Merge feat/local-model-recommendation: recommend and install a local coding model on this Mac (experimental)

Conflicts resolved as on test/desktop-macbook: config/test-suites.ts keeps both browser tests (desktop-connect-page and local-model-ui), and the CLAUDE.md state-files line keeps #778's cli-installed entry with the local model's local-model.json and local-model/ entries.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/web/server.ts

@@ -147,6 +147,7 @@ import { probeLocalPaths, readClaudeEditSources, resolveClaudeTranscript } from
 import { remoteLocateClaudeTranscript, remoteProbePaths, remoteReadClaudeEditSources } from '../remote-files.js';
 import { remoteTmuxLocation } from '../tmux-manager.js';
 import { stopDeepSeekWeb } from '../deepseek-web-server.js';
+import { getLocalModelService } from '../local-model/install-job.js';
 import {
   wireRespawnListeners,
   setupTimedRespawn,
@@ -265,6 +266,7 @@ import {
   pruneIdleLlamaSwapLogTails,
   tryWebviewRefererFallback,
   registerCliRegistryRoutes,
+  registerLocalModelRoutes,
 } from './routes/index.js';
 import { isLostWebviewFrameNavigation } from './webview-proxy.js';
 import { CronService } from '../cron/cron-service.js';
@@ -1418,6 +1420,7 @@ export class WebServer extends EventEmitter {
     registerDoctorRoutes(this.app);
     registerCustomModelRoutes(this.app);
     registerCliRegistryRoutes(this.app);
+    registerLocalModelRoutes(this.app, ctx);
 
     // Cron: build the service from the same context, recompute
     // due times for any persisted jobs, then expose it to its routes.
@@ -2192,6 +2195,17 @@ export class WebServer extends EventEmitter {
     // First keep-warm evaluation: publishes the effective opt-in for the Session Options
     // readout even before any cache report arrives.
     void this.keepWarmService.schedule(session.id);
+    // Before every start of a NEW agent process the session asks this (a fresh pane, the
+    // respawn of a dead one, a restart in place; never an attach to an agent that runs).
+    // The model Codeman runs on this Mac is the one endpoint with something to say: no agent
+    // is started on it while its runtime is down or its model is not the one that was
+    // installed. Every other session, and every other endpoint, is answered `undefined`.
+    // Set on every call, above the idempotency return: it holds no state of its own.
+    session.setLaunchGuard(async () => {
+      const selection = session.customModel;
+      if (!selection) return undefined;
+      return getLocalModelService().launchRefusalMessage(selection.endpointId, selection.modelId);
+    });
     // Idempotent: the wiring exit handler detaches ALL listeners on every PTY exit
     // (removeSessionListenerRefs), so the re-attach routes (/interactive,
     // /interactive-respawn, /shell) call this again to restore observability
@@ -3472,6 +3486,14 @@ export class WebServer extends EventEmitter {
       }
     }
 
+    // The model Codeman runs on this Mac (src/local-model/): a job a restart interrupted comes
+    // back paused and waits for a click, and an installed runtime that was not stopped is
+    // started again (an own orphan on its port is adopted or replaced). Off the startup path:
+    // boot() never throws, and nothing waits for a runtime to answer. Not in tests.
+    if (!this.testMode) {
+      void getLocalModelService().boot();
+    }
+
     // Sweep agent preamble caches whose sessions are gone (see
     // pruneAgentSessionPreambles). Once per boot, after restore, so every session this
     // instance owns is in the keep set. Best-effort and off the startup critical path.
@@ -4621,6 +4643,13 @@ export class WebServer extends EventEmitter {
     // got wrong once.
     void stopDeepSeekWeb();
 
+    // The local model runtime is a non-detached child, but a child is not ended by its
+    // parent's exit: it gets SIGTERM here, and an install job in flight is interrupted (the
+    // next start reads it as paused). An orphan a hard kill leaves is adopted at the next boot.
+    if (!this.testMode) {
+      void getLocalModelService().shutdown();
+    }
+
     // The header's GPU / CPU clock sampler is a Windows child process under WSL, and its idle sweep a timer.
     stopHostSensors();