fix: make MongoDB mandatory, fail loud instead of degrading

Reverse the best-effort error swallowing. MongoDB is core to PodMan's
continual-learning story and must always be used, so a broken memory
layer must surface immediately rather than silently masquerade as
working (which is how observations stayed at 0 unnoticed).

- agent verifies Mongo via initMemory() at boot; bad creds / unreachable
  Atlas now fail loudly before joining the room, not mid-demo
- server exits on Mongo init failure instead of warning and limping on
- getGitStates and onScreenFrame no longer swallow Mongo errors
- memory persist() logs the failure and rethrows instead of warning

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AaCFWMkYQmTcuPsxaaACft

backend/src/agent.ts

@@ -14,6 +14,7 @@ import sharp from 'sharp';
 import { AccessToken } from 'livekit-server-sdk';
 import { env } from './env.js';
 import { PodMan } from './agent/podman.js';
+import { initMemory } from './memory/db.js';
 
 const POD_ROOM = process.env.POD_ROOM ?? 'demo-pod';
 const HERMES_IDENTITY = 'podman-hermes';
@@ -30,6 +31,10 @@ async function agentToken(room: string): Promise<string> {
 }
 
 async function main() {
+  // MongoDB is mandatory. Verify the connection before joining the room so bad
+  // creds / unreachable Atlas fail loudly at boot, not silently mid-demo.
+  await initMemory();
+
   const room = new Room();
   const podman = new PodMan(room, POD_ROOM);
   await room.connect(env.LIVEKIT_URL, await agentToken(POD_ROOM), {

backend/src/agent/podman.ts

@@ -43,27 +43,21 @@ export class PodMan {
   }
 
   async onScreenFrame(engineerId: string, jpeg: Buffer): Promise<void> {
-    // Whole-frame guard: a Gemini/GitHub/Mongo failure on one frame must degrade
-    // gracefully, never crash the long-running live agent loop.
-    try {
-      const ctx = await analyzeFrame(engineerId, this.podId, jpeg);
-      this.contexts.set(engineerId, ctx);
-      await recordObservation(ctx);
+    const ctx = await analyzeFrame(engineerId, this.podId, jpeg);
+    this.contexts.set(engineerId, ctx);
+    await recordObservation(ctx);
 
-      // Fuse git ground truth: engineer_states written by scripts/podman-agent.mjs.
-      // Keyed by name (matches --name arg), same as LiveKit participant identity.
-      const gitStates = await getGitStates(this.podId);
-      for (const [id, c] of this.contexts) {
-        const git = gitStates.get(id);
-        if (git && git.changedFiles.length > 0) c.hasUnpushedChanges = true;
-      }
-
-      const github = await getGithubState(); // cached
-      const collisions = detectCollisions([...this.contexts.values()], github);
-      for (const collision of collisions) await this.handle(collision);
-    } catch (err) {
-      console.warn(`[agent] frame from ${engineerId} skipped: ${(err as Error).message}`);
+    // Fuse git ground truth: engineer_states written by scripts/podman-agent.mjs.
+    // Keyed by name (matches --name arg), same as LiveKit participant identity.
+    const gitStates = await getGitStates(this.podId);
+    for (const [id, c] of this.contexts) {
+      const git = gitStates.get(id);
+      if (git && git.changedFiles.length > 0) c.hasUnpushedChanges = true;
     }
+
+    const github = await getGithubState(); // cached
+    const collisions = detectCollisions([...this.contexts.values()], github);
+    for (const collision of collisions) await this.handle(collision);
   }
 
   private async handle(collision: Collision): Promise<void> {

backend/src/memory/db.ts

@@ -69,21 +69,15 @@ export async function getGitStates(podId: string): Promise<Map<string, GitState>
     recentCommit?: string | null;
     gitUpdatedAt?: Date;
   }>('engineer_states');
+  const docs = await col.find({ podId }).toArray();
   const map = new Map<string, GitState>();
-  try {
-    const docs = await col.find({ podId }).toArray();
-    for (const doc of docs) {
-      map.set(doc.name, {
-        changedFiles: doc.changedFiles ?? [],
-        branch: doc.branch ?? null,
-        recentCommit: doc.recentCommit ?? null,
-        gitUpdatedAt: doc.gitUpdatedAt ?? null,
-      });
-    }
-  } catch (err) {
-    // Best-effort: a Mongo hiccup degrades git fusion, it must not crash the
-    // live agent loop. Detection falls back to vision-only signals.
-    console.warn(`[memory] getGitStates failed: ${(err as Error).message}`);
+  for (const doc of docs) {
+    map.set(doc.name, {
+      changedFiles: doc.changedFiles ?? [],
+      branch: doc.branch ?? null,
+      recentCommit: doc.recentCommit ?? null,
+      gitUpdatedAt: doc.gitUpdatedAt ?? null,
+    });
   }
   return map;
 }

backend/src/memory/store.ts

@@ -10,14 +10,16 @@ import { enrichCollisionMemory } from './vectors.js';
 
 /**
  * Continual-learning memory: persist observations, collisions, interventions,
- * and outcomes to MongoDB so later sessions get sharper. Writes are best-effort
- * — a Mongo hiccup logs a warning rather than crashing the agent/server.
+ * and outcomes to MongoDB so later sessions get sharper. MongoDB is mandatory —
+ * a failed write is surfaced loudly and rethrown, never silently swallowed, so
+ * a broken memory layer can never masquerade as a working one.
  */
 async function persist(name: string, fn: () => Promise<unknown>): Promise<void> {
   try {
     await fn();
   } catch (err) {
-    console.warn(`[memory] ${name} persist failed: ${(err as Error).message}`);
+    console.error(`[memory] ${name} persist FAILED: ${(err as Error).message}`);
+    throw err;
   }
 }
 

backend/src/server.ts

@@ -177,7 +177,11 @@ http.listen(env.PORT, '0.0.0.0', () => {
   console.log(`[server] :${env.PORT}`);
   initMemory()
     .then(() => seedDefaultPods())
-    .catch((e) => console.warn(`[memory] init failed: ${(e as Error).message}`));
+    .catch((e) => {
+      // MongoDB is mandatory — do not run a half-dead API against a broken DB.
+      console.error(`[memory] init FAILED, exiting: ${(e as Error).message}`);
+      process.exit(1);
+    });
 });
 
 let shuttingDown = false;