docs: note codex dynamic tool fingerprint fix (#69976) · openclaw/openclaw@4177b27
steipete
·
2026-04-23
·
via Recent Commits to openclaw:main
| Original file line number | Diff line number | Diff line change |
|---|
@@ -28,6 +28,7 @@ Docs: https://docs.openclaw.ai
|
28 | 28 | |
29 | 29 | ### Fixes |
30 | 30 | |
| 31 | +- Codex harness: ignore dynamic tool descriptions when deciding whether to reuse a native app-server thread while still fingerprinting tool schemas, so channel-specific copy changes no longer reset otherwise compatible Codex conversations. (#69976) Thanks @chen-zhang-cs-code. |
31 | 32 | - Codex harness: show bounded, sanitized permission target samples in app-server approval prompts, so native permission requests keep their specific hosts, roots, and paths visible without leaking home usernames or URL credentials. (#70340) Thanks @Lucenx9. |
32 | 33 | - Docs/Codex harness: narrow native compaction docs to the current start/completion signals, without promising a readable summary or kept-entry audit list yet. (#69612) Thanks @91wan. |
33 | 34 | - Providers/Amazon Bedrock: use known context-window metadata for discovered models while keeping the unknown-model fallback conservative, so compaction and overflow handling improve for newer Bedrock models without overstating unlisted model limits. Thanks @wirjo. |
|
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。
