@hecer/yoke 1.9.0 → 1.11.0

package/canon/skills/yoke-retrofit/SKILL.md

@@ -1,26 +1,26 @@
----
-name: yoke-retrofit
-description: Use when asked to "retrofit", "yoke this project", or set up the Yoke harness in a project — runs the shared setup wizard and configures the same behavior for Claude, Codex, and Gemini.
----
-
-# Yoke Retrofit
-
-Set up or update Yoke through the shared `yoke setup` contract.
-
-1. Inspect the project and identify the current host (`claude`, `codex`, or `gemini`).
-2. Ask these setup questions one at a time and give a direct recommendation:
-   - target agents (recommend the current host; use `all` for deliberately cross-agent projects),
-   - code-graph tool,
-   - autonomous loop on/off,
-   - default runner (recommend the current host),
-   - decision mode: `auto` or `critical`.
-3. Recommend the code graph based on this project:
-   - **Serena** is LSP-accurate and best for large typed codebases or systematic symbol refactors where a missed reference is costly. It needs a language server per language.
-   - **graphify** is fast and multimodal, and is best for exploration, migration, onboarding, or mixed code and document repositories. Its graph is an index and can become stale.
-4. Apply the answers without a second round of prompts:
-   `yoke setup . --yes --host=<host> --agent=<agents> --code-graph=<choice> --runner=<runner> --decision-policy=<auto|critical> --loop|--no-loop`.
-   A human who runs `yoke setup .` directly receives the same five terminal questions.
-5. Show the generated report and backup paths. Existing files are backed up under `.yoke/backup/`; settings are merged where supported.
-6. If an old generated `CLAUDE.md` or `GEMINI.md` contained project-specific instructions, restore them inside its `<!-- yoke:preserve:start -->` / `<!-- yoke:preserve:end -->` block. Preserve blocks survive every later retrofit.
-
-The generated harness includes the provider-neutral `yoke-workflow` skill. It owns the planning questions, approved-plan handoff, autonomous stories, and critical-decision resume flow.
+---
+name: yoke-retrofit
+description: Use when asked to "retrofit", "yoke this project", or set up the Yoke harness in a project — runs the shared setup wizard and configures the same behavior for Claude, Codex, and Gemini.
+---
+
+# Yoke Retrofit
+
+Set up or update Yoke through the shared `yoke setup` contract.
+
+1. Inspect the project and identify the current host (`claude`, `codex`, or `gemini`).
+2. Ask these setup questions one at a time and give a direct recommendation:
+   - target agents (recommend the current host; use `all` for deliberately cross-agent projects),
+   - code-graph tool,
+   - autonomous loop on/off,
+   - default runner (recommend the current host),
+   - decision mode: `auto` or `critical`.
+3. Recommend the code graph based on this project:
+   - **Serena** is LSP-accurate and best for large typed codebases or systematic symbol refactors where a missed reference is costly. It needs a language server per language.
+   - **graphify** is fast and multimodal, and is best for exploration, migration, onboarding, or mixed code and document repositories. Its graph is an index and can become stale.
+4. Apply the answers without a second round of prompts:
+   `yoke setup . --yes --host=<host> --agent=<agents> --code-graph=<choice> --runner=<runner> --decision-policy=<auto|critical> --loop|--no-loop`.
+   A human who runs `yoke setup .` directly receives the same five terminal questions.
+5. Show the generated report and backup paths. Existing files are backed up under `.yoke/backup/`; settings are merged where supported.
+6. If an old generated `CLAUDE.md` or `GEMINI.md` contained project-specific instructions, restore them inside its `<!-- yoke:preserve:start -->` / `<!-- yoke:preserve:end -->` block. Preserve blocks survive every later retrofit.
+
+The generated harness includes the provider-neutral `yoke-workflow` skill. It owns the planning questions, approved-plan handoff, autonomous stories, and critical-decision resume flow.

package/canon/skills/yoke-workflow/SKILL.md

@@ -1,20 +1,20 @@
----
-name: yoke-workflow
-description: Use when the user asks Yoke to plan and build a feature, run stories autonomously, continue a Yoke loop, or only interrupt for major decisions.
----
-
-# Yoke Workflow
-
-Provide the same interaction contract in Claude, Codex, and Gemini.
-
-1. Read `.yoke/config.yaml`. If it is missing, offer `yoke setup . --host=<current-agent>` and run the setup flow before planning.
-2. Plan before starting the loop. Inspect the project, then ask one focused question at a time only where the answer changes product behavior, scope, architecture, security, data ownership, external cost, or an irreversible choice. Include a recommended answer. Resolve routine implementation details yourself.
-3. Summarize the agreed design in `.yoke/plan.md`, including goals, non-goals, constraints, and decisions. Use the `authoring-prd` skill to turn it into small stories with testable acceptance criteria. Run `yoke prd check .`.
-4. Ask once for approval of the complete plan and story set. Do not begin implementation before that approval.
-5. If `loop.enabled` is true, run the stories without routine follow-up questions using the configured runner. Prefer `yoke loop run . --max=5 --isolate`, report status after each batch, and continue until complete or genuinely blocked.
-6. Respect `loop.decisionPolicy`:
-   - `auto`: choose the most suitable option from the plan, current code, and established conventions. Record the interpretation and continue.
-   - `critical`: routine ambiguity is still resolved automatically. If the loop reports a pending critical decision, run `yoke loop decision .`, present its options and recommendation to the user, ask exactly that question, then run `yoke loop answer . --choice=<id> --rationale="<answer>"`. The answer command records the decision and resumes the same story.
-7. Never ask whether to run tests, review, commit, or continue to the next approved story. Those are part of the approved workflow.
-
-The user's configured commit identity is authoritative. Do not add an AI co-author unless `commit.allowCoAuthors` explicitly permits it.
+---
+name: yoke-workflow
+description: Use when the user asks Yoke to plan and build a feature, run stories autonomously, continue a Yoke loop, or only interrupt for major decisions.
+---
+
+# Yoke Workflow
+
+Provide the same interaction contract in Claude, Codex, and Gemini.
+
+1. Read `.yoke/config.yaml`. If it is missing, offer `yoke setup . --host=<current-agent>` and run the setup flow before planning.
+2. Plan before starting the loop. Inspect the project, then ask one focused question at a time only where the answer changes product behavior, scope, architecture, security, data ownership, external cost, or an irreversible choice. Include a recommended answer. Resolve routine implementation details yourself.
+3. Summarize the agreed design in `.yoke/plan.md`, including goals, non-goals, constraints, and decisions. Use the `authoring-prd` skill to turn it into small stories with testable acceptance criteria. Run `yoke prd check .`.
+4. Ask once for approval of the complete plan and story set. Do not begin implementation before that approval.
+5. If `loop.enabled` is true, run the stories without routine follow-up questions using the configured runner. Prefer `yoke loop run . --max=5 --isolate`, report status after each batch, and continue until complete or genuinely blocked.
+6. Respect `loop.decisionPolicy`:
+   - `auto`: choose the most suitable option from the plan, current code, and established conventions. Record the interpretation and continue.
+   - `critical`: routine ambiguity is still resolved automatically. If the loop reports a pending critical decision, run `yoke loop decision .`, present its options and recommendation to the user, ask exactly that question, then run `yoke loop answer . --choice=<id> --rationale="<answer>"`. The answer command records the decision and resumes the same story.
+7. Never ask whether to run tests, review, commit, or continue to the next approved story. Those are part of the approved workflow.
+
+The user's configured commit identity is authoritative. Do not add an AI co-author unless `commit.allowCoAuthors` explicitly permits it.

package/canon/tools/codex-rtk-hook.mjs

@@ -1,36 +1,36 @@
 import { spawnSync } from 'node:child_process'
-import { resolve } from 'node:path'
-import { pathToFileURL } from 'node:url'
-
-function rtkCheck(command) {
-  const result = spawnSync('rtk', ['hook', 'check', command], { encoding: 'utf8', timeout: 3000 })
-  return result.status === 0 ? result.stdout.trim() : ''
-}
-
-export function rewriteHookInput(input, check = rtkCheck) {
-  if (input?.tool_name !== 'Bash' && input?.toolName !== 'Bash') return null
-  const toolInput = input.tool_input ?? input.toolInput
-  const command = toolInput?.command
-  if (typeof command !== 'string' || command.trim() === '') return null
-  const rewritten = check(command)
-  if (!rewritten || rewritten === command) return null
-  return {
-    hookSpecificOutput: {
-      hookEventName: 'PreToolUse',
-      updatedInput: { ...toolInput, command: rewritten },
-    },
-  }
-}
-
-async function main() {
-  let raw = ''
-  for await (const chunk of process.stdin) raw += chunk
-  try {
-    const output = rewriteHookInput(JSON.parse(raw))
-    if (output) process.stdout.write(JSON.stringify(output))
-  } catch {
-    // Compression is an optimization. Malformed input must never block Codex.
-  }
-}
-
-if (process.argv[1] && pathToFileURL(resolve(process.argv[1])).href === import.meta.url) await main()
+import { resolve } from 'node:path'
+import { pathToFileURL } from 'node:url'
+
+function rtkCheck(command) {
+  const result = spawnSync('rtk', ['hook', 'check', command], { encoding: 'utf8', timeout: 3000 })
+  return result.status === 0 ? result.stdout.trim() : ''
+}
+
+export function rewriteHookInput(input, check = rtkCheck) {
+  if (input?.tool_name !== 'Bash' && input?.toolName !== 'Bash') return null
+  const toolInput = input.tool_input ?? input.toolInput
+  const command = toolInput?.command
+  if (typeof command !== 'string' || command.trim() === '') return null
+  const rewritten = check(command)
+  if (!rewritten || rewritten === command) return null
+  return {
+    hookSpecificOutput: {
+      hookEventName: 'PreToolUse',
+      updatedInput: { ...toolInput, command: rewritten },
+    },
+  }
+}
+
+async function main() {
+  let raw = ''
+  for await (const chunk of process.stdin) raw += chunk
+  try {
+    const output = rewriteHookInput(JSON.parse(raw))
+    if (output) process.stdout.write(JSON.stringify(output))
+  } catch {
+    // Compression is an optimization. Malformed input must never block Codex.
+  }
+}
+
+if (process.argv[1] && pathToFileURL(resolve(process.argv[1])).href === import.meta.url) await main()

package/canon/tools/gemini-rtk-hook.mjs

@@ -1,25 +1,25 @@
-#!/usr/bin/env node
-// Pure BeforeTool argument adapter. Never evaluates or executes tool commands.
-import { readFileSync } from 'node:fs'
-
-const record = value => value !== null && typeof value === 'object' && !Array.isArray(value)
-try {
-  const event = JSON.parse(readFileSync(0, 'utf8'))
-  if (!record(event) || typeof event.tool_name !== 'string' ||
-      (event.hook_event_name !== undefined && event.hook_event_name !== 'BeforeTool')) throw new Error('event')
-  let response = {}
-  if (event.tool_name === 'run_shell_command') {
-    if (!record(event.tool_input) || typeof event.tool_input.command !== 'string' || !event.tool_input.command.trim() || event.tool_input.command.includes('\0')) throw new Error('command')
-    const command = event.tool_input.command
-    // Restrict rewriting to simple supported invocations. Leave shell syntax,
-    // quoted executables, assignments and existing RTK wrappers untouched.
-    if (!/[;&|<>`$\r\n()]/u.test(command) && /^\s*(?:git|rg|npm|npx|cargo|pytest|go|docker|kubectl)\s/u.test(command)) {
-      const rewritten = command.trimStart().replace(/^rg\s/u, 'grep ')
-      response = { hookSpecificOutput: { tool_input: { ...event.tool_input, command: `rtk ${rewritten}` } } }
-    }
-  }
-  process.stdout.write(JSON.stringify(response) + '\n')
-} catch {
-  process.stderr.write('Invalid Gemini BeforeTool hook input\n')
-  process.exitCode = 2
-}
+#!/usr/bin/env node
+// Pure BeforeTool argument adapter. Never evaluates or executes tool commands.
+import { readFileSync } from 'node:fs'
+
+const record = value => value !== null && typeof value === 'object' && !Array.isArray(value)
+try {
+  const event = JSON.parse(readFileSync(0, 'utf8'))
+  if (!record(event) || typeof event.tool_name !== 'string' ||
+      (event.hook_event_name !== undefined && event.hook_event_name !== 'BeforeTool')) throw new Error('event')
+  let response = {}
+  if (event.tool_name === 'run_shell_command') {
+    if (!record(event.tool_input) || typeof event.tool_input.command !== 'string' || !event.tool_input.command.trim() || event.tool_input.command.includes('\0')) throw new Error('command')
+    const command = event.tool_input.command
+    // Restrict rewriting to simple supported invocations. Leave shell syntax,
+    // quoted executables, assignments and existing RTK wrappers untouched.
+    if (!/[;&|<>`$\r\n()]/u.test(command) && /^\s*(?:git|rg|npm|npx|cargo|pytest|go|docker|kubectl)\s/u.test(command)) {
+      const rewritten = command.trimStart().replace(/^rg\s/u, 'grep ')
+      response = { hookSpecificOutput: { tool_input: { ...event.tool_input, command: `rtk ${rewritten}` } } }
+    }
+  }
+  process.stdout.write(JSON.stringify(response) + '\n')
+} catch {
+  process.stderr.write('Invalid Gemini BeforeTool hook input\n')
+  process.exitCode = 2
+}

package/canon/tools/graphify.md

@@ -1,3 +1,3 @@
-# Tool: graphify (code-graph)
-
-MIT, multimodal code/doc graph. Wired as an MCP server for all three agents (stdio). Prefer symbol/graph lookups over reading whole files. Caveat: heuristic edges (INFERRED/AMBIGUOUS) and a static index that can go stale — rebuild on significant changes.
+# Tool: graphify (code-graph)
+
+MIT, multimodal code/doc graph. Wired as an MCP server for all three agents (stdio). Prefer symbol/graph lookups over reading whole files. Caveat: heuristic edges (INFERRED/AMBIGUOUS) and a static index that can go stale — rebuild on significant changes.

package/canon/tools/playwright-mcp.md

@@ -1,3 +1,3 @@
-# Tool: Playwright MCP (browser / dogfooding)
-
-Microsoft Playwright MCP, Apache-2.0. Wired as an MCP server for all three agents — the only browser tool with native MCP parity across Claude/Codex/Gemini. Used for QA, dogfooding user flows, screenshots, and deploy verification.
+# Tool: Playwright MCP (browser / dogfooding)
+
+Microsoft Playwright MCP, Apache-2.0. Wired as an MCP server for all three agents — the only browser tool with native MCP parity across Claude/Codex/Gemini. Used for QA, dogfooding user flows, screenshots, and deploy verification.

package/canon/tools/rtk.md

@@ -1,7 +1,7 @@
-# Tool: rtk (token compression)
-
-Per-agent wiring (generated by Baustein B):
-
-- **Claude Code:** PreToolUse hook auto-rewrites commands (`git status` → `rtk git status`). On Windows this needs WSL; otherwise fall back to instruction mode (this file injected into CLAUDE.md telling the agent to prefix commands with `rtk`).
-- **Codex CLI:** inject `RTK.md` / AGENTS.md instruction.
-- **Gemini CLI:** no hook system — register rtk as an MCP tool or inject the GEMINI.md instruction.
+# Tool: rtk (token compression)
+
+Per-agent wiring (generated by Baustein B):
+
+- **Claude Code:** PreToolUse hook auto-rewrites commands (`git status` → `rtk git status`). On Windows this needs WSL; otherwise fall back to instruction mode (this file injected into CLAUDE.md telling the agent to prefix commands with `rtk`).
+- **Codex CLI:** inject `RTK.md` / AGENTS.md instruction.
+- **Gemini CLI:** no hook system — register rtk as an MCP tool or inject the GEMINI.md instruction.

package/canon/tools/serena.md

@@ -1,9 +1,9 @@
-# Tool: Serena (code-graph, LSP-accurate)
-
-MIT, MCP-first. The alternative to graphify, selected via `yoke retrofit --code-graph=serena`. Serena uses real language servers (LSP) for symbol-accurate, cross-file retrieval and refactoring (`find_symbol`, `find_referencing_symbols`, rename/move) — no static index that goes stale, so it will not miss a reference.
-
-Wired as an MCP server for all three agents. Best for large, strongly-typed codebases (TypeScript, Python, Go) doing systematic refactoring, where missing a caller is costly.
-
+# Tool: Serena (code-graph, LSP-accurate)
+
+MIT, MCP-first. The alternative to graphify, selected via `yoke retrofit --code-graph=serena`. Serena uses real language servers (LSP) for symbol-accurate, cross-file retrieval and refactoring (`find_symbol`, `find_referencing_symbols`, rename/move) — no static index that goes stale, so it will not miss a reference.
+
+Wired as an MCP server for all three agents. Best for large, strongly-typed codebases (TypeScript, Python, Go) doing systematic refactoring, where missing a caller is costly.
+
 Caveat: needs one language server per language (can be fiddly on Windows for exotic languages) and requires `uv`. The launch command is a best-effort template — adjust to your install, e.g. `uvx --from git+https://github.com/oraios/serena serena-mcp-server`.
 
 Yoke disables Serena's automatic web-dashboard launch in generated MCP configurations. The

package/dist/agents/contracts.js

@@ -1,5 +1,5 @@
 import { z } from 'zod';
-export const AgentSchema = z.enum(['claude', 'codex', 'gemini']);
+export const AgentSchema = z.enum(['claude', 'codex', 'gemini', 'qwen']);
 export const PermissionProfileSchema = z.enum(['safe', 'unsafe', 'read-only']);
 export const ModelSelectionSchema = z.object({
     model: z.string().regex(/^[A-Za-z0-9][A-Za-z0-9._:/-]{0,127}$/).optional(),

package/dist/agents/host.js

@@ -7,12 +7,16 @@ export function detectHostAgent(env = process.env) {
         return 'claude';
     if (env.GEMINI_CLI)
         return 'gemini';
+    if (env.QWEN_CLI)
+        return 'qwen';
     if (env.CODEX_HOME)
         return 'codex';
     if (env.CLAUDE_CONFIG_DIR)
         return 'claude';
     if (env.GEMINI_CLI_HOME)
         return 'gemini';
+    if (env.QWEN_CLI_HOME)
+        return 'qwen';
     return undefined;
 }
 export function resolveRunnerAgent(config, explicit, host) {

package/dist/agents/process-incarnation.js

@@ -1,5 +1,5 @@
 import { execFileSync } from 'node:child_process';
-const queryProcessIdentity = (command, args, options) => execFileSync(command, args, { stdio: 'pipe', ...options }).toString();
+const queryProcessIdentity = (command, args, options) => execFileSync(command, args, { stdio: 'pipe', timeout: 5000, windowsHide: true, ...options }).toString();
 export function processIncarnation(pid, platform = process.platform, query = queryProcessIdentity) {
     try {
         if (platform === 'win32') {

package/dist/agents/process.js

@@ -4,35 +4,64 @@ import { killProcessTreeForCleanup } from '../loop/watchdog.js';
 import { createProviderProcessRecord, filesystemProviderProcessRecordAdapter, } from './process-record.js';
 import { createBoundedOutput, createTelemetryAccumulator } from './process-streams.js';
 import { processIncarnation } from './process-incarnation.js';
+import { prepareWindowsInvocation, resolveWindowsCommand } from './windows-launch.js';
+import { createSupervision, supervisionLimits, assertPreviousProvidersStopped } from './supervision.js';
 function cancellationReason(signal) {
     return typeof signal.reason === 'string' && signal.reason.length > 0
         ? signal.reason
         : 'provider process cancellation requested';
 }
 export function providerSpawnOptions(invocation, platform = process.platform) {
-    const windowsCommandShim = !/[\\/]/u.test(invocation.command) || /\.(?:bat|cmd)$/iu.test(invocation.command);
+    const resolved = platform === 'win32' ? resolveWindowsCommand(invocation.command, invocation.args) : invocation;
     return {
-        command: invocation.command,
-        args: invocation.args,
+        command: resolved.command,
+        args: resolved.args,
         cwd: invocation.cwd,
-        shell: platform === 'win32' && windowsCommandShim,
+        shell: false,
         detached: platform !== 'win32',
     };
 }
 export function startProviderProcess(agent, invocation, options = {}) {
-    const spawnOptions = providerSpawnOptions(invocation);
+    let failure = () => { };
+    let progress = () => { };
+    const limits = supervisionLimits(invocation.cwd);
+    const supervision = createSupervision(invocation.cwd, reason => failure(reason), () => progress(), options.attempt);
+    let prepared;
+    try {
+        assertPreviousProvidersStopped(invocation.cwd);
+        prepared = process.platform === 'win32' ? prepareWindowsInvocation(invocation) : { command: invocation.command, args: invocation.args, env: process.env };
+    }
+    catch (error) {
+        const message = error.message;
+        supervision.stop(message);
+        return { pid: undefined, invocation, recordPath: '', cancel: () => false, completion: Promise.resolve({ kind: 'spawn-failed', error: message, invocation, pid: undefined, stdout: '', stderr: '', stdoutTruncated: false, stderrTruncated: false, telemetry: { usageAvailable: false } }) };
+    }
+    const spawnOptions = { ...prepared, cwd: invocation.cwd, shell: false, detached: process.platform !== 'win32' };
     const child = spawn(spawnOptions.command, [...spawnOptions.args], {
         cwd: spawnOptions.cwd,
         shell: spawnOptions.shell,
         stdio: ['pipe', 'pipe', 'pipe'],
         detached: spawnOptions.detached,
+        env: prepared.env,
+        windowsHide: true,
     });
     const targetDir = resolve(invocation.cwd);
     const pid = child.pid;
     const startedAt = pid === undefined ? `unverified:${new Date().toISOString()}` : processIncarnation(pid) ?? `unverified:${new Date().toISOString()}`;
+    supervision.start(pid, 'shell' in prepared ? prepared.shell : undefined, startedAt.startsWith('unverified:') ? undefined : startedAt);
     const record = createProviderProcessRecord(targetDir, pid ?? 0, options.workerId, startedAt);
     const recordAdapter = options.recordAdapter ?? filesystemProviderProcessRecordAdapter;
-    const terminateProcessTree = options.terminateProcessTree ?? ((processPid) => killProcessTreeForCleanup(processPid));
+    const terminateProcessTree = options.terminateProcessTree ?? ((processPid) => {
+        try {
+            process.kill(processPid, 0);
+        }
+        catch {
+            return true;
+        }
+        if (startedAt.startsWith('unverified:') || processIncarnation(processPid) !== startedAt)
+            return false;
+        return killProcessTreeForCleanup(processPid);
+    });
     let recordPublished = false;
     const stdout = createBoundedOutput(options.outputLimitBytes ?? 1_048_576);
     const stderr = createBoundedOutput(options.outputLimitBytes ?? 1_048_576);
@@ -42,6 +71,9 @@ export function startProviderProcess(agent, invocation, options = {}) {
     let termination;
     let idleTimer;
     let forceTimer;
+    let totalTimer;
+    let progressTimer;
+    let completionTimer;
     let recordFailure;
     let terminationConfirmed = false;
     let settled = false;
@@ -58,6 +90,12 @@ export function startProviderProcess(agent, invocation, options = {}) {
             clearTimeout(idleTimer);
         if (forceTimer)
             clearTimeout(forceTimer);
+        if (totalTimer)
+            clearTimeout(totalTimer);
+        if (progressTimer)
+            clearTimeout(progressTimer);
+        if (completionTimer)
+            clearTimeout(completionTimer);
         idleTimer = undefined;
         forceTimer = undefined;
     };
@@ -66,6 +104,7 @@ export function startProviderProcess(agent, invocation, options = {}) {
             return;
         settled = true;
         clearTimers();
+        supervision.stop(termination?.reason ?? (result.kind === 'succeeded' ? 'provider-exited' : 'provider-failed'), !termination || terminationConfirmed);
         options.signal?.removeEventListener('abort', onAbort);
         if (!termination || terminationConfirmed)
             removeRecord();
@@ -81,6 +120,9 @@ export function startProviderProcess(agent, invocation, options = {}) {
         telemetry: telemetry.finish(),
     });
     const finalize = (exitCode) => {
+        if (settled)
+            return;
+        supervision.flush();
         // Windows can emit close before taskkill's process-tree state is observable.
         // Reconfirm here so successful termination does not leave a stale ownership record.
         if (termination && pid !== undefined && !terminationConfirmed) {
@@ -114,6 +156,21 @@ export function startProviderProcess(agent, invocation, options = {}) {
         forceTimer = setTimeout(() => {
             if (pid !== undefined && !settled)
                 terminationConfirmed = terminateProcessTree(pid, true);
+            // Allow close/pipe draining to confirm termination before the bounded fallback.
+            if (!settled)
+                completionTimer = setTimeout(() => {
+                    if (settled)
+                        return;
+                    // A killer's return value is not an observed process exit.
+                    if (pid !== undefined) {
+                        try {
+                            process.kill(pid, 0);
+                            terminationConfirmed = false;
+                        }
+                        catch { /* exited */ }
+                    }
+                    finalize(null);
+                }, 5000);
         }, terminationGraceMs);
         return true;
     };
@@ -140,8 +197,16 @@ export function startProviderProcess(agent, invocation, options = {}) {
             stderr.append(text);
         }
         options.onOutput?.({ stream, text });
+        supervision.output(stream, text);
         armIdleTimer();
     };
+    failure = reason => { terminate({ kind: 'cancelled', reason }); };
+    progress = () => {
+        if (progressTimer)
+            clearTimeout(progressTimer);
+        if ((options.progressTimeoutMs ?? limits.progressMs) > 0)
+            progressTimer = setTimeout(() => terminate({ kind: 'timed-out', reason: 'provider-progress-timeout' }), options.progressTimeoutMs ?? limits.progressMs);
+    };
     child.stdout?.on('data', chunk => { onOutput('stdout', chunk); });
     child.stderr?.on('data', chunk => { onOutput('stderr', chunk); });
     child.stdin?.on('error', () => { });
@@ -178,5 +243,8 @@ export function startProviderProcess(agent, invocation, options = {}) {
     else
         options.signal?.addEventListener('abort', onAbort, { once: true });
     armIdleTimer();
+    if ((options.totalTimeoutMs ?? limits.totalMs) > 0)
+        totalTimer = setTimeout(() => terminate({ kind: 'timed-out', reason: 'provider-total-timeout' }), options.totalTimeoutMs ?? limits.totalMs);
+    progress();
     return handle;
 }

package/dist/agents/providers.js

@@ -17,6 +17,13 @@ const argsFor = (agent, permissions) => {
         // Automatic review already selects workspace-write and conflicts with --sandbox.
         return ['exec', '--approve-for-me', '--json'];
     }
+    // Qwen CLI is a Gemini fork with similar arguments
+    if (agent === 'qwen') {
+        if (permissions === 'unsafe')
+            return ['--yolo', '--output-format', 'stream-json'];
+        const approval = permissions === 'read-only' ? 'plan' : 'auto_edit';
+        return ['--approval-mode', approval, '--sandbox', '--output-format', 'stream-json'];
+    }
     if (permissions === 'unsafe')
         return ['--yolo', '--output-format', 'stream-json'];
     const approval = permissions === 'read-only' ? 'plan' : 'auto_edit';
@@ -30,6 +37,12 @@ export function buildProviderInvocation(agent, prompt, cwd, permissions = 'safe'
         throw new Error('Gemini does not support the reasoningEffort selection');
     if (agent === 'gemini' && parsedSelection.nativeMultiAgent === true)
         throw new Error('Gemini does not support enabling the nativeMultiAgent selection');
+    if (agent === 'qwen' && parsedSelection.bare)
+        throw new Error('Qwen does not support the bare startup selection');
+    if (agent === 'qwen' && parsedSelection.reasoningEffort)
+        throw new Error('Qwen does not support the reasoningEffort selection');
+    if (agent === 'qwen' && parsedSelection.nativeMultiAgent === true)
+        throw new Error('Qwen does not support enabling the nativeMultiAgent selection');
     const args = argsFor(agent, permissions);
     if (output.schemaFile !== undefined || output.jsonSchema !== undefined) {
         if (agent === 'codex' && output.schemaFile && output.jsonSchema === undefined) {