wire up /agent/execute and /agent/stop endpoints

- Add runSessionAgent: streaming variant of runAgent that PATCHes VIBN DB
  after every LLM turn and tool call so frontend can poll live output
- Track changed files from write_file / replace_in_file tool calls
- Add /agent/execute: receives sessionId + giteaRepo + task, clones repo,
  scopes workspace to appPath, runs Coder agent async (returns 202 immediately)
- Add /agent/stop: sets stopped flag; agent checks between turns and exits cleanly
- Agent does NOT commit on completion — leaves changes for user review/approval

Made-with: Cursor

dist/atlas.js

@@ -38,7 +38,7 @@ function listAtlasSessions() {
 // ---------------------------------------------------------------------------
 // Main chat handler
 // ---------------------------------------------------------------------------
-const ATLAS_TOOLS = tools_1.ALL_TOOLS.filter(t => t.name === 'finalize_prd');
+const ATLAS_TOOLS = tools_1.ALL_TOOLS.filter(t => ['finalize_prd', 'web_search'].includes(t.name));
 async function atlasChat(sessionId, userMessage, ctx, opts) {
     const llm = (0, llm_1.createLLM)(process.env.ATLAS_MODEL ?? 'A', { temperature: 0.5 });
     const session = getOrCreateSession(sessionId);
@@ -48,7 +48,10 @@ async function atlasChat(sessionId, userMessage, ctx, opts) {
     }
     const oaiTools = (0, llm_1.toOAITools)(ATLAS_TOOLS);
     const systemPrompt = (0, loader_1.resolvePrompt)('atlas');
-    session.history.push({ role: 'user', content: userMessage });
+    // For init triggers, don't add the synthetic prompt as a user turn
+    if (!opts?.isInit) {
+        session.history.push({ role: 'user', content: userMessage });
+    }
     const buildMessages = () => [
         { role: 'system', content: systemPrompt },
         ...session.history.slice(-60)