hobokenchicken fdbb068a6c fix(ollama): map max_tokens to num_predict and increase context window ...

- Map MaxTokens to num_predict in options map
- Set default num_ctx to 8192 for common models (gemma, llama, etc.)
- This ensures Ollama doesn't cut off responses early due to default limits

2026-04-07 13:44:17 +00:00

..

deepseek.go

fix: improve cost tracking accuracy for modern models

2026-03-19 14:14:54 -04:00

gemini.go

feat(ollama): improve configuration and dashboard integration

2026-04-07 12:53:17 +00:00

grok.go

chore: rebrand project to GopherGate

2026-03-19 13:37:05 -04:00

helpers.go

fix(moonshot): resolve 401 Unauthorized errors by trimming API keys and improving request compatibility

2026-03-26 17:09:27 +00:00

moonshot.go

fix(moonshot): resolve 401 Unauthorized errors by trimming API keys and improving request compatibility

2026-03-26 17:09:27 +00:00

ollama.go

fix(ollama): map max_tokens to num_predict and increase context window

2026-04-07 13:44:17 +00:00

openai.go

chore: rebrand project to GopherGate

2026-03-19 13:37:05 -04:00

provider.go

chore: rebrand project to GopherGate

2026-03-19 13:37:05 -04:00