feat(backend): POST /sessions applies global settings, body is question-only

workspace/provider/model/thinking now come from getSettings() injected into
sessionRoutes; the request body supplies only question+name. Also teaches
fake_pi_rpc to respond to set_model and set_thinking_level RPC commands so
tests that pass real model settings don't hang.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/src/routes/sessions.ts

@@ -2,17 +2,32 @@ import type { FastifyInstance } from "fastify";
 import type { PiProcessManager } from "../pi/pi-process-manager.js";
 import type { ThtRunner } from "../tht/tht-runner.js";
 import type { SseHub } from "../sse/sse-hub.js";
+import type { Settings } from "../settings/settings-store.js";
 import { getUser } from "../auth/auth.js";
 
-export function sessionRoutes(app: FastifyInstance, d: { mgr: PiProcessManager; tht: ThtRunner; hub: SseHub }) {
+export function sessionRoutes(
+  app: FastifyInstance,
+  d: { mgr: PiProcessManager; tht: ThtRunner; hub: SseHub; getSettings: () => Settings },
+) {
   app.post("/sessions", async (req, reply) => {
-    const b = req.body as any;
-    // NOTE (MVP): `workspace` selects the tht `-c <config>` for the backend's own
-    // tht calls (session new/list/show). The gate/Pi side still uses the symlinked
-    // `config/tht.yaml` (single-workspace). Full multi-workspace on the Pi side is
-    // future work — the gate would need a THT_CONFIG/workspace env passed at spawn.
-    const { id } = await d.tht.sessionNew({ question: b.question, provider: b.provider, model: b.model, thinking: b.thinking, name: b.name, workspace: b.workspace });
-    const rt = await d.mgr.spawnFor(id, { provider: b.provider, model: b.model, thinking: b.thinking, author: getUser(req).id });
+    const b = req.body as { question: string; name?: string };
+    const s = d.getSettings();
+    // Settings (global) supply workspace/provider/model/thinking. The new-question
+    // form sends only the question text. `workspace` selects the tht `-c <config>`.
+    const { id } = await d.tht.sessionNew({
+      question: b.question,
+      name: b.name,
+      workspace: s.workspace,
+      provider: s.provider,
+      model: s.model,
+      thinking: s.thinking,
+    });
+    const rt = await d.mgr.spawnFor(id, {
+      provider: s.provider,
+      model: s.model,
+      thinking: s.thinking,
+      author: getUser(req).id,
+    });
     rt.bridge.onClientEvent((e) => d.hub.publish(id, e.type, e));
     return { id };
   });

backend/test/routes-sessions.test.ts

@@ -7,18 +7,23 @@ import { loadConfig } from "../src/config.js";
 const FAKE = path.resolve("../harness/tests/fake_pi/fake_pi_rpc.mjs");
 const SCRIPT = path.resolve("../harness/tests/fake_pi/scripts/f1_disambiguation.json");
 
-test("POST /sessions crea e avvia, GET /sessions lista; inoltra workspace a sessionNew", async () => {
+test("POST /sessions usa i settings (workspace/provider/model/thinking) e crea+avvia", async () => {
   let sessionNewArg: any;
+  let spawnArg: any;
   const app = buildApp(loadConfig({ THT_HARNESS_DIR: "../harness" }), {
     thtRunner: {
       sessionNew: async (o: any) => { sessionNewArg = o; return { id: "s1" }; },
       sessionList: async () => [{ id: "s1" }],
     } as any,
+    getSettings: () => ({ workspace: "w", provider: "zai", model: "glm-5.2", thinking: "high" }),
     spawnFn: () => spawn("node", [FAKE, SCRIPT]) as any,
   });
-  const created = await app.inject({ method: "POST", url: "/sessions", payload: { workspace: "w", question: "q" } });
+  const created = await app.inject({ method: "POST", url: "/sessions", payload: { question: "q" } });
   expect(created.json()).toEqual({ id: "s1" });
   expect(sessionNewArg.workspace).toBe("w");
+  expect(sessionNewArg.provider).toBe("zai");
+  expect(sessionNewArg.model).toBe("glm-5.2");
+  expect(sessionNewArg.thinking).toBe("high");
   expect(sessionNewArg.question).toBe("q");
   const list = await app.inject({ method: "GET", url: "/sessions" });
   expect(list.json()).toEqual([{ id: "s1" }]);
@@ -27,9 +32,10 @@ test("POST /sessions crea e avvia, GET /sessions lista; inoltra workspace a sess
 test("POST /sessions/:id/response inoltra al bridge (no error)", async () => {
   const app = buildApp(loadConfig({ THT_HARNESS_DIR: "../harness" }), {
     thtRunner: { sessionNew: async () => ({ id: "s1" }) } as any,
+    getSettings: () => ({ workspace: "w" }),
     spawnFn: () => spawn("node", [FAKE, SCRIPT]) as any,
   });
-  await app.inject({ method: "POST", url: "/sessions", payload: { workspace: "w", question: "q" } });
+  await app.inject({ method: "POST", url: "/sessions", payload: { question: "q" } });
   const res = await app.inject({ method: "POST", url: "/sessions/s1/response",
     payload: { ui_response: { id: "u1", choices: ["a"] } } });
   expect(res.statusCode).toBe(204);

harness/tests/fake_pi/fake_pi_rpc.mjs

@@ -27,6 +27,10 @@ process.stdin.on("data", (chunk) => {
     } else if (cmd.type === "get_state") {
       out({ type: "response", command: "get_state", id: cmd.id, success: true,
             data: { sessionId: "fake", thinkingLevel: "medium", isStreaming: false } });
+    } else if (cmd.type === "set_model") {
+      out({ type: "response", command: "set_model", id: cmd.id, success: true });
+    } else if (cmd.type === "set_thinking_level") {
+      out({ type: "response", command: "set_thinking_level", id: cmd.id, success: true });
     }
   }
 });