mirror of
https://github.com/getcompanion-ai/co-mono.git
synced 2026-04-17 03:03:44 +00:00
989af79752
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
17 lines
835 B
Markdown
17 lines
835 B
Markdown
# Changelog
|
|
|
|
## [Unreleased]
|
|
|
|
### Fixed
|
|
|
|
- **OpenAI Token Counting**: Fixed `usage.input` to exclude cached tokens for OpenAI providers. Previously, `input` included cached tokens, causing double-counting when calculating total context size via `input + cacheRead`. Now `input` represents non-cached input tokens across all providers, making `input + output + cacheRead + cacheWrite` the correct formula for total context size.
|
|
|
|
- **Fixed Claude Opus 4.5 cache pricing** (was 3x too expensive)
|
|
- Corrected cache_read: $1.50 → $0.50 per MTok
|
|
- Corrected cache_write: $18.75 → $6.25 per MTok
|
|
- Added manual override in `scripts/generate-models.ts` until upstream fix is merged
|
|
- Submitted PR to models.dev: https://github.com/sst/models.dev/pull/439
|
|
|
|
## [0.9.4] - 2025-11-26
|
|
|
|
Initial release with multi-provider LLM support.
|