feat(portal-bff): ai-bridge controller — SSE chat + JSON rag/models (#196)

## Summary

Step 3 of the AI-relay chantier (after #194 ADR and #195 client skeleton). Wires the BFF-side **live surface** that the SPA's future chatbot widget will consume. [ADR-0024](docs/decisions/0024-ai-service-relay-grpc-sse-bridge.md) is promoted from `proposed` to `accepted` in the same change.

Three end-user routes under `/api/ai/*`, gated by the active portal session (no `@RequireAdmin` — AI is a regular-user surface):

| Route | Verb | Wire | Maps to |
|---|---|---|---|
| `/api/ai/chat` | `POST` | `text/event-stream` | `apf.ai.v1.ChatService.Chat` (server-stream) |
| `/api/ai/rag/search` | `GET` | `application/json` | `apf.ai.v1.RagService.Search` (unary) |
| `/api/ai/models` | `GET` | `application/json` | `apf.ai.v1.ModelsService.ListModels` (unary) |

CSRF and session validation are delegated to the global middleware mounted in `main.ts` (per [ADR-0009](docs/decisions/0009-auth-flow-oidc-pkce-msal-node.md) and [ADR-0021](docs/decisions/0021-phase-2-security-baseline.md)); the controller asserts `req.session.user` and emits 401 if absent.

## What lands

### `apps/portal-bff/src/grpc/ai-bridge/`

```
ai-bridge/
├── ai-bridge.module.ts         imports AiClientModule, exports the controller
├── ai-bridge.controller.ts     3 routes — POST chat (SSE), GET rag/search, GET models
├── sse.writer.ts               ChatEvent oneof → SSE frame translator
├── sse.writer.spec.ts          unit tests for the codec
├── ai-bridge.controller.spec.ts  end-to-end against an in-process fake gRPC server
└── dto/
    ├── chat-request.dto.ts     class-validator body shape (POST /chat)
    └── rag-search-query.dto.ts class-validator query shape (GET /rag/search)
```

### SSE codec (`sse.writer.ts`)

Each `ChatEvent` oneof case becomes one SSE frame with a kebab-case `event:` name and a JSON-encoded `data:` payload:

```
event: token
data: {"token":"…","value":"…"}

event: agent-step
data: {"agent":"…","step":"…","stepId":"…"}

event: tool-call
data: {"callId":"…","name":"…","args":{…}}

event: done
data: {"stats":{"tokensIn":…,"tokensOut":…,"chunksRetrieved":…}}
```

A helper `relayErrorFrame(code, message, retriable)` synthesises a relay-side `event: error` frame that matches the AI service's own `ErrorEvent` shape — the SPA's renderer needs no second code path for relay-level failures vs upstream model errors. gRPC status codes map into the `urn:apf-ai:*` namespace (`UNAVAILABLE` → `urn:apf-ai:unavailable`, `DEADLINE_EXCEEDED` → `urn:apf-ai:timeout`, `PERMISSION_DENIED` → `urn:apf-ai:permission_denied`, `RESOURCE_EXHAUSTED` → `urn:apf-ai:rate_limited`, `INVALID_ARGUMENT` → `urn:apf-ai:invalid_argument`, anything else → `urn:apf-ai:relay_error`).

The terminal `done` frame closes the stream — no `[DONE]` sentinel, per ADR-0024.

### Controller (`ai-bridge.controller.ts`)

- `POST /api/ai/chat` — builds an `apf.ai.v1.ChatRequest` from the validated DTO + session-derived Principal, calls `ChatClient.chat()`, drains the `ClientReadableStream<ChatEvent>` into SSE frames written on the raw Express `Response`. `req.on('close', …)` propagates browser disconnect through an `AbortController` into `call.cancel()` so the upstream LLM stops (per `apf-ai-service/docs/streaming.md`).
- `GET /api/ai/rag/search` — unary RAG call. `topK` defaults to 0 (server picks the default). `source` and `documentId` query params surface the same filter fields the upstream RPC accepts.
- `GET /api/ai/models` — unary lookup of the provider catalogue.

The SSE writes happen on the raw Express response (manual `setHeader` + `flushHeaders` + `write` + `end`) rather than through NestJS's `@Sse()` decorator, because `@Sse()` is GET-only and the chat endpoint is POST (the SPA carries the conversation history in the body).

### Lifecycle hooks

`AiClientModule` now implements `OnApplicationShutdown` and closes the four gRPC stubs (Chat / Rag / Ingestion / Models). The four stubs share the same HTTP/2 channel (gRPC-js dedups on `endpoint + credentials`), so the `close()` calls are cheap, but kept explicit so adding a fifth stub later is an obvious one-line addition. `main.ts` now calls `app.enableShutdownHooks()` so `SIGTERM` / `SIGINT` / `SIGHUP` actually route through the lifecycle interface.

### DTOs

`ChatRequestDto` constrains:
- `messages` — 1 to 64 entries; each has `role ∈ {user, assistant, system}` (no `tool` — tool messages are constructed BFF-side per ADR-0024 §"Tool-dispatch contract") and `content` ≤ 16 KB.
- `conversationId`, `model`, `provider` — optional, ≤ 64 / 128 chars.

`RagSearchQueryDto`:
- `query` — required, non-empty.
- `topK` — optional, integer in `[1, 50]` (the AI service has its own cap; the BFF rejects out-of-range values early).
- `source` / `documentId` — optional pass-through filters.

### Documentation

- ADR-0024 frontmatter: `status: proposed` → `accepted`.
- `docs/decisions/README.md` index reflects the new status.
- `CLAUDE.md` Architecture section grows an "AI service relay" bullet; the roll-up line moves from "ADRs 0001 → 0023" to "0001 → 0024"; the shipped-on-main list grows an "AI relay surface" entry.
- `apps/portal-bff/.env.example` documents `AI_SERVICE_GRPC_ENDPOINT` / `AI_SERVICE_CLIENT_ID` / `AI_SERVICE_GRPC_TLS` and points operators at `apf-ai-service`'s own docker-compose for the runtime dependency.

## Notes for the reviewer

- **No live AI service in this PR's local-dev stack.** `apf-ai-service` runs from its own repo (`/home/jgautier/Works/apf-ai-service`) with its own `infra/docker-compose.yml`. The BFF dials `localhost:8080` by default — the host-published port of the AI service's container. This is option (a) from ADR-0024 §"Open question — Compose orchestration": two independent stacks, dial across via host networking. Merging the compose files into one would couple two release cadences without operational payoff.
- **Tests run against an in-process fake `grpc.Server`.** All five spec cases on the controller wire it up against a fake `ChatService` + `RagService` + `ModelsService` server bound to `127.0.0.1:0` (random port). No mocks — the controller's gRPC client makes a real connection, real serialisation, real cancellation propagation. Cost: ~0.5 s overhead from the gRPC server setup.
- **CSRF + session middleware are unchanged.** The new POST endpoint is protected by the existing double-submit CSRF middleware mounted in `main.ts` (per [ADR-0021](docs/decisions/0021-phase-2-security-baseline.md)). The SPA's fetch call needs to send the `X-CSRF-Token` header matching the `__Host-portal_csrf` cookie — same protocol as every other POST in the BFF. No per-controller wiring required.
- **Manual session check rather than a guard.** Three reasons: (1) matches the existing pattern in `me.controller.ts`; (2) the session check is the only authorization gate (no roles to evaluate) — a guard would add ceremony without payoff; (3) the SSE controller already takes control of the response object (`@Res()`), which `UseGuards` interacts with awkwardly. Throwing `UnauthorizedException` lets `StructuredErrorFilter` produce the 401 envelope before any header is flushed.
- **Why the controller does NOT use `@Sse()`.** NestJS's `@Sse()` decorator is GET-only and emits frames from `Observable<MessageEvent>`. The chat endpoint is POST (the SPA sends conversation history in the body) and the source is a Node `Readable` stream from `@grpc/grpc-js`. Manual response handling is simpler than adapting to / from `Observable` for a single consumer.
- **Cancellation contract.** When the SPA aborts the fetch, the browser closes the TCP connection, Express emits `'close'` on the request, the controller's `AbortController.abort()` triggers, `ChatClient` calls `.cancel()` on the gRPC stream, the AI service's `ServerCallContext.CancellationToken` cancels the upstream LLM. The spec covers the `'close'` → server-side `cancelled` event end-to-end.
- **No ingestion route in the BFF.** Per ADR-0024 §"Out of scope", v1 admin ingestion uses the `apf-ai-service/tools/Apf.Ai.Ingest/` CLI. A future PR adds the BFF endpoint when the admin "manage AI corpus" surface ships. `IngestionClient` remains in `AiClientModule` so that future PR is one new file, not a new module plus a new client.
- **No bundle-size or perf surprise.** The BFF is a Node process, not a SPA chunk — bundle budgets don't apply. The gRPC channel is opened lazily on first call; idle BFFs incur no upstream TCP cost.

## Test plan

- [x] `pnpm nx test portal-bff` — **461 specs pass** (was 443; +13 new: 8 SSE writer cases + 5 controller end-to-end cases against the in-process fake server). Worker-exit-leak warning persists from the gRPC server's slow shutdown — pre-existing pattern from PR #195; harmless.
- [x] `pnpm nx lint portal-bff` — 6 pre-existing warnings, no new ones from the diff.
- [x] `pnpm nx build portal-bff` — clean webpack compile.
- [x] Module wiring: `AppModule` imports `AiBridgeModule`, which imports `AiClientModule`. Resolves cleanly through DI; the audit-side `HashUserIdService` is satisfied by `AiClientModule`'s local provider (per the rationale recorded in PR #195's `AiClientModule` docstring).
- [ ] **Manual smoke** — bring up `apf-ai-service` from its own repo (`cd ../apf-ai-service && docker compose -f infra/docker-compose.yml up`), set `AI_SERVICE_GRPC_ENDPOINT=localhost:8080` in `apps/portal-bff/.env`, run `pnpm nx serve portal-bff`. Sign in to `portal-shell`, then in a terminal:
  ```bash
  curl --cookie-jar /tmp/portal-session http://localhost:3000/api/auth/login    # follow Entra…
  curl -N \
       -H 'Content-Type: application/json' \
       -H 'X-CSRF-Token: <copied from cookie>' \
       --cookie /tmp/portal-session \
       -d '{"messages":[{"role":"user","content":"hello"}]}' \
       http://localhost:3000/api/ai/chat
  ```
  Expect a streamed SSE response terminated by an `event: done` frame. Verify `GET /api/ai/rag/search?query=test` returns a JSON response. Verify `GET /api/ai/models` lists the configured providers.

## What's next

1. **PR (frontend chantier)** — chatbot widget on `portal-shell` consuming the SSE endpoint. Will use `fetch` + `ReadableStream` parsing (not native `EventSource`, since POST is needed). Drag / fullscreen / suggestion UX carries forward from the stargate POC's `ChatbotWidget.tsx`.
2. **PR (post-v1)** — proto-drift CI gate that diffs `proto/apf-ai/` against an upstream tag of `apf-ai-service`.
3. **Coordinated amendment** — when the first production deployment is in scope, both repos record the same prod-hardening choice (signed `Principal` envelope vs mTLS) on the same date.

---------

Co-authored-by: Julien Gautier <julien.gautier@apf.asso.fr>
Reviewed-on: #196

CLAUDE.md

@@ -52,17 +52,19 @@ The structural, security, observability, and quality choices are recorded as ADR
 - **Local quality gates:** Husky + lint-staged + commitlint with Conventional Commits — see [ADR-0007](docs/decisions/0007-pre-commit-hooks-and-conventional-commits.md).
 - **Documentation site:** `docs/**/*.md` rendered as a separate static site via **VitePress** (Vite-based, Node-only toolchain, Markdown-first). Mermaid diagrams via `vitepress-plugin-mermaid`. Deployed on its own hostname behind the shared reverse-proxy; CI hook on `docs/` changes rebuilds + publishes. Decoupled from the apps — content lives in `docs/`, no in-app Markdown viewer — see [ADR-0022](docs/decisions/0022-docs-site-vitepress.md).
 - **Charts + dashboards:** `D3 + Observable Plot` wrapped in `libs/shared/charts/`, one Angular component per chart type (bar, donut, line, stacked-bar, …). A11y baked in by the lib (SVG `<title>`/`<desc>`, `<details>` tabular fallback, colour-blind-safe palettes, AA-contrast text, `prefers-reduced-motion` gate). Bundle stays under [ADR-0017](docs/decisions/0017-performance-budgets-lighthouse-ci.md)'s lazy-chunk cap via per-`d3-*` module tree-shaking. Future bespoke visualisations land in raw D3 inside the same lib — see [ADR-0023](docs/decisions/0023-charts-d3-observable-plot.md).
+- **AI service relay:** dedicated `apf-ai-service` repo (ASP.NET Core, Microsoft Agent Framework) consumed via native gRPC HTTP/2 only — proto contract vendored under `apps/portal-bff/src/grpc/proto/apf-ai/` with `ts-proto` codegen committed alongside. BFF dials with `@grpc/grpc-js` (h2c in dev, h2 + TLS in prod), bridges `ChatService.Chat` to `text/event-stream` for the SPA, exposes `RagService.Search` and `ModelsService.ListModels` as plain JSON endpoints. Identity travels as an unsigned `Principal` (subject, roles, attributes) in the proto body for the POC, hashed via the audit module's `HashUserIdService` so portal and AI service audit trails join on the same `actor_id_hash`. Production hardening (signed envelope vs mTLS) deferred — see [ADR-0024](docs/decisions/0024-ai-service-relay-grpc-sse-bridge.md).
 - **Runtime:** Node.js latest LTS major.
 
 ## Repository status
 
 The Nx workspace is **scaffolded and operational**. The three apps (`portal-shell`, `portal-admin`, `portal-bff`) and the four lib roots (`libs/feature/`, `libs/shared/state`, `libs/shared/tokens`, `libs/shared/ui`, `libs/shared/util`) are in place; CI runs `format:check / lint / test / build` on every PR.
 
-ADRs 0001 → 0023 are accepted and cover the structural, security, observability, quality, i18n, admin-app, docs-site, and charts choices. **Shipped on `main`:**
+ADRs 0001 → 0024 are accepted and cover the structural, security, observability, quality, i18n, admin-app, docs-site, charts, and AI-relay choices. **Shipped on `main`:**
 
 - **Phase-1 foundation** — Nx workspace, Angular `portal-shell`, NestJS `portal-bff`, Prisma + Postgres, Pino + OpenTelemetry, Husky/lint-staged/commitlint, Gitea Actions CI.
 - **Phase-2 auth + audit + security** — OIDC Auth Code + PKCE via MSAL Node, Redis sessions with AES-256-GCM at rest, idle 30 min sliding + absolute 12 h hard ceiling, RP-initiated logout, double-submit CSRF, `audit.events` append-only schema with role-based grants, helmet + env-driven CORS allowlist + rate limiting + structured error envelope (see [ADR-0021](docs/decisions/0021-phase-2-security-baseline.md)).
 - **Phase-3a admin app skeleton** — `portal-admin` SPA exists with brand tokens and routing; business modules (CMS, menu management, user list, audit log viewer) not yet implemented.
+- **AI relay surface** — vendored protos + `AiClientModule` (gRPC clients, Principal mapper, metadata builder) + `AiBridgeController` exposing `POST /api/ai/chat` (SSE), `GET /api/ai/rag/search`, `GET /api/ai/models` (see [ADR-0024](docs/decisions/0024-ai-service-relay-grpc-sse-bridge.md)). Live consumer (chatbot widget on `portal-shell`) and the proto-drift CI gate ship next.
 
 **Still on the roadmap:**