3 Commits

Author SHA1 Message Date
keligrubb 7ea9f93dc8 Improve LLM client immutability and CI model defaults. (#9)
Release / generate-dungeon (push) Failing after 2m30s
Release / upload-to-gitea-release (push) Has been skipped
Replace mutable Ollama model export with a const fallback and initializeModel return value, resolving the model from the environment after optional API discovery. Use a for-of loop over attempt indices instead of let in the retry path.

Continue PDF generation when map image generation or upscaling fails, and avoid mutating request headers in place.

Document Open WebUI-style URLs in the README, pin OLLAMA_MODEL in the Gitea release workflow, and adjust integration and unit tests for the new initialization behavior.

Reviewed-on: #9
Co-authored-by: keligrubb <keligrubb324@gmail.com>
Co-committed-by: keligrubb <keligrubb324@gmail.com>
2026-04-15 02:45:25 +00:00
keligrubb 83eee20b2c add testing suite 2026-02-21 22:19:21 -05:00
keligrubb 96223b81e6 more tweaks
ci/woodpecker/cron/ci Pipeline was successful
2026-01-19 22:37:53 -05:00