@hecer/yoke 1.11.0 → 1.12.0

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/qwen-rtk-hook.mjs

@@ -0,0 +1,25 @@
+#!/usr/bin/env node
+// PreToolUse guard requesting a retry through RTK. 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 !== 'PreToolUse')) 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: { hookEventName: 'PreToolUse', permissionDecision: 'deny', permissionDecisionReason: `Retry this command through RTK: rtk ${rewritten}` } }
+    }
+  }
+  process.stdout.write(JSON.stringify(response) + '\n')
+} catch {
+  process.stderr.write('Invalid Qwen PreToolUse hook input\n')
+  process.exitCode = 2
+}

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/host.js

@@ -7,7 +7,7 @@ export function detectHostAgent(env = process.env) {
         return 'claude';
     if (env.GEMINI_CLI)
         return 'gemini';
-    if (env.QWEN_CLI)
+    if (env.QWEN_CODE || env.QWEN_CODE_SESSION_ID || env.QWEN_CLI)
         return 'qwen';
     if (env.CODEX_HOME)
         return 'codex';

package/dist/agents/providers.js

@@ -17,12 +17,12 @@ 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
+    // Qwen Code uses its own approval modes and native tool exclusions.
     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'];
+        const approval = permissions === 'read-only' ? 'plan' : 'auto-edit';
+        return ['--approval-mode', approval, '--sandbox', '--output-format', 'stream-json', ...(permissions === 'safe' ? ['--allowed-tools', 'run_shell_command'] : [])];
     }
     if (permissions === 'unsafe')
         return ['--yolo', '--output-format', 'stream-json'];
@@ -59,8 +59,18 @@ export function buildProviderInvocation(agent, prompt, cwd, permissions = 'safe'
         else
             throw new Error(`${agent} structured output schema requires ${agent === 'codex' ? 'schemaFile' : agent === 'claude' ? 'jsonSchema' : 'a supported native schema option (unavailable)'}`);
     }
-    if (parsedSelection.model)
-        args.push('--model', parsedSelection.model);
+    if (parsedSelection.model) {
+        const qualified = agent === 'qwen' && parsedSelection.model.includes('::')
+            ? parsedSelection.model.match(/^(openai|anthropic|gemini|vertex-ai|qwen-oauth)::(.+)$/u) : undefined;
+        if (agent === 'qwen' && parsedSelection.model.includes('::') && !qualified)
+            throw Error('Invalid Qwen auth/model selector');
+        if (qualified) {
+            const model = ModelSelectionSchema.shape.model.parse(qualified[2]);
+            args.push('--auth-type', qualified[1], '--model', model);
+        }
+        else
+            args.push('--model', parsedSelection.model);
+    }
     if (parsedSelection.reasoningEffort) {
         if (agent === 'claude')
             args.push('--effort', parsedSelection.reasoningEffort);
@@ -71,6 +81,9 @@ export function buildProviderInvocation(agent, prompt, cwd, permissions = 'safe'
         args.push('--disable', 'multi_agent');
     if (agent === 'claude' && parsedSelection.nativeMultiAgent === false)
         args.push('--disallowedTools', 'Agent', 'Task', 'TeamCreate', 'SendMessage');
+    if (agent === 'qwen' && parsedSelection.nativeMultiAgent === false) {
+        args.push('--exclude-tools', 'agent', 'task', 'create_sub_session', 'team_create', 'send_message');
+    }
     if (parsedSelection.bare) {
         if (agent === 'codex')
             args.push('--ignore-user-config');

package/dist/agents/telemetry.js

@@ -22,6 +22,8 @@ export function parseProviderResult(agent, output) {
         if (direct !== undefined)
             return direct;
     }
+    if (agent === 'qwen')
+        return parseQwenResult(output);
     const fragments = [];
     for (const line of output.split(/\r?\n/u)) {
         const parsed = parseJson(line);
@@ -45,10 +47,6 @@ export function parseProviderResult(agent, output) {
                 if (event.type === 'message' && event.role === 'assistant' && typeof event.content === 'string')
                     fragments.push(event.content);
                 break;
-            case 'qwen':
-                if (event.type === 'message' && event.role === 'assistant' && typeof event.content === 'string')
-                    fragments.push(event.content);
-                break;
         }
     }
     const joined = parseJson(fragments.join(''));
@@ -67,6 +65,34 @@ export function parseProviderResult(agent, output) {
     }
     return null;
 }
+/** Qwen uses assistant content blocks and result envelopes, not Gemini messages. */
+function parseQwenResult(output) {
+    let candidate = null;
+    for (const line of output.split(/\r?\n/u)) {
+        const parsed = parseJson(line);
+        if (!parsed.ok || !isRecord(parsed.value))
+            continue;
+        const event = parsed.value;
+        if (event.parent_tool_use_id != null)
+            continue;
+        if (event.type === 'result') {
+            if (event.is_error === true) {
+                candidate = null;
+                continue;
+            }
+            const structured = directMachineResult(event.structured_result);
+            const result = typeof event.result === 'string' ? parseJson(event.result) : { ok: false };
+            candidate = structured ?? (result.ok ? directMachineResult(result.value) : undefined) ?? null;
+        }
+        else if (event.type === 'assistant' && isRecord(event.message) && Array.isArray(event.message.content)) {
+            const text = event.message.content.filter(isRecord).filter(part => part.type === 'text' && typeof part.text === 'string').map(part => part.text).join('');
+            const result = parseJson(text);
+            if (result.ok)
+                candidate = directMachineResult(result.value) ?? candidate;
+        }
+    }
+    return candidate;
+}
 export function parseProviderTelemetry(agent, lines) {
     let inputTokens;
     let cachedInputTokens;
@@ -87,6 +113,8 @@ export function parseProviderTelemetry(agent, lines) {
         if (!parsed || typeof parsed !== 'object' || Array.isArray(parsed))
             continue;
         const event = parsed;
+        if (agent === 'qwen' && event.parent_tool_use_id != null)
+            continue;
         const message = event.message && typeof event.message === 'object' ? event.message : undefined;
         const stats = event.stats && typeof event.stats === 'object' ? event.stats : undefined;
         const usage = (event.usage && typeof event.usage === 'object'
@@ -105,41 +133,12 @@ export function parseProviderTelemetry(agent, lines) {
         // Older JSON stats only provide model-local token objects. Sum a field
         // only when every model measured it; a missing measurement is not zero.
         let source = usage ?? nestedModelTokens ?? modelUsage;
-        if (agent === 'gemini' && modelEntries.length > 0) {
-            reportedModels = modelEntries.map(([name]) => name);
-            model = firstModel?.[0];
-            const fields = {
-                input_tokens: ['input_tokens', 'inputTokens', 'promptTokenCount', 'input'],
-                output_tokens: ['output_tokens', 'outputTokens', 'candidatesTokenCount', 'output'],
-                cached_input_tokens: ['cached_input_tokens', 'cachedInputTokens', 'cachedContentTokenCount', 'cached'],
-                reasoning_output_tokens: ['reasoning_output_tokens', 'reasoningOutputTokens', 'thoughtsTokenCount', 'thoughts'],
-            };
-            const totals = {};
-            for (const [field, aliases] of Object.entries(fields)) {
-                const aggregate = aliases.map(key => finite(usage?.[key])).find(value => value !== undefined);
-                if (aggregate !== undefined) {
-                    totals[field] = aggregate;
-                    continue;
-                }
-                const values = modelEntries.map(([, value]) => {
-                    const entry = isRecord(value) ? value : {};
-                    const tokens = isRecord(entry.tokens) ? entry.tokens : entry;
-                    return aliases.map(key => finite(tokens[key])).find(value => value !== undefined);
-                });
-                if (values.every(value => value !== undefined))
-                    totals[field] = values.reduce((sum, value) => sum + value, 0);
-            }
-            source = { ...totals, ...usage };
-            const aggregateCached = finite(usage?.cached_input_tokens ?? usage?.cached);
-            if (aggregateCached !== undefined)
-                source.cached_input_tokens = aggregateCached;
-        }
-        if (agent === 'qwen' && modelEntries.length > 0) {
+        if ((agent === 'gemini' || agent === 'qwen') && modelEntries.length > 0) {
             reportedModels = modelEntries.map(([name]) => name);
             model = firstModel?.[0];
             const fields = {
-                input_tokens: ['input_tokens', 'inputTokens', 'promptTokenCount', 'input'],
-                output_tokens: ['output_tokens', 'outputTokens', 'candidatesTokenCount', 'output'],
+                input_tokens: ['input_tokens', 'inputTokens', 'promptTokenCount', 'input', 'prompt'],
+                output_tokens: ['output_tokens', 'outputTokens', 'candidatesTokenCount', 'output', 'candidates'],
                 cached_input_tokens: ['cached_input_tokens', 'cachedInputTokens', 'cachedContentTokenCount', 'cached'],
                 reasoning_output_tokens: ['reasoning_output_tokens', 'reasoningOutputTokens', 'thoughtsTokenCount', 'thoughts'],
             };

package/dist/cli.js

@@ -1,4 +1,5 @@
 #!/usr/bin/env node
+import { MODEL_PROVIDERS } from './setup/model-presets.js';
 import { pathToFileURL } from 'node:url';
 import { realpathSync } from 'node:fs';
 import { checkProject, checkExitCode, protectAcceptance } from './check/command.js';
@@ -114,7 +115,7 @@ export function main(argv) {
             const agentTokens = agentArg === 'all' ? valid : agentArg?.split(',').map(a => a.trim());
             const invalidAgents = agentTokens?.filter(a => !valid.includes(a)) ?? [];
             if (agentArg && (invalidAgents.length > 0 || agentTokens?.length === 0)) {
-                console.error(`Invalid --agent value: ${agentArg} (expected claude,codex,gemini|all)`);
+                console.error(`Invalid --agent value: ${agentArg} (expected claude,codex,gemini,qwen|all)`);
                 return 1;
             }
             const agents = agentTokens ? [...new Set(agentTokens)] : undefined;
@@ -140,7 +141,14 @@ export function main(argv) {
                 console.error('Invalid routing strategy');
                 return 1;
             }
+            const modelProviderArg = rest.find(a => a.startsWith('--model-provider='))?.slice('--model-provider='.length);
+            const modelProviders = modelProviderArg?.split(',').map(value => value.trim());
+            if (modelProviders?.some(value => !MODEL_PROVIDERS.includes(value))) {
+                console.error('Invalid --model-provider (expected deepseek,kimi)');
+                return 1;
+            }
             return runSetup(targetDir, {
+                modelProviders: modelProviders,
                 host: hostArg, agents, runner: runnerArg,
                 codeGraph: graphArg,
                 loop, routing, decisionPolicy: policyArg,
@@ -479,7 +487,7 @@ export function main(argv) {
                 let reviewer;
                 if (reviewerArg) {
                     if (!valid.includes(reviewerArg)) {
-                        console.error(`Invalid --reviewer value: ${reviewerArg} (expected claude|codex|gemini)`);
+                        console.error(`Invalid --reviewer value: ${reviewerArg} (expected claude|codex|gemini|qwen)`);
                         return 1;
                     }
                     reviewer = reviewerArg;
@@ -522,13 +530,13 @@ export function main(argv) {
                 }
                 return runLoopCommand(targetDir, { maxIterations: rawMax, agent, isolate, resumeWorktree: rest.includes('--resume-worktree'), parallel, parallelAuto: parallelArg === '--parallel=auto', reviewer, review, allowSelfReview, timeoutMinutes, json, routing, onAmbiguity: oaArg, decisionPolicy: dpArg, permissions, ...qualityFlags.options });
             }
-            console.log('usage: yoke loop <on|off|status|decision|answer|resume [--discard] [--quality|--no-quality] [--quality-rounds=N] [--quality-minutes=N] [--quality-policy=<blocking|advisory>] [--quality-unbounded] [--candidates=N]|cleanup [--remove-worktrees] [--discard-stale-recovery]|run [--max=N] [--parallel=<auto|N>] [--runner=<claude|codex|gemini>] [--reviewer=<claude|codex|gemini>] [--review] [--allow-self-review] [--routing|--no-routing] [--isolate|--no-isolate] [--unsafe] [--timeout=<minutes>] [--decision-policy=<auto|critical>] [--quality|--no-quality] [--quality-rounds=N] [--quality-minutes=N] [--quality-policy=<blocking|advisory>] [--quality-unbounded] [--candidates=N] [--json]> [targetDir]');
+            console.log('usage: yoke loop <on|off|status|decision|answer|resume [--discard] [--quality|--no-quality] [--quality-rounds=N] [--quality-minutes=N] [--quality-policy=<blocking|advisory>] [--quality-unbounded] [--candidates=N]|cleanup [--remove-worktrees] [--discard-stale-recovery]|run [--max=N] [--parallel=<auto|N>] [--runner=<claude|codex|gemini|qwen>] [--reviewer=<claude|codex|gemini|qwen>] [--review] [--allow-self-review] [--routing|--no-routing] [--isolate|--no-isolate] [--unsafe] [--timeout=<minutes>] [--decision-policy=<auto|critical>] [--quality|--no-quality] [--quality-rounds=N] [--quality-minutes=N] [--quality-policy=<blocking|advisory>] [--quality-unbounded] [--candidates=N] [--json]> [targetDir]');
             return 1;
         }
         case 'new': {
             const dir = rest.find(a => !a.startsWith('-'));
             if (!dir) {
-                console.error('usage: yoke new <dir> [--idea="..."] [--agent=claude,codex,gemini|all] [--runner=<claude|codex|gemini>] [--loop]');
+                console.error('usage: yoke new <dir> [--idea="..."] [--agent=claude,codex,gemini,qwen|all] [--runner=<claude|codex|gemini|qwen>] [--loop]');
                 return 1;
             }
             const idea = rest.find(a => a.startsWith('--idea='))?.slice('--idea='.length);
@@ -543,7 +551,7 @@ export function main(argv) {
             }
             const runnerArg = rest.find(a => a.startsWith('--runner='))?.slice('--runner='.length);
             if (runnerArg && !all.includes(runnerArg)) {
-                console.error(`Invalid --runner value: ${runnerArg} (expected claude|codex|gemini)`);
+                console.error(`Invalid --runner value: ${runnerArg} (expected claude|codex|gemini|qwen)`);
                 return 1;
             }
             return runNew(dir, { idea, agents, runner: runnerArg, loop });
@@ -562,7 +570,7 @@ export function main(argv) {
             if (sub === 'draft') {
                 const idea = rest.find(a => a.startsWith('--idea='))?.slice('--idea='.length);
                 if (!idea) {
-                    console.error('usage: yoke prd draft [dir] --idea="..." [--runner=<claude|codex|gemini>] [--force] [--timeout=<minutes>]');
+                    console.error('usage: yoke prd draft [dir] --idea="..." [--runner=<claude|codex|gemini|qwen>] [--force] [--timeout=<minutes>]');
                     return 1;
                 }
                 const valid = ['claude', 'codex', 'gemini', 'qwen'];
@@ -586,7 +594,7 @@ export function main(argv) {
             }
             if (sub === 'check')
                 return runPrdCheck(targetDir);
-            console.log('usage: yoke prd <draft|check|assess> [dir] [--idea="..."] [--runner=<claude|codex|gemini>] [--story=<id>] [--reassess] [--force] [--timeout=<minutes>]');
+            console.log('usage: yoke prd <draft|check|assess> [dir] [--idea="..."] [--runner=<claude|codex|gemini|qwen>] [--story=<id>] [--reassess] [--force] [--timeout=<minutes>]');
             return 1;
         }
         case 'context': {
@@ -601,10 +609,10 @@ export function main(argv) {
         }
         case 'review': {
             const targetDir = rest.find(a => !a.startsWith('-')) ?? '.';
-            const valid = ['claude', 'codex', 'gemini'];
+            const valid = ['claude', 'codex', 'gemini', 'qwen'];
             const reviewerArg = rest.find(a => a.startsWith('--reviewer='))?.slice('--reviewer='.length);
             if (reviewerArg && !valid.includes(reviewerArg)) {
-                console.error(`Invalid --reviewer value: ${reviewerArg} (expected claude|codex|gemini)`);
+                console.error(`Invalid --reviewer value: ${reviewerArg} (expected claude|codex|gemini|qwen)`);
                 return 1;
             }
             const base = rest.find(a => a.startsWith('--base='))?.slice('--base='.length);
@@ -651,7 +659,7 @@ export function main(argv) {
             return runUpgrade();
         default:
             console.log('Project workflows: yoke check [dir] [--json|--protect] | goal set|run|resume|pause|status|handoff|budget [dir] | projects add|list|remove | dashboard [dir] [--port=N]');
-            console.log('usage: yoke <setup [dir] | new <dir> [--idea="..."] | validate [canonDir] | retrofit [targetDir] [--agent=claude,codex,gemini|all] [--code-graph=graphify|serena] [--loop] | change <add|status> [dir] | prd <draft|check|assess> [dir] | loop <on|off|status|decision|answer|resume|run|cleanup> | context <init|status> | review [dir] [--reviewer=<claude|codex|gemini>] [--base=<ref>] [--focus="..."] | design-scan [dir] [--max=N] [--report] | flow-smoke [dir] [--url=<baseUrl>] [--label=<name>] | upgrade>');
+            console.log('usage: yoke <setup [dir] | new <dir> [--idea="..."] | validate [canonDir] | retrofit [targetDir] [--agent=claude,codex,gemini,qwen|all] [--code-graph=graphify|serena] [--loop] | change <add|status> [dir] | prd <draft|check|assess> [dir] | loop <on|off|status|decision|answer|resume|run|cleanup> | context <init|status> | review [dir] [--reviewer=<claude|codex|gemini|qwen>] [--base=<ref>] [--focus="..."] | design-scan [dir] [--max=N] [--report] | flow-smoke [dir] [--url=<baseUrl>] [--label=<name>] | upgrade>');
             return cmd ? 1 : 0;
     }
 }