Merge branch 'main' into cleanup/a2a-batch-stamp-crossprocess

Delete one-DB-era @deprecated shims and dead exports

container/agent-runner/src/current-batch.ts

@@ -1,29 +0,0 @@
-/**
- * Per-batch context the poll loop publishes for downstream consumers
- * (MCP tools, etc.) that don't sit on the poll-loop's call stack.
- *
- * Today the only field is `inReplyTo` — the id of the first inbound
- * message in the batch the agent is currently processing. MCP tools like
- * `send_message` and `send_file` read this and stamp it onto the outbound
- * row so the host's a2a return-path routing can correlate replies back to
- * the originating session.
- *
- * This is module-level state on purpose: the agent-runner is single-process
- * and processes one batch at a time. Poll-loop calls `setCurrentInReplyTo`
- * before invoking the provider and `clearCurrentInReplyTo` after the batch
- * completes (or errors out).
- */
-let currentInReplyTo: string | null = null;
-
-export function setCurrentInReplyTo(id: string | null): void {
-  currentInReplyTo = id;
-}
-
-export function clearCurrentInReplyTo(): void {
-  currentInReplyTo = null;
-}
-
-export function getCurrentInReplyTo(): string | null {
-  return currentInReplyTo;
-}
-

container/agent-runner/src/db/connection.ts

@@ -48,7 +48,11 @@ export function openInboundDb(): Database {
   // so the singleton survives for the rest of the test.
   if (_testMode && _inbound) {
     const db = _inbound;
-    return { prepare: (sql: string) => db.prepare(sql), exec: (sql: string) => db.exec(sql), close: () => {} } as unknown as Database;
+    return {
+      prepare: (sql: string) => db.prepare(sql),
+      exec: (sql: string) => db.exec(sql),
+      close: () => {},
+    } as unknown as Database;
   }
   const db = new Database(DEFAULT_INBOUND_PATH, { readonly: true });
   db.exec('PRAGMA busy_timeout = 5000');
@@ -260,11 +264,3 @@ export function closeSessionDb(): void {
   _outbound?.close();
   _outbound = null;
 }
-
-/**
- * @deprecated Use getInboundDb() / getOutboundDb() instead.
- * Kept for backward compatibility during migration.
- */
-export function getSessionDb(): Database {
-  return getInboundDb();
-}

container/agent-runner/src/db/index.ts

@@ -1,7 +1,6 @@
 export {
   getInboundDb,
   getOutboundDb,
-  getSessionDb,
   initTestSessionDb,
   closeSessionDb,
   touchHeartbeat,

container/agent-runner/src/db/session-state.ts

@@ -77,3 +77,47 @@ export function setContinuation(providerName: string, id: string): void {
 export function clearContinuation(providerName: string): void {
   deleteValue(continuationKey(providerName));
 }
+
+/**
+ * The a2a reply stamp: the id of the first inbound message in the batch the
+ * agent is currently processing. The poll loop publishes it at batch start;
+ * MCP tools (`send_message`, `send_file`) read it and stamp it onto outbound
+ * rows so the host's a2a return-path routing can correlate replies back to
+ * the originating session.
+ *
+ * This lives in outbound.db rather than module state because the MCP server
+ * runs as a separate stdio subprocess from the poll loop — module state set
+ * by the poll loop is invisible to it. Both processes open outbound.db
+ * (journal_mode=DELETE + busy_timeout make intra-container access safe).
+ */
+const IN_REPLY_TO_KEY = 'current_in_reply_to';
+
+/**
+ * Ignore a stamp older than this. The poll loop clears the stamp in a
+ * finally, but a container killed mid-batch (SIGKILL) can leave one behind;
+ * the guard stops a later out-of-batch read from picking up a dead stamp.
+ * Generous so a long-running batch's late sends still stamp correctly.
+ */
+const IN_REPLY_TO_MAX_AGE_MS = 30 * 60 * 1000;
+
+export function setCurrentInReplyTo(id: string | null): void {
+  if (id === null) {
+    clearCurrentInReplyTo();
+    return;
+  }
+  setValue(IN_REPLY_TO_KEY, id);
+}
+
+export function clearCurrentInReplyTo(): void {
+  deleteValue(IN_REPLY_TO_KEY);
+}
+
+export function getCurrentInReplyTo(): string | null {
+  const row = getOutboundDb()
+    .prepare('SELECT value, updated_at FROM session_state WHERE key = ?')
+    .get(IN_REPLY_TO_KEY) as { value: string; updated_at: string } | undefined;
+  if (!row) return null;
+  const age = Date.now() - new Date(row.updated_at).getTime();
+  if (!Number.isFinite(age) || age > IN_REPLY_TO_MAX_AGE_MS) return null;
+  return row.value;
+}

container/agent-runner/src/mcp-tools/core.test.ts

@@ -4,14 +4,31 @@
  * batch in poll-loop, and outbound writes from MCP tools (send_message,
  * send_file) must pick it up so a2a return-path routing on the host can
  * correlate replies back to the originating session.
+ *
+ * The stamp is published through session_state in outbound.db, not module
+ * state — the MCP server runs as a separate stdio subprocess from the poll
+ * loop, so it can only see the stamp through the shared DB. These tests seed
+ * it the same way the poll-loop process does (a direct DB write) rather than
+ * via any in-memory helper, so they exercise the real process boundary.
  */
 import { describe, it, expect, beforeEach, afterEach } from 'bun:test';
 
-import { initTestSessionDb, closeSessionDb, getInboundDb } from '../db/connection.js';
+import { initTestSessionDb, closeSessionDb, getInboundDb, getOutboundDb } from '../db/connection.js';
 import { getUndeliveredMessages } from '../db/messages-out.js';
-import { setCurrentInReplyTo, clearCurrentInReplyTo } from '../current-batch.js';
 import { sendMessage } from './core.js';
 
+/**
+ * Publish the a2a reply stamp the way the poll loop does: a direct write to
+ * session_state in outbound.db. `ageMs` back-dates updated_at to exercise the
+ * staleness guard MCP tools apply when reading it.
+ */
+function publishInReplyTo(id: string, ageMs = 0): void {
+  const updatedAt = new Date(Date.now() - ageMs).toISOString();
+  getOutboundDb()
+    .prepare('INSERT OR REPLACE INTO session_state (key, value, updated_at) VALUES (?, ?, ?)')
+    .run('current_in_reply_to', id, updatedAt);
+}
+
 beforeEach(() => {
   initTestSessionDb();
   // Seed a peer agent destination
@@ -24,13 +41,12 @@ beforeEach(() => {
 });
 
 afterEach(() => {
-  clearCurrentInReplyTo();
   closeSessionDb();
 });
 
 describe('send_message MCP tool — in_reply_to plumbing', () => {
-  it('stamps current batch in_reply_to on outbound rows', async () => {
-    setCurrentInReplyTo('inbound-msg-1');
+  it('stamps the batch in_reply_to (published via the DB) on outbound rows', async () => {
+    publishInReplyTo('inbound-msg-1');
 
     await sendMessage.handler({ to: 'peer', text: 'hello' });
 
@@ -40,7 +56,17 @@ describe('send_message MCP tool — in_reply_to plumbing', () => {
   });
 
   it('writes null when no batch is active', async () => {
-    // No setCurrentInReplyTo before this call — simulates ad-hoc / out-of-batch invocation.
+    // Nothing published to session_state — simulates ad-hoc / out-of-batch invocation.
+    await sendMessage.handler({ to: 'peer', text: 'hello' });
+
+    const out = getUndeliveredMessages();
+    expect(out).toHaveLength(1);
+    expect(out[0].in_reply_to).toBeNull();
+  });
+
+  it('ignores a stale stamp left behind by a killed container', async () => {
+    publishInReplyTo('inbound-msg-1', 60 * 60 * 1000); // an hour old
+
     await sendMessage.handler({ to: 'peer', text: 'hello' });
 
     const out = getUndeliveredMessages();

container/agent-runner/src/mcp-tools/core.ts

@@ -9,9 +9,9 @@
 import fs from 'fs';
 import path from 'path';
 
-import { getCurrentInReplyTo } from '../current-batch.js';
 import { findByName, getAllDestinations } from '../destinations.js';
 import { getMessageIdBySeq, getRoutingBySeq, writeMessageOut } from '../db/messages-out.js';
+import { getCurrentInReplyTo } from '../db/session-state.js';
 import { getSessionRouting } from '../db/session-routing.js';
 import { registerTools } from './server.js';
 import type { McpToolDefinition } from './types.js';

container/agent-runner/src/poll-loop.ts

@@ -2,8 +2,13 @@ import { findByName, getAllDestinations, type DestinationEntry } from './destina
 import { getPendingMessages, markProcessing, markCompleted, type MessageInRow } from './db/messages-in.js';
 import { writeMessageOut } from './db/messages-out.js';
 import { getInboundDb, touchHeartbeat, clearStaleProcessingAcks } from './db/connection.js';
-import { clearContinuation, migrateLegacyContinuation, setContinuation } from './db/session-state.js';
-import { clearCurrentInReplyTo, setCurrentInReplyTo } from './current-batch.js';
+import {
+  clearContinuation,
+  clearCurrentInReplyTo,
+  migrateLegacyContinuation,
+  setContinuation,
+  setCurrentInReplyTo,
+} from './db/session-state.js';
 import {
   formatMessages,
   extractRouting,

package.json

@@ -1,6 +1,6 @@
 {
   "name": "nanoclaw",
-  "version": "2.1.33",
+  "version": "2.1.34",
   "description": "Personal Claude assistant. Lightweight, secure, customizable.",
   "type": "module",
   "packageManager": "pnpm@10.33.0",

scripts/test-v2-agent.ts

@@ -33,7 +33,9 @@ db.exec(`
 `);
 
 // Insert test message
-db.prepare(`INSERT INTO messages_in (id, kind, timestamp, status, content) VALUES (?, 'chat', datetime('now'), 'pending', ?)`).run(
+db.prepare(
+  `INSERT INTO messages_in (id, kind, timestamp, status, content) VALUES (?, 'chat', datetime('now'), 'pending', ?)`,
+).run(
   'test-1',
   JSON.stringify({ sender: 'Gavriel', text: 'Say "Hello from v2!" and nothing else. Do not use any tools.' }),
 );
@@ -44,7 +46,7 @@ db.close();
 process.env.SESSION_DB_PATH = DB_PATH;
 process.env.AGENT_PROVIDER = 'claude';
 
-const { getSessionDb, closeSessionDb } = await import('../container/agent-runner/src/db/connection.js');
+const { getInboundDb, closeSessionDb } = await import('../container/agent-runner/src/db/connection.js');
 const { getUndeliveredMessages } = await import('../container/agent-runner/src/db/messages-out.js');
 const { getPendingMessages } = await import('../container/agent-runner/src/db/messages-in.js');
 const { createProvider } = await import('../container/agent-runner/src/providers/factory.js');

scripts/test-v2-channel-e2e.ts

@@ -71,7 +71,7 @@ import { routeInbound } from '../src/router.js';
 import { setDeliveryAdapter, startActiveDeliveryPoll, stopDeliveryPolls } from '../src/delivery.js';
 import { getChannelAdapter, registerChannelAdapter, initChannelAdapters } from '../src/channels/channel-registry.js';
 import { findSession } from '../src/db/sessions.js';
-import { sessionDbPath } from '../src/session-manager.js';
+import { inboundDbPath } from '../src/session-manager.js';
 import type { ChannelAdapter, ChannelSetup, OutboundMessage } from '../src/channels/adapter.js';
 
 // Track delivered messages
@@ -99,7 +99,9 @@ const mockAdapter: ChannelAdapter = {
 
   async setTyping() {},
   async teardown() {},
-  isConnected() { return true; },
+  isConnected() {
+    return true;
+  },
 };
 
 // Register mock adapter
@@ -179,15 +181,19 @@ console.log(`✓ Container status: ${session.container_status}`);
 import { execSync } from 'child_process';
 const checkContainerLogs = () => {
   try {
-    const containers = execSync('docker ps -a --filter name=nanoclaw-v2-test-channel --format "{{.Names}}"').toString().trim();
+    const containers = execSync('docker ps -a --filter name=nanoclaw-v2-test-channel --format "{{.Names}}"')
+      .toString()
+      .trim();
     for (const name of containers.split('\n').filter(Boolean)) {
       console.log(`\nContainer logs (${name}):`);
       console.log(execSync(`docker logs ${name} 2>&1`).toString());
     }
-  } catch { /* ignore */ }
+  } catch {
+    /* ignore */
+  }
 };
 
-const sessDbPath = sessionDbPath('ag-chan', session.id);
+const sessDbPath = inboundDbPath('ag-chan', session.id);
 console.log(`✓ Session DB: ${sessDbPath}`);
 
 // --- Step 4: Wait for delivery through mock adapter ---
@@ -210,7 +216,9 @@ await new Promise<void>((resolve) => {
         console.log(`  messages_out rows: ${out.length}`);
         if (out.length > 0) console.log('  (messages exist but delivery failed)');
         db.close();
-      } catch { /* ignore */ }
+      } catch {
+        /* ignore */
+      }
       checkContainerLogs();
       cleanup();
       process.exit(1);

src/db/session-db.ts

@@ -181,14 +181,6 @@ export function syncProcessingAcks(inDb: Database.Database, outDb: Database.Data
   })();
 }
 
-export function getStuckProcessingIds(outDb: Database.Database): string[] {
-  return (
-    outDb.prepare("SELECT message_id FROM processing_ack WHERE status = 'processing'").all() as Array<{
-      message_id: string;
-    }>
-  ).map((r) => r.message_id);
-}
-
 export interface ProcessingClaim {
   message_id: string;
   status_changed: string;

src/index.ts

@@ -24,16 +24,7 @@ import { enforceUpgradeTripwire } from './upgrade-state.js';
 // effects, and the modules call registerResponseHandler/onShutdown at top
 // level — which would hit a TDZ error if the arrays lived here. Re-exported
 // here so existing callers see the same surface.
-import {
-  registerResponseHandler,
-  getResponseHandlers,
-  onShutdown,
-  getShutdownCallbacks,
-  type ResponsePayload,
-  type ResponseHandler,
-} from './response-registry.js';
-export { registerResponseHandler, onShutdown };
-export type { ResponsePayload, ResponseHandler };
+import { getResponseHandlers, getShutdownCallbacks, type ResponsePayload } from './response-registry.js';
 
 async function dispatchResponse(payload: ResponsePayload): Promise<void> {
   for (const handler of getResponseHandlers()) {

src/session-manager.ts

@@ -64,14 +64,6 @@ export function heartbeatPath(agentGroupId: string, sessionId: string): string {
   return path.join(sessionDir(agentGroupId, sessionId), '.heartbeat');
 }
 
-/**
- * @deprecated Use inboundDbPath / outboundDbPath instead.
- * Kept temporarily for test compatibility during migration.
- */
-export function sessionDbPath(agentGroupId: string, sessionId: string): string {
-  return inboundDbPath(agentGroupId, sessionId);
-}
-
 function generateId(): string {
   return `sess-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`;
 }
@@ -402,34 +394,6 @@ export function writeOutboundDirect(
   }
 }
 
-/**
- * @deprecated Use openInboundDb / openOutboundDb instead.
- */
-export function openSessionDb(agentGroupId: string, sessionId: string): Database.Database {
-  return openInboundDb(agentGroupId, sessionId);
-}
-
-/** Write a system response to a session's inbound.db so the container's findQuestionResponse() picks it up. */
-export function writeSystemResponse(
-  agentGroupId: string,
-  sessionId: string,
-  requestId: string,
-  status: string,
-  result: Record<string, unknown>,
-): void {
-  writeSessionMessage(agentGroupId, sessionId, {
-    id: `sys-resp-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`,
-    kind: 'system',
-    timestamp: new Date().toISOString(),
-    content: JSON.stringify({
-      type: 'question_response',
-      questionId: requestId,
-      status,
-      result,
-    }),
-  });
-}
-
 /**
  * Load outbox attachments for a delivered message.
  *