@qwen-code/qwen-code 0.21.1 → 0.21.2-nightly.20260801.bc382c3ff

package/bundled/qc-helper/docs/features/skills.md

@@ -68,6 +68,20 @@ Use project Skills for:
 
 Project Skills can be checked into git and automatically become available to teammates.
 
+### Maintain auto-generated project Skills
+
+Qwen Code tracks successful uses of generated project Skills locally, including while new Auto Skill generation is disabled, so re-enabling maintenance cannot mistake a recently used skill for an inactive one. When **Auto Skill** is enabled, it periodically moves inactive generated Skills out of the active library. Only directories named `.qwen/skills/auto-skill-*` whose `SKILL.md` frontmatter contains `source: auto-skill` are managed; personal, extension, bundled, and hand-authored Skills are never selected.
+
+- After 30 days without a successful use or `SKILL.md` edit, an auto-skill is marked stale.
+- After 90 days, its complete directory is moved to `.qwen/archived-skills/`. Nothing is permanently deleted.
+- Automatic maintenance runs at most once every 7 days in trusted workspaces. Each newly observed auto-skill gets a full grace period before maintenance begins.
+- A pinned auto-skill is excluded from automatic stale and archive transitions until it is unpinned.
+- Archived directory names remain reserved, and an existing archive destination skips only that collision rather than stopping maintenance for other skills.
+
+Use `/curator` to see active, stale, archived, and pinned auto-skills. Run `/curator run --dry-run` to preview a maintenance pass, `/curator run` to apply it immediately, `/curator pin <directory>` or `/curator unpin <directory>` to control per-skill maintenance, or `/curator restore <directory>` to move an archived auto-skill back into the active library.
+
+Status and dry-run previews are available in safe mode and untrusted workspaces. Applying maintenance, changing pins, and restoring archived auto-skills require a trusted workspace outside safe mode.
+
 ## Write `SKILL.md`
 
 Create a `SKILL.md` file with YAML frontmatter and Markdown content:

package/bundled/qc-helper/docs/features/sub-agents.md

@@ -25,14 +25,61 @@ Only `subagent_type: "fork"` accepts `fork_turns`:
 
 Tool responses and pure system reminders do not count as user turns. Regular named subagents and agent-team teammates do not accept `fork_turns`; they keep their separate conversation context.
 
+## Restricting Fork Tool Execution with `fork_tools`
+
+Only `subagent_type: "fork"` accepts `fork_tools`. The array may contain exact canonical tool names, such as `read_file` and `grep_search`, or MCP server patterns such as `mcp__github`. The fork still receives the same model-visible tool declarations as an unrestricted fork, preserving its prompt-cache prefix, but its task prompt identifies the restriction and a call not matched by `fork_tools` is rejected before scheduling or approval.
+
+- Forks never execute `ask_user_question`; when user input is required, they report the blocker to their parent agent.
+- Omitting `fork_tools` allows every other inherited tool.
+- An empty array rejects every tool call.
+- `*` is not accepted; omit `fork_tools` to allow every otherwise-executable inherited tool.
+- Tool names cannot have surrounding whitespace. Wildcards are accepted only as `mcp__*` or as a trailing MCP tool-prefix pattern such as `mcp__github__read_*`.
+- `mcp__*` intentionally allows every MCP tool while still denying unlisted built-in tools.
+- Shell command argument patterns are not supported. Listing `run_shell_command` allows that tool to proceed through its normal permission checks but does not pre-approve any command.
+
+This is a per-invocation restriction supplied by the caller. It narrows a child fork's capabilities but is not an administrator-enforced security sandbox because the caller can omit or expand the list.
+
+## Reusing Fork Restrictions with `fork_profile`
+
+A project can save a named fork restriction in `.qwen/fork-profiles/<name>.md` and select it with `fork_profile`. This is useful when several calls need the same tool boundary and task guidance:
+
+```markdown
+---
+name: ro-research
+tools:
+  - read_file
+  - grep_search
+  - glob
+  - mcp__search__*
+promptHint: |
+  Work read-only. Prefer targeted searches and cite file evidence.
+---
+```
+
+Then launch the fork with:
+
+```text
+agent(description="Research", prompt="Inspect the retry path", subagent_type="fork", fork_profile="ro-research")
+```
+
+- `fork_profile` is valid only for a fork and cannot be combined with `fork_tools` or a named teammate.
+- Profiles are currently project-only. The requested name, filename, and frontmatter `name` must match exactly. The profile must resolve to a regular file inside `.qwen/fork-profiles/` and cannot exceed 64 KiB.
+- `tools` is required and follows the `fork_tools` rules, including empty-array deny-all behavior.
+- `promptHint` is optional and limited to 200 characters. It is escaped and framed as project-supplied guidance after the fork directive and before the authoritative tool restriction; it does not change the inherited system instruction or model-visible tool declarations. Profile files are frontmatter-only, so non-blank Markdown after the closing `---` is rejected instead of silently ignored.
+- The profile is resolved once at launch. A retained fork continues with the resolved tool snapshot even if the project file later changes.
+- Project fork profiles are unavailable in safe mode and bare mode, which disable local customizations.
+
+Like `fork_tools`, a fork profile is a caller-selected restriction rather than an administrator sandbox. Its optional prompt guidance is project-controlled content.
+
 ### How Fork Differs from Named Subagents
 
-|               | Named Subagent                                                 | Fork Subagent                                                                           |
-| ------------- | -------------------------------------------------------------- | --------------------------------------------------------------------------------------- |
-| Context       | Starts fresh with no parent conversation history               | Inherits all parent history by default; `fork_turns` can select a bounded recent window |
-| System prompt | Uses its own configured prompt                                 | Uses parent's exact system prompt (for cache sharing)                                   |
-| Execution     | Background by default; supports an explicit foreground opt-out | Always detached; parent continues immediately                                           |
-| Use case      | Specialized tasks (testing, docs)                              | Parallel tasks that need the current context                                            |
+|               | Named Subagent                                                 | Fork Subagent                                                                                                                                                                                        |
+| ------------- | -------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Context       | Starts fresh with no parent conversation history               | Inherits all parent history by default; `fork_turns` can select a bounded recent window                                                                                                              |
+| System prompt | Uses its own configured prompt                                 | Uses parent's exact system prompt (for cache sharing)                                                                                                                                                |
+| Tools         | Configured declaration set without interactive question tools  | Keeps the parent-derived declaration set for caching; execution always rejects `ask_user_question`, and `fork_tools` or `fork_profile` can independently narrow it without changing that declaration |
+| Execution     | Background by default; supports an explicit foreground opt-out | Always detached; parent continues immediately                                                                                                                                                        |
+| Use case      | Specialized tasks (testing, docs)                              | Parallel tasks that need the current context                                                                                                                                                         |
 
 ### When Fork is Used
 
@@ -46,9 +93,9 @@ The AI automatically uses fork when it needs to:
 
 All forks share the parent's exact API request prefix (system prompt, tools, conversation history), enabling DashScope prompt cache hits. When 3 forks run in parallel, the shared prefix is cached once and reused — saving 80%+ token costs compared to independent subagents.
 
-### Recursive Fork Prevention
+### Recursive Delegation Prevention
 
-Fork children cannot create further forks. This is enforced at runtime — if a fork attempts to spawn another fork, it receives an error instructing it to execute tasks directly.
+Fork children cannot spawn any further sub-agent. This is enforced at runtime — if a fork calls the Agent tool, it receives an error instructing it to execute tasks directly.
 
 ### Current Limitation
 

package/bundled/qc-helper/docs/features/tool-use-summaries.md

@@ -1,6 +1,6 @@
 # Tool-Use Summaries
 
-Qwen Code can generate a short, git-commit-subject-style label after each tool batch completes, summarizing what the batch accomplished. The label appears inline: for a completed tool group in the main view it replaces the generic `Tool × N` header; when the group is force-expanded (in the `Ctrl+O` full-detail transcript, or for error / user-initiated batches) it appears as a dim `● <label>` line below the group.
+Qwen Code can generate a short, git-commit-subject-style label after each tool batch completes, summarizing what the batch accomplished. The label appears inline: for a completed tool group in the main view it replaces the generic `Tool × N` header; when the group is force-expanded (in `Ctrl+O` expanded detail mode, or for error / user-initiated batches) it appears as a dim `● <label>` line below the group.
 
 This is a UX aid for parallel tool calls: when the model fans out into several `Read` + `Grep` + `Bash` calls at once, the summary tells you the intent at a glance instead of forcing you to scan the tool list.
 
@@ -18,11 +18,11 @@ In the main transcript, a completed collapsible batch folds into a single labele
 ╰──────────────────────────────────────────────╯
 ```
 
-The full per-tool output is a keystroke away: press `Ctrl+O` to open the full-detail transcript.
+The full per-tool output is a keystroke away: press `Ctrl+O` to toggle expanded detail mode.
 
-### Full-detail transcript (`Ctrl+O`) and force-expanded groups
+### Expanded detail mode (`Ctrl+O`) and force-expanded groups
 
-When a group is force-expanded — in the `Ctrl+O` transcript, or for error / user-initiated batches in the main view — each tool renders individually and the summary appears as a dim badge line below the group:
+When a group is force-expanded — in `Ctrl+O` expanded detail mode, or for error / user-initiated batches in the main view — each tool renders individually and the summary appears as a dim badge line below the group:
 
 ```
 ╭──────────────────────────────────────────────╮
@@ -122,7 +122,7 @@ These settings can be configured in `settings.json`:
 
 Three points that tend to trip up a first read of this feature:
 
-1. **One generation per batch, shared by both display modes.** The fast-model call happens exactly once in `handleCompletedTools` when a tool batch finalizes. Opening the `Ctrl+O` transcript afterwards does **not** trigger a new call — both the main view and the full-detail transcript read from the same `tool_use_summary` history entry that was captured the first time.
+1. **One generation per batch, shared by both display modes.** The fast-model call happens exactly once in `handleCompletedTools` when a tool batch finalizes. Toggling `Ctrl+O` expanded detail mode afterwards does **not** trigger a new call — both the collapsed and the expanded rendering read from the same `tool_use_summary` history entry that was captured the first time.
 2. **No backfill on toggle or on session resume.** A `tool_group` that completed before the feature was enabled (or before you flipped the setting on, or in a resumed session — `ChatRecordingService` does not persist summary entries) will never get a label. There is no "sweep existing history" pass. If you turn this setting on mid-session, only _future_ batches will show a label; older groups keep the default rendering with no indicator that a label is missing.
 3. **Main-agent batches only.** The trigger lives in the main session's turn loop (`useGeminiStream`), so:
    - ✅ Shell, MCP, file operations, and the `Task` / subagent tool _call itself_ (as it appears in the main batch) are summarized.
@@ -132,7 +132,7 @@ Three points that tend to trip up a first read of this feature:
 
 ## Display behavior
 
-The main view already folds a completed collapsible batch into a single labeled row (`✓  Read 4 text files`) — the summary does the work of the old per-tool list. For full per-tool detail, press `Ctrl+O` to open the full-detail transcript, where each tool renders individually with the summary as a trailing `● <label>` line below the group.
+The main view already folds a completed collapsible batch into a single labeled row (`✓  Read 4 text files`) — the summary does the work of the old per-tool list. For full per-tool detail, press `Ctrl+O` to toggle expanded detail mode, where each tool renders individually with the summary as a trailing `● <label>` line below the group.
 
 ```json
 {
@@ -170,5 +170,5 @@ If you do not want the extra cost, turn the feature off via `experimental.emitTo
 
 ## Related
 
-- [Full-detail transcript](../configuration/settings#ui) — press `Ctrl+O` to open the frozen full-detail transcript; the summary replaces the generic tool-group header for completed groups in the main view.
+- [Expanded detail mode](../configuration/settings#ui) — press `Ctrl+O` to expand all tool outputs inline; the summary replaces the generic tool-group header for completed groups in the main view.
 - [Followup Suggestions](./followup-suggestions) — another fast-model-driven UX enhancement that shares the same `fastModel` setting.

package/bundled/qc-helper/docs/qwen-serve.md

@@ -218,17 +218,19 @@ remediation.
 
 The daemon also exposes workspace file helpers:
 
-- `GET /file` reads text files and returns a raw-byte `sha256:<hex>` hash.
+- `GET /file` reads text files. Full-snapshot responses return a raw-byte
+  `sha256:<hex>` hash; finite-line windows from files above 256 KiB omit it.
 - `GET /file/bytes` reads bounded raw byte windows and returns base64 content.
 - `POST /file/write` creates or replaces text files.
 - `POST /file/edit` applies one exact text replacement.
 
 Write/edit are **strict mutation routes**: even on loopback they require a
 configured bearer token, otherwise they return `token_required`. Replacements
-and edits require the latest `expectedHash` from `GET /file` (or a full-window
-`GET /file/bytes`). `create` never overwrites. Explicit writes to ignored paths
-are allowed but audited. Binary writes, delete/move/mkdir, and recursive parent
-creation are not part of this surface.
+and edits require the latest `expectedHash` from a full-snapshot `GET /file`
+(or a full-window `GET /file/bytes`). A partial large-file window cannot be
+used as an optimistic-concurrency token. `create` never overwrites. Explicit
+writes to ignored paths are allowed but audited. Binary writes,
+delete/move/mkdir, and recursive parent creation are not part of this surface.
 
 ### 3. Open a session
 
@@ -386,10 +388,11 @@ Notes:
 | `--require-auth`                        | `false`         | Refuse to start without a bearer token, even on loopback. Hardens the `127.0.0.1` developer default for shared dev hosts / CI runners / multi-tenant workstations where any local user can hit the listener. Boots only with `--token` or `QWEN_SERVER_TOKEN` set; gates `/health` behind the bearer too.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
 | `--tls-cert <path>`                     | —               | Path to a PEM certificate file. Serve over **HTTPS** instead of HTTP. Must be paired with `--tls-key` (boot fails if only one is given). Unlocks secure-context browser APIs — voice input (`getUserMedia`), WebRTC — over a LAN IP, which browsers otherwise block on plain `http://`. TLS termination only; no auto-generation / ACME. See [HTTPS / TLS](#https--tls-for-mobile--cross-device-access) below.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
 | `--tls-key <path>`                      | —               | Path to a PEM private key file. Must be paired with `--tls-cert`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
-| `--max-sessions <n>`                    | `20`            | Cap on concurrent live sessions. New `POST /session` requests that would spawn a fresh child return `503` (with `Retry-After: 5`) when the cap is hit; attaches to existing sessions are NOT counted. Set to `0` to disable. Sized for single-user / small-team usage; raise it if your deployment has the RAM/FD headroom (~30–50 MB per session).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+| `--max-sessions <n>`                    | `32`            | Cap on concurrent live sessions. New `POST /session` requests that would spawn a fresh child return `503` (with `Retry-After: 5`) when the cap is hit; attaches to existing sessions are NOT counted. Set to `0` to disable. Sized for single-user / small-team usage; raise it if your deployment has the RAM/FD headroom (~30–50 MB per session).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
 | `--max-total-sessions <n>`              | derived         | Optional non-negative integer daemon-wide cap on fresh session creation across all registered workspace runtimes. It applies to new child sessions, session restore, and branch/fork-created sessions; attaching to an existing live session does not consume a slot. Set to `0` for unlimited. When omitted with several startup/restored workspaces, the daemon derives a fixed cap from the per-workspace limit and the startup workspace count; later dynamic registration does not recompute it.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
 | `--max-pending-prompts-per-session <n>` | `5`             | Per-session cap on prompts accepted by `POST /session/:id/prompt` but not yet settled, including queued prompts and the active prompt. The bridge rejects overflow synchronously with `503`, `Retry-After: 5`, and `code: "prompt_queue_full"` before returning a `promptId`. Set to `0` to disable. `branchSession` serializes on the same FIFO but does not count against this prompt cap.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
 | `--workspace <path>`                    | `process.cwd()` | Absolute workspace directory registered by this daemon. Repeat the flag to host multiple workspaces in one process; the first is primary and remains the default when a request omits `cwd`. Relative values are rejected. Session requests whose canonical `cwd` is not registered return `400 workspace_mismatch`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| `--memory-project-scope <mode>`         | `git-root`      | Project-memory partitioning mode. `git-root` (default) shares memory among workspaces resolved to the same Git root; `workspace` keys memory by the exact registered workspace directory so each daemon workspace gets its own isolated memory. Overrides `QWEN_CODE_MEMORY_PROJECT_SCOPE` when provided; an unrecognized env value is ignored with a one-time warning and falls back to `git-root`. Switching to `workspace` does not migrate existing git-root project memory — those entries stop being visible until you switch back.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
 | `--channel <name\|all>`                 | —               | Experimental daemon-managed channel worker. Repeat the flag to select multiple configured channels, or pass `all` to start every configured channel. `all` cannot be combined with named channels. Selected channel `cwd` values must resolve to a registered workspace; a multi-workspace daemon runs one worker per owning workspace. The worker is owned by `qwen serve`; stop the daemon to stop serve-managed channels.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
 | `--max-connections <n>`                 | `256`           | Listener-level TCP connection cap (`server.maxConnections`). Bounds raw socket count irrespective of session count — slow / phantom SSE clients get rejected at accept time once full. Raise alongside `--max-sessions` if your deployment expects many SSE subscribers per session.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
 | `--event-ring-size <n>`                 | `8000`          | Per-session SSE replay ring depth (#3803 §02 target). Sets the backlog available to `GET /session/:id/events` with `Last-Event-ID: N`. Larger = more reconnect headroom at the cost of a few hundred KB extra RAM per session. SDK clients can additionally request a larger per-subscriber backlog cap on a specific subscription via `?maxQueued=N` (range `[16, 2048]`, default 256). Daemons also emit a non-terminal `slow_client_warning` SSE frame at 75% queue fill so clients can drain / reconnect before getting evicted. Pre-flight `caps.features.slow_client_warning`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
@@ -404,6 +407,25 @@ Notes:
 | `--web` / `--no-web`                    | `true`          | Serve the built Web Shell SPA at the daemon root (`GET /`, `/assets/*`, and SPA deep-link fallback). The static shell is registered **before** the bearer-auth gate — a browser can't attach a token to a `<script>` subresource or an address-bar navigation, the shell carries no secrets, and every API route stays token-gated regardless. On non-loopback binds a one-line stderr warning notes the UI is reachable without auth. Use `--no-web` for an API-only daemon. No effect when the build omits the Web Shell assets (the daemon logs a breadcrumb and runs API-only).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
 | `--open`                                | `false`         | After the listener is up, open the Web Shell in your default browser at the daemon URL (with `#token=` appended as a URL fragment when a token is configured — a fragment is never sent to the server, keeping the token out of access logs and Referer headers). No-op with `--no-web`, or in headless / CI / SSH environments where no browser is available.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
 
+> **Memory project scope caveats.**
+>
+> - **Daemon vs. standalone CLI.** `--memory-project-scope` (and
+>   `QWEN_CODE_MEMORY_PROJECT_SCOPE`) only affects daemon-managed runtimes.
+>   A standalone `qwen` TUI started in the same directory still uses the
+>   git-root scope unless the environment variable is exported globally. To keep
+>   both entry points consistent, pin the scope in the workspace `.env` or
+>   `settings.env` so every process that reads the workspace agrees.
+> - **Directory-name collisions.** The storage key is derived by
+>   `sanitizeCwd`, which replaces every non-alphanumeric character with
+>   `-`. Sibling directories that differ only in punctuation (e.g.
+>   `feature_1` and `feature-1`) map to the same memory directory even
+>   under `workspace` scope. Avoid such naming when relying on workspace
+>   isolation.
+> - **Normalization differs between flag and env var.** The environment variable
+>   is trimmed and lowercased (`"  Workspace  "` works); the CLI flag is
+>   matched case-sensitively by yargs `choices` (`--memory-project-scope
+Workspace` is rejected). Use lowercase values when copying between the two.
+
 > **Sizing the load knobs.** `--max-sessions` is the per-workspace fresh-session cap. `--max-total-sessions`, when set, is the daemon-wide fresh-session cap.
 > Three other layers also limit load — when sizing for a high-concurrency
 > deployment, tune them together:

package/bundled/qc-helper/docs/reference/keyboard-shortcuts.md

@@ -10,7 +10,7 @@ This document lists the available keyboard shortcuts in Qwen Code.
 | `Ctrl+C`                       | Cancel the ongoing request and clear the input. Press twice to exit the application.                                                                                                                                                                                                                      |
 | `Ctrl+D`                       | Exit the application if the input is empty. Press twice to confirm.                                                                                                                                                                                                                                       |
 | `Ctrl+L`                       | Clear the screen.                                                                                                                                                                                                                                                                                         |
-| `Ctrl+O`                       | Open/close the full-detail transcript view (a scrollable, frozen snapshot showing every tool's complete output and full thinking). Press again, or `Esc`/`q`, to close.                                                                                                                                   |
+| `Ctrl+O`                       | Toggle expanded detail mode: expand or collapse all thinking blocks and tool outputs inline. Press again to collapse. When `ui.useTerminalBuffer` is off, toggling redraws the full conversation with untruncated output into terminal scrollback.                                                        |
 | `Ctrl+S`                       | Stashes non-empty input for the current project and restores it on the next launch. With empty input, allows long responses to print fully, disabling truncation. Use your terminal's scrollback to view the entire output.                                                                               |
 | `Ctrl+T`                       | Toggle the display of tool descriptions.                                                                                                                                                                                                                                                                  |
 | `Ctrl+B`                       | While a foreground shell command is running: promote it to a background task. The child keeps running, the agent's turn unblocks, and the shell appears in `/tasks` + the Background tasks dialog. No-op when no shell is executing — Ctrl+B then falls through to its prompt-area binding (cursor-left). |
@@ -45,7 +45,7 @@ This document lists the available keyboard shortcuts in Qwen Code.
 | `Ctrl+Y`                                              | Retry the last failed request.                                                                                                      |
 | `Ctrl+Right Arrow` / `Meta+Right Arrow` / `Meta+F`    | Move the cursor one word to the right.                                                                                              |
 | `Ctrl+U`                                              | Delete from the cursor to the beginning of the line.                                                                                |
-| `Ctrl+V` (Windows: `Alt+V`)                           | Paste clipboard content. If the clipboard contains an image, it will be saved and a reference to it will be inserted in the prompt. |
+| `Ctrl+V` / `Option+V` (Windows: `Alt+V`)              | Paste clipboard content. If the clipboard contains an image, it will be saved and a reference to it will be inserted in the prompt. |
 | `Ctrl+W` / `Meta+Backspace` / `Ctrl+Backspace`        | Delete the word to the left of the cursor.                                                                                          |
 | `Ctrl+X`                                              | Open the current input in an external editor.                                                                                       |
 

package/bundled/review/SKILL.md

@@ -444,7 +444,7 @@ An agent that finds nothing must say so **and say what it walked** — `No issue
 | `4`                                       | **Performance & efficiency.** N+1s, leaks, needless re-renders, bad data structures, bundle size. **Reproduces the PR's claimed numbers** rather than trusting them — confirms a cheap deterministic claim (bundle bytes, tree-shake) or flags an unreproducible/unsubstantiated benchmark as unverified.                                                                                                                                                                                                                                                                                                                |
 | `5`                                       | **Test coverage.** Specific untested paths in the diff, never "coverage is low"; a missing test is a Suggestion. **Mutation-tests the tests the diff adds/changes** — a test that stays green when the code under it is broken is vacuous — a Suggestion, Critical only when it asserts the opposite, was weakened in-diff, or lets a named incorrect behaviour ship (report the behaviour, not the gap).                                                                                                                                                                                                                |
 | `6a` `6b` `6c`                            | **Undirected audit, three personas** — attacker, 3 AM oncall, six-months-later maintainer. The framings force diverse paths; the union of what they find is the point, so all three run.                                                                                                                                                                                                                                                                                                                                                                                                                                 |
-| `7`                                       | **Build & test verification** (needs a local tree). Runs _one_ build and _one_ test command, and the **test-efficacy probe** — which reverts the diff's source, keeps its tests, and reports the ones that pass anyway. Its evidence is the commands it ran. `Source: [build]` / `[test]`, never `[review]`.                                                                                                                                                                                                                                                                                                             |
+| `7`                                       | **Build & test verification** (needs a local tree). Runs _one_ build and _one_ test command, and the **test-efficacy probe** — which reverts the diff's source, keeps its tests, and reports the ones that pass anyway, and deletes individual added safety statements (mutants) to find the ones no test notices. Its evidence is the commands it ran. `Source: [build]` / `[test]`, never `[review]`.                                                                                                                                                                                                                  |
 | `test-matrix`                             | **Test coverage matrix** (Step 3B). Maps each behavioural change to the test that exercises it — the pairing a territory agent cannot see, because it holds either the implementation or the test, rarely both.                                                                                                                                                                                                                                                                                                                                                                                                          |
 | `invariant-a` `invariant-b` `invariant-c` | **Whole-file invariants** on a `heavy` file, one checklist slice each: (a) mutable fields, timers, collections; (b) retry counters, ignored return values, error taxonomies; (c) config fields, early returns.                                                                                                                                                                                                                                                                                                                                                                                                           |
 

package/chunks/{MaxSizedBox-VI3ROJJA.js → MaxSizedBox-CDHTDITS.js}

@@ -4,71 +4,76 @@ import {
   MINIMUM_MAX_HEIGHT,
   MaxSizedBox,
   setMaxSizedBoxDebugging
-} from "./chunk-U3E3UQAA.js";
-import "./chunk-GKX7E4CO.js";
+} from "./chunk-LBWNSLJK.js";
+import "./chunk-U25CMJYY.js";
 import "./chunk-SV5PQVQE.js";
-import "./chunk-GATT5TKW.js";
-import "./chunk-UWMLWVCA.js";
+import "./chunk-2IIJTXYF.js";
+import "./chunk-KKN2IE7Q.js";
 import "./chunk-5QWWOFGG.js";
-import "./chunk-YDLJGZHL.js";
+import "./chunk-4NFY2S7N.js";
 import "./chunk-2MIN6GRR.js";
 import "./chunk-QHTIBUWB.js";
 import "./chunk-RKUWKYED.js";
-import "./chunk-X5WNMMIA.js";
+import "./chunk-NGWYUZZO.js";
+import "./chunk-GOFAQQZA.js";
+import "./chunk-5M6IDOMF.js";
 import "./chunk-TWPJO254.js";
 import "./chunk-H6XPXXMH.js";
-import "./chunk-5M6IDOMF.js";
-import "./chunk-UPUG4GXM.js";
-import "./chunk-64LQLPL7.js";
-import "./chunk-2LQTH543.js";
-import "./chunk-KRXPRVGL.js";
-import "./chunk-BMFALVGQ.js";
-import "./chunk-CVHIL5IG.js";
+import "./chunk-CWEIMFFW.js";
+import "./chunk-I7JDGNG6.js";
+import "./chunk-A6SX5TAH.js";
+import "./chunk-33FNCQSY.js";
+import "./chunk-6PVPNMXU.js";
+import "./chunk-PXA5AWHY.js";
 import "./chunk-IRH27ZC2.js";
 import "./chunk-QHWCP53L.js";
-import "./chunk-PONHVBRT.js";
+import "./chunk-MOHAWIAW.js";
+import "./chunk-MYT7N6QH.js";
+import "./chunk-O6GEWCJA.js";
 import "./chunk-T26EAKDL.js";
-import "./chunk-6PVPNMXU.js";
 import "./chunk-CPBF7KYF.js";
-import "./chunk-6QIGFD5W.js";
-import "./chunk-XWWKIXVD.js";
-import "./chunk-75GFAX4R.js";
-import "./chunk-OKF7JF3R.js";
-import "./chunk-JSD33JG6.js";
+import "./chunk-MISUEWB4.js";
+import "./chunk-KRXPRVGL.js";
+import "./chunk-A5YZ3FA2.js";
+import "./chunk-YAVY33G4.js";
+import "./chunk-2UISUFHQ.js";
+import "./chunk-6FMJLI5M.js";
+import "./chunk-PGEGUNH5.js";
 import "./chunk-S6LOFUVP.js";
-import "./chunk-JCW2R7WC.js";
-import "./chunk-2DN4J57Y.js";
+import "./chunk-K623ENWT.js";
+import "./chunk-AQ37AY7B.js";
+import "./chunk-432XCUHF.js";
 import "./chunk-ZPJWUGCS.js";
-import "./chunk-2LKVPASC.js";
+import "./chunk-XC656O42.js";
 import "./chunk-NAVJD2PQ.js";
-import "./chunk-LW3RFMG7.js";
-import "./chunk-W4MIWP6M.js";
+import "./chunk-QYPT3QUD.js";
+import "./chunk-QMBEW7EW.js";
 import "./chunk-DGEIYUC3.js";
 import "./chunk-MPHPFVKK.js";
 import "./chunk-GLNBDYUX.js";
 import "./chunk-DJ2GSRLV.js";
-import "./chunk-5KTQXHPY.js";
-import "./chunk-75MIQ3LV.js";
+import "./chunk-XCLLRKY5.js";
+import "./chunk-RPYYTL7E.js";
 import "./chunk-2J3OJGTL.js";
 import "./chunk-P3QQPMQA.js";
-import "./chunk-RPLGZJV2.js";
+import "./chunk-6O5DVH27.js";
 import "./chunk-GLCZKT5V.js";
-import "./chunk-DZLYR4U3.js";
-import "./chunk-PT722TDT.js";
+import "./chunk-2DNKEBXY.js";
+import "./chunk-M2F5PLOW.js";
 import "./chunk-VGC4I5JJ.js";
-import "./chunk-SGFT55XI.js";
-import "./chunk-Y4IHBGBP.js";
-import "./chunk-Y6AXW2OG.js";
-import "./chunk-VCPIZRYH.js";
+import "./chunk-E4WHKETF.js";
+import "./chunk-BV4QX43X.js";
+import "./chunk-I5GNT6ZS.js";
+import "./chunk-TFFMATHX.js";
 import "./chunk-46UV252V.js";
 import "./chunk-ZBVS26BY.js";
-import "./chunk-WZRWHXFE.js";
-import "./chunk-A3NDJ5SB.js";
-import "./chunk-7XATOOE7.js";
-import "./chunk-BGTQCTQW.js";
+import "./chunk-BFHXDAR7.js";
+import "./chunk-TYERNYH4.js";
+import "./chunk-UH7Z7Y45.js";
+import "./chunk-O2ZYHG33.js";
 import "./chunk-W4RQUHY3.js";
-import "./chunk-S7W2GKIO.js";
-import "./chunk-UHUSJ6X7.js";
+import "./chunk-G7XXKQYS.js";
+import "./chunk-3RXUYQJI.js";
 import "./chunk-VOQXFAY5.js";
 import "./chunk-75DOP5OR.js";
 import "./chunk-DMTGGOSA.js";

package/chunks/{StandaloneSessionPicker-LYXKD2EV.js → StandaloneSessionPicker-L63HUAHP.js}

@@ -4,112 +4,117 @@ import {
   ConfigContext,
   SessionPicker,
   SettingsContext
-} from "./chunk-OCESJA77.js";
-import "./chunk-TDL6LB4K.js";
+} from "./chunk-WISQLM4Q.js";
+import "./chunk-OBAIHYFT.js";
+import "./chunk-7IYLHTTM.js";
+import "./chunk-4WGODMVR.js";
+import "./chunk-LBWNSLJK.js";
+import "./chunk-KG22G46Y.js";
+import "./chunk-U25CMJYY.js";
 import {
   KeypressProvider
-} from "./chunk-CQL64ESB.js";
-import "./chunk-JX27F6QS.js";
-import "./chunk-7AEJDLRA.js";
-import "./chunk-M7OONWYU.js";
-import "./chunk-4WGODMVR.js";
-import "./chunk-KW7NOTN6.js";
-import "./chunk-U3E3UQAA.js";
-import "./chunk-GKX7E4CO.js";
+} from "./chunk-H4DSRWAS.js";
+import "./chunk-3LGZEYOF.js";
 import {
   require_jsx_runtime
 } from "./chunk-SV5PQVQE.js";
-import "./chunk-GATT5TKW.js";
 import {
   Box_default,
   render_default,
   use_app_default
-} from "./chunk-UWMLWVCA.js";
+} from "./chunk-2IIJTXYF.js";
+import "./chunk-42IKVPST.js";
+import "./chunk-KKN2IE7Q.js";
+import "./chunk-KW7NOTN6.js";
 import {
   require_react
 } from "./chunk-5QWWOFGG.js";
-import "./chunk-A2D5BAVP.js";
-import "./chunk-XFZYFU3I.js";
-import "./chunk-YDLJGZHL.js";
+import "./chunk-4NFY2S7N.js";
+import "./chunk-UHQ3L6GC.js";
 import "./chunk-2MIN6GRR.js";
 import "./chunk-QHTIBUWB.js";
 import "./chunk-QTERJVPZ.js";
-import "./chunk-WUZ7H6DP.js";
-import "./chunk-E5Z2AVNV.js";
+import "./chunk-K5Q62CGR.js";
+import "./chunk-3SH53ANB.js";
 import "./chunk-57OAHC2Y.js";
-import "./chunk-EIF3FXTB.js";
+import "./chunk-LAPK3GLC.js";
 import "./chunk-RKUWKYED.js";
-import "./chunk-TCIFAA7K.js";
-import "./chunk-2N7CODY5.js";
 import "./chunk-GOXKNSDZ.js";
 import "./chunk-IDS7MSUP.js";
+import "./chunk-CHCLO3M7.js";
+import "./chunk-AQEWCKX4.js";
 import "./chunk-6PEXNQTX.js";
-import "./chunk-Q43KPN7X.js";
+import "./chunk-434YCHSV.js";
 import "./chunk-ALGGS7UH.js";
 import "./chunk-MR3PXB6E.js";
-import {
-  writeStdoutLine
-} from "./chunk-OWAK7LMW.js";
 import {
   SessionService,
   getGitBranch
-} from "./chunk-X5WNMMIA.js";
+} from "./chunk-NGWYUZZO.js";
+import "./chunk-GOFAQQZA.js";
+import "./chunk-5M6IDOMF.js";
 import "./chunk-TWPJO254.js";
 import "./chunk-H6XPXXMH.js";
-import "./chunk-5M6IDOMF.js";
-import "./chunk-UPUG4GXM.js";
-import "./chunk-64LQLPL7.js";
-import "./chunk-2LQTH543.js";
-import "./chunk-KRXPRVGL.js";
-import "./chunk-BMFALVGQ.js";
-import "./chunk-CVHIL5IG.js";
+import "./chunk-CWEIMFFW.js";
+import "./chunk-I7JDGNG6.js";
+import "./chunk-A6SX5TAH.js";
+import "./chunk-33FNCQSY.js";
+import "./chunk-6PVPNMXU.js";
+import "./chunk-PXA5AWHY.js";
 import "./chunk-IRH27ZC2.js";
 import "./chunk-QHWCP53L.js";
-import "./chunk-PONHVBRT.js";
+import "./chunk-MOHAWIAW.js";
+import "./chunk-MYT7N6QH.js";
+import "./chunk-O6GEWCJA.js";
 import "./chunk-T26EAKDL.js";
-import "./chunk-6PVPNMXU.js";
 import "./chunk-CPBF7KYF.js";
-import "./chunk-6QIGFD5W.js";
-import "./chunk-XWWKIXVD.js";
-import "./chunk-75GFAX4R.js";
-import "./chunk-OKF7JF3R.js";
-import "./chunk-JSD33JG6.js";
+import "./chunk-MISUEWB4.js";
+import "./chunk-KRXPRVGL.js";
+import "./chunk-A5YZ3FA2.js";
+import "./chunk-YAVY33G4.js";
+import "./chunk-2UISUFHQ.js";
+import "./chunk-6FMJLI5M.js";
+import "./chunk-PGEGUNH5.js";
 import "./chunk-S6LOFUVP.js";
-import "./chunk-JCW2R7WC.js";
-import "./chunk-2DN4J57Y.js";
+import "./chunk-K623ENWT.js";
+import "./chunk-AQ37AY7B.js";
+import "./chunk-432XCUHF.js";
 import "./chunk-ZPJWUGCS.js";
-import "./chunk-2LKVPASC.js";
+import "./chunk-XC656O42.js";
 import "./chunk-NAVJD2PQ.js";
-import "./chunk-LW3RFMG7.js";
-import "./chunk-W4MIWP6M.js";
+import "./chunk-QYPT3QUD.js";
+import "./chunk-QMBEW7EW.js";
 import "./chunk-DGEIYUC3.js";
 import "./chunk-MPHPFVKK.js";
 import "./chunk-GLNBDYUX.js";
 import "./chunk-DJ2GSRLV.js";
-import "./chunk-5KTQXHPY.js";
-import "./chunk-75MIQ3LV.js";
+import "./chunk-XCLLRKY5.js";
+import "./chunk-RPYYTL7E.js";
 import "./chunk-2J3OJGTL.js";
 import "./chunk-P3QQPMQA.js";
-import "./chunk-RPLGZJV2.js";
+import "./chunk-6O5DVH27.js";
 import "./chunk-GLCZKT5V.js";
-import "./chunk-DZLYR4U3.js";
-import "./chunk-PT722TDT.js";
+import "./chunk-2DNKEBXY.js";
+import "./chunk-M2F5PLOW.js";
 import "./chunk-VGC4I5JJ.js";
-import "./chunk-SGFT55XI.js";
-import "./chunk-Y4IHBGBP.js";
-import "./chunk-Y6AXW2OG.js";
-import "./chunk-VCPIZRYH.js";
+import "./chunk-E4WHKETF.js";
+import "./chunk-BV4QX43X.js";
+import "./chunk-I5GNT6ZS.js";
+import "./chunk-TFFMATHX.js";
 import "./chunk-46UV252V.js";
 import "./chunk-ZBVS26BY.js";
-import "./chunk-WZRWHXFE.js";
-import "./chunk-A3NDJ5SB.js";
-import "./chunk-7XATOOE7.js";
-import "./chunk-BGTQCTQW.js";
+import "./chunk-BFHXDAR7.js";
+import "./chunk-TYERNYH4.js";
+import "./chunk-UH7Z7Y45.js";
+import "./chunk-O2ZYHG33.js";
 import "./chunk-W4RQUHY3.js";
-import "./chunk-S7W2GKIO.js";
-import "./chunk-UHUSJ6X7.js";
+import "./chunk-G7XXKQYS.js";
+import "./chunk-3RXUYQJI.js";
 import "./chunk-VOQXFAY5.js";
-import "./chunk-52ZSWYEG.js";
+import "./chunk-SK2UKB45.js";
+import {
+  writeStdoutLine
+} from "./chunk-OWAK7LMW.js";
 import "./chunk-75DOP5OR.js";
 import "./chunk-DMTGGOSA.js";
 import "./chunk-YQ3U5MUC.js";

package/chunks/{acp-startup-profiler-DFVPFQ6C.js → acp-startup-profiler-3RICG2YW.js}

@@ -9,8 +9,8 @@ import {
   markAcpStartup,
   recordAcpConfigStartupEvent,
   resetAcpStartupProfilerForTesting
-} from "./chunk-3L2SPEBH.js";
-import "./chunk-XZC5VLBZ.js";
+} from "./chunk-M744OFVE.js";
+import "./chunk-UKZEXS6K.js";
 import "./chunk-5O2XNYP6.js";
 import "./chunk-J2S4EL5Y.js";
 export {