@qwen-code/qwen-code 0.23.2 → 0.23.3-nightly.20260911.aaa6a32aae

package/README.md

@@ -7,7 +7,7 @@
 
 <a href="https://trendshift.io/repositories/15287" target="_blank"><img src="https://trendshift.io/api/badge/repositories/15287" alt="QwenLM%2Fqwen-code | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 
-**The open-source AI coding agent that lives in your terminal.**
+**The open-source AI coding agent for your terminal, editor, desktop, browser, and chat.**
 
 <a href="https://qwenlm.github.io/qwen-code-docs/zh/users/overview">中文</a> |
 <a href="https://qwenlm.github.io/qwen-code-docs/de/users/overview">Deutsch</a> |
@@ -19,12 +19,14 @@
 
 </div>
 
+![Qwen Code in the terminal, desktop app, browser, editor, and chat, with VS Code, Zed, JetBrains, Telegram, DingTalk, WeChat, and Feishu integrations](https://img.alicdn.com/imgextra/i3/O1CN01l5GyhGuOPGC3XHtt_!!6000000005884-2-tps-1742-903.png)
+
 ## Why Qwen Code?
 
 - **Agentic out of the box** — Auto-Memory, Auto-Skills, SubAgents, Agent Teams, and MCP. Dynamic workflows, zero setup.
 - **Open-source, inside and out** — The framework and the Qwen models are open-source. They evolve together. No vendor lock-in.
 - **Multi-protocol** — Supports OpenAI, Anthropic, Gemini, and Qwen APIs. Any third-party provider or local model (Ollama / vLLM). Switch at runtime.
-- **Beyond the terminal** — IDE plugins, Desktop app, daemon mode, SDKs, and IM bots (Telegram / DingTalk / WeChat / Feishu).
+- **Beyond the terminal** — IDE plugins, Desktop app, Web UI, SDKs, and chat integrations (Telegram / DingTalk / WeChat / Feishu).
 
 > [!TIP]
 > Qwen Code is actively iterating on itself — using its own agent and models to file issues, submit PRs, review code, and run tests. Powered by the community, driven by AI.
@@ -64,27 +66,45 @@ brew install qwen-code
 
 ## Quick Start
 
+Open a terminal in your project and start Qwen Code:
+
 ```bash
-qwen          # Launch interactive terminal UI
-# Inside the session:
-/auth         # Configure your provider and API key
+cd /path/to/your-project
+qwen
+```
+
+Inside the session, run `/auth` to configure your provider and API key. Then try:
+
+```text
+Explain this repository and show me where to start.
 ```
 
 See the [Authentication Guide](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/) and [Settings Reference](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/settings/) for detailed setup.
 
-![Qwen Code](https://img.alicdn.com/imgextra/i2/O1CN01K0nwj41RM1Il8kB0t_!!6000000002096-2-tps-1544-1060.png)
+<details>
+<summary>See the terminal interface</summary>
+
+![Qwen Code terminal interface](https://img.alicdn.com/imgextra/i2/O1CN01K0nwj41RM1Il8kB0t_!!6000000002096-2-tps-1544-1060.png)
+
+</details>
 
 ## How to Use Qwen Code
 
-| Mode            | Command         | Use Case                                                                                                                                                                                                                                        |
-| --------------- | --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Interactive** | `qwen`          | Terminal UI with rich rendering, `@file` references, slash commands                                                                                                                                                                             |
-| **Headless**    | `qwen -p "..."` | Scripts, CI/CD, batch processing — no UI                                                                                                                                                                                                        |
-| **IDE**         | —               | [VS Code](https://qwenlm.github.io/qwen-code-docs/en/users/integration-vscode/), [Zed](https://qwenlm.github.io/qwen-code-docs/en/users/integration-zed/), [JetBrains](https://qwenlm.github.io/qwen-code-docs/en/users/integration-jetbrains/) |
-| **Desktop**     | —               | [Qwen Code Desktop](https://github.com/QwenLM/qwen-code/releases/tag/desktop-latest) — GUI for macOS, Windows, Linux                                                                                                                            |
-| **Daemon**      | `qwen serve`    | Shared agent session over HTTP+SSE (ACP). Multiple clients, one agent. _(experimental)_ [Docs](https://qwenlm.github.io/qwen-code-docs/en/users/qwen-serve)                                                                                     |
-| **SDK**         | —               | [TypeScript](./packages/sdk-typescript/README.md), [Python](./packages/sdk-python/README.md), [Java](./packages/sdk-java/qwencode/README.md)                                                                                                    |
-| **IM Bot**      | `qwen channel`  | Connect to Telegram, DingTalk, WeChat, or Feishu                                                                                                                                                                                                |
+Choose the interface that fits your workflow:
+
+| Interface    | Get started                                                                                                                                                                                                                                                                                                                                                                                               |
+| ------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Terminal** | Run `qwen` in your project — see [Quick Start](#quick-start).                                                                                                                                                                                                                                                                                                                                             |
+| **Desktop**  | [Download Qwen Code Desktop](https://github.com/QwenLM/qwen-code/releases/tag/desktop-latest) for macOS, Windows, and Linux.                                                                                                                                                                                                                                                                              |
+| **Web**      | Run `qwen serve --open` to open the [Web UI](https://qwenlm.github.io/qwen-code-docs/en/users/qwen-serve/) in your browser. _(experimental)_                                                                                                                                                                                                                                                              |
+| **Editor**   | Set up [VS Code](https://qwenlm.github.io/qwen-code-docs/en/users/integration-vscode/), [Zed](https://qwenlm.github.io/qwen-code-docs/en/users/integration-zed/), or [JetBrains](https://qwenlm.github.io/qwen-code-docs/en/users/integration-jetbrains/).                                                                                                                                                |
+| **Chat**     | Connect [Telegram](https://qwenlm.github.io/qwen-code-docs/en/users/features/channels/telegram/), [DingTalk](https://qwenlm.github.io/qwen-code-docs/en/users/features/channels/dingtalk/), [WeChat](https://qwenlm.github.io/qwen-code-docs/en/users/features/channels/weixin/), or [Feishu](https://qwenlm.github.io/qwen-code-docs/en/users/features/channels/feishu/), then run `qwen channel start`. |
+
+For automation and custom integrations:
+
+- **Headless** — Run `qwen -p "..."` in scripts, CI/CD, or batch jobs.
+- **SDKs** — Build with [TypeScript](./packages/sdk-typescript/README.md), [Python](./packages/sdk-python/README.md), or [Java](./packages/sdk-java/qwencode/README.md).
+- **Daemon** — Run `qwen serve` to connect clients over HTTP + SSE (ACP). _(experimental)_ [Daemon guide](https://qwenlm.github.io/qwen-code-docs/en/users/qwen-serve/).
 
 <details>
 <summary>SDK example (Python)</summary>

package/bundled/computer-use/SKILL.md

@@ -17,7 +17,7 @@ If `node_repl` is unavailable, run:
 
 ```bash
 qwen mcp add --scope user node-repl npx -y @qwen-code/node-repl-mcp@0.1.3
-npm install --no-save --package-lock=false @qwen-code/cua-sdk@0.20.4
+npm install --no-save --package-lock=false @qwen-code/cua-sdk@0.20.5
 ```
 
 Tell the user to restart Qwen Code, then stop. If only the SDK import is missing,

package/bundled/goal-draft/SKILL.md

@@ -66,7 +66,7 @@ Use exactly these labels, in this order. Keep the whole objective on one line wh
 Outcome: <one sentence: what is true when done>
 Done when: 1) <command> exits 0 and its output shows <…> (paste that line); 2) <file/state assertion provable via read or grep>; 3) …
 Must not: <files not to touch; tests/thresholds not to weaken; irreversible actions not to take>
-Budget: <user's stopping agreement; otherwise stop as blocked after 20 turns, and mark that default [ASSUMPTION] in Context>
+Budget: <user's advisory stopping agreement; otherwise stop as blocked after 20 turns, and mark that default [ASSUMPTION] in Context>
 On block: propose blocked with the exact blocker and the decision a human must make; never claim completion without evidence for every Done-when item
 Context: <only facts the agent cannot derive: paths, branch, environment, earlier decisions>
 ```
@@ -80,18 +80,18 @@ Rules of thumb:
 - Prefer "the smallest safe change in `<scope>`" over open-ended refactors.
 - Put anything that must not change on the way into Must not — this is what stops the loop from deleting a failing test to "pass".
 - Keep it short: everything the agent can derive from the workspace stays out. Aim for under ~1200 characters.
-- `Budget` is a stopping agreement for the model, not a runtime-enforced turn or wall-clock limit. Do not claim that writing it configures a timer or changes the Goal token budget. Preserve a user-specified budget; otherwise mark the default `[ASSUMPTION]` in Context.
+- `Budget` is a stopping agreement for the model, not a runtime-enforced turn or wall-clock limit. Do not claim that writing it configures a timer or changes the Goal token budget. When the user needs an enforced ceiling, tell them to set `model.goalMaxTurns` or `model.goalMaxActiveMinutes` in their settings -- never write the setting into the objective, which the Goal's own model cannot act on -- and say that either takes effect after a restart and only for Goals created afterwards -- neither bounds a Goal that is already running. Preserve a user-specified budget; otherwise mark the default `[ASSUMPTION]` in Context.
 
 For example, an audit's Done-when checks can require a report covering the agreed scenarios, observed results and evidence for each scenario, and reproduction steps for each confirmed defect (or an explicit "no confirmed defects" result). Ground the scenarios and report destination before offering the objective for use.
 
 ### Weak → strong
 
-| Weak                          | Strong                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
-| ----------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| make checkout faster          | Outcome: checkout API p95 is below 250 ms on the documented slow path. Done when: 1) `npm run bench:checkout` exits 0 and prints a p95 below 250 (paste the line); 2) `npm test` exits 0. Must not: change the benchmark, skip tests, touch files outside `src/checkout`. Budget: stop as blocked after 20 turns. On block: report the measured p95 and what blocks it. Context: [ASSUMPTION] the 20-turn budget is the drafter's default, not the user's. |
-| keep handling the PR comments | Outcome: every unresolved review thread on PR #123 is fixed or answered. Done when: 1) the review-threads query shows zero unresolved threads (paste the count); 2) CI on the head commit is green (paste the check summary). Must not: force-push, resolve a thread without replying to it. Budget: stop as blocked after 30 turns. On block: list the threads that need a maintainer decision.                                                           |
-| clean up the auth module      | Not a goal — "clean" has no check. Ask what would be observable (zero lint warnings in `src/auth`? a file count? a coverage threshold?) or offer a refactor plan instead.                                                                                                                                                                                                                                                                                  |
-| get the release out           | Not a goal as written — publishing is irreversible. Either narrow it to a checkable pre-release state (tag exists, changelog entry present, `npm run release:dry-run` exits 0) and put "do not publish" in Must not, or leave publishing to a human.                                                                                                                                                                                                       |
+| Weak                          | Strong                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| ----------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| make checkout faster          | Outcome: checkout API p95 is below 250 ms on the documented slow path. Done when: 1) `npm run bench:checkout` exits 0 and prints a p95 below 250 (paste the line); 2) `npm test` exits 0. Must not: change the benchmark, skip tests, touch files outside `src/checkout`. Budget: as model guidance, stop as blocked after 20 turns. On block: report the measured p95 and what blocks it. Context: [ASSUMPTION] the 20-turn budget is the drafter's default, not the user's. |
+| keep handling the PR comments | Outcome: every unresolved review thread on PR #123 is fixed or answered. Done when: 1) the review-threads query shows zero unresolved threads (paste the count); 2) CI on the head commit is green (paste the check summary). Must not: force-push, resolve a thread without replying to it. Budget: as model guidance, stop as blocked after 30 turns. On block: list the threads that need a maintainer decision.                                                           |
+| clean up the auth module      | Not a goal — "clean" has no check. Ask what would be observable (zero lint warnings in `src/auth`? a file count? a coverage threshold?) or offer a refactor plan instead.                                                                                                                                                                                                                                                                                                     |
+| get the release out           | Not a goal as written — publishing is irreversible. Either narrow it to a checkable pre-release state (tag exists, changelog entry present, `npm run release:dry-run` exits 0) and put "do not publish" in Must not, or leave publishing to a human.                                                                                                                                                                                                                          |
 
 ## Step 5 — self-check, then hand off
 
@@ -114,10 +114,10 @@ Then hand off, and nothing else:
 
 **If the `propose_goal` tool is available and no Goal is active**, call it with the objective on one line. The user approves or declines it in a dialog; only their approval sets the Goal. If they decline you will not be told why: stop, do not ask about it, and do not propose the same or a reworded objective again. After approval, acknowledge it in one sentence and end the turn — the Goal runtime starts the first Goal turn on its own.
 
-**Otherwise** (Web Shell or another ACP client, headless, the tool is disabled, or a Goal is active), print:
+**Otherwise** (a client without Goal proposal support, headless, the tool is disabled, or a Goal is active), print:
 
 1. The objective in a fenced code block.
 2. One line the user can run as-is: `/goal set <objective on one line>` (or `/goal edit …` when tightening the active goal). Print it as plain text with no code markers, so it can be copied verbatim.
-3. One sentence explaining that the draft has not been applied and the user must run the command to apply it; include any `[ASSUMPTION]` items. Do not promise a dialog in Web Shell or other ACP sessions.
+3. One sentence explaining that the draft has not been applied and the user must run the command to apply it; include any `[ASSUMPTION]` items. Do not promise a dialog when the tool is unavailable.
 
 Do not run /goal yourself. Do not begin the task. Stop and wait for the user.

package/bundled/qc-helper/docs/configuration/model-providers.md

@@ -4,7 +4,7 @@ Qwen Code allows you to configure multiple model providers through the `modelPro
 
 ## Overview
 
-Use `modelProviders` to declare models per provider id that the `/model` picker can switch between. Each key is a provider id and its value is **an array of model definitions** (`ModelConfig[]`). For built-in providers the key must be a valid auth type (`openai`, `anthropic`, `gemini`, `vertex-ai`); a custom provider id (e.g. `idealab`) is allowed as long as you map it to a protocol via the top-level [`providerProtocol`](#custom-provider-ids-providerprotocol) setting. Each model entry requires an `id`; `envKey` is **optional and recommended** (when omitted, it falls back to the auth type's default env key, e.g. `OPENAI_API_KEY` for `openai`), with optional `name`, `description`, `baseUrl`, and `generationConfig`. Credentials are never persisted in settings; the runtime reads them from `process.env[envKey]`. Qwen OAuth models remain hard-coded and cannot be overridden.
+Use `modelProviders` to declare models per provider id that the `/model` picker can switch between. Each key is a provider id and its value is **an array of model definitions** (`ModelConfig[]`). For built-in providers the key must be a valid auth type (`openai`, `openai-responses`, `anthropic`, `gemini`, `vertex-ai`); a custom provider id (e.g. `idealab`) is allowed as long as you map it to a protocol via the top-level [`providerProtocol`](#custom-provider-ids-providerprotocol) setting. Each model entry requires an `id`; `envKey` is **optional and recommended** (when omitted, it falls back to the auth type's default env key, e.g. `OPENAI_API_KEY` for `openai`), with optional `name`, `description`, `baseUrl`, and `generationConfig`. Credentials are never persisted in settings; the runtime reads them from `process.env[envKey]`. Qwen OAuth models remain hard-coded and cannot be overridden.
 
 > [!note]
 >
@@ -77,13 +77,14 @@ Below are comprehensive configuration examples for different authentication type
 
 The `modelProviders` object keys must be valid `authType` values. Currently supported auth types are:
 
-| Auth Type    | Description                                                                                                                                     |
-| ------------ | ----------------------------------------------------------------------------------------------------------------------------------------------- |
-| `openai`     | OpenAI-compatible APIs (OpenAI, Azure OpenAI, local inference servers like vLLM/Ollama)                                                         |
-| `anthropic`  | Anthropic Claude API                                                                                                                            |
-| `gemini`     | Google Gemini API                                                                                                                               |
-| `qwen-oauth` | Qwen OAuth (hard-coded, cannot be overridden in `modelProviders`)                                                                               |
-| `vertex-ai`  | Google Vertex AI (uses the `gemini` protocol and the `@google/genai` SDK in Vertex AI mode; selecting it sets `GOOGLE_GENAI_USE_VERTEXAI=true`) |
+| Auth Type          | Description                                                                                                                                     |
+| ------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------- |
+| `openai`           | OpenAI-compatible APIs (OpenAI, Azure OpenAI, local inference servers like vLLM/Ollama)                                                         |
+| `openai-responses` | OpenAI's `/v1/responses` API (native reasoning replay via `reasoning.encrypted_content`, not the Chat Completions format used by `openai`)      |
+| `anthropic`        | Anthropic Claude API                                                                                                                            |
+| `gemini`           | Google Gemini API                                                                                                                               |
+| `qwen-oauth`       | Qwen OAuth (hard-coded, cannot be overridden in `modelProviders`)                                                                               |
+| `vertex-ai`        | Google Vertex AI (uses the `gemini` protocol and the `@google/genai` SDK in Vertex AI mode; selecting it sets `GOOGLE_GENAI_USE_VERTEXAI=true`) |
 
 > [!note]
 > Vertex AI entries can authenticate with **Application Default Credentials**. Set `GOOGLE_CLOUD_PROJECT` (and optionally `GOOGLE_CLOUD_LOCATION`, which defaults to `global`) and leave `envKey` unset, along with every other key source the resolver reads: `GOOGLE_API_KEY`, `settings.security.auth.apiKey`, and the CLI key flags. Any API key value that reaches a Vertex entry switches the Google SDK to Vertex Express mode, which ignores the project, the location and your ADC credentials. An entry that declares an `envKey` is never routed to ADC, so a key that fails to be injected keeps failing on that variable instead of silently authenticating as a different principal.
@@ -93,7 +94,7 @@ The `modelProviders` object keys must be valid `authType` values. Currently supp
 
 ### Custom provider ids (`providerProtocol`)
 
-Built-in provider ids (`openai`, `gemini`, `anthropic`, `vertex-ai`, `qwen-oauth`) are routed to their SDK protocol automatically. To use a **custom** provider id — for example to group several OpenAI-compatible endpoints under a friendlier name — declare it under `modelProviders` and map it to a built-in protocol with the top-level `providerProtocol` setting:
+Built-in provider ids (`openai`, `openai-responses`, `gemini`, `anthropic`, `vertex-ai`, `qwen-oauth`) are routed to their SDK protocol automatically. To use a **custom** provider id — for example to group several OpenAI-compatible endpoints under a friendlier name — declare it under `modelProviders` and map it to a built-in protocol with the top-level `providerProtocol` setting:
 
 ```json
 {
@@ -114,18 +115,19 @@ Built-in provider ids (`openai`, `gemini`, `anthropic`, `vertex-ai`, `qwen-oauth
 
 Without a matching `providerProtocol` entry, a custom provider id is skipped (see the warning above).
 
-### SDKs Used for API Requests
+### Transports Used for API Requests
 
-Qwen Code uses the following official SDKs to send requests to each provider:
+Qwen Code sends requests to each provider through an official SDK, except for `openai-responses`, which talks to the endpoint over direct HTTP/SSE:
 
-| Auth Type    | SDK Package                                                                                     |
-| ------------ | ----------------------------------------------------------------------------------------------- |
-| `openai`     | [`openai`](https://www.npmjs.com/package/openai) - Official OpenAI Node.js SDK                  |
-| `anthropic`  | [`@anthropic-ai/sdk`](https://www.npmjs.com/package/@anthropic-ai/sdk) - Official Anthropic SDK |
-| `gemini`     | [`@google/genai`](https://www.npmjs.com/package/@google/genai) - Official Google GenAI SDK      |
-| `qwen-oauth` | [`openai`](https://www.npmjs.com/package/openai) with custom provider (DashScope-compatible)    |
+| Auth Type          | Transport                                                                                                          |
+| ------------------ | ------------------------------------------------------------------------------------------------------------------ |
+| `openai`           | [`openai`](https://www.npmjs.com/package/openai) - Official OpenAI Node.js SDK                                     |
+| `openai-responses` | Direct HTTP/SSE calls to `/v1/responses` (no SDK); embeddings use [`openai`](https://www.npmjs.com/package/openai) |
+| `anthropic`        | [`@anthropic-ai/sdk`](https://www.npmjs.com/package/@anthropic-ai/sdk) - Official Anthropic SDK                    |
+| `gemini`           | [`@google/genai`](https://www.npmjs.com/package/@google/genai) - Official Google GenAI SDK                         |
+| `qwen-oauth`       | [`openai`](https://www.npmjs.com/package/openai) with custom provider (DashScope-compatible)                       |
 
-This means the `baseUrl` you configure should be compatible with the corresponding SDK's expected API format. For example, when using `openai` auth type, the endpoint must accept OpenAI API format requests.
+This means the `baseUrl` you configure should be compatible with the corresponding transport's expected API format. For example, when using `openai` auth type, the endpoint must accept OpenAI API format requests.
 
 ### OpenAI-compatible providers (`openai`)
 
@@ -215,6 +217,41 @@ This auth type supports not only OpenAI's official API but also any OpenAI-compa
 }
 ```
 
+### OpenAI Responses API (`openai-responses`)
+
+This auth type targets OpenAI's `/v1/responses` endpoint rather than Chat Completions. When the endpoint returns encrypted reasoning with visible thought text, it replays prior-turn reasoning across turns and `--resume` via `reasoning.encrypted_content`. Compatible endpoints that stream `response.reasoning_text.delta` also display their reasoning, but endpoints without `encrypted_content` cannot replay the opaque reasoning state. Use `reasoning.effort` (not `extra_body.enable_thinking`, which the Chat Completions wires use) to control reasoning intensity.
+
+```json
+{
+  "env": {
+    "OPENAI_API_KEY": "sk-your-actual-openai-key-here"
+  },
+  "modelProviders": {
+    "openai-responses": [
+      {
+        "id": "gpt-5.1",
+        "name": "GPT-5.1 (Responses API)",
+        "envKey": "OPENAI_API_KEY",
+        "baseUrl": "https://api.openai.com/v1",
+        "generationConfig": {
+          "timeout": 60000,
+          "reasoning": {
+            "effort": "high"
+          },
+          "samplingParams": {
+            "temperature": 0.7,
+            "max_tokens": 4096
+          }
+        }
+      }
+    ]
+  }
+}
+```
+
+> [!note]
+> `extra_body` on this wire is fill-only: a key is written to the request body only when the generated request has no value for it, so it cannot override a field the pipeline already set (`model`, `input`, `reasoning`, `temperature`, `max_output_tokens`, ...). The legacy `enable_thinking` key is the one exception to even that — it is removed rather than forwarded (it isn't a Responses API field), and translated into `reasoning.effort: "medium"` when no explicit `reasoning` is set. Set `reasoning.effort` directly instead of `extra_body.enable_thinking` for this provider.
+
 ### Anthropic (`anthropic`)
 
 ```json
@@ -385,7 +422,7 @@ export VLLM_API_KEY="not-needed"
 
 > [!note]
 >
-> The `extra_body` parameter is **only supported for OpenAI-compatible providers** (`openai`, `qwen-oauth`). It is ignored for Anthropic, and Gemini providers.
+> The `extra_body` parameter is **only supported for OpenAI-compatible providers** (`openai`, `openai-responses`, `qwen-oauth`). It is ignored for Anthropic, and Gemini providers. On `openai-responses` the `enable_thinking` key is translated rather than forwarded — see the [OpenAI Responses API](#openai-responses-api-openai-responses) note.
 
 > [!note]
 >
@@ -693,15 +730,16 @@ The optional `reasoning` field under `generationConfig` controls how aggressivel
 
 ### Per-provider behavior
 
-| Protocol / provider                           | Wire shape                                                                           | Notes                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
-| --------------------------------------------- | ------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **OpenAI / DashScope** (`qwen3.8-max` family) | Flat `reasoning_effort: <effort>` body parameter                                     | The `/effort` tiers are passed through for any model id starting with `qwen3.8-max` (including dated snapshots and `-latest` aliases); DashScope applies any model-specific mapping. This family's ladder stops at `xhigh`, so a configured `max` is clamped to `xhigh` (logged once) rather than sent and rejected. An explicit `reasoning_effort` in `samplingParams` or `extra_body` is a verbatim override and is not clamped. When `reasoning_effort` and `thinking_budget` conflict, the normal `extra_body` > `samplingParams` > `reasoning` precedence keeps only the higher-priority field; an explicit same-layer pair keeps `reasoning_effort`, matching the provider's behavior before cross-layer resolution. If a static field wins, `/effort` reports that field instead of implying the requested tier is effective. When an effort tier wins, a conflicting `enable_thinking` is also dropped. An explicit `enable_thinking: false` in `extra_body` is honoured rather than dropped: it overrides the configured tier as `reasoning_effort: 'none'`, one of the few places `extra_body` does not win verbatim. Other Qwen models continue to map a selected effort to `enable_thinking: true`; a `reasoning_effort` override passes through there unless it conflicts with a `thinking_budget` (a pair DashScope rejects), in which case the inert `reasoning_effort` is dropped and both `enable_thinking` and `thinking_budget` survive. |
-| **OpenAI / DeepSeek** (`api.deepseek.com`)    | Flat `reasoning_effort: <effort>` body parameter                                     | When `reasoning.effort` is set in the nested config shape, it's rewritten to flat `reasoning_effort` and `'low'`/`'medium'` are normalized to `'high'`, `'xhigh'` to `'max'` — mirroring DeepSeek's [server-side back-compat](https://api-docs.deepseek.com/zh-cn/api/create-chat-completion). Top-level `samplingParams.reasoning_effort` or `extra_body.reasoning_effort` overrides skip this normalization and ship verbatim. `max` is accepted only on a real DeepSeek hostname; a `deepseek`-named model on another host keeps the generic `xhigh` ceiling, matching the hostname gate on the reshape itself.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
-| **OpenAI / Z.ai** (`z.ai`, `bigmodel.cn`)     | Flat `reasoning_effort: <effort>` body parameter                                     | GLM-5.2+ on a Z.ai host takes the full ladder, `max` included, and the nested `reasoning.effort` is rewritten to the flat field. Older GLM ids, and a `glm-*` model reached on any other host, keep the generic `xhigh` ceiling: the model name alone says nothing about what that endpoint accepts.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
-| **OpenAI** (other compatible servers)         | Known GPT-5 / GPT-6 Astra: flat `reasoning_effort`; other models: nested `reasoning` | GPT effort is clamped in both directions to the supported subset for the known model. GPT-5.6 and GPT-6 Astra allow `max`, while earlier models have lower ceilings. Tiers below the model floor are raised: GPT-5 Pro accepts only `high`; GPT-5.2 Pro, GPT-5.4 Pro and GPT-5.5 Pro raise `low` to `medium`. OpenRouter retains nested `reasoning`. Unknown model names keep the generic `xhigh` ceiling and nested shape. Explicit reasoning values in `samplingParams` / `extra_body` bypass the configured-tier clamp.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
-| **Anthropic** (real `api.anthropic.com`)      | `output_config: { effort }` plus the `effort-2025-11-24` beta header                 | Real Anthropic accepts `'low'`/`'medium'`/`'high'` only. `'max'` is **clamped to `'high'`** with a `debugLogger.warn` line (once per generator); if you want max effort, switch the baseURL to a DeepSeek-compatible endpoint that supports it.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
-| **Anthropic** (`api.deepseek.com/anthropic`)  | Same `output_config: { effort }` + beta header                                       | `'max'` is passed through unchanged.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
-| **Gemini** (`@google/genai`)                  | `thinkingConfig: { includeThoughts: true, thinkingLevel }`                           | `'low'` → `LOW`, `'high'`/`'max'` → `HIGH`, others → `THINKING_LEVEL_UNSPECIFIED` (Gemini has no `MAX` tier).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Protocol / provider                           | Wire shape                                                                               | Notes                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| --------------------------------------------- | ---------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **OpenAI / DashScope** (`qwen3.8-max` family) | Flat `reasoning_effort: <effort>` body parameter                                         | The `/effort` tiers are passed through for any model id starting with `qwen3.8-max` (including dated snapshots and `-latest` aliases); DashScope applies any model-specific mapping. This family's ladder stops at `xhigh`, so a configured `max` is clamped to `xhigh` (logged once) rather than sent and rejected. An explicit `reasoning_effort` in `samplingParams` or `extra_body` is a verbatim override and is not clamped. When `reasoning_effort` and `thinking_budget` conflict, the normal `extra_body` > `samplingParams` > `reasoning` precedence keeps only the higher-priority field; an explicit same-layer pair keeps `reasoning_effort`, matching the provider's behavior before cross-layer resolution. If a static field wins, `/effort` reports that field instead of implying the requested tier is effective. When an effort tier wins, a conflicting `enable_thinking` is also dropped. An explicit `enable_thinking: false` in `extra_body` is honoured rather than dropped: it overrides the configured tier as `reasoning_effort: 'none'`, one of the few places `extra_body` does not win verbatim. Other Qwen models continue to map a selected effort to `enable_thinking: true`; a `reasoning_effort` override passes through there unless it conflicts with a `thinking_budget` (a pair DashScope rejects), in which case the inert `reasoning_effort` is dropped and both `enable_thinking` and `thinking_budget` survive. |
+| **OpenAI / DeepSeek** (`api.deepseek.com`)    | Flat `reasoning_effort: <effort>` body parameter                                         | When `reasoning.effort` is set in the nested config shape, it's rewritten to flat `reasoning_effort` and `'low'`/`'medium'` are normalized to `'high'`, `'xhigh'` to `'max'` — mirroring DeepSeek's [server-side back-compat](https://api-docs.deepseek.com/zh-cn/api/create-chat-completion). Top-level `samplingParams.reasoning_effort` or `extra_body.reasoning_effort` overrides skip this normalization and ship verbatim. `max` is accepted only on a real DeepSeek hostname; a `deepseek`-named model on another host keeps the generic `xhigh` ceiling, matching the hostname gate on the reshape itself.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+| **OpenAI / Z.ai** (`z.ai`, `bigmodel.cn`)     | Flat `reasoning_effort: <effort>` body parameter                                         | GLM-5.2+ on a Z.ai host takes the full ladder, `max` included, and the nested `reasoning.effort` is rewritten to the flat field. Older GLM ids, and a `glm-*` model reached on any other host, keep the generic `xhigh` ceiling: the model name alone says nothing about what that endpoint accepts.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| **OpenAI** (other compatible servers)         | Known GPT-5 / GPT-6 Astra: flat `reasoning_effort`; other models: nested `reasoning`     | GPT effort is clamped in both directions to the supported subset for the known model. GPT-5.6 and GPT-6 Astra allow `max`, while earlier models have lower ceilings. Tiers below the model floor are raised: GPT-5 Pro accepts only `high`; GPT-5.2 Pro, GPT-5.4 Pro and GPT-5.5 Pro raise `low` to `medium`. OpenRouter retains nested `reasoning`. Unknown model names keep the generic `xhigh` ceiling and nested shape. Explicit reasoning values in `samplingParams` / `extra_body` bypass the configured-tier clamp.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+| **OpenAI Responses** (`openai-responses`)     | `reasoning: { effort, summary: "auto" }` plus `include: ["reasoning.encrypted_content"]` | Every tier passes through verbatim with no clamping. `extra_body.enable_thinking: true` is translated to `reasoning: { effort: "medium" }` when no explicit `reasoning` is set (and is never itself forwarded — it has no meaning on this wire); prefer setting `reasoning.effort` directly.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
+| **Anthropic** (real `api.anthropic.com`)      | `output_config: { effort }` plus the `effort-2025-11-24` beta header                     | Real Anthropic accepts `'low'`/`'medium'`/`'high'` only. `'max'` is **clamped to `'high'`** with a `debugLogger.warn` line (once per generator); if you want max effort, switch the baseURL to a DeepSeek-compatible endpoint that supports it.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| **Anthropic** (`api.deepseek.com/anthropic`)  | Same `output_config: { effort }` + beta header                                           | `'max'` is passed through unchanged.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| **Gemini** (`@google/genai`)                  | `thinkingConfig: { includeThoughts: true, thinkingLevel }`                               | `'low'` → `LOW`, `'high'`/`'max'` → `HIGH`, others → `THINKING_LEVEL_UNSPECIFIED` (Gemini has no `MAX` tier).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
 
 ### `reasoning: false`
 

package/bundled/qc-helper/docs/configuration/settings.md

@@ -125,6 +125,8 @@ These settings are read from operator scopes only (User, System, and SystemDefau
 | --------------------------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------- |
 | `ui.theme`                              | string           | The color theme for the UI. See [Themes](../configuration/themes) for available options.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | `"Qwen Dark"` |
 | `ui.customThemes`                       | object           | Custom theme definitions.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 | `{}`          |
+| `ui.brand.name`                         | string           | Product name the Web Shell presents in its sidebar, welcome header, About panel and browser tab title. Sanitized to a single line and capped at 80 characters. Read from operator scopes only (User, System, SystemDefaults) — a workspace `.qwen/settings.json` cannot rebrand the shell. A placeholder value that substitution would change (`$VAR`/`${VAR}` with the variable set) is refused with a warning on the daemon's stderr, because the substitution source is process-wide and a workspace could supply it; an unresolvable placeholder is kept verbatim, so a typo'd variable shows as literal text rather than silently falling back. Not editable from the in-browser Settings page. The terminal banner has its own separate setting, `ui.customBannerTitle`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            | `""`          |
+| `ui.brand.logoPath`                     | string           | Path to an SVG used as the Web Shell sidebar logo and browser favicon. A leading `~` is expanded, and a relative path resolves against the directory of the settings file that declares it. Must be a regular file (not a symlink, and not reachable through more than one hard link) of at most 32 KiB — on disk and once UTF-8-decoded — whose root element is a namespaced `<svg>` (the `xmlns` attribute, or an `xmlns:svg` binding on a prefix-bound root, is what makes it renderable as an image). Environment variable placeholders that would resolve are refused, as with `ui.brand.name`. Read from operator scopes only. A rejected file logs a warning on the daemon's stderr and falls back to the built-in logo. A root `<svg>` with no usable `viewBox` or explicit positive width/height is accepted but logs an advisory, and so is a prefix-bound root whose unprefixed elements have no default-namespace binding, because the browser may render it blank at the sidebar's fixed size.                                                                                                                                                                                                                                                                                               | `""`          |
 | `ui.statusLine`                         | object           | Custom status line configuration. Supports `command`, `refreshInterval`, `respectUserColors`, and `hideContextIndicator` options. See [Status Line](../features/status-line).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | `undefined`   |
 | `ui.hideWindowTitle`                    | boolean          | Hide the window title bar.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | `false`       |
 | `ui.hideTips`                           | boolean          | Hide all tips (startup and post-response) in the UI. See [Contextual Tips](../features/tips).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | `false`       |
@@ -138,6 +140,7 @@ These settings are read from operator scopes only (User, System, and SystemDefau
 | `ui.history.collapseOnResume`           | boolean          | Whether to collapse history by default when resuming a session. Can be toggled via `/history collapse-on-resume` and `/history expand-on-resume`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | `false`       |
 | `ui.history.collapsePreviewCount`       | number           | Number of most recent user turns to keep visible when `ui.history.collapseOnResume` is enabled. `0` collapses all restored history by default; `-1` shows all restored history.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           | `0`           |
 | `ui.compactMode`                        | boolean          | **RETIRED everywhere.** The CLI now always shows the compact, type-based tool view in the main transcript; press `Ctrl+O` to toggle expanded detail mode (expand or collapse all thinking blocks and tool outputs inline) instead of toggling a mode, and the web shell now fixes its compact view on as well. The key is kept only so existing settings files do not warn; writes are accepted but nothing reads the value.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | `false`       |
+| `ui.showToolCallDetails`                | boolean          | Show tool arguments and results inline. Set to `false` to render ordinary tool calls as a one-line summary. Click the row in Virtualized History or press `Ctrl+O` to expand details. Approval prompts, user-initiated shell commands, and focused interactive shells remain expanded.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | `true`        |
 | `ui.showToolCallArgs`                   | boolean          | Render tool calls on their own line with their full raw arguments inline, instead of the type-based compact summary that folds read/search/list batches into `Read 3 files`. Recovers parameters the per-tool description summarizes away (e.g. `Edit` normally shows only the filename). Useful when debugging MCP integrations or tool schemas. The args row is capped at 2 wrapped lines (and at most 1000 characters), so a batch of pending calls cannot outgrow the terminal; press `Ctrl+O` to lift the cap and expand result output too. Two cases keep the compact view: groups of running parallel subagents, which the live agent roster owns — expanding them re-inflates the live frame past the terminal height (#5798) — and daemon-attached sessions, which do not carry arguments across the daemon boundary. Use `Ctrl+O` there. TUI only — the web shell is unaffected.                                                                                                                                                                                                                                                                                                                                                                                                                | `false`       |
 | `ui.shellOutputMaxLines`                | number           | Max number of shell output lines shown inline. Set to `0` to disable the cap and show full output. Hidden lines are surfaced via the `+N lines` indicator. Errors, `!`-prefix user-initiated commands, confirming tools, and focused embedded shells always show full output.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | `5`           |
 | `ui.enableWelcomeBack`                  | boolean          | Show welcome back dialog when returning to a project with conversation history. When enabled, Qwen Code will automatically detect if you're returning to a project with a previously generated project summary (`.qwen/PROJECT_SUMMARY.md`) and show a dialog allowing you to continue your previous conversation or start fresh. If you choose **Start new chat session**, that choice is remembered for the current project until the project summary changes. This feature integrates with the `/summary` command and quit confirmation dialog.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        | `true`        |
@@ -181,10 +184,12 @@ These settings are read from operator scopes only (User, System, and SystemDefau
 | `model.maxSessionTurns`                            | integer | Maximum number of user/model/tool turns to keep in a session. -1 means unlimited.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        | `-1`        |
 | `model.maxWallTimeSeconds`                         | number  | Wall-clock budget for headless / unattended runs, in seconds. `-1` means unlimited. Overridable per-invocation via `--max-wall-time`, which requires a positive duration (`90`, `30s`, `5m`, `1h`, `1.5h`); the minimum is 1 second — sub-second values (`500ms`, `0.5`) are rejected as typos. Omit the flag to fall back to this setting. Aborts with exit code 55 when exceeded.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      | `-1`        |
 | `model.goalTokenBudget`                            | integer | Autonomous spend window armed on each new Goal, in tokens as counted by the Goal meter (`totalTokenCount` summed over the model calls the Goal makes in its own turns). A Goal that spends its window gets one wind-down turn to hand off, then stops until you resume it, which arms another window. Unset uses the built-in default of 30,000,000; `-1` means unlimited. Zero, values above 300,000,000 (10x the default, a typo guard), other negative, fractional, or non-number values are rejected at startup.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | `30000000`  |
-| `model.goalCheckpointTimeoutSeconds`               | integer | Ceiling on one Goal evidence-checkpoint call, in seconds. A long Goal periodically compresses its evidence into checkpoint claims with a side model call; a call that does not finish in time is abandoned as an inconclusive check — the checkpoint stall streak is preserved rather than incremented — and a later turn retries it. Unset uses the built-in default of 180. Must be an integer between 1 and 900; other values are rejected at startup. The call is streamed, so the per-request transport timeout (`model.generationConfig.timeout`, default 120 s) bounds only connect and first response, and values above 900 are rejected because past the default stream lifetime guard that guard, not this setting, ends the call. The 900 ceiling is fixed: raising `QWEN_STREAM_MAX_LIFETIME_MS` does not lift it.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           | `180`       |
+| `model.goalCheckpointTimeoutSeconds`               | integer | Ceiling on one Goal evidence-checkpoint check, in seconds. A long Goal periodically compresses its evidence into checkpoint claims with a side model call; when a check makes its one corrective retry, both calls share this ceiling ([Goals](../features/goals.md) lists which failures earn one). A check that does not finish in time is abandoned as inconclusive; it counts toward the checkpoint stall limit only when the evidence window has overflowed, while a non-overflowing check preserves the streak and retries on a later turn. Unset uses the built-in default of 180. Must be an integer between 1 and 900; other values are rejected at startup. The calls are streamed, so the per-request transport timeout (`model.generationConfig.timeout`, default 120 s) bounds only connect and first response, and values above 900 are rejected because past the default stream lifetime guard that guard, not this setting, ends the check. The 900 ceiling is fixed: raising `QWEN_STREAM_MAX_LIFETIME_MS` does not lift it.                                                                                                                                                                                                                                                                                            | `180`       |
+| `model.goalMaxTurns`                               | integer | Goal-turn window armed on each new Goal. Every finished Goal turn counts, including user-driven turns; user turns are still admitted at the ceiling, but they can make the next autonomous continuation a wind-down. A Goal that reaches the ceiling gets one wind-down turn to hand off, then stops as usage-limited until you resume it, which authorizes another window on top of the turns already finished. Unset runs Goals with no turn ceiling, and `-1` says so explicitly -- but the opt-out only takes a ceiling off a Goal that has already spent it, on the resume or edit that follows; a Goal still under its ceiling keeps it. A ceiling is armed only on a Goal created after the change, so bounding a Goal already on the record means replacing it with `/goal set`, which starts a new Goal at revision 1 with its meters reset and its earlier evidence no longer citable, or clearing it and starting again. Zero, values above 10,000, other negative, fractional, or non-number values are rejected at startup. Changes take effect after restart.                                                                                                                                                                                                                                                              | (none)      |
+| `model.goalMaxActiveMinutes`                       | integer | Active-time window armed on each new Goal, in minutes of wall time while the Goal remains active, including waits and idle time between turns. Paused, blocked or stopped time does not count, nor does downtime across a restart; a suspended process is still charged. A Goal that reaches the ceiling gets one wind-down turn to hand off, then stops as usage-limited until you resume it, which authorizes another window measured from where it stopped. The ceiling is read between turns, not by a timer, so a Goal can run well past it before it stops. Active time is measured between recorded transitions, so time in a turn that a restart interrupted is not charged. Unset runs Goals with no time ceiling, and `-1` says so explicitly -- but the opt-out only takes a ceiling off a Goal that has already spent it, on the resume or edit that follows. A ceiling is armed only on a Goal created after the change, so bounding a Goal already on the record means replacing it with `/goal set`, which starts a new Goal at revision 1 with its meters reset and its earlier evidence no longer citable, or clearing it and starting again. Zero, values above 10,080 (one week), other negative, fractional, or non-number values are rejected at startup. Changes take effect after restart.                        | (none)      |
 | `model.maxToolCalls`                               | number  | Cumulative tool-call budget for a run (counts every executed tool, success or failure; `structured_output` under `--json-schema` is exempt). `-1` means unlimited; `0` means "no tool calls allowed". Capped at 1,000,000 to catch typos. Overridable via `--max-tool-calls`. Aborts with exit code 55 when exceeded.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | `-1`        |
 | `model.maxSubagentDepth`                           | number  | Maximum sub-agent nesting depth (1-based levels: a top-level sub-agent is level 1). `1` keeps sub-agents available but disables nesting — the pre-nesting behavior. Values clamp to the range 1–100; non-finite values fall back to the default. Teammates, forks, and workflow-spawned agents never nest regardless of this setting. Overridable via `--max-subagent-depth`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            | `5`         |
-| `model.generationConfig`                           | object  | Advanced overrides passed to the underlying content generator. Supports request controls such as `timeout`, `maxRetries`, `retryInitialDelayMs`, `retryMaxDelayMs`, `enableCacheControl`, `splitToolMedia` (default `true`; splits tool-returned media — including images read by the built-in read_file — into a follow-up user message instead of the spec-violating `role: "tool"` message, so strict OpenAI-compatible servers like doubao / new-api / LM Studio can see it; set `false` to restore the legacy embed-in-tool behavior), `toolResultContentFormat` (default `"parts"`; set `"string"` only for legacy OpenAI-compatible runtimes whose tool templates ignore text content parts), `contextWindowSize` (override model's context window size), `modalities` (override auto-detected input modalities), `customHeaders` (custom HTTP headers for API requests), and `extra_body` (additional body parameters for OpenAI-compatible API requests only), along with fine-tuning knobs under `samplingParams` (for example `temperature`, `top_p`, `max_tokens`). Leave unset to rely on provider defaults.                                                                                                                                                                                                                | `undefined` |
+| `model.generationConfig`                           | object  | Advanced overrides passed to the underlying content generator. Supports request controls such as `timeout`, `maxRetries`, `retryInitialDelayMs`, `retryMaxDelayMs`, `enableCacheControl`, `splitToolMedia` (default `true`; splits tool-returned media — including images read by the built-in read_file — into a follow-up user message instead of the spec-violating `role: "tool"` message, so strict OpenAI-compatible servers like doubao / new-api / LM Studio can see it; set `false` to restore the legacy embed-in-tool behavior), `toolResultContentFormat` (default `"parts"`; set `"string"` only for legacy OpenAI-compatible runtimes whose tool templates ignore text content parts), `contextWindowSize` (override model's context window size), `modalities` (override auto-detected input modalities), `customHeaders` (custom HTTP headers for API requests), and `extra_body` (additional body parameters for OpenAI-compatible and OpenAI Responses API requests), along with fine-tuning knobs under `samplingParams` (for example `temperature`, `top_p`, `max_tokens`). Leave unset to rely on provider defaults.                                                                                                                                                                                                | `undefined` |
 | `model.chatCompression.contextPercentageThreshold` | number  | **REMOVED.** Replaced by `context.autoCompactThreshold` (see `#### context` section below). Auto-compaction now uses a three-tier threshold ladder (warn / auto / hard) computed internally from the model's context window via the `computeThresholds()` function. The old setting is silently ignored (no startup warning). See PR #4345 / `docs/design/auto-compaction-threshold-redesign.md` for the redesign rationale.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | `N/A`       |
 | `model.chatCompression.maxRecentFilesToRetain`     | number  | Number of most-recently-touched files whose current content is restored (embedded if small, otherwise referenced by path) into history after auto-compaction. `0` restores none. Env override: `QWEN_COMPACT_MAX_RECENT_FILES`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `5`         |
 | `model.chatCompression.maxRecentImagesToRetain`    | number  | Number of most-recent images (tool screenshots / user pastes) restored into history after auto-compaction. `0` restores none. Env override: `QWEN_COMPACT_MAX_RECENT_IMAGES`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            | `3`         |
@@ -270,7 +275,7 @@ Overrides the auto-detected input modalities for the selected model. Qwen Code a
 
 Allows you to add custom HTTP headers to all API requests. This is useful for request tracing, monitoring, API gateway routing, or when different models require different headers. For provider models, define `customHeaders` in `modelProviders[].generationConfig.customHeaders`. For runtime models without a matching provider entry, define it in `model.generationConfig.customHeaders`. No merging occurs between the two levels.
 
-The `extra_body` field allows you to add custom parameters to the request body sent to the API. This is useful for provider-specific options that are not covered by the standard configuration fields. **Note: This field is only supported for OpenAI-compatible providers (`openai`, `qwen-oauth`). It is ignored for Anthropic and Gemini providers.** For provider models, define `extra_body` in `modelProviders[].generationConfig.extra_body`. For runtime models without a matching provider entry, define it in `model.generationConfig.extra_body`.
+The `extra_body` field allows you to add custom parameters to the request body sent to the API. This is useful for provider-specific options that are not covered by the standard configuration fields. **Note: This field is supported for OpenAI-compatible providers (`openai`, `qwen-oauth`) and the OpenAI Responses API (`openai-responses`). It is ignored for Anthropic and Gemini providers.** On the `openai-responses` wire, the legacy `enable_thinking` key is translated into `reasoning.effort` rather than forwarded verbatim — use `reasoning.effort` directly for that provider instead. For provider models, define `extra_body` in `modelProviders[].generationConfig.extra_body`. For runtime models without a matching provider entry, define it in `model.generationConfig.extra_body`.
 
 **model.openAILoggingDir examples:**
 

package/bundled/qc-helper/docs/features/_meta.ts

@@ -1,5 +1,6 @@
 export default {
   commands: 'Commands',
+  'cross-session-protocol': 'Cross-Session Protocol',
   'code-review': 'Code Review',
   'followup-suggestions': 'Followup Suggestions',
   'tool-use-summaries': 'Tool-Use Summaries',

package/bundled/qc-helper/docs/features/channels/dingtalk.md

@@ -111,26 +111,6 @@ Background Agent output is sent as soon as each response segment is available.
 Every message is labeled with the Agent name so concurrent work remains
 attributable.
 
-To buffer each Agent's notification turn and send it as one labeled message,
-enable aggregation for the DingTalk channel in `settings.json`:
-
-```json
-{
-  "channels": {
-    "my-dingtalk": {
-      "type": "dingtalk",
-      "clientId": "$DINGTALK_CLIENT_ID",
-      "clientSecret": "$DINGTALK_CLIENT_SECRET",
-      "aggregateBackgroundAgentResponses": true
-    }
-  }
-}
-```
-
-Aggregation is disabled by default. A partial labeled message is sent if the
-Agent turn is interrupted, fails before producing a final response, or does
-not finish within ten minutes.
-
 ## Running
 
 ```bash

package/bundled/qc-helper/docs/features/channels/dws.md

@@ -85,6 +85,12 @@ When a message quotes another DingTalk message, the quoted text is included as r
 
 `startReaction` is the emoji character or DingTalk reaction name added while an accepted task is running; an omitted or empty value uses the default `🤔`. `endReaction` replaces it after the task completes, fails, or is cancelled; an omitted or empty value disables the end reaction.
 
+### IM Reply Delivery
+
+A completed group @ or direct-message reply is checkpointed before its first send and retried in the background without rerunning the task. The backoff starts at five seconds, doubles, and caps at five minutes. A reply is abandoned after 16 failed delivery attempts. Local deferrals caused by a disconnected channel or an unreadable pairing approval use a separate limit of 32 consecutive checks, so they do not consume the transport-attempt budget. A reply is dropped immediately when its sender, group, or direct-message authorization is definitively revoked. The queue holds up to 100 replies and evicts the oldest entry regardless of its attempt count when full; switching the configured DWS profile clears the queue. These drops are reported on channel stderr, not sent as chat notifications.
+
+Queued IM replies longer than 12,000 code points are truncated, with `[Response truncated for DWS delivery.]` appended to the message the recipient sees. Document-comment and native-todo comment replies do not use this queued retry or truncation path: each turn makes one comment-send call, unknown outcomes are swallowed, and definitive failures propagate to the existing inbound-turn retry policy. The end reaction marks task completion, not reply delivery, so a retried IM reply can arrive after that reaction appears.
+
 ## Document Mentions
 
 There is no document or knowledge-base watch list. To start a document task:
@@ -121,6 +127,6 @@ qwen serve --workspace /path/to/your/project --channel dws-work
 
 Do not run both forms at once because they share the channel-service lease.
 
-For local verification, send a direct message from another account, approve pairing if required, and verify the configured start reaction appears while the task runs. If an end reaction is configured, verify that it replaces the start reaction afterward. Then add a document comment with @mention notification enabled. The channel should react to the notification message, read the document, and post the final answer under the original comment. A comment with notification disabled should produce no task.
+For local verification, send a direct message from another account, approve pairing if required, and verify the configured start reaction appears while the task runs. If an end reaction is configured, verify that it replaces the start reaction after the task finishes; reply delivery can complete later as described above. Then add a document comment with @mention notification enabled. The channel should react to the notification message, read the document, and post the final answer under the original comment. A comment with notification disabled should produce no task.
 
 The channel ignores events from sender IDs that DWS identifies as the authenticated account, preventing reply and pairing loops without inferring identity from message text. Starting the IM sources requires that authoritative self-identity: if the authenticated account exposes no openDingTalkId and no earlier session under the same profile recorded one, the channel refuses to connect. A reconnect that temporarily loses the ID keeps filtering on the previously recorded self sender IDs.