ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(ai): use HTTP timeout for Codex SSE headers

Browse Source 
Refs #4945
This commit is contained in:
Armin Ronacher
2026-06-28 19:57:47 +02:00
parent 8f64353e65
commit 54113731b2
3 changed files with 18 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/CHANGELOG.md
+4
View File
@@ -6,6 +6,10 @@
- Added an optional `reasoning` field to `Usage` reporting reasoning/thinking token counts as a subset of `output`. Populated for Anthropic (`output_tokens_details.thinking_tokens`), OpenAI Responses/Codex/Azure (`output_tokens_details.reasoning_tokens`), OpenAI Completions (`completion_tokens_details.reasoning_tokens`), and Google Generative AI / Vertex (`thoughtsTokenCount`). Bedrock Converse and Mistral are not populated because those APIs do not return a reasoning token breakdown ([#6057](https://github.com/earendil-works/pi/issues/6057)).
### Changed
- Changed OpenAI Codex Responses SSE response-header waits to use the configured HTTP timeout instead of the previous fixed 20 second timeout, reducing false timeouts on slow connections ([#4945](https://github.com/earendil-works/pi/issues/4945)).
### Fixed
- Fixed `streamSimple()` to send a context-aware max-token cap so providers that count input and output against one context window do not reject long requests ([#5595](https://github.com/earendil-works/pi/issues/5595)).