Juan Camilo Auriti 60d3d8961a fix: add missing o1-series and Ollama models to context window table (#250) ...

Models not in the lookup table fall through to a 200k default, causing
auto-compact to never trigger for models with smaller actual context
windows. Users hit hard context_window_exceeded errors instead.

Added to both context window and max output token tables:
- o1, o1-mini, o1-preview, o1-pro (OpenAI reasoning models)
- llama3.2:1b, qwen3:8b, codestral (common Ollama models)

Relates to #248

2026-04-06 06:39:24 +08:00

5.8 KiB

Raw Blame History

View Raw