b1e9cdd182
- A1: fire the hard filter (Apify is precise); embedding vibe-ranker (embed.py) blends with the floor-free white-box (rank.py) to sift ~90 -> top 18 - A2: Opus curator (curate.py) reads the 18 -> honest <=count + Gemini-voiced report cards; graceful fallback to the white-box + templated cards - LLM via opencode.ai/zen gateway (llm.py): Opus chat + direct-OpenAI embeddings - Run LLM work off the event loop (asyncio.to_thread) so the Redis response publishes - C1: dedicated Postgres (app/db/) persists the per-user feed; get_scout_feed replays it so matches survive navigation/refresh - match contract + report-card fields (schema.py); skills.py; tests/
6 lines
316 B
Python
6 lines
316 B
Python
"""Persistence layer — a dedicated Postgres for the per-user feed (so matches survive navigation).
|
|
|
|
Optional by design: if `DATABASE_URL` is unset or the DB is unreachable, the engine still serves live
|
|
searches — it just can't replay them. Every call here degrades gracefully (logs + no-ops), never crashes.
|
|
"""
|