hermes
6bc9fa0e8d
Previously 3 failed attempts at 06:00 (e.g. llamaswap model cold/starting) permanently blocked generation until the next day. Now the retry loop pauses SLOW_RETRY_MINUTES (default 60) after the burst budget is spent, then resumes — one attempt per hour until jokes exist.
21 lines
630 B
Bash
21 lines
630 B
Bash
# Copy to .env and adjust. docker compose reads this automatically.
|
|
|
|
# Any OpenAI-compatible endpoint (llamaswap example below)
|
|
OPENAI_BASE_URL=http://swap.obahan.xyz/v1
|
|
OPENAI_MODEL=halogen-qwen3.8-flash-next
|
|
OPENAI_API_KEY=***
|
|
|
|
# Daily generation time (in TZ below)
|
|
GENERATE_HOUR=6
|
|
GENERATE_MINUTE=0
|
|
|
|
# Failure handling: retry every RETRY_MINUTES, up to MAX_ATTEMPTS per day.
|
|
# After that, retries pause for SLOW_RETRY_MINUTES, then resume (so a cold
|
|
# LLM endpoint at 06:00 doesn't kill the whole day).
|
|
MAX_ATTEMPTS=3
|
|
RETRY_MINUTES=15
|
|
SLOW_RETRY_MINUTES=60
|
|
|
|
# Wikipedia language for the featured-article feed
|
|
WIKIPEDIA_LANG=en
|