@ljwei-stak/dsh-model-router 0.23.0 → 0.23.1

package/.dsh-plugin/client.js

@@ -4030,6 +4030,26 @@ var STAGE_TEXT = Object.freeze({
 });
 var ACTIVE_JOB_KEY = "dsh-model-router:active-run-job";
 var isJobSnapshot = (value) => Boolean(text2(value?.jobId) && JOB_STATUSES.has(value.status));
+var REMOTE_WAIT_MS = 15e3;
+async function waitForRemote(operation, controllers) {
+  const controller = new AbortController();
+  controllers.add(controller);
+  let timer;
+  try {
+    return await new Promise((resolve, reject) => {
+      controller.signal.onabort = () => {
+        clearTimeout(timer);
+        reject(new Error("\u5DE5\u4F5C\u53F0\u8BF7\u6C42\u7B49\u5F85\u8D85\u65F6\uFF0C\u8BF7\u5728\u8FDE\u63A5\u6062\u590D\u540E\u91CD\u8BD5\u3002"));
+      };
+      timer = setTimeout(() => controller.abort(), REMOTE_WAIT_MS);
+      Promise.resolve(operation(controller.signal)).then(resolve, reject);
+    });
+  } finally {
+    clearTimeout(timer);
+    controller.signal.onabort = null;
+    controllers.delete(controller);
+  }
+}
 function savedJob() {
   try {
     return typeof sessionStorage === "undefined" ? "" : text2(sessionStorage.getItem(ACTIVE_JOB_KEY));
@@ -4084,6 +4104,7 @@ function RunLauncher({ task, mode, directRoute, budgetUsd, defaultPreset, ledger
   const launchSequence = import_react3.default.useRef(0);
   const launching = import_react3.default.useRef(false);
   const awaitingLaunch = import_react3.default.useRef(null);
+  const pendingRemotes = import_react3.default.useRef(/* @__PURE__ */ new Set());
   const onFinished = import_react3.default.useRef(onStarted);
   onFinished.current = onStarted;
   const inputSignature = JSON.stringify([task, mode, directRoute?.provider, directRoute?.model, budgetUsd, runPreset, workspace, lastWorkspace, planningRevision, disabledReason, runExecutor, runMode, runEnvironment, assignmentMode, packagePlanKey2, packageAssignments]);
@@ -4140,6 +4161,8 @@ function RunLauncher({ task, mode, directRoute, budgetUsd, defaultPreset, ledger
     }
     return () => {
       mounted.current = false;
+      for (const controller of pendingRemotes.current) controller.abort();
+      pendingRemotes.current.clear();
       launchListeners.delete(receiveLaunch);
       pendingRequest.current += 1;
       activeRun.current = null;
@@ -4217,7 +4240,7 @@ function RunLauncher({ task, mode, directRoute, budgetUsd, defaultPreset, ledger
       if (disposed || activeRun.current !== active || active.terminal) return;
       const sequence = ++active.requestSequence;
       try {
-        const value = unwrapRemote(await runStatus({ jobId: runningJobId }), "\u6682\u65F6\u65E0\u6CD5\u8BFB\u53D6\u6267\u884C\u8FDB\u5EA6\u3002");
+        const value = unwrapRemote(await waitForRemote((signal) => runStatus({ jobId: runningJobId }, signal), pendingRemotes.current), "\u6682\u65F6\u65E0\u6CD5\u8BFB\u53D6\u6267\u884C\u8FDB\u5EA6\u3002");
         if (disposed) return;
         if (!isJobSnapshot(value) || value.jobId !== runningJobId) throw new Error("\u6682\u65F6\u65E0\u6CD5\u8BFB\u53D6\u6267\u884C\u8FDB\u5EA6\u3002");
         acceptSnapshot(value, active.token, sequence);
@@ -4281,7 +4304,7 @@ function RunLauncher({ task, mode, directRoute, budgetUsd, defaultPreset, ledger
     const signature2 = inputSignature;
     setPhase({ kind: "previewing" });
     try {
-      const value = unwrapRemote(await previewRun(snapshot), "\u6267\u884C\u9884\u89C8\u5931\u8D25\u3002");
+      const value = unwrapRemote(await waitForRemote((signal) => previewRun(snapshot, signal), pendingRemotes.current), "\u6267\u884C\u9884\u89C8\u5931\u8D25\u3002");
       if (mounted.current && current === pendingRequest.current && signature2 === latestSignature.current) setPhase({ kind: "preview", value, request: snapshot, signature: signature2 });
     } catch (error) {
       if (mounted.current && current === pendingRequest.current && signature2 === latestSignature.current) setPhase({ kind: "error", message: text2(error?.message) || "\u6267\u884C\u9884\u89C8\u5931\u8D25\u3002" });
@@ -4342,7 +4365,7 @@ function RunLauncher({ task, mode, directRoute, budgetUsd, defaultPreset, ledger
     const sequence = ++active.requestSequence;
     setPhase((previous) => previous.kind === "running" ? { ...previous, cancelPending: true, cancelError: "" } : previous);
     try {
-      const value = unwrapRemote(await cancelRun({ jobId: active.jobId }), "\u53D6\u6D88\u8BF7\u6C42\u672A\u786E\u8BA4\u3002");
+      const value = unwrapRemote(await waitForRemote((signal) => cancelRun({ jobId: active.jobId }, signal), pendingRemotes.current), "\u53D6\u6D88\u8BF7\u6C42\u672A\u786E\u8BA4\u3002");
       if (!isJobSnapshot(value) || value.jobId !== active.jobId) throw new Error("\u53D6\u6D88\u8BF7\u6C42\u672A\u786E\u8BA4\u3002");
       acceptSnapshot(value, active.token, sequence, true);
     } catch {
@@ -13863,7 +13886,7 @@ var xterm_default = `/**
 `;
 
 // .dsh-plugin/client/host-version.mjs
-var ROUTER_CLIENT_VERSION = true ? "0.23.0" : "";
+var ROUTER_CLIENT_VERSION = true ? "0.23.1" : "";
 var STALE_HOST_MESSAGE = "\u63D2\u4EF6\u540E\u53F0\u7248\u672C\u8F83\u65E7\uFF0C\u8BF7\u5B8C\u5168\u9000\u51FA\u5E76\u91CD\u542F Harness\uFF08\u5305\u62EC\u6258\u76D8\u56FE\u6807\uFF09\u540E\u518D\u4F7F\u7528\u3002";
 function isMissingRemoteMethod(message) {
   const value = String(message ?? "");
@@ -15874,7 +15897,7 @@ var terminalWriteCodec = strictCodec(`${OFFICIAL_TOOLS_REMOTE_PACKAGE}#TerminalW
 var terminalResizeCodec = strictCodec(`${OFFICIAL_TOOLS_REMOTE_PACKAGE}#TerminalResize`, parseTerminalResize);
 var terminalStopCodec = strictCodec(`${OFFICIAL_TOOLS_REMOTE_PACKAGE}#TerminalStop`, parseTerminalStop);
 var runRequestCodec = strictCodec(`${OFFICIAL_TOOLS_REMOTE_PACKAGE}#RunRequest`, parseRunRequest);
-function descriptor(method, parameters, result) {
+function descriptor(method, parameters, result, cancellable = false) {
   return Object.freeze({
     id: `${OFFICIAL_TOOLS_REMOTE_PACKAGE}#${OFFICIAL_TOOLS_REMOTE_NAMESPACE}/${method}`,
     service: OFFICIAL_TOOLS_REMOTE_NAMESPACE,
@@ -15882,7 +15905,8 @@ function descriptor(method, parameters, result) {
     method,
     invocation: { kind: "direct" },
     parameters,
-    result
+    result,
+    ...cancellable ? { cancellation: { parameter: "signal" } } : {}
   });
 }
 var toolIdParameter = Object.freeze({
@@ -15908,10 +15932,10 @@ var OFFICIAL_TOOLS_REMOTE_DESCRIPTORS = Object.freeze([
   descriptor("rerunStep", [jsonParameter("request", rerunRequestCodec)], anyObjectCodec("RerunResult")),
   descriptor("boundaries", [], anyObjectCodec("SecurityBoundaries")),
   // Workbench "start a run": plan preview with cost estimate and confirmation reasons, then execute.
-  descriptor("previewRun", [jsonParameter("request", runRequestCodec)], anyObjectCodec("RunPreview")),
+  descriptor("previewRun", [jsonParameter("request", runRequestCodec)], anyObjectCodec("RunPreview"), true),
   descriptor("startRun", [jsonParameter("request", runRequestCodec)], anyObjectCodec("RunStarted")),
-  descriptor("runStatus", [jsonParameter("request", runJobRequestCodec)], anyObjectCodec("RunJobStatus")),
-  descriptor("cancelRun", [jsonParameter("request", runJobRequestCodec)], anyObjectCodec("RunJobStatus")),
+  descriptor("runStatus", [jsonParameter("request", runJobRequestCodec)], anyObjectCodec("RunJobStatus"), true),
+  descriptor("cancelRun", [jsonParameter("request", runJobRequestCodec)], anyObjectCodec("RunJobStatus"), true),
   // Workbench "官方工具终端": interactive shell / fixed official CLI sessions.
   // Output streams through long-poll reads; input and resize are unary calls.
   descriptor("terminalInfo", [], anyObjectCodec("TerminalInfo")),
@@ -16363,10 +16387,10 @@ function registerUi(ctx) {
       rateResult: (request) => officialToolsRemote.rateResult(request),
       rerunStep: (request) => officialToolsRemote.rerunStep(request),
       loadBoundaries: () => officialToolsRemote.boundaries(),
-      previewRun: (request) => officialToolsRemote.previewRun(request),
+      previewRun: (request, signal) => officialToolsRemote.previewRun(request, signal),
       startRun: (request) => officialToolsRemote.startRun(request),
-      runStatus: (request) => officialToolsRemote.runStatus(request),
-      cancelRun: (request) => officialToolsRemote.cancelRun(request),
+      runStatus: (request, signal) => officialToolsRemote.runStatus(request, signal),
+      cancelRun: (request, signal) => officialToolsRemote.cancelRun(request, signal),
       terminalApi: Object.freeze({
         terminalInfo: () => officialToolsRemote.terminalInfo(),
         terminalStart: (request) => officialToolsRemote.terminalStart(request),

package/.dsh-plugin/index.mjs

@@ -4,7 +4,7 @@ import { homedir } from 'node:os'
 import { isAbsolute } from 'node:path'
 import z from '@deepseek-ai/schemastery'
 import { defineTool } from '@deepseek-ai/dsh-tools'
-import { DEFAULT_ROUTER_SETTINGS, modelMetadata } from './shared/router.mjs'
+import { DEFAULT_ROUTER_SETTINGS, estimateAssignedPackage, modelMetadata } from './shared/router.mjs'
 import { DEFAULT_ROUTING_PRESET, normalizeRoutingPreset, routingPreset } from './shared/routing-presets.mjs'
 import { HEALTH_CACHE_MS, apiKeyEnvPresent, healthCache, runHealthCheck, subscriptionLoginOf } from './shared/tool-health.mjs'
 import { latestVersions } from './shared/latest-versions.mjs'
@@ -995,6 +995,31 @@ export function rerunSupport(run) {
   return { ok: true, kind: run.kind === 'team' ? 'team' : 'assign', writes: false }
 }
 
+/** Estimate exactly the packages a retry will start, retaining unknown prices. */
+function rerunEstimates(run, ids, targetId, override, routes, dataOptions) {
+  const estimates = new Map()
+  for (const item of run.packages.filter(item => ids.has(item.id))) {
+    const assigned = item.id === targetId ? override : null
+    const provider = assigned?.provider ?? item.provider ?? item.recommendedProvider
+    const model = assigned?.model ?? item.model ?? item.recommendedModel
+    const changedRoute = provider !== item.recommendedProvider || model !== item.recommendedModel
+    const reassignsRoute = assigned && (assigned.provider !== (item.provider ?? item.recommendedProvider)
+      || assigned.model !== (item.model ?? item.recommendedModel))
+    let estimate = item.estimatedCost
+    // An unchanged route can retain its planned effort; changing identity uses
+    // the new adapter's default effort, just like rerunAssignmentPackage.
+    if (reassignsRoute || changedRoute) {
+      const route = routes.find(route => route.provider === provider && route.model === model)
+      estimate = route ? estimateAssignedPackage(route, item, run.task,
+        run.decision?.complexity?.band ?? 'balanced', dataOptions).estimatedCost : null
+    }
+    estimates.set(item.id, Number.isFinite(estimate) && estimate >= 0 ? estimate : null)
+  }
+  const values = [...estimates.values()]
+  const total = values.every(value => value !== null) ? values.reduce((sum, value) => sum + value, 0) : null
+  return { byId: estimates, total: Number.isFinite(total) ? total : null }
+}
+
 export async function rerunRecordedStep(ctx, config = {}, { runId, packageId, provider, model, confirmOverBudget = false, confirmWrite = false, confirmUnsandboxed = false, subscriptionChoice = null, workspace, root, signal, ...options } = {}) {
   const { run, saved } = await storedRun(runId)
   const target = run.packages.find(item => item.id === text(packageId))
@@ -1033,16 +1058,17 @@ export async function rerunRecordedStep(ctx, config = {}, { runId, packageId, pr
     return { paused: true, needsConfirmation: missingConfirmations, run,
       budget: null, message: '请确认续跑所需的文件修改与执行环境权限后继续；厂商 CLI 正常环境以当前用户权限运行，独立 Git 工作树不是操作系统读写边界。' }
   }
-  const sameRoute = !override || (override.provider === target.recommendedProvider && override.model === target.recommendedModel)
-  const budget = budgetFor(config, saved, sameRoute ? target.estimatedCost : null)
+  const retryIds = new Set([target.id, ...downstreamPackageIds(run.packages, target.id)
+    .filter(id => run.packages.find(item => item.id === id)?.ok !== true)])
+  const estimates = rerunEstimates(run, retryIds, target.id, override, routes, planDataOptions(refreshed, config))
+  const budget = budgetFor(config, saved, estimates.total)
   if (budget.exceeded && confirmOverBudget !== true) {
     return { paused: true, budget: { ...budget, paused: true, message: `${budget.message} 已暂停重跑，请确认后再试。` }, run }
   }
   const cwd = text(workspace) || run.workspace
   if (!cwd || !(await fileExists(cwd))) throw new Error(`原运行的工作区 ${cwd || '(未记录)'} 不可用，无法重跑该步骤；请恢复该目录，或在原工作区的会话中调用 model_router_rerun_step。`)
-  if (run.kind === 'team') return rerunTeamStep(ctx, { run, target, override, routes, budget, cwd, root: text(root) || cwd, signal, options, config })
-  const retryIds = new Set([target.id, ...downstreamPackageIds(run.packages, target.id)
-    .filter(id => run.packages.find(item => item.id === id)?.ok !== true)])
+  if (run.kind === 'team') return rerunTeamStep(ctx, { run, target, override, routes, budget,
+    ids: [...retryIds], estimates: estimates.byId, cwd, root: text(root) || cwd, signal, options, config })
   const manualRetries = Object.fromEntries(run.packages.filter(item => retryIds.has(item.id) && item.manualAssignment)
     .map(item => [item.id, item.id === target.id && override ? { kind: 'api', ...override } : item.manualAssignment]))
   if (Object.keys(manualRetries).length) {
@@ -1089,6 +1115,9 @@ export async function rerunRecordedStep(ctx, config = {}, { runId, packageId, pr
   })
   const updated = await routerStateStore().updateRun(run.id, current => {
     mergeRerun(current, execution, { rerunIds: execution.ranIds, pricingFor: item => routePricing(routes, item), billingFor: billingForResult })
+    for (const item of current.packages) {
+      if (execution.ranIds.includes(item.id)) item.estimatedCost = estimates.byId.get(item.id) ?? null
+    }
   })
   const awaiting = pausedSteps(execution)
   return { run: updated, execution, budget, ...(awaiting.length ? { awaitingConfirmation: awaiting } : {}) }
@@ -1114,7 +1143,7 @@ async function cancelPausedStep(runId, packageId) {
 }
 
 /** Stored team packages in plan shape; `override` reassigns the retried package. */
-function teamPlanFromRun(run, ids, override, targetId) {
+function teamPlanFromRun(run, ids, override, targetId, estimates) {
   const workPackages = run.packages.filter(item => ids.includes(item.id)).map(item => ({
     id: item.id, name: item.name, objective: item.objective, dependsOn: item.dependsOn ?? [],
     type: item.type ?? 'general', purpose: item.purpose ?? 'execution',
@@ -1124,7 +1153,7 @@ function teamPlanFromRun(run, ids, override, targetId) {
     ...(item.plannedReasoningEffort && !(item.id === targetId && override
       && (override.provider !== item.recommendedProvider || override.model !== item.recommendedModel))
       ? { recommendedReasoningEffort: item.plannedReasoningEffort } : {}),
-    estimatedCost: item.estimatedCost ?? null,
+    estimatedCost: estimates.get(item.id) ?? null,
   }))
   return { mode: 'team', team: { workPackages } }
 }
@@ -1133,13 +1162,10 @@ function teamPlanFromRun(run, ids, override, targetId) {
  * Read-only team retry: the failed step plus downstream steps that had not
  * succeeded run through the same signed runner; earlier answers are context.
  */
-async function rerunTeamStep(ctx, { run, target, override, routes, budget, cwd, root, signal, options, config = {} }) {
+async function rerunTeamStep(ctx, { run, target, override, routes, budget, ids, estimates, cwd, root, signal, options, config = {} }) {
   const mode = run.executionMode === 'workspace-write' ? 'workspace-write' : 'read-only'
   const executionEnvironment = teamExecutionEnvironment(run.executionEnvironment, mode)
-  const downstream = downstreamPackageIds(run.packages, target.id)
-    .filter(id => !run.packages.find(item => item.id === id)?.ok)
-  const ids = [target.id, ...downstream]
-  const plan = teamPlanFromRun(run, ids, override, target.id)
+  const plan = teamPlanFromRun(run, ids, override, target.id, estimates)
   const cliModels = Object.fromEntries(Object.entries(run.cliModels ?? {}).filter(([key]) => ids.includes(key) && !(override && key === target.id)))
   if (override) {
     const reassignedPlan = { team: { workPackages: plan.team.workPackages.filter(item => item.id === target.id) } }
@@ -1166,6 +1192,9 @@ async function rerunTeamStep(ctx, { run, target, override, routes, budget, cwd,
   }
   const updated = await routerStateStore().updateRun(run.id, current => {
     mergeRerun(current, converted, { rerunIds: ids, pricingFor: item => routePricing(routes, item), billingFor: billingForResult })
+    for (const item of current.packages) {
+      if (ids.includes(item.id)) item.estimatedCost = estimates.get(item.id) ?? null
+    }
     for (const [id, note] of quotaNotes) {
       const stored = current.packages.find(item => item.id === id)
       if (stored) stored.billingSwitch = note

package/.dsh-plugin/shared/official-tools-remote.mjs

@@ -205,7 +205,7 @@ const terminalStopCodec = strictCodec(`${OFFICIAL_TOOLS_REMOTE_PACKAGE}#Terminal
 
 const runRequestCodec = strictCodec(`${OFFICIAL_TOOLS_REMOTE_PACKAGE}#RunRequest`, parseRunRequest)
 
-function descriptor(method, parameters, result) {
+function descriptor(method, parameters, result, cancellable = false) {
   return Object.freeze({
     id: `${OFFICIAL_TOOLS_REMOTE_PACKAGE}#${OFFICIAL_TOOLS_REMOTE_NAMESPACE}/${method}`,
     service: OFFICIAL_TOOLS_REMOTE_NAMESPACE,
@@ -214,6 +214,7 @@ function descriptor(method, parameters, result) {
     invocation: { kind: 'direct' },
     parameters,
     result,
+    ...(cancellable ? { cancellation: { parameter: 'signal' } } : {}),
   })
 }
 
@@ -238,10 +239,10 @@ export const OFFICIAL_TOOLS_REMOTE_DESCRIPTORS = Object.freeze([
   descriptor('rerunStep', [jsonParameter('request', rerunRequestCodec)], anyObjectCodec('RerunResult')),
   descriptor('boundaries', [], anyObjectCodec('SecurityBoundaries')),
   // Workbench "start a run": plan preview with cost estimate and confirmation reasons, then execute.
-  descriptor('previewRun', [jsonParameter('request', runRequestCodec)], anyObjectCodec('RunPreview')),
+  descriptor('previewRun', [jsonParameter('request', runRequestCodec)], anyObjectCodec('RunPreview'), true),
   descriptor('startRun', [jsonParameter('request', runRequestCodec)], anyObjectCodec('RunStarted')),
-  descriptor('runStatus', [jsonParameter('request', runJobRequestCodec)], anyObjectCodec('RunJobStatus')),
-  descriptor('cancelRun', [jsonParameter('request', runJobRequestCodec)], anyObjectCodec('RunJobStatus')),
+  descriptor('runStatus', [jsonParameter('request', runJobRequestCodec)], anyObjectCodec('RunJobStatus'), true),
+  descriptor('cancelRun', [jsonParameter('request', runJobRequestCodec)], anyObjectCodec('RunJobStatus'), true),
   // Workbench "官方工具终端": interactive shell / fixed official CLI sessions.
   // Output streams through long-poll reads; input and resize are unary calls.
   descriptor('terminalInfo', [], anyObjectCodec('TerminalInfo')),

package/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## 0.23.1 — 2026-10-23
+
+- Check retry budgets against the target and every unfinished downstream package that will execute. Reassignment uses the selected route estimate; successful downstream packages are excluded and unknown prices remain unknown.
+- Bound workbench preview, progress and cancel requests to 15 seconds, abort stalled transport waits, retry progress against the same job and allow an unacknowledged cancellation to be retried. Never automatically replay task starts.
+- Preserve late-response fences and clear request lifetimes on panel close. Add offline Host budget, real SDK cancellation transport and hung-request UI regressions.
+
+
 ## 0.23.0 — 2026-10-23
 
 - Return an observable Host job when a workbench execution starts. Show elapsed time, the current work package and per-package states, with status reads and cancellation through the typed desktop gateway.

package/README.i18n.yaml

@@ -1,4 +1,4 @@
 # README translation pairing for this repository.
 # Reviewed together; Git blob hashes identify the exact synchronized texts.
-README.md: da3995c07c716f6ac776b93e0753c67afd4e5057
-README.zh.md: fa5f947d45c7473c4ec9fed6670f37b797a39ff5
+README.md: 3bb1e3507fc7451861fb3463f52f68827fb71690
+README.zh.md: 1d15eb0bf9c5ebeac41b74d349b0a709f16288c8

package/README.md

@@ -10,7 +10,7 @@ Want release notes only? Click **Watch → Custom → Releases** (you do not nee
 
 A cost-aware model-routing workbench for **DeepSeek Harness Desktop**. Plan locally, compare configured routes, inspect execution permissions, and run dependent work packages through model APIs or supported official vendor CLIs.
 
-Current version: **0.23.0** (`@ljwei-stak/dsh-model-router`). Workbench execution now shows live elapsed time and per-package progress, supports cancellation with completed results and reported costs retained, and reconnects to the active job when the panel is reopened. Choose algorithm recommendations or manually assign each decomposed package to an exact model API or official tool, preserving dependencies, refreshed cost previews and retry targets. Routing now supports task-specific quality evidence, joint model/effort selection, historical P90 resource estimates and dependency-aware search. Manual mixed execution is read-only; tools use their configured default model, while the existing editable official-team workflow remains available. Compatibility remains **DeepSeek Harness Desktop 0.2.0-rc.1 / 0.2.0-rc.2 / 0.2.1-rc.2**, including Hermes/Pi installation and terminal support; neither has a verified managed runner yet. Real vendor execution evidence remains tied to **0.20.0**, with no new model experiments in this release. The router and [GAL](https://github.com/Alice-Marx/deepseek-harness-galgame) have been independent plugins since 0.12.0.
+Current version: **0.23.1** (`@ljwei-stak/dsh-model-router`). Retries now check the whole unfinished downstream group against the budget, and stalled progress/cancel requests recover after a bounded wait. Workbench execution shows live elapsed time and per-package progress, supports cancellation with completed results and reported costs retained, and reconnects to the active job when the panel is reopened. Choose algorithm recommendations or manually assign each decomposed package to an exact model API or official tool, preserving dependencies, refreshed cost previews and retry targets. Routing now supports task-specific quality evidence, joint model/effort selection, historical P90 resource estimates and dependency-aware search. Manual mixed execution is read-only; tools use their configured default model, while the existing editable official-team workflow remains available. Compatibility remains **DeepSeek Harness Desktop 0.2.0-rc.1 / 0.2.0-rc.2 / 0.2.1-rc.2**, including Hermes/Pi installation and terminal support; neither has a verified managed runner yet. Real vendor execution evidence remains tied to **0.20.0**, with no new model experiments in this release. The router and [GAL](https://github.com/Alice-Marx/deepseek-harness-galgame) have been independent plugins since 0.12.0.
 
 Official CLI teamwork runs packages sequentially with dependency context and no automatic model-directory API fallback. Editable teams explicitly choose the Harness sandbox or the vendor CLI's normal environment. In the latter, Git worktrees collect edits but do not restrict OS access. CLIs retain their configured model unless explicitly mapped. See [real Windows validation and its limits](docs/releases/0.20.0-validation.md).
 
@@ -27,22 +27,22 @@ Both README versions describe the same interfaces, formulas, defaults and limits
 **Install (DSH Plugin Hub / web profile):** With the DSH CLI available, install the published npm package with:
 
 ```sh
-dsh plugin --profile web add @ljwei-stak/dsh-model-router@0.23.0
+dsh plugin --profile web add @ljwei-stak/dsh-model-router@0.23.1
 ```
 
 **Install in Harness Desktop:** Launch Desktop once to initialize its `desktop` profile, quit Desktop fully, then run:
 
 ```sh
-dsh plugin --profile desktop add @ljwei-stak/dsh-model-router@0.23.0
+dsh plugin --profile desktop add @ljwei-stak/dsh-model-router@0.23.1
 ```
 
 You can also paste the package spec into **Harness Desktop → Plugins → Add plugin**. Restart Desktop after installation. A global `npm install -g` by itself does not register a Desktop plugin.
 
-**Package and entry point:** [`@ljwei-stak/dsh-model-router@0.23.0` on npm](https://www.npmjs.com/package/@ljwei-stak/dsh-model-router) is published. The root [`package.json`](package.json) declares the package and bundle patch; [`.dsh-plugin/index.mjs`](.dsh-plugin/index.mjs) exports the required `apply(ctx)` entry point. License: [MIT](LICENSE).
+**Package and entry point:** [`@ljwei-stak/dsh-model-router@0.23.1` on npm](https://www.npmjs.com/package/@ljwei-stak/dsh-model-router) is published. The root [`package.json`](package.json) declares the package and bundle patch; [`.dsh-plugin/index.mjs`](.dsh-plugin/index.mjs) exports the required `apply(ctx)` entry point. License: [MIT](LICENSE).
 
 **Configuration:** There is no supported import of a user-authored JSON/YAML configuration file. Configure providers, models, and credentials on Harness's **Models** page; configure routing profiles and preferences in the plugin settings. Persistent router state is stored in `$DSH_HOME/model-router/state.json` (default: `~/.dsh/model-router/state.json`). Provider CLIs retain their own login and configuration. The router does not copy API keys into model profiles or terminal logs.
 
-**Screenshots and evidence:** The [workbench screenshot](docs/assets/workbench-task-preview.jpg) uses fixture models, prices, and health data; it is a simulated UI preview, not a live Harness or model run. See the [routing workflow diagram](docs/assets/routing-workflow.svg) for the execution flow. The [real Windows validation report](docs/releases/0.20.0-validation.md) documents specific 0.20.0 executions and their limits; 0.23.0 has no verified end-to-end vendor run. The [live progress screenshot](docs/assets/workbench-run-progress.png) is an offline simulation; see the [0.23.0 acceptance report](docs/releases/0.23.0-validation.md) for cancellation, recovery and validation boundaries.
+**Screenshots and evidence:** The [workbench screenshot](docs/assets/workbench-task-preview.jpg) uses fixture models, prices, and health data; it is a simulated UI preview, not a live Harness or model run. See the [routing workflow diagram](docs/assets/routing-workflow.svg) for the execution flow. The [real Windows validation report](docs/releases/0.20.0-validation.md) documents specific 0.20.0 executions and their limits; 0.23.1 has no verified end-to-end vendor run. The [live progress screenshot](docs/assets/workbench-run-progress.png) is an offline simulation; see the [0.23.1 acceptance report](docs/releases/0.23.1-validation.md) for cancellation, recovery and validation boundaries.
 
 **Permissions and risks:** Planning is local and makes no model call. Execution sends the selected task/context to the chosen model API or vendor CLI and may incur charges. The default Harness-restricted environment separates read-only runs from approved `workspace-write` runs. An explicitly selected `cli-native` editable team runs with the current OS user's permissions, outside the Harness process sandbox; a Git worktree collects changes but does not restrict OS access. External providers and CLI services apply their own data handling and billing terms.
 
@@ -78,16 +78,16 @@ Generating a route recommendation is local: it does not start a vendor CLI or ma
 Open **Plugins → Add plugin** and enter:
 
 ```text
-@ljwei-stak/dsh-model-router@0.23.0
+@ljwei-stak/dsh-model-router@0.23.1
 ```
 
-Use the official HTTPS npm source `https://registry.npmjs.org/` when a mirror lacks that exact version. Enable the plugin, then fully quit Harness (including its tray process) and restart it. Plugin details should show **0.23.0** and the sidebar should contain **模型路由** (Model Router). A global `npm install -g` alone does not register a Desktop plugin.
+Use the official HTTPS npm source `https://registry.npmjs.org/` when a mirror lacks that exact version. Enable the plugin, then fully quit Harness (including its tray process) and restart it. Plugin details should show **0.23.1** and the sidebar should contain **模型路由** (Model Router). A global `npm install -g` alone does not register a Desktop plugin.
 
 You can instead install a local `.tgz` archive or its extracted inner `package` directory through the plugin manager. Both must contain `package.json` and `.dsh-plugin`. See [releases](https://github.com/Alice-Marx/dsh-model-router/releases) for archived builds, or build your own checkout below.
 
 ### Upgrade from the old package name
 
-The old name `@ljwei-stak/model-router-galgame` ended at 0.13.0. Remove that plugin entry while retaining your profile/application data, then add `@ljwei-stak/dsh-model-router@0.23.0`. Do not keep both entries installed: they share the internal plugin id `model-router-galgame` and tool names. The retained id lets existing router settings and history carry over.
+The old name `@ljwei-stak/model-router-galgame` ended at 0.13.0. Remove that plugin entry while retaining your profile/application data, then add `@ljwei-stak/dsh-model-router@0.23.1`. Do not keep both entries installed: they share the internal plugin id `model-router-galgame` and tool names. The retained id lets existing router settings and history carry over.
 
 For the combined 0.11.x package, back up the profile and export the GAL saves you want to preserve before upgrading. Story playback, artwork, music and saves now belong to the independent `@ljwei-stak/dsh-galgame` package. The detailed save limitations are in [MIGRATION.md](docs/archive/MIGRATION.md).
 
@@ -119,6 +119,8 @@ Switching tabs keeps the panels mounted, preserving in-progress installation and
 
 After execution starts, the workbench shows elapsed time, the current package and each package's state. **取消执行** requests cancellation of the active call and stops later packages from starting; **正在取消** remains visible until the executor finishes cleanup. Completed results and reported usage remain in history. Cancelling cannot undo charges already incurred or changes already integrated. Closing the panel does not cancel a run; reopening it in the same browser session can reconnect while the Host retains that job. Host restarts clear these in-memory jobs, and completed ledger records remain available.
 
+Preview, progress and cancellation requests stop waiting after 15 seconds. Progress reads retry against the same job; an unacknowledged cancellation can be retried explicitly. A transport timeout does not establish that the Host task stopped and never automatically resubmits `startRun`. Before retrying a recorded step, budget checks include that step and all unfinished downstream packages that will execute; reassignment uses the selected route estimate and unknown prices remain unknown. The [timeout recovery screenshot](docs/assets/workbench-run-timeout.png) is an offline simulation.
+
 Changing task text, planning mode, profiles, directory or relevant settings invalidates the prior recommendation. Changing execution inputs also discards the pending or completed preview, so execution requires a new preview of the current request. Previewing execution uses current Host state and can differ from a previous local plan.
 
 Example task:

package/README.zh.md

@@ -10,7 +10,7 @@
 
 面向 **DeepSeek Harness Desktop** 的成本感知模型路由工作台。在本地规划任务、比较已配置路线、检查执行权限，并通过模型 API 或支持的厂商官方 CLI 执行有依赖关系的工作包。
 
-当前版本：**0.23.0**（`@ljwei-stak/dsh-model-router`）。工作台执行新增实时耗时、逐工作包进度和取消，保留已完成结果与已报告费用；关闭重开面板可接管原任务。支持“按算法推荐分配 / 手动调整分配”：拆分后的工作包可逐个指定模型 API 或官方工具，保留依赖、重新预览费用，并保存重跑目标。同时接入任务相关质量证据、模型与推理档位联合选择、历史资源 P90 估计与依赖感知搜索。手动混合执行当前只读；官方工具使用自身默认模型，原有官方团队编辑流程保留。继续兼容 **DeepSeek Harness Desktop 0.2.0-rc.1 / 0.2.0-rc.2 / 0.2.1-rc.2**，沿用 Hermes/Pi 安装与终端支持；两者仍无经过验证的托管执行器。真实厂商执行证据仍见 **0.20.0** 报告，本版未新增模型实测。路由器与 [GAL](https://github.com/Alice-Marx/deepseek-harness-galgame) 自 0.12.0 起已拆分为独立插件。
+当前版本：**0.23.1**（`@ljwei-stak/dsh-model-router`）。重跑预算现在覆盖实际会执行的未完成下游，进度和取消请求挂起后可恢复。工作台支持实时耗时、逐工作包进度和取消，保留已完成结果与已报告费用；关闭重开面板可接管原任务。支持“按算法推荐分配 / 手动调整分配”：拆分后的工作包可逐个指定模型 API 或官方工具，保留依赖、重新预览费用，并保存重跑目标。同时接入任务相关质量证据、模型与推理档位联合选择、历史资源 P90 估计与依赖感知搜索。手动混合执行当前只读；官方工具使用自身默认模型，原有官方团队编辑流程保留。继续兼容 **DeepSeek Harness Desktop 0.2.0-rc.1 / 0.2.0-rc.2 / 0.2.1-rc.2**，沿用 Hermes/Pi 安装与终端支持；两者仍无经过验证的托管执行器。真实厂商执行证据仍见 **0.20.0** 报告，本版未新增模型实测。路由器与 [GAL](https://github.com/Alice-Marx/deepseek-harness-galgame) 自 0.12.0 起已拆分为独立插件。
 
 官方 CLI 协作按依赖顺序逐包执行、传递依赖上下文，不会自动回退到模型目录 API。可编辑团队需明确选择 Harness 沙箱或厂商 CLI 正常环境。后者通过 Git worktree 收集修改，但不限制操作系统访问。未显式设置模型映射时，各 CLI 沿用自身配置的模型。参见[真实 Windows 验证及其局限](docs/releases/0.20.0-validation.md)。
 
@@ -27,22 +27,22 @@
 **安装（DSH Plugin Hub / web profile）：** 确保 DSH CLI 可用，然后安装已发布的 npm 包：
 
 ```sh
-dsh plugin --profile web add @ljwei-stak/dsh-model-router@0.23.0
+dsh plugin --profile web add @ljwei-stak/dsh-model-router@0.23.1
 ```
 
 **安装到 Harness Desktop：** 首次先启动一次 Desktop 初始化 `desktop` 配置，再彻底退出 Desktop，运行：
 
 ```sh
-dsh plugin --profile desktop add @ljwei-stak/dsh-model-router@0.23.0
+dsh plugin --profile desktop add @ljwei-stak/dsh-model-router@0.23.1
 ```
 
 也可以在 **Harness Desktop → 插件 → 添加插件** 中粘贴包名。安装后重启 Desktop。单独运行全局 `npm install -g` 不会注册 Desktop 插件。
 
-**发布包与入口：** [npm 上的 `@ljwei-stak/dsh-model-router@0.23.0`](https://www.npmjs.com/package/@ljwei-stak/dsh-model-router) 已发布。根目录[`package.json`](package.json)声明包名和 bundle patch；[`.dsh-plugin/index.mjs`](.dsh-plugin/index.mjs)导出所需的 `apply(ctx)` 入口。[许可证：MIT](LICENSE)。
+**发布包与入口：** [npm 上的 `@ljwei-stak/dsh-model-router@0.23.1`](https://www.npmjs.com/package/@ljwei-stak/dsh-model-router) 已发布。根目录[`package.json`](package.json)声明包名和 bundle patch；[`.dsh-plugin/index.mjs`](.dsh-plugin/index.mjs)导出所需的 `apply(ctx)` 入口。[许可证：MIT](LICENSE)。
 
 **配置文件与配置入口：** 当前不支持导入用户编写的 JSON/YAML 配置文件。Provider、模型和凭据在 Harness **模型**页面配置；路由档案与偏好在插件设置中配置。路由器持久状态存于 `$DSH_HOME/model-router/state.json`（默认：`~/.dsh/model-router/state.json`）。Provider CLI 沿用各自的登录和配置；路由器不会把 API 密钥复制进模型档案或终端日志。
 
-**截图与证据：** [工作台截图](docs/assets/workbench-task-preview.jpg)使用固定的模型、价格和健康状态数据，是模拟 UI 预览，不是实时 Harness 或模型运行。[路由流程图](docs/assets/routing-workflow.svg)展示执行路径。[真实 Windows 验证报告](docs/releases/0.20.0-validation.md)记录了 0.20.0 的具体执行及局限；0.23.0 尚无经过验证的端到端厂商运行。[实时进度截图](docs/assets/workbench-run-progress.png)是离线模拟；取消、重开恢复与验证边界见[0.23.0 验收报告](docs/releases/0.23.0-validation.md)。
+**截图与证据：** [工作台截图](docs/assets/workbench-task-preview.jpg)使用固定的模型、价格和健康状态数据，是模拟 UI 预览，不是实时 Harness 或模型运行。[路由流程图](docs/assets/routing-workflow.svg)展示执行路径。[真实 Windows 验证报告](docs/releases/0.20.0-validation.md)记录了 0.20.0 的具体执行及局限；0.23.1 尚无经过验证的端到端厂商运行。[实时进度截图](docs/assets/workbench-run-progress.png)是离线模拟；取消、重开恢复与验证边界见[0.23.1 验收报告](docs/releases/0.23.1-validation.md)。
 
 **权限与风险：** 任务规划在本地完成，不调用模型。实际执行会把选定任务和上下文发送到所选模型 API 或厂商 CLI，并可能产生费用。默认使用 Harness 受限环境；只读运行不修改工作区，`workspace-write` 需要用户明确批准。明确选择 `cli-native` 的可编辑团队会在 Harness 进程沙箱之外，以当前操作系统用户权限运行；Git worktree 只收集修改，不限制操作系统访问。外部 Provider 和 CLI 服务各自适用其数据处理及计费规则。
 
@@ -78,16 +78,16 @@ dsh plugin --profile desktop add @ljwei-stak/dsh-model-router@0.23.0
 打开 **插件 → 添加插件**，输入：
 
 ```text
-@ljwei-stak/dsh-model-router@0.23.0
+@ljwei-stak/dsh-model-router@0.23.1
 ```
 
-镜像缺少该精确版本时，使用官方 HTTPS npm 源 `https://registry.npmjs.org/`。启用插件，然后完全退出 Harness（包括托盘进程）并重启。插件详情应显示 **0.23.0**，侧栏应出现 **模型路由**。仅执行全局 `npm install -g` 不会把插件注册到 Desktop。
+镜像缺少该精确版本时，使用官方 HTTPS npm 源 `https://registry.npmjs.org/`。启用插件，然后完全退出 Harness（包括托盘进程）并重启。插件详情应显示 **0.23.1**，侧栏应出现 **模型路由**。仅执行全局 `npm install -g` 不会把插件注册到 Desktop。
 
 也可以通过插件管理器安装本地 `.tgz` 压缩包，或解压后的内部 `package` 目录。两者都必须包含 `package.json` 和 `.dsh-plugin`。历史构建见 [Releases](https://github.com/Alice-Marx/dsh-model-router/releases)，也可按下文从源码构建。
 
 ### 从旧包名升级
 
-旧名称 `@ljwei-stak/model-router-galgame` 停留在 0.13.0。保留配置档/应用数据，移除旧插件条目，再添加 `@ljwei-stak/dsh-model-router@0.23.0`。不要同时保留两条插件：它们共用内部插件 id `model-router-galgame` 和工具名。保留该 id 能让现有路由设置与历史记录继续使用。
+旧名称 `@ljwei-stak/model-router-galgame` 停留在 0.13.0。保留配置档/应用数据，移除旧插件条目，再添加 `@ljwei-stak/dsh-model-router@0.23.1`。不要同时保留两条插件：它们共用内部插件 id `model-router-galgame` 和工具名。保留该 id 能让现有路由设置与历史记录继续使用。
 
 从合包 0.11.x 升级前，先备份配置档，并导出需要保留的 GAL 存档。剧情播放、立绘、音乐与存档现属于独立的 `@ljwei-stak/dsh-galgame`。详细存档限制见 [MIGRATION.md](docs/archive/MIGRATION.md)。
 
@@ -119,6 +119,8 @@ dsh plugin --profile desktop add @ljwei-stak/dsh-model-router@0.23.0
 
 执行开始后，工作台显示已耗时、当前工作包与每包状态。**取消执行**会请求停止当前调用，并阻止后续工作包启动；执行器完成收尾前持续显示**正在取消**。已完成结果和已报告用量仍保留在历史中。取消不能撤销已经产生的费用或已经整合的改动。关闭面板不会取消执行；同一浏览器会话重新打开后，可在 Host 仍保留该任务时重新连接。Host 重启会清除内存任务，已保存的历史记录仍可查看。
 
+预览、进度和取消请求最长等待 15 秒。进度读取超时后继续查询同一任务；取消未确认时可手动重试。网络等待超时不代表 Host 任务已停止，也不会自动重发 `startRun`。重跑历史步骤前，预算覆盖该步及实际会执行的全部未完成下游；改派使用所选路线估价，未知价格仍保持未知。[超时恢复截图](docs/assets/workbench-run-timeout.png)为离线模拟。
+
 修改任务文本、规划模式、路线配置、目录或相关设置，会使旧建议失效。修改执行输入也会丢弃待确认或已完成的预览，必须对当前请求重新预览。执行预览使用 Host 当前状态，因此可能与先前本地计划不同。
 
 任务示例：

package/docs/WORKBENCH_USER_GUIDE.zh.md

@@ -1,6 +1,6 @@
 # 模型路由工作台：配置、规划与实际执行
 
-适用版本：`@ljwei-stak/dsh-model-router@0.23.0`。声明兼容 DeepSeek Harness Desktop `0.2.0-rc.1 / 0.2.0-rc.2 / 0.2.1-rc.2`。安装与开发见[中文 README](../README.zh.md)，旧包迁移见[迁移说明](archive/MIGRATION.md)。
+适用版本：`@ljwei-stak/dsh-model-router@0.23.1`。声明兼容 DeepSeek Harness Desktop `0.2.0-rc.1 / 0.2.0-rc.2 / 0.2.1-rc.2`。安装与开发见[中文 README](../README.zh.md)，旧包迁移见[迁移说明](archive/MIGRATION.md)。
 
 0.22.0 新增“按算法推荐分配 / 手动调整分配”：生成任务建议后，可为每个工作包选择模型 API 或官方工具；修改后重新预览费用与渠道，再确认执行。任务依赖与重跑目标保留。手动混合执行当前只读，官方工具使用自身默认模型；编辑文件继续选择官方工具协作。详见[手动分配说明](MANUAL_TASK_ASSIGNMENT.zh.md)。Hermes 自定义程序目录、原配置/登录/历史位置，以及工具页顶部终端的行为继续保留。
 
@@ -285,3 +285,5 @@ Windows Codex 在 Harness 环境仅支持只读：其原 `CODEX_HOME` 状态仍
 | 工具名在会话中不可用 | 确认插件启用，重新开始会话；记录宿主/插件版本与脱敏错误。 |
 
 问题反馈请附宿主/插件版本、执行模式、工具状态及脱敏错误，勿提供密钥。源码、安装和资料入口见[中文 README](../README.zh.md)。
+
+执行恢复：预览、进度与取消请求等待超过15秒会终止该次网络等待；进度会重试同一任务，取消未确认可手动重试，任务不会自动重新启动。历史步骤重跑前，预算按目标及未成功的下游步骤合计；整组超限时先确认再运行，改派按所选路线重估，缺失价格不视为零费用。

package/docs/releases/0.23.1-validation.md

@@ -0,0 +1,23 @@
+# 0.23.1 release acceptance
+
+Date: 2026-10-23. Package: `@ljwei-stak/dsh-model-router@0.23.1`.
+
+## Reproduced problems and fixes
+
+- A retry could pass a daily budget of USD 0.5 with a USD 0.2 target, then also start its USD 0.4 downstream package without approval. Retry budgets now cover the target plus every unfinished downstream package that will execute. Both routed and official-team retries use that same set; completed downstream packages are excluded. Changed routes use the selected route estimate, unchanged routes retain their planned reasoning effort estimate and unknown prices remain unknown under the existing unknown-price budget policy.
+- A never-settling progress request permanently stopped polling; a never-settling cancel request permanently disabled the cancel button. Preview/progress/cancel now have a 15-second deadline and a real SDK transport AbortSignal outside the business JSON. Progress retries use the same job, cancellation can be retried explicitly and late replies cannot replace newer state. Task starts are never automatically replayed.
+
+## Validation
+
+- Full suite: 1055 tests, 1052 passed, 0 failed, 3 existing platform-dependent skips.
+- Twenty new regressions: 11 offline Host retry-budget tests, 6 actual SDK transport tests and 3 hung-request UI tests. Budget rejection asserts zero model calls; approval, transitive downstream, completed-package exclusion, reassignment, planned effort and unknown prices are covered.
+- Strict frozen pnpm installation, actual client build, generated-client consistency, README translation/formula checks, workbench preview compilation, npm dry-run and diff checks passed. Formula content was not changed.
+- Actual workbench browser inspection with the offline hanging-request scenario confirmed resumed package progress after a stalled status read, a re-enabled cancel button with explicit failure feedback, and successful retry cancellation with completed results retained. Browser warning/error logs were empty. The [timeout screenshot](../assets/workbench-run-timeout.png) is simulated, with no model, credentials or real workspace access.
+- An independent GPT review checked estimate/actual-retry set consistency, reasoning effort, unknown prices, SDK signal wiring, cleanup and late-response fences.
+- Every packaged file is checked against the exact release commit's Git blobs; npm and GitHub Release assets are anonymously downloaded for byte comparison, with digests in the external publication audit.
+
+## Boundaries
+
+A transport deadline only stops waiting for the request. It does not prove that a cancellation reached Host or that the task stopped; the UI keeps the original job and checks status. Execution/cancellation cleanup can exceed 15 seconds, and a pending start is not retried automatically. Jobs remain in Host memory and do not survive a Host restart. Reported costs already incurred remain chargeable.
+
+No real paid-provider or vendor CLI inference or installed-DSH end-to-end acceptance was performed in this patch. Prior execution evidence remains dated in the [0.20.0 report](0.20.0-validation.md). Fully quit Harness, including tray/Host processes, update the plugin, then restart.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ljwei-stak/dsh-model-router",
-  "version": "0.23.0",
+  "version": "0.23.1",
   "type": "module",
   "description": "Model Router for official DeepSeek Harness Desktop: cost-aware task routing, dependent work packages and official vendor CLI discovery, installation and execution. GAL is available separately as @ljwei-stak/dsh-galgame.",
   "repository": {
@@ -104,7 +104,9 @@
     "docs/MANUAL_TASK_ASSIGNMENT.zh.md",
     "docs/releases/0.22.0-validation.md",
     "docs/releases/0.23.0-validation.md",
-    "docs/assets/workbench-run-progress.png"
+    "docs/assets/workbench-run-progress.png",
+    "docs/releases/0.23.1-validation.md",
+    "docs/assets/workbench-run-timeout.png"
   ],
   "scripts": {
     "build:client": "node scripts/build-client.mjs",
@@ -116,7 +118,7 @@
     "experiment:routing-summary": "node scripts/summarize-routing-search.mjs",
     "experiment:routing-adaptive": "node scripts/adaptive-routing-study.mjs",
     "audit:livebench": "node scripts/livebench-aggregate-audit.mjs",
-    "test": "node scripts/check-readme.mjs && node --test tests/adaptive-*.test.mjs tests/dynamic-data.test.mjs tests/router.test.mjs tests/routing-optimizer.test.mjs tests/routing-evaluation.test.mjs tests/routing-paired-statistics.test.mjs tests/routing-selftest-tools.test.mjs tests/livebench-aggregate-audit.test.mjs tests/livebench-prior-study.test.mjs tests/routing-search-experiment.test.mjs tests/routing-regression-study.test.mjs tests/routing-search-summary.test.mjs tests/harness-*.test.mjs tests/official-tools.test.mjs tests/official-tool-result.test.mjs tests/native-environment.test.mjs tests/native-entry-trust.test.mjs tests/tool-failure-ledger.test.mjs tests/official-team-runtime.test.mjs tests/model-profiles.test.mjs tests/model-profile-editor.test.mjs tests/tool-install-state.test.mjs tests/tool-install-sdk-ui.test.mjs tests/vendor-adapters.test.mjs tests/desktop-compat.test.mjs tests/plugin-split.test.mjs tests/install-settings-host.test.mjs tests/task-executors.test.mjs tests/tool-install-preferences.test.mjs tests/roadmap.test.mjs tests/insights-state.test.mjs tests/billing-team-ledger.test.mjs tests/subscription-billing.test.mjs tests/subscription-host.test.mjs tests/test-pass-regressions.test.mjs tests/roadmap-gaps.test.mjs tests/cordis-inject.test.mjs tests/cli-terminal.test.mjs tests/cli-terminal-gateway.test.mjs tests/latest-versions.test.mjs tests/vendor-installer-validation.test.mjs tests/install-entry-selection.test.mjs tests/script-directory-safety.test.mjs tests/zcode-config.test.mjs tests/zcode-runtime.test.mjs tests/client-loader.test.mjs tests/hermes-pi.test.mjs tests/effort-execution.test.mjs tests/routing-evidence.test.mjs tests/routing-query-effort.test.mjs tests/routing-search-frontier.test.mjs tests/quality-gates.test.mjs tests/algorithm-host-integration.test.mjs tests/quality-attempt-ledger.test.mjs tests/manual-package-execution.test.mjs tests/manual-plan.test.mjs tests/manual-assignment-ui.test.mjs tests/manual-assignment-host.test.mjs tests/readme-math.test.mjs tests/run-jobs.test.mjs tests/run-progress-host.test.mjs tests/run-progress-ui.test.mjs tests/execution-progress.test.mjs",
+    "test": "node scripts/check-readme.mjs && node --test tests/adaptive-*.test.mjs tests/dynamic-data.test.mjs tests/router.test.mjs tests/routing-optimizer.test.mjs tests/routing-evaluation.test.mjs tests/routing-paired-statistics.test.mjs tests/routing-selftest-tools.test.mjs tests/livebench-aggregate-audit.test.mjs tests/livebench-prior-study.test.mjs tests/routing-search-experiment.test.mjs tests/routing-regression-study.test.mjs tests/routing-search-summary.test.mjs tests/harness-*.test.mjs tests/official-tools.test.mjs tests/official-tool-result.test.mjs tests/native-environment.test.mjs tests/native-entry-trust.test.mjs tests/tool-failure-ledger.test.mjs tests/official-team-runtime.test.mjs tests/model-profiles.test.mjs tests/model-profile-editor.test.mjs tests/tool-install-state.test.mjs tests/tool-install-sdk-ui.test.mjs tests/vendor-adapters.test.mjs tests/desktop-compat.test.mjs tests/plugin-split.test.mjs tests/install-settings-host.test.mjs tests/task-executors.test.mjs tests/tool-install-preferences.test.mjs tests/roadmap.test.mjs tests/insights-state.test.mjs tests/billing-team-ledger.test.mjs tests/subscription-billing.test.mjs tests/subscription-host.test.mjs tests/test-pass-regressions.test.mjs tests/roadmap-gaps.test.mjs tests/cordis-inject.test.mjs tests/cli-terminal.test.mjs tests/cli-terminal-gateway.test.mjs tests/latest-versions.test.mjs tests/vendor-installer-validation.test.mjs tests/install-entry-selection.test.mjs tests/script-directory-safety.test.mjs tests/zcode-config.test.mjs tests/zcode-runtime.test.mjs tests/client-loader.test.mjs tests/hermes-pi.test.mjs tests/effort-execution.test.mjs tests/routing-evidence.test.mjs tests/routing-query-effort.test.mjs tests/routing-search-frontier.test.mjs tests/quality-gates.test.mjs tests/algorithm-host-integration.test.mjs tests/quality-attempt-ledger.test.mjs tests/manual-package-execution.test.mjs tests/manual-plan.test.mjs tests/manual-assignment-ui.test.mjs tests/manual-assignment-host.test.mjs tests/readme-math.test.mjs tests/run-jobs.test.mjs tests/run-progress-host.test.mjs tests/run-progress-ui.test.mjs tests/execution-progress.test.mjs tests/rerun-budget-host.test.mjs tests/run-progress-transport.test.mjs",
     "prepack": "node scripts/prepack.mjs",
     "pack:local": "npm pack --pack-destination dist",
     "test:routing-algorithm": "node --test tests/effort-execution.test.mjs tests/routing-evidence.test.mjs tests/routing-query-effort.test.mjs tests/routing-search-frontier.test.mjs tests/quality-gates.test.mjs tests/algorithm-host-integration.test.mjs tests/quality-attempt-ledger.test.mjs",