailsAllowed() {
+		t.Fatal("run details should be allowed")
 	}
 
 	m = typeRunes(t, m, "hello")
@@ -289,10 +291,10 @@ func TestExplicitDefaultChordConfigStillRequiresEmptyComposer(t *testing.T) {
 		t.Fatal("explicit ctrl+e config should NOT toggle mouseReleased with a non-empty composer")
 	}
 
-	initialSidebar := next.sidebarHidden
+	initialDetails := next.runDetailsOpen
 	updated, _ = next.Update(testKeyCtrl('b'))
 	next = updated.(model)
-	if next.sidebarHidden != initialSidebar {
-		t.Fatal("explicit ctrl+b config should NOT toggle sidebarHidden with a non-empty composer")
+	if next.runDetailsOpen != initialDetails {
+		t.Fatal("explicit ctrl+b config should NOT toggle run details with a non-empty composer")
 	}
 }