feat: Knowledge Agents — queryable corpora from claude-mem (#1653)

* feat: add knowledge agent types, store, builder, and renderer

Phase 1 of Knowledge Agents feature. Introduces corpus compilation
pipeline that filters observations from the database into portable
corpus files stored at ~/.claude-mem/corpora/.

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

* feat: add corpus CRUD HTTP endpoints and wire into worker service

Phase 2 of Knowledge Agents. Adds CorpusRoutes with 5 endpoints
(build, list, get, delete, rebuild) and registers them during
worker background initialization alongside SearchRoutes.

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

* feat: add KnowledgeAgent with V1 SDK prime/query/reprime

Phase 3 of Knowledge Agents. Uses Agent SDK V1 query() with
resume and disallowedTools for Q&A-only knowledge sessions.
Auto-reprimes on session expiry. Adds prime, query, and reprime
HTTP endpoints to CorpusRoutes.

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

* feat: add MCP tools and skill for knowledge agents

Phase 4 of Knowledge Agents. Adds build_corpus, list_corpora,
prime_corpus, and query_corpus MCP tools delegating to worker
HTTP endpoints. Includes /knowledge-agent skill with workflow docs.

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

* fix: handle SDK process exit in KnowledgeAgent, add e2e test

The Agent SDK may throw after yielding all messages when the
Claude process exits with a non-zero code. Now tolerates this
if session_id/answer were already captured. Adds comprehensive
e2e test script (31 assertions) orchestrated via tmux-cli.

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

* fix: use settings model ID instead of hardcoded model in KnowledgeAgent

Reads CLAUDE_MEM_MODEL from user settings via getModelId(), matching
the existing SDKAgent pattern. No more hardcoded model assumptions.

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

* feat: improve knowledge agents developer experience

Add public documentation page, rebuild/reprime MCP tools, and actionable
error messages. DX review scored knowledge agents 4/10 — core engineering
works (31/31 e2e) but the feature was invisible. This addresses
discoverability (docs, cross-links), API completeness (missing MCP tools),
and error quality (fix/example fields in error responses).

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

* docs: add quick start guide to knowledge agents page

Covers the three main use cases upfront: creating an agent, asking a
single question, and starting a fresh conversation with reprime. Includes
keeping-it-current section for rebuild + reprime workflow.

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

* fix: address code review issues — path traversal, session safety, prompt injection

- Block path traversal in CorpusStore with alphanumeric name validation and resolved path check
- Harden system prompt against instruction injection from untrusted corpus content
- Validate question field as non-empty string in query endpoint
- Only persist session_id after successful prime (not null on failure)
- Persist refreshed session_id after query execution
- Only auto-reprime on session resume errors, not all query failures
- Add fenced code block language tags to SKILL.md

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

* fix: address remaining code review issues — e2e robustness, MCP validation, docs

- Harden e2e curl wrappers with connect-timeout, fallback to HTTP 000 on transport failure
- Use curl_post wrapper consistently for all long-running POST calls
- Add runtime name validation to all corpus MCP tool handlers
- Fix docs: soften hallucination guarantee to probabilistic claim
- Fix architecture diagram: add missing rebuild_corpus and reprime_corpus tools

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

* fix: enforce string[] type in safeParseJsonArray for corpus data integrity

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

* fix: add blank line before fenced code blocks in SKILL.md maintenance section

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

---------

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

src/services/worker-service.ts

@@ -95,6 +95,12 @@ import { SearchRoutes } from './worker/http/routes/SearchRoutes.js';
 import { SettingsRoutes } from './worker/http/routes/SettingsRoutes.js';
 import { LogsRoutes } from './worker/http/routes/LogsRoutes.js';
 import { MemoryRoutes } from './worker/http/routes/MemoryRoutes.js';
+import { CorpusRoutes } from './worker/http/routes/CorpusRoutes.js';
+
+// Knowledge agent services
+import { CorpusStore } from './worker/knowledge/CorpusStore.js';
+import { CorpusBuilder } from './worker/knowledge/CorpusBuilder.js';
+import { KnowledgeAgent } from './worker/knowledge/KnowledgeAgent.js';
 
 // Process management for zombie cleanup (Issue #737)
 import { startOrphanReaper, reapOrphanedProcesses, getProcessBySession, ensureProcessExit } from './worker/ProcessRegistry.js';
@@ -143,6 +149,7 @@ export class WorkerService {
   private paginationHelper: PaginationHelper;
   private settingsManager: SettingsManager;
   private sessionEventBroadcaster: SessionEventBroadcaster;
+  private corpusStore: CorpusStore;
 
   // Route handlers
   private searchRoutes: SearchRoutes | null = null;
@@ -188,6 +195,7 @@ export class WorkerService {
     this.paginationHelper = new PaginationHelper(this.dbManager);
     this.settingsManager = new SettingsManager(this.dbManager);
     this.sessionEventBroadcaster = new SessionEventBroadcaster(this.sseBroadcaster, this);
+    this.corpusStore = new CorpusStore();
 
     // Set callback for when sessions are deleted
     this.sessionManager.setOnSessionDeleted(() => {
@@ -388,6 +396,22 @@ export class WorkerService {
       this.server.registerRoutes(this.searchRoutes);
       logger.info('WORKER', 'SearchManager initialized and search routes registered');
 
+      // Register corpus routes (knowledge agents) — needs SearchOrchestrator from search module
+      const { SearchOrchestrator } = await import('./worker/search/SearchOrchestrator.js');
+      const corpusSearchOrchestrator = new SearchOrchestrator(
+        this.dbManager.getSessionSearch(),
+        this.dbManager.getSessionStore(),
+        this.dbManager.getChromaSync()
+      );
+      const corpusBuilder = new CorpusBuilder(
+        this.dbManager.getSessionStore(),
+        corpusSearchOrchestrator,
+        this.corpusStore
+      );
+      const knowledgeAgent = new KnowledgeAgent(this.corpusStore);
+      this.server.registerRoutes(new CorpusRoutes(this.corpusStore, corpusBuilder, knowledgeAgent));
+      logger.info('WORKER', 'CorpusRoutes registered');
+
       // DB and search are ready — mark initialization complete so hooks can proceed.
       // MCP connection is tracked separately via mcpReady and is NOT required for
       // the worker to serve context/search requests.