changelog: add codex MCP agent scoping and Responses cached usage clamp · openclaw/openclaw@947c951
vincentkoc
·
2026-05-16
·
via Recent Commits to openclaw:main
| Original file line number | Diff line number | Diff line change |
|---|
@@ -12,6 +12,8 @@ Docs: https://docs.openclaw.ai
|
12 | 12 | |
13 | 13 | ### Fixes |
14 | 14 | |
| 15 | +- Codex app-server/MCP: scope user MCP servers to specific OpenClaw agent ids through an optional `mcp.servers.<name>.codex.agents` list and accept `codex.defaultToolsApprovalMode` (`auto`/`prompt`/`approve`) for native Codex approval defaults; OpenClaw strips the `codex` block before handing `mcp_servers` config to Codex. (#82180) Thanks @sercada. |
| 16 | +- Agents/OpenAI Responses: clamp `input_tokens - cached_tokens` at zero and reconstruct `totalTokens` from input + output + cached components so Responses-API streams report consistent usage when providers under-report `input_tokens` relative to `cached_tokens`. |
15 | 17 | - Hooks: raise bounded gateway lifecycle hook wait budgets to 5 seconds for shutdown and 10 seconds for pre-restart, giving short restart notification handlers time to finish before shutdown continues. (#82273) Thanks @bryanbaer. |
16 | 18 | - Plugin releases: require external package compatibility metadata in the npm plugin publish plan, matching the ClawHub package contract before packages ship. |
17 | 19 | - Agents/OpenAI-compatible: honor per-model `max_completion_tokens`/`max_tokens` params in embedded OpenAI-completions runs so high-token Kimi-style routes keep their configured completion cap. Fixes #82230. Thanks @albert-zen. |
|
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。
