feat: add governed chat console

packages/casan-control-panel/README.md

@@ -7,7 +7,7 @@ harness-owned governance CLI; the UI never writes harness files directly or bypa
 
 ```
 backend/   NestJS API (/api/v1 + /healthz) over .specify telemetry + governed settings
-frontend/  React + Vite + Tailwind + TanStack Query Ops Console + Settings/Approvals/Kill-switch/FinOps/Command pages
+frontend/  React + Vite + Tailwind + TanStack Query Ops Console + Settings/Approvals/Kill-switch/FinOps/Command/Chat pages
 ```
 
 ## Run (local)
@@ -56,6 +56,20 @@ Approval inbox / HITL:
 - `POST /api/v1/approvals/decide` — approve/reject with SoD and reason; approved
   settings proposals apply through `control-plane-settings.py`.
 
+Governed Chat (Plan-18 MVP-0/1):
+
+- `POST /api/v1/chat/ask` — Ask CASAN endpoint. The API only wraps harness
+  `chat-turn.py`; router verdicts, H4 input/output scan, action-gate decisions,
+  H5 chat audit, H6 token metrics, evidence source selection, and operator action
+  execution remain harness-owned.
+- `GET /api/v1/chat/actions` — list registered operator actions from
+  `operator-actions.yaml`; no free-command execution is exposed.
+- `GET /api/v1/chat/audit/verify` — verifies the chat audit hash chain.
+- `/chat` UI shows actor/role scope, `mode/risk/decision` badges, certified answer,
+  evidence sources, registered operator actions, action-gate status, router details,
+  and audit hash. Side-effect requests outside registered actions return governed
+  `BLOCK` or `NOT_SUPPORTED` responses.
+
 FinOps/SLO:
 
 - `/finops` UI reads `GET /api/v1/cost` plus `GET /api/v1/settings`.
@@ -77,7 +91,7 @@ the same harness engine.
 
 ## Test
 ```bash
-npm run console:test             # backend telemetry/settings/approvals/kill-switch/auth mapping/command contract
+npm run console:test             # backend telemetry/settings/approvals/kill-switch/auth mapping/command/chat contract
 npm run console:build            # backend tsc + frontend typecheck/vite build
 ```