Refresh benchmark integration baseline from current main

.github/GOVERNANCE.md

@@ -322,12 +322,12 @@ voluntary: anyone may decline, narrow, pause, or hand back a scope without
 losing attribution for their work. Silence is not acceptance or approval.
 
 Status reflects accepted scopes and follow-up invitations in #4069 through
-2026-10-22. The last column says what still separates each contact from a `CODEOWNERS` route under the
+2026-10-24. The last column says what still separates each contact from a `CODEOWNERS` route under the
 [eligibility rule](#code-owner-eligibility).
 
 | Surface | Contact | Responsibility / status | Path to a code-owner route |
 | --- | --- | --- | --- |
-| Chat/runtime session lifecycle | [`@Duang777`](https://github.com/Duang777) | Accepted 2026-09-08: managed-session resume/submit/close, request idempotency, focused regressions and follow-up fixes. Shared goal, quota, lease and permission contracts remain outside this assignment. | Has write access and an accepted scope; needs three qualifying in-scope cross-author reviews. |
+| Chat/runtime session lifecycle and cohesive Host recovery | [`@Duang777`](https://github.com/Duang777) | Initial session scope accepted 2026-09-08; [expanded and accepted 2026-10-24](https://github.com/loopx-project/loopx/issues/4069#issuecomment-6377902612): first-review contact for resume/submit/close, request idempotency, focused regressions and follow-up maintenance, including Host/recovery surfaces within the same session boundary. Best-effort availability, no fixed SLA; will state on the PR when unavailable. Shared goal/quota/lease policy, canonical-authority promotion, provider activation, release and bypass decisions remain outside this scope. | Write remains active. No Maintain or code-owner change requested or granted; any future route still needs the existing qualifying cross-author reviews and a separate appointment PR. |
 | Shared goal authority qualification | [`@wchwawa`](https://github.com/wchwawa) | Accepted 2026-09-08: implementation review, writer/cursor recovery evidence and bounded qualification. Canonical-authority promotion, provider activation and shared-state policy require separate lead-maintainer review. | Has write access and an accepted scope; needs three in-scope cross-author reviews. |
 | Windows runtime correctness | [`@BigDataDZ`](https://github.com/BigDataDZ) | Accepted 2026-10-12: Python CLI Windows paths/encoding, filesystem behavior and native repro-first test qualification; best-effort availability and stated recusals retained. | Bounded Windows code-owner route recorded above; shared semantic and CI-policy decisions remain with existing owners. |
 | Usage and host usage ingestion | [`@liubf21`](https://github.com/liubf21) | Invited to coordinate usage correctness and historical-data compatibility review; no acceptance recorded. Pricing policy and unrelated host/session authority remain outside this scope. | Has write access; needs scope acceptance and in-scope reviews. |

apps/presentation/dashboard/package.json

@@ -98,7 +98,7 @@
     "recharts": "^3.8.1",
     "tailwind-merge": "^3.6.0",
     "tailwindcss": "^4.3.0",
-    "zod": "^4.4.3"
+    "zod": "^4.6.6"
   },
   "devDependencies": {
     "@types/react": "^19.2.15",

apps/presentation/dashboard/src/data/chat.ts

@@ -2630,6 +2630,14 @@ const privateConversationSchema = z.object({
       goal_active: z.boolean().optional(), monitor: z.object({todo_id: z.string(), status: z.string(),
         cadence_minutes: z.number().int().nullable(), next_due_at: z.string().nullable(),
         last_checked_at: z.string().nullable()}).nullable().optional(),
+      report: z.discriminatedUnion("available", [
+        z.object({available: z.literal(true), enabled: z.boolean(), configured: z.boolean(),
+          schedule: z.record(z.string(), z.unknown()).nullable().optional(), next_due_at: z.string().nullable().optional(),
+          retained_window_due_at: z.string().nullable().optional(), generation_id: z.string().nullable().optional(),
+          delivery_status: z.string().optional(), publication_verified: z.boolean().optional(),
+          destination: z.string().optional()}),
+        z.object({available: z.literal(false), error_code: z.string()}),
+      ]).optional(),
       goal_id: z.string().optional(), agent_id: z.string().optional(), session_id: z.string().optional()}),
     z.object({available: z.literal(false), error_code: z.string()}),
   ]).optional(),
@@ -2695,6 +2703,21 @@ export async function changePrivateAgentTarget(bindingId: string, revision: numb
   }));
 }
 
+const stewardReportPlanSchema = z.object({ok: z.literal(true), applied: z.boolean(), stop_status: z.string().optional(), plan: z.object({
+  schema_version: z.literal("loopx_steward_report_plan_v0"), plan_id: z.string().regex(/^[a-f0-9]{64}$/),
+})});
+export async function configureStewardReport(bindingId: string, operation: "enable" | "pause" | "cancel", schedule?: Record<string, unknown>) {
+  const path = "/api/chat/lark/private-conversations/managed-steward/report";
+  const send = (body: unknown) => requestJson<unknown>(path, {method: "POST",
+    headers: {"Content-Type": "application/json"}, body: JSON.stringify(body)});
+  const request = {binding_id: bindingId, operation, ...(operation === "enable" ? {schedule} : {})};
+  const preview = stewardReportPlanSchema.parse(await send({...request, execute: false}));
+  const applied = stewardReportPlanSchema.parse(await send({...request, execute: true, plan_id: preview.plan.plan_id}));
+  if (!applied.applied) throw new Error("The original report setting was not applied.");
+  if (applied.stop_status === "unconfirmed") throw new Error("汇报计划已取消；正在生成的任务是否停止尚未确认。Report cancelled; the active task's stop is unconfirmed.");
+  return applied;
+}
+
 export async function changeOwnerNotifications(bindingId: string, bindingRevision: number, revision: number, enabled: boolean) {
   return privateConversationsSchema.parse(await requestJson<unknown>("/api/chat/lark/private-conversations/owner-notifications", {
     method: "POST", headers: {"Content-Type": "application/json"},

apps/presentation/dashboard/src/features/personal-workspace/goal-research-analysis.css

@@ -7,7 +7,7 @@
 .research-analysis h3 { font-size: var(--text-heading); font-weight: 600; margin: 0; }
 .research-analysis h4 { font-size: var(--text-lead); font-weight: 600; line-height: 1.5; margin: 0 0 8px; }
 .research-analysis p { margin: 8px 0; }
-.research-analysis header p, .analysis-scope, .analysis-boundary, .research-analysis small, .analysis-method, .analysis-finding > span { color: var(--pw-muted); font-size: var(--text-caption); }
+.research-analysis header p, .analysis-scope, .analysis-boundary, .research-analysis small, .analysis-finding > span { color: var(--pw-muted); font-size: var(--text-caption); }
 .research-analysis button, .research-analysis select { font: inherit; color: inherit; border: 1px solid var(--pw-line); background: var(--pw-bg); border-radius: 6px; min-height: 44px; padding: 8px 12px; display: inline-flex; align-items: center; justify-content: center; gap: 6px; cursor: pointer; }
 .research-analysis button:disabled { opacity: .5; cursor: not-allowed; }
 .research-analysis button.analysis-primary { color: var(--pw-bg); background: var(--pw-text); border-color: var(--pw-text); }
@@ -18,33 +18,44 @@
 .analysis-actions small { flex-basis: 100%; }
 .analysis-warning { border-inline-start: 2px solid var(--pw-caution); padding-inline-start: 12px; }
 .analysis-error { color: var(--pw-red); }
-.analysis-finding { border-block-start: 1px solid var(--pw-line); padding-block: 20px 8px; margin-top: 20px; max-width: 76ch; }
+.analysis-finding { padding-block: 12px 8px; margin-top: 12px; max-width: 76ch; }
 .analysis-finding h4 { margin-top: 8px; }
+.analysis-episode-columns, .analysis-episode > summary { display: grid; grid-template-columns: minmax(0, 1fr) 8rem 6rem 9rem 1rem; align-items: baseline; gap: 16px; }
+.analysis-episode-columns { color: var(--pw-muted); padding-block: 8px; border-bottom: 1px solid var(--pw-line); }
+.analysis-episode-group + .analysis-episode-group { margin-top: 12px; }
+.research-analysis .analysis-shared-question { margin: 12px 0 4px; max-width: 76ch; color: var(--pw-muted); font-size: var(--text-body); }
 .analysis-episode { border-block-end: 1px solid var(--pw-line); }
-.analysis-episode > summary { display: flex; align-items: center; gap: 16px; min-height: 64px; padding-block: 12px; cursor: pointer; list-style: none; }
+.analysis-episode > summary { min-height: 48px; padding-block: 12px; cursor: pointer; list-style: none; }
 .analysis-episode > summary::-webkit-details-marker { display: none; }
-.analysis-episode-name { flex: 1; min-width: 0; max-width: 76ch; font-weight: 500; display: -webkit-box; -webkit-box-orient: vertical; -webkit-line-clamp: 2; overflow: hidden; }
+.analysis-episode-name { min-width: 0; max-width: 76ch; font-weight: 500; display: -webkit-box; -webkit-box-orient: vertical; -webkit-line-clamp: 2; overflow: hidden; }
 .analysis-episode[open] > summary .analysis-episode-name { display: block; }
-.analysis-episode-verdicts { display: flex; flex-shrink: 0; flex-wrap: wrap; justify-content: end; gap: 4px 24px; }
+.analysis-verdict-label { display: none; }
+.analysis-episode-exceptions { display: flex; flex-direction: column; color: var(--pw-muted); }
 .analysis-episode > summary > svg { flex-shrink: 0; }
 .analysis-episode[open] > summary > svg { transform: rotate(180deg); }
-.analysis-episode-body { padding-block: 8px 24px; max-width: 90ch; }
+.analysis-episode-body { padding-block: 8px 24px; max-width: 90ch; font-size: var(--text-lead); }
 .analysis-episode-context { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 24px; margin-block: 20px; }
-.analysis-episode-context strong, .analysis-episode-context small { display: block; }
-.analysis-episode-context strong { font-weight: 500; }
+.analysis-episode-context > :only-child { grid-column: 1 / -1; max-width: 76ch; }
+.analysis-reason-judgments { display: flex; flex-wrap: wrap; gap: 4px 20px; font-size: var(--text-body); }
+.analysis-reason-judgments > span { display: inline-flex; flex-wrap: wrap; gap: 8px; }
+.analysis-reason-judgments strong { font-weight: 500; }
+.analysis-reason-judgments > span > span { color: var(--pw-muted); }
+.analysis-episode-question { margin-top: 12px; }
+.analysis-episode-question > summary { cursor: pointer; padding-block: 10px; min-height: 44px; }
+.analysis-episode-question h5 { font: inherit; font-weight: 500; margin: 12px 0 0; }
 .analysis-judgments { border-top: 1px solid var(--pw-line); }
 .analysis-judgments details { border-bottom: 1px solid var(--pw-line); }
 .analysis-judgments summary { min-height: 48px; padding-block: 10px; cursor: pointer; display: flex; align-items: baseline; justify-content: space-between; gap: 16px; }
 .analysis-judgments summary strong { font-weight: 500; }
-.analysis-judgments summary span { color: var(--pw-muted); font-size: var(--text-caption); }
+.analysis-judgments summary span { font-size: var(--text-body); }
 .analysis-judgments details > p, .analysis-citations { margin: 4px 0 12px; }
 .analysis-question { color: var(--pw-muted); font-size: var(--text-caption); }
 .analysis-citations { display: flex; flex-wrap: wrap; gap: 8px; }
 .analysis-citations button { font-size: var(--text-caption); }
 .analysis-source { border: 1px solid var(--pw-line); border-radius: 8px; padding: 16px; margin-block: 16px; }
 .analysis-source p { font-size: var(--text-caption); color: var(--pw-muted); }
-.analysis-source pre { font-family: var(--font-mono); font-size: var(--text-caption); line-height: 1.7; white-space: pre-wrap; overflow-wrap: anywhere; max-height: 360px; overflow: auto; }
-.analysis-method { border-block-start: 1px solid var(--pw-line); margin-top: 16px; padding-top: 12px; }
+.analysis-source pre { font-family: var(--font-mono); font-size: var(--text-body); line-height: 1.7; white-space: pre-wrap; overflow-wrap: anywhere; max-height: 360px; overflow: auto; }
+.analysis-method { border-block-start: 1px solid var(--pw-line); margin-top: 16px; padding-top: 12px; color: var(--pw-muted); font-size: var(--text-lead); }
 .analysis-method summary { min-height: 44px; display: flex; align-items: center; cursor: pointer; color: var(--pw-text); }
 .analysis-method dl { display: grid; grid-template-columns: 100px minmax(0, 1fr); gap: 8px 16px; }
 .analysis-method dd { margin: 0; color: var(--pw-text); }
@@ -58,7 +69,15 @@
 .analysis-spin { animation: analysis-request-spin 1s linear infinite; }
 @keyframes analysis-request-spin { to { transform: rotate(360deg); } }
 @media (prefers-reduced-motion: reduce) { .analysis-spin { animation: none; } }
-@media (max-width: 640px) { .research-analysis { padding: 16px; } .analysis-episode > summary { display: grid; grid-template-columns: minmax(0, 1fr) auto; gap: 4px 12px; } .analysis-episode-verdicts { grid-column: 1; grid-row: 2; flex-direction: column; gap: 0; } .analysis-episode > summary > svg { grid-column: 2; grid-row: 1 / 3; } .analysis-episode-context { grid-template-columns: 1fr; gap: 12px; } .analysis-method dl { grid-template-columns: 1fr; gap: 2px; } .analysis-method dd { margin-bottom: 8px; } .analysis-pack-choice { flex-direction: column; align-items: stretch; } }
+@media (max-width: 1024px) {
+  .analysis-episode-columns { display: none; }
+  .analysis-episode > summary { grid-template-columns: minmax(0, 1fr) auto; gap: 4px 12px; }
+  .analysis-episode-name, .analysis-episode-verdict, .analysis-episode-exceptions { grid-column: 1; }
+  .analysis-verdict-label { display: inline; }
+  .analysis-episode > summary > svg { grid-column: 2; grid-row: 1; }
+  .analysis-episode-exceptions:empty { display: none; }
+}
+@media (max-width: 640px) { .research-analysis { padding: 16px; } .analysis-episode-context { grid-template-columns: 1fr; gap: 12px; } .analysis-method dl { grid-template-columns: 1fr; gap: 2px; } .analysis-method dd { margin-bottom: 8px; } .analysis-pack-choice { flex-direction: column; align-items: stretch; } }
 
 /* Readback has one status surface, shared by the summary and its detail. */
 .analysis-read-error,.analysis-read-empty{display:flex;align-items:center;flex-wrap:wrap;gap:8px;margin-block:12px;color:var(--pw-muted)}