shumengya/sproutclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(ai): support xhigh for Codex GPT-5.5

Browse Source
This commit is contained in:
Mario Zechner
2026-04-23 22:49:09 +02:00
parent 8700ac1f0e
commit bf4aa3a601
7 changed files with 80 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
packages/ai/CHANGELOG.md
View File

@@ -8,6 +8,8 @@
### Fixed
- Fixed `anthropic-messages` tool streaming compatibility by adding `compat.supportsEagerToolInputStreaming`, allowing Anthropic-compatible providers to omit per-tool `eager_input_streaming` and use the legacy fine-grained tool streaming beta header instead ([#3575](https://github.com/badlogic/pi-mono/issues/3575))
- Fixed `supportsXhigh()` to recognize `openai-codex` `gpt-5.5`, preserving `xhigh` reasoning requests instead of clamping them to `high`.
- Fixed `openai-completions` streamed tool-call assembly to coalesce deltas by stable tool index when OpenAI-compatible gateways mutate tool call IDs mid-stream, preventing malformed Kimi K2.6/OpenCode tool streams from splitting one call into multiple bogus tool calls ([#3576](https://github.com/badlogic/pi-mono/issues/3576))
- Fixed `packages/ai` E2E coverage to use currently supported OpenAI Responses and OpenAI Codex models, and updated the Bedrock adaptive-thinking payload expectation to match the current `display: "summarized"` shape.
- Fixed built-in `kimi-coding` model generation to attach `User-Agent: KimiCLI/1.5` to all generated Kimi models, overriding the Anthropic SDK default UA so direct Kimi Coding requests use the provider's expected client identity ([#3586](https://github.com/badlogic/pi-mono/issues/3586))