fix(openai): restore Codex xhigh thinking metadata (#82761) · openclaw/openclaw@c1c6730
steipete
·
2026-05-17
·
via Recent Commits to openclaw:main
| Original file line number | Diff line number | Diff line change |
|---|
@@ -25,6 +25,7 @@ Docs: https://docs.openclaw.ai
|
25 | 25 | ### Fixes |
26 | 26 | |
27 | 27 | - Channels/stream previews: contain rejected background draft-stream flushes so preview send failures do not surface as fatal unhandled rejections. Fixes #82712. (#82713) Thanks @coygeek. |
| 28 | +- Providers/OpenAI Codex: include base `gpt-5.5` and `gpt-5.4` reasoning metadata in the bundled Codex catalog so `/think xhigh` remains available for those models. Fixes #82744. |
28 | 29 | - Agents/edit tool: honor `file_path` and related path aliases when resolving edit-recovery targets, so post-write errors no longer surface false edit failures after the file actually changed. Fixes #81909. Thanks @giodl73-repo. |
29 | 30 | - QQBot: treat only explicit truthy `QQBOT_DEBUG` values as enabling debug logs, so false-like values such as `0` no longer expose debug output. Fixes #82644. (#82697) Thanks @leno23. |
30 | 31 | - Gateway/diagnostics: add opt-in critical memory pressure stability snapshots with gateway logs, V8 heap, cgroup, active-resource, and redacted large session-file evidence. Fixes #82518. |
|
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。
