3 Commits

Include renames

Author	SHA1	Message	Date
hermes	7dc32a50e2	Raise LLM read timeout to 300s; prefer LAN endpoint in env example ... Midnight failures were read timeouts against the public URL — hairpin NAT and/or the request queuing behind other traffic on the shared model. LAN endpoint + longer timeout covers both.	2026-09-30 08:06:18 +00:00
hermes	c6fd9a5c77	Repair curly-quote JSON from LLM before parsing ... halogen-qwen3.8-flash-next sometimes uses typographic quotes (“ ”) as JSON string delimiters, which breaks strict json.loads. Add a scanner that normalizes curly-delimited strings to straight quotes while preserving curly quotes used as content inside straight-quoted strings.	2026-09-29 19:54:56 +00:00
hermes	075b72ec6c	Wiki Jokes: daily LLM jokes from Wikipedia featured article ... - FastAPI + APScheduler + SQLite, single container - Daily generation at 06:00 Europe/Copenhagen + cold-start generation - Retry with backoff (3 attempts/15 min), stale fallback with banner - OpenAI-compatible endpoint via env (OPENAI_BASE_URL/MODEL/API_KEY) - docker-compose with named volume for joke persistence	2026-09-29 19:38:01 +00:00