fix(agents): honor disabled reasoning in thinking policy (#81454) · openclaw/openclaw@8c9ec07
giodl73-repo
·
2026-05-16
·
via Recent Commits to openclaw:main
| Original file line number | Diff line number | Diff line change |
|---|
@@ -675,6 +675,7 @@ Docs: https://docs.openclaw.ai
|
675 | 675 | - Codex app-server: keep per-agent `CODEX_HOME` isolation without rewriting `HOME` by default, so Codex-run subprocesses can still find normal user-home config, tokens, and CLI state unless the launch explicitly overrides `HOME`. Thanks @pashpashpash. |
676 | 676 | - iMessage: stop sending visible `<media:image>` placeholder text for media-only native image sends while preserving the internal echo key that prevents self-echo duplicate replies. (#81209) Thanks @homer-byte. |
677 | 677 | - Agents/sessions: create configured agent main sessions before first `sessions_send` or gateway send, so agent-to-agent messages no longer fail when the target agent has not started yet. |
| 678 | +- Google models: honor configured `reasoning: false` when resolving thinking policy, preventing non-thinking Google/Gemma models from advertising `thinking=medium`. Fixes #81424. |
678 | 679 | - gateway: pass Talk session scope to resolver [AI]. (#81379) Thanks @pgondhi987. |
679 | 680 | - Gateway protocol: require v4 clients and stream explicit chat `deltaText`/`replace` frames so SDK clients can consume assistant updates without local diffing. (#80725) Thanks @samzong. |
680 | 681 | - GitHub Copilot: exchange OAuth tokens for Copilot API tokens on image understanding requests and route Gemini image payloads through Chat Completions, fixing Copilot Gemini image descriptions. (#80393, #80442) Thanks @afunnyhy. |
|
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。
