Mario Zechner 989af79752 fix: normalize OpenAI token counting, add branch source tracking ... pi-ai: - Fixed usage.input to exclude cached tokens for OpenAI providers - Previously input included cached tokens, causing double-counting - Now input + output + cacheRead + cacheWrite correctly gives total context coding-agent: - Session header now includes branchedFrom field for branched sessions - Updated compaction.md with refined implementation plan - Updated session.md with branchedFrom documentation		2025-12-03 17:11:22 +01:00
..
agent	chore: bump coding-agent to 0.7.14 - fix Anthropic OAuth and Mistral API compatibility	2025-11-17 12:46:59 +01:00
providers	fix: normalize OpenAI token counting, add branch source tracking	2025-12-03 17:11:22 +01:00
utils	Add Unicode surrogate sanitization for all providers	2025-10-13 14:26:54 +02:00
index.ts	refactor(ai): improve error handling and stop reason types	2025-09-18 19:57:13 +02:00
models.generated.ts	Use ordered root build instead of parallel workspace build in CI	2025-12-03 15:05:04 +01:00
models.ts	refactor(ai): Simplify API with new streaming interface and model management	2025-09-03 01:25:19 +02:00
stream.ts	Limit max output tokens to 32k	2025-10-30 15:47:36 +01:00
types.ts	Add custom headers support for models.json	2025-11-20 17:05:31 +01:00