hermes 6bc9fa0e8d Resume retries after cooldown instead of giving up for the day ...

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.

2026-09-30 07:55:40 +00:00

..

__init__.py

Wiki Jokes: daily LLM jokes from Wikipedia featured article

2026-09-29 19:38:01 +00:00

config.py

Resume retries after cooldown instead of giving up for the day

2026-09-30 07:55:40 +00:00

db.py

Wiki Jokes: daily LLM jokes from Wikipedia featured article

2026-09-29 19:38:01 +00:00

generator.py

Resume retries after cooldown instead of giving up for the day

2026-09-30 07:55:40 +00:00

llm_client.py

Repair curly-quote JSON from LLM before parsing

2026-09-29 19:54:56 +00:00

main.py

Add security headers, external CSS, HTML escaping

2026-09-29 20:41:16 +00:00

templates.py

Add security headers, external CSS, HTML escaping

2026-09-29 20:41:16 +00:00

wiki_client.py

Wiki Jokes: daily LLM jokes from Wikipedia featured article

2026-09-29 19:38:01 +00:00