modcomms/backend/app
michael 8a9a24ebe6 Parallelize LlamaParse document processing with asyncio.gather
Parse documents concurrently (up to 10 at a time via semaphore) instead
of serially. Each coroutine uses its own DB session for per-document
status updates, while a shared lock serializes job progress increments
on the main session to avoid session-sharing issues.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-12 17:39:01 -06:00
..
agents Pass proof metadata (channel, sub-channel, proof type) to AI agents during analysis 2026-02-12 11:30:38 -06:00
api Fix processing job not visible to background task (FK violation) 2026-02-12 16:09:50 -06:00
dependencies Reduce auth logging verbosity: INFO → DEBUG 2026-02-12 16:13:25 -06:00
models Fix SpecVersion/ProcessingJob circular relationship direction error 2026-02-12 15:42:35 -06:00
repositories Fix stuck processing state: auto-fail stale jobs, improve active job detection 2026-02-12 16:03:25 -06:00
services Parallelize LlamaParse document processing with asyncio.gather 2026-02-12 17:39:01 -06:00
websocket Wire up Errors tab in Auditing: auto-create ErrorItem on Analysis Error 2026-02-12 13:55:16 -06:00
__init__.py permissions changes 2025-12-18 16:51:27 +00:00
config.py Add Knowledge Base management system for AI agent specs 2026-02-12 15:00:36 -06:00
main.py Add Knowledge Base management system for AI agent specs 2026-02-12 15:00:36 -06:00