OpenClaw v2026.6.10-beta.2

## 2026.6.10 ### 亮点 - **对话自动快速模式：** OpenClaw 可在简短对话轮次中启用快速模式，然后对较长的运行恢复至正常模式，并附有受限的回退和投递行为。（#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等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。 - **更安全的会话与频道状态：** 频道切换会重置过期的原始字段，cron 投递感知会保持附着在目标会话上。（#95328、#93580）感谢 @ZengWen-DT、@jalehman、@gorkem2020 和 @scotthuang。 - **受信任策略在钩子组合中得以保留：** 组合后的钩子注册表会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 - **Agent 与频道运行时：** 快速模式状态现在能在重试、回退转换、进度事件以及嵌入式/CLI/ACP 规范化中存活；会话与频道路由会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。 - **提供者行为：** 模型目录现在能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 - **快速模式与策略正确性：** 回退截断和重置通知现在有边界，重复的进度事件保持可见，Codex 服务层状态已规范化，钩子注册表组合时不会丢失受信任策略。（#85104、#94545）感谢 @alexph-dev、@vincentkoc 和 @jesse-merhi。 - **模型与投递边界情况：** Zai 和 GLM 故障转移路径使用正确的运行时元数据，过期的频道原始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。 ### 完整贡献记录本次审计记录涵盖了完整的 v2026.6.9..HEAD 历史：共 11 个合并的 PR。生成清单还提供了作为编辑输入的直接提交；上述分组笔记优先考虑用户影响。 #### 拉取请求 - **PR #86627** 保持核心医生健康在贡献顺序中。感谢 @giodl73-repo。 - **PR #93580** 修复：为目标会话保留 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)：在频道切换时重置过期的每频道原始字段。相关 #95325。感谢 @ZengWen-DT、@jalehman 和 @gorkem2020。 - **PR #94461** 修复(zai)：回退到用于合成 GLM-5 模型的清单 baseUrl。相关 #94269。感谢 @Pandah97 和 @chrysb。 - **PR #93241** 修复(agents)：将智谱 GLM 过载分类为过载以进行故障转移。相关 #93211。感谢 @0xghost42 和 @zhengli0922。 - **PR #94067** 修复(channels)：通过运行时目录解析实时发现模型的原生 /think 菜单级别。相关 #93835。感谢 @openperf 和 @civiltox。 - **PR #94136** 修复(zai)：公开 GLM-5.2 推理等级 [AI 辅助]。感谢 @BorClaw。 - **PR #85104** 特性：快速对话自动模式。相关 #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。 ### 发布验证 - npm 包：https://www.npmjs.com/package/openclaw/v/2026.6.10-beta.2 - 注册表 tarball：https://registry.npmjs.org/openclaw/-/openclaw-2026.6.10-beta.2.tgz - 完整性：`sha512-fOz52YzVw3MhQjQ5qqfPsfSbaMWOM62DNCxDsO/wZXvgvgrqPdZuNEPQokjFX9J7QXDeidl2uMBCnXRxynMzRg==` - 发布 SHA：`87b40c7160da1e9d470f86520f64ff1642a55b66` - 完整发布 CI 报告：https://github.com/openclaw/releases/blob/main/evidence/2026.6.10-beta.2/release-evidence.md - 发布发布：https://github.com/openclaw/openclaw/actions/runs/27942155128 - npm 预检查：https://github.com/openclaw/openclaw/actions/runs/27938779493 - 完整发布验证：https://github.com/openclaw/openclaw/actions/runs/27938779833 - 插件 npm 发布：https://github.com/openclaw/openclaw/actions/runs/27942563340 - 插件 ClawHub 发布：https://github.com/openclaw/openclaw/actions/runs/27942565547 - 插件 ClawHub 引导：不需要 - OpenClaw npm 发布：https://github.com/openclaw/openclaw/actions/runs/27943117132 - npm Telegram 测试版 E2E：https://github.com/openclaw/openclaw/actions/runs/27941744910

## 2026.6.10 ### 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. ### Complete contribution record This audited record covers the complete v2026.6.9..HEAD history: 11 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. ### Release verification - npm package: https://www.npmjs.com/package/openclaw/v/2026.6.10-beta.2 - registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.6.10-beta.2.tgz - integrity: `sha512-fOz52YzVw3MhQjQ5qqfPsfSbaMWOM62DNCxDsO/wZXvgvgrqPdZuNEPQokjFX9J7QXDeidl2uMBCnXRxynMzRg==` - release SHA: `87b40c7160da1e9d470f86520f64ff1642a55b66` - full release CI report: https://github.com/openclaw/releases/blob/main/evidence/2026.6.10-beta.2/release-evidence.md - release publish: https://github.com/openclaw/openclaw/actions/runs/27942155128 - npm preflight: https://github.com/openclaw/openclaw/actions/runs/27938779493 - full release validation: https://github.com/openclaw/openclaw/actions/runs/27938779833 - plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/27942563340 - plugin ClawHub publish: https://github.com/openclaw/openclaw/actions/runs/27942565547 - plugin ClawHub bootstrap: not needed - OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/27943117132 - npm Telegram beta E2E: https://github.com/openclaw/openclaw/actions/runs/27941744910

OpenClaw v2026.6.10-beta.2 预发布