### 亮点
- **对话自动快模式:** OpenClaw 可为短轮次对话启用快模式,随后在带有有界回退和投递行为的长轮次中返回正常模式。(#85104)感谢 @alexph-dev 和 @vincentkoc。
- **更可靠的模型路由:** Zai 模型合成、GLM 过载故障转移以及原生推理层级选择现在能更一致地遵循活跃模型目录。(#94461、#93241、#94067、#94136)感谢 @Pandah97、@chrysb、@0xghost42、@zhengli0922、@openperf、@civiltox 和 @BorClaw。
- **更安全的会话和频道状态:** 频道切换会重置过时的源字段,cron 投递感知保持附加到目标会话上。(#95328、#93580)感谢 @ZengWen-DT、@jalehman、@gorkem2020 和 @scotthuang。
- **受信任策略在钩子组合中存活:** 组合的钩子注册表保留审批敏感流程所需的受信任工具策略。(#94545)感谢 @jesse-merhi。
### 变更
- **代理和频道运行时:** 快模式状态现在在重试、回退转换、进度事件以及嵌入式/CLI/ACP 规范化中保持;会话和频道路由保留当前目标和投递上下文。(#85104、#93580、#95328)感谢 @alexph-dev、@vincentkoc、@scotthuang、@ZengWen-DT、@jalehman 和 @gorkem2020。
- **提供商行为:** 模型目录现在为实时发现的模型提供正确的 Zai 基础 URL、过载分类和原生推理控制。(#94461、#93241、#94067、#94136)感谢 @Pandah97、@chrysb、@0xghost42、@zhengli0922、@openperf、@civiltox 和 @BorClaw。
### 修复
- **快模式和策略正确性:** 回退截断和重置通知有界,重复的进度事件保持可见,Codex 服务层级状态已规范化,并且组合钩子注册表时不会丢失受信任策略。(#85104、#94545)感谢 @alexph-dev、@vincentkoc 和 @jesse-merhi。
- **模型和投递边缘情况:** Zai 和 GLM 故障转移路径使用正确的运行时元数据,过时的频道源状态不再跨会话更改泄露。(#94461、#93241、#95328)感谢 @Pandah97、@chrysb、@0xghost42、@zhengli0922、@ZengWen-DT、@jalehman 和 @gorkem2020。
- **提供商插件入门:** 安装通过设置选择的提供商插件后,安装程序会刷新提供商插件注册表元数据,因此身份验证延续会使用新安装的提供商而不是过时的注册表状态。(#95792)感谢 @snowzlmbot。
### 完整贡献记录
本审计记录涵盖完整的 v2026.6.9..HEAD 历史:12 个已合并的 PR。生成清单也提供直接提交作为编辑输入;上述分组说明优先考虑用户影响。
#### 拉取请求
- **PR #86627** 按贡献顺序保持核心医生健康。感谢 @giodl73-repo。
- **PR #93580** 修复:保留目标会话的 cron 投递感知。感谢 @scotthuang 和 @jalehman。
- **PR #95030** 重构:添加 SDK 转录本身份目标 API。感谢 @jalehman。
- **PR #94838** 重构(copilot):完成 harness 生命周期对等。感谢 @vincentkoc。
- **PR #95328** 修复(会话):在频道切换时重置每个频道的过时源字段。关联 #95325。感谢 @ZengWen-DT、@jalehman 和 @gorkem2020。
- **PR #94461** 修复(zai):回退到清单 baseUrl 以合成 GLM-5 模型。关联 #94269。感谢 @Pandah97 和 @chrysb。
- **PR #93241** 修复(代理):将智谱 GLM 过载分类为过载以进行故障转移。关联 #93211。感谢 @0xghost42 和 @zhengli0922。
- **PR #94067** 修复(频道):通过运行时目录解析实时发现的模型的原生 /think 菜单层级。关联 #93835。感谢 @openperf 和 @civiltox。
- **PR #94136** 修复(zai):公开 GLM-5.2 推理层级 [AI 辅助]。感谢 @BorClaw。
- **PR #85104** 特性:快速对话自动模式。关联 #85087。感谢 @alexph-dev。
- **PR #94545** 修复:在钩子注册表中保留受信任策略。感谢 @jesse-merhi。
- **PR #95792** 修复(入门):在 setup 安装后刷新提供商插件注册表。关联 #95765。感谢 @snowzlmbot。
### 发布验证
- npm 包:https://www.npmjs.com/package/openclaw/v/2026.6.10
- 注册表压缩包:https://registry.npmjs.org/openclaw/-/openclaw-2026.6.10.tgz
- 完整性:`sha512-LcooND2tBQw8A+kc1Ujltu3lg30bJ0w7XaeRy7eYzobb8BBdcW6DOGbwJL4vpj1vl9+gjRceOtlh5nh9OARcug==`
- 发布 SHA:`aa69b12d0086b631b139c1435c9621a5783e3a40`
- 完整发布 CI 报告:https://github.com/openclaw/releases/blob/main/evidence/2026.6.10/release-evidence.md
- 发布发布:https://github.com/openclaw/openclaw/actions/runs/28071368306
- npm 预检:https://github.com/openclaw/openclaw/actions/runs/28068484614
- 完整发布验证:https://github.com/openclaw/openclaw/actions/runs/28068476120
- 插件 npm 发布:https://github.com/openclaw/openclaw/actions/runs/28071564667
- 插件 ClawHub 发布:https://github.com/openclaw/openclaw/actions/runs/28071565774
- 插件 ClawHub 引导:不需要
- OpenClaw npm 发布:https://github.com/openclaw/openclaw/actions/runs/28071984141
- npm Telegram beta E2E:未提供
- Windows Hub 推广:https://github.com/openclaw/openclaw/actions/runs/28072271374 来自 openclaw/
[email protected]
### Highlights
- **Automatic fast mode for talks:** OpenClaw can enable fast mode for short conversational turns, then return to normal mode for longer runs with bounded fallback and delivery behavior. (#85104) Thanks @alexph-dev and @vincentkoc.
- **More reliable model routing:** Zai model synthesis, GLM overload failover, and native reasoning-level selection now follow the active model catalog more consistently. (#94461, #93241, #94067, #94136) Thanks @Pandah97, @chrysb, @0xghost42, @zhengli0922, @openperf, @civiltox, and @BorClaw.
- **Safer session and channel state:** channel switches reset stale origin fields, and cron delivery awareness stays attached to the target session. (#95328, #93580) Thanks @ZengWen-DT, @jalehman, @gorkem2020, and @scotthuang.
- **Trusted policies survive hook composition:** composed hook registries keep the trusted tool policies required by approval-sensitive flows. (#94545) Thanks @jesse-merhi.
### Changes
- **Agent and channel runtime:** fast-mode state now survives retries, fallback transitions, progress events, and embedded/CLI/ACP normalization; session and channel routing retain the current target and delivery context. (#85104, #93580, #95328) Thanks @alexph-dev, @vincentkoc, @scotthuang, @ZengWen-DT, @jalehman, and @gorkem2020.
- **Provider behavior:** model catalogs now supply the correct Zai base URL, overload classification, and native reasoning controls for live-discovered models. (#94461, #93241, #94067, #94136) Thanks @Pandah97, @chrysb, @0xghost42, @zhengli0922, @openperf, @civiltox, and @BorClaw.
### Fixes
- **Fast-mode and policy correctness:** fallback cutoffs and reset notices are bounded, repeated progress events remain visible, Codex service-tier state is normalized, and trusted policies are not lost when hook registries are composed. (#85104, #94545) Thanks @alexph-dev, @vincentkoc, and @jesse-merhi.
- **Model and delivery edge cases:** Zai and GLM failover paths use the right runtime metadata, while stale channel-origin state no longer leaks across session changes. (#94461, #93241, #95328) Thanks @Pandah97, @chrysb, @0xghost42, @zhengli0922, @ZengWen-DT, @jalehman, and @gorkem2020.
- **Provider plugin onboarding:** setup refreshes provider plugin registry metadata after installing setup-selected provider plugins, so auth continuation uses the newly installed provider instead of stale registry state. (#95792) Thanks @snowzlmbot.
### Complete contribution record
This audited record covers the complete v2026.6.9..HEAD history: 12 merged PRs. The generation manifest also supplies direct commits as editorial input; the grouped notes above prioritize user impact.
#### Pull requests
- **PR #86627** Keep core doctor health in contribution order. Thanks @giodl73-repo.
- **PR #93580** fix: preserve cron delivery awareness for target sessions. Thanks @scotthuang and @jalehman.
- **PR #95030** refactor: add SDK transcript identity target API. Thanks @jalehman.
- **PR #94838** refactor(copilot): complete harness lifecycle parity. Thanks @vincentkoc.
- **PR #95328** fix(sessions): reset stale per-channel origin fields on channel switch. Related #95325. Thanks @ZengWen-DT and @jalehman and @gorkem2020.
- **PR #94461** fix(zai): fall back to manifest baseUrl for synthesized GLM-5 models. Related #94269. Thanks @Pandah97 and @chrysb.
- **PR #93241** fix(agents): classify Zhipu GLM overload as overloaded for failover. Related #93211. Thanks @0xghost42 and @zhengli0922.
- **PR #94067** fix(channels): resolve native /think menu levels via runtime catalog for live-discovered models. Related #93835. Thanks @openperf and @civiltox.
- **PR #94136** fix(zai): expose GLM-5.2 reasoning levels [AI-assisted]. Thanks @BorClaw.
- **PR #85104** feat: fast talks auto mode. Related #85087. Thanks @alexph-dev.
- **PR #94545** fix: keep trusted policies with hook registry. Thanks @jesse-merhi.
- **PR #95792** fix(onboard): refresh provider plugin registry after setup installs. Related #95765. Thanks @snowzlmbot.
### Release verification
- npm package: https://www.npmjs.com/package/openclaw/v/2026.6.10
- registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.6.10.tgz
- integrity: `sha512-LcooND2tBQw8A+kc1Ujltu3lg30bJ0w7XaeRy7eYzobb8BBdcW6DOGbwJL4vpj1vl9+gjRceOtlh5nh9OARcug==`
- release SHA: `aa69b12d0086b631b139c1435c9621a5783e3a40`
- full release CI report: https://github.com/openclaw/releases/blob/main/evidence/2026.6.10/release-evidence.md
- release publish: https://github.com/openclaw/openclaw/actions/runs/28071368306
- npm preflight: https://github.com/openclaw/openclaw/actions/runs/28068484614
- full release validation: https://github.com/openclaw/openclaw/actions/runs/28068476120
- plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/28071564667
- plugin ClawHub publish: https://github.com/openclaw/openclaw/actions/runs/28071565774
- plugin ClawHub bootstrap: not needed
- OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/28071984141
- npm Telegram beta E2E: not supplied
- Windows Hub promotion: https://github.com/openclaw/openclaw/actions/runs/28072271374 from openclaw/
[email protected]