Kimi Agent 9c59b386d8 feat: add OLLAMA_NUM_CTX config to cap context window (#83) ...

- Add ollama_num_ctx setting (default 4096) to config.py
- Pass num_ctx option to Ollama in agent.py and agents/base.py
- Add OLLAMA_NUM_CTX to .env.example with usage docs
- Add context_window note in providers.yaml
- Fix mock_settings in test_agent.py for new attribute
- qwen3:30b with 4096 ctx uses ~19GB vs 45GB default

2026-03-14 18:54:43 -04:00

..

agents.yaml

[loop-cycle-1] feat: tool allowlist for autonomous operation (#69)

2026-03-14 17:39:48 -04:00

allowlist.yaml

[loop-cycle-1] feat: tool allowlist for autonomous operation (#69)

2026-03-14 17:39:48 -04:00

providers.yaml

feat: add OLLAMA_NUM_CTX config to cap context window (#83)

2026-03-14 18:54:43 -04:00