Commit Graph

7 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
Madison Grubb 96480a351f make it start working again
ci/woodpecker/cron/ci Pipeline failed
2025-12-11 23:13:07 -05:00
Madison Grubb 714d0351ea fix png compression 2025-09-04 23:02:28 -04:00
keligrubb af315783e0 cleanup everything lol
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/cron/ci Pipeline was successful
2025-09-01 16:53:37 -04:00
keligrubb fc4589384d completely rework generation to make it more flavorful and fast.
ci/woodpecker/push/ci Pipeline failed
ci/woodpecker/cron/ci Pipeline failed
2025-08-30 23:03:15 -04:00
keligrubb ed95dd08a2 initial commit
ci/woodpecker/push/ci Pipeline was successful
2025-08-29 22:56:40 -04:00