ci: read main's sccache on every run, write it only from main

The sccache install step now runs on every event in ci.yml and
ci-test-suite.yml, and each Enable sccache step sets
SCCACHE_GHA_RW_MODE to READ_WRITE only on refs/heads/main and READ_ONLY
everywhere else (sccache docs/GHA.md; the action installs the latest
release, v0.19.0). Pull request and branch-dispatch runs, which now run
the full sharded suite, get main's compiler cache hits without writing
the refs/pull/N entries that once pushed the repo past its 10 GiB cache
cap. rust-cache save-if stays main-only and the Windows RUSTC_WRAPPER
guard from MAIN-GREEN is unchanged.

release-workflows.test.js now checks, per file, that every sccache
enable carries the off-main read-only switch and that no sccache install
is gated on main; both checks were confirmed to fail on a mutated copy.

Windows test legs keep debug 0: no test asserts on backtrace content
(only RUST_BACKTRACE pass-through lists and compile-time
Location::caller, which debug info does not affect).

Checks: node .github/scripts/release-workflows.test.js passed (211
paths, 11 wrapper cases x 12 steps, 15 hermetic checks, workflow
contracts); actionlint 1.7.12 with the repo's CI args (-ignore SC2129
-ignore SC2221 -ignore SC2222) clean on all workflows;
scripts/test_ci_migration_wiring.py 19 tests OK.

First drafted by a duplicate agent run in this worktree; reviewed and
tightened here.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

.github/AUTHOR_MAP

@@ -319,3 +319,5 @@ namezzb = sailorZ <[email protected]>
 alphapku-ux = Alpha Wu <[email protected]>
 BX166 = BX166 <[email protected]>
 c020627 = c020627 <[email protected]>
+[email protected] = Parman Mohammadalizadeh <[email protected]>
+Parman Mohammadalizadeh = Parman Mohammadalizadeh <[email protected]>

.github/scripts/release-workflows.test.js

@@ -32,6 +32,7 @@ function namedStep(source, name) {
 }
 
 const ci = read(".github/workflows/ci.yml");
+const ciSuite = read(".github/workflows/ci-test-suite.yml");
 const nightly = read(".github/workflows/nightly.yml");
 const candidate = read(".github/workflows/release-candidate.yml");
 const artifacts = read(".github/workflows/release-artifacts.yml");
@@ -46,28 +47,212 @@ const archiveInstaller = read("scripts/release/install.sh");
 const cliDispatcher = read("crates/cli/src/lib.rs");
 const runbook = read("docs/RELEASE_RUNBOOK.md");
 
-const ciTestJob = ci.slice(ci.indexOf("\n  test:\n"));
-assert.match(
-  ciTestJob,
-  /matrix\.os == 'ubuntu-latest'.*github\.event_name == 'pull_request'/,
-  "heavy pull requests must select the real Ubuntu test lane",
-);
-assert.match(
-  ciTestJob,
-  /cargo nextest run --workspace --all-features --locked --profile ci/,
-  "the Ubuntu pull-request lane must run workspace nextest",
-);
-assert.match(
-  ciTestJob,
-  /name: Linux test location \(CNB\)/,
-  "the non-PR CNB fallback must be named explicitly",
-);
+function jobBlock(source, job) {
+  const match = source.match(new RegExp(`^  ${job}:\\n([\\s\\S]*?)(?=^  \\S|(?![\\s\\S]))`, "m"));
+  assert.ok(match, `missing job: ${job}`);
+  return match[1];
+}
 
+function jobIf(source, job) {
+  const lines = jobBlock(source, job).split("\n");
+  const at = lines.findIndex((line) => /^    if:/.test(line));
+  assert.notEqual(at, -1, `${job} must declare an if`);
+  const first = lines[at].replace(/^    if:\s*/, "");
+  if (first !== ">-") return first.replace(/^'(.*)'$/, "$1");
+  const folded = [];
+  for (let i = at + 1; i < lines.length && /^      \S/.test(lines[i]); i += 1) folded.push(lines[i].trim());
+  return folded.join(" ");
+}
+
+function evaluate(expression, context) {
+  return Boolean(vm.runInNewContext(expression, context));
+}
+
+// The sharded suite: one archive per OS, partitions of it in parallel shards,
+// doctests once, and a check that the shards add up to the archive's list.
 assert.match(
-  namedStep(ciTestJob, "Build canonical executable for acceptance tests"),
+  namedStep(ciSuite, "Archive test binaries"),
+  /cargo nextest archive --workspace --all-features --locked --profile ci/,
+  "the suite must archive the same workspace, features and profile the old single run used",
+);
+assert.match(
+  namedStep(ciSuite, "Build canonical executable for acceptance tests"),
   /cargo build -p codewhale-cli --bin codewhale --all-features --locked/,
   "Engine acceptance must build the canonical executable first",
 );
+assert.match(
+  namedStep(ciSuite, "Run doctests"),
+  /cargo test --workspace --all-features --locked --doc/,
+  "nextest does not run doctests; the suite must run them once per OS",
+);
+const shardRun = namedStep(ciSuite, "Run tests");
+assert.match(shardRun, /--partition "count:\$\{\{ matrix\.shard \}\}\/\$\{\{ inputs\.shards \}\}"/);
+assert.match(shardRun, /-E "not \(\$NATIVE_FILTER\)"/, "every shard must exclude the native tests that shard 1 runs apart");
+assert.match(namedStep(ciSuite, "Run native containment tests"), /-E "\$NATIVE_FILTER"/);
+assert.match(ciSuite, /nextest-shard-count\.py check counts/, "the suite must prove the shards add up to the archive's list");
+for (const name of ["Run tests", "Run native containment tests", "Run doctests"]) {
+  const step = namedStep(ciSuite, name);
+  assert.match(step, /shell: bash/, `${name} must invoke the POSIX helper on Windows too`);
+}
+assert.match(ciSuite, /RUST_MIN_STACK: '16777216'/);
+
+// The native receipt script requires its tests in one JUnit report, so the
+// shard that runs them must select exactly the script's list.
+const receiptScript = read("scripts/compiled-host-native-receipt.py");
+const receiptNames = [
+  receiptScript.match(/^COMPILED = "([^"]+)"$/m)[1],
+  receiptScript.match(/^MEMORY = "([^"]+)"$/m)[1],
+  ...[...receiptScript.match(/^WINDOWS = \[([\s\S]*?)^\]/m)[1].matchAll(/"([^"]+)"/g)].map((m) => m[1]),
+];
+const nativeFilter = ciSuite.match(/NATIVE_FILTER: >-\n([\s\S]*?)\n    steps:/)[1];
+assert.deepEqual(
+  [...nativeFilter.matchAll(/test\(=([^)]+)\)/g)].map((m) => m[1]).sort(),
+  receiptNames.sort(),
+  "NATIVE_FILTER must list exactly the tests scripts/compiled-host-native-receipt.py requires",
+);
+
+// Shard counts: each caller's shards equals the length of its shard_list, the
+// suite's own list agrees with it, and every OS keeps a pipeline.
+const suiteCallers = {};
+for (const job of ["test-ubuntu", "test-macos", "test-windows"]) {
+  const block = jobBlock(ci, job);
+  const os = block.match(/^      os: (\S+)$/m)[1];
+  const shards = Number(block.match(/^      shards: (\d+)$/m)[1]);
+  const list = JSON.parse(block.match(/^      shard_list: '(.+)'$/m)[1]);
+  assert.deepEqual(list, Array.from({ length: shards }, (_, i) => i + 1), `${job} shard_list must be 1..shards`);
+  assert.match(block, /uses: \.\/\.github\/workflows\/ci-test-suite\.yml/);
+  assert.equal(jobIf(ci, job), jobIf(ci, "test-ubuntu"), `${job} must share the suite condition`);
+  suiteCallers[os] = shards;
+}
+assert.deepEqual(Object.keys(suiteCallers).sort(), ["macos-latest", "ubuntu-latest", "windows-latest"]);
+
+// Required contexts. The ruleset requires exactly "Lint" and "Test
+// (windows-latest)". Only Lint and the compile-only test-windows-pr job may
+// produce them; a shard, build or suite check must never share a name.
+const jobNames = (source) => [...source.matchAll(/^  [A-Za-z0-9_-]+:\n    name: (.+)$/gm)].map((m) => m[1]);
+assert.deepEqual(
+  [...jobNames(ci), ...jobNames(ciSuite)].filter((name) => /^Test \(/.test(name) || name === "Lint"),
+  ["Lint", "Test (windows-latest)"],
+  "only Lint and the compile-only Windows leg may use the required context names",
+);
+assert.match(jobBlock(ci, "test-windows-pr"), /^    name: Test \(windows-latest\)$/m);
+assert.equal(jobIf(ci, "test-windows-pr"), "github.event_name == 'pull_request'");
+assert.match(jobBlock(ci, "test-windows-pr"), /cargo check --workspace --all-features --all-targets|cargo check --workspace --all-targets --all-features --locked/);
+
+// Each gate that pull requests lost on 2026-11-07 (99cb5a0f4f) runs on a heavy
+// pull request again, plus on dispatch; a docs-only pull request keeps skipping
+// them; a scoped dispatch skips all of them.
+const gates = ["safety-gate", "msrv", "test-ubuntu", "test-macos", "test-windows", "portable-boundaries", "npm-wrapper-smoke", "mobile-smoke"];
+for (const job of gates) {
+  const guard = jobIf(ci, job);
+  const base = { inputs: { workspace_test_mode: "nextest" } };
+  const run = (event, heavy, extra = {}) =>
+    evaluate(guard, {
+      github: { event_name: event },
+      needs: { changes: { outputs: { heavy: String(heavy), mobile: "true", scoped: "false", ...extra } } },
+      ...base,
+    });
+  assert.equal(run("pull_request", true), true, `${job} must run on a heavy pull request`);
+  if (job !== "npm-wrapper-smoke") {
+    assert.equal(run("pull_request", false), false, `${job} must skip a docs-only pull request`);
+  }
+  assert.equal(run("workflow_dispatch", true), true, `${job} must run on a full dispatch`);
+  assert.equal(run("workflow_dispatch", true, { scoped: "true" }), false, `${job} must skip a scoped dispatch`);
+}
+assert.equal(
+  evaluate(jobIf(ci, "mobile-smoke"), {
+    github: { event_name: "pull_request" },
+    needs: { changes: { outputs: { heavy: "true", mobile: "false", scoped: "false" } } },
+  }),
+  false,
+  "mobile smoke keeps its path filter on pull requests",
+);
+for (const job of ["test-ubuntu", "test-macos", "test-windows"]) {
+  assert.equal(
+    evaluate(jobIf(ci, job), {
+      github: { event_name: "workflow_dispatch" },
+      inputs: { workspace_test_mode: "shared-process-twice" },
+      needs: { changes: { outputs: { heavy: "true", scoped: "false" } } },
+    }),
+    false,
+    `${job} must yield to the shared-process qualification`,
+  );
+}
+const sharedGuard = jobIf(ci, "test");
+for (const [event, mode, scoped, expected] of [
+  ["workflow_dispatch", "shared-process-twice", "false", true],
+  ["workflow_dispatch", "nextest", "false", false],
+  ["workflow_dispatch", "shared-process-twice", "true", false],
+  ["pull_request", "nextest", "false", false],
+]) {
+  assert.equal(
+    evaluate(sharedGuard, {
+      github: { event_name: event },
+      inputs: { workspace_test_mode: mode },
+      needs: { changes: { outputs: { heavy: "true", scoped } } },
+    }),
+    expected,
+    `shared-process job: ${event} ${mode} scoped=${scoped}`,
+  );
+}
+assert.equal(
+  evaluate(jobIf(ci, "scoped-test"), { needs: { changes: { outputs: { scoped: "true" } } } }),
+  true,
+);
+assert.equal(
+  evaluate(jobIf(ci, "scoped-test"), { needs: { changes: { outputs: { scoped: "false" } } } }),
+  false,
+);
+assert.match(ci, /^      expected_sha:\n        description: .*\n        required: true\n        type: string$/m, "expected_sha stays required");
+for (const input of ["crate", "filter", "os"]) {
+  assert.match(ci, new RegExp(`^      ${input}:\\n        description: .*\\n        required: false\\n`, "m"), `scoped dispatch input ${input}`);
+}
+
+// Concurrency: a new push to the same pull request or non-main branch cancels
+// the older run; runs on main and scoped dispatches never cancel anything.
+const concurrency = ci.match(/^concurrency:\n  group: (.+)\n  cancel-in-progress: (.+)$/m);
+assert.ok(concurrency, "ci.yml must declare its concurrency");
+const strip = (value) => value.replace(/^\$\{\{ /, "").replace(/ \}\}$/, "");
+const format = (template, ...args) => template.replace(/\{(\d)\}/g, (_, i) => args[Number(i)]);
+const groupOf = (context) =>
+  vm.runInNewContext(strip(concurrency[1]), { ...context, format });
+const cancelOf = (context) => vm.runInNewContext(strip(concurrency[2]), context);
+const dispatch = (ref, sha, inputs = {}) => ({
+  github: { event_name: "workflow_dispatch", ref, sha, workflow: "CI", run_id: `run-${sha}` },
+  inputs: { crate: "", filter: "", ...inputs },
+});
+const pr = (number, sha) => ({
+  github: { event_name: "pull_request", ref: `refs/pull/${number}/merge`, sha, workflow: "CI", event: { pull_request: { number } }, run_id: `run-${sha}` },
+  inputs: {},
+});
+assert.equal(groupOf(pr(7, "a")), groupOf(pr(7, "b")), "a new push to a pull request shares its group");
+assert.notEqual(groupOf(pr(7, "a")), groupOf(pr(8, "a")));
+assert.equal(cancelOf(pr(7, "a")), true);
+assert.equal(groupOf(dispatch("refs/heads/ci/x", "a")), groupOf(dispatch("refs/heads/ci/x", "b")), "a new dispatch on the same ci branch shares its group");
+assert.notEqual(groupOf(dispatch("refs/heads/ci/x", "a")), groupOf(dispatch("refs/heads/ci/y", "a")));
+assert.equal(cancelOf(dispatch("refs/heads/ci/x", "a")), true);
+assert.notEqual(groupOf(dispatch("refs/heads/main", "a")), groupOf(dispatch("refs/heads/main", "b")), "runs on main never share a group");
+assert.equal(cancelOf(dispatch("refs/heads/main", "a")), false, "runs on main never cancel");
+assert.notEqual(
+  groupOf(dispatch("refs/heads/ci/x", "a", { crate: "codewhale-tui" })),
+  groupOf(dispatch("refs/heads/ci/x", "a")),
+  "a scoped dispatch never shares the full run's group",
+);
+assert.equal(cancelOf(dispatch("refs/heads/ci/x", "a", { filter: "test(x)" })), false, "a scoped dispatch cancels nothing");
+
+// Security for pull requests from forks: the workflows use pull_request (no
+// pull_request_target), read-only permissions, no secrets, and write caches
+// only from main.
+for (const [name, source] of [["ci.yml", ci], ["ci-test-suite.yml", ciSuite]]) {
+  assert.doesNotMatch(source, /pull_request_target/, `${name} must not use pull_request_target`);
+  assert.doesNotMatch(source, /\$\{\{\s*secrets\./, `${name} must not read secrets`);
+  assert.match(source, /^permissions:\n  contents: read\n/m, `${name} must keep read-only default permissions`);
+  assert.doesNotMatch(source.replace(/^permissions:\n  contents: read\n/m, ""), /^\s+(?:contents|actions|id-token|pull-requests|packages):\s*write/m, `${name} must not grant write permissions`);
+  for (const match of source.matchAll(/Swatinem\/rust-cache@[^\n]*\n(?:\s+(?:with|cache-bin):[^\n]*\n)*\s+save-if: ([^\n]+)/g)) {
+    assert.match(match[1], /refs\/heads\/main|false/, `${name}: rust-cache must save only on main`);
+  }
+  assert.doesNotMatch(source, /actions\/cache(?:\/save)?@/, `${name} must not write caches outside rust-cache and sccache`);
+}
 const npmSmokeJob = ci.match(/^  npm-wrapper-smoke:\n([\s\S]*?)(?=^  \S)/m)?.[1];
 assert.ok(npmSmokeJob, "CI must retain the npm-wrapper job");
 assert.match(
@@ -79,13 +264,13 @@ assert.match(
   /run: node scripts\/release\/npm-wrapper-smoke\.js/,
 );
 const npmSmokeSteps = npmSmokeJob.split(/(?=^      - )/m).slice(1);
-// Exercise the workflow's actual Boolean guards. The smoke is manual-only
-// (workflow_dispatch); pull requests, pushes and schedules skip the job.
+// Exercise the workflow's actual Boolean guards. The smoke runs on pull
+// requests and dispatches (§180); pushes and schedules skip the job.
 const npmSmokeCases = [
   // name, event, heavy, OS, trusted, cache success, execute, Linux deps, CNB
-  ["own PR", "pull_request", true, "ubuntu-latest", true, true, false, false, false],
-  ["fork PR", "pull_request", true, "ubuntu-latest", false, true, false, false, false],
-  ["PR cache failure", "pull_request", true, "ubuntu-latest", false, false, false, false, false],
+  ["own PR", "pull_request", true, "ubuntu-latest", true, true, true, true, false],
+  ["fork PR", "pull_request", true, "ubuntu-latest", false, true, true, true, false],
+  ["PR cache failure", "pull_request", true, "ubuntu-latest", false, false, true, true, false],
   ["light PR", "pull_request", false, "ubuntu-latest", true, true, false, false, false],
   ["manual Ubuntu", "workflow_dispatch", true, "ubuntu-latest", true, true, true, true, false],
   ["main Ubuntu", "push", true, "ubuntu-latest", true, true, false, false, false],
@@ -95,15 +280,22 @@ const npmSmokeCases = [
   ["light main", "push", false, "ubuntu-latest", true, true, false, false, false],
   ["schedule", "schedule", true, "ubuntu-latest", true, true, false, false, false],
 ];
-// The sccache GitHub Actions backend is main-only, mirroring rust-cache's
-// save-if: pull requests never install or enable it (cache bloat, PLAN D).
+// The sccache GitHub Actions backend is read-only off main: every run reads
+// main's cache, and only main writes it (SCCACHE_GHA_RW_MODE), mirroring
+// rust-cache's save-if (cache bloat, PLAN D).
+for (const [name, source] of [["ci.yml", ci], ["ci-test-suite.yml", ciSuite]]) {
+  const enabled = source.match(/SCCACHE_GHA_ENABLED=true/g) ?? [];
+  const modes = source.match(/if \[ "\$\{GITHUB_REF\}" = refs\/heads\/main \]; then rw=READ_WRITE; else rw=READ_ONLY; fi\n\s+echo "SCCACHE_GHA_RW_MODE=\$\{rw\}"/g) ?? [];
+  assert.ok(enabled.length > 0, `${name} must enable sccache`);
+  assert.equal(modes.length, enabled.length, `${name}: every sccache enable must be read-only off main`);
+  assert.doesNotMatch(source, /sccache-action[^\n]*\n(?:[^\n]*\n){0,4}\s+if: [^\n]*github\.ref == 'refs\/heads\/main'/, `${name}: sccache must install on every run`);
+}
 const sccacheInstallStep = "mozilla-actions/[email protected]";
 for (const [label, event, heavy, os, trusted, cache, execute, linuxDeps, cnb] of npmSmokeCases) {
   const ref = event === "pull_request" ? "refs/pull/1/merge" : "refs/heads/main";
-  const onMain = ref === "refs/heads/main";
-  const installed = execute && onMain;
+  const installed = execute;
   const context = {
-    needs: { changes: { outputs: { heavy: String(heavy), trusted: String(trusted) } } },
+    needs: { changes: { outputs: { heavy: String(heavy), trusted: String(trusted), scoped: "false" } } },
     github: { event_name: event, ref },
     matrix: { os },
     steps: { sccache: { outcome: installed ? (cache ? "success" : "failure") : "skipped" } },
@@ -688,7 +880,8 @@ assert.doesNotMatch(
 // itself runs none: its parity job calls release-parity.yml.
 let hermeticInvocations = 0;
 for (const [label, workflow, expected] of [
-  ["CI", ci, 6],
+  ["CI", ci, 5],
+  ["CI test suite", ciSuite, 3],
   ["release", release, 0],
   ["release parity", parityWorkflow, 4],
   ["CNB", cnb, 3],
@@ -707,11 +900,6 @@ for (const [label, workflow, expected] of [
   }
   hermeticInvocations += commands.length;
 }
-for (const name of ["Run tests", "Run doctests"]) {
-  const step = namedStep(ciTestJob, name);
-  assert.match(step, /shell: bash/, `${name} must invoke the POSIX helper on Windows too`);
-  assert.match(step, /RUST_MIN_STACK: '16777216'/);
-}
 console.log(`Hermetic Rust workflow invocations OK: ${hermeticInvocations} checks passed.`);
 
 const nextest = read(".config/nextest.toml");
@@ -853,6 +1041,7 @@ for (const [name, source] of [
   ["release-parity.yml", parityWorkflow],
   ["release-republish.yml", republish],
   ["ci.yml", ci],
+  ["ci-test-suite.yml", ciSuite],
   ["nightly.yml", nightly],
 ]) {
   assert.deepEqual(

.github/workflows/ci-test-suite.yml

@@ -0,0 +1,388 @@
+name: CI test suite
+
+# Called by ci.yml, once per operating system, so each OS is its own pipeline:
+# one build of the whole workspace's test binaries, parallel shards that run
+# partitions of that one nextest archive, and a check that the shards together
+# ran exactly the tests the archive lists. Running per OS means Linux reports
+# as soon as Linux is done instead of waiting for the slowest build.
+#
+# Trust boundary: this runs with the caller's event. For a pull request from a
+# fork that is the read-only token and no secrets; nothing here writes a cache
+# (rust-cache and sccache save only on main) or uses a write permission. The
+# artifacts passed between jobs live inside one run.
+
+on:
+  workflow_call:
+    inputs:
+      os:
+        description: Hosted runner label
+        required: true
+        type: string
+      shards:
+        description: Number of shards, equal to the length of shard_list
+        required: true
+        type: number
+      shard_list:
+        description: JSON array of shard numbers, for example [1,2,3,4]
+        required: true
+        type: string
+      build_jobs:
+        description: CARGO_BUILD_JOBS for the test build
+        required: true
+        type: string
+      debug:
+        description: Debug-table level for the test build (CARGO_PROFILE_*_DEBUG)
+        required: true
+        type: string
+
+permissions:
+  contents: read
+
+env:
+  CARGO_TERM_COLOR: always
+  CARGO_INCREMENTAL: 0
+  RUSTFLAGS: -Dwarnings
+  RUST_MIN_STACK: 8388608
+
+jobs:
+  build:
+    name: Build
+    # A cold hosted Mac compiled for 65 minutes with one Cargo job (run
+    # 43216596942) and the old one-job cap was 210; this job only compiles, so
+    # it keeps real margin without the test run in it.
+    timeout-minutes: 150
+    runs-on: ${{ inputs.os }}
+    env:
+      # Test builds compile all features of the whole workspace. One Cargo job
+      # kept hosted runners inside memory (exit 143 on 2026-10-19 with four);
+      # trimmed debug tables shrink compiler and linker memory so Linux and
+      # Windows can run two. Assertions and every test are unchanged.
+      CARGO_BUILD_JOBS: ${{ inputs.build_jobs }}
+      CARGO_PROFILE_DEV_DEBUG: ${{ inputs.debug }}
+      CARGO_PROFILE_TEST_DEBUG: ${{ inputs.debug }}
+    steps:
+      - uses: actions/checkout@v7
+      - name: Test Windows installer PATH helper
+        if: inputs.os == 'windows-latest'
+        shell: pwsh
+        run: ./scripts/installer/update-user-path.tests.ps1
+      - name: Install NSIS for Windows installer regression
+        if: inputs.os == 'windows-latest'
+        shell: pwsh
+        run: ./scripts/installer/install-nsis.ps1
+      - name: Test Windows installer PATH regression
+        if: inputs.os == 'windows-latest'
+        shell: pwsh
+        run: ./scripts/installer/installer-path-regression.tests.ps1 -AllowUserPathMutation
+      - uses: dtolnay/rust-toolchain@stable
+      - name: Install macOS LLVM tools
+        if: inputs.os == 'macos-latest'
+        run: rustup component add llvm-tools --toolchain stable
+      - uses: mozilla-actions/[email protected]
+        id: sccache
+        continue-on-error: true
+        # Every run reads the GitHub Actions cache main wrote; only main writes (see Enable sccache).
+      - name: Enable sccache
+        if: steps.sccache.outcome == 'success'
+        shell: bash
+        run: |
+          echo "SCCACHE_GHA_ENABLED=true" >> "${GITHUB_ENV}"
+          if [ "${GITHUB_REF}" = refs/heads/main ]; then rw=READ_WRITE; else rw=READ_ONLY; fi
+          echo "SCCACHE_GHA_RW_MODE=${rw}" >> "${GITHUB_ENV}"
+          echo "RUSTC_WRAPPER=sccache" >> "${GITHUB_ENV}"
+          echo "SCCACHE_IGNORE_SERVER_IO_ERROR=1" >> "${GITHUB_ENV}"
+      - name: Install Linux system dependencies
+        if: inputs.os == 'ubuntu-latest'
+        run: |
+          bash scripts/ci-apt-install.sh libdbus-1-dev pkg-config bubblewrap apparmor-profiles
+          sh scripts/prepare-linux-test-sandbox.sh
+      - name: Ubuntu build headroom
+        # Reuse the same fixed hosted-runner provisioning as Safety and Lint.
+        # Exit 143 is a shutdown observation, not proof of OOM or timeout.
+        if: inputs.os == 'ubuntu-latest'
+        shell: bash
+        run: bash scripts/prepare-ubuntu-build-headroom.sh
+      - uses: Swatinem/rust-cache@v2
+        with:
+          cache-bin: false
+          save-if: ${{ github.ref == 'refs/heads/main' }}
+      - uses: taiki-e/install-action@nextest
+      - uses: actions/[email protected]
+        with:
+          node-version: 22
+      - name: Build canonical executable for acceptance tests
+        shell: bash
+        run: cargo build -p codewhale-cli --bin codewhale --all-features --locked
+        env:
+          RUSTC_WRAPPER: ${{ inputs.os != 'windows-latest' && env.RUSTC_WRAPPER || '' }}
+      - name: Windows Terminal clipboard-to-draft acceptance
+        if: inputs.os == 'windows-latest'
+        timeout-minutes: 5
+        shell: pwsh
+        run: node scripts/release/windows-terminal-clipboard.mjs target/debug/codewhale.exe "${{ runner.temp }}/windows-clipboard"
+      - name: Retain Windows Terminal clipboard-to-draft evidence
+        if: ${{ !cancelled() && inputs.os == 'windows-latest' }}
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: windows-clipboard-${{ github.sha }}-${{ github.run_attempt }}
+          path: ${{ runner.temp }}/windows-clipboard/
+          if-no-files-found: error
+          retention-days: 7
+      - name: Archive test binaries
+        # One compile per OS. Shards run this archive with
+        # `cargo nextest run --archive-file`, so the suite is the same test
+        # binaries, built once. Doctests are not in the archive; they run
+        # below, once, while the library artifacts are still warm.
+        shell: bash
+        run: |
+          set -euo pipefail
+          mkdir -p "$RUNNER_TEMP/test-archive" "$RUNNER_TEMP/test-expected"
+          cargo nextest archive --workspace --all-features --locked --profile ci \
+            --archive-file "$RUNNER_TEMP/test-archive/nextest-archive.tar.zst"
+          exe=codewhale
+          if [ "$RUNNER_OS" = Windows ]; then exe=codewhale.exe; fi
+          cp "target/debug/$exe" "$RUNNER_TEMP/test-archive/$exe"
+        env:
+          RUSTC_WRAPPER: ${{ inputs.os != 'windows-latest' && env.RUSTC_WRAPPER || '' }}
+      - name: Count the tests the archive selects
+        shell: bash
+        run: |
+          set -euo pipefail
+          cargo nextest list --archive-file "$RUNNER_TEMP/test-archive/nextest-archive.tar.zst" \
+            --workspace-remap . --profile ci --message-format json > "$RUNNER_TEMP/test-listing.json"
+          tests="$(python3 -I scripts/ci/nextest-shard-count.py list "$RUNNER_TEMP/test-listing.json")"
+          printf '{"os": "%s", "tests": %s, "shards": %s}\n' "${{ inputs.os }}" "$tests" "${{ inputs.shards }}" \
+            > "$RUNNER_TEMP/test-expected/expected-${{ inputs.os }}.json"
+          cat "$RUNNER_TEMP/test-expected/expected-${{ inputs.os }}.json"
+      - name: Run doctests
+        # nextest does not run doctests; this keeps them once per OS.
+        shell: bash
+        run: sh scripts/with-hermetic-test-home.sh cargo test --workspace --all-features --locked --doc
+        env:
+          RUSTC_WRAPPER: ${{ inputs.os != 'windows-latest' && env.RUSTC_WRAPPER || '' }}
+          RUST_MIN_STACK: '16777216'
+      - name: Lockfile drift guard
+        run: git diff --exit-code -- Cargo.lock
+      - name: sccache stats
+        if: steps.sccache.outcome == 'success'
+        continue-on-error: true
+        shell: bash
+        run: sccache --show-stats
+      - name: Retain test archive for the shards
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-archive-${{ inputs.os }}
+          path: ${{ runner.temp }}/test-archive/
+          if-no-files-found: error
+          retention-days: 1
+          compression-level: 0
+      - name: Retain expected test count
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-expected-${{ inputs.os }}
+          path: ${{ runner.temp }}/test-expected/
+          if-no-files-found: error
+          retention-days: 7
+
+  shard:
+    name: Shard ${{ matrix.shard }}/${{ inputs.shards }}
+    needs: build
+    timeout-minutes: 60
+    runs-on: ${{ inputs.os }}
+    strategy:
+      # A failure in one shard must not erase the others' results; the suite
+      # gate needs every conclusion.
+      fail-fast: false
+      matrix:
+        shard: ${{ fromJSON(inputs.shard_list) }}
+    env:
+      CODEWHALE_EXT_HOST_TESTS: '1'
+      CODEWHALE_EXT_HOST_BUN_TESTS: '1'
+      # Give test threads the stack the product gives itself; the reasoning is
+      # on the shared-process step above and in scripts/dev-cargo.sh.
+      RUST_MIN_STACK: '16777216'
+      # The exact-image Native containment tests (and, on Windows, the LPAC
+      # owner and profile tests) that scripts/compiled-host-native-receipt.py
+      # requires in ONE JUnit report. Shard 1 runs them in their own nextest
+      # invocation and every shard excludes them from its partition, so each
+      # still runs exactly once. release-workflows.test.js keeps this list equal
+      # to the script's.
+      NATIVE_FILTER: >-
+        package(codewhale-engine) & kind(lib) & (
+        test(=extension_host::tests::compiled_native_host_cannot_read_secrets_or_write_outside_its_data_dir) |
+        test(=extension_host::tests::compiled_native_host_memory_cap_is_enforced) |
+        test(=extension_host::windows::tests::windows_native_lpac_node_owner_boundary) |
+        test(=extension_host::windows::tests::windows_native_lpac_bun_owner_boundary) |
+        test(=extension_host::windows::tests::windows_native_lpac_compiled_owner_boundary) |
+        test(=extension_host::windows::tests::windows_native_profiles_are_distinct_and_acl_grant_refuses_junctions) |
+        test(=extension_host::windows::tests::windows_argv_and_environment_keep_exact_values_and_reject_nul) |
+        test(=extension_host::windows::tests::windows_profile_retirement_removes_only_its_grants_and_inherited_data_on_restarts) |
+        test(=extension_host::windows::tests::windows_profile_directory_budget_and_recorded_identity_refuse_before_overwrite))
+    steps:
+      - uses: actions/checkout@v7
+      - name: Point terminal failure diagnostics at the runner temp directory
+        shell: bash
+        run: echo "QA_PTY_DIAGNOSTICS_DIR=${RUNNER_TEMP}/pty-failures" >> "${GITHUB_ENV}"
+      - uses: dtolnay/rust-toolchain@stable
+      - name: Install Linux system dependencies
+        if: inputs.os == 'ubuntu-latest'
+        run: |
+          bash scripts/ci-apt-install.sh libdbus-1-dev pkg-config bubblewrap apparmor-profiles
+          sh scripts/prepare-linux-test-sandbox.sh
+      - uses: taiki-e/install-action@nextest
+      - uses: actions/[email protected]
+        # The extension-host integration tests spawn the real bundle under
+        # Node >= 22.19; CODEWHALE_EXT_HOST_TESTS makes a missing Node a
+        # failure instead of a silent skip.
+        with:
+          node-version: 22
+      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2.2
+        with:
+          bun-version: 1.4.0
+      - name: Build matching compiled-host input for required Native containment receipts
+        shell: bash
+        run: bash scripts/ci/compiled-host-test-input.sh
+      - uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8
+        with:
+          name: test-archive-${{ inputs.os }}
+          path: ${{ runner.temp }}/test-archive
+      - name: Place the canonical executable for acceptance tests
+        shell: bash
+        run: |
+          set -euo pipefail
+          mkdir -p target/debug
+          cp "$RUNNER_TEMP"/test-archive/codewhale* target/debug/
+          if [ "$RUNNER_OS" != Windows ]; then chmod +x target/debug/codewhale; fi
+      - name: Run native containment tests
+        if: matrix.shard == 1
+        shell: bash
+        run: |
+          set -euo pipefail
+          mkdir -p "$RUNNER_TEMP/test-count" "$RUNNER_TEMP/nextest-extract"
+          sh scripts/with-hermetic-test-home.sh cargo nextest run \
+            --archive-file "$RUNNER_TEMP/test-archive/nextest-archive.tar.zst" \
+            --extract-to "$RUNNER_TEMP/nextest-extract" --extract-overwrite \
+            --workspace-remap . --profile ci -E "$NATIVE_FILTER"
+          cp target/nextest/ci/junit.xml "$RUNNER_TEMP/native-junit.xml"
+          python3 -I scripts/ci/nextest-shard-count.py junit "$RUNNER_TEMP/native-junit.xml" > "$RUNNER_TEMP/native-count.txt"
+      - name: Run tests
+        # Same test binaries as `cargo test`, run by cargo-nextest: one
+        # process per test, all runner cores busy, slow tests named instead
+        # of stalling the binary. `.config/nextest.toml` serializes the PTY
+        # binary and bounds the integration binary that spawns the real
+        # executable; retries are off, so a flake is a red run, not a hidden
+        # one. This shard runs partition k of N of everything except the
+        # native containment tests; test-suite proves the shards add up to the
+        # archive's full list.
+        shell: bash
+        run: |
+          set -euo pipefail
+          mkdir -p "$RUNNER_TEMP/test-count" "$RUNNER_TEMP/nextest-extract"
+          monitor=
+          if [ "$RUNNER_OS" = Linux ]; then
+            # Headroom trace: if the runner is terminated again, the last lines
+            # say whether memory or disk ran out.
+            ( while sleep 30; do
+                echo "[headroom] $(free -m | awk '/^Mem:/{print "mem used " $3 "/" $2 " MiB"} /^Swap:/{print "swap used " $3 "/" $2 " MiB"}' | paste -sd ' ') disk free $(df -h / | awk 'NR==2{print $4}')"
+              done ) &
+            monitor=$!
+          fi
+          status=0
+          sh scripts/with-hermetic-test-home.sh cargo nextest run \
+            --archive-file "$RUNNER_TEMP/test-archive/nextest-archive.tar.zst" \
+            --extract-to "$RUNNER_TEMP/nextest-extract" --extract-overwrite \
+            --workspace-remap . --profile ci \
+            --partition "count:${{ matrix.shard }}/${{ inputs.shards }}" \
+            -E "not ($NATIVE_FILTER)" || status=$?
+          if [ -n "$monitor" ]; then kill "$monitor" 2>/dev/null || true; fi
+          if [ "$status" -ne 0 ]; then exit "$status"; fi
+          tests="$(python3 -I scripts/ci/nextest-shard-count.py junit target/nextest/ci/junit.xml)"
+          if [ -f "$RUNNER_TEMP/native-count.txt" ]; then tests=$((tests + $(cat "$RUNNER_TEMP/native-count.txt"))); fi
+          printf '{"os": "%s", "shard": %s, "tests": %s}\n' "${{ inputs.os }}" "${{ matrix.shard }}" "$tests" \
+            > "$RUNNER_TEMP/test-count/shard-${{ inputs.os }}-${{ matrix.shard }}.json"
+          cat "$RUNNER_TEMP/test-count/shard-${{ inputs.os }}-${{ matrix.shard }}.json"
+      - name: Retain sealed terminal failure diagnostics
+        if: failure()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: terminal-failures-${{ runner.os }}-${{ matrix.shard }}-${{ github.sha }}-${{ github.run_attempt }}
+          path: ${{ runner.temp }}/pty-failures/
+          include-hidden-files: true
+          if-no-files-found: ignore
+          retention-days: 7
+      - name: Export exact compiled-image Native containment receipt
+        # JUnit is from the same archive's native invocation: no second
+        # compile. The official entire CI run must be green before release can
+        # consume this artifact. Missing/changed inputs or silent test skips
+        # are red.
+        if: matrix.shard == 1
+        shell: bash
+        run: |
+          set -euo pipefail
+          test "$(git rev-parse HEAD)" = "$GITHUB_SHA"
+          git diff --exit-code
+          git diff --cached --exit-code
+          python3 scripts/compiled-host-native-receipt.py \
+            --junit "$RUNNER_TEMP/native-junit.xml" \
+            --compiled-image "$CODEWHALE_COMPILED_HOST_TEST_BINARY" \
+            --bundle crates/engine/extension-host/dist/codewhale-extension-host.mjs \
+            --bun "$CODEWHALE_COMPILED_HOST_TEST_BUN" --source-sha "$GITHUB_SHA" \
+            --image-platform "$CODEWHALE_COMPILED_HOST_TEST_PLATFORM" --image-arch "$CODEWHALE_COMPILED_HOST_TEST_ARCH" \
+            --host-sha256 "$CODEWHALE_COMPILED_HOST_TEST_SHA256" \
+            --runtime-sha256 "$CODEWHALE_COMPILED_HOST_TEST_RUNTIME_SHA256" \
+            --bundle-sha256 "$CODEWHALE_COMPILED_HOST_TEST_BUNDLE_SHA256" \
+            --output "$RUNNER_TEMP/native-compiled-host"
+      - name: Retain exact compiled image and Native receipt
+        if: matrix.shard == 1
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: native-compiled-host-${{ runner.os }}-${{ runner.arch }}
+          path: ${{ runner.temp }}/native-compiled-host/
+          if-no-files-found: error
+          retention-days: 30
+      - name: Lockfile drift guard
+        run: git diff --exit-code -- Cargo.lock
+      - name: Retain shard test count
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-count-${{ inputs.os }}-${{ matrix.shard }}
+          path: ${{ runner.temp }}/test-count/
+          if-no-files-found: error
+          retention-days: 7
+
+  check:
+    # The job that answers "did this OS's whole suite pass": the build and every
+    # shard succeeded, and the shards together ran exactly the tests the archive
+    # lists. Not a required check (§180).
+    name: Suite check
+    needs: [build, shard]
+    if: '!cancelled()'
+    timeout-minutes: 10
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+        with:
+          sparse-checkout: scripts/ci
+      - name: Every build and shard succeeded
+        shell: bash
+        env:
+          BUILD_RESULT: ${{ needs.build.result }}
+          SHARD_RESULT: ${{ needs.shard.result }}
+        run: |
+          echo "build: ${BUILD_RESULT}"
+          echo "shard: ${SHARD_RESULT}"
+          if [ "${BUILD_RESULT}" != success ] || [ "${SHARD_RESULT}" != success ]; then
+            echo "::error::The sharded suite did not complete successfully."
+            exit 1
+          fi
+      - uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8
+        with:
+          name: test-expected-${{ inputs.os }}
+          path: counts
+      - uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8
+        with:
+          pattern: test-count-${{ inputs.os }}-*
+          path: counts
+          merge-multiple: true
+      - name: Shards ran every listed test exactly once
+        run: python3 -I scripts/ci/nextest-shard-count.py check counts

.github/workflows/ci.yml

@@ -16,13 +16,32 @@ on:
         options:
           - nextest
           - shared-process-twice
+      crate:
+        description: Scoped run, in a few minutes. One workspace package (for example codewhale-tui); with crate or filter set only the scoped test runs, not the full suite
+        required: false
+        default: ''
+        type: string
+      filter:
+        description: Scoped run, in a few minutes. A nextest filterset (for example 'test(auto_review)'), alone or with crate; with crate or filter set only the scoped test runs
+        required: false
+        default: ''
+        type: string
+      os:
+        description: Operating systems for a scoped run, comma separated (ubuntu-latest, macos-latest, windows-latest, or all); ignored by a full run
+        required: false
+        default: ubuntu-latest
+        type: string
 
 permissions:
   contents: read
 
+# A new push to a pull request, or a new dispatch on the same non-main branch
+# (an agent's ci/<task> branch), cancels the older run still in progress.
+# Runs on main are keyed by SHA and never cancel each other, and a scoped
+# dispatch gets its own group so it cannot cancel a full run on the same branch.
 concurrency:
-  group: ${{ github.event_name == 'pull_request' && format('ci-pr-{0}', github.event.pull_request.number) || format('ci-{0}-{1}', github.workflow, github.sha) }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+  group: ${{ github.event_name == 'pull_request' && format('ci-pr-{0}', github.event.pull_request.number) || (github.event_name == 'workflow_dispatch' && (inputs.crate != '' || inputs.filter != '') && format('ci-scoped-{0}', github.run_id)) || (github.ref != 'refs/heads/main' && format('ci-ref-{0}', github.ref)) || format('ci-{0}-{1}', github.workflow, github.sha) }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' && !(github.event_name == 'workflow_dispatch' && (inputs.crate != '' || inputs.filter != '')) }}
 
 env:
   CARGO_TERM_COLOR: always
@@ -45,6 +64,8 @@ jobs:
       mobile: ${{ steps.detect.outputs.mobile }}
       actions: ${{ steps.detect.outputs.actions }}
       trusted: ${{ steps.trust.outputs.trusted }}
+      scoped: ${{ steps.scope.outputs.scoped }}
+      scoped_os: ${{ steps.scope.outputs.scoped_os }}
     steps:
       - name: Classify event trust
         id: trust
@@ -64,6 +85,48 @@ jobs:
           else
             echo "trusted=false" >> "$GITHUB_OUTPUT"
           fi
+      - name: Classify scoped dispatch
+        id: scope
+        shell: bash
+        env:
+          EVENT_NAME: ${{ github.event_name }}
+          SCOPE_CRATE: ${{ inputs.crate }}
+          SCOPE_FILTER: ${{ inputs.filter }}
+          SCOPE_OS: ${{ inputs.os }}
+        run: |
+          set -euo pipefail
+          # A dispatch with a crate or a filter runs only the scoped test job.
+          # Inputs reach the shell only through env, and the crate and OS
+          # names are validated before anything uses them.
+          scoped=false
+          scoped_os='["ubuntu-latest"]'
+          if [[ "${EVENT_NAME}" == "workflow_dispatch" && ( -n "${SCOPE_CRATE}" || -n "${SCOPE_FILTER}" ) ]]; then
+            scoped=true
+            if [[ -n "${SCOPE_CRATE}" && ! "${SCOPE_CRATE}" =~ ^[A-Za-z0-9_-]+$ ]]; then
+              echo "::error::crate must be a package name (letters, digits, - and _)." >&2
+              exit 1
+            fi
+            oses=()
+            IFS=',' read -r -a requested <<< "${SCOPE_OS:-ubuntu-latest}"
+            for name in "${requested[@]}"; do
+              name="${name//[[:space:]]/}"
+              case "${name}" in
+                ubuntu|ubuntu-latest|linux) oses+=("ubuntu-latest") ;;
+                macos|macos-latest) oses+=("macos-latest") ;;
+                windows|windows-latest) oses+=("windows-latest") ;;
+                all) oses+=("ubuntu-latest" "macos-latest" "windows-latest") ;;
+                "") ;;
+                *)
+                  echo "::error::os entries must be ubuntu-latest, macos-latest, windows-latest or all." >&2
+                  exit 1
+                  ;;
+              esac
+            done
+            if [[ "${#oses[@]}" -eq 0 ]]; then oses=("ubuntu-latest"); fi
+            scoped_os="$(printf '%s\n' "${oses[@]}" | sort -u | jq -R . | jq -sc .)"
+          fi
+          echo "scoped=${scoped}" >> "${GITHUB_OUTPUT}"
+          echo "scoped_os=${scoped_os}" >> "${GITHUB_OUTPUT}"
       - uses: actions/checkout@v7
         with:
           fetch-depth: 0
@@ -197,6 +260,8 @@ jobs:
 
   versions:
     name: Version drift
+    needs: changes
+    if: needs.changes.outputs.scoped != 'true'
     timeout-minutes: 15
     runs-on: ubuntu-latest
     steps:
@@ -274,6 +339,8 @@ jobs:
 
   plugin-conversion:
     name: Plugin conversion
+    needs: changes
+    if: needs.changes.outputs.scoped != 'true'
     timeout-minutes: 5
     runs-on: ubuntu-latest
     steps:
@@ -293,6 +360,8 @@ jobs:
 
   integrations:
     name: Integrations
+    needs: changes
+    if: needs.changes.outputs.scoped != 'true'
     timeout-minutes: 15
     runs-on: ubuntu-latest
     steps:
@@ -349,7 +418,7 @@ jobs:
   extension-host-runtimes:
     name: Extension host runtimes (${{ matrix.os }})
     needs: changes
-    if: needs.changes.outputs.heavy == 'true'
+    if: needs.changes.outputs.heavy == 'true' && needs.changes.outputs.scoped != 'true'
     timeout-minutes: 15
     strategy:
       fail-fast: false
@@ -388,6 +457,8 @@ jobs:
 
   vscode-extension:
     name: VS Code extension
+    needs: changes
+    if: needs.changes.outputs.scoped != 'true'
     timeout-minutes: 15
     runs-on: ubuntu-latest
     defaults:
@@ -421,7 +492,7 @@ jobs:
   safety-gate:
     name: Safety gate
     needs: changes
-    if: github.event_name == 'workflow_dispatch' && needs.changes.outputs.heavy == 'true'
+    if: needs.changes.outputs.heavy == 'true' && needs.changes.outputs.scoped != 'true'
     timeout-minutes: 30
     runs-on: ubuntu-latest
     steps:
@@ -431,16 +502,18 @@ jobs:
           toolchain: stable
       - uses: mozilla-actions/[email protected]
         id: sccache
-        # The GitHub Actions cache backend is main-only, mirroring
-        # rust-cache's save-if: PR runs wrote thousands of refs/pull/N
-        # entries that pushed the repo past its 10 GiB cache cap.
-        if: github.ref == 'refs/heads/main'
+        # Every run reads the cache main wrote; only main writes it
+        # (SCCACHE_GHA_RW_MODE in Enable sccache), mirroring rust-cache's
+        # save-if. PR runs once wrote thousands of refs/pull/N entries that
+        # pushed the repo past its 10 GiB cache cap.
         continue-on-error: true
       - name: Enable sccache
         if: steps.sccache.outcome == 'success'
         shell: bash
         run: |
           echo "SCCACHE_GHA_ENABLED=true" >> "${GITHUB_ENV}"
+          if [ "${GITHUB_REF}" = refs/heads/main ]; then rw=READ_WRITE; else rw=READ_ONLY; fi
+          echo "SCCACHE_GHA_RW_MODE=${rw}" >> "${GITHUB_ENV}"
           echo "RUSTC_WRAPPER=sccache" >> "${GITHUB_ENV}"
           echo "SCCACHE_IGNORE_SERVER_IO_ERROR=1" >> "${GITHUB_ENV}"
       - name: Install Linux system dependencies
@@ -475,6 +548,7 @@ jobs:
   lint:
     name: Lint
     needs: changes
+    if: needs.changes.outputs.scoped != 'true'
     # Measured on 89ee629e with runner headroom: clippy 10 min, runtime-contract
     # budget 16 min, and persistence-backlog still running at the old 45-minute
     # cancellation. Commands, filters and budgets are unchanged.
@@ -494,13 +568,15 @@ jobs:
         # Cache bootstrap failures (e.g. GitHub 504s fetching the sccache
         # binary) degrade to an uncached build instead of failing product CI.
         continue-on-error: true
-        # Main-only GitHub Actions cache backend; see the Safety gate job.
-        if: needs.changes.outputs.heavy == 'true' && github.ref == 'refs/heads/main'
+        # Every run reads the GitHub Actions cache main wrote; only main writes (see Enable sccache).
+        if: needs.changes.outputs.heavy == 'true'
       - name: Enable sccache
         if: needs.changes.outputs.heavy == 'true' && steps.sccache.outcome == 'success'
         shell: bash
         run: |
           echo "SCCACHE_GHA_ENABLED=true" >> "${GITHUB_ENV}"
+          if [ "${GITHUB_REF}" = refs/heads/main ]; then rw=READ_WRITE; else rw=READ_ONLY; fi
+          echo "SCCACHE_GHA_RW_MODE=${rw}" >> "${GITHUB_ENV}"
           echo "RUSTC_WRAPPER=sccache" >> "${GITHUB_ENV}"
           echo "SCCACHE_IGNORE_SERVER_IO_ERROR=1" >> "${GITHUB_ENV}"
       - name: Install Linux system dependencies
@@ -725,7 +801,7 @@ jobs:
     # fail the build there while stable stays green (#6543).
     name: MSRV check (1.89)
     needs: changes
-    if: github.event_name == 'workflow_dispatch' && needs.changes.outputs.heavy == 'true'
+    if: needs.changes.outputs.heavy == 'true' && needs.changes.outputs.scoped != 'true'
     timeout-minutes: 45
     runs-on: ubuntu-latest
     steps:
@@ -746,7 +822,7 @@ jobs:
   workflow-rlm-cache:
     name: Workflow RLM cache
     needs: changes
-    if: needs.changes.outputs.workflow == 'true'
+    if: needs.changes.outputs.workflow == 'true' && needs.changes.outputs.scoped != 'true'
     timeout-minutes: 30
     runs-on: ubuntu-latest
     steps:
@@ -754,14 +830,15 @@ jobs:
       - uses: dtolnay/rust-toolchain@stable
       - uses: mozilla-actions/[email protected]
         id: sccache
-        # Main-only GitHub Actions cache backend; see the Safety gate job.
-        if: github.ref == 'refs/heads/main'
+        # Every run reads the GitHub Actions cache main wrote; only main writes (see Enable sccache).
         continue-on-error: true
       - name: Enable sccache
         if: steps.sccache.outcome == 'success'
         shell: bash
         run: |
           echo "SCCACHE_GHA_ENABLED=true" >> "${GITHUB_ENV}"
+          if [ "${GITHUB_REF}" = refs/heads/main ]; then rw=READ_WRITE; else rw=READ_ONLY; fi
+          echo "SCCACHE_GHA_RW_MODE=${rw}" >> "${GITHUB_ENV}"
           echo "RUSTC_WRAPPER=sccache" >> "${GITHUB_ENV}"
           echo "SCCACHE_IGNORE_SERVER_IO_ERROR=1" >> "${GITHUB_ENV}"
       - uses: Swatinem/rust-cache@v2
@@ -772,261 +849,64 @@ jobs:
         run: sh scripts/with-hermetic-test-home.sh cargo test -p codewhale-workflow --locked
 
   test:
-    name: Test
+    # Manual shared-process qualification only (workspace_test_mode =
+    # shared-process-twice): the GH6698 evidence of two libtest passes at one
+    # exact revision on one hosted Ubuntu runner. Every other run executes the
+    # suite through test-build, test-shard and test-suite below.
+    name: Shared-process tests
     needs: changes
-    if: github.event_name == 'workflow_dispatch'
-    # Contexts "Test (ubuntu-latest)" / "Test (macos-latest)" /
-    # "Test (windows-latest)" derive from job name + matrix.os and are
-    # independent of runs-on. For light changes the macOS/Windows legs only
-    # echo a skip line, so run them on ubuntu instead of queueing for scarce
-    # macOS/Windows runners. Pull requests run only the Linux leg here; the
-    # required "Test (windows-latest)" context comes from test-windows-pr.
-    # The ternary is safe: matrix.os is always a non-empty literal, so
-    # runs-on can never evaluate to empty.
-    # A cold GitHub-hosted Mac spent 77-80 minutes in Test on 2026-09-23
-    # (fork PRs #6431, #6417), too close to the old 90-minute limit.
-    # On 2026-10-04 a PR leg spent 111 minutes compiling with no cache and
-    # was cancelled at 120 with 12,356 tests passed and none failed. The
-    # limit stays a literal (release-workflows.test.js, #5496); 210 bounds
-    # cold compilation and the complete suite without disabling test deadlines.
+    if: github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice' && needs.changes.outputs.heavy == 'true' && needs.changes.outputs.scoped != 'true'
+    # A cold GitHub-hosted runner spent 111 minutes compiling with no cache on
+    # 2026-10-04. The limit stays a literal (release-workflows.test.js, #5496);
+    # 210 bounds cold compilation and both complete passes.
     timeout-minutes: 210
-    # macOS legs go to the self-hosted Mac ONLY when all three hold: the
-    # change is heavy, the event is trusted (not a fork PR), and the
-    # CW_SELF_HOSTED_MAC repo variable is 'true'. That variable is the kill
-    # switch: unset it and every leg falls back to GitHub-hosted runners
-    # immediately, with no commit — important because an offline
-    # self-hosted runner queues jobs forever, which is worse than a slow one.
-    runs-on: ${{ needs.changes.outputs.heavy != 'true' && 'ubuntu-latest' || (matrix.os == 'macos-latest' && needs.changes.outputs.trusted == 'true' && vars.CW_SELF_HOSTED_MAC == 'true' && fromJSON('["self-hosted","macOS","ARM64","codewhale-mac"]')) || matrix.os }}
-    strategy:
-      # A failure on one desktop platform must not erase evidence from the
-      # other one. We need both conclusions to diagnose and release safely.
-      fail-fast: false
-      matrix:
-        # Pull requests run the Linux workspace suite only; the macOS and
-        # Windows suites run in final validation. The explicit manual
-        # libtest qualification uses one hosted Ubuntu job, never a fork PR or
-        # self-hosted runner; normal dispatches keep all three legs.
-        os: ${{ fromJSON((github.event_name == 'pull_request' || (github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice')) && '["ubuntu-latest"]' || '["ubuntu-latest","macos-latest","windows-latest"]') }}
+    runs-on: ubuntu-latest
     steps:
-      - name: Skip tests for light change
-        if: needs.changes.outputs.heavy != 'true'
-        run: echo "No executable Rust changes detected; preserving required Test context."
       - uses: actions/checkout@v7
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
-      - name: Test Windows installer PATH helper
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'windows-latest'
-        shell: pwsh
-        run: ./scripts/installer/update-user-path.tests.ps1
-      - name: Install NSIS for Windows installer regression
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'windows-latest'
-        shell: pwsh
-        run: ./scripts/installer/install-nsis.ps1
-      - name: Test Windows installer PATH regression
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'windows-latest'
-        shell: pwsh
-        run: ./scripts/installer/installer-path-regression.tests.ps1 -AllowUserPathMutation
       - uses: dtolnay/rust-toolchain@stable
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
-      - name: Install macOS LLVM tools
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'macos-latest'
-        run: rustup component add llvm-tools --toolchain stable
-      - name: Omit macOS build debug metadata
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'macos-latest'
-        shell: bash
-        # Match the existing full-workspace CNB gate. Keep debug assertions and
-        # every test; only disposable build debug tables change on this lane.
-        run: printf '%s\n' 'CARGO_PROFILE_DEV_DEBUG=0' 'CARGO_PROFILE_TEST_DEBUG=0' >> "$GITHUB_ENV"
       - uses: mozilla-actions/[email protected]
         id: sccache
         continue-on-error: true
-        # Main-only GitHub Actions cache backend; see the Safety gate job.
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request') && github.ref == 'refs/heads/main'
+        # Every run reads the GitHub Actions cache main wrote; only main writes (see Enable sccache).
       - name: Enable sccache
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request') && steps.sccache.outcome == 'success'
+        if: steps.sccache.outcome == 'success'
         shell: bash
         run: |
           echo "SCCACHE_GHA_ENABLED=true" >> "${GITHUB_ENV}"
+          if [ "${GITHUB_REF}" = refs/heads/main ]; then rw=READ_WRITE; else rw=READ_ONLY; fi
+          echo "SCCACHE_GHA_RW_MODE=${rw}" >> "${GITHUB_ENV}"
           echo "RUSTC_WRAPPER=sccache" >> "${GITHUB_ENV}"
           echo "SCCACHE_IGNORE_SERVER_IO_ERROR=1" >> "${GITHUB_ENV}"
       - name: Install Linux system dependencies
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'ubuntu-latest' && (github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
         run: |
           bash scripts/ci-apt-install.sh libdbus-1-dev pkg-config bubblewrap apparmor-profiles
           sh scripts/prepare-linux-test-sandbox.sh
       - name: Ubuntu build headroom
         # Reuse the same fixed hosted-runner provisioning as Safety and Lint.
         # Exit 143 is a shutdown observation, not proof of OOM or timeout.
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'ubuntu-latest' && (github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
         shell: bash
         run: bash scripts/prepare-ubuntu-build-headroom.sh
       - uses: Swatinem/rust-cache@v2
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
         with:
           cache-bin: false
           save-if: ${{ github.ref == 'refs/heads/main' }}
-      - uses: taiki-e/install-action@nextest
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
-      - name: Check portable config policy boundary
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'ubuntu-latest' && (github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
-        shell: bash
-        run: |
-          python3 -B scripts/test_check_command_config_proof.py
-          sh scripts/check-portable-config.sh
-      - name: Check portable core navigation boundary
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'ubuntu-latest' && (github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
-        shell: bash
-        run: |
-          python3 -B scripts/test_check_command_core_navigation_proof.py
-          sh scripts/check-portable-core-navigation.sh
       - uses: actions/[email protected]
         # The extension-host integration tests spawn the real bundle under
         # Node >= 22.19; CODEWHALE_EXT_HOST_TESTS below makes a missing Node a
         # failure instead of a silent skip.
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
         with:
           node-version: 22
       - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2.2
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
         with:
           bun-version: 1.4.0
       - name: Build matching compiled-host input for required Native containment receipts
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
         shell: bash
-        run: |
-          set -euo pipefail
-          bun_binary="$(bun -p 'process.execPath')"
-          host_binary="$(node -p "require('path').join(process.env.RUNNER_TEMP, 'codewhale-extension-host' + (process.platform === 'win32' ? '.exe' : ''))")"
-          compiled_info="$(node crates/engine/extension-host/compile-host.mjs --bun "$bun_binary" --output "$host_binary")"
-          printf 'CODEWHALE_COMPILED_HOST_TEST_BINARY=%s\n' "$host_binary" >> "$GITHUB_ENV"
-          node - "$host_binary" "$bun_binary" "$compiled_info" >> "$GITHUB_ENV" <<'JS'
-          const fs = require('node:fs'), crypto = require('node:crypto');
-          const digest = (file) => crypto.createHash('sha256').update(fs.readFileSync(file)).digest('hex');
-          const info = JSON.parse(process.argv[4]);
-          if (!info.platform || !info.arch || info.platform !== info.compiler?.platform || info.arch !== info.compiler?.arch) throw new Error('image/compiler identity mismatch');
-          console.log('CODEWHALE_COMPILED_HOST_TEST_PLATFORM=' + info.platform);
-          console.log('CODEWHALE_COMPILED_HOST_TEST_ARCH=' + info.arch);
-          console.log('CODEWHALE_COMPILED_HOST_TEST_SHA256=' + digest(process.argv[2]));
-          console.log('CODEWHALE_COMPILED_HOST_TEST_BUN=' + process.argv[3]);
-          console.log('CODEWHALE_COMPILED_HOST_TEST_RUNTIME_SHA256=' + digest(process.argv[3]));
-          console.log('CODEWHALE_COMPILED_HOST_TEST_BUNDLE_SHA256=' + digest('crates/engine/extension-host/dist/codewhale-extension-host.mjs'));
-          JS
-          # The required hermetic full invocation executes the shared actual
-          # compiled Native secret/history/write scenario on each OS; Windows
-          # additionally requires Node/Bun/compiled LPAC owner/reparse probes.
-          # Missing requested compiled input or a failed sandbox is red.
-      - name: Hold this machine's build lock (self-hosted)
-        # The self-hosted Mac is also a developer machine: local agents build
-        # through scripts/dev-cargo.sh, which holds this lock, and two Cargo
-        # builds at once exhaust its memory. Opt-in: the runner's `.env` names
-        # the same file as CODEWHALE_BUILD_LOCK_FILE. The holder is a
-        # background process; the runner kills orphans when the job ends, so a
-        # cancelled or crashed job cannot leave the lock held.
-        # (`env.*` in `if:` cannot see the runner's `.env`, so the opt-in is
-        # checked in the script.)
-        if: needs.changes.outputs.heavy == 'true' && runner.environment == 'self-hosted'
-        shell: bash
-        run: |
-          if [ -z "${CODEWHALE_BUILD_LOCK_FILE:-}" ]; then
-            echo "CODEWHALE_BUILD_LOCK_FILE is not set on this runner; building without the machine lock."
-            exit 0
-          fi
-          hold="$RUNNER_TEMP/cw-build-lock.hold"
-          ready="$RUNNER_TEMP/cw-build-lock.ready"
-          log="$RUNNER_TEMP/cw-build-lock.log"
-          touch "$hold"
-          rm -f "$ready"
-          # The single quotes are deliberate: the inner sh expands $1/$2.
-          # shellcheck disable=SC2016
-          nohup python3 scripts/build-lock.py "$CODEWHALE_BUILD_LOCK_FILE" -- \
-            sh -c 'touch "$1"; while [ -e "$2" ]; do sleep 2; done' _ "$ready" "$hold" \
-            >"$log" 2>&1 &
-          shown=0
-          until [ -e "$ready" ]; do
-            if [ "$shown" -eq 0 ] && [ -s "$log" ]; then cat "$log"; shown=1; fi
-            sleep 2
-          done
-          cat "$log"
-          # Scripts inside this job already run under the lock.
-          echo "CODEWHALE_BUILD_LOCK_HELD=1" >> "$GITHUB_ENV"
+        run: bash scripts/ci/compiled-host-test-input.sh
       - name: Build canonical executable for acceptance tests
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
         shell: bash
         run: cargo build -p codewhale-cli --bin codewhale --all-features --locked
-        env:
-          RUSTC_WRAPPER: ${{ matrix.os != 'windows-latest' && env.RUSTC_WRAPPER || '' }}
-      - name: Windows Terminal clipboard-to-draft acceptance
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'windows-latest'
-        timeout-minutes: 5
-        shell: pwsh
-        run: node scripts/release/windows-terminal-clipboard.mjs target/debug/codewhale.exe "${{ runner.temp }}/windows-clipboard"
-      - name: Retain Windows Terminal clipboard-to-draft evidence
-        if: ${{ !cancelled() && matrix.os == 'windows-latest' && needs.changes.outputs.heavy == 'true' }}
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
-        with:
-          name: windows-clipboard-${{ github.sha }}-${{ github.run_attempt }}
-          path: ${{ runner.temp }}/windows-clipboard/
-          if-no-files-found: error
-          retention-days: 7
-      - name: Run tests
-        # Same test binaries as `cargo test`, run by cargo-nextest: one
-        # process per test, all runner cores busy, slow tests named instead
-        # of stalling the binary. `.config/nextest.toml` serializes the PTY
-        # binary and bounds the integration binary that spawns the real
-        # executable; retries are off, so a flake is a red run, not a hidden
-        # one. nextest does not run doctests — the next step keeps them.
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request') && !(github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice')
-        shell: bash
-        run: |
-          monitor=
-          if [ "$RUNNER_OS" = Linux ]; then
-            # Headroom trace: if the runner is terminated again, the last lines
-            # say whether memory or disk ran out.
-            ( while sleep 30; do
-                echo "[headroom] $(free -m | awk '/^Mem:/{print "mem used " $3 "/" $2 " MiB"} /^Swap:/{print "swap used " $3 "/" $2 " MiB"}' | paste -sd ' ') disk free $(df -h / | awk 'NR==2{print $4}')"
-              done ) &
-            monitor=$!
-          fi
-          status=0
-          sh scripts/with-hermetic-test-home.sh cargo nextest run --workspace --all-features --locked --profile ci || status=$?
-          if [ -n "$monitor" ]; then kill "$monitor" 2>/dev/null || true; fi
-          exit "$status"
-        env:
-          CARGO_BUILD_JOBS: '1'
-          QA_PTY_DIAGNOSTICS_DIR: ${{ runner.temp }}/pty-failures
-          CODEWHALE_EXT_HOST_TESTS: '1'
-          CODEWHALE_EXT_HOST_BUN_TESTS: '1'
-          # sccache 0.17 panics resolving its config directory under the
-          # isolated Windows home before Cargo can compile or run any test.
-          # Bypass only that optional cache; keep the full suite and isolation.
-          RUSTC_WRAPPER: ${{ matrix.os != 'windows-latest' && env.RUSTC_WRAPPER || '' }}
-          # Give test threads the stack the product gives itself. main.rs runs
-          # the owner thread and every tokio worker at
-          # CODEWHALE_MAIN_STACK_BYTES (32 MiB) because the engine and
-          # runtime-thread futures are genuinely deep. `#[tokio::test]` builds
-          # its own runtime and never sees that, so tests ran the same code on
-          # ~2 MiB (~1 MiB on Windows) — a configuration that never ships.
-          # That gap is what aborted the whole Windows test binary with
-          # STATUS_STACK_OVERFLOW in start_turn_accepts_dynamic_tools_and_
-          # environment_id, masking every other Windows result (78afd8d3d4
-          # Box::pin'd that one frame; the mismatch itself remained). std reads
-          # this for any thread spawned without an explicit size, which covers
-          # both libtest's per-test threads and tokio's workers. Test threads
-          # hold 16 MiB: the engine-only chains they run measured a ~2.5 MiB
-          # debug high-water, while the full ~16.5 MiB UI-loop chain that
-          # forced 32 MiB lives in spawned binaries, which size their own
-          # stacks explicitly and never read this variable.
-          RUST_MIN_STACK: '16777216'
-      - name: Retain sealed terminal failure diagnostics
-        if: failure()
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
-        with:
-          name: terminal-failures-${{ runner.os }}-${{ github.sha }}-${{ github.run_attempt }}
-          path: ${{ runner.temp }}/pty-failures/
-          include-hidden-files: true
-          if-no-files-found: ignore
-          retention-days: 7
       - name: Shared-process workspace qualification
-        if: github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice' && matrix.os == 'ubuntu-latest'
+        if: github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice'
         shell: bash
         env:
           CARGO_BUILD_JOBS: '1'
@@ -1128,83 +1008,193 @@ jobs:
           cat "$evidence/results.txt"
           exit "$failed"
       - name: Retain shared-process qualification evidence
-        if: always() && github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice' && matrix.os == 'ubuntu-latest'
+        if: always() && github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice'
         uses: actions/upload-artifact@v7
         with:
           name: shared-process-workspace-${{ github.sha }}-${{ github.run_attempt }}
           path: ${{ runner.temp }}/shared-process-workspace/
           if-no-files-found: error
           retention-days: 30
-      - name: Export exact compiled-image Native containment receipt
-        # JUnit is from the same full invocation: no second compile/test run.
-        # The official entire CI run must be green before release can consume
-        # this artifact. Missing/changed inputs or silent test skips are red.
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request') && !(github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice')
+
+  # One sharded pipeline per OS (ci-test-suite.yml). Shard counts follow the
+  # measured serial test time of each OS (2026-11-12, run 43216596942: Linux 19
+  # min, macOS 24 min, Windows 25 min of test execution, on top of 30 to 65
+  # minutes of single-job compilation), so a shard is five to eight minutes of
+  # tests plus setup. Hosted macOS is the scarce pool, so it gets three shards.
+  # The caller names ("Sharded tests (...)") never equal the required
+  # "Test (windows-latest)" context, which test-windows-pr still produces on
+  # every pull request.
+  test-ubuntu:
+    name: Sharded tests (ubuntu-latest)
+    needs: changes
+    if: >-
+      needs.changes.outputs.heavy == 'true' &&
+      needs.changes.outputs.scoped != 'true' &&
+      (github.event_name == 'pull_request' || github.event_name == 'workflow_dispatch') &&
+      !(github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice')
+    uses: ./.github/workflows/ci-test-suite.yml
+    with:
+      os: ubuntu-latest
+      shards: 4
+      shard_list: '[1,2,3,4]'
+      build_jobs: '2'
+      debug: line-tables-only
+
+  test-macos:
+    name: Sharded tests (macos-latest)
+    needs: changes
+    if: >-
+      needs.changes.outputs.heavy == 'true' &&
+      needs.changes.outputs.scoped != 'true' &&
+      (github.event_name == 'pull_request' || github.event_name == 'workflow_dispatch') &&
+      !(github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice')
+    uses: ./.github/workflows/ci-test-suite.yml
+    with:
+      os: macos-latest
+      shards: 3
+      shard_list: '[1,2,3]'
+      build_jobs: '1'
+      debug: '0'
+
+  test-windows:
+    name: Sharded tests (windows-latest)
+    needs: changes
+    if: >-
+      needs.changes.outputs.heavy == 'true' &&
+      needs.changes.outputs.scoped != 'true' &&
+      (github.event_name == 'pull_request' || github.event_name == 'workflow_dispatch') &&
+      !(github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice')
+    uses: ./.github/workflows/ci-test-suite.yml
+    with:
+      os: windows-latest
+      shards: 4
+      shard_list: '[1,2,3,4]'
+      build_jobs: '2'
+      debug: '0'
+
+  portable-boundaries:
+    name: Portable boundaries
+    needs: changes
+    if: >-
+      needs.changes.outputs.heavy == 'true' &&
+      needs.changes.outputs.scoped != 'true' &&
+      (github.event_name == 'pull_request' || github.event_name == 'workflow_dispatch')
+    timeout-minutes: 45
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+      - uses: dtolnay/rust-toolchain@stable
+      - uses: mozilla-actions/[email protected]
+        id: sccache
+        continue-on-error: true
+        # Every run reads the GitHub Actions cache main wrote; only main writes (see Enable sccache).
+      - name: Enable sccache
+        if: steps.sccache.outcome == 'success'
+        shell: bash
+        run: |
+          echo "SCCACHE_GHA_ENABLED=true" >> "${GITHUB_ENV}"
+          if [ "${GITHUB_REF}" = refs/heads/main ]; then rw=READ_WRITE; else rw=READ_ONLY; fi
+          echo "SCCACHE_GHA_RW_MODE=${rw}" >> "${GITHUB_ENV}"
+          echo "RUSTC_WRAPPER=sccache" >> "${GITHUB_ENV}"
+          echo "SCCACHE_IGNORE_SERVER_IO_ERROR=1" >> "${GITHUB_ENV}"
+      - name: Install Linux system dependencies
+        run: |
+          bash scripts/ci-apt-install.sh libdbus-1-dev pkg-config bubblewrap apparmor-profiles
+          sh scripts/prepare-linux-test-sandbox.sh
+      - uses: Swatinem/rust-cache@v2
+        with:
+          cache-bin: false
+          save-if: ${{ github.ref == 'refs/heads/main' }}
+      - uses: taiki-e/install-action@nextest
+      - uses: actions/[email protected]
+        with:
+          node-version: 22
+      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2.2
+        with:
+          bun-version: 1.4.0
+      - name: Check portable config policy boundary
+        shell: bash
+        run: |
+          python3 -B scripts/test_check_command_config_proof.py
+          sh scripts/check-portable-config.sh
+      - name: Check portable core navigation boundary
+        shell: bash
+        run: |
+          python3 -B scripts/test_check_command_core_navigation_proof.py
+          sh scripts/check-portable-core-navigation.sh
+
+  scoped-test:
+    # workflow_dispatch with `crate` and/or `filter`: one package or one nextest
+    # filterset on the chosen OSes (default ubuntu-latest) instead of the full
+    # suite. `changes` skips every other job for such a run. The build uses the
+    # same flags as the full build; only `-p` and `-E` narrow what runs.
+    name: Scoped test (${{ matrix.os }})
+    needs: changes
+    if: needs.changes.outputs.scoped == 'true'
+    timeout-minutes: 90
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: ${{ fromJSON(needs.changes.outputs.scoped_os) }}
+    env:
+      CARGO_BUILD_JOBS: ${{ matrix.os == 'macos-latest' && '1' || '2' }}
+      CARGO_PROFILE_DEV_DEBUG: ${{ matrix.os == 'ubuntu-latest' && 'line-tables-only' || '0' }}
+      CARGO_PROFILE_TEST_DEBUG: ${{ matrix.os == 'ubuntu-latest' && 'line-tables-only' || '0' }}
+      CODEWHALE_EXT_HOST_TESTS: '1'
+      CODEWHALE_EXT_HOST_BUN_TESTS: '1'
+      RUST_MIN_STACK: '16777216'
+      SCOPE_CRATE: ${{ inputs.crate }}
+      SCOPE_FILTER: ${{ inputs.filter }}
+    steps:
+      - uses: actions/checkout@v7
+      - name: Point terminal failure diagnostics at the runner temp directory
+        shell: bash
+        run: echo "QA_PTY_DIAGNOSTICS_DIR=${RUNNER_TEMP}/pty-failures" >> "${GITHUB_ENV}"
+      - uses: dtolnay/rust-toolchain@stable
+      - name: Install Linux system dependencies
+        if: matrix.os == 'ubuntu-latest'
+        run: |
+          bash scripts/ci-apt-install.sh libdbus-1-dev pkg-config bubblewrap apparmor-profiles
+          sh scripts/prepare-linux-test-sandbox.sh
+      - uses: Swatinem/rust-cache@v2
+        with:
+          cache-bin: false
+          save-if: false
+      - uses: taiki-e/install-action@nextest
+      - uses: actions/[email protected]
+        with:
+          node-version: 22
+      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2.2
+        with:
+          bun-version: 1.4.0
+      - name: Build matching compiled-host input for required Native containment receipts
+        shell: bash
+        run: bash scripts/ci/compiled-host-test-input.sh
+      - name: Build canonical executable for acceptance tests
+        # Acceptance tests in the TUI, engine and CLI crates, and any run that
+        # names no crate, look for the codewhale binary next to the test
+        # binaries; a narrow run on another crate does not need it.
+        if: env.SCOPE_CRATE == '' || env.SCOPE_CRATE == 'codewhale-tui' || env.SCOPE_CRATE == 'codewhale-engine' || env.SCOPE_CRATE == 'codewhale-cli'
+        shell: bash
+        run: cargo build -p codewhale-cli --bin codewhale --all-features --locked
+      - name: Run the scoped tests
         shell: bash
         run: |
           set -euo pipefail
-          test "$(git rev-parse HEAD)" = "$GITHUB_SHA"
-          git diff --exit-code
-          git diff --cached --exit-code
-          python3 scripts/compiled-host-native-receipt.py \
-            --junit target/nextest/ci/junit.xml \
-            --compiled-image "$CODEWHALE_COMPILED_HOST_TEST_BINARY" \
-            --bundle crates/engine/extension-host/dist/codewhale-extension-host.mjs \
-            --bun "$CODEWHALE_COMPILED_HOST_TEST_BUN" --source-sha "$GITHUB_SHA" \
-            --image-platform "$CODEWHALE_COMPILED_HOST_TEST_PLATFORM" --image-arch "$CODEWHALE_COMPILED_HOST_TEST_ARCH" \
-            --host-sha256 "$CODEWHALE_COMPILED_HOST_TEST_SHA256" \
-            --runtime-sha256 "$CODEWHALE_COMPILED_HOST_TEST_RUNTIME_SHA256" \
-            --bundle-sha256 "$CODEWHALE_COMPILED_HOST_TEST_BUNDLE_SHA256" \
-            --output "$RUNNER_TEMP/native-compiled-host"
-      - name: Retain exact compiled image and Native receipt
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request') && !(github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice')
+          args=(--all-features --locked --profile ci --no-tests=fail)
+          if [ -n "${SCOPE_CRATE}" ]; then args+=(-p "${SCOPE_CRATE}"); else args+=(--workspace); fi
+          if [ -n "${SCOPE_FILTER}" ]; then args+=(-E "${SCOPE_FILTER}"); fi
+          sh scripts/with-hermetic-test-home.sh cargo nextest run "${args[@]}"
+      - name: Retain sealed terminal failure diagnostics
+        if: failure()
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         with:
-          name: native-compiled-host-${{ runner.os }}-${{ runner.arch }}
-          path: ${{ runner.temp }}/native-compiled-host/
-          if-no-files-found: error
-          retention-days: 30
-      - name: Run doctests
-        # The shared-process command already includes every workspace doctest.
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request') && !(github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice')
-        shell: bash
-        run: sh scripts/with-hermetic-test-home.sh cargo test --workspace --all-features --locked --doc
-        env:
-          RUSTC_WRAPPER: ${{ matrix.os != 'windows-latest' && env.RUSTC_WRAPPER || '' }}
-          RUST_MIN_STACK: '16777216'
-      # The Ubuntu lint lane validates non-RSS backlog fields. Run the same
-      # source-bound measurement on macOS so loss or growth of RSS evidence
-      # fails closed instead of becoming an unsupported-field skip.
-      # Only on the self-hosted Mac: there it reuses the warm build. Every
-      # hosted Mac leg (fork PRs, or any PR with CW_SELF_HOSTED_MAC off) runs
-      # it in the separate `macos-budget` job with its own timeout, because
-      # on a cold hosted Mac it pushed Test past 90 minutes.
-      - name: Check persistence-backlog RSS budget
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'macos-latest' && needs.changes.outputs.trusted == 'true' && vars.CW_SELF_HOSTED_MAC == 'true'
-        run: python3 scripts/check-persistence-backlog-budget.py
-      - name: Lockfile drift guard
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
-        run: git diff --exit-code -- Cargo.lock
-      - name: Run Offline Eval Harness
-        # The eval harness is OS-independent prompt/composition checking;
-        # running it once (on the faster macOS leg, warm from the test build)
-        # instead of once per desktop OS keeps the coverage while taking
-        # ~2min off the Windows critical path. Self-hosted Mac only; hosted
-        # Mac legs run it in `macos-budget` (see the RSS step above).
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'macos-latest' && needs.changes.outputs.trusted == 'true' && vars.CW_SELF_HOSTED_MAC == 'true'
-        run: cargo run -p codewhale-cli --bin codewhale --all-features -- eval
-      - name: sccache stats
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request') && steps.sccache.outcome == 'success'
-        continue-on-error: true
-        shell: bash
-        run: sccache --show-stats
-      - name: Linux test location (CNB)
-        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'ubuntu-latest' && github.event_name != 'workflow_dispatch' && github.event_name != 'pull_request'
-        run: echo "Linux workspace tests run on CNB for non-PR release/main pushes; pull requests run directly on Ubuntu."
-      - name: Release this machine's build lock (self-hosted)
-        if: always() && runner.environment == 'self-hosted'
-        shell: bash
-        run: rm -f "$RUNNER_TEMP/cw-build-lock.hold"
+          name: terminal-failures-scoped-${{ runner.os }}-${{ github.sha }}-${{ github.run_attempt }}
+          path: ${{ runner.temp }}/pty-failures/
+          include-hidden-files: true
+          if-no-files-found: ignore
+          retention-days: 7
 
   test-windows-pr:
     name: Test (windows-latest)
@@ -1239,7 +1229,7 @@ jobs:
             echo "## Test (windows-latest) on a pull request"
             echo
             echo "Compiled every workspace target for Windows with warnings denied and ran the installer PATH helper tests."
-            echo "The Windows and macOS test suites run in final validation, before a release, not on pull requests."
+            echo "The full Windows test suite runs beside this check as Sharded tests (windows-latest); it is not a required check."
           } >> "$GITHUB_STEP_SUMMARY"
 
   macos-budget:
@@ -1252,15 +1242,15 @@ jobs:
     # macOS leg runs on the self-hosted Mac (trusted event and
     # CW_SELF_HOSTED_MAC == 'true'), it runs these two steps on the warm
     # build instead. The name keeps "(fork PR)" so check contexts stay stable.
-    # Hosted macOS allows only five concurrent jobs per account, and this job
-    # doubled every pull request's claim on them, queueing the required Test
-    # (macos-latest) leg for hours. So pull requests skip it and every push to
-    # main still runs it; a regression shows up on the merge that caused it.
+    # Hosted macOS allows only five concurrent jobs per account, and the macOS
+    # test build and shards already take most of them, so pull requests skip
+    # this job and every dispatch (main-landing issues one per push to main)
+    # still runs it; a regression shows up on the merge that caused it. The
+    # sharded macOS suite never runs on the self-hosted Mac, so these gates no
+    # longer depend on CW_SELF_HOSTED_MAC.
     name: macOS budget and eval (fork PR)
     needs: changes
-    # The explicit Ubuntu-only qualification has no warm Test macOS leg, so
-    # retain these gates on the hosted fallback even when self-hosting is on.
-    if: needs.changes.outputs.heavy == 'true' && github.event_name != 'pull_request' && ((github.event_name == 'workflow_dispatch' && inputs.workspace_test_mode == 'shared-process-twice') || !(needs.changes.outputs.trusted == 'true' && vars.CW_SELF_HOSTED_MAC == 'true'))
+    if: needs.changes.outputs.heavy == 'true' && needs.changes.outputs.scoped != 'true' && github.event_name != 'pull_request'
     # Cold hosted builds consumed 73 minutes before eval could start (F run
     # 37497498829). Match Test's compile allowance; RSS/eval limits stay intact.
     timeout-minutes: 210
@@ -1282,9 +1272,10 @@ jobs:
   npm-wrapper-smoke:
     name: npm wrapper smoke
     needs: changes
-    if: github.event_name == 'workflow_dispatch'
-    # Same ternary rationale as the Test job: light legs only echo, so keep
-    # them off macOS/Windows runners. On pull_request the matrix is
+    if: needs.changes.outputs.scoped != 'true' && (github.event_name == 'pull_request' || github.event_name == 'workflow_dispatch')
+    # Light legs only echo, so keep them off macOS/Windows runners. The
+    # ternary is safe: matrix.os is always a non-empty literal. On
+    # pull_request the matrix is
     # ubuntu-only, so the required "npm wrapper smoke (ubuntu-latest)"
     # context is unaffected. Heavy pull requests execute the Ubuntu smoke
     # here; their branches may not be mirrored to CNB.
@@ -1310,13 +1301,15 @@ jobs:
       - uses: mozilla-actions/[email protected]
         id: sccache
         continue-on-error: true
-        # Main-only GitHub Actions cache backend; see the Safety gate job.
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request') && github.ref == 'refs/heads/main'
+        # Every run reads the GitHub Actions cache main wrote; only main writes (see Enable sccache).
+        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
       - name: Enable sccache
-        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request') && steps.sccache.outcome == 'success'
+        if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request') && steps.sccache.outcome == 'success' && matrix.os != 'windows-latest'
         shell: bash
         run: |
           echo "SCCACHE_GHA_ENABLED=true" >> "${GITHUB_ENV}"
+          if [ "${GITHUB_REF}" = refs/heads/main ]; then rw=READ_WRITE; else rw=READ_ONLY; fi
+          echo "SCCACHE_GHA_RW_MODE=${rw}" >> "${GITHUB_ENV}"
           echo "RUSTC_WRAPPER=sccache" >> "${GITHUB_ENV}"
           echo "SCCACHE_IGNORE_SERVER_IO_ERROR=1" >> "${GITHUB_ENV}"
       - uses: actions/[email protected]
@@ -1358,8 +1351,14 @@ jobs:
   mobile-smoke:
     name: Mobile runtime smoke
     needs: changes
-    # Manual (workflow_dispatch) only; the release candidate builds android-arm64.
-    if: github.event_name == 'workflow_dispatch' && needs.changes.outputs.heavy == 'true'
+    # Not a required PR context. Pull requests run it only when the mobile
+    # runtime surface changed (see the `mobile` filter above); every dispatch,
+    # which main-landing issues for each push to main, runs it unconditionally
+    # as the pre-release safety net.
+    if: >-
+      needs.changes.outputs.scoped != 'true' &&
+      needs.changes.outputs.heavy == 'true' &&
+      (github.event_name != 'pull_request' || needs.changes.outputs.mobile == 'true')
     timeout-minutes: 30
     runs-on: ubuntu-latest
     steps:
@@ -1367,14 +1366,15 @@ jobs:
       - uses: dtolnay/rust-toolchain@stable
       - uses: mozilla-actions/[email protected]
         id: sccache
-        # Main-only GitHub Actions cache backend; see the Safety gate job.
-        if: github.ref == 'refs/heads/main'
+        # Every run reads the GitHub Actions cache main wrote; only main writes (see Enable sccache).
         continue-on-error: true
       - name: Enable sccache
         if: steps.sccache.outcome == 'success'
         shell: bash
         run: |
           echo "SCCACHE_GHA_ENABLED=true" >> "${GITHUB_ENV}"
+          if [ "${GITHUB_REF}" = refs/heads/main ]; then rw=READ_WRITE; else rw=READ_ONLY; fi
+          echo "SCCACHE_GHA_RW_MODE=${rw}" >> "${GITHUB_ENV}"
           echo "RUSTC_WRAPPER=sccache" >> "${GITHUB_ENV}"
           echo "SCCACHE_IGNORE_SERVER_IO_ERROR=1" >> "${GITHUB_ENV}"
       - name: Install Linux system dependencies
@@ -1401,7 +1401,7 @@ jobs:
   actionlint:
     name: Workflow lint
     needs: changes
-    if: needs.changes.outputs.actions == 'true'
+    if: needs.changes.outputs.actions == 'true' && needs.changes.outputs.scoped != 'true'
     timeout-minutes: 15
     runs-on: ubuntu-latest
     steps:
@@ -1418,7 +1418,8 @@ jobs:
   # Check documentation builds without warnings
   docs:
     name: Documentation
-    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
+    needs: changes
+    if: needs.changes.outputs.scoped != 'true' && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
     timeout-minutes: 60
     runs-on: ubuntu-latest
     steps:
@@ -1439,17 +1440,17 @@ jobs:
   cargo-deny:
     name: cargo-deny
     needs: changes
-    if: github.event_name == 'workflow_dispatch'
+    if: github.event_name == 'workflow_dispatch' && needs.changes.outputs.scoped != 'true'
     uses: ./.github/workflows/cargo-deny.yml
 
   security-audit:
     name: Security audit
     needs: changes
-    if: github.event_name == 'workflow_dispatch'
+    if: github.event_name == 'workflow_dispatch' && needs.changes.outputs.scoped != 'true'
     uses: ./.github/workflows/security-audit.yml
 
   ohos:
     name: OpenHarmony
     needs: changes
-    if: github.event_name == 'workflow_dispatch'
+    if: github.event_name == 'workflow_dispatch' && needs.changes.outputs.scoped != 'true'
     uses: ./.github/workflows/ohos.yml

.github/workflows/nightly.yml

@@ -73,7 +73,7 @@ jobs:
         id: sccache
         continue-on-error: true
       - name: Enable sccache
-        if: steps.sccache.outcome == 'success'
+        if: steps.sccache.outcome == 'success' && runner.os != 'Windows'
         shell: bash
         run: |
           {

.github/workflows/release-artifacts.yml

@@ -178,7 +178,7 @@ jobs:
         id: sccache
         continue-on-error: true
       - name: Enable sccache
-        if: steps.sccache.outcome == 'success'
+        if: steps.sccache.outcome == 'success' && runner.os != 'Windows'
         shell: bash
         run: |
           {

CHANGELOG.md

@@ -11,12 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **Non-ASCII file names:** `/diff`, the `@git` and `@diff` mentions and the Runtime API workspace diff now show paths with Chinese, emoji and other non-ASCII characters as written instead of as quoted octal escapes, and the turn context no longer lists the workspace root as an empty "Active paths" entry. Thanks [@luochen211](https://github.com/luochen211) (PR 7317).
 - **Session names after a crash, and keep-forever snapshot retention:** a session name saved right after a crash that cut off the previous session-index line is no longer lost, because the new entry now starts on its own line; and a very large `[snapshots] max_age_days` (such as `9223372036854775807` for "keep forever") no longer wraps around and deletes every undo snapshot at session start. Thanks [@luochen211](https://github.com/luochen211) (PR 7316).
 - **Blank environment variables:** exporting a variable empty (for example `CODEWHALE_MODEL=` from a compose `${VAR:-}` template) no longer hides its legacy alias. `DEEPSEEK_MODEL`, `DEEPSEEK_BASE_URL`, `KIMI_BASE_URL`, `DEEPSEEK_FORCE_HTTP1`, `DEEPSEEK_STREAM_OPEN_TIMEOUT_SECS` and the other provider alias variables now apply as they do when the primary is unset. Thanks [@luochen211](https://github.com/luochen211) (PR 7315).
-- **Qwen Code as an external agent:** Codewhale now finds an installed Qwen Code CLI (`qwen`, 0.6.1 or newer) and can run it as a session over ACP with `qwen --acp`. `GET /v1/agents/external` lists it, an older install is reported as needing `npm i -g @qwen-code/qwen-code@latest`, and sign-in stays inside Qwen Code (`/auth`). Thanks [@MannXo](https://github.com/MannXo) (PR 7293).
-- **Telemetry setting default:** the settings schema API reports telemetry's default as on, matching what Codewhale does when you have not chosen.
-- **Auto routing abstention:** when the decision model marks a tier, effort or shadow answer `abstained: true`, Auto no longer acts on it, even with `min_confidence = 0`: an abstained tier takes the local fallback, an abstained effort keeps the tier and drops only the effort, and the routing receipt lists the abstained questions.
-- **Plugin index (Runtime API):** a new `GET /v1/apps/plugin-index` route lists plugins, skills, connectors, hooks and hand-written commands with kind, source and state, and `/v1/commands` rows say which plugin (`plugin_id`) added a command and whether a command came from the project (`workspace_sourced`) (CW-8092).
-- **Model commands and routing:** `codewhale model list` now lists every custom endpoint you have configured, under its own name. `codewhale model resolve` no longer refuses a model on a custom endpoint, router or local server whose model list has not been fetched yet; once a list is fetched, a model missing from it is still refused. Automatic routing marks a context window as verified only when the route itself supplies it, and no longer reports a guessed output limit.
-- **ACP:** when a plugin tool asks the core to run a tool that needs approval, the editor now gets a `session/request_permission` on the plugin tool's call that names the nested tool and its input; before, the prompt ended with an internal error (CW-8050).
+- **Qwen Code as an external agent:** Codewhale now finds an installed Qwen Code CLI (`qwen`, 0.6.1 or newer) and can run it as a session over ACP with `qwen --acp`. `GET /v1/agents/external` lists it, an older install is reported as needing `npm i -g @qwen-code/qwen-code@latest`, and sign-in stays inside Qwen Code (`/auth`). Thanks [@MannXo](https://github.com/MannXo) (#7293).
 - **README and contributor credit:** the repository front page now opens the way the website does: the line "The model can be anyone's. The agent should be yours.", one sentence on what Codewhale is, the install command and one picture, with reference detail moved into the linked guides; the 18 translated READMEs follow the same structure and say they are machine-drafted. The contributor wall and the website now count the same 433 people (407 GitHub accounts and the commit authors whose email is not linked to an account), where the website had counted accounts only. `DEPENDENCY_SECURITY.md` moved into `docs/dependency-maintenance.md`, and `.github/SUPPORT.md` says where to ask for help.
 - **Website Plugins page:** The website's Plugins page now describes what the released version does, and a labelled section says what 0.10.3 adds: one Plugins place, Standard and Creator mode, and the Permissions control.
 - **Plugin docs and plugin-creator:** Docs now say everything you add is a plugin. The bundled plugin-creator skill no longer tells an agent never to trust or enable a plugin (in Full Access it may, for one it wrote and installed from its project), points code and screen plugins at cordis-plugin-development, and an untouched copy from 0.10.2 now upgrades. The Chinese extension and Runtime API docs now say editor ACP sessions get plugin tools and configured MCP servers.

CONTRIBUTING.md

@@ -165,7 +165,7 @@ before starting a change; preserve any local work when updating your branch.
 
 - Write tests for new functionality
 - Run the tests near your change (see [Fast local loop](#fast-local-loop));
-  your pull request runs the Linux workspace suite and a Windows build for
+  your pull request runs the full test suite on Linux, macOS and Windows for
   you (see [What happens after you open a pull request](#what-happens-after-you-open-a-pull-request))
 - Colocate unit tests beside the code they cover (standard Rust `#[cfg(test)]`
   modules), and add integration tests under the owning crate's `tests/`
@@ -174,8 +174,8 @@ before starting a change; preserve any local work when updating your branch.
 
 ### Pre-push verification
 
-These are the Rust commands your pull request runs on Linux (the `Lint` and
-`Test (ubuntu-latest)` checks). You do not need all of them before every
+These are the Rust commands your pull request runs on Linux (the `Lint` check
+and the Linux shards of `Sharded tests (ubuntu-latest)`). You do not need all of them before every
 push: run `cargo fmt`, then check and test the crates you touched (see
 [Fast local loop](#fast-local-loop)). Run the full set locally when a change
 spans many crates, or let the pull request run it for you:
@@ -215,7 +215,7 @@ cargo install cargo-nextest --locked      # once
 scripts/dev-test.sh tui
 scripts/dev-cargo.sh nextest run --workspace --all-features --locked
 
-# 4. The Linux suite your PR runs:
+# 4. The suite your PR runs on Linux (hosted CI runs it as parallel shards):
 cargo test --workspace --all-features --locked
 ```
 
@@ -340,6 +340,9 @@ maintainer to approve the first run for a brand-new GitHub account.
 | --- | --- | --- |
 | `Lint` (required) | `cargo fmt --check`, clippy on every target, and the fast drift checks (locales, READMEs, provider registry, dead-code and blocking-call budgets) | Run `cargo fmt --all` and the clippy command in [Pre-push verification](#pre-push-verification); the log names the file and the check |
 | `Test (windows-latest)` (required) | Compiles every workspace target for Windows with warnings denied, and the installer PATH helper tests | Usually a `cfg(windows)` path or an import only Windows sees; the log has the compiler error |
+| `Sharded tests (ubuntu-latest)`, `(macos-latest)`, `(windows-latest)` | The full workspace test suite, built once per OS and run as parallel shards of one nextest archive, plus the doctests; each OS ends with a `Suite check` that fails if the shards did not run every test exactly once | Open the failing `Shard k/N` job; the log names the test. The same test reproduces locally with `cargo nextest run -E 'test(name)'` |
+| `Safety gate`, `MSRV check (1.89)`, `npm wrapper smoke`, `Portable boundaries` | The hermetic safety and authorization tests, a build on the minimum Rust version, the npm wrapper install smoke and the portable-core boundary checks | The log names the failing test or the compiler error |
+| `Mobile runtime smoke` | The `codewhale serve --mobile` HTTP and event-stream smoke, only when the mobile runtime surface changed | The log shows the failing request |
 | `Version drift` | Version files, the `feat:` release-note rule, release helper tests and contributor credit | The credit step only reports: a maintainer adds your credit when the PR merges |
 
 Smaller checks cover the VS Code extension, integrations, the extension host
@@ -347,11 +350,15 @@ and plugin conversion, plus workflow lint when you change `.github/workflows`.
 A documentation-only change skips the Rust builds but still reports the
 required checks, so it can merge.
 
-Your pull request does not run the test suites, the safety gate, MSRV, the npm
-wrapper smoke, the slow runtime-contract and persistence-backlog measurements,
-the dependency audits or the OpenHarmony build. Maintainers run those once per
-release, on the exact commit being released. If that run finds a problem your
-change introduced, we fix it on `main`; we will not ask you to chase it.
+Only `Lint` and `Test (windows-latest)` are required. Every other job above is
+informational for a contributor's pull request: a red one tells you and the
+maintainers something, and never blocks the merge. Your pull request does not
+run the slow runtime-contract and persistence-backlog measurements, the macOS
+budget and eval job, the dependency audits or the OpenHarmony build; those run
+on `main` and for each release, on the exact commit. If one of them finds a
+problem your change introduced, we fix it on `main`; we will not ask you to
+chase it. A newer push to your branch cancels the older run of the same pull
+request, so the runners always work on your latest commit.
 
 A red check that your change did not cause is not your job to fix. We rerun it
 or fix it on `main`, and we never close a PR because CI is slow or flaky. Your

Cargo.lock

@@ -1179,7 +1179,6 @@ dependencies = [
  "agent-client-protocol",
  "agent-client-protocol-schema",
  "anyhow",
- "arboard",
  "async-stream",
  "async-trait",
  "axum",

crates/app-server/src/acp_server/runtime.rs

@@ -47,18 +47,6 @@ impl Drop for TurnClaim {
         }
     }
 }
-fn admitted_call<'a>(
-    calls: &'a HashMap<String, PendingToolCall>,
-    execution: &str,
-) -> Option<(&'a str, &'a PendingToolCall)> {
-    let mut id = execution;
-    loop {
-        if let Some((key, call)) = calls.get_key_value(id) {
-            return Some((key.as_str(), call));
-        }
-        id = id.rsplit_once('.')?.0;
-    }
-}
 fn update(session: &str, update: acp::SessionUpdate) -> Outgoing {
     Outgoing::Update(acp::SessionNotification::new(session.to_string(), update))
 }
@@ -431,50 +419,27 @@ impl PromptRun {
                         && pending.turn_id == turn
                         && pending.tool_call_id.as_deref() == Some(execution)
                 }) {
-                    let (shown, call) = admitted_call(calls, execution)
+                    let call = calls
+                        .get(execution)
                         .ok_or_else(|| anyhow!("Approval projection lacks admitted tool start"))?;
                     let id = uuid::Uuid::new_v4().to_string();
-                    let nested = shown != execution;
-                    let nested_call;
-                    let shown_call = if nested {
-                        nested_call = PendingToolCall {
-                            execution_id: execution.to_string(),
-                            name: p
-                                .get("tool_name")
-                                .and_then(Value::as_str)
-                                .unwrap_or(&call.name)
-                                .to_string(),
-                            input: p.get("input").cloned().unwrap_or(Value::Null),
-                        };
-                        &nested_call
-                    } else {
-                        call
-                    };
-                    let title = tool_call_title(shown_call);
-                    let description = p
+                    let title = tool_call_title(call);
+                    let text = p
                         .get("description")
                         .and_then(Value::as_str)
-                        .filter(|text| !text.trim().is_empty());
-                    let summary = p
-                        .get("summary")
-                        .and_then(Value::as_str)
-                        .filter(|text| nested && !text.trim().is_empty());
-                    let text = match (summary, description) {
-                        (Some(summary), Some(description)) => format!("{summary}\n{description}"),
-                        (Some(text), None) | (None, Some(text)) => text.to_string(),
-                        (None, None) => title.clone(),
-                    };
-                    let mut fields = acp::ToolCallUpdateFields::new()
-                        .title(title)
-                        .kind(tool_call_kind(shown_call))
-                        .raw_input((!shown_call.input.is_null()).then(|| shown_call.input.clone()))
-                        .content(vec![acp::ToolCallContent::from(text)]);
-                    if !nested {
-                        fields = fields.status(acp::ToolCallStatus::Pending);
-                    }
+                        .filter(|text| !text.trim().is_empty())
+                        .map_or_else(|| title.clone(), str::to_string);
                     let request = acp::RequestPermissionRequest::new(
                         session.to_string(),
-                        acp::ToolCallUpdate::new(shown.to_string(), fields),
+                        acp::ToolCallUpdate::new(
+                            execution.to_string(),
+                            acp::ToolCallUpdateFields::new()
+                                .title(title)
+                                .kind(tool_call_kind(call))
+                                .status(acp::ToolCallStatus::Pending)
+                                .raw_input((!call.input.is_null()).then(|| call.input.clone()))
+                                .content(vec![acp::ToolCallContent::from(text)]),
+                        ),
                         vec![
                             acp::PermissionOption::new(
                                 "allow-once",

crates/app-server/src/runtime_api.rs

@@ -129,7 +129,6 @@ mod members;
 mod memory_lens;
 mod mobile;
 mod plans;
-mod plugin_index;
 mod plugins;
 pub(crate) mod review;
 mod secrets;
@@ -3373,7 +3372,6 @@ pub fn build_router(state: RuntimeApiState) -> Router {
         .route("/v1/skills/{name}/audit", get(audit_skill_api))
         .route("/v1/apps/mcp/tools", get(list_mcp_tools))
         .route("/v1/apps/plugins", get(plugins::list_plugins))
-        .route("/v1/apps/plugin-index", get(plugin_index::get_plugin_index))
         .route("/v1/apps/avatars", get(avatars::list_avatars))
         .route(
             "/v1/apps/avatars/{handle}/atlases/{page}",
@@ -5877,10 +5875,6 @@ struct CommandCatalogEntry {
     #[serde(skip_serializing_if = "Option::is_none")]
     origin: Option<String>,
     #[serde(skip_serializing_if = "Option::is_none")]
-    plugin_id: Option<String>,
-    #[serde(skip_serializing_if = "std::ops::Not::not")]
-    workspace_sourced: bool,
-    #[serde(skip_serializing_if = "Option::is_none")]
     registration_id: Option<String>,
 }
 
@@ -5939,8 +5933,6 @@ fn command_catalog(
             shadowed_by,
             shadowed_aliases,
             origin: None,
-            plugin_id: None,
-            workspace_sourced: false,
             registration_id: None,
         });
     }
@@ -5964,8 +5956,6 @@ fn command_catalog(
             shadowed_by: None,
             shadowed_aliases: Vec::new(),
             origin: None,
-            plugin_id: command.plugin_id.clone(),
-            workspace_sourced: command.workspace_sourced,
             registration_id: None,
         });
     }
@@ -6048,8 +6038,6 @@ async fn list_commands(
                 shadowed_by: None,
                 shadowed_aliases: Vec::new(),
                 origin: Some(reference.origin.clone()),
-                plugin_id: Some(reference.plugin_id.clone()),
-                workspace_sourced: false,
                 registration_id: query
                     .thread_id
                     .as_deref()

crates/app-server/src/runtime_api/plugin_index.rs

@@ -1,489 +0,0 @@
-use std::collections::{BTreeSet, HashMap};
-use std::path::{Path as FsPath, PathBuf};
-
-use axum::Json;
-use axum::extract::{Query, State};
-use serde::Serialize;
-use serde_json::Value;
-
-use super::plugins::{self, PluginSummaryEntry};
-use super::{ApiError, CommandsQuery, HooksQuery, RuntimeApiState};
-
-const MAX_ADDED_NAMES: usize = 512;
-
-#[derive(Debug, Serialize)]
-pub(super) struct PluginIndexResponse {
-    workspace: String,
-    items: Vec<IndexItem>,
-    unavailable: Vec<IndexNote>,
-    problems: Vec<IndexNote>,
-}
-
-#[derive(Debug, Serialize)]
-struct IndexNote {
-    kind: &'static str,
-    message: String,
-}
-
-#[derive(Debug, Serialize)]
-struct IndexItem {
-    id: String,
-    kind: &'static str,
-    name: String,
-    description: Option<String>,
-    source: &'static str,
-    state: &'static str,
-    labels: Vec<&'static str>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    plugin: Option<String>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    adds: Option<PluginAdds>,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    tier: Option<&'static str>,
-    owner: &'static str,
-    row: Value,
-}
-
-#[derive(Debug, Default, Serialize)]
-struct PluginAdds {
-    skills: Vec<String>,
-    connectors: Vec<String>,
-    hooks: Vec<String>,
-    commands: Vec<String>,
-    profiles: Vec<String>,
-}
-
-impl PluginAdds {
-    fn labels(&self, entry: &PluginSummaryEntry) -> Vec<&'static str> {
-        [
-            ("skill", !self.skills.is_empty()),
-            ("connector", !self.connectors.is_empty()),
-            ("hook", !self.hooks.is_empty()),
-            ("command", !self.commands.is_empty()),
-            (
-                "tool",
-                entry.inventory.native > 0 || entry.inventory.lsp > 0,
-            ),
-            ("profile", !self.profiles.is_empty()),
-        ]
-        .into_iter()
-        .filter_map(|(label, present)| present.then_some(label))
-        .collect()
-    }
-}
-
-fn row_value<T: Serialize>(row: &T) -> Value {
-    serde_json::to_value(row).unwrap_or(Value::Null)
-}
-
-fn note_failure(unavailable: &mut Vec<IndexNote>, kind: &'static str, error: &ApiError) {
-    unavailable.push(IndexNote {
-        kind,
-        message: error.message.clone(),
-    });
-}
-
-fn plugin_source(origin: &str) -> &'static str {
-    match origin {
-        "codewhale-builtin" => "built_in",
-        "workspace-codewhale" => "project",
-        _ => "user",
-    }
-}
-
-fn plugin_state(entry: &PluginSummaryEntry) -> &'static str {
-    if matches!(
-        entry.trust_status,
-        "content-changed" | "capabilities-changed"
-    ) || entry.state == "enabled-untrusted"
-    {
-        return "needs_review";
-    }
-    match entry.state {
-        "active" => "enabled",
-        "disabled" => "disabled",
-        _ => "unavailable",
-    }
-}
-
-fn add_stem(names: &mut BTreeSet<String>, path: &FsPath, extension: Option<&str>, lowercase: bool) {
-    if let Some(wanted) = extension
-        && path.extension().and_then(|value| value.to_str()) != Some(wanted)
-    {
-        return;
-    }
-    if let Some(stem) = path.file_stem().and_then(|value| value.to_str()) {
-        names.insert(if lowercase {
-            stem.to_lowercase()
-        } else {
-            stem.to_string()
-        });
-    }
-}
-
-async fn component_names(
-    paths: &[PathBuf],
-    extension: Option<&str>,
-    lowercase: bool,
-    omitted: &mut bool,
-) -> Vec<String> {
-    let mut names = BTreeSet::new();
-    for path in paths {
-        let Ok(meta) = tokio::fs::symlink_metadata(path).await else {
-            continue;
-        };
-        if meta.is_file() {
-            add_stem(&mut names, path, extension, lowercase);
-        } else if meta.is_dir()
-            && let Ok(mut entries) = tokio::fs::read_dir(path).await
-        {
-            let mut seen = 0;
-            while let Ok(Some(entry)) = entries.next_entry().await {
-                seen += 1;
-                if seen > MAX_ADDED_NAMES {
-                    *omitted = true;
-                    break;
-                }
-                if entry.file_type().await.is_ok_and(|kind| kind.is_file()) {
-                    add_stem(&mut names, &entry.path(), extension, lowercase);
-                }
-            }
-        }
-        if names.len() >= MAX_ADDED_NAMES {
-            *omitted = true;
-            break;
-        }
-    }
-    if names.iter().any(|name| name.chars().any(char::is_control)) {
-        *omitted = true;
-        names.retain(|name| !name.chars().any(char::is_control));
-    }
-    names.into_iter().take(MAX_ADDED_NAMES).collect()
-}
-
-async fn plugin_adds(
-    plugin: &codewhale_plugins::types::LoadedPlugin,
-    omitted: &mut bool,
-) -> PluginAdds {
-    let mut skills: Vec<String> = plugin
-        .skill_snapshots
-        .iter()
-        .map(|skill| skill.name.clone())
-        .collect();
-    skills.sort();
-    let mut connectors: Vec<String> = plugin
-        .manifest
-        .mcp_servers
-        .as_ref()
-        .map(|servers| servers.keys().cloned().collect())
-        .unwrap_or_default();
-    connectors.sort();
-    PluginAdds {
-        skills,
-        connectors,
-        hooks: component_names(&plugin.components.hooks, None, false, omitted).await,
-        commands: component_names(&plugin.components.commands, Some("md"), true, omitted).await,
-        profiles: component_names(&plugin.components.agents, Some("toml"), false, omitted).await,
-    }
-}
-
-async fn plugin_adds_by_id(
-    state: &RuntimeApiState,
-    omitted: &mut BTreeSet<String>,
-) -> HashMap<String, PluginAdds> {
-    let registry = state
-        .plugin_discovery
-        .registry_for_workspace(&state.workspace);
-    let mut adds = HashMap::new();
-    for plugin in registry.list() {
-        let mut cut = false;
-        adds.insert(
-            plugin.id.as_str().to_string(),
-            plugin_adds(plugin, &mut cut).await,
-        );
-        if cut {
-            omitted.insert(plugin.name().to_string());
-        }
-    }
-    adds
-}
-
-fn skill_source(
-    path: Option<&PathBuf>,
-    is_bundled: bool,
-    skills_dir: &FsPath,
-    workspace: &FsPath,
-) -> &'static str {
-    if is_bundled {
-        return "built_in";
-    }
-    match path {
-        Some(path) if path.starts_with(skills_dir) => "user",
-        Some(path) if path.starts_with(workspace) => "project",
-        Some(_) => "other_app",
-        None => "plugin",
-    }
-}
-
-pub(super) async fn get_plugin_index(
-    State(state): State<RuntimeApiState>,
-) -> Result<Json<PluginIndexResponse>, ApiError> {
-    let mut items = Vec::new();
-    let mut unavailable = Vec::new();
-    let mut problems = Vec::new();
-
-    let commands = super::list_commands(
-        State(state.clone()),
-        Query(CommandsQuery { thread_id: None }),
-    )
-    .await;
-    let mut plugin_commands: HashMap<String, BTreeSet<String>> = HashMap::new();
-    if let Ok(Json(response)) = &commands {
-        for command in &response.commands {
-            if let (Some(plugin_id), "user") = (command.plugin_id.as_ref(), command.kind) {
-                plugin_commands
-                    .entry(plugin_id.clone())
-                    .or_default()
-                    .insert(command.name.clone());
-            }
-        }
-    }
-
-    match plugins::list_plugins(State(state.clone())).await {
-        Ok(Json(response)) => {
-            let mut omitted = BTreeSet::new();
-            let mut adds_by_id = plugin_adds_by_id(&state, &mut omitted).await;
-            for name in &omitted {
-                problems.push(IndexNote {
-                    kind: "plugin",
-                    message: format!(
-                        "plugin '{name}' adds more files than are listed, or a file name with control characters; some names are left out of `adds`"
-                    ),
-                });
-            }
-            for diagnostic in &response.registry_diagnostics {
-                problems.push(IndexNote {
-                    kind: "plugin",
-                    message: diagnostic.message.clone(),
-                });
-            }
-            for entry in &response.plugins {
-                let mut adds = adds_by_id.remove(&entry.id);
-                if entry.state == "active"
-                    && commands.is_ok()
-                    && let Some(adds) = adds.as_mut()
-                {
-                    adds.commands = plugin_commands
-                        .remove(&entry.id)
-                        .map(|names| names.into_iter().collect())
-                        .unwrap_or_default();
-                }
-                items.push(IndexItem {
-                    id: format!("plugin:{}", entry.id),
-                    kind: "plugin",
-                    name: entry
-                        .display_name
-                        .clone()
-                        .unwrap_or_else(|| entry.name.clone()),
-                    description: entry.description.clone(),
-                    source: plugin_source(entry.origin),
-                    state: plugin_state(entry),
-                    labels: adds
-                        .as_ref()
-                        .map(|adds| adds.labels(entry))
-                        .unwrap_or_default(),
-                    plugin: None,
-                    adds,
-                    tier: None,
-                    owner: "/v1/apps/plugins",
-                    row: row_value(entry),
-                });
-            }
-        }
-        Err(error) => note_failure(&mut unavailable, "plugin", &error),
-    }
-
-    match plugins::list_plugin_catalog(State(state.clone())).await {
-        Ok(Json(catalog)) => {
-            for (tier, rows) in [
-                ("builtin", &catalog.builtin),
-                ("experimental", &catalog.experimental),
-                ("more", &catalog.more),
-            ] {
-                for row in rows {
-                    items.push(IndexItem {
-                        id: format!("plugin:catalog:{}", row.id),
-                        kind: "plugin",
-                        name: row.title.clone(),
-                        description: row.description.clone(),
-                        source: "built_in",
-                        state: if !row.available {
-                            "unavailable"
-                        } else if row.enabled {
-                            "enabled"
-                        } else {
-                            "disabled"
-                        },
-                        labels: Vec::new(),
-                        plugin: None,
-                        adds: None,
-                        tier: Some(tier),
-                        owner: "/v1/apps/plugins/catalog",
-                        row: row_value(row),
-                    });
-                }
-            }
-        }
-        Err(error) => note_failure(&mut unavailable, "plugin", &error),
-    }
-
-    match super::list_skills(State(state.clone())).await {
-        Ok(Json(response)) => {
-            for warning in &response.warnings {
-                problems.push(IndexNote {
-                    kind: "skill",
-                    message: warning.clone(),
-                });
-            }
-            for skill in &response.skills {
-                if skill.plugin_id.is_some() {
-                    continue;
-                }
-                items.push(IndexItem {
-                    id: format!("skill:{}", skill.name),
-                    kind: "skill",
-                    name: skill.name.clone(),
-                    description: Some(skill.description.clone()),
-                    source: skill_source(
-                        skill.path.as_ref(),
-                        skill.is_bundled,
-                        &response.directory,
-                        &state.workspace,
-                    ),
-                    state: if skill.enabled { "enabled" } else { "disabled" },
-                    labels: vec!["skill"],
-                    plugin: None,
-                    adds: None,
-                    tier: None,
-                    owner: "/v1/skills",
-                    row: row_value(skill),
-                });
-            }
-        }
-        Err(error) => note_failure(&mut unavailable, "skill", &error),
-    }
-
-    match super::list_mcp_servers(State(state.clone())).await {
-        Ok(Json(response)) => {
-            for server in &response.servers {
-                let source = match server.origin {
-                    "plugin" => continue,
-                    "project" => "project",
-                    "runtime" => "runtime",
-                    _ => "user",
-                };
-                items.push(IndexItem {
-                    id: format!("connector:{}", server.name),
-                    kind: "connector",
-                    name: server.name.clone(),
-                    description: None,
-                    source,
-                    state: if !server.enabled {
-                        "disabled"
-                    } else if server.auth_required {
-                        "needs_sign_in"
-                    } else {
-                        "enabled"
-                    },
-                    labels: vec!["connector"],
-                    plugin: None,
-                    adds: None,
-                    tier: None,
-                    owner: "/v1/apps/mcp/servers",
-                    row: row_value(server),
-                });
-            }
-        }
-        Err(error) => note_failure(&mut unavailable, "connector", &error),
-    }
-
-    match super::list_hooks(State(state.clone()), Query(HooksQuery { thread_id: None })).await {
-        Ok(Json(response)) => {
-            for problem in &response.problems {
-                problems.push(IndexNote {
-                    kind: "hook",
-                    message: problem.clone(),
-                });
-            }
-            let mut ordinals: HashMap<&'static str, usize> = HashMap::new();
-            for hook in &response.hooks {
-                let ordinal = ordinals.entry(hook.event).or_default();
-                *ordinal += 1;
-                let source = match hook.source {
-                    "plugin" => continue,
-                    "project" => "project",
-                    _ => "user",
-                };
-                let name = hook
-                    .name
-                    .clone()
-                    .unwrap_or_else(|| format!("{} {}", hook.event, ordinal));
-                items.push(IndexItem {
-                    id: format!("hook:{source}:{}:{name}", hook.event),
-                    kind: "hook",
-                    name,
-                    description: None,
-                    source,
-                    state: if response.enabled {
-                        "enabled"
-                    } else {
-                        "disabled"
-                    },
-                    labels: vec!["hook"],
-                    plugin: None,
-                    adds: None,
-                    tier: None,
-                    owner: "/v1/hooks",
-                    row: row_value(hook),
-                });
-            }
-        }
-        Err(error) => note_failure(&mut unavailable, "hook", &error),
-    }
-
-    match commands {
-        Ok(Json(response)) => {
-            for command in &response.commands {
-                let (source, plugin) = match (command.kind, command.plugin_id.as_ref()) {
-                    ("builtin", _) => continue,
-                    ("user", Some(_)) => continue,
-                    ("extension", plugin_id) => ("plugin", plugin_id.cloned()),
-                    _ if command.workspace_sourced => ("project", None),
-                    _ => ("user", None),
-                };
-                items.push(IndexItem {
-                    id: format!("command:{}", command.name),
-                    kind: "command",
-                    name: command.name.clone(),
-                    description: command.summary.clone(),
-                    source,
-                    state: "enabled",
-                    labels: vec!["command"],
-                    plugin,
-                    adds: None,
-                    tier: None,
-                    owner: "/v1/commands",
-                    row: row_value(command),
-                });
-            }
-        }
-        Err(error) => note_failure(&mut unavailable, "command", &error),
-    }
-
-    Ok(Json(PluginIndexResponse {
-        workspace: state.workspace.display().to_string(),
-        items,
-        unavailable,
-        problems,
-    }))
-}

crates/app-server/src/runtime_api/tests.rs

@@ -15,7 +15,6 @@ use tokio::sync::{Mutex, mpsc, oneshot};
 use tokio::time::sleep;
 use uuid::Uuid;
 
-mod catalog_parity;
 mod command_catalog;
 #[cfg(unix)]
 mod control_socket_selection;
@@ -29,7 +28,6 @@ mod headless_catalog;
 mod member_operations;
 #[cfg(unix)]
 mod owner_bootstrap;
-mod plugin_index;
 mod plugin_ui;
 mod profile_constitution;
 #[cfg(any(unix, windows))]

crates/app-server/src/runtime_api/tests/catalog_parity.rs

@@ -1,600 +0,0 @@
-use super::*;
-use codewhale_config::catalog::{
-    CatalogOffering, CatalogSource, CatalogStatus, ProviderCatalogDelta, base_url_fingerprint,
-    now_unix,
-};
-use codewhale_engine::cost_status::EffectiveRouteEnvelope;
-use codewhale_engine::model_inventory::ModelInventory;
-use codewhale_runtime::config::ProviderIdentity;
-use sha2::{Digest, Sha256};
-use std::collections::BTreeMap;
-
-const SINGULAR: &str = "model list / model resolve";
-const PLURAL: &str = "models";
-const RUNTIME: &str = "runtime api";
-const ROUTING: &str = "routing inventory";
-const COST: &str = "cost";
-const UNKNOWN: &str = "unknown";
-
-const ROSTER: &[&str] = &["claude-opus-5", "claude-haiku-4-5", "claude-parity-probe-1"];
-
-type Readings = BTreeMap<(String, String, &'static str), BTreeMap<&'static str, String>>;
-
-struct Route {
-    label: &'static str,
-    api_path: &'static str,
-    identity: ProviderIdentity,
-    base_url: String,
-    models: &'static [&'static str],
-}
-
-fn cold_process() {
-    codewhale_engine::provider_catalog_live::reset_cache_for_test();
-    codewhale_engine::provider_lake::clear_live_snapshot();
-}
-
-fn known<T: ToString>(value: Option<T>) -> String {
-    value.map_or_else(|| UNKNOWN.to_string(), |value| value.to_string())
-}
-
-fn rate(value: &Value) -> String {
-    let number = match value {
-        Value::Number(number) => number.as_f64(),
-        Value::String(text) => text.parse::<f64>().ok(),
-        _ => None,
-    };
-    known(number)
-}
-
-fn roster(mut models: Vec<String>) -> String {
-    models.sort();
-    models.dedup();
-    models.join(",")
-}
-
-fn read(
-    readings: &mut Readings,
-    route: &Route,
-    model: &str,
-    field: &'static str,
-    surface: &'static str,
-    value: String,
-) {
-    readings
-        .entry((route.label.to_string(), model.to_string(), field))
-        .or_default()
-        .insert(surface, value);
-}
-
-fn persist_id_only_roster(identity: &ProviderIdentity, base_url: &str) {
-    let fingerprint = base_url_fingerprint(base_url);
-    let fetched_at = now_unix();
-    let ticket = codewhale_engine::provider_catalog_live::begin_refresh_for_identity(
-        identity.provider,
-        identity.key.as_str(),
-        base_url,
-    );
-    assert_eq!(
-        codewhale_engine::provider_catalog_live::record_success_if_current(
-            &ticket,
-            ProviderCatalogDelta {
-                provider: identity.key.to_string(),
-                base_url_fingerprint: fingerprint.clone(),
-                fetched_at,
-                offerings: ROSTER
-                    .iter()
-                    .map(|id| CatalogOffering {
-                        provider: identity.key.to_string(),
-                        wire_model_id: (*id).to_string(),
-                        endpoint_key: "chat".into(),
-                        source: CatalogSource::Live {
-                            base_url_fingerprint: fingerprint.clone(),
-                            fetched_at,
-                        },
-                        ..Default::default()
-                    })
-                    .collect(),
-            },
-        ),
-        Some(CatalogStatus::Fresh)
-    );
-}
-
-fn read_singular(readings: &mut Readings, config_path: &Path, route: &Route) -> Result<()> {
-    cold_process();
-    let store = codewhale_config::ConfigStore::load(Some(config_path.to_path_buf()))?;
-    let listed =
-        codewhale_engine::route_preferences::list_models(&store, Some(route.identity.provider))?
-            .into_iter()
-            .find(|(listed, _)| listed == route.identity.key.as_str())
-            .map(|(_, models)| roster(models));
-    read(
-        readings,
-        route,
-        "*",
-        "roster",
-        SINGULAR,
-        listed.unwrap_or_else(|| "route not listed".into()),
-    );
-    for model in route.models {
-        let limits = codewhale_engine::route_preferences::resolve_model(
-            config_path,
-            route.identity.key.as_str(),
-            &route.base_url,
-            Some(model),
-        )
-        .map(|candidate| candidate.limits());
-        let (context, output) = match limits {
-            Ok(limits) => (known(limits.context_tokens), known(limits.output_tokens)),
-            Err(error) => (format!("refused: {error}"), format!("refused: {error}")),
-        };
-        read(readings, route, model, "limit.context", SINGULAR, context);
-        read(readings, route, model, "limit.output", SINGULAR, output);
-    }
-    Ok(())
-}
-
-fn read_plural(readings: &mut Readings, config: &Config, route: &Route) -> Result<()> {
-    cold_process();
-    codewhale_engine::models_dev_live::maybe_load_persisted_cache();
-    let mut route_config = config.clone();
-    route_config
-        .scope_to_provider_identity(&route.identity)
-        .map_err(anyhow::Error::msg)?;
-    read(
-        readings,
-        route,
-        "*",
-        "roster",
-        PLURAL,
-        roster(codewhale_engine::provider_lake::listed_models_for_route(
-            &route_config,
-            &route.identity,
-        )),
-    );
-    Ok(())
-}
-
-async fn read_runtime(
-    readings: &mut Readings,
-    client: &reqwest::Client,
-    addr: &SocketAddr,
-    route: &Route,
-) -> Result<()> {
-    let body: Value = client
-        .get(format!("http://{addr}/v1/providers/{}", route.api_path))
-        .send()
-        .await?
-        .error_for_status()?
-        .json()
-        .await?;
-    let models = body["models"].as_array().context("models array")?;
-    read(
-        readings,
-        route,
-        "*",
-        "roster",
-        RUNTIME,
-        roster(
-            models
-                .iter()
-                .filter_map(|model| model["id"].as_str().map(str::to_string))
-                .collect(),
-        ),
-    );
-    for model in route.models {
-        let facts = models
-            .iter()
-            .find(|entry| entry["id"] == *model)
-            .map_or(&Value::Null, |entry| &entry["facts"]);
-        read(
-            readings,
-            route,
-            model,
-            "limit.context",
-            RUNTIME,
-            known(facts["effective_limits"]["context_tokens"].as_u64()),
-        );
-        read(
-            readings,
-            route,
-            model,
-            "limit.output",
-            RUNTIME,
-            known(facts["effective_limits"]["output_tokens"].as_u64()),
-        );
-        read(
-            readings,
-            route,
-            model,
-            "window",
-            RUNTIME,
-            known(facts["effective_context"]["tokens"].as_u64()),
-        );
-        read(
-            readings,
-            route,
-            model,
-            "window.source",
-            RUNTIME,
-            known(facts["effective_context"]["source"].as_str()),
-        );
-        read(
-            readings,
-            route,
-            model,
-            "price.input",
-            RUNTIME,
-            rate(&facts["pricing"]["input_per_million"]),
-        );
-        read(
-            readings,
-            route,
-            model,
-            "price.output",
-            RUNTIME,
-            rate(&facts["pricing"]["output_per_million"]),
-        );
-        read(
-            readings,
-            route,
-            model,
-            "price.basis",
-            RUNTIME,
-            format!(
-                "provenance={} status={} source={}",
-                facts["pricing"]["provenance"], facts["pricing_status"], facts["source"]
-            ),
-        );
-    }
-    Ok(())
-}
-
-fn read_routing(readings: &mut Readings, config: &Config, route: &Route) -> Result<()> {
-    let inventory = ModelInventory::from_config(config).map_err(anyhow::Error::msg)?;
-    let candidates: Vec<_> = inventory
-        .candidates
-        .iter()
-        .filter(|candidate| candidate.identity == route.identity)
-        .collect();
-    read(
-        readings,
-        route,
-        "*",
-        "roster",
-        ROUTING,
-        roster(
-            candidates
-                .iter()
-                .map(|candidate| candidate.model.clone())
-                .collect(),
-        ),
-    );
-    for model in route.models {
-        let candidate = candidates
-            .iter()
-            .find(|candidate| candidate.model == *model);
-        read(
-            readings,
-            route,
-            model,
-            "window",
-            ROUTING,
-            known(candidate.map(|candidate| candidate.context_window)),
-        );
-        read(
-            readings,
-            route,
-            model,
-            "window.source",
-            ROUTING,
-            known(candidate.map(|candidate| {
-                if candidate.context_window_unverified {
-                    "unverified"
-                } else {
-                    "verified"
-                }
-            })),
-        );
-        read(
-            readings,
-            route,
-            model,
-            "limit.output",
-            ROUTING,
-            known(candidate.and_then(|candidate| candidate.max_output)),
-        );
-    }
-    Ok(())
-}
-
-fn read_cost(readings: &mut Readings, config: &Config, route: &Route) {
-    let usage = Usage {
-        input_tokens: 100_000,
-        output_tokens: 10_000,
-        ..Default::default()
-    };
-    for model in route.models {
-        let envelope = EffectiveRouteEnvelope::from_admitted(
-            Some(config),
-            &route.identity,
-            *model,
-            Some(&route.base_url),
-            chrono::Utc::now(),
-        );
-        let quote = envelope.provider_live_pricing.as_ref();
-        let audit = envelope.audit(&usage);
-        read(
-            readings,
-            route,
-            model,
-            "price.input",
-            COST,
-            quote
-                .and_then(|quote| quote.input_per_million.as_deref())
-                .map_or_else(|| UNKNOWN.to_string(), |text| rate(&json!(text))),
-        );
-        read(
-            readings,
-            route,
-            model,
-            "price.output",
-            COST,
-            quote
-                .and_then(|quote| quote.output_per_million.as_deref())
-                .map_or_else(|| UNKNOWN.to_string(), |text| rate(&json!(text))),
-        );
-        read(
-            readings,
-            route,
-            model,
-            "price.basis",
-            COST,
-            format!(
-                "provenance={:?} billing={:?} charge_usd={} unpriced={:?}",
-                quote.map(|quote| quote.provenance.clone()),
-                envelope.billing_mode,
-                known(audit.exact_usd.as_deref()),
-                audit.unpriced_reason,
-            ),
-        );
-    }
-}
-
-#[tokio::test]
-async fn one_captured_catalog_reads_the_same_on_every_model_surface() -> Result<()> {
-    let _env = lock_test_env();
-    let _live = codewhale_engine::provider_lake::lock_live_snapshot();
-    let root = tempfile::tempdir()?;
-    let captured = codewhale_config::catalog::BUNDLED_MODELS_DEV_JSON;
-    let catalog_path = root.path().join("captured-models-dev.json");
-    fs::write(&catalog_path, captured)?;
-    let _catalog = EnvVarGuard::set("CODEWHALE_MODELS_DEV_PATH", &catalog_path);
-    let _home = EnvVarGuard::set("CODEWHALE_HOME", root.path());
-    let _config_path = EnvVarGuard::remove("CODEWHALE_CONFIG_PATH");
-    let _legacy_config_path = EnvVarGuard::remove("DEEPSEEK_CONFIG_PATH");
-    let _cli = EnvVarGuard::remove(codewhale_config::CLI_API_KEY_ENV);
-    cold_process();
-
-    let config_path = root.path().join("config.toml");
-    fs::write(
-        &config_path,
-        r#"provider = "anthropic"
-
-[providers.anthropic]
-api_key = "parity-fixture-key"
-model = "claude-opus-5"
-
-[providers.zai]
-api_key = "parity-fixture-key"
-model = "GLM-5.3"
-
-[providers.lab]
-kind = "openai-compatible"
-base_url = "http://127.0.0.1:9/v1"
-api_key = "parity-fixture-key"
-model = "claude-haiku-4-5"
-"#,
-    )?;
-    let config = Config::load(Some(config_path.clone()), None)?;
-    let route = |label: &'static str,
-                 api_path: &'static str,
-                 key: &str,
-                 models: &'static [&'static str]|
-     -> Result<Route> {
-        let identity = config
-            .resolve_provider_pin_identity(key)
-            .map_err(anyhow::Error::msg)?;
-        Ok(Route {
-            label,
-            api_path,
-            base_url: config.base_url_for_route(&identity),
-            identity,
-            models,
-        })
-    };
-    let routes = [
-        route(
-            "anthropic (official, id-only roster)",
-            "anthropic/models",
-            "anthropic",
-            ROSTER,
-        )?,
-        route(
-            "lab (custom endpoint, same spelling)",
-            "custom/models?model_provider_id=lab",
-            "lab",
-            &["claude-haiku-4-5"],
-        )?,
-        route(
-            "zai (plan endpoint)",
-            "zai/models",
-            "zai",
-            &["GLM-5.3", "GLM-5.2"],
-        )?,
-    ];
-
-    assert!(
-        codewhale_engine::models_dev_live::refresh(false)
-            .await
-            .map_err(|error| anyhow::anyhow!("{error}"))?
-            > 0
-    );
-    persist_id_only_roster(&routes[0].identity, &routes[0].base_url);
-
-    let mut readings = Readings::new();
-    for route in &routes {
-        read_singular(&mut readings, &config_path, route)?;
-        read_plural(&mut readings, &config, route)?;
-    }
-    cold_process();
-    let (addr, _, handle) = spawn_test_server_with_config_path(config_path.clone())
-        .await?
-        .expect("loopback server required");
-    let client = codewhale_release::tls::reqwest_client();
-    for route in &routes {
-        read_runtime(&mut readings, &client, &addr, route).await?;
-        read_routing(&mut readings, &config, route)?;
-        read_cost(&mut readings, &config, route);
-    }
-    handle.abort();
-    cold_process();
-
-    println!(
-        "PARITY captured_catalog sha256={} bytes={}",
-        Sha256::digest(captured.as_bytes())
-            .iter()
-            .map(|byte| format!("{byte:02x}"))
-            .collect::<String>(),
-        captured.len()
-    );
-    let mut differing = Vec::new();
-    let mut known_differences: Vec<String> = Vec::new();
-    for ((route, model, field), surfaces) in &readings {
-        let mut values: Vec<String> = surfaces
-            .values()
-            .map(|value| {
-                if *field == "roster" {
-                    roster(
-                        value
-                            .to_ascii_lowercase()
-                            .split(',')
-                            .map(str::to_string)
-                            .collect(),
-                    )
-                } else {
-                    value.clone()
-                }
-            })
-            .collect();
-        values.sort();
-        values.dedup();
-        let compared = !matches!(*field, "price.basis" | "window.source");
-        let borrowed_window = *field == "window"
-            && surfaces.get(RUNTIME).map(String::as_str) == Some(UNKNOWN)
-            && readings
-                .get(&(route.clone(), model.clone(), "window.source"))
-                .and_then(|sources| sources.get(ROUTING))
-                .map(String::as_str)
-                == Some("unverified");
-        let verdict = if !compared {
-            "info"
-        } else if borrowed_window {
-            known_differences.push(format!("{route} | {model} | {surfaces:?}"));
-            "KNOWN-DIFFERENCE"
-        } else if values.len() == 1 {
-            "agree"
-        } else {
-            differing.push(format!("{route} | {model} | {field} | {surfaces:?}"));
-            "DIFFER"
-        };
-        println!("PARITY {verdict} | {route} | {model} | {field} | {surfaces:?}");
-    }
-    let value = |route: &Route, model: &str, field: &'static str, surface: &'static str| {
-        readings
-            .get(&(route.label.to_string(), model.to_string(), field))
-            .and_then(|surfaces| surfaces.get(surface))
-            .cloned()
-            .unwrap_or_default()
-    };
-    assert_eq!(
-        value(&routes[0], "*", "roster", SINGULAR),
-        "claude-haiku-4-5,claude-opus-5,claude-parity-probe-1",
-        "the singular command lists the route's own roster, not every bundled row"
-    );
-    assert_eq!(
-        value(&routes[0], "claude-opus-5", "limit.context", RUNTIME),
-        "1000000"
-    );
-    assert_eq!(
-        value(&routes[0], "claude-haiku-4-5", "limit.context", RUNTIME),
-        "200000"
-    );
-    assert_eq!(value(&routes[0], "claude-opus-5", "price.input", COST), "5");
-    assert_eq!(
-        value(&routes[0], "claude-haiku-4-5", "price.output", COST),
-        "5"
-    );
-    for field in ["limit.context", "limit.output", "price.input"] {
-        assert_eq!(
-            value(&routes[1], "claude-haiku-4-5", field, RUNTIME),
-            UNKNOWN,
-            "a custom endpoint borrows no fact from a same-named model: {field}"
-        );
-    }
-    assert_eq!(
-        value(&routes[1], "claude-haiku-4-5", "window.source", ROUTING),
-        "unverified",
-        "routing never presents a same-named model's window as this endpoint's"
-    );
-    assert_eq!(
-        value(&routes[1], "claude-haiku-4-5", "limit.output", ROUTING),
-        UNKNOWN
-    );
-    for model in ["GLM-5.3", "GLM-5.2"] {
-        let basis = value(&routes[2], model, "price.basis", COST);
-        assert!(
-            basis.contains("NotMoneyMetered") && basis.contains("charge_usd=unknown"),
-            "a plan route is never billed per token: {model}: {basis}"
-        );
-    }
-    for (model, rate) in [("GLM-5.3", UNKNOWN), ("GLM-5.2", "1.4")] {
-        for surface in [COST, RUNTIME] {
-            assert_eq!(
-                value(&routes[2], model, "price.input", surface),
-                rate,
-                "the list rate is shown the same everywhere and never turned into a charge: {model} {surface}"
-            );
-        }
-    }
-    let basis = value(&routes[1], "claude-haiku-4-5", "price.basis", COST);
-    assert!(
-        basis.contains("UnknownBillingBasis") && basis.contains("charge_usd=unknown"),
-        "a custom endpoint is never given a charge: {basis}"
-    );
-    for surface in [COST, RUNTIME] {
-        assert_eq!(
-            value(&routes[0], "claude-parity-probe-1", "price.input", surface),
-            UNKNOWN,
-            "a metered first-party model with no price row reads unknown: {surface}"
-        );
-    }
-    let basis = value(&routes[0], "claude-parity-probe-1", "price.basis", COST);
-    assert!(
-        basis.contains("charge_usd=unknown") && !basis.contains("unpriced=None"),
-        "an unpriced model produces no charge and says why: {basis}"
-    );
-    assert_eq!(
-        known_differences,
-        vec![
-            "lab (custom endpoint, same spelling) | claude-haiku-4-5 | {\"routing inventory\": \"200000\", \"runtime api\": \"unknown\"}"
-        ],
-        "the only named difference is the custom endpoint's borrowed routing window"
-    );
-    assert!(
-        differing.is_empty(),
-        "surfaces disagree on the same captured catalog:\n{}",
-        differing.join("\n")
-    );
-    Ok(())
-}

crates/app-server/src/runtime_api/tests/command_catalog.rs

@@ -28,8 +28,6 @@ fn user(name: &str) -> UserCommand {
         takes_arguments: false,
         hidden: false,
         extension: false,
-        plugin_id: None,
-        workspace_sourced: false,
         builtin_bindings: vec![name.to_string()],
     }
 }

crates/app-server/src/runtime_api/tests/plugin_index.rs

@@ -1,139 +0,0 @@
-use super::*;
-use codewhale_engine::command_catalog::{BuiltinCommand, CommandCatalog, UserCommand};
-
-struct Catalog(Arc<std::sync::Mutex<Option<String>>>);
-
-impl CommandCatalog for Catalog {
-    fn answers_to(&self, _name: &str) -> bool {
-        false
-    }
-    fn builtins(&self) -> Vec<BuiltinCommand> {
-        Vec::new()
-    }
-    fn user_commands(&self, _workspace: &Path) -> Vec<UserCommand> {
-        let plugin_id = self.0.lock().expect("plugin id").clone();
-        let command = |name: &str, plugin: Option<String>| UserCommand {
-            name: name.to_string(),
-            aliases: Vec::new(),
-            description: Some("A command.".to_string()),
-            usage: None,
-            takes_arguments: false,
-            hidden: false,
-            extension: false,
-            plugin_id: plugin,
-            workspace_sourced: false,
-            builtin_bindings: Vec::new(),
-        };
-        vec![command("mine", None), command("ship", plugin_id)]
-    }
-}
-
-#[tokio::test]
-async fn the_index_lists_every_kind_once_and_a_plugin_carries_what_it_adds() -> Result<()> {
-    let _env = lock_test_env();
-    let temp = tempfile::tempdir()?;
-    let root = temp.path().join("index-route");
-    let workspace = root.join("workspace");
-    fs::create_dir_all(&workspace)?;
-    let plugin_id = Arc::new(std::sync::Mutex::new(None));
-    let _catalog = codewhale_engine::command_catalog::CatalogGuard::install(Arc::new(Catalog(
-        plugin_id.clone(),
-    )));
-    let sources = root.join("sources");
-    fs::create_dir_all(&sources)?;
-    let bundle = write_plugin_source_bundle(&sources, "indexed")?;
-    fs::create_dir_all(bundle.join("commands"))?;
-    fs::write(bundle.join("commands/ship.md"), "Ship it.\n")?;
-    fs::create_dir_all(bundle.join("agents"))?;
-    fs::write(bundle.join("agents/reviewer.toml"), "name = \"reviewer\"\n")?;
-    fs::write(
-        bundle.join("plugin.toml"),
-        "schema_version = 1\n[plugin]\nname = \"indexed\"\nversion = \"1.0.0\"\n\
-         description = \"test bundle\"\n\n[skills]\npath = \"skills\"\n\
-         [commands]\npath = \"commands\"\n[agents]\npath = \"agents\"\n",
-    )?;
-
-    let Some((addr, handle)) = spawn_plugin_api_server(root, workspace).await? else {
-        return Ok(());
-    };
-    let client = codewhale_release::tls::reqwest_client();
-    plugin_ui::install_active(
-        &client,
-        &format!("http://{addr}/v1/apps/plugins"),
-        bundle.display().to_string(),
-    )
-    .await?;
-
-    let listed: Value = client
-        .get(format!("http://{addr}/v1/apps/plugins"))
-        .send()
-        .await?
-        .error_for_status()?
-        .json()
-        .await?;
-    let id = listed["plugins"]
-        .as_array()
-        .and_then(|plugins| plugins.iter().find(|plugin| plugin["name"] == "indexed"))
-        .and_then(|plugin| plugin["id"].as_str())
-        .expect("installed plugin id")
-        .to_string();
-    *plugin_id.lock().expect("plugin id") = Some(id.clone());
-
-    let commands: Value = client
-        .get(format!("http://{addr}/v1/commands"))
-        .send()
-        .await?
-        .error_for_status()?
-        .json()
-        .await?;
-    let ship = commands["commands"]
-        .as_array()
-        .and_then(|rows| rows.iter().find(|row| row["name"] == "ship"))
-        .expect("ship row");
-    assert_eq!(ship["plugin_id"], id.as_str());
-
-    let index: Value = client
-        .get(format!("http://{addr}/v1/apps/plugin-index"))
-        .send()
-        .await?
-        .error_for_status()?
-        .json()
-        .await?;
-    let items = index["items"].as_array().expect("items");
-    let find = |id: &str| items.iter().find(|item| item["id"] == id);
-
-    let plugin = items
-        .iter()
-        .find(|item| item["kind"] == "plugin" && item["row"]["name"] == "indexed")
-        .unwrap_or_else(|| panic!("plugin row in {index}"));
-    assert_eq!(plugin["kind"], "plugin");
-    assert_eq!(plugin["state"], "enabled");
-    assert_eq!(plugin["adds"]["skills"], serde_json::json!(["greet"]));
-    assert_eq!(plugin["adds"]["commands"], serde_json::json!(["ship"]));
-    assert_eq!(plugin["adds"]["profiles"], serde_json::json!(["reviewer"]));
-    assert_eq!(
-        plugin["labels"],
-        serde_json::json!(["skill", "command", "profile"])
-    );
-    assert_eq!(plugin["row"]["name"], "indexed");
-
-    assert!(find("skill:greet").is_none());
-    assert!(find("command:ship").is_none());
-    let mine = find("command:mine").expect("a hand-written command is a row");
-    assert_eq!(mine["source"], "user");
-    assert_eq!(mine["labels"], serde_json::json!(["command"]));
-    assert!(
-        items
-            .iter()
-            .any(|item| item["kind"] == "plugin" && item["tier"] == "builtin"),
-        "built-in switches are rows"
-    );
-    assert_eq!(
-        index["unavailable"].as_array().map(Vec::len),
-        Some(0),
-        "{index}"
-    );
-
-    handle.abort();
-    Ok(())
-}

crates/app-server/src/runtime_api/tests/plugin_ui.rs

@@ -79,7 +79,7 @@ fn write_native_ui_bundle(dir: &Path, name: &str) -> Result<PathBuf> {
     Ok(bundle)
 }
 
-pub(super) async fn install_active(
+async fn install_active(
     client: &reqwest::Client,
     base: &str,
     source: String,

crates/app-server/tests/acp_journey.rs

@@ -3,13 +3,13 @@ mod acp_support;
 use acp_support::{Client, fixture_config, text_of, updates};
 use anyhow::{Result, anyhow};
 use codewhale_app_server::acp_server::capture_frontend;
-use codewhale_engine::llm_client::mock::{CannedTurn, MockLlmClient, canned};
+use codewhale_engine::llm_client::mock::{MockLlmClient, canned};
 use codewhale_engine::runtime_threads::RuntimeTurnStatus;
 use codewhale_engine::runtime_threads::manager::{
     RuntimeThreadManager, RuntimeThreadManagerConfig,
 };
 use serde_json::{Value, json};
-use std::path::{Path, PathBuf};
+use std::path::PathBuf;
 use std::sync::Arc;
 use std::time::Duration;
 use tokio::io::{AsyncWriteExt, BufReader};
@@ -497,346 +497,3 @@ async fn extension_journey() -> Result<()> {
     host.shutdown().await;
     Ok(())
 }
-
-const GATES_MCP_FIXTURE: &str = r#"import readline from 'node:readline';
-readline.createInterface({input:process.stdin}).on('line', line => {
-  const r = JSON.parse(line); if (r.id === undefined) return;
-  let result = {};
-  if (r.method === 'initialize') result = {protocolVersion:'2024-11-05',capabilities:{tools:{}},serverInfo:{name:'fixture',version:'1'}};
-  if (r.method === 'tools/list') result = {tools:['echo','hidden'].map(name => ({name,description:'Echo text',inputSchema:{type:'object',properties:{text:{type:'string'}},required:['text']}}))};
-  if (r.method === 'tools/call') result = {content:[{type:'text',text:'mcp-ran:' + r.params.name + ':' + r.params.arguments.text}]};
-  process.stdout.write(JSON.stringify({jsonrpc:'2.0',id:r.id,result}) + '\n');
-});
-"#;
-
-struct Outcome {
-    response: Value,
-    frames: Vec<Value>,
-    asked: Vec<Value>,
-}
-
-impl Outcome {
-    fn rendered(&self) -> String {
-        serde_json::to_string(&self.frames).unwrap_or_default()
-    }
-    fn completed(&self) -> usize {
-        updates(&self.frames, "tool_call_update")
-            .iter()
-            .filter(|frame| frame.pointer("/params/update/status") == Some(&json!("completed")))
-            .count()
-    }
-    fn titles(&self) -> Vec<String> {
-        self.asked
-            .iter()
-            .map(|frame| {
-                frame["params"]["toolCall"]["title"]
-                    .as_str()
-                    .unwrap_or_default()
-                    .to_string()
-            })
-            .collect()
-    }
-    fn announced_ids(&self) -> Vec<String> {
-        updates(&self.frames, "tool_call")
-            .iter()
-            .filter_map(|frame| frame.pointer("/params/update/toolCallId")?.as_str())
-            .map(str::to_string)
-            .collect()
-    }
-}
-
-async fn run_prompt(
-    client: &mut Client,
-    session: &str,
-    allow: &dyn Fn(usize) -> bool,
-) -> Result<Outcome> {
-    client.next_id += 1;
-    let prompt_id = client.next_id;
-    client
-        .send(
-            json!({"jsonrpc":"2.0","id":prompt_id,"method":"session/prompt","params":{
-            "sessionId":session,"prompt":[{"type":"text","text":"go"}]}}),
-        )
-        .await?;
-    let mut frames = Vec::new();
-    let mut asked = Vec::new();
-    let response = loop {
-        let frame = client.recv().await?;
-        if frame["method"] == "session/request_permission" {
-            let option = if allow(asked.len()) {
-                "allow-once"
-            } else {
-                "reject-once"
-            };
-            client
-                .send(json!({"jsonrpc":"2.0","id":frame["id"],
-                    "result":{"outcome":{"outcome":"selected","optionId":option}}}))
-                .await?;
-            asked.push(frame);
-        } else if frame["id"] == json!(prompt_id) && frame.get("method").is_none() {
-            break frame;
-        } else {
-            frames.push(frame);
-        }
-    };
-    Ok(Outcome {
-        response,
-        frames,
-        asked,
-    })
-}
-
-async fn new_session(
-    client: &mut Client,
-    manager: &RuntimeThreadManager,
-    workspace: &Path,
-    turns: Vec<CannedTurn>,
-    plan: bool,
-) -> Result<String> {
-    manager.set_test_model_client(Arc::new(MockLlmClient::new(turns)));
-    let (created, _) = client
-        .request("session/new", json!({"cwd":workspace}))
-        .await?;
-    let session = created["result"]["sessionId"]
-        .as_str()
-        .ok_or_else(|| anyhow!("session/new returned no sessionId: {created}"))?
-        .to_string();
-    if plan {
-        let (set, _) = client
-            .request(
-                "session/set_mode",
-                json!({"sessionId":session,"modeId":"plan"}),
-            )
-            .await?;
-        assert!(set.get("error").is_none(), "{set}");
-    }
-    Ok(session)
-}
-
-#[test]
-fn extension_tools_keep_the_permission_boundary_in_an_acp_session() -> Result<()> {
-    std::thread::Builder::new()
-        .stack_size(64 << 20)
-        .spawn(|| {
-            tokio::runtime::Builder::new_current_thread()
-                .enable_all()
-                .build()?
-                .block_on(async {
-                    tokio::time::timeout(Duration::from_secs(180), gates())
-                        .await
-                        .map_err(|_| anyhow!("extension gates exceeded 180s"))?
-                })
-        })?
-        .join()
-        .map_err(|_| anyhow!("extension gates thread panicked"))?
-}
-
-async fn gates() -> Result<()> {
-    use codewhale_engine::extension_host::test_support::{FixturePlugins, node_for_tests};
-    let Some(node) = node_for_tests("extension_tools_keep_the_permission_boundary") else {
-        return Ok(());
-    };
-    let _policy = codewhale_plugins::activation::TestPolicyGuard::extension_host(true);
-    let fixture = FixturePlugins::new(&["plugin-context", "core-call"]).await;
-    let host = fixture.manager(node.clone());
-    let _host = codewhale_engine::extension_host::TestManagerGuard::install(Arc::clone(&host));
-    let dir = tempfile::tempdir()?;
-    let _home = codewhale_engine::test_support::SealedHome::at(dir.path());
-    let workspace = fixture.workspace().to_path_buf();
-    std::fs::write(workspace.join("seed.txt"), "seed-content-xyz")?;
-    let server = dir.path().join("fixture-mcp.mjs");
-    std::fs::write(&server, GATES_MCP_FIXTURE)?;
-    let mcp_config = dir.path().join("mcp.json");
-    std::fs::write(
-        &mcp_config,
-        serde_json::to_vec(&json!({"servers":{
-            "fixture":{"command":node,"args":[server],"disabled_tools":["hidden"]},
-            "off":{"command":node,"args":[server],"disabled":true}
-        }}))?,
-    )?;
-    let runtime_dir = dir.path().join("runtime");
-    let mut config = fixture_config();
-    config.set_feature("mcp", true).unwrap();
-    config.set_feature("extension_host", true).unwrap();
-    config.mcp_config_path = Some(mcp_config.to_string_lossy().into_owned());
-    let manager = Arc::new(RuntimeThreadManager::open_host(
-        config.clone(),
-        workspace.clone(),
-        RuntimeThreadManagerConfig {
-            mcp_auth_context: Default::default(),
-            data_dir: runtime_dir.clone(),
-            task_data_dir: runtime_dir,
-            sessions_dir: None,
-            max_active_threads: 16,
-        },
-        fixture.registry(),
-        codewhale_engine::core::engine::EngineHostProfile::Acp,
-        None,
-        None,
-    )?);
-    let frontend = capture_frontend(
-        config,
-        "fixture-model".into(),
-        workspace.clone(),
-        Arc::clone(&manager),
-        codewhale_engine::session_manager::default_sessions_dir()?,
-        None,
-        None,
-    )?;
-    let (mut client, agent_read, agent_write) = Client::connect(false);
-    let connection = frontend.serve(Box::new(BufReader::new(agent_read)), Box::new(agent_write));
-    let manager_for_script = Arc::clone(&manager);
-    let script =
-        async {
-            let manager = manager_for_script;
-            let result = async {
-            client
-                .request(
-                    "initialize",
-                    json!({"protocolVersion":1,"clientCapabilities":{}}),
-                )
-                .await?;
-
-            let session = new_session(
-                &mut client,
-                &manager,
-                &workspace,
-                vec![
-                    canned::tool_call_turn(
-                        "n1",
-                        "cc_call",
-                        r#"{"name":"write","input":{"path":"nested.txt","content":"via-plugin"}}"#,
-                    ),
-                    canned::simple_text_turn("nested allowed"),
-                ],
-                false,
-            )
-            .await?;
-            let allowed = run_prompt(&mut client, &session, &|_| true).await?;
-            assert!(allowed.response.get("error").is_none(), "{}", allowed.response);
-            assert_eq!(allowed.response["result"]["stopReason"], "end_turn");
-            assert_eq!(allowed.asked.len(), 2, "{:?}", allowed.titles());
-            assert!(allowed.titles()[0].starts_with("cc_call"));
-            let announced = allowed.announced_ids();
-            for request in &allowed.asked {
-                let id = request["params"]["toolCall"]["toolCallId"]
-                    .as_str()
-                    .unwrap_or_default();
-                assert!(
-                    announced.iter().any(|known| known == id),
-                    "a nested approval is shown on a tool call the editor knows: {id} {announced:?}"
-                );
-            }
-            let nested = &allowed.asked[1]["params"]["toolCall"];
-            assert_eq!(nested["title"], "write: nested.txt", "{nested}");
-            assert_eq!(nested["kind"], "edit", "{nested}");
-            assert_eq!(nested["rawInput"]["path"], "nested.txt", "{nested}");
-            assert!(nested.get("status").is_none(), "{nested}");
-            assert_eq!(
-                std::fs::read_to_string(workspace.join("nested.txt"))?,
-                "via-plugin"
-            );
-
-            std::fs::remove_file(workspace.join("nested.txt"))?;
-            let session = new_session(
-                &mut client,
-                &manager,
-                &workspace,
-                vec![
-                    canned::tool_call_turn(
-                        "n2",
-                        "cc_call",
-                        r#"{"name":"write","input":{"path":"nested.txt","content":"via-plugin"}}"#,
-                    ),
-                    canned::simple_text_turn("nested denied"),
-                ],
-                false,
-            )
-            .await?;
-            let denied = run_prompt(&mut client, &session, &|index| index == 0).await?;
-            assert!(denied.response.get("error").is_none(), "{}", denied.response);
-            assert_eq!(denied.response["result"]["stopReason"], "end_turn");
-            assert_eq!(denied.asked.len(), 2, "{:?}", denied.titles());
-            assert!(
-                !workspace.join("nested.txt").exists(),
-                "a rejected nested write must not run"
-            );
-
-            let session = new_session(
-                &mut client,
-                &manager,
-                &workspace,
-                vec![
-                    canned::tool_call_turn("r1", "ctx_probe", "{}"),
-                    canned::tool_call_turn("r2", "mcp_fixture_echo", r#"{"text":"control"}"#),
-                    canned::tool_call_turn("r3", "ctx_note", r#"{"text":"must-not-be-written"}"#),
-                    canned::tool_call_turn("r4", "mcp_fixture_echo", r#"{"text":"rejected"}"#),
-                    canned::simple_text_turn("rejections done"),
-                ],
-                false,
-            )
-            .await?;
-            let rejected = run_prompt(&mut client, &session, &|index| index < 2).await?;
-            assert_eq!(rejected.asked.len(), 4, "{:?}", rejected.titles());
-            let rendered = rejected.rendered();
-            assert!(rendered.contains("mcp-ran:echo:control"), "{rendered}");
-            assert!(!rendered.contains("mcp-ran:echo:rejected"), "{rendered}");
-            assert!(!rendered.contains("note.txt"), "{rendered}");
-
-            let session = new_session(
-                &mut client,
-                &manager,
-                &workspace,
-                vec![
-                    canned::tool_call_turn("p1", "ctx_probe", "{}"),
-                    canned::tool_call_turn("p2", "mcp_fixture_echo", r#"{"text":"plan"}"#),
-                    canned::simple_text_turn("plan done"),
-                ],
-                true,
-            )
-            .await?;
-            let plan = run_prompt(&mut client, &session, &|_| true).await?;
-            assert!(plan.asked.is_empty(), "{:?}", plan.titles());
-            assert_eq!(plan.completed(), 0, "{}", plan.rendered());
-            assert!(!plan.rendered().contains("mcp-ran:"));
-
-            let session = new_session(
-                &mut client,
-                &manager,
-                &workspace,
-                vec![
-                    canned::tool_call_turn("f1", "mcp_fixture_hidden", r#"{"text":"hid"}"#),
-                    canned::tool_call_turn("f2", "mcp_off_echo", r#"{"text":"off"}"#),
-                    canned::tool_call_turn("f3", "mcp_evil_echo", r#"{"text":"evil"}"#),
-                    canned::tool_call_turn(
-                        "f4",
-                        "start_mcp_server",
-                        r#"{"name":"evil","command":"node","args":["-e","0"]}"#,
-                    ),
-                    canned::tool_call_turn("f5", "agent", r#"{"action":"start","prompt":"p"}"#),
-                    canned::simple_text_turn("fabricated done"),
-                ],
-                false,
-            )
-            .await?;
-            let fabricated = run_prompt(&mut client, &session, &|_| true).await?;
-            assert!(fabricated.asked.is_empty(), "{:?}", fabricated.titles());
-            assert_eq!(fabricated.completed(), 0, "{}", fabricated.rendered());
-            assert!(!fabricated.rendered().contains("mcp-ran:"));
-
-            client.request("shutdown", json!({})).await?;
-            Ok::<_, anyhow::Error>(())
-        }
-        .await;
-            if result.is_err() {
-                let _ = client.write.shutdown().await;
-            }
-            result
-        };
-    let (served, scripted) = tokio::join!(connection, script);
-    served?;
-    scripted?;
-    manager.shutdown_and_wait().await?;
-    host.shutdown().await;
-    Ok(())
-}

crates/config/src/settings_schema.rs

@@ -1313,7 +1313,7 @@ pub const SETTINGS_SCHEMA: &[SettingDef] = &[
     def(
         "telemetry",
         SettingKind::Bool(TELEMETRY),
-        "true",
+        "false",
         ui(
             TAB_TRUST,
             "network",

crates/engine/Cargo.toml

@@ -219,9 +219,6 @@ libc = "0.2"
 windows-sys = { version = "0.61.2", features = ["Wdk_Storage_FileSystem", "Win32_System_IO", "Win32_Foundation", "Win32_Security", "Win32_Security_Authorization", "Win32_Security_Isolation", "Win32_Storage_FileSystem", "Win32_System_LibraryLoader", "Win32_System_Pipes", "Win32_System_Threading", "Win32_System_SystemServices", "Win32_System_WindowsProgramming"] }
 
 
-[target.'cfg(any(target_os = "macos", target_os = "windows", all(target_os = "linux", not(target_env = "ohos"))))'.dependencies]
-arboard = { version = "3.4", features = ["wayland-data-control"] }
-
 [target.'cfg(not(target_env = "ohos"))'.dependencies]
 portable-pty = "0.9"
 

crates/engine/src/client/system_one.rs

@@ -138,16 +138,6 @@ pub struct SystemOneResponse {
     pub answers_validated: Option<bool>,
 }
 
-impl SystemOneResponse {
-    pub fn abstained_questions(&self, names: &[&str]) -> Vec<String> {
-        names
-            .iter()
-            .filter(|name| self.answers.get(**name).is_some_and(|a| a.abstained))
-            .map(|name| (*name).to_string())
-            .collect()
-    }
-}
-
 impl<'de> Deserialize<'de> for SystemOneResponse {
     fn deserialize<D: serde::Deserializer<'de>>(
         deserializer: D,
@@ -211,8 +201,6 @@ pub struct SystemOneAnswer {
     pub probabilities: BTreeMap<String, Option<f64>>,
     #[serde(default)]
     pub confidence: Option<f64>,
-    #[serde(default)]
-    pub abstained: bool,
 }
 
 /// Provider usage. OpenRouter adds `cost`; the token-count casing differs

crates/engine/src/command_catalog.rs

@@ -29,8 +29,6 @@ pub struct UserCommand {
     pub takes_arguments: bool,
     pub hidden: bool,
     pub extension: bool,
-    pub plugin_id: Option<String>,
-    pub workspace_sourced: bool,
     pub builtin_bindings: Vec<String>,
 }
 

crates/engine/src/core/authority/auto_review.rs

@@ -2152,10 +2152,7 @@ fn git_push_refspec_is_protected(refspec: &str) -> bool {
     // Tag-like names (`v1`, `v0.9.1`): git resolves branch-vs-tag on the
     // server, so treat them as publishes.
     let mut chars = lower.chars();
-    if chars.next() == Some('v') && chars.next().is_some_and(|ch| ch.is_ascii_digit()) {
-        return true;
-    }
-    false
+    chars.next() == Some('v') && chars.next().is_some_and(|ch| ch.is_ascii_digit())
 }
 
 fn git_tag_tokens_are_publish_like(tokens: &[&str]) -> bool {

crates/engine/src/core/engine/tests/rlm_host.rs

@@ -456,7 +456,7 @@ async fn captured_identity_cancel_and_task_bounds_refuse_before_any_provider() {
 
 #[tokio::test]
 async fn dropping_an_actual_dispatched_core_call_keeps_unknown_usage_without_retaining_authority() {
-    struct Pending(Arc<tokio::sync::Notify>);
+    struct Pending;
     impl Replies for Pending {
         fn effective_route_envelope(
             &self,
@@ -478,42 +478,24 @@ async fn dropping_an_actual_dispatched_core_call_keeps_unknown_usage_without_ret
             &self,
             _: MessageRequest,
         ) -> Pin<Box<dyn Future<Output = anyhow::Result<MessageResponse>> + Send + '_>> {
-            self.0.notify_one();
             Box::pin(std::future::pending())
         }
     }
-    let entered = Arc::new(tokio::sync::Notify::new());
-    let caller = Arc::new(caller_for(
-        Arc::new(Pending(entered.clone())),
-        "captured-model",
-    ));
+    let caller = Arc::new(caller_for(Arc::new(Pending), "captured-model"));
     let weak_caller = Arc::downgrade(&caller);
     let usage = RlmUsageAccumulator::new();
-    let mut dispatch = caller.dispatch(RlmInvocation {
-        prompt: "pending".into(),
-        mode: RlmMode::Completion,
-        max_tokens: None,
-        task_instructions: None,
-        deadline: Some(tokio::time::Instant::now() + Duration::from_secs(600)),
-        gate: None,
-        events: None,
-        usage: usage.clone(),
-    });
-    tokio::time::timeout(Duration::from_secs(10), async {
-        tokio::select! {
-            biased;
-            () = entered.notified() => {}
-            result = &mut dispatch => panic!(
-                "dropped dispatch never reached the client: {:?}",
-                result.error
-            ),
-        }
-    })
-    .await
-    .expect("the dispatched call must reach the client");
-    tokio::time::pause();
-    tokio::time::advance(Duration::from_secs(601)).await;
-    let result = dispatch.await;
+    let result = caller
+        .dispatch(RlmInvocation {
+            prompt: "pending".into(),
+            mode: RlmMode::Completion,
+            max_tokens: None,
+            task_instructions: None,
+            deadline: Some(tokio::time::Instant::now() + Duration::from_millis(100)),
+            gate: None,
+            events: None,
+            usage: usage.clone(),
+        })
+        .await;
     assert!(
         result
             .error

crates/engine/src/cost_status.rs

@@ -2643,7 +2643,6 @@ pub fn decision_receipt_fixture(source_id: &str) -> RuntimeDecisionReceipt {
             probabilities_bp: Default::default(),
             confidence_bp: 0,
             min_confidence_bp: 5_000,
-            abstained_questions: Vec::new(),
             cost_saving_kept_fast: false,
             thinking: None,
             provider_reported_cost_usd: Some("0.000012054".to_string()),

crates/engine/src/extension_host/dsh_workspace.rs

@@ -203,10 +203,13 @@ impl Drop for TestOverlay {
 
 fn overlay_granted() -> bool {
     #[cfg(test)]
-    if TEST_OVERLAY.with(std::cell::Cell::get) {
-        return true;
+    {
+        TEST_OVERLAY.with(std::cell::Cell::get)
+    }
+    #[cfg(not(test))]
+    {
+        false
     }
-    false
 }
 
 fn caller(call: &BrokerCall, tool_name: &'static str) -> Result<ToolContext, BrokerRefusal> {

crates/engine/src/fleet/manager.rs

@@ -1748,11 +1748,7 @@ impl FleetManager {
                 return Err(start_error);
             }
         };
-        if !started {
-            return Ok(false);
-        }
-
-        Ok(true)
+        Ok(started)
     }
 
     fn start_leased_workers(

crates/engine/src/model_inventory.rs

@@ -282,20 +282,31 @@ impl ModelInventory {
                 // vendor-family heuristic) carries the number *and* the fact
                 // that nobody verified it — the auto-router must not read a
                 // guessed window as a route capability.
-                let mut context_window_unverified = true;
+                let mut context_window_unverified =
+                    codewhale_config::catalog::reviewed::intrinsic_model(&model)
+                        .and_then(|row| row.context_window)
+                        .is_none();
                 if let Ok(route) = crate::route_runtime::resolve_runtime_route_for_identity(
                     config,
                     &identity,
                     Some(&model),
                 ) {
-                    capability.context_window = route.context_window.tokens;
-                    context_window_unverified = !route.context_window.source.is_verified();
-                    capability.max_output = route
+                    if let Some(context_window) = route.candidate.limits().context_tokens {
+                        capability.context_window = context_window.min(u64::from(u32::MAX)) as u32;
+                        context_window_unverified = !route.context_window.source.is_verified();
+                    }
+                    // A concrete offering maximum is a stronger fact than the
+                    // static compatibility matrix — and is the only way a
+                    // membership route (no static cap) gets a known ceiling.
+                    if let Some(max_output) = route
                         .candidate
                         .limits()
                         .output_tokens
                         .and_then(|tokens| u32::try_from(tokens).ok())
-                        .filter(|tokens| *tokens > 0);
+                        .filter(|tokens| *tokens > 0)
+                    {
+                        capability.max_output = Some(max_output);
+                    }
                     user_declared = route
                         .candidate
                         .applied_limit_overrides()
@@ -305,6 +316,13 @@ impl ModelInventory {
                                 == codewhale_config::route::OverrideSource::UserModelMetadata
                         });
                     if user_declared {
+                        context_window_unverified = !route.context_window.source.is_verified();
+                        capability.context_window = route.context_window.tokens;
+                        capability.max_output = route
+                            .candidate
+                            .limits()
+                            .output_tokens
+                            .and_then(|value| u32::try_from(value).ok());
                         capability.thinking_supported = route.candidate.capabilities().reasoning
                             == codewhale_config::route::CapabilityState::Supported;
                     }

crates/engine/src/model_routing.rs

@@ -1852,7 +1852,6 @@ pub struct ValidChoice {
     pub choice: String,
     pub probabilities_bp: BTreeMap<String, u16>,
     pub confidence_bp: u16,
-    pub abstained: bool,
 }
 
 /// Validate one `choice` answer against the offered options. Any violation
@@ -1895,7 +1894,6 @@ pub fn validated_choice(answer: Option<&SystemOneAnswer>, options: &[&str]) -> O
         choice: choice.to_string(),
         probabilities_bp,
         confidence_bp: probability_bp(confidence),
-        abstained: answer.abstained,
     })
 }
 
@@ -1984,7 +1982,6 @@ fn decision_attempt_from_response(
         probabilities_bp: Default::default(),
         confidence_bp: 0,
         min_confidence_bp: inventory.router_min_confidence_bp,
-        abstained_questions: response.abstained_questions(&["tier", "thinking"]),
         cost_saving_kept_fast: false,
         thinking: None,
         provider_reported_cost_usd: response
@@ -2008,18 +2005,17 @@ fn decision_attempt_from_response(
     let min_confidence_bp = inventory.router_min_confidence_bp;
     // An invalid or unsure `thinking` answer drops only the effort.
     let thinking = validated_choice(response.answers.get("thinking"), &DECISION_THINKING_OPTIONS)
-        .filter(|thinking| !thinking.abstained && thinking.confidence_bp >= min_confidence_bp)
+        .filter(|thinking| thinking.confidence_bp >= min_confidence_bp)
         .map(|thinking| thinking.choice);
     let strong_bp = tier.probabilities_bp.get("strong").copied().unwrap_or(0);
     let cost_saving_kept_fast =
         cost_saving && tier.choice == "strong" && strong_bp < COST_SAVING_STRONG_MIN_BP;
-    let acted = !tier.abstained && tier.confidence_bp >= min_confidence_bp;
+    let acted = tier.confidence_bp >= min_confidence_bp;
     attempt.decision = Some(AutoRouteDecisionEvidence {
         choice: tier.choice.clone(),
         probabilities_bp: tier.probabilities_bp,
         confidence_bp: tier.confidence_bp,
         min_confidence_bp,
-        abstained_questions: response.abstained_questions(&["tier", "thinking"]),
         cost_saving_kept_fast: acted && cost_saving_kept_fast,
         thinking: thinking.clone().filter(|_| acted),
         provider_reported_cost_usd: response
@@ -4191,60 +4187,6 @@ mod decision_router_tests {
         );
     }
 
-    #[test]
-    fn explicit_abstention_survives_decode_and_never_authorizes_auto_at_floor_zero() {
-        let _env = hermetic_env();
-        let mut config = decision_config("https://openrouter.invalid/api/v1", false, 2);
-        config
-            .auto
-            .as_mut()
-            .unwrap()
-            .router
-            .as_mut()
-            .unwrap()
-            .min_confidence = Some(0.0);
-        let inventory = ModelInventory::from_config(&config).unwrap();
-        let attempt = |body: serde_json::Value| {
-            decision_attempt_from_response(false, &inventory, &pair(), None, &parsed(body), 120)
-        };
-        let mut body = answer_body(0.1, 0.9);
-        body["answers"]["thinking"]["abstained"] = true.into();
-        let effort_abstained = attempt(body.clone());
-        let recommendation = effort_abstained
-            .recommendation
-            .expect("valid tier survives effort abstention");
-        assert_eq!(recommendation.model, "deepseek-v4-flash");
-        assert_eq!(recommendation.reasoning_effort, None);
-        assert_eq!(
-            effort_abstained.decision.unwrap().abstained_questions,
-            vec!["thinking"]
-        );
-        body["answers"]["tier"]["abstained"] = true.into();
-        let tier_abstained = attempt(body);
-        assert!(tier_abstained.recommendation.is_none());
-        assert_eq!(
-            tier_abstained.fallback_reason,
-            Some(AutoRouteHeuristicReason::LowConfidence)
-        );
-        assert_eq!(tier_abstained.failure, None);
-        let decision = tier_abstained.decision.unwrap();
-        assert_eq!(decision.abstained_questions, vec!["tier", "thinking"]);
-        assert_eq!(decision.choice, "fast");
-        assert_eq!(
-            decision.provider_reported_cost_usd.as_deref(),
-            Some("0.000019992")
-        );
-    }
-
-    #[test]
-    fn non_boolean_abstention_is_refused_not_ignored() {
-        let mut body = answer_body(0.1, 0.9);
-        body["answers"]["tier"]["abstained"] = "yes".into();
-        let attempt = policy(false, &parsed(body));
-        assert!(attempt.recommendation.is_none());
-        assert_eq!(attempt.failure, Some(AutoRouterFailure::InvalidAnswer));
-    }
-
     #[test]
     fn invalid_answers_are_rejected_not_repaired() {
         let mut outside = answer_body(0.8, 0.6);

crates/engine/src/provider_lake.rs

@@ -1455,24 +1455,6 @@ pub fn configured_catalog_models_for_route(
     ids
 }
 
-pub fn listed_models_for_route(route_config: &Config, identity: &ProviderIdentity) -> Vec<String> {
-    let mut models = configured_catalog_models_for_route(
-        route_config,
-        identity.provider,
-        identity.key.as_str(),
-        &route_config.active_route_base_url(),
-    );
-    if identity.provider != ProviderKind::OpenaiCodex {
-        let default_model = route_config.default_model();
-        if !default_model.is_empty() && !default_model.eq_ignore_ascii_case("auto") {
-            push_unique_model(&mut models, &default_model);
-        }
-        models.sort();
-        models.dedup();
-    }
-    models
-}
-
 /// Look up the **bundled-snapshot** offering for `(provider, wire_model_id)`,
 /// ignoring any live rows merged over it.
 ///
@@ -2237,8 +2219,23 @@ pub async fn run_models(
     route_config
         .scope_to_provider_identity(identity)
         .map_err(anyhow::Error::msg)?;
-    let models = listed_models_for_route(&route_config, identity);
+    let mut models = configured_catalog_models_for_route(
+        &route_config,
+        identity.provider,
+        identity.key.as_str(),
+        &route_config.active_route_base_url(),
+    );
     let default_model = route_config.default_model();
+    if identity.provider != ProviderKind::OpenaiCodex
+        && !default_model.is_empty()
+        && !default_model.eq_ignore_ascii_case("auto")
+    {
+        push_unique_model(&mut models, &default_model);
+    }
+    if identity.provider != ProviderKind::OpenaiCodex {
+        models.sort();
+        models.dedup();
+    }
     if json {
         // Preserve the existing array + AvailableModel field shape.
         let chatgpt_roster = (identity.provider == ProviderKind::OpenaiCodex)

crates/engine/src/route_preferences.rs

@@ -325,7 +325,7 @@ pub fn selected_route(path: &Path) -> Result<(String, String, codewhale_config::
 pub fn list_models(
     store: &codewhale_config::ConfigStore,
     filter: Option<ProviderKind>,
-) -> Result<Vec<(String, Vec<String>)>> {
+) -> Result<Vec<(ProviderKind, Vec<String>)>> {
     crate::models_dev_live::maybe_load_persisted_cache();
     let mut config = saved_config(store)?;
     config.base_url_env_receipt = config
@@ -333,33 +333,42 @@ pub fn list_models(
         .map_or(BaseUrlEnvReceipt::NoOwner, |identity| {
             BaseUrlEnvReceipt::Route(identity.provider, identity.key.to_string())
         });
-    let mut custom_routes: Vec<String> = config
-        .providers
-        .as_ref()
-        .map(|providers| providers.custom.keys().cloned().collect())
-        .unwrap_or_default();
-    custom_routes.sort();
     let providers = filter
         .as_ref()
         .map_or(ProviderKind::all(), std::slice::from_ref);
     let mut catalogs = Vec::with_capacity(providers.len());
     for provider in providers {
-        let routes = if *provider == ProviderKind::Custom {
-            custom_routes.clone()
-        } else {
-            vec![provider.as_str().to_string()]
-        };
-        for route in routes {
-            let identity = config
-                .legacy_selection_identity(&route)
-                .map_err(anyhow::Error::msg)?;
-            let mut route_config = config.clone();
-            route_config
-                .scope_to_provider_identity(&identity)
-                .map_err(anyhow::Error::msg)?;
-            let models = crate::provider_lake::listed_models_for_route(&route_config, &identity);
-            catalogs.push((route, models));
+        if *provider == ProviderKind::Custom
+            && config
+                .providers
+                .as_ref()
+                .and_then(|providers| providers.custom_provider_config(provider.as_str()))
+                .is_none()
+        {
+            continue;
         }
+        let identity = config
+            .legacy_selection_identity(provider.as_str())
+            .map_err(anyhow::Error::msg)?;
+        let mut route_config = config.clone();
+        route_config
+            .scope_to_provider_identity(&identity)
+            .map_err(anyhow::Error::msg)?;
+        let mut models = crate::provider_lake::configured_catalog_models_for_route(
+            &route_config,
+            identity.provider,
+            identity.key.as_str(),
+            &route_config.active_route_base_url(),
+        );
+        if identity.provider != ProviderKind::OpenaiCodex {
+            let default_model = route_config.default_model();
+            if !default_model.is_empty() && !default_model.eq_ignore_ascii_case("auto") {
+                models.push(default_model);
+            }
+            models.sort();
+            models.dedup();
+        }
+        catalogs.push((*provider, models));
     }
     Ok(catalogs)
 }
@@ -409,12 +418,10 @@ pub fn resolve_model(
                 .into(),
             );
         }
-        if !crate::provider_catalog_live::provider_owns_live_catalog(identity.provider, base_url) {
-            codewhale_agent::ModelRegistry::default().resolve(
-                model.filter(|model| *model != "auto"),
-                Some(identity.provider),
-            )?;
-        }
+        codewhale_agent::ModelRegistry::default().resolve(
+            model.filter(|model| *model != "auto"),
+            Some(identity.provider),
+        )?;
     }
     Ok(route?.candidate)
 }

crates/engine/src/superfast.rs

@@ -451,11 +451,6 @@ async fn evaluate(
                             .map_or_else(Default::default, |v| v.probabilities_bp.clone()),
                         confidence_bp: intent.as_ref().map_or(0, |v| v.confidence_bp),
                         min_confidence_bp: 5_000,
-                        abstained_questions: response.abstained_questions(&[
-                            "intent",
-                            "needs_tool",
-                            "answerable_from_context",
-                        ]),
                         cost_saving_kept_fast: false,
                         thinking: None,
                         provider_reported_cost_usd: response
@@ -526,7 +521,7 @@ fn unit_interval(value: Option<f64>) -> Option<f64> {
 /// fast route.
 fn read_noul(response: &SystemOneResponse, key: &str) -> Option<f64> {
     let answer = response.answers.get(key)?;
-    (answer.kind == "noul" && !answer.abstained)
+    (answer.kind == "noul")
         .then_some(answer.noul)
         .and_then(unit_interval)
 }
@@ -553,9 +548,7 @@ fn derive_route(response: &SystemOneResponse) -> Route {
         response.answers.get("intent"),
         &["code_change", "code_question", "command", "chat", "other"],
     )
-    .is_some_and(|intent| {
-        !intent.abstained && intent.choice == "chat" && intent.confidence_bp >= 5_000
-    });
+    .is_some_and(|intent| intent.choice == "chat" && intent.confidence_bp >= 5_000);
     if intent_is_calibrated_chat && needs_tool.is_some_and(|nt| nt <= 0.2) {
         return Route::PlainChat;
     }
@@ -571,23 +564,6 @@ mod tests {
 
     const TYPESAFE_TEST_KEY: &str = "sf-typesafe-test-key-0123456789";
 
-    #[test]
-    fn explicit_abstention_never_authorizes_a_shadow_route() {
-        let mut value = json!({"answers":{
-            "intent":{"type":"choice","choice":"chat","confidence":0.9,
-                "probabilities":{"chat":0.9,"code_change":0.1,"code_question":0.0,"command":0.0,"other":0.0}},
-            "needs_tool":{"type":"noul","noul":0.1},
-            "answerable_from_context":{"type":"noul","noul":0.1}}});
-        let decoded =
-            |value: Value| serde_json::from_value::<SystemOneResponse>(value).expect("response");
-        assert_eq!(derive_route(&decoded(value.clone())), Route::PlainChat);
-        value["answers"]["intent"]["abstained"] = true.into();
-        assert_eq!(derive_route(&decoded(value.clone())), Route::Unknown);
-        value["answers"]["needs_tool"]["noul"] = 0.95.into();
-        value["answers"]["needs_tool"]["abstained"] = true.into();
-        assert_eq!(derive_route(&decoded(value)), Route::Unknown);
-    }
-
     /// Fields drop in declaration order: restore the environment before the
     /// lock is released, or another test observes our overrides.
     struct Env {

crates/engine/src/tools/subagent/coord/ledger.rs

@@ -133,14 +133,9 @@ impl WriteScopeClaim {
                 return true;
             }
         }
-        if self
-            .contracts
+        self.contracts
             .iter()
             .any(|contract| other.contracts.iter().any(|other| other == contract))
-        {
-            return true;
-        }
-        false
     }
 
     #[must_use]

crates/models/src/auto_route_evidence.rs

@@ -11,8 +11,6 @@ pub struct AutoRouteDecisionEvidence {
     pub probabilities_bp: BTreeMap<String, u16>,
     pub confidence_bp: u16,
     pub min_confidence_bp: u16,
-    #[serde(default, skip_serializing_if = "Vec::is_empty")]
-    pub abstained_questions: Vec<String>,
     /// `[auto] cost_saving` kept the fast tier because the strong tier's
     /// probability was below the cost-saving floor.
     #[serde(default, skip_serializing_if = "std::ops::Not::not")]

crates/tui/CHANGELOG.md

@@ -11,12 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **Non-ASCII file names:** `/diff`, the `@git` and `@diff` mentions and the Runtime API workspace diff now show paths with Chinese, emoji and other non-ASCII characters as written instead of as quoted octal escapes, and the turn context no longer lists the workspace root as an empty "Active paths" entry. Thanks [@luochen211](https://github.com/luochen211) (PR 7317).
 - **Session names after a crash, and keep-forever snapshot retention:** a session name saved right after a crash that cut off the previous session-index line is no longer lost, because the new entry now starts on its own line; and a very large `[snapshots] max_age_days` (such as `9223372036854775807` for "keep forever") no longer wraps around and deletes every undo snapshot at session start. Thanks [@luochen211](https://github.com/luochen211) (PR 7316).
 - **Blank environment variables:** exporting a variable empty (for example `CODEWHALE_MODEL=` from a compose `${VAR:-}` template) no longer hides its legacy alias. `DEEPSEEK_MODEL`, `DEEPSEEK_BASE_URL`, `KIMI_BASE_URL`, `DEEPSEEK_FORCE_HTTP1`, `DEEPSEEK_STREAM_OPEN_TIMEOUT_SECS` and the other provider alias variables now apply as they do when the primary is unset. Thanks [@luochen211](https://github.com/luochen211) (PR 7315).
-- **Qwen Code as an external agent:** Codewhale now finds an installed Qwen Code CLI (`qwen`, 0.6.1 or newer) and can run it as a session over ACP with `qwen --acp`. `GET /v1/agents/external` lists it, an older install is reported as needing `npm i -g @qwen-code/qwen-code@latest`, and sign-in stays inside Qwen Code (`/auth`). Thanks [@MannXo](https://github.com/MannXo) (PR 7293).
-- **Telemetry setting default:** the settings schema API reports telemetry's default as on, matching what Codewhale does when you have not chosen.
-- **Auto routing abstention:** when the decision model marks a tier, effort or shadow answer `abstained: true`, Auto no longer acts on it, even with `min_confidence = 0`: an abstained tier takes the local fallback, an abstained effort keeps the tier and drops only the effort, and the routing receipt lists the abstained questions.
-- **Plugin index (Runtime API):** a new `GET /v1/apps/plugin-index` route lists plugins, skills, connectors, hooks and hand-written commands with kind, source and state, and `/v1/commands` rows say which plugin (`plugin_id`) added a command and whether a command came from the project (`workspace_sourced`) (CW-8092).
-- **Model commands and routing:** `codewhale model list` now lists every custom endpoint you have configured, under its own name. `codewhale model resolve` no longer refuses a model on a custom endpoint, router or local server whose model list has not been fetched yet; once a list is fetched, a model missing from it is still refused. Automatic routing marks a context window as verified only when the route itself supplies it, and no longer reports a guessed output limit.
-- **ACP:** when a plugin tool asks the core to run a tool that needs approval, the editor now gets a `session/request_permission` on the plugin tool's call that names the nested tool and its input; before, the prompt ended with an internal error (CW-8050).
+- **Qwen Code as an external agent:** Codewhale now finds an installed Qwen Code CLI (`qwen`, 0.6.1 or newer) and can run it as a session over ACP with `qwen --acp`. `GET /v1/agents/external` lists it, an older install is reported as needing `npm i -g @qwen-code/qwen-code@latest`, and sign-in stays inside Qwen Code (`/auth`). Thanks [@MannXo](https://github.com/MannXo) (#7293).
 - **README and contributor credit:** the repository front page now opens the way the website does: the line "The model can be anyone's. The agent should be yours.", one sentence on what Codewhale is, the install command and one picture, with reference detail moved into the linked guides; the 18 translated READMEs follow the same structure and say they are machine-drafted. The contributor wall and the website now count the same 433 people (407 GitHub accounts and the commit authors whose email is not linked to an account), where the website had counted accounts only. `DEPENDENCY_SECURITY.md` moved into `docs/dependency-maintenance.md`, and `.github/SUPPORT.md` says where to ask for help.
 - **Website Plugins page:** The website's Plugins page now describes what the released version does, and a labelled section says what 0.10.3 adds: one Plugins place, Standard and Creator mode, and the Permissions control.
 - **Plugin docs and plugin-creator:** Docs now say everything you add is a plugin. The bundled plugin-creator skill no longer tells an agent never to trust or enable a plugin (in Full Access it may, for one it wrote and installed from its project), points code and screen plugins at cordis-plugin-development, and an untouched copy from 0.10.2 now upgrades. The Chinese extension and Runtime API docs now say editor ACP sessions get plugin tools and configured MCP servers.

crates/tui/src/commands/discovery.rs

@@ -85,7 +85,6 @@ mod tests {
             aliases: aliases.iter().map(|s| s.to_string()).collect(),
             hidden,
             plugin_authority: None,
-            workspace_sourced: false,
             extension: None,
         }
     }

crates/tui/src/commands/mod.rs

@@ -296,11 +296,6 @@ impl codewhale_engine::command_catalog::CommandCatalog for CommandTable {
                     takes_arguments: metadata.takes_arguments(),
                     hidden: metadata.hidden,
                     extension: metadata.extension.is_some(),
-                    plugin_id: metadata
-                        .plugin_authority
-                        .as_ref()
-                        .map(|authority| authority.plugin_id.as_str().to_string()),
-                    workspace_sourced: metadata.workspace_sourced,
                     builtin_bindings: bindings.remove(&metadata.name).unwrap_or_default(),
                 })
                 .collect()

crates/tui/src/commands/user_registry.rs

@@ -80,7 +80,6 @@ pub struct UserCommandMetadata {
     pub aliases: Vec<String>,
     pub hidden: bool,
     pub plugin_authority: Option<codewhale_config::PluginAuthority>,
-    pub workspace_sourced: bool,
     /// Set for a command contributed by an extension-host plugin: it runs in
     /// the host (`command/run`) instead of expanding `body`.
     pub extension: Option<codewhale_engine::extension_host::command::ExtensionCommandRef>,
@@ -247,7 +246,6 @@ impl UserCommandRegistry {
                 let (mut metadata, errors) =
                     parse_metadata(entry.name, &entry.content, &entry.path);
                 metadata.plugin_authority = entry.plugin_authority;
-                metadata.workspace_sourced = entry.workspace_sourced;
                 (metadata, errors, entry.path, entry.workspace_sourced)
             })
             .collect::<Vec<_>>();
@@ -397,7 +395,6 @@ impl UserCommandRegistry {
                     aliases: Vec::new(),
                     hidden: false,
                     plugin_authority: Some(entry.authority),
-                    workspace_sourced: false,
                     extension: Some(reference),
                 },
             );
@@ -485,7 +482,6 @@ fn parse_metadata(
         aliases: Vec::new(),
         hidden: false,
         plugin_authority: None,
-        workspace_sourced: false,
         extension: None,
     };
     let mut configured_name = None;

crates/tui/src/tui/context_menu.rs

@@ -284,8 +284,8 @@ impl ContextMenuView {
         if start > 0 {
             rows.push(MenuRow::MoreAbove(start));
         }
-        for idx in start..end {
-            if idx > start && self.entries[idx].section_start {
+        for (idx, entry) in self.entries.iter().enumerate().take(end).skip(start) {
+            if idx > start && entry.section_start {
                 rows.push(MenuRow::Divider);
             }
             rows.push(MenuRow::Entry(idx));

crates/tui/src/tui/transcript/tests.rs

@@ -1441,8 +1441,8 @@ fn prose_cells_fill_full_width_on_ultrawide_by_default() {
     let mut cache = TranscriptViewCache::new();
     cache.ensure_filtered(&refs, &revisions, 220, options, &HashMap::new(), None, None);
 
-    for idx in 0..3 {
-        let width = max_line_width(&cache.per_cell[idx].lines);
+    for (idx, cell) in cache.per_cell.iter().enumerate().take(3) {
+        let width = max_line_width(&cell.lines);
         assert!(
             width > RETIRED_RAIL_MEASURE,
             "prose cell {idx} wrapped to {width} columns — still on the retired \
@@ -1495,8 +1495,8 @@ fn transcript_prose_measure_caps_prose_but_not_tools() {
     let mut cache = TranscriptViewCache::new();
     cache.ensure_filtered(&refs, &revisions, 220, options, &HashMap::new(), None, None);
 
-    for idx in 0..3 {
-        let width = max_line_width(&cache.per_cell[idx].lines);
+    for (idx, cell) in cache.per_cell.iter().enumerate().take(3) {
+        let width = max_line_width(&cell.lines);
         assert!(
             width > 105,
             "prose cell {idx} wrapped to {width} columns — still on the retired \

crates/tui/src/tui/ui/activity_detail.rs

@@ -1771,7 +1771,6 @@ mod tests {
                 .collect(),
             confidence_bp: 6400,
             min_confidence_bp: 5000,
-            abstained_questions: Vec::new(),
             cost_saving_kept_fast: false,
             thinking: Some("max".to_string()),
             provider_reported_cost_usd: Some("0.000019992".to_string()),

crates/tui/src/tui/ui/terminal.rs

@@ -1110,7 +1110,7 @@ mod screen_mode_tests {
                         viewport: ratatui::Viewport::Inline(3),
                     },
                 )
-                .map_err(|err| io::Error::other(err.to_string()))
+                .map_err(|err| match err {})
             },
         )
         .expect("a successful probe must switch");

docs/CONTRIBUTORS.md

@@ -44,6 +44,7 @@ changelog or release notes, and this contributor record.
 
 **Contributions**
 
+- **[MannXo](https://github.com/MannXo)** — added Qwen Code to the external agent registry so an installed Qwen Code CLI runs as a session over ACP ([#7293](https://github.com/codewhale-hq/Codewhale/pull/7293)).
 - **[SamhandsomeLee](https://github.com/SamhandsomeLee)** — drove Responses request, URL and stream behavior from one checked dialect profile table ([#7261](https://github.com/codewhale-hq/Codewhale/pull/7261)).
 - **[gaord](https://github.com/gaord)** — ran the read-only `/system`, `/tokens` and `/cost` builtins over the Runtime API through one gated terminal-host catalog ([#7277](https://github.com/codewhale-hq/Codewhale/pull/7277)).
 

docs/EXTENSIONS.md

@@ -545,7 +545,7 @@ Return `{kind:'deny', reason}`, `{kind:'ask', reason?}`, `{kind:'revise', input}
 
 Native hooks run first, then mod listeners in core registration order. Denial always wins; the last accepted input revision wins. Rust re-prepares revised arguments and reruns the existing authority, policy, and approval checks. Input revisions use the existing 32 KiB hook limit; context and reasons use the existing sanitizers. Unloading a fiber removes its listener, and disabling or revoking an owner retires its admitted handles before host teardown. Other workspaces do not receive the call.
 
-This bridge runs on Engine sessions, including model tools, gated code-mode calls, and `exec.core` calls. Sessions an editor drives over ACP (`codewhale serve --acp`) get the same extension host, under the same `[features]` flags (`extension_host`, `mcp`): reviewed plugin tools (TypeScript and DSH) and the MCP servers configured in Codewhale appear as ACP tool calls and ask through the session's permission setting; Plan stays read-only. When a plugin tool asks the core to run a tool that needs approval (`exec.core`), the editor's permission request is shown on the plugin tool's call and names the nested tool and its input. The ACP server's capabilities say so (`agentCapabilities._meta.codewhale`). Servers an ACP client passes in `mcpServers` and configured shell hooks are not attached. Prepend/global listener ordering, DSH runtime/agent handles, around-execution wrappers, and post-result rewriting are not provided. Native `tool_call_after` remains an observer contract.
+This bridge runs on Engine sessions, including model tools, gated code-mode calls, and `exec.core` calls. Sessions an editor drives over ACP (`codewhale serve --acp`) get the same extension host, under the same `[features]` flags (`extension_host`, `mcp`): reviewed plugin tools (TypeScript and DSH) and the MCP servers configured in Codewhale appear as ACP tool calls and ask through the session's permission setting; Plan stays read-only. The ACP server's capabilities say so (`agentCapabilities._meta.codewhale`). Servers an ACP client passes in `mcpServers` and configured shell hooks are not attached. Prepend/global listener ordering, DSH runtime/agent handles, around-execution wrappers, and post-result rewriting are not provided. Native `tool_call_after` remains an observer contract.
 
 ## Asking the core to run a tool
 

docs/RELEASE_RUNBOOK.md

@@ -244,7 +244,30 @@ The manual `ci.yml` path verifies that the dispatch resolved to
 `expected_sha`, disables light-change shortcuts, and forces the heavy Rust,
 workflow, mobile, Actions, Linux, macOS, Windows, npm-wrapper, and documentation
 gates. A mismatch fails before those gates start; it never silently tests a
-different head.
+different head. The Linux, macOS and Windows suites run as `Sharded tests (<os>)`
+(`ci-test-suite.yml`): one test build per OS, parallel nextest shards of that
+archive, and a `Suite check` job that fails unless the shards together ran
+exactly the tests the archive lists; read that job, not only the shard jobs.
+
+`ci.yml` also takes optional scoped-run inputs for a quick answer from an agent
+or a maintainer. With `crate` (one workspace package, for example
+`codewhale-tui`) and/or `filter` (a nextest filterset such as
+`test(auto_review)`) set, only the `Scoped test` job runs, on the operating
+systems named by `os` (default `ubuntu-latest`; a comma-separated list or
+`all`), and the full suite and every other gate are skipped. `expected_sha`
+stays required and is still verified:
+
+```bash
+gh workflow run ci.yml --ref ci/my-task \
+  -f expected_sha="$(git rev-parse HEAD)" \
+  -f crate=codewhale-tui -f filter='test(auto_review)'
+```
+
+A scoped run proves a slice, never a release; release evidence is a full
+dispatch with the scoped inputs empty. A newer dispatch on the same non-main
+branch, and a newer push to a pull request, cancels the older run of the same
+workflow; runs on `main` are keyed by SHA and never cancel each other, and a
+scoped run never cancels a full one.
 
 Verify beforehand that clean local `HEAD`, `main` and `origin/main` agree.
 Record both run URLs, resolved SHAs and required job results; inspect executed

docs/RUNTIME_API.md

@@ -886,13 +886,6 @@ Plugin tools and configured MCP servers on this transport are on main after
 0.10.2; 0.10.2 itself does not have them.
 Client-supplied MCP servers, dynamic tools, task/PTY/background shell,
 interpreter, subagent and RLM lifecycles are unavailable on this transport.
-ACP has no tool search, so every connected MCP tool and its schema is sent with
-every request, and a server marked `lazy = true` never starts. A large MCP set
-therefore costs tokens on each turn and can exceed a provider's tool limit.
-MCP servers a model starts at run time stay out of an ACP-profile host. When
-`serve --acp` instead attaches to a running Runtime owner (see below), its turns
-use that owner's MCP pool, which includes servers started at run time in other
-sessions of the same workspace.
 Built-in overrides remove the
 whole compatibility alias family. Final dispatch rechecks the profile, so a
 fabricated alias, hook rewrite or omitted catalog entry cannot bypass it. Plan
@@ -913,11 +906,7 @@ produced.
 Tool updates begin `pending`. `in_progress` means Core reached final dispatch;
 `completed`/`failed` and typed image blocks come from the actual Core result.
 `session/request_permission` correlates a private JSON-RPC ID to the same
-Runtime-minted pending approval and Core execution ID. When a plugin tool asks
-the core to run a tool that needs approval (`exec.core`), the request is shown
-on the plugin tool's call, names the nested tool and carries its input, and the
-answer releases the nested call; the nested call is decided under the session's
-permission setting. Only an exact live
+Runtime-minted pending approval and Core execution ID. Only an exact live
 `allow-once` response can release that waiter; wrong IDs are ignored, invalid
 options deny, and cancellation withdraws it. ACP grants neither remembered
 permissions nor Native capabilities. Core typed rules, strict hooks, repo law,
@@ -2683,35 +2672,6 @@ thread deletion.
   pure over the snapshot — so a client must not look for one. Anything that
   mutates the session stays a terminal-side command.
 
-**Plugin index**
-- `GET /v1/apps/plugin-index` — `{workspace, items: [...], unavailable: [...],
-  problems: [...]}`: one list across every plugin, skill, connector, hook and
-  hand-written command. It is a projection: each item's `row` is the row its
-  owner's own route returns (`/v1/apps/plugins`, `/v1/apps/plugins/catalog`,
-  `/v1/skills`, `/v1/apps/mcp/servers`, `/v1/hooks`, `/v1/commands`), and
-  `owner` names that route. Per item: `id`, `kind` (`plugin`, `skill`,
-  `connector`, `hook`, `command`), `name`, `description`, `source`
-  (`built_in`, `user`, `project`, `other_app`, `runtime`, `plugin`), `state`
-  (`enabled`, `disabled`, `needs_review`, `needs_sign_in`, `unavailable`) and
-  `labels` (what the item adds: `skill`, `connector`, `hook`, `command`,
-  `tool`, `profile`). A plugin item also has `adds` (`skills`, `connectors`,
-  `hooks`, `commands`, `profiles`: names, not rows), and what a plugin adds is
-  not listed a second time as an item of its own. A built-in switch is a
-  `plugin` item with a `tier` and no labels. `/v1/commands` rows carry
-  `plugin_id` (the same id as `/v1/apps/plugins`, and the `plugin:<id>` item)
-  for a command a plugin adds, and `workspace_sourced` for one read from the
-  project; a command item's `plugin` is that id. An owner that fails is named in
-  `unavailable` and the other kinds still list; `problems` carries the owners'
-  load warnings. Names under `adds` are file names, so a profile's `id` inside its
-  file can differ; a command another plugin registers through the extension host
-  is an item with `source` `plugin`. For an active plugin `adds.commands` comes
-  from the `/v1/commands` rows; for any other plugin, and for `hooks` and
-  `profiles`, it is the file names found in the bundle, at most 512 per kind,
-  with names holding control characters left out; a cut list is reported
-  under `problems`. A hook's row names no plugin, so `adds.hooks` stays file
-  names. `tool` means the plugin declares native or language-server components;
-  a screen a plugin draws is not labelled yet.
-
 **Hooks**
 - `GET /v1/hooks[?thread_id=...]` — `{workspace, enabled, hooks: [...],
   problems: [...]}`: the hook set Runtime API threads run for that workspace

docs/RUNTIME_ROUTES.md

@@ -54,7 +54,6 @@ registration index.
 | POST | `/v1/apps/mcp/servers/{name}/enable` |
 | POST | `/v1/apps/mcp/servers/{name}/reconnect` |
 | GET | `/v1/apps/mcp/tools` |
-| GET | `/v1/apps/plugin-index` |
 | GET | `/v1/apps/plugins` |
 | DELETE / GET | `/v1/apps/plugins/{selector}` |
 | POST | `/v1/apps/plugins/{selector}/disable` |
@@ -264,4 +263,4 @@ registration index.
 | GET / POST | `/v1/worktrees` |
 | POST | `/v1/worktrees/remove` |
 
-The source contains 244 distinct literal paths in this table.
+The source contains 243 distinct literal paths in this table.

docs/zh_hans/EXTENSIONS.md

@@ -252,8 +252,6 @@ DSH 的 `allow` 被视为不干预，每个所有者提示一次；不能预先
 调用。编辑器通过 ACP（`codewhale serve --acp`）驱动的会话获得同一个扩展宿主，并受相同的
 `[features]` 开关（`extension_host`、`mcp`）约束：已审查的插件工具（TypeScript 与 DSH）和
 Codewhale 中配置的 MCP 服务器会作为 ACP 工具调用出现，并通过会话的权限设置询问；Plan 保持只读。
-插件工具通过 `exec.core` 请求核心执行需要审批的工具时，审批请求显示在该插件
-工具的调用上，并写明嵌套工具及其输入。
 ACP 服务器的能力声明会说明这一点（`agentCapabilities._meta.codewhale`）。ACP 客户端在
 `mcpServers` 中传入的服务器和已配置的 shell hooks 不会挂载。`prepend`/`global` 顺序
 覆盖、包裹实际执行的中间件、DSH 运行时句柄和执行后结果改写均不支持。Native

docs/zh_hans/RUNTIME_API.md

@@ -660,11 +660,7 @@ shell 工具，外加已审查的插件工具（`extension_host` 功能）和 Co
 MCP 服务器的工具（`mcp` 功能），均受同一权限设置约束；这一点见于 0.10.2 之后的 main，0.10.2 本身不含。Shell 同时要求编辑器声明
 terminal 支持、操作者允许 `allow_shell`；指定的外部沙箱不可用时不提供 shell。此接口
 不提供客户端传入的 MCP 服务器、动态工具、任务、PTY、后台 shell、解释器、子智能体
-或 RLM 生命周期。ACP 没有工具搜索，因此每个已连接的 MCP 工具及其 schema 都会随每个请求
-发送，标记为 `lazy = true` 的服务器永不启动；MCP 集合很大时每回合都会消耗令牌，并可能超出
-提供商的工具数量上限。模型在运行时启动的 MCP 服务器不会进入 ACP profile 宿主；但当
-`serve --acp` 附着到正在运行的 Runtime owner 时（见下文），其回合使用该 owner 的 MCP 池，
-其中包含同一工作区其他会话在运行时启动的服务器。内置工具覆盖会移除整个兼容别名族。
+或 RLM 生命周期。内置工具覆盖会移除整个兼容别名族。
 最终派发再次校验 profile；伪造别名、hook 改写或目录中缺失的工具不能绕过限制。
 Full Access 下 Plan 仍只读。Full Access 与普通审批姿态是服务端拥有的只读选项，
 编辑器不能放宽。`approval_policy = "never"` 不是 ACP 审批姿态，服务端会拒绝
@@ -673,9 +669,7 @@ Full Access 下 Plan 仍只读。Full Access 与普通审批姿态是服务端
 
 工具首先显示 `pending`；只有 Core 到达最终派发才显示 `in_progress`。
 `completed`/`failed` 和类型化图片块来自实际 Core 结果。审批请求的私有 JSON-RPC ID
-绑定同一个 Runtime 铸造的待决审批与 Core 执行 ID。插件工具通过 `exec.core` 请求核心运行
-需要审批的工具时，请求显示在该插件工具的调用上，写明嵌套工具及其输入，答复释放嵌套调用，嵌套调用在会话的
-权限设置下决定。只有精确匹配、仍有效的
+绑定同一个 Runtime 铸造的待决审批与 Core 执行 ID。只有精确匹配、仍有效的
 `allow-once` 响应能释放等待器；错误 ID 被忽略，无效选项拒绝，取消会撤销等待器。
 ACP 不授予记忆权限或 Native 能力。
 
@@ -1993,19 +1987,6 @@ POST 前保留预期指纹，并在响应及按键 GET 恢复时核对，之后
   保留命令回执——每个提供的处理器对快照都是纯函数——因此客户端不应寻找回执。
   任何会修改会话的操作仍是终端侧命令。
 
-**插件索引**
-- `GET /v1/apps/plugin-index` — `{workspace, items: [...], unavailable: [...],
-  problems: [...]}`：跨所有插件、技能、连接器、钩子和手写命令的统一列表。它只是投影：每个条目的
-  `row` 就是其所属路由（`/v1/apps/plugins`、`/v1/apps/plugins/catalog`、`/v1/skills`、
-  `/v1/apps/mcp/servers`、`/v1/hooks`、`/v1/commands`）返回的那一行，`owner` 给出该路由。
-  每个条目有 `id`、`kind`（`plugin`、`skill`、`connector`、`hook`、`command`）、`name`、
-  `description`、`source`（`built_in`、`user`、`project`、`other_app`、`runtime`、`plugin`）、
-  `state`（`enabled`、`disabled`、`needs_review`、`needs_sign_in`、`unavailable`）和
-  `labels`（它添加的内容：`skill`、`connector`、`hook`、`command`、`tool`、`profile`）。插件条目另有 `adds`（`skills`、`connectors`、`hooks`、`commands`、
-  `profiles`：只含名称），插件所添加的内容不会再作为独立条目重复列出。内置开关是带 `tier`、无 `labels` 的
-  `plugin` 条目。`/v1/commands` 的行对插件添加的命令带有 `plugin_id`（与 `/v1/apps/plugins` 的 id 相同，即 `plugin:<id>` 条目），对从项目读取的命令带有 `workspace_sourced`；命令条目的 `plugin` 即该 id。某个所属路由失败时记入 `unavailable`，其余种类照常列出；`problems`
-  汇总各所属路由的加载警告。`adds` 中的名称是文件名，因此档案文件内部的 `id` 可能不同；通过扩展宿主注册的命令是 `source` 为 `plugin` 的条目。对已启用的插件，`adds.commands` 取自 `/v1/commands` 的行；其他插件以及 `hooks`、`profiles` 取自包内的文件名，每类最多 512 个，含控制字符的名称被略去，列表被截断时在 `problems` 中说明。钩子的行不带插件名，因此 `adds.hooks` 仍是文件名。`tool` 表示插件声明了原生或语言服务器组件；插件绘制的界面暂无标签。
-
 **钩子**
 - `GET /v1/hooks[?thread_id=...]` — `{workspace, enabled, hooks: [...],
   problems: [...]}`：Runtime API 线程为该工作区运行的钩子集合

scripts/ci/compiled-host-test-input.sh

@@ -0,0 +1,18 @@
+#!/usr/bin/env bash
+set -euo pipefail
+bun_binary="$(bun -p 'process.execPath')"
+host_binary="$(node -p "require('path').join(process.env.RUNNER_TEMP, 'codewhale-extension-host' + (process.platform === 'win32' ? '.exe' : ''))")"
+compiled_info="$(node crates/engine/extension-host/compile-host.mjs --bun "$bun_binary" --output "$host_binary")"
+printf 'CODEWHALE_COMPILED_HOST_TEST_BINARY=%s\n' "$host_binary" >> "$GITHUB_ENV"
+node - "$host_binary" "$bun_binary" "$compiled_info" >> "$GITHUB_ENV" <<'JS'
+const fs = require('node:fs'), crypto = require('node:crypto');
+const digest = (file) => crypto.createHash('sha256').update(fs.readFileSync(file)).digest('hex');
+const info = JSON.parse(process.argv[4]);
+if (!info.platform || !info.arch || info.platform !== info.compiler?.platform || info.arch !== info.compiler?.arch) throw new Error('image/compiler identity mismatch');
+console.log('CODEWHALE_COMPILED_HOST_TEST_PLATFORM=' + info.platform);
+console.log('CODEWHALE_COMPILED_HOST_TEST_ARCH=' + info.arch);
+console.log('CODEWHALE_COMPILED_HOST_TEST_SHA256=' + digest(process.argv[2]));
+console.log('CODEWHALE_COMPILED_HOST_TEST_BUN=' + process.argv[3]);
+console.log('CODEWHALE_COMPILED_HOST_TEST_RUNTIME_SHA256=' + digest(process.argv[3]));
+console.log('CODEWHALE_COMPILED_HOST_TEST_BUNDLE_SHA256=' + digest('crates/engine/extension-host/dist/codewhale-extension-host.mjs'));
+JS

scripts/ci/nextest-shard-count.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+"""Count nextest tests so a sharded run can prove it ran every test once.
+
+  list LISTING_JSON         tests the archive selects (nextest list --message-format json)
+  junit JUNIT_XML           tests one nextest invocation ran
+  check DIRECTORY           per OS, the shard files must cover the expected total exactly
+
+The sharded CI suite splits one archive across jobs. A shard that is skipped,
+runs a different filter, or double-counts a partition changes the sum, so the
+suite gate fails instead of reporting a smaller run as a pass.
+"""
+from __future__ import annotations
+
+import json
+import sys
+import xml.etree.ElementTree as ET
+from pathlib import Path
+
+
+def listed(path: str) -> int:
+    suites = json.loads(Path(path).read_text(encoding="utf-8"))["rust-suites"]
+    return sum(
+        1
+        for suite in suites.values()
+        for case in suite["testcases"].values()
+        if case["filter-match"]["status"] == "matches"
+    )
+
+
+def ran(path: str) -> int:
+    return int(ET.parse(path).getroot().get("tests", "0"))
+
+
+def check(directory: str) -> int:
+    files = sorted(Path(directory).rglob("*.json"))
+    expected = {}
+    shards: dict[str, dict[int, int]] = {}
+    for file in files:
+        record = json.loads(file.read_text(encoding="utf-8"))
+        if file.name.startswith("expected-"):
+            expected[record["os"]] = record
+        elif file.name.startswith("shard-"):
+            slot = shards.setdefault(record["os"], {})
+            if record["shard"] in slot:
+                print(f"{record['os']}: shard {record['shard']} reported twice")
+                return 1
+            slot[record["shard"]] = record["tests"]
+    if not expected:
+        print("no expected-<os>.json found")
+        return 1
+    failed = False
+    for os_name, record in sorted(expected.items()):
+        got = shards.get(os_name, {})
+        want = set(range(1, record["shards"] + 1))
+        total = sum(got.values())
+        print(f"{os_name}: archive lists {record['tests']}, shards ran {total} {dict(sorted(got.items()))}")
+        if set(got) != want:
+            print(f"{os_name}: expected shards {sorted(want)}, found {sorted(got)}")
+            failed = True
+        if total != record["tests"]:
+            print(f"{os_name}: shard total {total} differs from the archive's {record['tests']}")
+            failed = True
+        if any(count <= 0 for count in got.values()):
+            print(f"{os_name}: a shard ran no tests")
+            failed = True
+    return 1 if failed else 0
+
+
+def main(argv: list[str]) -> int:
+    if len(argv) == 3 and argv[1] == "list":
+        print(listed(argv[2]))
+        return 0
+    if len(argv) == 3 and argv[1] == "junit":
+        print(ran(argv[2]))
+        return 0
+    if len(argv) == 3 and argv[1] == "check":
+        return check(argv[2])
+    print(__doc__, file=sys.stderr)
+    return 2
+
+
+if __name__ == "__main__":
+    raise SystemExit(main(sys.argv))

scripts/test_ci_migration_wiring.py

@@ -273,7 +273,7 @@ class CiWiringTests(unittest.TestCase):
         block = ci[start:next_step]
         self.assertIn(
             "sh scripts/with-hermetic-test-home.sh cargo nextest run "
-            "-p codewhale-tui -p codewhale-runtime --lib --locked --no-tests=fail "
+            "-p codewhale-engine -p codewhale-tui -p codewhale-runtime --lib --locked --no-tests=fail "
             "-E 'test(auto_review) | test(authority) | test(sandbox)'", block
         )
         self.assertIn(
@@ -290,27 +290,27 @@ class CiWiringTests(unittest.TestCase):
         self.assertIn("check-command-migration-manifest.py", ci)
         self.assertIn("needs.changes.outputs.heavy == 'true'", ci)
 
-    def test_shared_process_mode_is_manual_hosted_and_preserves_default_runner(self) -> None:
+    def test_shared_process_mode_is_manual_hosted_ubuntu_only_and_replaces_the_sharded_suite(self) -> None:
         ci = load_ci()
         self.assertIn("default: nextest", ci)
-        matrix = ci.split("  test:\n", 1)[1].split("    steps:\n", 1)[0]
-        self.assertIn(
-            SHARED_PROCESS_MODE + " && '[\"ubuntu-latest\"]' || "
-            "'[\"ubuntu-latest\",\"macos-latest\",\"windows-latest\"]'", matrix,
-        )
-        self.assertIn("needs.changes.outputs.trusted == 'true'", matrix)
+        job = ci.split("  test:\n", 1)[1].split("    steps:\n", 1)[0]
+        self.assertIn("runs-on: ubuntu-latest", job)
+        self.assertIn(SHARED_PROCESS_MODE, job)
+        self.assertNotIn("pull_request", job)
+        for name in ("test-ubuntu", "test-macos", "test-windows"):
+            caller = ci.split(f"  {name}:\n", 1)[1].split("    uses:", 1)[0]
+            self.assertIn(f"!({SHARED_PROCESS_MODE})", caller)
         qualification = named_step(ci, "Shared-process workspace qualification")
-        self.assertIn("if: " + SHARED_PROCESS_MODE + " && matrix.os == 'ubuntu-latest'", qualification)
-        for name, command in (
-            ("Run tests", "cargo nextest run --workspace --all-features --locked --profile ci"),
-            ("Run doctests", "cargo test --workspace --all-features --locked --doc"),
-        ):
-            step = named_step(ci, name)
-            self.assertIn(command, step)
-            self.assertIn(f"!({SHARED_PROCESS_MODE})", step)
+        self.assertIn("if: " + SHARED_PROCESS_MODE, qualification)
         upload = named_step(ci, "Retain shared-process qualification evidence")
         self.assertIn("if: always() && " + SHARED_PROCESS_MODE, upload)
         self.assertIn("if-no-files-found: error", upload)
+        suite = (ROOT / ".github" / "workflows" / "ci-test-suite.yml").read_text(encoding="utf-8")
+        for name, command in (
+            ("Run tests", "cargo nextest run"),
+            ("Run doctests", "cargo test --workspace --all-features --locked --doc"),
+        ):
+            self.assertIn(command, named_step(suite, name))
 
     def test_shared_process_runs_exact_command_twice_with_fresh_hermetic_homes(self) -> None:
         proof = run_shared_process_fixture()
@@ -332,31 +332,24 @@ class CiWiringTests(unittest.TestCase):
             for identity in ISSUE_6698_TESTS:
                 self.assertIn(f"test {identity} ... ok", proof["evidence"][f"run-{run}.log"])
 
-    def test_shared_process_keeps_macos_budget_when_self_hosted_test_leg_is_absent(self) -> None:
+    def test_macos_budget_runs_on_every_heavy_dispatch_and_never_on_pull_requests(self) -> None:
         job = load_ci().split("  macos-budget:\n", 1)[1].split("    steps:\n", 1)[0]
         condition = next(line.strip()[4:] for line in job.splitlines() if line.strip().startswith("if: "))
         self.assertIn("runs-on: macos-latest", job)
         for event in ("pull_request", "push", "schedule", "workflow_dispatch"):
-            for mode in ("nextest", "shared-process-twice"):
-                for heavy, trusted, self_hosted in (
-                    (True, True, True), (True, True, False),
-                    (True, False, True), (False, True, True),
-                ):
-                    with self.subTest(event=event, mode=mode, heavy=heavy, trusted=trusted, self_hosted=self_hosted):
+            for heavy in (True, False):
+                for scoped in (True, False):
+                    with self.subTest(event=event, heavy=heavy, scoped=scoped):
                         expression = condition
                         for name, value in {
                             "github.event_name": event,
-                            "inputs.workspace_test_mode": mode,
                             "needs.changes.outputs.heavy": str(heavy).lower(),
-                            "needs.changes.outputs.trusted": str(trusted).lower(),
-                            "vars.CW_SELF_HOSTED_MAC": str(self_hosted).lower(),
+                            "needs.changes.outputs.scoped": str(scoped).lower(),
                         }.items():
                             expression = expression.replace(name, repr(value))
                         expression = re.sub(r"!(?!=)", "not ", expression.replace("&&", "and").replace("||", "or"))
                         actual = eval(expression, {"__builtins__": {}}, {})
-                        previous = heavy and event != "pull_request" and not (trusted and self_hosted)
-                        qualification = heavy and event == "workflow_dispatch" and mode == "shared-process-twice"
-                        self.assertEqual(actual, previous or qualification)
+                        self.assertEqual(actual, heavy and not scoped and event != "pull_request")
 
     def test_shared_process_retains_failed_first_run_and_still_runs_second_once(self) -> None:
         proof = run_shared_process_fixture("first_failure")

web/data/agent-docs.generated.json

@@ -323,8 +323,8 @@
       },
       {
         "path": "docs/EXTENSIONS.md",
-        "sha256": "8582de93c01083314119639678c1ea1ab4ba46317c5a400fb9dd139ffdcb232a",
-        "content": "# Writing an extension tool or command\n\nThe experimental TypeScript extension host runs reviewed plugin code in a\nshared Node process (or, as an opt-in, Bun). Rust still owns sessions, tool admission, approval and\nexecution. Extensions currently contribute tools and slash commands; they\ncannot provide an approval service, run a second agent loop or replace\nbuilt-in tools or commands.\n\n## Quick start\n\nStart with [hello-extension](examples/plugins/hello-extension/hello.mts) and its\n[plugin.json](examples/plugins/hello-extension/plugin.json). The example is\nexecuted unchanged by the host tests. It returns a greeting and does not read\nfiles or use the network.\n\n1. Explicitly enable `[features] extension_host = true` in your configuration,\n   or start Codewhale with `codewhale --enable extension_host` (the flag goes\n   before any subcommand).\n2. Install the example's directory using `/plugin install <local-directory>`.\n3. Run `/plugin validate hello-extension`, then `/plugin show hello-extension`.\n4. Run `/plugin enable hello-extension` to open its content/capability review.\n   Read the review and personally run its exact `/plugin trust <token>` command,\n   then enable the plugin. Trust alone does not execute the code.\n5. Ask Codewhale to use `hello_greet`. The tool follows the normal approval gate.\n6. Run `/hello-greet Codewhale`. The command runs when you type it, and shows\n   its answer in the transcript with its origin, `extension:hello-extension`.\n\nAn authoring agent should stop after installation and validation and present\nthe review to the person, unless it runs in Full Access and the plugin is one\nit wrote and installed from a folder in its project: then it may trust and\nenable it for that project with `codewhale plugins trust` and `enable`. Those\nshell commands go through the session's approval like any other: Ask asks the\nperson, Auto-Review's reviewer judges, and Full Access runs them.\n\n## Locations, installation and trust\n\nUser bundles live under `~/.codewhale/plugins/`; workspace bundles live under\n`<workspace>/.codewhale/plugins/`. New bundles use Agent Plugins v1.0.0\n`plugin.json`. Declare `extensions[\"net.codewhale\"].native.path` as one regular\n`.mjs`, `.js` or `.mts` file inside the bundle. Directories and other extensions\nfail validation when the host is enabled. With the flag off, native entries\nremain inventory-only.\n\nA plugin may split its code across several entries with `native.paths` (up to\n64, alone or beside `path`). They are activated in the order declared, as the\nfibers of one plugin: they share one owner, so one disable, review change or\ncrash tears all of them down together. Each entry is a separate module with its\nown `apply`, and tool and command names must be unique across them. If an entry\nfails to activate (throws, requires a service the host does not provide, or has\na registration refused), only that entry is withdrawn: entries that already\nactivated stay registered, later entries still activate, and the plugin fails\nonly when no entry activates. Listing the same file twice is one entry.\n\n## Runtime\n\n`[extension_host] runtime` selects what runs the host. Node is the default.\nBun is an opt-in: it is qualified on macOS only, and becomes the default only\nafter an explicit, recorded cutover.\n\n```toml\n[extension_host]\nruntime = \"node\"   # default: Node only\n# runtime = \"bun\"  # Bun only; fails rather than falling back to Node\n# runtime = \"auto\" # Bun >= 1.4.0 if one is found and starts, otherwise Node\n# bun = \"~/.bun/bin/bun\"          # the only Bun tried when set\n# node = \"/opt/homebrew/bin/node\" # the only Node tried when set\n# mcp_backend = \"rust\" # temporary opt-out; default is \"host\"\n```\n\nThe default `mcp_backend = \"host\"` uses the pinned MCP SDK independently of\n`[features] extension_host`, which controls optional Native extensions. Existing\nstdio and HTTP servers use modern discovery when supported; explicitly configured\nlegacy SSE servers use their legacy handshake. Rust retains process and network\nauthority, credential resolution, catalog admission, tool approval and cancellation.\nThe SDK receives opaque session selectors and exact operation grants. Modern\nrequests carry Rust-approved protocol metadata and headers without a session id.\n\nA typed discovery refusal can admit a legacy handshake. Only an explicit HTTP\ntransport refusal during that handshake can admit legacy SSE with a fresh exact\nRust grant. Legacy HTTP retains its GET preflight and bounded OAuth refresh;\nmodern HTTP does not inherit those session or resend behaviors. Incomplete result\nflows are reported without automatically repeating the operation. Credentials,\nconfigured URLs, OAuth browser/login operations and Computer Use decision keys\nstay in Rust.\n\nBoth backends share recorded semantic MCP goldens and retain separate transport\ngoldens, including discovery, authentication and sessioLine truncated
+        "sha256": "45dc87bc8293156cc221a0d1181ddcdfe6970caef3874d2127a5b86ba2b32d9d",
+        "content": "# Writing an extension tool or command\n\nThe experimental TypeScript extension host runs reviewed plugin code in a\nshared Node process (or, as an opt-in, Bun). Rust still owns sessions, tool admission, approval and\nexecution. Extensions currently contribute tools and slash commands; they\ncannot provide an approval service, run a second agent loop or replace\nbuilt-in tools or commands.\n\n## Quick start\n\nStart with [hello-extension](examples/plugins/hello-extension/hello.mts) and its\n[plugin.json](examples/plugins/hello-extension/plugin.json). The example is\nexecuted unchanged by the host tests. It returns a greeting and does not read\nfiles or use the network.\n\n1. Explicitly enable `[features] extension_host = true` in your configuration,\n   or start Codewhale with `codewhale --enable extension_host` (the flag goes\n   before any subcommand).\n2. Install the example's directory using `/plugin install <local-directory>`.\n3. Run `/plugin validate hello-extension`, then `/plugin show hello-extension`.\n4. Run `/plugin enable hello-extension` to open its content/capability review.\n   Read the review and personally run its exact `/plugin trust <token>` command,\n   then enable the plugin. Trust alone does not execute the code.\n5. Ask Codewhale to use `hello_greet`. The tool follows the normal approval gate.\n6. Run `/hello-greet Codewhale`. The command runs when you type it, and shows\n   its answer in the transcript with its origin, `extension:hello-extension`.\n\nAn authoring agent should stop after installation and validation and present\nthe review to the person, unless it runs in Full Access and the plugin is one\nit wrote and installed from a folder in its project: then it may trust and\nenable it for that project with `codewhale plugins trust` and `enable`. Those\nshell commands go through the session's approval like any other: Ask asks the\nperson, Auto-Review's reviewer judges, and Full Access runs them.\n\n## Locations, installation and trust\n\nUser bundles live under `~/.codewhale/plugins/`; workspace bundles live under\n`<workspace>/.codewhale/plugins/`. New bundles use Agent Plugins v1.0.0\n`plugin.json`. Declare `extensions[\"net.codewhale\"].native.path` as one regular\n`.mjs`, `.js` or `.mts` file inside the bundle. Directories and other extensions\nfail validation when the host is enabled. With the flag off, native entries\nremain inventory-only.\n\nA plugin may split its code across several entries with `native.paths` (up to\n64, alone or beside `path`). They are activated in the order declared, as the\nfibers of one plugin: they share one owner, so one disable, review change or\ncrash tears all of them down together. Each entry is a separate module with its\nown `apply`, and tool and command names must be unique across them. If an entry\nfails to activate (throws, requires a service the host does not provide, or has\na registration refused), only that entry is withdrawn: entries that already\nactivated stay registered, later entries still activate, and the plugin fails\nonly when no entry activates. Listing the same file twice is one entry.\n\n## Runtime\n\n`[extension_host] runtime` selects what runs the host. Node is the default.\nBun is an opt-in: it is qualified on macOS only, and becomes the default only\nafter an explicit, recorded cutover.\n\n```toml\n[extension_host]\nruntime = \"node\"   # default: Node only\n# runtime = \"bun\"  # Bun only; fails rather than falling back to Node\n# runtime = \"auto\" # Bun >= 1.4.0 if one is found and starts, otherwise Node\n# bun = \"~/.bun/bin/bun\"          # the only Bun tried when set\n# node = \"/opt/homebrew/bin/node\" # the only Node tried when set\n# mcp_backend = \"rust\" # temporary opt-out; default is \"host\"\n```\n\nThe default `mcp_backend = \"host\"` uses the pinned MCP SDK independently of\n`[features] extension_host`, which controls optional Native extensions. Existing\nstdio and HTTP servers use modern discovery when supported; explicitly configured\nlegacy SSE servers use their legacy handshake. Rust retains process and network\nauthority, credential resolution, catalog admission, tool approval and cancellation.\nThe SDK receives opaque session selectors and exact operation grants. Modern\nrequests carry Rust-approved protocol metadata and headers without a session id.\n\nA typed discovery refusal can admit a legacy handshake. Only an explicit HTTP\ntransport refusal during that handshake can admit legacy SSE with a fresh exact\nRust grant. Legacy HTTP retains its GET preflight and bounded OAuth refresh;\nmodern HTTP does not inherit those session or resend behaviors. Incomplete result\nflows are reported without automatically repeating the operation. Credentials,\nconfigured URLs, OAuth browser/login operations and Computer Use decision keys\nstay in Rust.\n\nBoth backends share recorded semantic MCP goldens and retain separate transport\ngoldens, including discovery, authentication and sessioLine truncated
       }
     ]
   },
@@ -334,8 +334,8 @@
     "sources": [
       {
         "path": "docs/RUNTIME_API.md",
-        "sha256": "e3040635df0cf62717f5acbe9aacf4909b6ad60db8468b06e90a5e9be1d76d1e",
-        "content": "# Codewhale Engine Runtime API & Integration Contract\n\n> 阅读简体中文版：[zh_hans/RUNTIME_API.md](zh_hans/RUNTIME_API.md)。\n\n`codewhale app-server --http` exposes the [Codewhale Engine](ARCHITECTURE.md) through\nits canonical local Runtime API and control plane.\nLocal SDKs, mobile/remote-control clients, and editor integrations talk to it\ninstead of screen-scraping terminal output. It serves the full HTTP/SSE runtime\nAPI (`/v1/*`), a JSON-RPC control transport over stdio, and the phone-friendly\nmobile page. `codewhale doctor --json` provides machine-readable health, and\n`codewhale serve --acp` speaks the Agent Client Protocol over stdio for editors\nsuch as Zed.\n\n`codewhale serve --http` / `serve --mobile` remain as **compatibility aliases**\nfor `codewhale app-server --http` / `--mobile`; both launch the identical\nserver. Desktop, web, SDK and custom integrations should target\n`app-server --http`. `--stdio` and `--socket` expose compatibility controls.\nBare `app-server` selects initialized JSONL control over stdio. Local stdio,\nsocket and ACP owners do not bind a hidden TCP listener. Explicit `--http`\nretains HTTP/SSE and compatibility routes on the same Runtime owner.\n\n`codewhale exec` is the separate one-shot headless worker path (stream-json,\nfleet worker subprocess, CI primitive). It is not part of this API, but it\nshares the same runtime, provider/model resolution, permission profiles, and\nevent vocabulary.\n\nThis document is the stable integration contract for native workbench\napplications (and other local supervisors) that embed the Codewhale Engine.\n\n## Architecture\n\n```\nlocal supervisor / SDK / automation harness\n        │\n        ├─ codewhale app-server --http     → HTTP/SSE runtime API (/v1/*)        [canonical]\n        ├─ codewhale app-server --mobile   → runtime API + mobile control page\n        ├─ codewhale app-server --stdio    → JSON-RPC control transport over stdio\n        ├─ codewhale app-server --socket   → same JSON-RPC over a unix domain socket (desktop daemon)\n        ├─ codewhale doctor --json         → machine-readable health & capability\n        ├─ codewhale serve --acp           → ACP stdio agent for editors such as Zed\n        ├─ codewhale serve --mcp           → MCP stdio server\n        ├─ codewhale serve --http/--mobile → legacy aliases for `app-server --http/--mobile`\n        └─ codewhale exec [args]           → one-shot headless worker (stream-json)\n```\n\nThe engine runs as a local-only process. All APIs bind to `localhost` by\ndefault. No hosted relay, no provider-token custody, no secret leakage.\n\nFor the read-only record of what a thread or turn did, see\n[`docs/RECEIPTS.md`](RECEIPTS.md): `codewhale receipts` on the CLI and the\n`/receipt` routes under **Threads** below.\n\n## Runtime API entrypoints\n\n| Entry | Transport | Use |\n|---|---|---|\n| `codewhale web [--port 7878]` | HTTP/SSE on `127.0.0.1:7878` + embedded client | First-class loopback-only browser client; opens the default browser |\n| `codewhale app-server --http` | HTTP/SSE on `127.0.0.1:7878` | Full `/v1/*` runtime API (canonical) |\n| `codewhale app-server --mobile` | HTTP/SSE on loopback + `/mobile` | Runtime API + local mobile control page |\n| `codewhale app-server --stdio` | Initialized JSONL over stdio | Compatibility controls and explicit tool-free turns through the held manager; no hidden TCP listener or full Codex interaction channel. |\n| `codewhale app-server --socket [--socket-path P]` | RPC text messages over WebSocket on a `0600` Unix domain socket (macOS/Linux) or an owner-only named pipe (Windows) | Desktop daemon: multi-client, kernel peer identity checked, `daemon/attach` claim handshake. Windows native-app qualification remains open. |\n| `codewhale app-server` | Initialized JSONL over stdio | Same selection as `--stdio`; HTTP requires explicit `--http`. |\n| `codewhale serve --http` / `--mobile` | same server as `app-server --http`/`--mobile` | Compatibility aliases |\n\n`app-server --http` and `--mobile` launch the same mature runtime API server\nhistorically reached through `serve --http` — no routes or behavior changed, so\nevery endpoint documented below is identical across both entrypoints. The\nruntime API token is read from `--auth-token`, then `CODEWHALE_RUNTIME_TOKEN`,\nthen `DEEPSEEK_RUNTIME_TOKEN`; use `--insecure-no-auth` only with a loopback\nbind. The `serve` compatibility aliases keep their `--insecure` flag.\nBare `app-server` does not open an HTTP port. Selected attached HTTP listeners\nretain their explicit bearer and non-loopback security checks.\n\nInitialized stdio/private-socket controls support `thread/loaded/list` with\n`{cursor?: string | null, limit?: number | null}`. The result is\n`{data: string[], nextCursor: string | null}` from the held manager's loaded\nengine snapshot, including idle and archived engines still in memory. It dLine truncated
+        "sha256": "6f3b8885978ef2e1b33d0fdf66ad6ccf5c25464c1951b59658aec00745390db2",
+        "content": "# Codewhale Engine Runtime API & Integration Contract\n\n> 阅读简体中文版：[zh_hans/RUNTIME_API.md](zh_hans/RUNTIME_API.md)。\n\n`codewhale app-server --http` exposes the [Codewhale Engine](ARCHITECTURE.md) through\nits canonical local Runtime API and control plane.\nLocal SDKs, mobile/remote-control clients, and editor integrations talk to it\ninstead of screen-scraping terminal output. It serves the full HTTP/SSE runtime\nAPI (`/v1/*`), a JSON-RPC control transport over stdio, and the phone-friendly\nmobile page. `codewhale doctor --json` provides machine-readable health, and\n`codewhale serve --acp` speaks the Agent Client Protocol over stdio for editors\nsuch as Zed.\n\n`codewhale serve --http` / `serve --mobile` remain as **compatibility aliases**\nfor `codewhale app-server --http` / `--mobile`; both launch the identical\nserver. Desktop, web, SDK and custom integrations should target\n`app-server --http`. `--stdio` and `--socket` expose compatibility controls.\nBare `app-server` selects initialized JSONL control over stdio. Local stdio,\nsocket and ACP owners do not bind a hidden TCP listener. Explicit `--http`\nretains HTTP/SSE and compatibility routes on the same Runtime owner.\n\n`codewhale exec` is the separate one-shot headless worker path (stream-json,\nfleet worker subprocess, CI primitive). It is not part of this API, but it\nshares the same runtime, provider/model resolution, permission profiles, and\nevent vocabulary.\n\nThis document is the stable integration contract for native workbench\napplications (and other local supervisors) that embed the Codewhale Engine.\n\n## Architecture\n\n```\nlocal supervisor / SDK / automation harness\n        │\n        ├─ codewhale app-server --http     → HTTP/SSE runtime API (/v1/*)        [canonical]\n        ├─ codewhale app-server --mobile   → runtime API + mobile control page\n        ├─ codewhale app-server --stdio    → JSON-RPC control transport over stdio\n        ├─ codewhale app-server --socket   → same JSON-RPC over a unix domain socket (desktop daemon)\n        ├─ codewhale doctor --json         → machine-readable health & capability\n        ├─ codewhale serve --acp           → ACP stdio agent for editors such as Zed\n        ├─ codewhale serve --mcp           → MCP stdio server\n        ├─ codewhale serve --http/--mobile → legacy aliases for `app-server --http/--mobile`\n        └─ codewhale exec [args]           → one-shot headless worker (stream-json)\n```\n\nThe engine runs as a local-only process. All APIs bind to `localhost` by\ndefault. No hosted relay, no provider-token custody, no secret leakage.\n\nFor the read-only record of what a thread or turn did, see\n[`docs/RECEIPTS.md`](RECEIPTS.md): `codewhale receipts` on the CLI and the\n`/receipt` routes under **Threads** below.\n\n## Runtime API entrypoints\n\n| Entry | Transport | Use |\n|---|---|---|\n| `codewhale web [--port 7878]` | HTTP/SSE on `127.0.0.1:7878` + embedded client | First-class loopback-only browser client; opens the default browser |\n| `codewhale app-server --http` | HTTP/SSE on `127.0.0.1:7878` | Full `/v1/*` runtime API (canonical) |\n| `codewhale app-server --mobile` | HTTP/SSE on loopback + `/mobile` | Runtime API + local mobile control page |\n| `codewhale app-server --stdio` | Initialized JSONL over stdio | Compatibility controls and explicit tool-free turns through the held manager; no hidden TCP listener or full Codex interaction channel. |\n| `codewhale app-server --socket [--socket-path P]` | RPC text messages over WebSocket on a `0600` Unix domain socket (macOS/Linux) or an owner-only named pipe (Windows) | Desktop daemon: multi-client, kernel peer identity checked, `daemon/attach` claim handshake. Windows native-app qualification remains open. |\n| `codewhale app-server` | Initialized JSONL over stdio | Same selection as `--stdio`; HTTP requires explicit `--http`. |\n| `codewhale serve --http` / `--mobile` | same server as `app-server --http`/`--mobile` | Compatibility aliases |\n\n`app-server --http` and `--mobile` launch the same mature runtime API server\nhistorically reached through `serve --http` — no routes or behavior changed, so\nevery endpoint documented below is identical across both entrypoints. The\nruntime API token is read from `--auth-token`, then `CODEWHALE_RUNTIME_TOKEN`,\nthen `DEEPSEEK_RUNTIME_TOKEN`; use `--insecure-no-auth` only with a loopback\nbind. The `serve` compatibility aliases keep their `--insecure` flag.\nBare `app-server` does not open an HTTP port. Selected attached HTTP listeners\nretain their explicit bearer and non-loopback security checks.\n\nInitialized stdio/private-socket controls support `thread/loaded/list` with\n`{cursor?: string | null, limit?: number | null}`. The result is\n`{data: string[], nextCursor: string | null}` from the held manager's loaded\nengine snapshot, including idle and archived engines still in memory. It dLine truncated
       }
     ]
   },
@@ -377,8 +377,8 @@
     "sources": [
       {
         "path": "CONTRIBUTING.md",
-        "sha256": "7b3e523585eb5535555b1d8aaa66153ce0451b1cedc165dfba212e372dd71d41",
-        "content": "# Contributing to Codewhale\n\nCodewhale is what it is because of the people who used it, reported what broke,\ntranslated it, added their providers and sent fixes. Thank you for being here.\nEveryone is welcome, in English or 中文, with or without code.\n\nAll feedback is a gift to this project, including \"this looked wrong\" or \"I got\nlost here\" with no fix attached. The [roadmap](docs/ROADMAP.md) says where\nCodewhale is going and where help counts most.\n\n## Where things go\n\n| You have | Best place |\n| --- | --- |\n| A bug, a crash, or behavior that surprised you | [Bug report](https://github.com/codewhale-hq/CodeWhale/issues/new?template=bug_report.yml) |\n| An idea or a feature you want | [Feature request](https://github.com/codewhale-hq/CodeWhale/issues/new?template=feature_request.yml), or [Ideas](https://github.com/codewhale-hq/CodeWhale/discussions/categories/ideas) to talk it through first |\n| Feedback on how something looks, reads or feels | [Feedback](https://github.com/codewhale-hq/CodeWhale/issues/new?template=feedback.yml) |\n| A question | [Q&A](https://github.com/codewhale-hq/CodeWhale/discussions/categories/q-a) or [Discord](https://discord.gg/37gfS3ksug) |\n| A security problem | A [private advisory](https://github.com/codewhale-hq/CodeWhale/security/advisories/new), never a public issue ([policy](.github/SECURITY.md)) |\n| A fix for an open issue | A pull request that links the issue |\n| A translation, a provider or model, a docs fix | A pull request, no issue needed ([standing projects](#standing-projects)) |\n| A new feature, already written or not | An issue first ([why](#new-features-start-as-an-issue)) |\n\nIf you are not sure, open an issue. Nothing is filed in the wrong place for\nlong: a maintainer moves it.\n\n## New features start as an issue\n\nIssues are the best place for feature requests, ideas and bugs. A pull request\nis the best place for work we have already agreed on.\n\nA feature that first appears as a pull request takes longer to land than one\nthat starts as an issue, even when we want it. The questions that decide a\nfeature are about the product, not the diff: does it belong in the engine or in\na plugin, what does it do in each permission mode, how does it show up in\nreceipts, what is it called in 19 languages. Answering those in a review means\nrewriting code you already finished. Answering them in an issue costs you a few\nsentences.\n\nSo for a new feature:\n\n1. Open a [feature request](https://github.com/codewhale-hq/CodeWhale/issues/new?template=feature_request.yml).\n   Say what you are trying to do and what gets in the way. A proposed design is\n   welcome and optional.\n2. Tick \"I would like to open a pull request\" if you want to build it.\n3. A maintainer answers with the shape that fits, or with what is still\n   undecided. Then the pull request is small and merges quickly.\n\nA feature pull request that arrives without an issue is still read, and it is\nnever closed for that reason. We will most likely ask the same questions there\nand it will take longer.\n\n## Standing projects\n\nThese are always open, and a pull request needs no issue first:\n\n- **Translations.** You can improve the terminal language packs, the translated\n  READMEs in `docs/i18n/`, the website, and the translated docs in\n  `docs/zh_hans/` and `docs/id/`. The [localization matrix](docs/LOCALIZATION.md)\n  shows what each language has and how to add one, and the\n  [Chinese localization group](https://github.com/codewhale-hq/CodeWhale/issues/6804)\n  is recruiting.\n- **Providers and models.** You can add a missing provider or a new model, or\n  correct a price, a context size or a provider quirk.\n  [Providers](docs/PROVIDERS.md) lists what ships, and\n  `python3 scripts/check-provider-registry.py` checks your change.\n- **Documentation.** You can fix a typo, an unclear step, a missing example or\n  an instruction that no longer matches the product.\n- **Bug fixes.** If there is no issue yet, describe the bug in the pull request\n  by saying what you ran, what happened and what you expected.\n- **Planned work.** You can take anything in a\n  [milestone](docs/ROADMAP.md#releases) or anything labelled\n  [help wanted](https://github.com/codewhale-hq/CodeWhale/issues?q=is%3Aissue+is%3Aopen+label%3A%22help+wanted%22).\n  Comment on the issue to claim it so two people do not build the same thing.\n\nLarge changes to planned work are easier in layers; see\n[Layered and EPIC-Sized Work](#layered-and-epic-sized-work).\n\n### What a planned-work issue gives you\n\nEvery issue a maintainer opens for planned work, and every release tracking issue, has the same parts, so you can pick one up without asking first:\n\n- **Status:** what is on `main` already, with commit links, and what is still missing.\n- **Ways to help:** each piece open to contributors, with the files to read, the command to test it locally (usually `scripts/dev-test.sh <crate> <filter>Line truncated
+        "sha256": "096a609f93d82c8bcea9f967072d5306807cd4375390218f9d3784023df0dcb0",
+        "content": "# Contributing to Codewhale\n\nCodewhale is what it is because of the people who used it, reported what broke,\ntranslated it, added their providers and sent fixes. Thank you for being here.\nEveryone is welcome, in English or 中文, with or without code.\n\nAll feedback is a gift to this project, including \"this looked wrong\" or \"I got\nlost here\" with no fix attached. The [roadmap](docs/ROADMAP.md) says where\nCodewhale is going and where help counts most.\n\n## Where things go\n\n| You have | Best place |\n| --- | --- |\n| A bug, a crash, or behavior that surprised you | [Bug report](https://github.com/codewhale-hq/CodeWhale/issues/new?template=bug_report.yml) |\n| An idea or a feature you want | [Feature request](https://github.com/codewhale-hq/CodeWhale/issues/new?template=feature_request.yml), or [Ideas](https://github.com/codewhale-hq/CodeWhale/discussions/categories/ideas) to talk it through first |\n| Feedback on how something looks, reads or feels | [Feedback](https://github.com/codewhale-hq/CodeWhale/issues/new?template=feedback.yml) |\n| A question | [Q&A](https://github.com/codewhale-hq/CodeWhale/discussions/categories/q-a) or [Discord](https://discord.gg/37gfS3ksug) |\n| A security problem | A [private advisory](https://github.com/codewhale-hq/CodeWhale/security/advisories/new), never a public issue ([policy](.github/SECURITY.md)) |\n| A fix for an open issue | A pull request that links the issue |\n| A translation, a provider or model, a docs fix | A pull request, no issue needed ([standing projects](#standing-projects)) |\n| A new feature, already written or not | An issue first ([why](#new-features-start-as-an-issue)) |\n\nIf you are not sure, open an issue. Nothing is filed in the wrong place for\nlong: a maintainer moves it.\n\n## New features start as an issue\n\nIssues are the best place for feature requests, ideas and bugs. A pull request\nis the best place for work we have already agreed on.\n\nA feature that first appears as a pull request takes longer to land than one\nthat starts as an issue, even when we want it. The questions that decide a\nfeature are about the product, not the diff: does it belong in the engine or in\na plugin, what does it do in each permission mode, how does it show up in\nreceipts, what is it called in 19 languages. Answering those in a review means\nrewriting code you already finished. Answering them in an issue costs you a few\nsentences.\n\nSo for a new feature:\n\n1. Open a [feature request](https://github.com/codewhale-hq/CodeWhale/issues/new?template=feature_request.yml).\n   Say what you are trying to do and what gets in the way. A proposed design is\n   welcome and optional.\n2. Tick \"I would like to open a pull request\" if you want to build it.\n3. A maintainer answers with the shape that fits, or with what is still\n   undecided. Then the pull request is small and merges quickly.\n\nA feature pull request that arrives without an issue is still read, and it is\nnever closed for that reason. We will most likely ask the same questions there\nand it will take longer.\n\n## Standing projects\n\nThese are always open, and a pull request needs no issue first:\n\n- **Translations.** You can improve the terminal language packs, the translated\n  READMEs in `docs/i18n/`, the website, and the translated docs in\n  `docs/zh_hans/` and `docs/id/`. The [localization matrix](docs/LOCALIZATION.md)\n  shows what each language has and how to add one, and the\n  [Chinese localization group](https://github.com/codewhale-hq/CodeWhale/issues/6804)\n  is recruiting.\n- **Providers and models.** You can add a missing provider or a new model, or\n  correct a price, a context size or a provider quirk.\n  [Providers](docs/PROVIDERS.md) lists what ships, and\n  `python3 scripts/check-provider-registry.py` checks your change.\n- **Documentation.** You can fix a typo, an unclear step, a missing example or\n  an instruction that no longer matches the product.\n- **Bug fixes.** If there is no issue yet, describe the bug in the pull request\n  by saying what you ran, what happened and what you expected.\n- **Planned work.** You can take anything in a\n  [milestone](docs/ROADMAP.md#releases) or anything labelled\n  [help wanted](https://github.com/codewhale-hq/CodeWhale/issues?q=is%3Aissue+is%3Aopen+label%3A%22help+wanted%22).\n  Comment on the issue to claim it so two people do not build the same thing.\n\nLarge changes to planned work are easier in layers; see\n[Layered and EPIC-Sized Work](#layered-and-epic-sized-work).\n\n### What a planned-work issue gives you\n\nEvery issue a maintainer opens for planned work, and every release tracking issue, has the same parts, so you can pick one up without asking first:\n\n- **Status:** what is on `main` already, with commit links, and what is still missing.\n- **Ways to help:** each piece open to contributors, with the files to read, the command to test it locally (usually `scripts/dev-test.sh <crate> <filter>Line truncated
       },
       {
         "path": "docs/AGENT_ETHOS.md",
@@ -387,8 +387,8 @@
       },
       {
         "path": "docs/CONTRIBUTORS.md",
-        "sha256": "bedd1cc62969108856f75d823d13bde9f7217a936d4b0e7af3d2e6232cad5770",
-        "content": "# Contributors\n\nCodewhale is built in the open with a growing community of contributors. Every\nissue report and pull request is real project work — welcome at any experience\nlevel. This is the full per-PR contributor record, grouped into release/time\nbands with the newest band first so it stays scannable. Expand any band to see\neveryone.\n\nFor the live list, see the\n[GitHub contributors page](https://github.com/codewhale-hq/CodeWhale/graphs/contributors),\n[`AUTHOR_MAP`](https://github.com/codewhale-hq/CodeWhale/blob/main/.github/AUTHOR_MAP),\nand [CHANGELOG.md](../CHANGELOG.md).\n\n<!-- contributor-wall:start -->\n## Everyone\n\n[![433 people built Codewhale](assets/contributors.png)](#everyone)\n\n433 people have code, co-authored commits, carried-forward pull requests or credited reports in Codewhale. GitHub's contributor list shows only commit authors whose email is linked to their account, so it counts 212 of them. If your commits are missing there, add your commit email to your GitHub account and they will link.\n\n[0gl20shk0sbt36](https://github.com/0gl20shk0sbt36) · [1Git2Clone](https://github.com/1Git2Clone) · [20bytes](https://github.com/20bytes) · [47Cid](https://github.com/47Cid) · [7jrxt42BxFZo4iAnN4CX](https://github.com/7jrxt42BxFZo4iAnN4CX) · [8sero](https://github.com/8sero) · [A-Corner](https://github.com/A-Corner) · [aboimpinto](https://github.com/aboimpinto) · [Aboysky](https://github.com/Aboysky) · [adity982](https://github.com/adity982) · [AdityaVG13](https://github.com/AdityaVG13) · [AGSaturn](https://github.com/AGSaturn) · [ai-dengwsh](https://github.com/ai-dengwsh) · [aiapienthusiast](https://github.com/aiapienthusiast) · [Aitensa](https://github.com/Aitensa) · [AiurArtanis](https://github.com/AiurArtanis) · [alitvak69](https://github.com/alitvak69) · [all-lopezg](https://github.com/all-lopezg) · [alvin1](https://github.com/alvin1) · [amuthantamil](https://github.com/amuthantamil) · [AnaheimEX](https://github.com/AnaheimEX) · [Andrea-Bruno](https://github.com/Andrea-Bruno) · [Angel-Hair](https://github.com/Angel-Hair) · [angziii](https://github.com/angziii) · [AnonymousUser443](https://github.com/AnonymousUser443) · [antarikshraya](https://github.com/antarikshraya) · [Anyexyz](https://github.com/Anyexyz) · [Apeiron0w0](https://github.com/Apeiron0w0) · [aqilaziz](https://github.com/aqilaziz) · [AresNing](https://github.com/AresNing) · [ArronAI007](https://github.com/ArronAI007) · [Artenx](https://github.com/Artenx) · [asdfg314284230](https://github.com/asdfg314284230) · [Asteria1028](https://github.com/Asteria1028) · [asto18089](https://github.com/asto18089) · [atmosuwiryo](https://github.com/atmosuwiryo) · [axobase001](https://github.com/axobase001) · [aznikline](https://github.com/aznikline) · [baendlorel](https://github.com/baendlorel) · [banqii](https://github.com/banqii) · [Beltran12138](https://github.com/Beltran12138) · [bevis-wong](https://github.com/bevis-wong) · [BH8GCJ](https://github.com/BH8GCJ) · [BigBenLabs](https://github.com/BigBenLabs) · [Biilow](https://github.com/Biilow) · [bistack](https://github.com/bistack) · [BrathonBai](https://github.com/BrathonBai) · [bruce6135](https://github.com/bruce6135) · [BryonGo](https://github.com/BryonGo) · [buiducnhat](https://github.com/buiducnhat) · [buko](https://github.com/buko) · [BX166](https://github.com/BX166) · [c020627](https://github.com/c020627) · [cacdcaecawae](https://github.com/cacdcaecawae) · [caeserchen](https://github.com/caeserchen) · [caiyilian](https://github.com/caiyilian) · [CCChisato](https://github.com/CCChisato) · [ccomma](https://github.com/ccomma) · [cenab](https://github.com/cenab) · [ChaceLyee2101](https://github.com/ChaceLyee2101) · [chatman-media](https://github.com/chatman-media) · [chennest](https://github.com/chennest) · [chinaqy110](https://github.com/chinaqy110) · [chnjames](https://github.com/chnjames) · [chuntseevolving](https://github.com/chuntseevolving) · [ci4ic4](https://github.com/ci4ic4) · [cian-lien](https://github.com/cian-lien) · [cmdcorp6534](https://github.com/cmdcorp6534) · [cmyyy](https://github.com/cmyyy) · [codepgq](https://github.com/codepgq) · [Colorful-glassblock](https://github.com/Colorful-glassblock) · [ComeFromTheMars](https://github.com/ComeFromTheMars) · [CrepuscularIRIS](https://github.com/CrepuscularIRIS) · [ct-jaryn](https://github.com/ct-jaryn) · [ctxyao](https://github.com/ctxyao) · [cy2311](https://github.com/cy2311) · [cyq1017](https://github.com/cyq1017) · [czf0718](https://github.com/czf0718) · [dajiaohuang](https://github.com/dajiaohuang) · [DarrellThomas](https://github.com/DarrellThomas) · [ddlw](https://github.com/ddlw) · [demian-welt](https://github.com/demian-welt) · [Dev-next-gen](https://github.com/Dev-next-gen) · [dfwqdyl-ui](https://github.com/dfwqdyl-ui) · [DI-HUO-MING-YI](https://github.com/DI-HUO-MING-YI) · [DieMoe233](https://github.Line truncated
+        "sha256": "4368939ea860f6db9484fd86e613574b72eca71361f08a1130ec87c5f5c66c78",
+        "content": "# Contributors\n\nCodewhale is built in the open with a growing community of contributors. Every\nissue report and pull request is real project work — welcome at any experience\nlevel. This is the full per-PR contributor record, grouped into release/time\nbands with the newest band first so it stays scannable. Expand any band to see\neveryone.\n\nFor the live list, see the\n[GitHub contributors page](https://github.com/codewhale-hq/CodeWhale/graphs/contributors),\n[`AUTHOR_MAP`](https://github.com/codewhale-hq/CodeWhale/blob/main/.github/AUTHOR_MAP),\nand [CHANGELOG.md](../CHANGELOG.md).\n\n<!-- contributor-wall:start -->\n## Everyone\n\n[![433 people built Codewhale](assets/contributors.png)](#everyone)\n\n433 people have code, co-authored commits, carried-forward pull requests or credited reports in Codewhale. GitHub's contributor list shows only commit authors whose email is linked to their account, so it counts 212 of them. If your commits are missing there, add your commit email to your GitHub account and they will link.\n\n[0gl20shk0sbt36](https://github.com/0gl20shk0sbt36) · [1Git2Clone](https://github.com/1Git2Clone) · [20bytes](https://github.com/20bytes) · [47Cid](https://github.com/47Cid) · [7jrxt42BxFZo4iAnN4CX](https://github.com/7jrxt42BxFZo4iAnN4CX) · [8sero](https://github.com/8sero) · [A-Corner](https://github.com/A-Corner) · [aboimpinto](https://github.com/aboimpinto) · [Aboysky](https://github.com/Aboysky) · [adity982](https://github.com/adity982) · [AdityaVG13](https://github.com/AdityaVG13) · [AGSaturn](https://github.com/AGSaturn) · [ai-dengwsh](https://github.com/ai-dengwsh) · [aiapienthusiast](https://github.com/aiapienthusiast) · [Aitensa](https://github.com/Aitensa) · [AiurArtanis](https://github.com/AiurArtanis) · [alitvak69](https://github.com/alitvak69) · [all-lopezg](https://github.com/all-lopezg) · [alvin1](https://github.com/alvin1) · [amuthantamil](https://github.com/amuthantamil) · [AnaheimEX](https://github.com/AnaheimEX) · [Andrea-Bruno](https://github.com/Andrea-Bruno) · [Angel-Hair](https://github.com/Angel-Hair) · [angziii](https://github.com/angziii) · [AnonymousUser443](https://github.com/AnonymousUser443) · [antarikshraya](https://github.com/antarikshraya) · [Anyexyz](https://github.com/Anyexyz) · [Apeiron0w0](https://github.com/Apeiron0w0) · [aqilaziz](https://github.com/aqilaziz) · [AresNing](https://github.com/AresNing) · [ArronAI007](https://github.com/ArronAI007) · [Artenx](https://github.com/Artenx) · [asdfg314284230](https://github.com/asdfg314284230) · [Asteria1028](https://github.com/Asteria1028) · [asto18089](https://github.com/asto18089) · [atmosuwiryo](https://github.com/atmosuwiryo) · [axobase001](https://github.com/axobase001) · [aznikline](https://github.com/aznikline) · [baendlorel](https://github.com/baendlorel) · [banqii](https://github.com/banqii) · [Beltran12138](https://github.com/Beltran12138) · [bevis-wong](https://github.com/bevis-wong) · [BH8GCJ](https://github.com/BH8GCJ) · [BigBenLabs](https://github.com/BigBenLabs) · [Biilow](https://github.com/Biilow) · [bistack](https://github.com/bistack) · [BrathonBai](https://github.com/BrathonBai) · [bruce6135](https://github.com/bruce6135) · [BryonGo](https://github.com/BryonGo) · [buiducnhat](https://github.com/buiducnhat) · [buko](https://github.com/buko) · [BX166](https://github.com/BX166) · [c020627](https://github.com/c020627) · [cacdcaecawae](https://github.com/cacdcaecawae) · [caeserchen](https://github.com/caeserchen) · [caiyilian](https://github.com/caiyilian) · [CCChisato](https://github.com/CCChisato) · [ccomma](https://github.com/ccomma) · [cenab](https://github.com/cenab) · [ChaceLyee2101](https://github.com/ChaceLyee2101) · [chatman-media](https://github.com/chatman-media) · [chennest](https://github.com/chennest) · [chinaqy110](https://github.com/chinaqy110) · [chnjames](https://github.com/chnjames) · [chuntseevolving](https://github.com/chuntseevolving) · [ci4ic4](https://github.com/ci4ic4) · [cian-lien](https://github.com/cian-lien) · [cmdcorp6534](https://github.com/cmdcorp6534) · [cmyyy](https://github.com/cmyyy) · [codepgq](https://github.com/codepgq) · [Colorful-glassblock](https://github.com/Colorful-glassblock) · [ComeFromTheMars](https://github.com/ComeFromTheMars) · [CrepuscularIRIS](https://github.com/CrepuscularIRIS) · [ct-jaryn](https://github.com/ct-jaryn) · [ctxyao](https://github.com/ctxyao) · [cy2311](https://github.com/cy2311) · [cyq1017](https://github.com/cyq1017) · [czf0718](https://github.com/czf0718) · [dajiaohuang](https://github.com/dajiaohuang) · [DarrellThomas](https://github.com/DarrellThomas) · [ddlw](https://github.com/ddlw) · [demian-welt](https://github.com/demian-welt) · [Dev-next-gen](https://github.com/Dev-next-gen) · [dfwqdyl-ui](https://github.com/dfwqdyl-ui) · [DI-HUO-MING-YI](https://github.com/DI-HUO-MING-YI) · [DieMoe233](https://github.Line truncated
       },
       {
         "path": "docs/RELEASE_CHECKLIST.md",
@@ -403,13 +403,13 @@
     "sources": [
       {
         "path": "docs/RUNTIME_API.md",
-        "sha256": "e3040635df0cf62717f5acbe9aacf4909b6ad60db8468b06e90a5e9be1d76d1e",
-        "content": "# Codewhale Engine Runtime API & Integration Contract\n\n> 阅读简体中文版：[zh_hans/RUNTIME_API.md](zh_hans/RUNTIME_API.md)。\n\n`codewhale app-server --http` exposes the [Codewhale Engine](ARCHITECTURE.md) through\nits canonical local Runtime API and control plane.\nLocal SDKs, mobile/remote-control clients, and editor integrations talk to it\ninstead of screen-scraping terminal output. It serves the full HTTP/SSE runtime\nAPI (`/v1/*`), a JSON-RPC control transport over stdio, and the phone-friendly\nmobile page. `codewhale doctor --json` provides machine-readable health, and\n`codewhale serve --acp` speaks the Agent Client Protocol over stdio for editors\nsuch as Zed.\n\n`codewhale serve --http` / `serve --mobile` remain as **compatibility aliases**\nfor `codewhale app-server --http` / `--mobile`; both launch the identical\nserver. Desktop, web, SDK and custom integrations should target\n`app-server --http`. `--stdio` and `--socket` expose compatibility controls.\nBare `app-server` selects initialized JSONL control over stdio. Local stdio,\nsocket and ACP owners do not bind a hidden TCP listener. Explicit `--http`\nretains HTTP/SSE and compatibility routes on the same Runtime owner.\n\n`codewhale exec` is the separate one-shot headless worker path (stream-json,\nfleet worker subprocess, CI primitive). It is not part of this API, but it\nshares the same runtime, provider/model resolution, permission profiles, and\nevent vocabulary.\n\nThis document is the stable integration contract for native workbench\napplications (and other local supervisors) that embed the Codewhale Engine.\n\n## Architecture\n\n```\nlocal supervisor / SDK / automation harness\n        │\n        ├─ codewhale app-server --http     → HTTP/SSE runtime API (/v1/*)        [canonical]\n        ├─ codewhale app-server --mobile   → runtime API + mobile control page\n        ├─ codewhale app-server --stdio    → JSON-RPC control transport over stdio\n        ├─ codewhale app-server --socket   → same JSON-RPC over a unix domain socket (desktop daemon)\n        ├─ codewhale doctor --json         → machine-readable health & capability\n        ├─ codewhale serve --acp           → ACP stdio agent for editors such as Zed\n        ├─ codewhale serve --mcp           → MCP stdio server\n        ├─ codewhale serve --http/--mobile → legacy aliases for `app-server --http/--mobile`\n        └─ codewhale exec [args]           → one-shot headless worker (stream-json)\n```\n\nThe engine runs as a local-only process. All APIs bind to `localhost` by\ndefault. No hosted relay, no provider-token custody, no secret leakage.\n\nFor the read-only record of what a thread or turn did, see\n[`docs/RECEIPTS.md`](RECEIPTS.md): `codewhale receipts` on the CLI and the\n`/receipt` routes under **Threads** below.\n\n## Runtime API entrypoints\n\n| Entry | Transport | Use |\n|---|---|---|\n| `codewhale web [--port 7878]` | HTTP/SSE on `127.0.0.1:7878` + embedded client | First-class loopback-only browser client; opens the default browser |\n| `codewhale app-server --http` | HTTP/SSE on `127.0.0.1:7878` | Full `/v1/*` runtime API (canonical) |\n| `codewhale app-server --mobile` | HTTP/SSE on loopback + `/mobile` | Runtime API + local mobile control page |\n| `codewhale app-server --stdio` | Initialized JSONL over stdio | Compatibility controls and explicit tool-free turns through the held manager; no hidden TCP listener or full Codex interaction channel. |\n| `codewhale app-server --socket [--socket-path P]` | RPC text messages over WebSocket on a `0600` Unix domain socket (macOS/Linux) or an owner-only named pipe (Windows) | Desktop daemon: multi-client, kernel peer identity checked, `daemon/attach` claim handshake. Windows native-app qualification remains open. |\n| `codewhale app-server` | Initialized JSONL over stdio | Same selection as `--stdio`; HTTP requires explicit `--http`. |\n| `codewhale serve --http` / `--mobile` | same server as `app-server --http`/`--mobile` | Compatibility aliases |\n\n`app-server --http` and `--mobile` launch the same mature runtime API server\nhistorically reached through `serve --http` — no routes or behavior changed, so\nevery endpoint documented below is identical across both entrypoints. The\nruntime API token is read from `--auth-token`, then `CODEWHALE_RUNTIME_TOKEN`,\nthen `DEEPSEEK_RUNTIME_TOKEN`; use `--insecure-no-auth` only with a loopback\nbind. The `serve` compatibility aliases keep their `--insecure` flag.\nBare `app-server` does not open an HTTP port. Selected attached HTTP listeners\nretain their explicit bearer and non-loopback security checks.\n\nInitialized stdio/private-socket controls support `thread/loaded/list` with\n`{cursor?: string | null, limit?: number | null}`. The result is\n`{data: string[], nextCursor: string | null}` from the held manager's loaded\nengine snapshot, including idle and archived engines still in memory. It dLine truncated
+        "sha256": "6f3b8885978ef2e1b33d0fdf66ad6ccf5c25464c1951b59658aec00745390db2",
+        "content": "# Codewhale Engine Runtime API & Integration Contract\n\n> 阅读简体中文版：[zh_hans/RUNTIME_API.md](zh_hans/RUNTIME_API.md)。\n\n`codewhale app-server --http` exposes the [Codewhale Engine](ARCHITECTURE.md) through\nits canonical local Runtime API and control plane.\nLocal SDKs, mobile/remote-control clients, and editor integrations talk to it\ninstead of screen-scraping terminal output. It serves the full HTTP/SSE runtime\nAPI (`/v1/*`), a JSON-RPC control transport over stdio, and the phone-friendly\nmobile page. `codewhale doctor --json` provides machine-readable health, and\n`codewhale serve --acp` speaks the Agent Client Protocol over stdio for editors\nsuch as Zed.\n\n`codewhale serve --http` / `serve --mobile` remain as **compatibility aliases**\nfor `codewhale app-server --http` / `--mobile`; both launch the identical\nserver. Desktop, web, SDK and custom integrations should target\n`app-server --http`. `--stdio` and `--socket` expose compatibility controls.\nBare `app-server` selects initialized JSONL control over stdio. Local stdio,\nsocket and ACP owners do not bind a hidden TCP listener. Explicit `--http`\nretains HTTP/SSE and compatibility routes on the same Runtime owner.\n\n`codewhale exec` is the separate one-shot headless worker path (stream-json,\nfleet worker subprocess, CI primitive). It is not part of this API, but it\nshares the same runtime, provider/model resolution, permission profiles, and\nevent vocabulary.\n\nThis document is the stable integration contract for native workbench\napplications (and other local supervisors) that embed the Codewhale Engine.\n\n## Architecture\n\n```\nlocal supervisor / SDK / automation harness\n        │\n        ├─ codewhale app-server --http     → HTTP/SSE runtime API (/v1/*)        [canonical]\n        ├─ codewhale app-server --mobile   → runtime API + mobile control page\n        ├─ codewhale app-server --stdio    → JSON-RPC control transport over stdio\n        ├─ codewhale app-server --socket   → same JSON-RPC over a unix domain socket (desktop daemon)\n        ├─ codewhale doctor --json         → machine-readable health & capability\n        ├─ codewhale serve --acp           → ACP stdio agent for editors such as Zed\n        ├─ codewhale serve --mcp           → MCP stdio server\n        ├─ codewhale serve --http/--mobile → legacy aliases for `app-server --http/--mobile`\n        └─ codewhale exec [args]           → one-shot headless worker (stream-json)\n```\n\nThe engine runs as a local-only process. All APIs bind to `localhost` by\ndefault. No hosted relay, no provider-token custody, no secret leakage.\n\nFor the read-only record of what a thread or turn did, see\n[`docs/RECEIPTS.md`](RECEIPTS.md): `codewhale receipts` on the CLI and the\n`/receipt` routes under **Threads** below.\n\n## Runtime API entrypoints\n\n| Entry | Transport | Use |\n|---|---|---|\n| `codewhale web [--port 7878]` | HTTP/SSE on `127.0.0.1:7878` + embedded client | First-class loopback-only browser client; opens the default browser |\n| `codewhale app-server --http` | HTTP/SSE on `127.0.0.1:7878` | Full `/v1/*` runtime API (canonical) |\n| `codewhale app-server --mobile` | HTTP/SSE on loopback + `/mobile` | Runtime API + local mobile control page |\n| `codewhale app-server --stdio` | Initialized JSONL over stdio | Compatibility controls and explicit tool-free turns through the held manager; no hidden TCP listener or full Codex interaction channel. |\n| `codewhale app-server --socket [--socket-path P]` | RPC text messages over WebSocket on a `0600` Unix domain socket (macOS/Linux) or an owner-only named pipe (Windows) | Desktop daemon: multi-client, kernel peer identity checked, `daemon/attach` claim handshake. Windows native-app qualification remains open. |\n| `codewhale app-server` | Initialized JSONL over stdio | Same selection as `--stdio`; HTTP requires explicit `--http`. |\n| `codewhale serve --http` / `--mobile` | same server as `app-server --http`/`--mobile` | Compatibility aliases |\n\n`app-server --http` and `--mobile` launch the same mature runtime API server\nhistorically reached through `serve --http` — no routes or behavior changed, so\nevery endpoint documented below is identical across both entrypoints. The\nruntime API token is read from `--auth-token`, then `CODEWHALE_RUNTIME_TOKEN`,\nthen `DEEPSEEK_RUNTIME_TOKEN`; use `--insecure-no-auth` only with a loopback\nbind. The `serve` compatibility aliases keep their `--insecure` flag.\nBare `app-server` does not open an HTTP port. Selected attached HTTP listeners\nretain their explicit bearer and non-loopback security checks.\n\nInitialized stdio/private-socket controls support `thread/loaded/list` with\n`{cursor?: string | null, limit?: number | null}`. The result is\n`{data: string[], nextCursor: string | null}` from the held manager's loaded\nengine snapshot, including idle and archived engines still in memory. It dLine truncated
       },
       {
         "path": "docs/RUNTIME_ROUTES.md",
-        "sha256": "eae9cc4778f7c6f4ae2db5fe0d2d39d757521337a0818b2c2bf4a4f5dd686e0e",
-        "content": "# Runtime HTTP route inventory\n\nThis table is generated from literal route registrations in\n`crates/app-server/src/runtime_api.rs`. It names the paths and methods that\nthe current source registers, including native-client and compatibility\nsurfaces. A registered path is not a grant of permission or a promise that\na feature is enabled in your installed version.\n\nThe [Runtime API contract](RUNTIME_API.md) explains request fields, events,\nauthorization and compatibility. This inventory is a navigation index, not\na replacement for those schemas; routes used by the native client can have\nclient-specific contracts. Provider calls, file mutations and connected-service\nactions remain subject to their documented authority boundaries.\n\nRun `node web/scripts/check-runtime-routes.mjs --write` after changing a\nregistration; `npm run check:docs` refuses a stale inventory. Dynamic nested\nrouters, fallback handlers and static-asset mounts are outside this literal\nregistration index.\n\n| HTTP method | Path |\n| --- | --- |\n| GET | `/` |\n| GET | `/__codewhale/bootstrap/{nonce}` |\n| GET | `/__codewhale/mobile/bootstrap/{nonce}` |\n| POST | `/__codewhale/mobile/session` |\n| POST | `/__codewhale/mobile/stream-ticket` |\n| POST | `/__codewhale/web/stream-ticket` |\n| GET | `/assets/codewhale-192.png` |\n| GET | `/assets/codewhale-web.css` |\n| GET | `/assets/codewhale-web.js` |\n| GET | `/health` |\n| GET | `/mobile` |\n| GET | `/mobile/` |\n| DELETE / GET / PUT | `/v1/account/model-access` |\n| POST | `/v1/agent-mail` |\n| GET | `/v1/agent-runs` |\n| GET | `/v1/agent-runs/{run_id}` |\n| POST | `/v1/agent-runs/{run_id}/cancel` |\n| GET | `/v1/agents/external` |\n| GET | `/v1/agents/external/{id}/options` |\n| GET | `/v1/agents/external/quota` |\n| GET | `/v1/approvals` |\n| POST | `/v1/approvals/{approval_id}` |\n| GET | `/v1/apps/avatars` |\n| GET | `/v1/apps/avatars/{handle}/atlases/{page}` |\n| GET / POST | `/v1/apps/marketplaces` |\n| DELETE / GET | `/v1/apps/marketplaces/{name}` |\n| POST | `/v1/apps/marketplaces/{name}/install` |\n| POST | `/v1/apps/mcp/desktop-browser` |\n| GET / POST | `/v1/apps/mcp/imports` |\n| GET / POST | `/v1/apps/mcp/servers` |\n| DELETE / GET / PATCH | `/v1/apps/mcp/servers/{name}` |\n| POST | `/v1/apps/mcp/servers/{name}/disable` |\n| POST | `/v1/apps/mcp/servers/{name}/enable` |\n| POST | `/v1/apps/mcp/servers/{name}/reconnect` |\n| GET | `/v1/apps/mcp/tools` |\n| GET | `/v1/apps/plugin-index` |\n| GET | `/v1/apps/plugins` |\n| DELETE / GET | `/v1/apps/plugins/{selector}` |\n| POST | `/v1/apps/plugins/{selector}/disable` |\n| POST | `/v1/apps/plugins/{selector}/enable` |\n| POST | `/v1/apps/plugins/{selector}/restage` |\n| POST | `/v1/apps/plugins/{selector}/revoke` |\n| ANY | `/v1/apps/plugins/{selector}/routes/{*path}` |\n| POST | `/v1/apps/plugins/{selector}/trust` |\n| GET | `/v1/apps/plugins/{selector}/ui` |\n| GET | `/v1/apps/plugins/{selector}/ui/{*path}` |\n| POST | `/v1/apps/plugins/{selector}/update` |\n| GET | `/v1/apps/plugins/catalog` |\n| POST | `/v1/apps/plugins/catalog/{id}/disable` |\n| POST | `/v1/apps/plugins/catalog/{id}/enable` |\n| PUT | `/v1/apps/plugins/catalog/{id}/settings` |\n| POST | `/v1/apps/plugins/import/dsh/preview` |\n| POST | `/v1/apps/plugins/install` |\n| GET / POST | `/v1/automations` |\n| DELETE / GET / PATCH | `/v1/automations/{id}` |\n| GET | `/v1/automations/{id}/missed` |\n| PUT | `/v1/automations/{id}/missed/policy` |\n| POST | `/v1/automations/{id}/missed/run` |\n| POST | `/v1/automations/{id}/missed/skip` |\n| POST | `/v1/automations/{id}/pause` |\n| POST | `/v1/automations/{id}/resume` |\n| POST | `/v1/automations/{id}/run` |\n| GET | `/v1/automations/{id}/runs` |\n| GET | `/v1/automations/missed` |\n| GET | `/v1/changes` |\n| GET / POST | `/v1/cloud` |\n| POST | `/v1/cloud/attach` |\n| GET | `/v1/commands` |\n| GET / POST | `/v1/config` |\n| POST | `/v1/config/reload` |\n| GET | `/v1/constitution` |\n| POST | `/v1/constitution/preview` |\n| GET | `/v1/crashes` |\n| GET | `/v1/crashes/{name}` |\n| GET | `/v1/definition` |\n| GET | `/v1/diagnostics` |\n| GET | `/v1/diff` |\n| POST | `/v1/fleet/placement` |\n| GET | `/v1/fleet/profiles` |\n| GET | `/v1/fleet/profiles/{id}/document` |\n| GET / POST | `/v1/fleet/runs` |\n| GET | `/v1/fleet/runs/{run_id}` |\n| GET | `/v1/fleet/runs/{run_id}/events` |\n| GET | `/v1/fleet/runs/{run_id}/events/replay` |\n| GET | `/v1/fleet/runs/{run_id}/receipts` |\n| GET | `/v1/fleet/runs/{run_id}/receipts/{task_id}` |\n| GET | `/v1/fleet/runs/{run_id}/receipts/{task_id}/evidence` |\n| POST | `/v1/fleet/runs/{run_id}/start` |\n| POST | `/v1/fleet/runs/{run_id}/stop` |\n| GET | `/v1/fleet/runs/{run_id}/workers` |\n| GET | `/v1/fleet/workers/{worker_id}` |\n| POST | `/v1/fleet/workers/{worker_id}/interrupt` |\n| POST | `/v1/fleet/workers/{worker_id}/restart` |\n| POST | `/v1/fleet/workers/{worker_id}/stop` |\n| GET | `/v1/git` |\n| POST | `/v1/git/branch` |\n| POST | `/v1/git/commitLine truncated
+        "sha256": "1a21c05b0249c2ff225f7b554e1e610fc12122ab3da52e6ac7ceb06c90448984",
+        "content": "# Runtime HTTP route inventory\n\nThis table is generated from literal route registrations in\n`crates/app-server/src/runtime_api.rs`. It names the paths and methods that\nthe current source registers, including native-client and compatibility\nsurfaces. A registered path is not a grant of permission or a promise that\na feature is enabled in your installed version.\n\nThe [Runtime API contract](RUNTIME_API.md) explains request fields, events,\nauthorization and compatibility. This inventory is a navigation index, not\na replacement for those schemas; routes used by the native client can have\nclient-specific contracts. Provider calls, file mutations and connected-service\nactions remain subject to their documented authority boundaries.\n\nRun `node web/scripts/check-runtime-routes.mjs --write` after changing a\nregistration; `npm run check:docs` refuses a stale inventory. Dynamic nested\nrouters, fallback handlers and static-asset mounts are outside this literal\nregistration index.\n\n| HTTP method | Path |\n| --- | --- |\n| GET | `/` |\n| GET | `/__codewhale/bootstrap/{nonce}` |\n| GET | `/__codewhale/mobile/bootstrap/{nonce}` |\n| POST | `/__codewhale/mobile/session` |\n| POST | `/__codewhale/mobile/stream-ticket` |\n| POST | `/__codewhale/web/stream-ticket` |\n| GET | `/assets/codewhale-192.png` |\n| GET | `/assets/codewhale-web.css` |\n| GET | `/assets/codewhale-web.js` |\n| GET | `/health` |\n| GET | `/mobile` |\n| GET | `/mobile/` |\n| DELETE / GET / PUT | `/v1/account/model-access` |\n| POST | `/v1/agent-mail` |\n| GET | `/v1/agent-runs` |\n| GET | `/v1/agent-runs/{run_id}` |\n| POST | `/v1/agent-runs/{run_id}/cancel` |\n| GET | `/v1/agents/external` |\n| GET | `/v1/agents/external/{id}/options` |\n| GET | `/v1/agents/external/quota` |\n| GET | `/v1/approvals` |\n| POST | `/v1/approvals/{approval_id}` |\n| GET | `/v1/apps/avatars` |\n| GET | `/v1/apps/avatars/{handle}/atlases/{page}` |\n| GET / POST | `/v1/apps/marketplaces` |\n| DELETE / GET | `/v1/apps/marketplaces/{name}` |\n| POST | `/v1/apps/marketplaces/{name}/install` |\n| POST | `/v1/apps/mcp/desktop-browser` |\n| GET / POST | `/v1/apps/mcp/imports` |\n| GET / POST | `/v1/apps/mcp/servers` |\n| DELETE / GET / PATCH | `/v1/apps/mcp/servers/{name}` |\n| POST | `/v1/apps/mcp/servers/{name}/disable` |\n| POST | `/v1/apps/mcp/servers/{name}/enable` |\n| POST | `/v1/apps/mcp/servers/{name}/reconnect` |\n| GET | `/v1/apps/mcp/tools` |\n| GET | `/v1/apps/plugins` |\n| DELETE / GET | `/v1/apps/plugins/{selector}` |\n| POST | `/v1/apps/plugins/{selector}/disable` |\n| POST | `/v1/apps/plugins/{selector}/enable` |\n| POST | `/v1/apps/plugins/{selector}/restage` |\n| POST | `/v1/apps/plugins/{selector}/revoke` |\n| ANY | `/v1/apps/plugins/{selector}/routes/{*path}` |\n| POST | `/v1/apps/plugins/{selector}/trust` |\n| GET | `/v1/apps/plugins/{selector}/ui` |\n| GET | `/v1/apps/plugins/{selector}/ui/{*path}` |\n| POST | `/v1/apps/plugins/{selector}/update` |\n| GET | `/v1/apps/plugins/catalog` |\n| POST | `/v1/apps/plugins/catalog/{id}/disable` |\n| POST | `/v1/apps/plugins/catalog/{id}/enable` |\n| PUT | `/v1/apps/plugins/catalog/{id}/settings` |\n| POST | `/v1/apps/plugins/import/dsh/preview` |\n| POST | `/v1/apps/plugins/install` |\n| GET / POST | `/v1/automations` |\n| DELETE / GET / PATCH | `/v1/automations/{id}` |\n| GET | `/v1/automations/{id}/missed` |\n| PUT | `/v1/automations/{id}/missed/policy` |\n| POST | `/v1/automations/{id}/missed/run` |\n| POST | `/v1/automations/{id}/missed/skip` |\n| POST | `/v1/automations/{id}/pause` |\n| POST | `/v1/automations/{id}/resume` |\n| POST | `/v1/automations/{id}/run` |\n| GET | `/v1/automations/{id}/runs` |\n| GET | `/v1/automations/missed` |\n| GET | `/v1/changes` |\n| GET / POST | `/v1/cloud` |\n| POST | `/v1/cloud/attach` |\n| GET | `/v1/commands` |\n| GET / POST | `/v1/config` |\n| POST | `/v1/config/reload` |\n| GET | `/v1/constitution` |\n| POST | `/v1/constitution/preview` |\n| GET | `/v1/crashes` |\n| GET | `/v1/crashes/{name}` |\n| GET | `/v1/definition` |\n| GET | `/v1/diagnostics` |\n| GET | `/v1/diff` |\n| POST | `/v1/fleet/placement` |\n| GET | `/v1/fleet/profiles` |\n| GET | `/v1/fleet/profiles/{id}/document` |\n| GET / POST | `/v1/fleet/runs` |\n| GET | `/v1/fleet/runs/{run_id}` |\n| GET | `/v1/fleet/runs/{run_id}/events` |\n| GET | `/v1/fleet/runs/{run_id}/events/replay` |\n| GET | `/v1/fleet/runs/{run_id}/receipts` |\n| GET | `/v1/fleet/runs/{run_id}/receipts/{task_id}` |\n| GET | `/v1/fleet/runs/{run_id}/receipts/{task_id}/evidence` |\n| POST | `/v1/fleet/runs/{run_id}/start` |\n| POST | `/v1/fleet/runs/{run_id}/stop` |\n| GET | `/v1/fleet/runs/{run_id}/workers` |\n| GET | `/v1/fleet/workers/{worker_id}` |\n| POST | `/v1/fleet/workers/{worker_id}/interrupt` |\n| POST | `/v1/fleet/workers/{worker_id}/restart` |\n| POST | `/v1/fleet/workers/{worker_id}/stop` |\n| GET | `/v1/git` |\n| POST | `/v1/git/branch` |\n| POST | `/v1/git/commit` |\n| POST | `/v1/git/discard` |\nLine truncated
       }
     ]
   },

web/lib/release-credits.ts

@@ -35,6 +35,7 @@ export const RELEASE_CONTRIBUTORS: string[] = [
   "@luochen211",
   "@gannp",
   "@Felixkw12",
+  "@MannXo",
 ];
 
 /**