0.10.1: contributor integration, human-wait lifecycle, and release qualification

.config/nextest.toml

@@ -77,7 +77,9 @@ filter = 'package(codewhale-tui) & kind(lib) & test(/^fleet::manager::tests::/)'
 test-group = 'fleet-manager-lifecycle'
 
 [[profile.default.overrides]]
-filter = 'package(codewhale-tui) & kind(lib) & (test(/^extension_host::/) | test(/^core::engine::.*extension/))'
+# DSH preparation also launches the isolated host against the shared hermetic
+# home. Keep its ACL grants/retirement in this existing serial lane.
+filter = 'package(codewhale-tui) & kind(lib) & (test(/^extension_host::/) | test(/^core::engine::.*extension/) | test(/^plugins::install::dsh::/) | test(/^plugins::tests::dsh_/) | test(/^runtime_api::tests::dsh_package_preview_then_exact_install_over_http$/) | test(/^commands::groups::plugins::tests::dsh_import_reviews_without_installing_then_installs_the_exact_bundle$/))'
 test-group = 'extension-host'
 
 [[profile.default.overrides]]

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

@@ -848,21 +848,30 @@ function jobTimeout(source, job) {
   return Number(match[1]);
 }
 
-// Pin the measured release-lane budget: fast setup and packaging fail quickly,
-// while cross-platform compilation keeps real margin over the 40-45m Windows
-// build observed on the release train.
+// Fast setup and packaging fail quickly. Native builds need the same finite
+// cold-build allowance as full CI: both 0.10.1 macOS artifacts hit the old
+// 90m compilation cap before reaching their launch and inventory checks.
 assert.equal(jobTimeout(candidate, "resolve"), 10);
 assert.equal(jobTimeout(candidate, "web"), 15);
 assert.equal(jobTimeout(artifacts, "pin"), 10);
-assert.equal(jobTimeout(artifacts, "build"), 90);
+assert.ok(
+  jobTimeout(artifacts, "build") >= jobTimeout(ci, "test"),
+  "native artifacts must allow the full CI cold-build budget",
+);
 for (const job of ["bundle", "windows-installer", "assemble", "smoke"]) {
   assert.equal(jobTimeout(artifacts, job), 15, `${job} must keep the 15m packaging cap`);
 }
-assert.equal(jobTimeout(nightly, "build"), 90);
+assert.equal(
+  jobTimeout(nightly, "build"), jobTimeout(artifacts, "build"),
+  "nightly and release must share the native cold-build allowance",
+);
 assert.equal(jobTimeout(release, "resolve"), 10);
-// The v0.9.12 tag push finished every parity step and was then cancelled at
-// 20 minutes inside rust-cache's post-run save; 45 keeps that margin.
-assert.equal(jobTimeout(parityWorkflow, "parity"), 45);
+// The 0.10.1 cold parity build exhausted 45 minutes before tests started.
+// Reuse the full CI suite's budget rather than pinning an older release's cap.
+assert.ok(
+  jobTimeout(parityWorkflow, "parity") >= jobTimeout(ci, "test"),
+  "release parity must allow the full CI suite's cold-build budget",
+);
 
 console.log(
   "Workflow contracts OK: 6-target/12-asset single-runtime nightly and exact-head 7-target/34-asset release candidate.",

.github/workflows/ci.yml

@@ -912,6 +912,12 @@ jobs:
           save-if: ${{ github.ref == 'refs/heads/main' }}
       - uses: taiki-e/install-action@nextest
         if: needs.changes.outputs.heavy == 'true' && (matrix.os != 'ubuntu-latest' || github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
+      - name: Check portable config policy boundary
+        if: needs.changes.outputs.heavy == 'true' && matrix.os == 'ubuntu-latest' && (github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request')
+        shell: bash
+        run: |
+          python3 -B scripts/test_check_command_config_policy_proof.py
+          sh scripts/check-portable-config-policy.sh
       - uses: actions/setup-node@v7
         # The extension-host integration tests spawn the real bundle under
         # Node >= 22.19; CODEWHALE_EXT_HOST_TESTS below makes a missing Node a
@@ -1012,6 +1018,7 @@ jobs:
           if [ -n "$monitor" ]; then kill "$monitor" 2>/dev/null || true; fi
           exit "$status"
         env:
+          QA_PTY_DIAGNOSTICS_DIR: ${{ runner.temp }}/pty-failures
           CODEWHALE_EXT_HOST_TESTS: '1'
           CODEWHALE_EXT_HOST_BUN_TESTS: '1'
           # sccache 0.17 panics resolving its config directory under the
@@ -1035,6 +1042,15 @@ jobs:
           # forced 32 MiB lives in spawned binaries, which size their own
           # stacks explicitly and never read this variable.
           RUST_MIN_STACK: '16777216'
+      - name: Retain sealed terminal failure diagnostics
+        if: failure()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: terminal-failures-${{ 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'
         shell: bash
@@ -1234,7 +1250,9 @@ jobs:
     # 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'))
-    timeout-minutes: 75
+    # 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: 165
     runs-on: macos-latest
     steps:
       - uses: actions/checkout@v7

.github/workflows/nightly.yml

@@ -26,7 +26,8 @@ env:
 jobs:
   build:
     name: Build ${{ matrix.platform }}
-    timeout-minutes: 90
+    # Native builds use the same finite cold-build allowance as release/CI.
+    timeout-minutes: 165
     strategy:
       fail-fast: false
       matrix:

.github/workflows/release-artifacts.yml

@@ -84,7 +84,9 @@ jobs:
 
   build:
     name: Build ${{ matrix.platform }}
-    timeout-minutes: 90
+    # Both cold macOS artifact builds on 0.10.1 exhausted 90 minutes inside
+    # compilation. Keep the full CI build budget; packaging stays capped below.
+    timeout-minutes: 165
     # FreeBSD is a source-build target validated via `cargo check --target x86_64-unknown-freebsd -p codewhale-cli --locked`
     # (see packaging/freebsd/README.md and docs/INSTALL.md#freebsd). The 7×1 prebuilt matrix stays 7 targets;
     # FreeBSD has no prebuilt asset, no npm binary, and no matrix bloat — it builds from source.

.github/workflows/release-parity.yml

@@ -21,7 +21,9 @@ env:
 jobs:
   parity:
     name: Workspace parity
-    timeout-minutes: 45
+    # Cold check, Clippy, executable and test builds exceeded the old 45m
+    # limit before the suite started. Retain the full CI test-job budget.
+    timeout-minutes: 165
     runs-on: ubuntu-latest
     steps:
       # Every caller's resolve job already proved GITHUB_SHA equals the
@@ -53,7 +55,8 @@ jobs:
             echo "apt-get update failed (attempt $i); retrying in 15s"
             sleep 15
           done
-          sudo apt-get install -y libdbus-1-dev pkg-config
+          sudo apt-get install -y libdbus-1-dev pkg-config bubblewrap apparmor-profiles
+          sh scripts/prepare-linux-test-sandbox.sh
       # Restore after the trusted lockfile is on disk. Key is OS + arch +
       # explicit stable toolchain + rust-cache's Cargo.lock / rust-toolchain
       # hash. Never interpolate github.event, github.ref, github.sha, or inputs.

.github/workflows/web.yml

@@ -162,8 +162,8 @@ jobs:
       - name: Check Cloudflare deploy environment
         run: npm run check:deploy-env
       # npm's deploy script performs one OpenNext build, then deploys that exact
-      # bundle. Wrangler must not run a custom post-cache build: OpenNext
-      # populates the remote cache before it hands the bundle to Wrangler.
+      # bundle. OpenNext populates the remote cache before cf deploy --prebuilt;
+      # the bundler has no custom build that could invalidate that cache.
       - name: Build and deploy exact OpenNext bundle
         run: npm run deploy
       - name: Verify exact deployed revision

.gitignore

@@ -174,6 +174,9 @@ CODEWHALE_0_9_0_CUTOVER.md
 # computer-use plugin smoke receipts (per-run local evidence)
 crates/tui/plugins/computer-use/receipts/
 
+# OrcaRouter provider screenshot evidence (per-run local evidence)
+orca-evidence/
+
 # Portable pet build entry points are source.
 !pet/**/*.sh
 !pet/verify.sh

CHANGELOG.md

@@ -9,6 +9,19 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [0.10.1] - 2026-10-01
 
+### Contributor integration and reliability
+
+- Runtime clients can read one tool call's actual workspace changes and reviewed skill details (thanks @gaord, #6817 and #6869). In-flight snapshot pairs remain pending; missing objects and corrupt repository metadata are distinguished.
+- Search accepts valid preferred locales, and image dimensions describe the same bytes sent to the model (thanks @asto18089, #6860 and #6858). Automation deletion keeps its definition until cleanup succeeds, and compaction preserves its original summary anchor (#6864 and #6857).
+- Config/status/permission commands share portable contracts while the host retains mutation authority; queue workers acknowledge a scheduled retry for temporary first-claim contention and fail honestly on corruption (thanks @aboimpinto, #6832).
+- Indefinite questions, approvals and elevation waits survive the TUI watchdog. Answers get time to resume the current turn; settled requests disappear by identity. Thanks @7jrxt42BxFZo4iAnN4CX for #6872.
+- Configured approval expiry belongs to the held Engine request; hiding or covering its card cannot restart the deadline, and a late queued answer cannot approve an expired call.
+- Tool discovery keeps the highest-ranked matches when a result batch exceeds the existing cache bounds, preserving search order and the 16 KiB limit (adapted from @AdityaVG13's #6393).
+- Model-switch receipts now translate their session-only saving note in every complete locale pack; the three save commands remain directly usable (thanks @Lstarsky0, #6875).
+- The bundled `computer-use` plugin is 0.12.1, reconciled with canonical source
+  `a656f67455fc5639f28304fbf61075db3925058a` while retaining Core's embedding
+  manifest and version contract.
+
 Codewhale v0.10.1 focuses on reliability and first-run behavior. Turns that
 stall now say so, approvals keep what you approved, plugin suggestions are
 quieter, and Fleet runs can be checked before they spend anything.
@@ -17,6 +30,19 @@ note below before upgrading.
 
 ### Added
 
+- `/plugin doctor` reports stale built-in records and snapshots, and
+  `/plugin doctor --fix` retires them. A user plugin, a snapshot a running
+  process names, and a snapshot inside the grace window are kept. The
+  previous `state.json` is kept as `state.json.pre-gc`.
+- Reviewed plugins can declare named OpenAI-compatible OAuth routes. The host
+  owns PKCE, refresh and credential storage, and checks the review at each
+  request ([docs/PLUGIN_PROVIDERS.md](docs/PLUGIN_PROVIDERS.md), #6805).
+  The provider capability advances plugin review policy to v5 (v6 with the
+  extension host): older receipts require explicit review again.
+- OrcaRouter account sign-in uses PKCE and saves the same durable API key as
+  manual setup; its live catalog keeps chat-capable rows and stated pricing
+  and modality facts (#6867).
+
 - Experimental TypeScript extension host. New in this release and off by
   default: turn it on with `[features] extension_host = true`. A plugin that
   declares a `native` TypeScript or JavaScript entry (the Cordis / DeepSeek
@@ -259,6 +285,15 @@ note below before upgrading.
 
 ### Fixed
 
+- A failure Codewhale can name is no longer labelled an internal fault. An HTTP
+  400/405/409/413/422 rejection, an out-of-credits 402, the context-budget stop
+  and a turn's own step or wall-clock ceiling now carry an input or budget
+  label, and a bare `ERROR` from a provider is reported as an unreadable error
+  instead of a warning. Refs #6843.
+- A transient upstream failure reported as an error frame inside a successful
+  response is retried within the stream retry budget. When the budget is spent
+  the turn fails once with an error card instead of an amber warning that
+  promised a retry. Refs #6795.
 - Diff lines and tool output wrap at grapheme boundaries, so emoji families,
   skin tones and variation selectors no longer split across lines
   ([#6829](https://github.com/codewhale-hq/Codewhale/pull/6829), thanks @Lstarsky0).
@@ -1200,7 +1235,13 @@ note below before upgrading.
 
 ### Contributors
 
-Seventeen contributors and issue reporters are credited below, including
+- **[@AdityaVG13](https://github.com/AdityaVG13)** — supplied the discovery-cache priority correction adapted from [#6393](https://github.com/codewhale-hq/Codewhale/pull/6393), keeping highest-ranked tools through cache overflow. Its broader echo and fork-inheritance draft remains open.
+- **[@7jrxt42BxFZo4iAnN4CX](https://github.com/7jrxt42BxFZo4iAnN4CX)** — reported indefinite questions cancelled by the TUI watchdog and supplied the timer evidence ([#6872](https://github.com/codewhale-hq/Codewhale/issues/6872)).
+
+- **[@hodeswildsmith455-boop](https://github.com/hodeswildsmith455-boop)** — added OrcaRouter account sign-in with PKCE and its live chat catalog ([#6867](https://github.com/codewhale-hq/Codewhale/pull/6867)).
+- **[@LIghtJUNction](https://github.com/LIghtJUNction)** — added reviewed plugin-provided AI routes with host-owned OAuth PKCE credentials and request-time authority checks ([#6805](https://github.com/codewhale-hq/Codewhale/pull/6805)).
+
+Contributors and issue reporters are credited below, including
 @cenab's provider report.
 
 - **[@Guan0923](https://github.com/Guan0923)** — accepted case-insensitive HTTP(S) schemes in `config doctor` without rewriting the configured URL ([#6819](https://github.com/codewhale-hq/Codewhale/pull/6819)), and routed the Python and JavaScript execution tools through the session's execution policy ([#6820](https://github.com/codewhale-hq/Codewhale/pull/6820)).
@@ -1211,7 +1252,7 @@ Seventeen contributors and issue reporters are credited below, including
 - **[@Andrea-Bruno](https://github.com/Andrea-Bruno)** — designed the Superfast Decision Gate and contributed its off-by-default shadow classifier ([#6604](https://github.com/codewhale-hq/Codewhale/pull/6604), [#6603](https://github.com/codewhale-hq/Codewhale/issues/6603)).
 - **[@aiapienthusiast](https://github.com/aiapienthusiast)** — added Cheaper Inference to the bundled provider catalog ([#6761](https://github.com/codewhale-hq/Codewhale/pull/6761)).
 - **[@gaord](https://github.com/gaord)** — let a client fork a thread at a named turn ([#6580](https://github.com/codewhale-hq/Codewhale/pull/6580)), let undo roll back files for the turn it is undoing ([#6483](https://github.com/codewhale-hq/Codewhale/pull/6483)), stopped resume and fork from duplicating threads and sessions ([#6406](https://github.com/codewhale-hq/Codewhale/pull/6406)), exposed user-defined provider routes to native clients ([#6404](https://github.com/codewhale-hq/Codewhale/pull/6404)), and kept a fork going when a turn lost its tool call ([#6664](https://github.com/codewhale-hq/Codewhale/pull/6664)).
-- **[@Lstarsky0](https://github.com/Lstarsky0)** — moved the docs/work, legal, digest and FAQ pages onto the dictionary spine ([#6405](https://github.com/codewhale-hq/Codewhale/pull/6405), [#6417](https://github.com/codewhale-hq/Codewhale/pull/6417), [#6499](https://github.com/codewhale-hq/Codewhale/pull/6499), [#6574](https://github.com/codewhale-hq/Codewhale/pull/6574)), tightened the Chinese-branching ceiling to 18 ([#6403](https://github.com/codewhale-hq/Codewhale/pull/6403)), and made Fleet publish without a two-link window ([#6431](https://github.com/codewhale-hq/Codewhale/pull/6431)). Also moved the constitution page onto the dictionary spine and kept its install link in the selected locale ([#6733](https://github.com/codewhale-hq/Codewhale/pull/6733)), wrapped diff and tool output at grapheme boundaries ([#6829](https://github.com/codewhale-hq/Codewhale/pull/6829)), and translated the context inspector rows twelve packs still shipped in English ([#6831](https://github.com/codewhale-hq/Codewhale/pull/6831)).
+- **[@Lstarsky0](https://github.com/Lstarsky0)** — moved the docs/work, legal, digest and FAQ pages onto the dictionary spine ([#6405](https://github.com/codewhale-hq/Codewhale/pull/6405), [#6417](https://github.com/codewhale-hq/Codewhale/pull/6417), [#6499](https://github.com/codewhale-hq/Codewhale/pull/6499), [#6574](https://github.com/codewhale-hq/Codewhale/pull/6574)), tightened the Chinese-branching ceiling to 18 ([#6403](https://github.com/codewhale-hq/Codewhale/pull/6403)), and made Fleet publish without a two-link window ([#6431](https://github.com/codewhale-hq/Codewhale/pull/6431)). Also moved the constitution page onto the dictionary spine and kept its install link in the selected locale ([#6733](https://github.com/codewhale-hq/Codewhale/pull/6733)), wrapped diff and tool output at grapheme boundaries ([#6829](https://github.com/codewhale-hq/Codewhale/pull/6829)), and translated the context inspector rows twelve packs still shipped in English ([#6831](https://github.com/codewhale-hq/Codewhale/pull/6831)). Translated the session-only note after model switches across the complete TUI locale packs ([#6875](https://github.com/codewhale-hq/Codewhale/pull/6875)).
 - **[@aboimpinto](https://github.com/aboimpinto)** — restored a green Linux full-workspace test gate without loosening any test, twice ([#6581](https://github.com/codewhale-hq/Codewhale/pull/6581), [#6666](https://github.com/codewhale-hq/Codewhale/pull/6666)). Completed the seventeen-command portable session group, including `/structcopy` ([#6793](https://github.com/codewhale-hq/Codewhale/pull/6793)).
 - **[@dajiaohuang](https://github.com/dajiaohuang)** — `codewhale config set` checks a known setting's value against its schema type before saving it ([#6568](https://github.com/codewhale-hq/Codewhale/pull/6568)).
 - **[@jayanthvee](https://github.com/jayanthvee)** — reported and diagnosed that killing the npm launcher's `node.exe` ends Windows sessions without cleanup, with reproductions and fix directions ([#6827](https://github.com/codewhale-hq/Codewhale/issues/6827)).

CONTRIBUTING.md

@@ -6,7 +6,7 @@ Thank you for your interest in contributing to codewhale! This document provides
 
 ### Prerequisites
 
-- Rust 1.88 or later (edition 2024)
+- Rust 1.89 or later (edition 2024)
 - Cargo package manager
 - Git
 
@@ -18,21 +18,43 @@ Thank you for your interest in contributing to codewhale! This document provides
    cd CodeWhale
    ```
 
-2. Build the project:
+2. Build the current engine and terminal:
    ```bash
-   cargo build
+   CODEWHALE_BUILD_SHA="$(git rev-parse HEAD)" cargo build --locked -p codewhale-cli
    ```
 
-3. Run tests:
+3. Run the tests near your change (see [Fast local loop](#fast-local-loop)):
    ```bash
-   cargo test --workspace --all-features
+   scripts/dev-test.sh tui your_test_filter
    ```
 
 4. Run with development settings:
    ```bash
-   cargo run --bin codewhale
+   ./target/debug/codewhale --version
+   ./target/debug/codewhale
    ```
 
+### Testing the latest source
+
+The canonical source is [`codewhale-hq/Codewhale`'s `main` branch](https://github.com/codewhale-hq/Codewhale/tree/main).
+Release candidates land there after their CI gates pass, so contributors can
+test and build on the same source. Tagged downloads remain the latest published
+release; their version can lag the development version on `main`.
+
+For a fresh checkout of the current source:
+
+```bash
+git clone --branch main https://github.com/codewhale-hq/Codewhale.git
+cd Codewhale
+CODEWHALE_BUILD_SHA="$(git rev-parse HEAD)" cargo build --release --locked -p codewhale-cli
+./target/release/codewhale --version
+./target/release/codewhale
+```
+
+Include the commit shown by `--version` when reporting a problem. If you work
+from a fork, add the canonical repository as `upstream` and fetch `upstream/main`
+before starting a change; preserve any local work when updating your branch.
+
 ## Development Workflow
 
 ### Code Style