backup: Phase 1 agent work (security, persistence, batch endpoint)

This is a backup of all work done by the 3 Phase 1 agents:

Agent A - Command Injection Fix (Issue #354):
- Fixed command injection in BranchManager.ts
- Fixed unnecessary shell usage in bun-path.ts
- Added comprehensive security test suite
- Created SECURITY.md and SECURITY_AUDIT_REPORT.md

Agent B - Observation Persistence Fix (Issue #353):
- Added PendingMessageStore from PR #335
- Integrated persistent queue into SessionManager
- Modified SDKAgent to mark messages complete
- Updated SessionStore with pending_messages migration
- Updated worker-types.ts with new interfaces

Agent C - Batch Endpoint Verification (Issue #348):
- Created batch-observations.test.ts
- Updated worker-service.mdx documentation

Also includes:
- Documentation context files (biomimetic, windows struggles)
- Build artifacts from agent testing

This work will be re-evaluated after v7.3.0 release.
This commit is contained in:
Alex Newman
2025-12-16 15:44:06 -05:00
parent 2e919df2b4
commit 282345f379
41 changed files with 3130 additions and 147 deletions
+367
View File
@@ -0,0 +1,367 @@
import { Database } from './sqlite-compat.js';
import type { PendingMessage } from '../worker-types.js';
/**
* Persistent pending message record from database
*/
export interface PersistentPendingMessage {
id: number;
session_db_id: number;
claude_session_id: string;
message_type: 'observation' | 'summarize';
tool_name: string | null;
tool_input: string | null;
tool_response: string | null;
cwd: string | null;
last_user_message: string | null;
last_assistant_message: string | null;
prompt_number: number | null;
status: 'pending' | 'processing' | 'processed' | 'failed';
retry_count: number;
created_at_epoch: number;
started_processing_at_epoch: number | null;
completed_at_epoch: number | null;
}
/**
* PendingMessageStore - Persistent work queue for SDK messages
*
* Messages are persisted before processing and marked complete after success.
* This enables recovery from SDK hangs and worker crashes.
*
* Lifecycle:
* 1. enqueue() - Message persisted with status 'pending'
* 2. markProcessing() - Status changes to 'processing' when yielded to SDK
* 3. markProcessed() - Status changes to 'processed' after successful SDK response
* 4. markFailed() - Status changes to 'failed' if max retries exceeded
*
* Recovery:
* - resetStuckMessages() - Moves 'processing' messages back to 'pending' if stuck
* - getSessionsWithPendingMessages() - Find sessions that need recovery on startup
*/
export class PendingMessageStore {
private db: Database;
private maxRetries: number;
constructor(db: Database, maxRetries: number = 3) {
this.db = db;
this.maxRetries = maxRetries;
}
/**
* Enqueue a new message (persist before processing)
* @returns The database ID of the persisted message
*/
enqueue(sessionDbId: number, claudeSessionId: string, message: PendingMessage): number {
const now = Date.now();
const stmt = this.db.prepare(`
INSERT INTO pending_messages (
session_db_id, claude_session_id, message_type,
tool_name, tool_input, tool_response, cwd,
last_user_message, last_assistant_message,
prompt_number, status, retry_count, created_at_epoch
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, 'pending', 0, ?)
`);
const result = stmt.run(
sessionDbId,
claudeSessionId,
message.type,
message.tool_name || null,
message.tool_input ? JSON.stringify(message.tool_input) : null,
message.tool_response ? JSON.stringify(message.tool_response) : null,
message.cwd || null,
message.last_user_message || null,
message.last_assistant_message || null,
message.prompt_number || null,
now
);
return result.lastInsertRowid as number;
}
/**
* Peek at oldest pending message for session (does NOT change status)
* @returns The oldest pending message or null if none
*/
peekPending(sessionDbId: number): PersistentPendingMessage | null {
const stmt = this.db.prepare(`
SELECT * FROM pending_messages
WHERE session_db_id = ? AND status = 'pending'
ORDER BY id ASC
LIMIT 1
`);
return stmt.get(sessionDbId) as PersistentPendingMessage | null;
}
/**
* Get all pending messages for session (ordered by creation time)
*/
getAllPending(sessionDbId: number): PersistentPendingMessage[] {
const stmt = this.db.prepare(`
SELECT * FROM pending_messages
WHERE session_db_id = ? AND status = 'pending'
ORDER BY id ASC
`);
return stmt.all(sessionDbId) as PersistentPendingMessage[];
}
/**
* Get all queue messages (for UI display)
* Returns pending, processing, and failed messages (not processed - they're deleted)
* Joins with sdk_sessions to get project name
*/
getQueueMessages(): (PersistentPendingMessage & { project: string | null })[] {
const stmt = this.db.prepare(`
SELECT pm.*, ss.project
FROM pending_messages pm
LEFT JOIN sdk_sessions ss ON pm.claude_session_id = ss.claude_session_id
WHERE pm.status IN ('pending', 'processing', 'failed')
ORDER BY
CASE pm.status
WHEN 'failed' THEN 0
WHEN 'processing' THEN 1
WHEN 'pending' THEN 2
END,
pm.created_at_epoch ASC
`);
return stmt.all() as (PersistentPendingMessage & { project: string | null })[];
}
/**
* Get count of stuck messages (processing longer than threshold)
*/
getStuckCount(thresholdMs: number): number {
const cutoff = Date.now() - thresholdMs;
const stmt = this.db.prepare(`
SELECT COUNT(*) as count FROM pending_messages
WHERE status = 'processing' AND started_processing_at_epoch < ?
`);
const result = stmt.get(cutoff) as { count: number };
return result.count;
}
/**
* Retry a specific message (reset to pending)
* Works for pending (re-queue), processing (reset stuck), and failed messages
*/
retryMessage(messageId: number): boolean {
const stmt = this.db.prepare(`
UPDATE pending_messages
SET status = 'pending', started_processing_at_epoch = NULL
WHERE id = ? AND status IN ('pending', 'processing', 'failed')
`);
const result = stmt.run(messageId);
return result.changes > 0;
}
/**
* Reset all processing messages for a session to pending
* Used when force-restarting a stuck session
*/
resetProcessingToPending(sessionDbId: number): number {
const stmt = this.db.prepare(`
UPDATE pending_messages
SET status = 'pending', started_processing_at_epoch = NULL
WHERE session_db_id = ? AND status = 'processing'
`);
const result = stmt.run(sessionDbId);
return result.changes;
}
/**
* Abort a specific message (delete from queue)
*/
abortMessage(messageId: number): boolean {
const stmt = this.db.prepare('DELETE FROM pending_messages WHERE id = ?');
const result = stmt.run(messageId);
return result.changes > 0;
}
/**
* Retry all stuck messages at once
*/
retryAllStuck(thresholdMs: number): number {
const cutoff = Date.now() - thresholdMs;
const stmt = this.db.prepare(`
UPDATE pending_messages
SET status = 'pending', started_processing_at_epoch = NULL
WHERE status = 'processing' AND started_processing_at_epoch < ?
`);
const result = stmt.run(cutoff);
return result.changes;
}
/**
* Get recently processed messages (for UI feedback)
* Shows messages completed in the last N minutes so users can see their stuck items were processed
*/
getRecentlyProcessed(limit: number = 10, withinMinutes: number = 30): (PersistentPendingMessage & { project: string | null })[] {
const cutoff = Date.now() - (withinMinutes * 60 * 1000);
const stmt = this.db.prepare(`
SELECT pm.*, ss.project
FROM pending_messages pm
LEFT JOIN sdk_sessions ss ON pm.claude_session_id = ss.claude_session_id
WHERE pm.status = 'processed' AND pm.completed_at_epoch > ?
ORDER BY pm.completed_at_epoch DESC
LIMIT ?
`);
return stmt.all(cutoff, limit) as (PersistentPendingMessage & { project: string | null })[];
}
/**
* Mark message as being processed (status: pending -> processing)
*/
markProcessing(messageId: number): void {
const now = Date.now();
const stmt = this.db.prepare(`
UPDATE pending_messages
SET status = 'processing', started_processing_at_epoch = ?
WHERE id = ? AND status = 'pending'
`);
stmt.run(now, messageId);
}
/**
* Mark message as successfully processed (status: processing -> processed)
*/
markProcessed(messageId: number): void {
const now = Date.now();
const stmt = this.db.prepare(`
UPDATE pending_messages
SET status = 'processed', completed_at_epoch = ?
WHERE id = ? AND status = 'processing'
`);
stmt.run(now, messageId);
}
/**
* Mark message as failed (status: processing -> failed or back to pending for retry)
* If retry_count < maxRetries, moves back to 'pending' for retry
* Otherwise marks as 'failed' permanently
*/
markFailed(messageId: number): void {
const now = Date.now();
// Get current retry count
const msg = this.db.prepare('SELECT retry_count FROM pending_messages WHERE id = ?').get(messageId) as { retry_count: number } | undefined;
if (!msg) return;
if (msg.retry_count < this.maxRetries) {
// Move back to pending for retry
const stmt = this.db.prepare(`
UPDATE pending_messages
SET status = 'pending', retry_count = retry_count + 1, started_processing_at_epoch = NULL
WHERE id = ?
`);
stmt.run(messageId);
} else {
// Max retries exceeded, mark as permanently failed
const stmt = this.db.prepare(`
UPDATE pending_messages
SET status = 'failed', completed_at_epoch = ?
WHERE id = ?
`);
stmt.run(now, messageId);
}
}
/**
* Reset stuck messages (processing -> pending if stuck longer than threshold)
* @param thresholdMs Messages processing longer than this are considered stuck (0 = reset all)
* @returns Number of messages reset
*/
resetStuckMessages(thresholdMs: number): number {
const cutoff = thresholdMs === 0 ? Date.now() : Date.now() - thresholdMs;
const stmt = this.db.prepare(`
UPDATE pending_messages
SET status = 'pending', started_processing_at_epoch = NULL
WHERE status = 'processing' AND started_processing_at_epoch < ?
`);
const result = stmt.run(cutoff);
return result.changes;
}
/**
* Get count of pending messages for a session
*/
getPendingCount(sessionDbId: number): number {
const stmt = this.db.prepare(`
SELECT COUNT(*) as count FROM pending_messages
WHERE session_db_id = ? AND status IN ('pending', 'processing')
`);
const result = stmt.get(sessionDbId) as { count: number };
return result.count;
}
/**
* Check if any session has pending work
*/
hasAnyPendingWork(): boolean {
const stmt = this.db.prepare(`
SELECT COUNT(*) as count FROM pending_messages
WHERE status IN ('pending', 'processing')
`);
const result = stmt.get() as { count: number };
return result.count > 0;
}
/**
* Get all session IDs that have pending messages (for recovery on startup)
*/
getSessionsWithPendingMessages(): number[] {
const stmt = this.db.prepare(`
SELECT DISTINCT session_db_id FROM pending_messages
WHERE status IN ('pending', 'processing')
`);
const results = stmt.all() as { session_db_id: number }[];
return results.map(r => r.session_db_id);
}
/**
* Get session info for a pending message (for recovery)
*/
getSessionInfoForMessage(messageId: number): { sessionDbId: number; claudeSessionId: string } | null {
const stmt = this.db.prepare(`
SELECT session_db_id, claude_session_id FROM pending_messages WHERE id = ?
`);
const result = stmt.get(messageId) as { session_db_id: number; claude_session_id: string } | undefined;
return result ? { sessionDbId: result.session_db_id, claudeSessionId: result.claude_session_id } : null;
}
/**
* Cleanup old processed messages (retention policy)
* @param retentionMs Delete processed messages older than this (0 = delete all processed)
* @returns Number of messages deleted
*/
cleanupProcessed(retentionMs: number): number {
const cutoff = retentionMs === 0 ? Date.now() : Date.now() - retentionMs;
const stmt = this.db.prepare(`
DELETE FROM pending_messages
WHERE status = 'processed' AND completed_at_epoch < ?
`);
const result = stmt.run(cutoff);
return result.changes;
}
/**
* Convert a PersistentPendingMessage back to PendingMessage format
*/
toPendingMessage(persistent: PersistentPendingMessage): PendingMessage {
return {
type: persistent.message_type,
tool_name: persistent.tool_name || undefined,
tool_input: persistent.tool_input ? JSON.parse(persistent.tool_input) : undefined,
tool_response: persistent.tool_response ? JSON.parse(persistent.tool_response) : undefined,
prompt_number: persistent.prompt_number || undefined,
cwd: persistent.cwd || undefined,
last_user_message: persistent.last_user_message || undefined,
last_assistant_message: persistent.last_assistant_message || undefined
};
}
}