From 6a6fbca9e07b677f39db89b9befe6fa147921cd9 Mon Sep 17 00:00:00 2001
From: Ramis <r_hasanli@u.pacific.edu>
Date: Sat, 27 Jun 2026 20:31:38 -0700
Subject: [PATCH] fix: stop agent crashing on Mongo errors during live loop

A Mongo auth/connection failure in getGitStates escaped uncaught and
killed the agent process on the first screen frame, so collision
detection never ran. Make git-state fusion best-effort (degrade to
vision-only) and wrap the whole onScreenFrame loop so no per-frame
Gemini/GitHub/Mongo error can crash the long-running agent.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AaCFWMkYQmTcuPsxaaACft
---
 backend/src/agent/podman.ts | 32 +++++++++++++++++++-------------
 backend/src/memory/db.ts    | 22 ++++++++++++++--------
 2 files changed, 33 insertions(+), 21 deletions(-)

diff --git a/backend/src/agent/podman.ts b/backend/src/agent/podman.ts
index 97cf920..e4fec6d 100644
--- a/backend/src/agent/podman.ts
+++ b/backend/src/agent/podman.ts
@@ -43,21 +43,27 @@ export class PodMan {
   }
 
   async onScreenFrame(engineerId: string, jpeg: Buffer): Promise<void> {
-    const ctx = await analyzeFrame(engineerId, this.podId, jpeg);
-    this.contexts.set(engineerId, ctx);
-    await recordObservation(ctx);
+    // 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);
 
-    // 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;
+      // 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}`);
     }
-
-    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> {
diff --git a/backend/src/memory/db.ts b/backend/src/memory/db.ts
index 5b64c73..19ad06e 100644
--- a/backend/src/memory/db.ts
+++ b/backend/src/memory/db.ts
@@ -69,15 +69,21 @@ 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>();
-  for (const doc of docs) {
-    map.set(doc.name, {
-      changedFiles: doc.changedFiles ?? [],
-      branch: doc.branch ?? null,
-      recentCommit: doc.recentCommit ?? null,
-      gitUpdatedAt: doc.gitUpdatedAt ?? null,
-    });
+  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}`);
   }
   return map;
 }