Use Cases Timeline Weekly Claw Benchy Subscribe Contact
Appearance
GitHub X HiM Privacy
OpenClaw release

2026.6.10

30 changes and 0 fixes shipped in OpenClaw 2026.6.10. Every entry links back to its upstream PR or issue.

Upstream notes
30changes
0fixes

30 entries

Changes30 total

  1. 01Adds /fast auto so short conversational calls can start quickly, while longer or fallback work returns to normal mode with the effective state still visiblePR #85104, Issue #85087. Thanks @alexph-dev and @vincentkoc.
  2. 02Shows the effective automatic fast-mode state in status instead of reducing it to on/off, and avoids carrying a cleared Codex service-tier choice into later runs. 8845f2fThanks @vincentkoc.
  3. 03Keeps automatic fast-mode timing consistent when a turn switches to a fallback model. 075091dThanks @vincentkoc.
  4. 04Keeps the original fast-mode timing and progress behavior when a live model switch retries a turn. d1e190fThanks @vincentkoc.
  5. 05Keeps automatic fast-mode progress and reset behavior distinct from explicit fast mode after a run switches modes. 20aec98Thanks @vincentkoc.
  6. 06Shows the effective fast-mode value in connected-agent sessions instead of the configured value, so status reflects what the session is actually using. 9509aa0Thanks @vincentkoc.
  7. 07Keeps the effective automatic fast-mode setting visible through fallback transitions in connected-agent sessions. 7f5423cThanks @vincentkoc.
  8. 08Keeps automatic fast-mode timing and progress consistent when reply and scheduled-agent runs retry or switch models. 6c29f88Thanks @vincentkoc.
  9. 09Keeps fast-mode cleanup and status consistent when a run switches between fallback models. c4694f8Thanks @vincentkoc.
  10. 10Shows the automatic fast-mode reset only when fallback work is finished, so status messages match the end of the transition. f4d93c8Thanks @vincentkoc.
  11. 11Shows reset and delivery progress at the right time when auto-reply or other follow-up runs retry or leave automatic fast mode. 684e440Thanks @vincentkoc.
  12. 12Prevents the next turn after a scheduled message from losing what was delivered or whether delivery failed, so replies can use that context without exposing cron details in the channelPR #93580. Thanks @jalehman and @scotthuang.
  13. 13Prevents streamed channel progress from dropping a repeated status that represents a separate step, so each meaningful step remains visible in the draft. 2d42e52Thanks @vincentkoc.
  14. 14Prevents keyed streamed progress from staying on an older status, so viewers see the latest state instead of stale text. 8bb6472Thanks @vincentkoc.
  15. 15Treats Zhipu/GLM overload responses as overloads, so a configured fallback is selected for the right reason instead of following the wrong failover pathPR #93241, Issue #93211. Thanks @0xghost42 and @zhengli0922.
  16. 16Prevents Telegram, Slack, and Discord /think menus for live Ollama models from hiding supported levels, so users can choose valid reasoning settings without guessingPR #94067, Issue #93835. Thanks @civiltox and @openperf.
  17. 17Expands zai/glm-5.2 thinking choices beyond binary on/off and sends high or max requests as the intended Z.AI reasoning effortPR #94136. Thanks @borclaw.
  18. 18Prevents bundled Z.ai GLM-5 models from falling through to OpenAI and producing misleading API-key errors, so they use Z.AI by defaultPR #94461, Issue #94269. Thanks @chrysb and @pandah97.
  19. 19Adds GLM-5.2 and Kimi K2.7 Code to the OpenCode Go catalog with current limits, so users can select the models from OpenClaw. 66f84a9Thanks @samson1357924.
  20. 20Corrects `kimi-k2Corrects kimi-k2.7-code capability listings so OpenCode Go users are not offered unsupported video prompts when the model accepts text and images. 715dc71.
  21. 21Prevents first-run setup from skipping the selected provider's credential prompt after plugin installation, so onboarding continues with that provider instead of falling back to OpenAIPR #95792, Issue #95765. Thanks @snowzlmbot.
  22. 22Adds a durable session-transcript SDK contract so plugins can read, append, publish, and lock the intended transcript without treating legacy file paths as identityPR #95030. Thanks @jalehman.
  23. 23Prevents a shared direct-message session from carrying the previous channel's identity after a switch, so status, reactions, threads, and message references target the current channelPR #95328, Issue #95325. Thanks @gorkem2020, @jalehman, and @zengwen-dt.
  24. 24Keeps empty prompts separate from hook-added context during compaction or session reuse in Copilot and Codex sessions, so prompt boundaries remain consistentPR #94838. Thanks @vincentkoc.
  25. 25Keeps approval-sensitive Gateway and plugin tools protected when connected extensions change, so configured safeguards continue to applyPR #94545. Thanks @jesse-merhi.
  26. 26Prevents authenticated package-source tokens from being sent to an allowed redirect on another origin, while the valid redirected download still completes. b0df6dc
  27. 27Prevents Docker and Podman setup from running unbounded on hosts where GNU timeout is installed as gtimeout, so image pulls, builds, and detached startup receive the intended guard. 62b2e9e
  28. 28Prevents cleared Codex service tiers from being persisted as explicit stale state, so resumed or switched conversations use the normal default instead. cd32d9fThanks @vincentkoc.
  29. 29Restores ClawHub discovery for the StepFun provider plugin, so operators can install it through either ClawHub or npm. ecb82f1Thanks @vincentkoc.
  30. 30Keeps core openclaw doctor diagnostics in their normal order before extension checks, making lint and repair output easier to followPR #86627. Thanks @giodl73-repo.