can1357 a4026c588e fix(ai): corrected thinking config format and model context windows across 100+ definitions ...

- Fixed thinking configuration format by replacing `levels` array with `minLevel`/`maxLevel` properties across 100+ model definitions.
- Corrected GPT-5.4 mini/nano context window from 400000 to 272000 tokens for accurate token limit reporting.
- Normalized GPT-5.4 variant priority handling to use parsed variant instead of raw model IDs for consistent behavior.
- Added "mini" variant support to OpenAI model parsing regex and updated thinking mode configuration for Claude models.
- Fixed test robustness by replacing exact string matching with numeric range comparison to handle BSD seq notation on macOS.
- Corrected model generation script execution order to apply policy overrides before promotion target linking.

2026-03-21 17:34:38 +01:00

..

cursor-log.py

feat(ai): added conversation caching, JSONL debug logging, and cursor-log.py script

2026-01-11 08:28:09 +01:00

generate-models.ts

fix(ai): corrected thinking config format and model context windows across 100+ definitions

2026-03-21 17:34:38 +01:00

proto-extractor.py

feat(ai): added conversation caching, JSONL debug logging, and cursor-log.py script

2026-01-11 08:28:09 +01:00