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

..

config

feat(ollama): improve configuration and dashboard integration

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

db

fix: resolve user dashboard field mapping and session consistency

2026-03-19 14:01:59 -04:00

middleware

chore: rebrand project to GopherGate

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

models

fix: improve analytics accuracy and cost calculation

2026-03-19 12:58:08 -04:00

providers

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

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

server

fix(ollama): increase timeout and add default max_tokens for large models

2026-04-07 13:42:10 +00:00

utils

fix: prioritize database provider configs and implement API key encryption

2026-03-25 13:04:26 +00:00