Merge main into thedotmack/file-read-timeline-inject

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/cli/handlers/context.ts

@@ -39,7 +39,7 @@ export const contextHandler: EventHandler = {
     // Pass all projects (parent + worktree if applicable) for unified timeline
     const projectsParam = context.allProjects.join(',');
     const apiPath = `/api/context/inject?projects=${encodeURIComponent(projectsParam)}`;
-    const colorApiPath = `${apiPath}&colors=true`;
+    const colorApiPath = input.platform === 'claude-code' ? `${apiPath}&colors=true` : apiPath;
 
     // Note: Removed AbortSignal.timeout due to Windows Bun cleanup issue (libuv assertion)
     // Worker service has its own timeouts, so client-side timeout is redundant

src/cli/handlers/session-init.ts

@@ -87,17 +87,18 @@ export const sessionInitHandler: EventHandler = {
 
     // Skip SDK agent re-initialization if context was already injected for this session (#1079)
     // The prompt was already saved to the database by /api/sessions/init above —
-    // no need to re-start the SDK agent on every turn
-    if (initResult.contextInjected) {
+    // no need to re-start the SDK agent on every turn.
+    // Note: we do NOT return here — semantic injection below must run on every prompt.
+    const skipAgentInit = Boolean(initResult.contextInjected);
+    if (skipAgentInit) {
       logger.info('HOOK', `INIT_COMPLETE | sessionDbId=${sessionDbId} | promptNumber=${promptNumber} | skipped_agent_init=true | reason=context_already_injected`, {
         sessionId: sessionDbId
       });
-      return { continue: true, suppressOutput: true };
     }
 
     // Only initialize SDK agent for Claude Code (not Cursor)
     // Cursor doesn't use the SDK agent - it only needs session/observation storage
-    if (input.platform !== 'cursor' && sessionDbId) {
+    if (!skipAgentInit && input.platform !== 'cursor' && sessionDbId) {
       // Strip leading slash from commands for memory agent
       // /review 101 -> review 101 (more semantic for observations)
       const cleanedPrompt = prompt.startsWith('/') ? prompt.substring(1) : prompt;
@@ -115,14 +116,58 @@ export const sessionInitHandler: EventHandler = {
         // Log but don't throw - SDK agent failure should not block the user's prompt
         logger.failure('HOOK', `SDK agent start failed: ${response.status}`, { sessionDbId, promptNumber });
       }
-    } else if (input.platform === 'cursor') {
+    } else if (!skipAgentInit && input.platform === 'cursor') {
       logger.debug('HOOK', 'session-init: Skipping SDK agent init for Cursor platform', { sessionDbId, promptNumber });
     }
 
+    // Semantic context injection: query Chroma for relevant past observations
+    // and inject as additionalContext so Claude receives relevant memory each prompt.
+    // Controlled by CLAUDE_MEM_SEMANTIC_INJECT setting (default: true).
+    const semanticInject =
+      String(settings.CLAUDE_MEM_SEMANTIC_INJECT).toLowerCase() === 'true';
+    let additionalContext = '';
+
+    if (semanticInject && prompt && prompt.length >= 20 && prompt !== '[media prompt]') {
+      try {
+        const limit = settings.CLAUDE_MEM_SEMANTIC_INJECT_LIMIT || '5';
+        const semanticRes = await workerHttpRequest('/api/context/semantic', {
+          method: 'POST',
+          headers: { 'Content-Type': 'application/json' },
+          body: JSON.stringify({ q: prompt, project, limit })
+        });
+        if (semanticRes.ok) {
+          const data = await semanticRes.json() as { context: string; count: number };
+          if (data.context) {
+            additionalContext = data.context;
+            logger.debug('HOOK', `Semantic injection: ${data.count} observations for prompt`, {
+              sessionId: sessionDbId, count: data.count
+            });
+          }
+        }
+      } catch (e) {
+        // Graceful degradation — semantic injection is optional
+        logger.debug('HOOK', 'Semantic injection unavailable', {
+          error: e instanceof Error ? e.message : String(e)
+        });
+      }
+    }
+
     logger.info('HOOK', `INIT_COMPLETE | sessionDbId=${sessionDbId} | promptNumber=${promptNumber} | project=${project}`, {
       sessionId: sessionDbId
     });
 
+    // Return with semantic context if available
+    if (additionalContext) {
+      return {
+        continue: true,
+        suppressOutput: true,
+        hookSpecificOutput: {
+          hookEventName: 'UserPromptSubmit',
+          additionalContext
+        }
+      };
+    }
+
     return { continue: true, suppressOutput: true };
   }
 };

src/cli/handlers/summarize.ts

@@ -1,9 +1,16 @@
 /**
  * Summarize Handler - Stop
  *
- * Extracted from summary-hook.ts - sends summary request to worker.
- * Transcript parsing stays in the hook because only the hook has access to
- * the transcript file path.
+ * Runs in the Stop hook (120s timeout, not capped like SessionEnd).
+ * This is the ONLY place where we can reliably wait for async work.
+ *
+ * Flow:
+ * 1. Queue summarize request to worker
+ * 2. Poll worker until summary processing completes
+ * 3. Call /api/sessions/complete to clean up session
+ *
+ * SessionEnd (1.5s cap from Claude Code) is just a lightweight fallback —
+ * all real work must happen here in Stop.
  */
 
 import type { EventHandler, NormalizedHookInput, HookResult } from '../types.js';
@@ -13,6 +20,8 @@ import { extractLastMessage } from '../../shared/transcript-parser.js';
 import { HOOK_EXIT_CODES, HOOK_TIMEOUTS, getTimeout } from '../../shared/hook-constants.js';
 
 const SUMMARIZE_TIMEOUT_MS = getTimeout(HOOK_TIMEOUTS.DEFAULT);
+const POLL_INTERVAL_MS = 500;
+const MAX_WAIT_FOR_SUMMARY_MS = 110_000; // 110s — fits within Stop hook's 120s timeout
 
 export const summarizeHandler: EventHandler = {
   async execute(input: NormalizedHookInput): Promise<HookResult> {
@@ -43,11 +52,21 @@ export const summarizeHandler: EventHandler = {
       return { continue: true, suppressOutput: true, exitCode: HOOK_EXIT_CODES.SUCCESS };
     }
 
+    // Skip summary if transcript has no assistant message (prevents repeated
+    // empty summarize requests that pollute logs — upstream bug)
+    if (!lastAssistantMessage || !lastAssistantMessage.trim()) {
+      logger.debug('HOOK', 'No assistant message in transcript - skipping summary', {
+        sessionId,
+        transcriptPath
+      });
+      return { continue: true, suppressOutput: true, exitCode: HOOK_EXIT_CODES.SUCCESS };
+    }
+
     logger.dataIn('HOOK', 'Stop: Requesting summary', {
       hasLastAssistantMessage: !!lastAssistantMessage
     });
 
-    // Send to worker - worker handles privacy check and database operations
+    // 1. Queue summarize request — worker returns immediately with { status: 'queued' }
     const response = await workerHttpRequest('/api/sessions/summarize', {
       method: 'POST',
       headers: { 'Content-Type': 'application/json' },
@@ -59,11 +78,49 @@ export const summarizeHandler: EventHandler = {
     });
 
     if (!response.ok) {
-      // Return standard response even on failure (matches original behavior)
       return { continue: true, suppressOutput: true };
     }
 
-    logger.debug('HOOK', 'Summary request sent successfully');
+    logger.debug('HOOK', 'Summary request queued, waiting for completion');
+
+    // 2. Poll worker until pending work for this session is done.
+    //    This keeps the Stop hook alive (120s timeout) so the SDK agent
+    //    can finish processing the summary before SessionEnd kills the session.
+    const waitStart = Date.now();
+    while ((Date.now() - waitStart) < MAX_WAIT_FOR_SUMMARY_MS) {
+      await new Promise(resolve => setTimeout(resolve, POLL_INTERVAL_MS));
+      try {
+        const statusResponse = await workerHttpRequest(`/api/sessions/status?contentSessionId=${encodeURIComponent(sessionId)}`, {
+          timeoutMs: 5000
+        });
+        if (statusResponse.ok) {
+          const status = await statusResponse.json() as { queueLength?: number };
+          if ((status.queueLength ?? 0) === 0) {
+            logger.info('HOOK', 'Summary processing complete', {
+              waitedMs: Date.now() - waitStart
+            });
+            break;
+          }
+        }
+      } catch {
+        // Worker may be busy — keep polling
+      }
+    }
+
+    // 3. Complete the session — clean up active sessions map.
+    //    This runs here in Stop (120s timeout) instead of SessionEnd (1.5s cap)
+    //    so it reliably fires after summary work is done.
+    try {
+      await workerHttpRequest('/api/sessions/complete', {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ contentSessionId: sessionId }),
+        timeoutMs: 10_000
+      });
+      logger.info('HOOK', 'Session completed in Stop hook', { contentSessionId: sessionId });
+    } catch (err) {
+      logger.warn('HOOK', `Stop hook: session-complete failed: ${err instanceof Error ? err.message : err}`);
+    }
 
     return { continue: true, suppressOutput: true };
   }

src/cli/handlers/user-message.ts

@@ -23,9 +23,11 @@ export const userMessageHandler: EventHandler = {
     const project = basename(input.cwd ?? process.cwd());
 
     // Fetch formatted context directly from worker API
+    // Only request ANSI colors for platforms that render them (claude-code)
+    const colorsParam = input.platform === 'claude-code' ? '&colors=true' : '';
     try {
       const response = await workerHttpRequest(
-        `/api/context/inject?project=${encodeURIComponent(project)}&colors=true`
+        `/api/context/inject?project=${encodeURIComponent(project)}${colorsParam}`
       );
 
       if (!response.ok) {