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

2026.7.1

1,714 changes and 0 fixes shipped in OpenClaw 2026.7.1, split across 2 pages. Every entry links back to its upstream PR or issue.

Upstream notes
1,714changes
0fixes
1/2page

Showing 1–1,500 of 1,714

Changes1–1,500 of 1,714

  1. 01New Control UI chats now receive concise sidebar titles from their first message, and operators can route dashboard, Telegram topic, and Discord thread title generation through a smaller utilityModel#87643 Thanks @juliangsm, @zhangguiping-xydt.
  2. 02Paired administrators can now create a mobile setup QR or copyable code from Control UI Nodes and use it to connect an official iOS or Android app#94672 Thanks @bkudiess, @douhualili.
  3. 03Control UI now makes conversations easier to create, find, and switch from a populated session sidebar, while keeping context pressure and provider quota information close at hand#99289 Related #99288.
  4. 04The Control UI sidebar now focuses on sessions and a few default destinations while letting users pin their preferred pages and keep those choices across reloads#100296
  5. 05The redesigned Control UI composer keeps attachments, provider and model selection, voice, run state, and message actions clearer and more stable across mobile and desktop layouts#100461 Thanks @fuller-stack-dev.
  6. 06Control UI Talk users can choose and refresh a microphone on narrow screens and read clear permission guidance when browser access is blocked#101377 Thanks @fuller-stack-dev.
  7. 07Control UI chat can now show multiple resizable sessions side by side or stacked, preserve the pane layout across reloads, and keep the active pane usable on narrow screens#100754
  8. 08The Control UI now has a live Tasks page where operators can inspect active and recent background work, open its session, refresh details, and cancel queued or running tasks when authorized#100789
  9. 09Session lists across web and mobile now support pinned and custom groups, shared read and unread status, background-output indicators, transcript forking, and in-place rename, archive, move, and delete actions#100814
  10. 10The Control UI Sessions page now fits more useful status and actions on a typical screen, with row details opening to reveal labels, tuning controls, and checkpoint history instead of forcing routine sideways scrolling#100943
  11. 11Control UI users can drag a session directly into the current pane or onto any side to create a split, with a preview showing where it will land#101191
  12. 12Operators can configure token or full per-reply usage footers once with messages.responseUsage, while users can turn them off or reset a session to the inherited default#89762 Thanks @marvinthebored, @obviyus, @peetiegonzalez.
  13. 13The Control UI Usage page now makes recent estimated costs, daily values, and each provider, model, agent, or channel's share easier to compare without repeated reloads or hovering#100432
  14. 14The Usage page now shows provider-reported plans, quotas, reset times, balances, spending, and budgets alongside OpenClaw session analysis, including OpenRouter and Venice coverage#100520
  15. 15Control UI Usage can now show Anthropic and OpenAI daily spend, tokens, requests, top models, and billing categories for today, seven days, and thirty days when admin credentials are configured#100672
  16. 16Daily token and cost charts now include zero-activity days across bounded date ranges, so 7-day, 30-day, and 90-day views show the full calendar period instead of shrinking around active days#81467 Thanks @adapepper.
  17. 17All-agent cost reports on large installations now limit concurrent Gateway work so the dashboard is less likely to slow down, time out, or add memory pressure#101589 Thanks @vincentkoc, @zw-xysk.
  18. 18Hovering or keyboard-focusing a public GitHub issue or pull request in Control UI chat now previews its status, title, author, activity, comments, and change size without leaving the conversation#100434
  19. 19File paths in Control UI chats are now clickable, opening a searchable syntax-highlighted preview at the cited line with options to reveal, copy, or open the file in a supported editor#100679
  20. 20Control UI connection failures now show actionable messages such as "Pairing required" instead of replacing them with a generic gateway disconnect#54758 Thanks @ruanrrn.
  21. 21Control UI sessions using full verbose output now open tool inputs and results by default, reducing repeated clicks during debugging and review#74398 Thanks @samrusani.
  22. 22The Control UI context indicator now remains visible with an approximate cached total while a response is active, without using stale data for urgent warnings or the Compact action#89772 Thanks @bladin.
  23. 23Control UI and WebChat no longer let a non-terminal internal tool failure dominate the transcript with a red error banner after the assistant has already produced a normal final answer#90122 Thanks @harjothkhara.
  24. 24A default agent selected in the Control UI now remains selected after refresh without saving unrelated unfinished settings#91457 Thanks @zengwen-dt.
  25. 25Segmented streaming replies in Control UI WebChat now stay under one assistant avatar and footer instead of appearing as several separate responses#92063 Related #63956. Thanks @contentfree, @harjothkhara.
  26. 26Dashboard WebChat users can right-click a completed message and reply with visible quote context instead of manually copying and formatting it#92654 Thanks @programmingwtf, @vincentkoc.
  27. 27After an update installs, the Control UI now says when a Gateway restart is already in progress instead of making the Update button appear unresponsive#93082 Thanks @goutamadwant.
  28. 28Live tool-using replies in Control UI WebChat now keep the assistant's introduction ahead of the tool card, even when browser and Gateway clocks differ#93184 Thanks @pick-cat.
  29. 29Control UI Quick Create now lets users choose a model for an agent-turn cron job and shows whether existing jobs use that model or the default#95341 Thanks @ly85206559.
  30. 30Control UI WebChat can now show Codex preamble and commentary while tools are running, with a choice to hide or retain that progress after the final answer#95708 Thanks @obviyus, @ragesaq.
  31. 31Long reply IDs containing emoji or other supplementary characters now remain valid when shortened for WebChat and Gateway reply directives instead of being cut into malformed text#96938 Thanks @ly-wang19.
  32. 32Long tool activity details now remain readable when shortened for chat, UI, or logs, even when an emoji or other supplementary character falls at the cutoff#96958 Thanks @bartok9, @ly-wang19, @vincentkoc.
  33. 33WebChat now shows long provider and model names together with the selected reasoning level in the composer, while narrow screens retain a sensible overflow limit#96990 Thanks @maweibin, @xiayingren123.
  34. 34Agents can use targetless `messageAgents can use targetless message.send for progress or intermediate updates in the current WebChat without an explicit destination. #97167 Related #96840. Thanks @mantiscartography, @zhangguiping-xydt.
  35. 35New Control UI chats now use the selected model's current context window instead of inheriting an outdated, smaller limit from a parent session#97332 Thanks @galiniliev.
  36. 36WebChat stays on the newest reply when assistant audio or video finishes loading, while respecting readers who intentionally scrolled upward#97575 Thanks @turbotheturtle.
  37. 37Control UI pages for multiple Gateways on one domain now stay connected to the Gateway named by their path instead of reusing a sibling page's saved destination#97665 Thanks @alix-007.
  38. 38/pair qr now delivers a scannable code in Telegram and Control UI or a readable code in the TUI without storing the one-time setup secret in chat history#97933 Thanks @joshavant.
  39. 39Expired /pair qr cards in Control UI now clearly say the code is unusable and direct users to generate a fresh one#98049 Related #98039. Thanks @ooiuuii.
  40. 40Expired mobile-pairing codes now explain how to run /pair qr again in the selected languageSources: bb4afe4, da9308d, dfaec18, 6b7986e, 21af6e7, 4e62124, 6cd0106, a72a641, a143ae4, cd30b1c, f69e27a, ccddbee, 9ed03df, f84243f, 3d06ee9, 9bd071e, 405b7a5, 1a160ce.
  41. 41Control UI now shows channel-triggered agent runs as in progress, so users can tell that messages from channels such as Weixin are actively being handled#98257 Thanks @scotthuang.
  42. 42The Control UI workspace rail now gives long Project files lists their own scrollbar so files remain browsable without spilling off screen#98646 Related #98566. Thanks @645648406-max, @wuqxuan.
  43. 43Session Workspace file paths can now be copied from Chat even when the Control UI runs over plain HTTP or another context without the standard Clipboard API#98764 Related #98759. Thanks @adinballew, @zengwen-dt.
  44. 44Tool-heavy Control UI chats now use compact expandable activity rows, so commands and results take less space while full details stay one click away#99763
  45. 45The Control UI now stays fixed during trackpad overscroll on Mac and desktop browsers while chat threads and lists continue scrolling normally#99830
  46. 46Control UI chat is easier to scan with quieter composer controls, a Faster-to-Smarter reasoning slider, and connection status that no longer competes with persistent version text#99838 Related #99837.
  47. 47Mounted deep links, Set Default, authenticated avatars, cron alerts, and Workboard scrolling now behave correctly again across the Control UI#100106
  48. 48Administrators can now open mobile pairing from any Control UI page or Quick Settings, while non-admin operators continue to see the action disabled with an access explanation#100157
  49. 49The Control UI now shows a ready mobile-pairing QR code immediately even when the pending-device list is slow, then adds approval requests when they arrive#100179
  50. 50Control UI users can select and copy tool activity without toggling its row, and failed tools no longer repeat redundant error indicators#100199 Thanks @steipete-oai.
  51. 51The Gateway Dashboard login now fits and behaves better on phones and short windows, with larger touch targets, easier URL entry, and reachable recovery help#100208
  52. 52Control UI users can organize large session lists by custom group, channel, kind, agent, or date, with persistent assignments and drag-and-drop management#100262
  53. 53Users can open the Control UI context ring to inspect exact context use, the latest input and output token counts, and the active model without leaving chat#100264
  54. 54Images returned by tools such as read now appear directly in the Control UI conversation instead of only being mentioned in text#100295 Thanks @lzyyzznl, @pandah97, @rquinones84.
  55. 55Control UI tool activity now combines matching calls and results into one consistent row, removes repeated labels and categories, and keeps inputs, outputs, previews, and real errors accessible#100318
  56. 56The Control UI context panel now shows the latest run's estimated total cost and available input, output, cache-read, and cache-write breakdowns beside the provider and model#100379
  57. 57The Control UI sidebar now keeps all pinned chats visible alongside nine ordinary recent chats in a more compact, conversation-focused desktop and tablet layout#100386
  58. 58The Control UI composer now shows reasoning level clearly, keeps Talk and its settings together, and preserves usable model controls on phone and landscape layouts#100445
  59. 59Control UI Talk now starts from a simpler composer while administrators can set durable provider, transport, timing, and reasoning defaults in Settings#100453
  60. 60Temporary Gateway disconnects no longer replace an authenticated Control UI page with the login screen, preserving dashboard context while automatic reconnection continues#100479
  61. 61The Control UI Cron Jobs page now uses compact summaries, clear status cues, expandable details, and an overflow menu so large job lists are faster to review#100646
  62. 62The Control UI sidebar now keeps recent chats in place while switching, combines search entry points, supports touch session actions, and reduces unnecessary chrome#100648
  63. 63Images received through Telegram, iMessage, and other channels now reappear inline when users revisit Control UI chat history after a reload#100725 Thanks @sweetcornna, @vergissberlin.
  64. 64The Control UI goal pill now supports pause, resume, clear, inspection, and edit preparation with live timing and token details, while command and TUI users can reword a goal without resetting its budget#100736
  65. 65The Control UI keeps Overview, Workboard, Agents, and More visible while allowing the session list to use available height and scroll independently#100742
  66. 66Assistant documents downloaded from the Control UI now keep recognizable original filenames instead of exposing UUID-suffixed staging names#100743
  67. 67Copying code from a long Control UI reply now keeps the chat at the same reading position instead of jumping upward#100807 Thanks @jvlegod.
  68. 68Desktop Control UI users can choose whether Enter sends or inserts a new line, with Command+Enter or Ctrl+Enter available as the send shortcut and the choice retained for that Gateway#100810 Thanks @moomx, @vincentkoc.
  69. 69Switching Control UI chats no longer unexpectedly moves the selected session to the top, and users can choose stable creation order or recently updated order for the sidebar#100927 Thanks @shakkernerd, @vyctorbrzezowski.
  70. 70Control UI Settings now use consistent `/settings/Control UI Settings now use consistent /settings/... paths while old bookmarks continue to work, making reloads and links more reliable on hosted or reverse-proxied installations. #100928 Thanks @vyctorbrzezowski.
  71. 71Control UI navigation now places branding, search, and sidebar controls where desktop and mobile users expect them, with clearer active sessions, compact timestamps, and easier terminal access#101017 Thanks @shakkernerd, @vyctorbrzezowski.
  72. 72The Control UI sidebar collapse control now sits in the sidebar it affects instead of looking like an unrelated topbar or terminal button#101038
  73. 73Control UI Talk users can choose the system default or any browser-visible microphone beside the Talk button and receive a clear message when a saved device is unavailable#101100
  74. 74Sidebar session groups can now be renamed, removed without deleting sessions, created while empty, or disabled to restore one flat recent-session list#101117
  75. 75The Control UI now shows Workboard navigation only when Workboard is enabled and presents a cleaner collapsed sidebar with clearer icons and status spacing#101123
  76. 76The Control UI now puts search, sidebar access, theme choice, and macOS branding in clearer, more predictable locations with accurate screen-reader labels#101497
  77. 77Temporary Gateway drops no longer push Control UI content down with a full-width banner, so the dashboard stays in place while a compact Retry notice appears#101812
  78. 78Temporary Gateway disconnects now use a calmer, dashboard-native reconnect pill with the same Retry and accessibility behavior#101844
  79. 79Control UI commentary settings now use the selected language across the supported translations in this releaseSources: 34badde, a9cb866, ce9166d, 6b67ada, 006c2f7, 6bdffa5, b4476ab, 5b5c623, 1520d09, 6140326, 75bd44a, c1aeaf9, 49edc0a, cb69ce7, bb0af61, 0dcfbb0, db73ece, 21e6fc9.
  80. 80The All Sessions sidebar label now uses the selected language across the supported Control UI translations in this releaseSources: b2c3dc2, 61347a5, a2674b6, bbabad4, 8909289, 22552d6, 96e3615, 452351c, 5e9a62c, 0a9648b, a803589, 7c30ff8, e3d2878, 620f2e3, aa0f36c, c336256, 64dd688, e2ecbc8.
  81. 81The Control UI mobile-pairing flow now appears in the selected language across 18 supported locales instead of mixing localized screens with English setup text. c78b0d5
  82. 82A failed Control UI login or Gateway connection now immediately shows the error, recovery steps, and relevant documentation link instead of hiding them in a collapsed panel. f9e194e
  83. 83The web sidebar now reliably fills pinned and overflow navigation routes, keeping destinations such as Worktrees available. 55a0012 Thanks @vincentkoc
  84. 84Non-English Control UI users now see translated cron overflow-menu and "run if due" labels, including the assistive label for more actions. 2585d6b
  85. 85The Control UI microphone-access warning for realtime voice input now appears in the user's selected language. 68c85ef
  86. 86The Control UI sidebar now builds cleanly with session grouping and drag-to-split behavior intact after stray merge-conflict text was removed. 0e3ce24
  87. 87Hindi and Russian users can now receive matching Control UI translations, and documentation operators can generate those language editions through the existing locale workflow. 689baa5 Thanks @vincentkoc
  88. 88During device pairing, / pair qr now follows the same authorized pairing flow as /pair qr without starting an agent turn or disrupting the existing Control UI route#98262 Thanks @brokemac79.
  89. 89Opening or reconnecting the Control UI dashboard now uses much less temporary Gateway memory, reducing false rss_growth warnings while preserving requested usage totals#100054 Thanks @nianjiuzst.
  90. 90Control UI Settings now shows a remote Gateway's host identity, address, operating system, runtime, uptime, CPU load, memory, and free disk space without requiring SSH#100478
  91. 91The Control UI now shows execution approvals for supported desktop nodes and rejects pending, unsupported, or policy-blocked requests before they reach the node#100505 Thanks @vincentkoc.
  92. 92A configured `uiA configured ui.seamColor now changes Control UI buttons, highlights, selections, and focus rings, while invalid values fall back cleanly. #93699 Thanks @dennis-lynch, @goutamadwant.
  93. 93QR codes and other half-block text art in the Control UI now preserve spacing, scroll when needed, and copy with enough padding to remain usable#93869 Thanks @emg110, @vincentkoc.
  94. 94Open Control UI tabs now switch to the active build after a service-worker update, reducing stale JavaScript, CSS, and protocol mismatch errors after upgrades#96141 Thanks @andrewccctechlink, @brokemac79.
  95. 95Chat clients can now match each pending user message to its exact Gateway-confirmed message, reducing duplicate or mismatched bubbles during interleaved turns#96273 Thanks @datus1982, @wyf027.
  96. 96Clicking a cron job's History button now gives immediate feedback and scrolls directly to that job's updated run history#96281 Thanks @wyf027, @yzhong52.
  97. 97Control UI token totals near one million now display as `1Control UI token totals near one million now display as 1.0M instead of the confusing 1000k. #96298 Thanks @ly-wang19.
  98. 98Usage Mosaic and usage summaries now show near-million token totals as `1Usage Mosaic and usage summaries now show near-million token totals as 1.0M instead of 1000.0K. #96450 Thanks @ly-wang19.
  99. 99The Voice, Model, and Sensitivity controls in Control UI Talk settings now align consistently in one row without duplicate selected-value text disturbing the layout#96925 Thanks @evan-ym.
  100. 100Control UI approval prompts no longer inherit failures from older requests or re-enable controls while the current decision is still being processed#98394 Thanks @haruaiclone-droid.
  101. 101Control UI now stops retrying after detecting an incompatible Gateway protocol and shows the update or reload guidance needed to reconnect#98414 Thanks @haruaiclone-droid.
  102. 102On phones and other short landscape screens, the Control UI composer now scrolls within a bounded area so chat history and all composing controls remain accessible#98683 Related #98615. Thanks @jin-li, @qingminglong.
  103. 103The Control UI now retries after a temporary failed load during a Gateway restart or stale-asset transition instead of remaining stuck until the page is refreshed manually#99111 Thanks @zengwen-dt.
  104. 104Large pasted PNG screenshots can now be sent through Control UI webchat without failing during attachment processing#99213 Thanks @jincheng-xydt, @vincentkoc.
  105. 105The Control UI mobile-pairing flow is now fully localized for Hindi and Russian users, from setup-code creation through pending-device management#100040
  106. 106The Control UI workspace rail now sits flush with the window and uses less space when collapsed, removing the empty strip without overlapping chat#100088
  107. 107Control UI chat history now hides only exact duplicate final delivery mirrors, leaving legitimate repeated sends, forwards, and distinct replies visible#100136
  108. 108Control UI chats now leave consistent space above the first message across phones, standard desktops, and tall windows#100144 Thanks @steipete-oai.
  109. 109Control UI Settings now offers a persistent Simple/Advanced switch, cleaner Appearance controls, and a Pending label only when a Context Profile change is actually staged#100147
  110. 110Control UI tool-call bubbles and error badges now share clean right-edge alignment, so failed activity is easier to scan on phone-sized and desktop chats#100163 Thanks @steipete-oai.
  111. 111OpenAI users now see only the supported Standard and Fast choices in the Control UI speed picker, with inherited Fast mode shown correctly#100190
  112. 112Short drafts in the Control UI composer no longer show an unnecessary scrollbar gutter, while long drafts still scroll when needed#100252
  113. 113Clearing a session label now removes the old name promptly from other subscribed Control UI clients without requiring a full refresh#100266
  114. 114Desktop Control UI users can hover a shortened recent-session name to reveal its hidden tail and distinguish similar conversations without opening each one#100276
  115. 115The expanded Control UI sidebar no longer repeats provider quota information already available in chat, Overview, and Usage views#100356 Thanks @shakkernerd.
  116. 116Completed Control UI messages now use the timestamp to open token, cache, context, cost, and model details instead of adding a separate Context control to every footer#100391 Thanks @steipete-oai.
  117. 117Autonomous session history now keeps an earlier failed cron or scheduled turn marked as an error even after a later turn succeeds or the page reloads#100514 Thanks @qingminglong.
  118. 118The Control UI Skills page now shows readable Agent and Search labels with aligned filters and correctly sized selection controls#100526 Thanks @evan-ym.
  119. 119After a Control UI reply finishes, the composer now stays on Send despite delayed completed-run state, while a real new run still switches it to Stop#100527 Thanks @tiffanychum.
  120. 120Control UI and Skill Workshop file previews now show a single Escape shortcut hint while retaining Escape-to-close behavior#100528 Thanks @xianshishan.
  121. 121Expanded Control UI tool activity no longer repeats the tool name and icon, making completed and in-progress calls quicker to scan#100606
  122. 122Clearing a Control UI session model override now shows the selected agent's own default model rather than the unrelated global default#100719 Thanks @hyspacex.
  123. 123Assistant-sent documents in WebChat now download with their original server-provided filename, including Unicode names, instead of opening as an unnamed browser document#100728 Thanks @lptrichor.
  124. 124The Control UI now accepts /steer guidance during an active run instead of incorrectly replying No active run#100803 Thanks @hackerismydream.
  125. 125New Control UI sessions now stay visible at the front of the sidebar after users switch to another chat, without requiring a page refresh#100981 Thanks @shakkernerd.
  126. 126Worktrees management now lives under Control UI Settings instead of occupying a top-level sidebar item, while existing deep links remain valid#100995
  127. 127Long /btw answers in the desktop Control UI now stay within the browser window and scroll inside the result card, while mobile retains full-card scrolling#101169 Thanks @snoutfirst.
  128. 128Finished chats no longer remain stuck with a busy spinner in the Control UI sidebar, even when an older Gateway update arrives afterward#101293 Thanks @fuller-stack-dev.
  129. 129Large Skill Workshop support files now scroll, switch, filter, wrap, and copy without freezing or severely slowing the Control UI#101319 Thanks @shakkernerd, @xianshishan.
  130. 130Users can stay signed in to multiple path- or query-routed Control UI gateways on one HTTPS origin without one gateway overwriting another's device token#101352 Thanks @fuller-stack-dev.
  131. 131Control UI users can type /approve to release a waiting exec prompt without the decision getting queued behind the blocked chat run#101532 Thanks @vincentkoc.
  132. 132Control UI build errors now keep emoji and other supplementary characters intact when command output is shortened for display#101591 Thanks @maweibin.
  133. 133Workboard cards can now be edited, moved, archived, stopped, opened, or deleted directly from the detail drawer, while read-only viewers still see no mutation controls#101658 Thanks @momothemage, @princebansal.
  134. 134The Control UI microphone button is now visually quieter while idle and more distinct while recording, making the current voice state easier to recognize#101843
  135. 135Users with saved working dashboard credentials no longer see the login screen flash briefly while Control UI reconnects#101849
  136. 136Typing anywhere in the active Control UI chat now places the first character in the message composer without stealing input from the command palette#102210 Thanks @shakkernerd.
  137. 137openclaw doctor and updates now refuse to replace an unreadable `openclawOpenclaw doctor and updates now refuse to replace an unreadable openclaw.json, preserving existing Gateway, agent, channel, and plugin settings instead of breaking the installation. #96469 Thanks @obviyus, @yetval.
  138. 138openclaw doctor --fix now preserves aliases, parameters, streaming choices, runtime settings, and other model tuning when several retired model names merge into one current model, and reports any merge conflicts accurately#96544 Thanks @vincentkoc, @yetval.
  139. 139Owners and admins can now restore an expired Codex or OpenAI login from a browser through private Telegram, Web UI, Discord, or Slack commands without SSH access#98006 Thanks @100yenadmin, @jalehman, @obviyus.
  140. 140The CLI now guides fresh installs through setup, opens configured installs directly in the TUI, preserves existing choices on reruns, and finishes onboarding in a usable terminal chat#98218 Thanks @fuller-stack-dev.
  141. 141Package installs can now select and retain openclaw update --channel extended-stable, inspect its availability, and fail safely if its npm metadata is incomplete#99811 Thanks @kevinslin.
  142. 142Fresh installs can now complete conversational Crestodian setup, approve the proposed plan once, connect channels, and continue into the normal agent while classic and scripted onboarding remain available#99935
  143. 143First-time onboarding now preserves earlier choices after authentication or pairing trouble and gives users an actionable model-configuration next step instead of opening an unusable first chat#100632
  144. 144Container upgrades now finish required migrations and plugin repairs before reporting the Gateway ready, and failed repairs stop with actionable guidance instead of leaving a false-green service#101881 Thanks @sallyom.
  145. 145Crestodian setup now guides users who lack a usable model provider through masked credential entry and model selection, while deterministic setup and repair commands remain available until inference is configured#101887 Thanks @fuller-stack-dev.
  146. 146OpenClaw now blocks unsafe runtimes before they can open SQLite-backed state, guides legacy Bun services to Node, and selects a WAL-safe Node runtime during setup and repair#106065 Thanks @vincentkoc.
  147. 147iOS and Android chats now preserve the reader's scroll position as new messages and tool activity arrive, with a clear way to return to the latest reply#98258 Related #98255. Thanks @christopheraaronhogg.
  148. 148iPhone and iPad chat now opens with the last known conversation and lets users browse recent cached sessions while the Gateway is unavailable#100219
  149. 149iOS users can queue chat messages while disconnected, keep them through app restarts, and send them in order after reconnection with clear retry and delete controls#100331
  150. 150Android chat now shows the last known transcript immediately and keeps recent cached conversations readable during a Gateway outage, then refreshes them after reconnection#100227
  151. 151Android users can queue text while the Gateway is offline, keep it through an app restart, and send it in order after reconnection with Retry and Delete controls for failures#100290
  152. 152Mac chat now restores recent sessions and transcripts immediately, remains browsable while disconnected, and queues offline sends for the correct Gateway identity#100275
  153. 153The native macOS chat window now provides a full session sidebar, real new-session creation, slash-command completion, context and cost visibility, message copying, transcript export, and compact or clear-history actions#101103
  154. 154GPT-5GPT-5.6 users can now select supported Ultra modes consistently, keep model and thinking choices aligned across OpenClaw surfaces, and receive native Codex child-agent results as tracked tasks. #98021 Thanks @anyech.
  155. 155Organizations with GPT-5Organizations with GPT-5.6 preview access can select Sol, Terra, or Luna across supported OpenAI and Codex paths with correct reasoning controls, context metadata, and cache-write accounting. #98333 Related #98296. Thanks @steipete-oai.
  156. 156Legacy-state upgrades no longer stall repeatedly, while fresh OpenAI and ChatGPT/Codex setups select the intended GPT-5.6 defaults and use supported temperature and tool-call behavior#104656 Thanks @bdjben, @obviyus, @sallyom.
  157. 157Tencent Hunyuan Hy3 now has a complete supported OpenClaw setup path through TokenHub or TokenPlan, including first-class authentication, model discovery, configuration validation, CLI onboarding, and compatibility for existing hy3-preview setups#99076 Thanks @moncac.
  158. 158OpenClaw now supports Meta Model API setup and the Muse Spark 1OpenClaw now supports Meta Model API setup and the Muse Spark 1.1 model, including streaming, tool calling, image input, and supported reasoning controls. #102873 Thanks @davemorin, @hamidshojanazeri, @jalehman, @solvely-colin.
  159. 159Claude Sonnet 5 is now selectable across Anthropic, Claude CLI, supported Vertex regions, Bedrock inference profiles, and Bedrock Mantle with its documented context, output, image, thinking, and pricing behavior#98254 Thanks @vortexopenclaw.
  160. 160Users with Claude Mythos 5 access can select it through Anthropic, Anthropic Vertex, Amazon Bedrock, or Bedrock Mantle with its required context, output, thinking, caching, and replay behavior#101238 Thanks @vincentkoc.
  161. 161Copilot sessions can now use explicitly selected custom OpenAI, Azure OpenAI, Ollama-compatible, or Anthropic providers and restart cleanly when model, endpoint, credentials, headers, or token limits change#96345 Thanks @vincentkoc.
  162. 162OpenClaw agents can now run short tasks on chat-capable Ollama models installed on paired macOS, Linux, or Windows nodes, with a separate control for disabling node inference#99234 Related #99228.
  163. 163A single CLAWROUTER_API_KEY can now expose only its granted models across supported transports and show managed requests, tokens, spend, and monthly budget in normal status views#99658 Related #99657.
  164. 164Users can discover active promotional models and claim them with openclaw promos claim <slug> without rerunning onboarding or unexpectedly replacing existing defaults and credentials#100236 Thanks @fuller-stack-dev.
  165. 165Hosted LongCat-2Hosted LongCat-2.0 can now be installed through the official LongCat plugin, configured with LONGCAT_API_KEY during onboarding, and selected as longcat/LongCat-2.0 for multi-turn tool use. #100501 Thanks @vincentkoc.
  166. 166Gemini latest aliases now continue tool-calling conversations across both supported Google transports instead of stopping with a missing-thought-signature HTTP 400#100605 Thanks @chenxiaoyu209, @guarismo.
  167. 167External tools can now receive session-scoped Gateway access without process-wide credentials or permission to impersonate another session, forming the secure base for openclaw attach#96351 Thanks @anagnorisis2peripeteia, @obviyus.
  168. 168openclaw attach now launches Claude Code with temporary access to the main or selected Gateway session, keeps credentials out of arguments, and revokes the grant when the session ends#96454 Thanks @anagnorisis2peripeteia, @obviyus.
  169. 169GPT-5GPT-5.6 users can now select supported Ultra modes consistently, keep model and thinking choices aligned across OpenClaw surfaces, and receive native Codex child-agent results as tracked tasks. #98021 Thanks @anyech.
  170. 170Codex app-server agents can again list allowed agents, spawn OpenClaw or connected subagents, and yield during delegated work without resumed heartbeats hitting incompatible tool definitions#99561 Related #99464. Thanks @100yenadmin, @joshavant.
  171. 171Codex-native delegation from OpenClaw threads now creates native task records again, while unsupported custom Codex app-server versions fail startup with a clear minimum-version error#101221
  172. 172Copilot sessions can now use explicitly selected custom OpenAI, Azure OpenAI, Ollama-compatible, or Anthropic providers and restart cleanly when model, endpoint, credentials, headers, or token limits change#96345 Thanks @vincentkoc.
  173. 173Sessions can now be pinned, archived without losing transcripts, restored, renamed from chat surfaces, and monitored for active runs as durable conversation threads#98510 Thanks @maziyang2.
  174. 174An active /goal now keeps guiding later turns and survives compaction, queues, and interruptions until the goal is paused, completed, blocked, or limited#100468
  175. 175Telegram photo albums now give the model every successfully downloaded image in order instead of only one photo and unusable file references, while failed items are omitted#97045 Thanks @nianjiuzst, @obviyus.
  176. 176Telegram's live progress view now keeps reasoning, commentary, formatting, and tool activity readable and stable, then leaves a concise completion summary instead of disappearing#98907 Thanks @marvinthebored, @peetiegonzalez.
  177. 177Telegram users should see fewer failed final replies or bot delivery sends during flaky network handshakes, without increasing duplicate-message risk for failures that may have happened after a request was sent#101258 Thanks @lzw112.
  178. 178Telegram PDFs and other documents now provide agents with a usable local path so normal runner tools can open the attachment#97647 Thanks @gallup007, @joshavant.
  179. 179Telegram timeout logs now hide bot tokens embedded in Bot API paths, including custom and proxy roots, while retaining useful endpoint context#99428 Related #96982. Thanks @liuhaiyang14, @xialonglee.
  180. 180Telegram bot tokens now remain masked even when they cross internal boundaries inside very large logs or tool-error messages#103861 Thanks @vincentkoc.
  181. 181When a Telegram plugin approval cannot be routed, operators now receive practical Web UI, terminal UI, and configuration guidance instead of a generic failure or timeout#95973 Related #95800. Thanks @chrisbot2026, @monkeyleet.
  182. 182Scheduled deliveries to numeric threads such as Telegram forum topics now return to the configured thread after Gateway restarts instead of falling back to the general chat#98699 Thanks @yetval.
  183. 183Slack replies stay attached to the root thread's session history instead of accumulating separate, nearly empty child sessions#97168 Related #96535. Thanks @gorkem2020, @liuwqgit.
  184. 184When Slack accepts a reply but the confirmation is lost, OpenClaw can verify the existing post and avoid sending a duplicate#97480 Thanks @joeyfrasier.
  185. 185Slack and similar channel turns with context-injecting plugins now send each inbound system label to the model once instead of duplicating it#95349 Thanks @gorkem2020, @openperf, @vincentkoc.
  186. 186Slack rooms that require a mention no longer wake OpenClaw for ordinary messages when the bot identity is missing or untrusted, and setup warnings point operators to a Bot User OAuth Token when needed#91584 Thanks @hiragram.
  187. 187Completed partial-stream Discord replies now arrive as fresh messages that can trigger normal unread cues after a user leaves the channel#99711 Thanks @davelutztx.
  188. 188Discord replies, cron reports, and other outbound messages are less likely to disappear during a brief Gateway reconnect, without replaying chunks or media Discord already accepted#100896 Thanks @tiffanychum.
  189. 189Discord bots can now recover in place after repeated session-resume rejection, reducing prolonged outages, lost replies, and full Gateway restarts#103596
  190. 190Discord Code Mode progress no longer fills with repetitive Wait rows from background polling, while ordinary custom and plugin tools remain visible#100164
  191. 191Long Discord approval previews now preserve complete emoji and flags when shortened, avoiding broken replacement characters#99539 Thanks @zhangguiping-xydt.
  192. 192Discord read allowlists now block guild metadata, channel details, and thread listings before any provider request when those resources are outside the configured scope#98966 Thanks @pgondhi987.
  193. 193Discord users can complete approved Codex Computer Use actions such as get_app_state and receive the native tool result instead of getting a false timeout while the tool is still running#96818 Thanks @pollybot13, @zhangguiping-xydt.
  194. 194Photos bridged from a remote iMessage Mac to a separate Gateway host now arrive in Codex conversations through a readable local path rather than a Mac-only filename#91803 Thanks @turbotheturtle.
  195. 195AppleScript-only and bot-user or SSH iMessage setups now deliver replies even when threading is unavailable, and database changes no longer leave inbound messages hidden behind stale recovery state#100446 Thanks @omarshahine.
  196. 196Direct iMessage chats using the imsg private API bridge now show typing as soon as a slow turn is accepted, without waiting for a read receipt#95621 Thanks @omarshahine.
  197. 197iMessage replies no longer lose ordinary sentence text that happens to end with user:, system:, or assistant#96392 Thanks @ly-wang19.
  198. 198Hidden MiniMax reasoning no longer appears as a new iMessage or feeds back into the conversation as an echo-triggering inbound message#93820 Thanks @alix-007.
  199. 199Renaming iMessage groups, changing icons or membership, and leaving groups now require verified owner or administrator authority#97961 Thanks @eleqtrizit.
  200. 200Mac users setting up iMessage can install or update imsg from the setup flow, receive clearer probe guidance, and recover sessions that still reference the old skill location#101407 Thanks @omarshahine.
  201. 201A repeatedly crashing supervised Gateway now leaves a stable control process available for inspection and repair instead of trapping operators in a restart loop. a18708c Thanks @obviyus
  202. 202A cron job can now watch a build, deploy, script, or other command and resume the originating workflow with its exit code and recent output when it finishes#92037 Thanks @anagnorisis2peripeteia.
  203. 203Cron declarations can now be safely reapplied without duplicate jobs or lost history, while ownership, next run, latest result, delivery, and failure notifications are easier to inspect#100480
  204. 204Cron jobs can now watch an outside condition and run their real payload only when that state changes, avoiding full agent wakeups on unchanged polls#101195
  205. 205Windows and WSL2 users now get IPv4 and IPv6 checks plus the matching portproxy guidance needed to restore Chrome browser control without broadening CDP exposure#100590 Thanks @owlock, @zengwen-dt.
  206. 206The bundled Chrome extension now lets users control selected signed-in tabs from a phone or another channel without someone approving remote debugging at the desktop, and removing a tab revokes access#100619
  207. 207Remote Gateway users can pair the bundled Chrome extension from another browser machine with openclaw browser extension pair --gateway-url wss://..., without installing OpenClaw or Node.js there or opening an inbound port#101127
  208. 208Agents can now save a browser download to a chosen guarded path or wait for a delayed export, receiving the final URL, filename, and local path#101369 Thanks @grd-chang.
  209. 209Authenticated admins can open an interactive terminal in an agent workspace from Gateway-backed controls, while fully sandboxed agents remain blocked and the feature can be disabled with gateway.terminal.enabled. f083f35
  210. 210Control UI admins can now keep chat, session controls, and live shells together by opening multiple dockable, resizable terminal tabs inside the browser workspace. ec72de4
  211. 211Opt-in Control UI terminal sessions can now survive page reloads, sleep, and brief network drops, letting operators reattach and replay recent output instead of losing running commands#100089
  212. 212Opening a new Control UI terminal after closing the final tab now starts with a blank fresh shell instead of restoring the closed terminal output#100665
  213. 213Control UI terminal tabs now close cleanly while opening, follow theme changes, and reopen at a usable size instead of leaving hidden sessions, stale colors, or unreachable controls. 2399ce7
  214. 214An already-open Control UI page now notices when terminal support is enabled and makes the terminal available without requiring a manual refresh. 3f976f9
  215. 215Opening a new Control UI terminal tab after closing another no longer inherits an old exited state. 3c03389
  216. 216The Control UI terminal no longer crashes when its web component is loaded more than once in a shared browser registry. f2e5159
  217. 217Control UI terminals now use installed Nerd Font fallbacks so supported prompt and listing icons render as glyphs instead of placeholder boxes#100128
  218. 218The Control UI integrated terminal now shows one cursor instead of overlapping Chrome and terminal carets, making focus and typing state clearer#100240
  219. 219The Control UI terminal's new-session button now aligns with the surrounding tabs for a cleaner, easier-to-scan tab bar#100256
  220. 220Telegram automations can now tell from platform metadata whether a sender is a bot, making routing and classification less dependent on usernames or naming conventions#96810 Thanks @lin-hongkuan, @ohyeah521.
  221. 221Telegram sends and message actions that omit an account now consistently use the configured default bot instead of a stale identity that can misroute or reject the action#98789 Thanks @yetval.
  222. 222Telegram destinations genuinely named current, self, this, or me can now be reached through configured entries, while accidental bare session words fail closed#94107 Thanks @obviyus, @silver-state, @zhangguiping-xydt.
  223. 223Telegram sends to an username now use the account's configured proxy or custom Bot API endpoint for both target resolution and message delivery#100868 Thanks @machine3at.
  224. 224Telegram webhook startup now releases its listener, bot, and network resources after a fatal registration error such as invalid or revoked credentials#100863 Thanks @machine3at.
  225. 225Telegram photo albums now give the model every successfully downloaded image in order instead of only one photo and unusable file references, while failed items are omitted#97045 Thanks @nianjiuzst, @obviyus.
  226. 226Telegram replies now omit internal tool-execution failure lines and deliver only the intended assistant answer#95774 Thanks @mushuiyu886.
  227. 227Telegram replies retain literal wording such as `&ltTelegram replies retain literal wording such as <think> when it is part of the answer, while genuinely marked reasoning remains hidden. #97286 Thanks @drickon, @obviyus.
  228. 228Telegram heartbeat fallbacks now hide the notify=false control marker and deliver silently as requested, including suppressing marker-only replies#100735 Thanks @hackerismydream, @vincentkoc.
  229. 229Telegram stickers and other plugin message actions now stay in the active forum topic or thread when sent to the matching conversation, including through Gateway dispatch#80293 Thanks @artdaal.
  230. 230Telegram messages can now be sent proactively through the message tool or openclaw message send instead of failing as an unsupported channel#92107 Thanks @bladin, @obviyus.
  231. 231sessions_send now rejects Telegram topic child sessions before dispatch and directs callers to the parent group, reducing misrouted agent work#99845 Thanks @nianjiuzst, @qingminglong.
  232. 232Polls now follow the selected direct or hybrid channel instead of being misrouted through the Gateway, with clear errors for unsupported duration or anonymity options#99950 Thanks @nianjiuzst.
  233. 233Established Telegram direct-message sessions now avoid resending recent messages already stored in the transcript, reducing token use and repetitive or confused replies#89855 Thanks @sweetcornna.
  234. 234Telegram direct-message follow-ups now include one copy of the previous assistant reply in recent context instead of duplicating it and wasting tokens#98769 Related #98767. Thanks @rabsef-bicrym.
  235. 235Telegram bots in ambient group mode now see recent room context before deciding whether to speak, reducing replies to isolated fragments that were not directed at the bot#99143 Related #99142. Thanks @obviyus.
  236. 236Telegram group agents now receive one chronological copy of recent messages instead of duplicated history and repeated delivery details consuming context#99256 Related #99218. Thanks @obviyus.
  237. 237Telegram ambient group conversations can now retain unmentioned room context across later turns, restarts, and compaction without repeatedly replaying the same window#99306 Related #99257. Thanks @obviyus.
  238. 238Telegram ambient group sessions now restore the relevant older chat context after a reset instead of silently treating archived messages as already visible#99385 Related #99373. Thanks @obviyus.
  239. 239Telegram group agents now post visible replies when directly mentioned or replied to, while continuing to ignore unaddressed background chatter#99866 Related #99854. Thanks @obviyus.
  240. 240Telegram direct-message follow-ups now include one accurate copy of each earlier assistant reply instead of duplicating a hidden-instruction version#100573 Thanks @momothemage, @mooresoftware.
  241. 241Telegram's live progress view now keeps reasoning, commentary, formatting, and tool activity readable and stable, then leaves a concise completion summary instead of disappearing#98907 Thanks @marvinthebored, @peetiegonzalez.
  242. 242Telegram rich replies and progress messages containing OAuth email addresses now arrive instead of being rejected by Telegram validation#95900 Thanks @obviyus.
  243. 243Telegram progress updates now truncate safely around emoji and other multi-unit characters, preventing broken glyphs and rejected Bot API payloads#96456 Thanks @he-yufeng.
  244. 244Telegram streaming draft previews no longer break or show garbled text when an emoji falls at the size boundary, so long previews can keep updating normally#96504 Thanks @mushuiyu886, @obviyus.
  245. 245Telegram replies now keep typing visible through more temporary API failures and fall back to plain text when valid rich content cannot be delivered#99745 Thanks @obviyus, @veda-openclaw.
  246. 246Telegram typing indicators now retry after transient network failures, restoring status feedback without adding duplicate-message risk to normal sends#100762 Thanks @lzw112, @vincentkoc.
  247. 247Telegram's final collapsed progress summary now includes Claude CLI thinking activity that was shown during the run instead of making that work appear to vanish. 4212de9 Thanks @vincentkoc
  248. 248Telegram users with /reasoning on now receive the model's saved reasoning messages alongside the final answer#97875 Thanks @fuller-stack-dev, @marvinthebored.
  249. 249Telegram groups and forum topics now show a typing indicator as soon as an addressed message is accepted, without signaling activity for ignored chatter#99965 Thanks @moeedahmed.
  250. 250Telegram configurations with legacy `capabilities[]` now inherit the normal inline-button policy, restoring clickable buttons without overriding intentional opt-outs. #96468 Thanks @vincentkoc, @zhangguiping-xydt.
  251. 251Telegram users still receive a plain-text reply when rich formatting for an email, URL, mention, hashtag, command, phone number, bank card, or similar entity is rejected, instead of the bot going silent#96642 Thanks @moguangyu5-design.
  252. 252Telegram inline buttons supplied by plugins now run their intended actions and cleanup instead of posting raw callback data into chat#97174 Thanks @goldmar.
  253. 253Telegram rich-text replies now render math formulas more reliably instead of exposing raw LaTeX-style markers#97197 Thanks @vincentkoc, @wangwllu.
  254. 254Telegram final replies and media sends now fall back to readable plain text when formatting, captions, or quotes are rejected, and routine flood waits up to 60 seconds are honored instead of dropping the message#98786 Related #98778. Thanks @obviyus.
  255. 255Telegram plugins can now turn a button tap into a normal user reply to the agent, while failed or skipped submissions leave the button available for another attempt#98922 Thanks @goldmar.
  256. 256Telegram tables, rankings, and literal line breaks now remain readable, with explicit logs when rich content must fall back to plain text#99861 Related #99833. Thanks @obviyus.
  257. 257Telegram rich messages using `richMessagesTrue and Markdown table mode block` now display bordered, striped tables with the source column alignment. #95822 Thanks @obviyus, @zhangguiping-xydt.
  258. 258Telegram fallback messages now replace invalid numeric Unicode surrogate entities safely instead of emitting malformed text, while valid numeric emoji entities still render#96581 Thanks @llagy007, @weeli-009.
  259. 259Telegram documents received through a containerized local Bot API now arrive with their actual contents when its mounted data path differs between containers#91984 Thanks @ailucasdz, @dizesales.
  260. 260Telegram documents sent near a Gateway restart now retry after recovery instead of disappearing silently, while permanent failures still request a resend#98102 Related #98076. Thanks @davearcher18, @luoyanglang, @obviyus.
  261. 261Telegram rich messages and text-bearing forwards without a normal caption now reach the agent as readable conversation content instead of an unsupported-message placeholder#98735 Thanks @obviyus.
  262. 262Telegram now tells users when an attachment cannot be downloaded, reports the actual size limit for oversized files, and still retries transient failures such as rate limits#100051 Thanks @batyaro777.
  263. 263Telegram replies and forwards now preserve visible text from rich details, lists, math, captions, and credits so the agent receives the context users actually saw#100570 Thanks @veda-openclaw, @wangwllu.
  264. 264MP3 speech from Piper, Kokoro, and other OpenAI-compatible TTS endpoints now arrives in Telegram as a native voice note rather than a filename-style audio attachment#100715 Thanks @hemantsudarshan.
  265. 265Telegram no longer follows a successfully delivered final answer with a contradictory generic error when a later dispatch step fails, while partial-only failures still receive the existing fallback#90152 Thanks @zhangguiping-xydt.
  266. 266A temporary Telegram reply-session conflict no longer traps a DM or forum topic in constant retries that block later messages; retries are paced, conversation order is retained, and unrelated chats continue processing#96550 Thanks @cnbarrier404, @vacinc.
  267. 267Telegram reactions and message deletions now retry brief socket or Undici network failures, reducing unnecessary action failures without adding duplicate risk to ordinary message sends#96612 Thanks @miorbnli.
  268. 268Telegram messages entering through isolated ingress now proceed to the agent reply instead of replaying the same message in a loop#96847 Thanks @obviyus.
  269. 269Long-running Telegram turns can finish without being reclaimed and processed again midway, reducing stalled or duplicate delivery while giving operators a clearer unhealthy status when the backlog stops draining#96962 Thanks @joshavant.
  270. 270Telegram bots using isolated polling can resume ordered message processing after a stalled drain or Gateway restart without manual database repair#97118 Thanks @romneyda, @vincentkoc.
  271. 271Long non-streamed Telegram group replies now keep every chunk visible, including the beginning, while delivery receipts cover all generated text chunks#97304 Thanks @aliseturtle-lu, @obviyus.
  272. 272Long streamed Telegram replies now deliver their middle sections under the default configuration instead of silently omitting part of the answer#97312 Thanks @brycemurray, @obviyus.
  273. 273Telegram polling now recovers from temporary rate limits, server failures, and malformed error responses without disabling the account, while busy bots avoid cache writes that could trigger false stall restarts#98775 Related #98772, #98773. Thanks @obviyus.
  274. 274A repeatedly failing Telegram update no longer blocks later messages in the same chat or topic, and replayed updates are retried safely without duplicate commands or apology spam#98776 Related #98774. Thanks @obviyus.
  275. 275Telegram webhook messages now survive Gateway restarts and temporary processing failures, while accounts recover from brief startup errors and repeated restarts stop leaking network connections#98806 Related #98777. Thanks @obviyus.
  276. 276Queued Telegram updates now remain replayable until restart recovery is safely recorded, reducing message loss during a crash at processing startup#104032 Thanks @obviyus, @vincentkoc.
  277. 277Telegram sends now retry a safe TCP or TLS connection timeout, reducing lost final replies during flaky handshakes without retrying failures that may already have reached Telegram#101258 Thanks @lzw112.
  278. 278Telegram startup logs now show local socket failures such as EADDRNOTAVAIL instead of incorrectly steering operators toward DNS troubleshooting#97130 Thanks @zhangguiping-xydt.
  279. 279Telegram bot probes, webhook checks, membership audits, and polling now reject oversized Bot API success bodies before they can exhaust Gateway memory#97271 Thanks @hugenshen.
  280. 280Telegram chat-ID lookup now fails safely on oversized getChat responses instead of risking excessive Gateway memory use during onboarding or routing#97274 Thanks @hugenshen.
  281. 281Telegram onboarding now offers both the classic BotFather chat flow and the official web interface for creating a bot and copying its token into OpenClaw#100540
  282. 282After /login codex succeeds in Telegram, retrying the request now uses the newly authenticated OpenAI profile instead of the previous account. fca0c81 Thanks @100yenadmin
  283. 283Telegram /steer and /tell commands can redirect an active Codex task during streaming or tool work instead of arriving late or becoming follow-up messages#98126 Related #81594. Thanks @100yenadmin, @kyzcreig.
  284. 284Saying wait in a Telegram group conversation no longer cancels active OpenClaw work, while explicit stop commands still take effect immediately#98639 Thanks @ianchen08.
  285. 285Telegram messages that cannot be steered into an active Codex turn are now retained for handling afterward instead of disappearing without a reply#103916 Thanks @jalehman.
  286. 286When Telegram requests overlap, the newest authorized message now wins without an outdated reply being sent or replaced queued work being started#103965
  287. 287A Telegram reply that has already started is no longer unexpectedly cancelled when another authorized command arrives. 52a3314 Thanks @vincentkoc
  288. 288Signal auto-replies now quote the message that triggered them, making responses easier to follow in groups and busy conversations#95718 Thanks @jesse-merhi.
  289. 289Signal reaction shortcuts now apply only to the intended structured exec or plugin approval, including forwarded monitor and chunked prompts, while ordinary messages that merely quote approval commands no longer gain controls; older delivered prompts may still require /approve once after upgrade#96880 Thanks @joshavant.
  290. 290Signal users who enable status reactions can now see when OpenClaw accepts a message, works, uses tools, compacts, stalls, or finishes in direct and group chats#98791 Thanks @jesse-merhi.
  291. 291Signal QuickStart now shows one clear signal-cli installation failure and proceeds directly to the custom-path prompt instead of repeating the missing-binary message#96932 Thanks @romneyda.
  292. 292Signal plugin setup now handles slow, malformed, or oversized GitHub release metadata without risking process memory exhaustion#97536 Thanks @hugenshen.
  293. 293Signal container mode now stops oversized or runaway signal-cli-rest-api responses from threatening the entire OpenClaw process#97539 Thanks @alix-007.
  294. 294Invalid JSON from the Signal REST container now produces a clear Signal-specific failure instead of exposing a raw parser error#98073 Thanks @lsr911, @vincentkoc.
  295. 295Signal QuickStart on macOS now installs signal-cli through Homebrew instead of downloading an incompatible Linux package, and gives platform-specific guidance when Homebrew is unavailable#96909 Thanks @romneyda.
  296. 296Signal container receives now reject oversized JSON frames before buffering them, limiting memory pressure without affecting normal messages or separately fetched attachments#99992 Thanks @sunlit-deng.
  297. 297Signal users can assign stable names such as `signalMe or signal:ops` to repeat contacts and groups instead of reusing raw phone numbers, UUIDs, or IDs. #95738 Thanks @jesse-merhi.
  298. 298Signal users now receive clean assistant replies without internal tool status, reasoning tags, or tool-call markup#97360 Thanks @masatohoshino.
  299. 299Signal local-file attachments that are oversized or use suspicious paths now fail quickly with a clear error before consuming excessive Gateway memory#101391 Thanks @cxbasdev.
  300. 300Slack channels can keep ambient OpenClaw participation while the opt-in ignoreOtherMentions setting prevents replies to conversations aimed at another person or group and retains that conversation as context for a later bot mention#53467 Thanks @hanamizuki.
  301. 301Slack operators can now choose off, first, all, or batched reply threading per channel, with automatic replies and message tools following the same effective choice#82253
  302. 302Slack button and select interactions now remain in the correct assistant thread and show a working status there until the follow-up turn finishes#82895 Thanks @wukongai-cmu.
  303. 303The first Slack reply after a daily or idle reset can reuse recent thread history, so the conversation does not suddenly start from scratch#97100 Thanks @bek91.
  304. 304Slack replies stay attached to the root thread's session history instead of accumulating separate, nearly empty child sessions#97168 Related #96535. Thanks @gorkem2020, @liuwqgit.
  305. 305Ordinary Slack thread replies no longer download and process the opening message attachments again, while new or reset sessions still receive those files once#100516
  306. 306Session history now identifies Slack replies that were generated but intentionally superseded before delivery, so operators do not mistake them for messages the user received#100607 Thanks @bek91.
  307. 307Slack replies in very long threads and on busy Gateways now avoid several unnecessary waits, reducing stalls before thread and direct-message events reach the agent#101888 Thanks @obviyus.
  308. 308Slack agents can now read thread messages whose visible content exists only in attachments or blocks, including alerts with empty top-level text#97727 Thanks @chthtlo.
  309. 309Slack Codex conversations now retain one final assistant reply in history instead of duplicating it through both the app-server transcript and delivery fallback#100160 Thanks @steipete-oai.
  310. 310Scheduled and heartbeat-driven Slack messages now use the configured agent name and icon, with graceful fallback to the app identity when Slack rejects customization#84335 Thanks @rohang2005.
  311. 311Longer Slack assistant-thread replies now show changing progress notes so users can tell OpenClaw is still working#85507 Thanks @emergentash.
  312. 312Slack presentation messages now arrive as native Block Kit cards with working headers, controls, and receipts instead of flattened plain text#95463 Thanks @zoowh.
  313. 313Slack rich-text block actions can now include emoji near the preview limit without producing malformed interaction text or downstream encoding failures#96577 Thanks @llagy007, @weeli-009.
  314. 314Slack buttons and menus now preserve time labels such as `900` and return the intended action value when selected. #99877 Thanks @qingminglong, @rodja.
  315. 315Slack message reactions now accept common emoji or shortcode names, can target the current message without repeating its ID, and provide clearer member-lookup guidance#100375 Thanks @gorkem2020.
  316. 316Slack now uses one static acknowledgement reaction alongside its native assistant loading status by default, avoiding two competing progress displays for the same reply#100462 Thanks @steipete-oai.
  317. 317Slack messages and Block Kit labels now truncate without splitting emoji into broken replacement characters or invalid payload text#96382 Thanks @ly-wang19.
  318. 318Long Slack command and plugin approval previews now keep emoji intact at the length boundary, avoiding malformed approval text or payloads#96576 Thanks @llagy007, @weeli-009.
  319. 319Slack slash-command choice menus now shorten long labels without splitting emoji at the 75-character limit#97923 Thanks @lexes7.
  320. 320Slack replies now keep each agent's custom name and avatar through streaming or fallback delivery instead of reverting to the app identity#100084 Thanks @moerai.
  321. 321Slack operators running multiple Gateways through one Socket Mode app now receive a startup warning explaining why events may reach another connection and how to choose a safer deployment setup#79938 Thanks @jeffvsutherland.
  322. 322Slack replies no longer expose internal tool-failure banners, reasoning scaffolding, or tool-call markup to users#97367 Thanks @masatohoshino.
  323. 323When Slack accepts a reply but the confirmation is lost, OpenClaw can verify the existing post and avoid sending a duplicate#97480 Thanks @joeyfrasier.
  324. 324Slack replies now retry after a temporary session-start conflict instead of stopping before the expected message is delivered#99647 Thanks @steipete-oai.
  325. 325Slack read actions can again access intentionally allowlisted channel names when Slack supplies an ID and dangerouslyAllowNameMatching is enabled#95313 Thanks @jontsai.
  326. 326Slack message and attachment text is no longer copied into verbose or debug logs during inbound processing#96312 Thanks @steipete-oai.
  327. 327OpenClaw can use a trusted override for a compatible Slack API endpoint, while normal workspaces continue using Slack's public API and untrusted project .env files cannot redirect bearer-token requests#97154 Thanks @romneyda.
  328. 328Slack agents can now identify admitted bot-authored messages through is_bot: true, making it easier to prevent unwanted bot-to-bot replies#97822 Thanks @masatohoshino, @vincentkoc.
  329. 329Slack Socket Mode relay diagnostics now distinguish malformed WebSocket frames from transport failures, making channel problems easier to identify#98587 Thanks @lsr911, @vincentkoc.
  330. 330Slack startup and account checks now warn when a user OAuth credential is configured as the bot token, before identity confusion affects mentions or replies#99931 Thanks @ooiuuii.
  331. 331Long-running Slack integrations now keep conversation metadata caching within a fixed limit, preventing memory use from growing indefinitely as more channels and workspaces are encountered#101562 Thanks @vincentkoc, @zhangguiping-xydt.
  332. 332Discord tool-only replies no longer leave overlapping typing refreshes that suggest another answer is still coming, while explicitly configured typing behavior remains intact#84288 Thanks @dr00-eth.
  333. 333When a Discord voice-note reply fails, users now receive the assistant's answer as a threaded text fallback without duplicating text that was already delivered#89962 Thanks @danhayman.
  334. 334Discord's clear-all reactions action now returns a real error if any bot reaction remains instead of claiming complete success#90038 Thanks @masatohoshino.
  335. 335Discord now shows enabled Anthropic reasoning, notes, and tool activity in the right order with accurate counters and nonblank summaries#96106 Thanks @marvinthebored, @obviyus, @peetiegonzalez.
  336. 336Discord users now receive the reply text and a clear notice when an attachment is too large instead of seeing the completed response disappear#99577 Thanks @lin-hongkuan.
  337. 337Completed partial-stream Discord replies now arrive as fresh messages that can trigger normal unread cues after a user leaves the channel#99711 Thanks @davelutztx.
  338. 338Discord completion and error reactions now remain visible for the configured doneHoldMs and errorHoldMs durations instead of fixed default delays#94736 Thanks @liuwqgit.
  339. 339Discord voice replies now keep their accompanying text and extra media attached to the original message even when single-use reply mode is enabled#95978 Thanks @nxmxbbd.
  340. 340Discord attachments queued while OpenClaw is busy now remain available when the message finally runs instead of disappearing after temporary download links expire#96183 Thanks @judsonnudson, @zacharyyw.
  341. 341Generated Discord thread names now preserve multiple Markdown emphasis spans without dropping or stranding formatting markers#96394 Thanks @ly-wang19.
  342. 342Discord's recent-model buttons now shorten long names without breaking emoji or producing invalid picker payloads#97600 Thanks @llagy007, @weeli-009.
  343. 343Long or media-rich implicit Discord replies now quote and notify the referenced user once in first or batched mode, while explicit and all replies retain every intended reference#100784 Thanks @qingminglong, @revision-co-ltd.
  344. 344Discord replies, cron reports, and other outbound messages are less likely to disappear during a brief Gateway reconnect, without replaying chunks or media Discord already accepted#100896 Thanks @tiffanychum.
  345. 345Discord automatic thread titles now handle long messages and channel details containing emoji without building malformed prompt text#101551 Thanks @alix-007.
  346. 346Discord voice playback failures now produce a readable error within the 8,192-byte limit, including when ffmpeg output contains non-English text or emoji#104230 Thanks @qingminglong.
  347. 347Multiple Discord bot accounts in one server now keep independent voice sessions, and configured voice auto-join works even when Discord becomes ready before voice startup completes#87530 Thanks @geekhuashan.
  348. 348Checking a Discord member who is not in voice now reports them as disconnected instead of raising a misleading command or gateway failure#90969 Thanks @asock.
  349. 349Adding a named Discord account no longer knocks a SecretRef-backed default account offline or into a restart loop#96401 Thanks @849261680.
  350. 350Discord voice conversations in stt-tts mode now retain earlier spoken context across turns instead of starting over after each reply#97746 Thanks @karabaralex, @sanjays2402.
  351. 351Discord voice playback now turns broken ffmpeg output pipes into a normal playback error instead of an uncaught Gateway-level exception#101088 Thanks @masatohoshino.
  352. 352Discord bots can now recover in place after repeated session-resume rejection, reducing prolonged outages, lost replies, and full Gateway restarts#103596
  353. 353Discord voice playback now cleans up ffmpeg after output-pipe failures, reducing both Gateway crashes and leftover transcoder processes#101124
  354. 354The configured primary Discord account now starts first in multi-account setups, so the main bot is not delayed behind secondary or invalid entries after a restart#101292 Thanks @turbotheturtle.
  355. 355Discord message reads and searches now decode raw compressed responses correctly and return clear errors for unexpected data instead of garbled output or opaque failures#80788 Thanks @jbetala7.
  356. 356Discord REST calls now fail with a clear error when a response is oversized or stalls instead of risking unbounded memory use and process instability#95412 Thanks @alix-007.
  357. 357Discord account health checks now fail safely on oversized identity responses instead of risking a Gateway crash or out-of-memory failure#97278 Thanks @hugenshen.
  358. 358Discord message, thread-history, and attachment requests now reject oversized successful responses before they can drive excessive Gateway memory growth#97693 Thanks @alix-007.
  359. 359Discord PluralKit lookups and voice-upload setup now stop unexpectedly large JSON responses before they can exhaust memory#97706 Thanks @cxbasdev.
  360. 360Malformed successful Discord responses now fail with endpoint-specific context instead of surfacing a raw parser error or crashing OpenClaw#97889 Thanks @lsr911.
  361. 361An oversized Discord gateway metadata response now logs a bounded error and falls back to Discord's default gateway URL instead of risking a Gateway crash#98682 Thanks @wings1029.
  362. 362Discord deployments in restricted networks can now route Gateway and REST traffic through an explicitly configured DNS or private HTTP(S) proxy without opening broad direct HTTPS egress#99126 Related #98266. Thanks @joshavant, @sallyom, @svuppala2006.
  363. 363Discord Gateway connections now cap incoming frames at 16 MiB, preserving tested large member events while rejecting extreme traffic before it pressures memory#99998 Thanks @sunlit-deng.
  364. 364Discord agents now receive `is_botTrue` for admitted bot messages while human and PluralKit sender behavior stays unchanged. #97824 Thanks @masatohoshino, @vincentkoc.
  365. 365Logged-out or replaced WhatsApp accounts now stay stopped until reconnection instead of entering repeated restart loops that can consume resources and slow other accounts#78511 Thanks @openperf.
  366. 366Eligible WhatsApp messages received during a brief reconnect now reach OpenClaw for an automatic reply instead of being marked read and silently skipped#80642 Thanks @vishalj99.
  367. 367Concurrent WhatsApp Web replies, media, reactions, and queued messages now send one at a time per account, reducing interference and unpredictable delivery order#99050 Thanks @ooiuuii.
  368. 368Completed WhatsApp replies now continue delivering when another message arrives mid-delivery, so overlapping conversations are less likely to go unexpectedly silent#100205
  369. 369Invalid OPENCLAW_WHATSAPP_WEB_SOCKET_URL values now fail immediately with a clear configuration error instead of breaking later during socket startup#97697 Thanks @romneyda.
  370. 370WhatsApp can now restore a saved linked-device session from a valid credential backup when the primary file is interrupted or corrupted, avoiding an unnecessary QR re-pair#99070 Thanks @leonidaslux.
  371. 371openclaw channels login --channel whatsapp now replaces expired QR codes in place so interactive terminals show one current, scannable code#100159
  372. 372A WhatsApp message interrupted by a temporary reply-session conflict can now be retried instead of being marked delivered and silently ignored on redelivery#101106 Thanks @andersonjeccel.
  373. 373OpenClaw can use a trusted override to point the normal Baileys socket at a compatible local WebSocket endpoint, while normal WhatsApp connections continue using the default path unless explicitly overridden#97155 Thanks @romneyda.
  374. 374WhatsApp group owners can reliably use /new, /stop, /status, and similar commands even when their sender identity arrives as an internal LID#93379 Related #77755. Thanks @jiveshkalra, @xialonglee.
  375. 375Direct WhatsApp polls now honor the same outreach timelock as other sends instead of reaching recipients during a blocked window. 1d128b4 Thanks @vincentkoc
  376. 376Replies to OpenClaw-authored WhatsApp group messages now remain visible on WhatsApp Desktop and other multi-device clients with their quote context intact#94879 Thanks @bartok9.
  377. 377WhatsApp direct sends and automatic replies now render combined bold-and-italic Markdown without stray asterisks, including when the formatted text contains emoji#96570 Thanks @llagy007, @weeli-009.
  378. 378Long WhatsApp auto-reply and inbound-message previews now preserve emoji and report the truncated character count accurately, making affected diagnostics readable without changing delivery#96580 Thanks @llagy007, @weeli-009.
  379. 379WhatsApp direct messages blocked by a reachout timelock now fail immediately with an explicit explanation instead of appearing accepted before a later delivery error#101264 Thanks @mcaxtr.
  380. 380With `channelsWith channels.whatsapp.actions.calls, MeowCaller, and telephony TTS configured, a WhatsApp agent can now call the requester and speak a short task-completion or urgent message. #99635
  381. 381Configured Weixin accounts with opaque IDs containing characters such as an at sign or . now start normally and preserve their account-specific routing#93686 Related #93556. Thanks @htkillermax-gif, @zhangguiping-xydt.
  382. 382Official Weixin installs and core-upgrade reconciliation now target plugin version 2.4.6 with its correct compatibility requirement instead of unexpectedly returning users to 2.4.3#96801 Thanks @lin-hongkuan.
  383. 383Compatible iMessage bridge users can create, read, and vote on native Apple Messages polls, with upgrade guidance for unsupported imsg installations#98421 Thanks @lobster, @omarshahine.
  384. 384Photos bridged from a remote iMessage Mac to a separate Gateway host now arrive in Codex conversations through a readable local path rather than a Mac-only filename#91803 Thanks @turbotheturtle.
  385. 385Voting for an emoji-labeled iMessage poll option no longer sends an extra one-word message that repeats the selected answer#98691 Thanks @omarshahine.
  386. 386Agents now answer iMessage polls, including polls with comments, with one native vote instead of an ordinary text answer, a repeated selection, or a separate reply to the comment#98781 Thanks @omarshahine.
  387. 387AppleScript-only and bot-user or SSH iMessage setups now deliver replies even when threading is unavailable, and database changes no longer leave inbound messages hidden behind stale recovery state#100446 Thanks @omarshahine.
  388. 388Direct iMessage chats using the imsg private API bridge now show typing as soon as a slow turn is accepted, without waiting for a read receipt#95621 Thanks @omarshahine.
  389. 389iMessage replies no longer lose ordinary sentence text that happens to end with user:, system:, or assistant#96392 Thanks @ly-wang19.
  390. 390Bursts of long iMessage messages can now be combined without cutting an emoji in half and sending broken text to the agent#97598 Thanks @weeli-009.
  391. 391iMessage startup warnings now distinguish working sender-allowlisted group setups from truly blocked configurations and point blocked operators to the correct fix#100046
  392. 392Bare 32-character iMessage group IDs from imsg now route scheduled and direct sends to the intended conversation instead of a nonexistent phone number#99525 Related #89235. Thanks @matthewdelprado.
  393. 393An iMessage helper pipe failure now ends pending work predictably and lets the monitor recover or stop cleanly instead of crashing the Gateway or hanging requests#101084 Thanks @masatohoshino.
  394. 394iMessage CLI send and action failures caused by broken output pipes now return a controlled error instead of risking a Gateway worker crash#101401 Thanks @cxbasdev.
  395. 395Default and named LINE bots configured under `channelsDefault and named LINE bots configured under channels.line.accounts now receive working webhook routes unless explicitly disabled, preventing valid inbound messages from ending in 404 responses. #81471 Thanks @edenfunf, @honorlin.
  396. 396LINE file uploads now retain recognizable audio extensions such as `LINE file uploads now retain recognizable audio extensions such as .m4a, allowing valid recordings to reach transcription instead of being treated as unknown files. #96403 Thanks @tancolo, @zaidazmi.
  397. 397LINE template titles, fallback text, and alt text now keep emoji intact at field limits, preventing broken previews and rejected payloads#97428 Thanks @ly-wang19, @vincentkoc.
  398. 398Long LINE button labels, quick replies, postback data, and media controls now preserve emoji at field limits instead of producing malformed text#97470 Thanks @ly-wang19, @vincentkoc.
  399. 399LINE messages, cards, menus, locations, and code blocks now preserve emoji and other multi-unit characters at field limits instead of producing broken text or rejected payloads#98994 Thanks @lexes7, @vincentkoc.
  400. 400LINE replies that combine text with an image, card, or location now report a failed rich-media portion accurately while delivering the text once and avoiding duplicate retries#100996 Thanks @masatohoshino.
  401. 401Feishu replies now arrive as completed blocks when block streaming is enabled without streaming cards, rather than disappearing entirely#94250 Related #55027. Thanks @vincentkoc, @xialonglee, @zichaolong.
  402. 402When an interactive command button falls back to text, users now receive the command they can copy, with Feishu document comments explaining the manual step#94385 Related #69754. Thanks @1yihui, @xialonglee.
  403. 403openclaw channels login --channel feishu now prints a compact QR code that stays scannable in a normal terminal window#97087 Thanks @nianjiuzst.
  404. 404Long Feishu streaming-card summaries now keep emoji and other non-BMP characters intact at the truncation boundary#97462 Thanks @ly-wang19.
  405. 405Long Feishu comments containing emoji at the cutoff now reach the agent as valid text instead of being split into malformed characters#97595 Thanks @llagy007, @weeli-009.
  406. 406Feishu and Lark registration and streaming-card requests now reject oversized provider JSON before it can place unbounded pressure on memory#97782 Thanks @alix-007.
  407. 407Supported interactive-card JSON sent through Feishu messages, thread replies, or text payloads now renders as a card instead of appearing as raw JSON#100883 Thanks @martingarramon, @vincentkoc, @zenorewn.
  408. 408Stalled Feishu tenant-token or streaming-card requests now time out with a clear error and release the processing lane so other Gateway messages can continue#102948 Thanks @hugenshen, @sallyom.
  409. 409Feishu setups that could send bot pushes but silently lost user replies now pass incoming messages into OpenClaw instead of failing during monitor startup#94013 Thanks @xydt-tanshanshan.
  410. 410Feishu one-to-one chats can receive text, media, card, and fallback replies again instead of losing the response after the incoming message was processed#94760 Thanks @obviyus, @xydigit-zt.
  411. 411Feishu card headers now show a clean agent emoji and name instead of descriptive text from identity.emoji, while flags, skin-tone variants, family emoji, and other valid sequences remain intact#96587 Thanks @harjothkhara, @leedongyu1128.
  412. 412Feishu video messages now show the duration of local and remotely loaded MP4 clips when duration detection is available#98235 Thanks @areslp.
  413. 413Temporary Feishu streaming-card refresh failures are now contained and logged for diagnosis instead of surfacing as unhandled errors#99301 Thanks @lwy-2.
  414. 414Feishu direct messages received while the bot identity is temporarily unavailable no longer turn ordinary user mentions into accidental forwarding targets#100891 Thanks @zhangguiping-xydt.
  415. 415Feishu error logs now shorten emoji-containing text at a valid character boundary, making card-action and WebSocket cleanup failures easier to read#101364 Thanks @zengwen-dt.
  416. 416Feishu Drive can now list files beyond the first page of a large shared folder by accepting its returned next_page_token, with invalid page sizes rejected clearly before the request#101572 Thanks @zhangguiping-xydt.
  417. 417A Feishu connection that stops receiving messages is less likely to remain falsely marked healthy because transport activity now updates channel health#90966 Thanks @acache, @richardataxai-lab, @vincentkoc.
  418. 418Canceling a Feishu reconnect, startup, or bot-identity retry wait now ends cleanly instead of risking a ReferenceError during cleanup#98137 Thanks @zhanglei99586.
  419. 419Feishu bot replies no longer expose internal tool or runtime failure banners alongside the intended response#98705 Thanks @zengwen-dt.
  420. 420Multi-account Feishu setups can now start the default channel with an environment-backed top-level SecretRef and separate inline secrets for named accounts, without replacing the protected secret with plaintext#96965 Thanks @zw-xysk.
  421. 421Google Chat sends and request verification now bound oversized API, certificate, and error responses, allowing normal traffic through while broken or hostile bodies fail or truncate without exhausting memory#96772 Thanks @vincentkoc, @wangmiao0668000666.
  422. 422Google Chat agents can now distinguish allowed bot messages through is_bot: true and handle automated senders differently from people#97825 Thanks @masatohoshino, @vincentkoc.
  423. 423Long Google Chat approval cards now preserve emoji at the text limit, preventing corrupted approval text or malformed card payloads#96573 Thanks @llagy007, @weeli-009.
  424. 424Google Meet join, creation, talk-back, transcription, and related automation now work across browser and account languages by using English in OpenClaw-controlled Meet tabs#89671 Thanks @unayung.
  425. 425Google Meet sessions launched through a paired macOS Chrome node now open the intended URL with the configured Chrome profile and audio tools, while unsupported actions and executable overrides are rejected before reaching the node#96908 Thanks @joshavant.
  426. 426When Google Meet's local OAuth callback port is occupied, openclaw meet auth login now offers the manual redirect-paste flow instead of stopping sign-in#96492 Thanks @jinduwang1001-max, @yetval.
  427. 427Microsoft Teams replies to long parent messages now keep emoji and similar characters intact in the agent's parent-message context instead of inserting malformed text#96569 Thanks @llagy007, @weeli-009.
  428. 428Microsoft Teams Adaptive Card button clicks now deliver the submitted value to the agent instead of arriving as empty messages#97546 Thanks @jimmypuckett.
  429. 429Microsoft Teams file delivery and chat lookup now cap large Microsoft Graph responses and return a labeled error instead of risking a process crash#97784 Thanks @alix-007.
  430. 430Microsoft Teams attachment recovery now declines oversized Graph metadata with diagnostics instead of buffering it into Gateway memory, while normal hosted media still downloads within configured limits#101082 Thanks @cxbasdev.
  431. 431The Microsoft Teams personal-chat welcome card now displays its greeting with the intended bold, medium emphasis#96290 Thanks @ly-wang19, @vincentkoc.
  432. 432Microsoft Teams thread history now preserves literal entity text such as `&ltMicrosoft Teams thread history now preserves literal entity text such as <APIKEY> instead of turning it into different markup before the agent sees it. #96342 Thanks @ly-wang19.
  433. 433Microsoft Teams feedback on long responses now carries intact emoji into reflection processing, preventing a cutoff from corrupting prompts, logs, or encoding#96578 Thanks @llagy007, @weeli-009.
  434. 434Oversized or malformed Microsoft Teams personal-chat attachment metadata now fails safely with a warning instead of consuming unbounded Gateway memory#99125 Thanks @ly85206559.
  435. 435Long Matrix thread starters keep emoji and other special characters intact when OpenClaw shortens them for agent context#97121 Thanks @bartok9, @ly-wang19.
  436. 436Matrix operators now receive a structured warning when token rotations leave multiple populated storage roots, with details for identifying and carefully archiving stale folders#97353 Thanks @eldron81-r2d2, @outdog-hwh.
  437. 437Long Matrix reply quotes sent to agents now truncate emoji and other multi-unit characters without leaving broken text#97471 Thanks @ly-wang19.
  438. 438Matrix media downloads now enforce size and idle-timeout limits before buffering, including for encrypted media#97662 Thanks @alix-007.
  439. 439Malformed successful Matrix responses now produce a controlled homeserver error instead of an opaque unhandled JSON parsing failure#97973 Thanks @lsr911.
  440. 440Matrix dependency setup now stops its child process predictably and reports the failure when a local command's output pipe breaks#101597 Thanks @alix-007.
  441. 441Matrix replies now deliver the intended answer without leaking internal tool diagnostics, reasoning tags, or assistant-only scaffolding#97372 Thanks @masatohoshino.
  442. 442Mattermost streaming draft previews now shorten long text containing emoji without showing a malformed replacement character#97472 Thanks @ly-wang19.
  443. 443Mattermost channel monitoring now rejects inbound events above 16 MiB and reconnects, limiting memory exposure while continuing to accept normal large messages#99366 Thanks @sunlit-deng.
  444. 444Mattermost API calls now stop oversized or endless successful responses before they can consume unbounded memory, while normal requests and uploads continue unchanged#96033 Thanks @alix-007.
  445. 445Mattermost API failures with an empty JSON body now produce a clear status-based error instead of an Unexpected end of JSON input crash#97851 Thanks @pick-cat.
  446. 446Mattermost installations repaired after an upgrade now load and reconnect on Gateway restart without requiring a manual plugin-enable setting, including restrictive allowlist setups#98608 Related #98564. Thanks @jacobtomlinson, @shakkernerd.
  447. 447Mattermost teams with more than 200 members can now discover and address valid peers beyond the first page of the team directory#98877 Related #98871. Thanks @qingminglong.
  448. 448Mattermost replies now show the intended assistant response without exposing internal tool-failure diagnostics#98693 Thanks @zengwen-dt.
  449. 449Native /oc_* Mattermost commands work again in packaged installs using openclaw/mattermost, without allowing disabled or denied plugins to bypass Gateway checks#98819 Related #98740. Thanks @amknight, @keltech-services.
  450. 450Nextcloud Talk sends and reactions now bound server response sizes, protecting OpenClaw from hangs or runaway memory use while preserving normal delivery#96031 Thanks @alix-007.
  451. 451Nextcloud Talk startup checks now show a concise bot-admin API failure without buffering an arbitrarily large error body#97811 Thanks @pick-cat.
  452. 452Long IRC messages now keep emoji and other supplementary characters intact when split into delivery chunks, including with unusually small configured chunk limits#96572 Thanks @llagy007, @weeli-009.
  453. 453IRC reconnects now rotate fallback nicknames after a 433 conflict instead of repeatedly retrying the same occupied name#96108 Thanks @wendy-chsy.
  454. 454IRC outbound text now preserves escaped emoji and keeps invalid surrogate escapes literal instead of silently replacing them with corrupted characters#97683 Thanks @llagy007, @weeli-009.
  455. 455Long IRC replies now arrive complete when they contain Chinese, Cyrillic, emoji, or other non-ASCII text, while respecting messageChunkMaxChars#99138 Thanks @yetval.
  456. 456IRC bots now reconnect and rejoin configured channels after a temporary server or network disconnect instead of staying silent until OpenClaw is restarted#100799 Thanks @zhangguiping-xydt.
  457. 457IRC users now receive the intended answer without internal tool-failure banners or assistant-only scaffolding appearing in channel messages#97214 Thanks @masatohoshino, @studentzhou-svg, @vincentkoc.
  458. 458IRC allowlists now reject host-less nick!user entries by default and guide operators toward verified full host masks, reducing impersonation risk#98339 Thanks @yetval.
  459. 459Twilio SMS account checks now handle malformed successful JSON with safe phone-number listing or a clear Messaging Service error#97999 Thanks @lsr911.
  460. 460SMS replies now hide internal tool-trace failure banners and show only the intended assistant response#97989 Thanks @zengwen-dt.
  461. 461Long Synology Chat messages and diagnostic previews now truncate without cutting an emoji or other supplementary character in half, keeping downstream text valid#96574 Thanks @weeli-009.
  462. 462Zalo setup, polling, sending, and health checks now reject abnormally large successful replies before they can push the Gateway into severe memory pressure#97277 Thanks @hugenshen.
  463. 463Zalo operators can point Bot API calls at a compatible alternate endpoint without patching code, while ordinary workspace environment files cannot silently redirect traffic and millisecond message times remain accurate#98768 Thanks @romneyda.
  464. 464Zalo gateway startup output now shows the connected bot account name when the Bot Platform supplies it#99274 Thanks @romneyda.
  465. 465Zalo operators can send proactive CLI or scripted messages to valid nonnumeric chat_id values without an Unknown target rejection#101548 Thanks @goutamadwant.
  466. 466QQBot upgrades now migrate recoverable credential backups into SQLite without deleting source files when import fails, while disposable caches rebuild separately#89597
  467. 467QQBot can now deliver documents and media created by sandboxed agents from authorized workspace paths while continuing to block path escapes#92872 Thanks @sliverp, @zhangguiping-xydt.
  468. 468QQBot speech-to-text now returns an early, labelled error when an OpenAI-compatible transcription endpoint sends an oversized response instead of buffering the full body in memory#96968 Thanks @mushuiyu886.
  469. 469QQBot Markdown tables now keep escaped pipe characters inside their cells, so commands and expressions do not shift into the wrong columns#97429 Thanks @ly-wang19.
  470. 470QQBot reminders created from long text now receive readable job names even when an emoji falls at the cutoff, rather than storing a broken character#96575 Thanks @llagy007, @weeli-009.
  471. 471QQBot status now reports disconnections and fatal close reasons accurately, then returns to connected only after a READY or RESUMED event#100127 Thanks @masatohoshino, @vincentkoc.
  472. 472QQBot approval cards, message previews, logs, media paths, and retry warnings now shorten emoji-containing text without broken replacement characters#101421 Thanks @wangmiao0668000666.
  473. 473QQBot previews, errors, commands, speech-to-text messages, media diagnostics, and logs now remain valid when emoji-containing text reaches a length limit#101516 Thanks @vincentkoc, @wangmiao0668000666.
  474. 474QQBot now avoids accidental reminders, limits exposure of private media details, and requires explicit confirmation before destructive channel or announcement actions#98032 Thanks @patrick-erichsen.
  475. 475Tlon and Urbit channel failures now bound oversized or malformed error responses before they can cause memory spikes, while retaining useful short messages#98496 Thanks @pandah97.
  476. 476Tlon now stops oversized or stalled external image downloads before they consume unbounded memory and can continue the message with the original URL#100374 Thanks @hugenshen.
  477. 477Oversized Tlon scry responses now fail with a clear path-specific error instead of risking a Gateway out-of-memory crash#100376 Thanks @hugenshen.
  478. 478Tlon approval notifications now keep emoji intact at the preview limit, preventing malformed message previews#97599 Thanks @llagy007, @weeli-009.
  479. 479Tlon media uploads now stop safely when Memex returns an oversized or malformed response instead of allowing the upload attempt to consume excessive memory#101115 Thanks @cxbasdev.
  480. 480Repeated Nostr profile publishing now clears relay timeout timers after success, reducing stale resource buildup in long-running agents#98720 Related #98463. Thanks @wangmiao0668000666, @zhanglei99586.
  481. 481Google Meet and direct Voice Call sessions now keep the identity, workspace, routing, and transcript attribution of the agent that started the call instead of silently switching to the default agent#77763 Thanks @quangtran88.
  482. 482Google Live call history now keeps both sides of the conversation, while reconnects avoid submitting unfinished speech or combining unrelated utterances#84161
  483. 483OpenAI Realtime outbound calls now play one opening greeting even when the recipient speaks immediately after answering, while later interruptions continue to stop active speech#86285 Thanks @giodl73-repo, @jnikolaidis.
  484. 484Callers using realtime OpenAI or Google voice calls can now interrupt assistant speech and have buffered phone audio stop promptly, while other providers keep the existing local fallback#90749 Thanks @moellenbeck.
  485. 485Voice callers now hear a completed answer without waiting for post-turn compaction, and a successful early playback is no longer repeated#94015 Thanks @xialonglee.
  486. 486Twilio voice-call operators can select US1, IE1, or AU1 so call control and records use the intended Region, with US1 remaining the default#95832 Thanks @jodok.
  487. 487Inbound Telnyx-style and Plivo voice conversations can now continue after the caller's first response instead of falling silent before OpenClaw speaks again#100255 Thanks @dvy.
  488. 488Valid Twilio and Plivo callbacks now pass signature checks behind trusted IPv4 reverse proxies even when Node reports the proxy as an IPv4-mapped IPv6 address#100261 Thanks @rohitjavvadi.
  489. 489Repeated voice-call webhook deliveries are now acknowledged without repeating call or transcript side effects within the replay window#100263 Thanks @xialonglee.
  490. 490The Twilio voice-call provider now rejects unsupported API hostnames before sending a request and accepts only OpenClaw's supported Twilio regional hosts. 094c0d4 Thanks @vincentkoc
  491. 491An accepted voice message that arrives while OpenClaw is already replying can still receive a voice response when tts.auto: "inbound" is configured#95596 Thanks @mcaxtr.
  492. 492Realtime voice prompts now remain readable when long agent names or injected context containing emoji must be shortened#101304 Thanks @alix-007.
  493. 493Google Meet local audio bridges now shut down cleanly and log a warning when a capture or playback command pipe fails, rather than crashing on an unhandled stream error#101596 Thanks @alix-007.
  494. 494Voice Call history now stays with the correct configured agent across Gateway restarts and upgrades, while ambiguous legacy state is left untouched with actionable warnings#89884 Thanks @mushuiyu886.
  495. 495Completed Voice Call status remains available through the Gateway, tool, and CLI after restart or eviction instead of incorrectly appearing missing#99797 Thanks @darren2030.
  496. 496ClickClack agent replies to top-level messages now stay in the active channel or direct message, while replies inside real threads remain threaded#100582 Thanks @marvinthebored, @vincentkoc.
  497. 497ClickClack can now show opt-in, durable commentary and tool activity during a run so users are not left with an empty channel until the final reply#99954 Thanks @obviyus, @ragesaq.
  498. 498ClickClack now stops oversized REST success responses at the provider limit, giving users and operators a predictable failure instead of continued streaming and memory growth#96970 Thanks @mushuiyu886, @vincentkoc.
  499. 499Messages that fail before reaching Discord, Slack, Matrix, or another channel can now be replayed after connectivity returns, while uncertain post-send outcomes still avoid blind duplicates#101024 Thanks @sunnyshu0925.
  500. 500Messages sent through OpenClaw's message tool now retain configured static or identity response prefixes, keeping routed and broadcast messages consistently labeled#93639 Thanks @zengwen-dt.
  501. 501Completions from subagents, scheduled tasks, media jobs, and agent harnesses now return through the same configured account, destination, and thread that requested them#98240 Thanks @yetval.
  502. 502Replies and attachments already accepted by a channel are no longer resent after a restart or recovery failure, while genuinely unsent items remain retryable#99600 Thanks @zhangguiping-xydt.
  503. 503Outbound sends now report failed and partially delivered messages with useful per-part outcomes instead of presenting every attempt as a success#99928 Thanks @masatohoshino.
  504. 504Non-streaming channels no longer send the same final text or media twice for one message, while genuinely separate replies with different routing or thread identities still go through#100828 Thanks @vincentkoc, @zhangxiaojiujiayi.
  505. 505Cron and outbound channel sends no longer report success without a usable platform receipt, making missing notifications show as not delivered or suppressed instead of falsely delivered#79811 Thanks @indulgeback.
  506. 506Queued messages now resume at a gentler pace after an outage, restart, or reconnect, reducing avoidable channel and provider rate-limit bursts while keeping recovery bounded#101118 Thanks @zengwen-dt.
  507. 507Noisy phone numbers with extra plus signs now match the intended Signal, iMessage, or WhatsApp contact, while identities with no digits are rejected safely#100467 Thanks @morluto.
  508. 508Reply directives containing hidden unsafe characters now produce stable, display-safe reply IDs before chat routing uses them#96446 Thanks @lin-hongkuan.
  509. 509Ambient agents now stay quieter in observed group conversations and honor operator instructions such as replying only when spoken to#99144 Thanks @obviyus.
  510. 510Ambient group chats now remain silent unless the agent deliberately sends a message, without stray status lines, tool summaries, compaction notices, delivery warnings, or overflow follow-ups#99145 Thanks @obviyus.
  511. 511Always-on group agents can now receive and answer valid unmentioned messages after a plugin fallback instead of silently dropping them#99506 Related #99457. Thanks @lzy3538, @zqchris.
  512. 512Agents catching up in busy group chats now receive clearer sender-by-sender history, making multi-person conversations easier to follow without exposing local paths or URLs#100366 Thanks @gorkem2020.
  513. 513Telegram and Discord plugin commands that send their own response can return { suppressReply: true }, preventing a second misleading empty-response warning or failure#80928 Related #80756. Thanks @alexuser, @unclouded77.
  514. 514With `messages.ackReactionScope"all"`, ambient room messages now receive the configured acknowledgement reaction across Discord, Slack, and Telegram. #87433 Thanks @paul-phan, @scoootscooob.
  515. 515Channel plugins can resume automatic recovery after a long healthy run, so an occasional later disconnect is not blocked by an old restart budget while true rapid crash loops remain capped#101413 Thanks @clintoncodewell.
  516. 516Telegram and other channels can recover automatically after certain API outages and timed-out shutdowns instead of remaining silent until a Gateway restart#94016 Thanks @sheyanmin.
  517. 517A partially delivered queued send is no longer blindly replayed after reconnect, reducing duplicate Telegram and other channel messages#96247 Thanks @obviyus, @rosenlo.
  518. 518Discord and other progress views now hide repetitive internal Code Mode polling while continuing to show meaningful tool activity#99893
  519. 519Long-running Discord and Nextcloud Talk integrations now bound their channel metadata caches instead of letting each newly encountered room increase memory use forever#101650 Thanks @alix-007, @vincentkoc.
  520. 520A transient Gmail watch-renewal failure now produces an error without crashing a long-running foreground openclaw webhooks gmail run process#100342 Thanks @cxbasdev, @vincentkoc.
  521. 521Channel previews, thread names, snippets, and shortened errors across browser and messaging integrations now preserve whole emoji and other Unicode characters. c16bb87 Thanks @vincentkoc
  522. 522Long Slack context labels, Zalo messages and captions, and extension command output now truncate without breaking emoji or other non-BMP characters. 7e03242 Thanks @hugenshen, @mushuiyu886, @vincentkoc
  523. 523Fenced code blocks that contain example lines resembling Markdown fence markers are now kept together instead of being split mid-block and becoming confusing or misread#96745 Thanks @ly-wang19, @vincentkoc.
  524. 524Long unbroken messages now keep emoji intact when split into delivery-sized chunks, preventing garbled replacement characters for users and channel plugins#96951 Thanks @bartok9, @ly-wang19.
  525. 525Skill command descriptions now remain fuller where supported and stay valid in Discord and Mattermost when emoji appears near a platform limit#99593 Thanks @pick-cat.
  526. 526Long emoji-containing agent labels now produce clean native channel thread names and introductions instead of broken characters#101527 Thanks @lsr911.
  527. 527Chinese, Japanese, and Korean bold labels followed immediately by text now render as bold instead of exposing literal `` markers in Telegram and other shared-Markdown channels#101230 Thanks @nicknmorty.
  528. 528Attachment download failures across WhatsApp, LINE, Signal, iMessage, Teams, Feishu, Mattermost, and Zalo now remain visible and actionable instead of disappearing or masquerading as successful media#100119
  529. 529OpenClaw now recognizes `OpenClaw now recognizes .m2a recordings as audio, allowing them to move through attachment, transcription, memory, and chat display workflows without conversion. #92167 Thanks @llljjjwww333.
  530. 530Files sent through Telegram and other supported chat channels now keep clean names such as report.png instead of exposing an internal cache identifier in the attachment filename#96565 Thanks @narahariraghava, @obviyus.
  531. 531Cron summaries, Teams and Slack replies, and other embedded assistant responses no longer expose provider reasoning markers such as </mm:think&gt#101036 Thanks @velanir-ai-manager.
  532. 532Punctuation around a model's NO_REPLY token no longer turns it into a visible chat message, while legitimate messages containing the token still arrive#98224 Thanks @sunnyshu0925.
  533. 533Slack, Discord, Telegram, WhatsApp, and Microsoft Teams users now receive a clear retry and re-authentication message when a model provider returns a recognized HTTP 401 error instead of seeing only a reaction or no useful reply#96599 Thanks @sjf-oa.
  534. 534Text commands such as /model fable now reliably display their confirmation even in flows that suppress ordinary source replies#100151
  535. 535The bare /think command now shows available thinking levels promptly in Telegram, Slack, and Discord without waiting on slow model discovery#101926 Thanks @vincentkoc.
  536. 536Direct mentions to Telegram and Discord group bots using message_tool_only now produce visible channel replies on both new and resumed sessions#99389 Related #99371. Thanks @obviyus.
  537. 537The /usage full footer is shorter and easier to read on Telegram and other narrow displays, with detailed token information still available through dedicated views#92877 Thanks @marvinthebored.
  538. 538Custom usage footers now render alias and map fallbacks correctly even when model or mode names collide with properties such as toString or constructor#98503 Related #98466. Thanks @chenyangjun-xy, @zhanglei99586.
  539. 539Transient stdout or stderr read errors from gog gmail watch serve no longer crash OpenClaw while Gmail watch mode is running#100519 Thanks @cxbasdev.
  540. 540OpenCode Zen users can browse and run its supported Claude, GPT, Gemini, GLM, DeepSeek, MiniMax, Qwen, and other models without manually defining each route#92495 Thanks @mushuiyu886, @sallyom.
  541. 541Library and integration developers can now install a version-matched package, create independent AI runtimes, and reuse OpenClaw's supported model transports without embedding the full application#99059
  542. 542Featherless AI now has an official provider install and onboarding path, including FEATHERLESS_API_KEY, a curated featherless/Qwen/Qwen3-32B default, and support for exact Featherless model IDs#101092 Thanks @vincentkoc.
  543. 543Meta Model API is now exposed through the public meta provider, with meta/muse-spark-1.1, canonical provider docs, and standalone npm or ClawHub installation paths#103070 Thanks @vincentkoc.
  544. 544The bundled Meta provider now uses `https//api.meta.ai/v1`, advertises Muse Spark 1.1's documented 131,072-token output limit, and applies official-host request protections. #103680 Thanks @vincentkoc.
  545. 545Claude Fable 5 now works through Anthropic Vertex for simple-completion tasks such as generated conversation labels instead of failing before the request reaches Vertex#98932
  546. 546Claude CLI users can combine multiple --mcp-config files without losing servers or corrupting the prompt, and concurrent Gemini CLI runs are less likely to interfere with shared credential files#98983 Related #98944, #98945. Thanks @obviyus.
  547. 547Google image generation can now use `modelsGoogle image generation can now use models.providers.google.apiKey and an optional custom baseUrl without separate environment credentials or an auth profile. #100779 Thanks @amknight.
  548. 548OpenAI image generation can now be enabled from `modelsOpenAI image generation can now be enabled from models.providers.openai with a usable API key and custom base URL, without also requiring OPENAI_API_KEY or an auth profile. #100745 Thanks @amknight.
  549. 549Configurations using the retired openai-codex-responses API ID now receive a validation message naming the supported replacement instead of a generic failure#96257 Thanks @james-16, @yetval.
  550. 550Legacy openai-codex references now direct operators to openclaw doctor --fix and openclaw models status instead of suggesting configuration that fails validation#100120 Thanks @jason-vaughan, @sunnyshu0925, @vincentkoc.
  551. 551Ollama model discovery now stops oversized or never-ending endpoint responses before they can exhaust memory or leave setup hanging#96027 Thanks @alix-007.
  552. 552LM Studio model discovery and startup now stop pathological server responses at a fixed size and report a clear error instead of buffering them indefinitely#96042 Thanks @alix-007.
  553. 553openclaw models list now reports configured local Ollama models as available when they are running and usable#97491 Thanks @lingfeizi, @qingminglong.
  554. 554Custom Xiaomi MiMo and other OpenAI-compatible models without a known output limit can now complete chats instead of failing with an invented oversized cap#98312 Thanks @peole, @sanjays2402.
  555. 555Provider setup now stops reading runaway model-discovery responses before they can stall or exhaust memory, while normal self-hosted server responses continue to work#95244 Thanks @alix-007, @sallyom.
  556. 556Rerunning provider onboarding or refreshing models now preserves operator-owned timeouts, transport settings, MiniMax models, and SecretRef credentials instead of silently erasing them#100107 Thanks @frank-beans.
  557. 557With `modelsWith models.mode set to replace, agent startup now uses only explicitly configured providers and skips the slow implicit provider scan. #82638 Related #66957. Thanks @eldar702, @wangzhengshu.
  558. 558Bundled provider aliases now accept supported overlay settings such as request timeouts without demanding custom-provider fields like baseUrl and models#88400 Thanks @pluviobyte.
  559. 559Isolated cron jobs can now use models supplied by enabled bundled plugins without failing as unknown or silently resolving to the wrong provider#96070 Thanks @sallyom, @sunnyshu0925.
  560. 560ZZ.AI endpoint and model detection now fails gracefully on oversized or endless error responses instead of exhausting host memory. #97540 Thanks @alix-007.
  561. 561Microsoft Foundry connection tests now stop oversized or continuously streamed error responses while preserving concise setup diagnostics#97812 Thanks @pick-cat.
  562. 562Generic provider configurations for official DashScope/Qwen, Moonshot, ZGeneric provider configurations for official DashScope/Qwen, Moonshot, Z.AI, DeepSeek, Groq, Cerebras, and Chutes endpoints now retain the compatibility behavior those services require even without optional plugins. #100125
  563. 563Provider onboarding no longer writes an empty request block when no request overrides were supplied. 3a0a736 Thanks @vincentkoc
  564. 564Switching a live Control UI or TUI session through a provider-qualified model alias now saves the canonical provider and model, preventing the next request from being rejected#100209 Thanks @sahilsatralkar.
  565. 565Bedrock Mantle model discovery now times out and caps oversized catalog responses instead of hanging or consuming excessive memory, while cached models remain available#99961 Thanks @zhangguiping-xydt.
  566. 566OpenRouter video model discovery now stops oversized or runaway catalog responses promptly instead of letting them consume memory without limit, while normal discovery behavior is preserved#96505 Thanks @mushuiyu886.
  567. 567Model aliases and partial names such as opus now resolve to the newest matching version even when catalogs reach double-digit versions, preventing silent routing to an older model#96609 Thanks @yetval, @zw-xysk.
  568. 568Paginated provider catalogs now expose models beyond the first page, while malformed, endless, or redirected catalogs fail safely instead of caching an incomplete list or forwarding sensitive headers across origins#97012 Thanks @zhangguiping-xydt.
  569. 569Hugging Face model discovery now falls back to the bundled catalog when a provider response is malformed or oversized instead of risking excessive memory use#101079 Thanks @cxbasdev.
  570. 570Trusted official external providers can now show model-specific thinking choices before full runtime activation, including off, low, high, and max for Z.AI GLM 5.2. b4fce16 Thanks @vincentkoc
  571. 571Status summaries now respect provider-local model aliases, showing the selected alias without a false pinned-model mismatch warning. 1d4e789
  572. 572OpenRouter scans now interpret model names such as 8b-70b by their larger parameter size, improving minimum-size filters and small-model security warnings#96288 Thanks @ly-wang19.
  573. 573Media-generation catalogs now keep the correct default model marker even when provider metadata includes harmless surrounding whitespace#96430 Thanks @lin-hongkuan.
  574. 574Very long OpenRouter Fusion model IDs now remain valid Unicode in the agent prompt instead of showing a corrupted character when an emoji reaches the display limit#104433 Thanks @zhangguiping-xydt.
  575. 575Anthropic OAuth token exchange and refresh now reject oversized endpoint responses early instead of reading an unbounded body into memory#96644 Thanks @solodmd.
  576. 576Anthropic sign-in now rejects unsupported callback-host overrides, keeps authorization on standard local loopback addresses, and avoids callback failures or exposure through a non-local listener#96917 Thanks @xialonglee.
  577. 577Expired Claude CLI authentication now shows the exact recovery command claude auth login && openclaw models auth login --provider anthropic --method cli instead of a generic failure#97669 Thanks @alix-007.
  578. 578Anthropic OAuth subscription requests now carry the Claude Code-style billing identity, helping them use the intended subscription route instead of failing or being treated as the wrong request type. 709be93 Thanks @vincentkoc
  579. 579ChatGPT OAuth sign-in and refresh now reject unexpectedly large token responses cleanly instead of risking Gateway memory exhaustion#99479 Thanks @pandah97.
  580. 580Cloudflare 403 challenges on OpenAI or Codex OAuth requests now produce gateway-block guidance instead of incorrectly telling users their authentication failed#94440 Related #94432. Thanks @lzyyzznl, @pbm9z95m6z-hue.
  581. 581OpenAI authentication errors now point ChatGPT/Codex OAuth users to a model compatible with their existing sign-in instead of recommending an outdated default#100579 Thanks @zhangguiping-xydt.
  582. 582For Codex-backed OpenAI models, /status now identifies ChatGPT login authentication as oauth (codex-cli) instead of incorrectly labeling it as an environment API key#91240 Related #91099. Thanks @849261680, @ukstem.
  583. 583OpenAI Realtime voice in Talk, Voice Call, and Discord was announced with a Codex/OpenAI OAuth fallback inCorrection: public Codex OAuth accounts do not have a supported realtime transport, so current builds require an OpenAI Platform API key. Thanks @steipete-oai.
  584. 584Google Gemini CLI sign-in now rejects oversized OAuth, profile, project, and onboarding responses with labeled errors instead of risking excessive memory use#97587 Thanks @hugenshen.
  585. 585Google Gemini CLI OAuth failures now keep oversized or malformed provider responses bounded while preserving useful error details#99605 Thanks @mushuiyu886.
  586. 586Google OAuth sign-in, token exchange, and project discovery now return a bounded error for oversized responses instead of risking a process crash#97628 Thanks @vincentkoc, @wangmiao0668000666.
  587. 587GitHub Copilot sign-in, refresh, and model-list checks now fail with labeled size limits when GitHub or a proxy returns an oversized response#97499 Thanks @wangmiao0668000666.
  588. 588GitHub Copilot sign-in and token refresh now reject oversized service responses with a clear error before they can exhaust OpenClaw's memory#97579 Thanks @hugenshen.
  589. 589GitHub Copilot device login now fails cleanly on an oversized successful response instead of risking an out-of-memory crash#97583 Thanks @hugenshen.
  590. 590OpenAI-compatible providers routed through the GitHub Copilot BYOK harness now retain bearer authentication, reducing false 401 errors for valid credentials#99955 Thanks @hxy91819.
  591. 591xAI and Grok OAuth sign-in now works on SSH hosts, containers, VPS systems, and other headless environments without forwarding a localhost callback port#97249 Thanks @fuller-stack-dev, @jaaneek.
  592. 592xAI sign-in, token refresh, and device approval now stop oversized OAuth responses before they can consume unbounded memory#97615 Thanks @cxbasdev.
  593. 593Existing xAI and Grok OAuth sessions using the retired token endpoint can renew after expiry without forcing another browser or SSH-tunneled login#96146 Thanks @fuller-stack-dev, @jaaneek.
  594. 594Ollama Cloud setup now stops oversized or malicious authentication responses before they can consume excessive memory, while normal sign-in remains unchanged#97581 Thanks @hugenshen.
  595. 595MiniMax OAuth device setup now limits authorization response size so a faulty proxied or self-hosted endpoint cannot exhaust Gateway memory#96322 Thanks @lsr911.
  596. 596Chutes login, user lookup, and token refresh now stop unexpectedly large OAuth responses with a bounded error instead of buffering them without limit#96777 Thanks @wangmiao0668000666.
  597. 597Chutes onboarding now fails clearly when token-exchange or user-info responses are oversized, preventing abnormal authentication traffic from causing unbounded memory growth#96779 Thanks @wangmiao0668000666.
  598. 598ZZ.AI users can recover a profile that accidentally stored an onboarding command as the API key without wiping all authentication state. #97520 Thanks @zhangguiping-xydt.
  599. 599Chutes sign-in and token refresh errors now include a useful bounded snippet without allowing an endpoint to stream an unlimited response into memory#97808 Thanks @pick-cat.
  600. 600OpenRouter sign-in now fails safely on oversized replies, and Discord webhook sends remain successful when their optional response body is absent, malformed, or too large#98098 Thanks @lwy-2.
  601. 601OpenRouter model probes and agent requests now use discovered environment or profile API keys correctly instead of failing with a missing-authentication-header error#98187 Related #97934. Thanks @laurencebrown, @sunlit-deng.
  602. 602ClawRouter models selected in agent defaults now resolve at runtime when the credential is stored in an auth profile instead of the environment#99759
  603. 603Amazon Bedrock users can now analyze images and PDFs with the same AWS profile, role, SSO, environment, or instance credentials already used for chat#72092 Thanks @truffle-dev.
  604. 604OpenAI/Codex and Anthropic OAuth result pages now show OpenClaw branding instead of the legacy Pi logo. 1834592
  605. 605Agents created by copying credentials now preserve the source agent's portable provider-profile priority instead of unexpectedly choosing a different credential#100833 Thanks @machine3at.
  606. 606New or updated provider credentials entered through the CLI now appear in the running Gateway and Control UI model picker without a manual secrets reload or restart#101256 Thanks @fuller-stack-dev.
  607. 607OAuth-backed models now become available in Gateway model browsing after credentials are renewed from another CLI process, without requiring a Gateway restart#104732 Thanks @fuller-stack-dev.
  608. 608Anthropic conversations rejected for a missing tool result now tell users to retry or start a fresh session with /new instead of showing only a generic provider failure#98163 Thanks @masatohoshino.
  609. 609Claude native-thinking sessions can now recover automatically after Anthropic rejects a replayed thinking block, without manual compaction or transcript loss#98411 Related #98308. Thanks @clearhorizoninvestments, @sunlit-deng.
  610. 610Claude CLI agent runs now fail over instead of presenting provider errors or raw stream data as answers, preserve multilingual and emoji output, and stop runaway one-shot output before it exhausts Gateway memory#98942 Related #98896. Thanks @obviyus.
  611. 611Eligible direct API-key requests to Claude Fable 5 now return an Opus 4Eligible direct API-key requests to Claude Fable 5 now return an Opus 4.8 answer when Anthropic's safety classifier declines Fable, with diagnostics and Opus billing made clear. #99906
  612. 612Gemini streaming can retry with another configured API key after a retryable quota or rate-limit response instead of failing on the first key#97328 Thanks @monkeyleet.
  613. 613Ollama requests whose native response stream ends early can now continue to a configured fallback model instead of stopping with LLM request failed#100482 Thanks @turbotheturtle.
  614. 614A detail-less failure from an OpenAI-compatible provider no longer puts a valid API-key profile into cooldown or forces avoidable fallback traffic#100617 Thanks @fengjikui.
  615. 615ZZ.AI and similar HTTP 429 responses now distinguish temporary service overload from ordinary rate limiting and preserve provider-supplied retry timing. #98165 Thanks @sunnyshu0925.
  616. 616Continued conversations with strict custom OpenAI Responses-compatible endpoints no longer fail on an unsupported input[n].status field and needlessly switch to a fallback model#100831 Thanks @chenxiaoyu209.
  617. 617Replay-safe model timeouts can now advance to the next configured provider, letting agent, chat, and cron runs recover without repeating work that may have side effects#96142 Thanks @brokemac79, @riazrahaman.
  618. 618Agent runs can move to the next configured model after a provider drops a stream, while genuine cancellations still stop promptly#90908 Thanks @shengting.
  619. 619Embedded-agent runs can now try the next configured fallback model after a temporary upstream LLM request failed error#95542 Thanks @altaywtf, @mikasa0818.
  620. 620Configured fallback chains now try an alternate model when the primary provider reports model_not_found, reducing failures after model availability changes#97571 Thanks @liuhao1024.
  621. 621When a configured runtime model is no longer available, chat now explains that a new session will not help and directs operators to choose an available model#97611 Thanks @romneyda.
  622. 622Provider failures now keep fallback error text within the configured size limit, preventing oversized responses from overwhelming logs or visible diagnostics#99340 Thanks @pick-cat.
  623. 623/model default now actually returns an active session to its configured model after steering, fallback, or a previous manual selection#96318 Thanks @marsman-lab, @sunnyshu0925.
  624. 624Gateway chat now classifies mixed provider messages as rate limits when throttling is the real failure, giving users recovery guidance that matches the problem#100755 Thanks @pick-cat.
  625. 625openclaw status and session_status now identify when a session is using a fallback model and show the configured primary model beside it#101337 Thanks @lzy3538.
  626. 626Claude CLI replies that streamed successfully are now retained when the final success envelope contains no text, preventing the completed answer from disappearing or triggering an empty-response fallback#90450 Thanks @totobusnello.
  627. 627Claude Code 2Claude Code 2.1 users can again approve and run Bash, WebFetch, Grep, Glob, AskUserQuestion, and other native tools in claude-cli sessions. #98665 Related #95171. Thanks @carterdawson, @yetval.
  628. 628Claude CLI-backed agents now show native reasoning in /reasoning stream or /reasoning on, while /reasoning off consistently suppresses it for queued follow-ups too#99401 Thanks @marvinthebored.
  629. 629Anthropic Opus 4Anthropic Opus 4.8 can now run with tools.profile=coding without every turn failing with an HTTP 400 schema error before the assistant replies. #100492 Thanks @lin-hongkuan, @vincentkoc.
  630. 630Anthropic Messages-compatible proxy users no longer see raw antml tool-call XML or arguments leak into visible Claude replies. b2787a1 Thanks @jerry-xin
  631. 631Anthropic agents routed through AWS Bedrock can keep Feishu Bitable write tools enabled without the tool definitions blocking every conversation#94990 Thanks @twinslee, @vincentkoc.
  632. 632Claude Fable 5 now uses the expected Anthropic context1m stream setup when 1M context is enabled, without affecting similar model IDs#100572 Thanks @zhangguiping-xydt.
  633. 633Claude conversations through GitHub Copilot can continue after a tool failure with no visible output instead of entering repeated provider-schema failures#101373 Thanks @galiniliev.
  634. 634Anthropic-compatible calls with token caps too small for manual thinking now run normally without thinking instead of failing provider validation#101415 Thanks @pick-cat.
  635. 635Ollama Cloud and other OpenAI-compatible Ollama chats can now continue after a tool call instead of failing the next turn with a provider 400 error#96474 Thanks @849261680.
  636. 636vLLM, Ollama proxies, and other OpenAI-compatible gateways can deliver streamed replies even when they incorrectly label an event stream as JSON, avoiding an early parsing failure that previously ended the agent run#96503 Thanks @zengwen-dt.
  637. 637GPT-5GPT-5.5 and other models can send valid streaming events larger than 64 KiB through ChatGPT Responses without failing the request, while malformed unbounded streams remain limited. #98198 Thanks @marvinthebored, @obviyus, @peetiegonzalez.
  638. 638openclaw agent --local now reports a clear first-event timeout when a provider opens a stream but never sends usable output instead of appearing to hang indefinitely#98525 Thanks @osolmaz.
  639. 639MCP tools that expect arrays or objects can now accept those values when Xiaomi MiMo, Ollama, or another affected provider returns them as JSON strings, avoiding a pre-execution validation failure#96922 Thanks @liuhao1024.
  640. 640Repaired plain-text tool calls from LM Studio, xAI, and Ollama now emit a final completion event so plugins and other streaming consumers can finish them reliably#104714
  641. 641Google Live voice sessions can now register and call OpenClaw tools instead of rejecting their declarations before a tool-backed turn begins#100260
  642. 642MiniMax M3 replies, including those routed through Fireworks, no longer expose hidden mm: reasoning in visible chat or progress output#93767 Thanks @drhack1, @vincentkoc.
  643. 643Long opencode-go model runs are less likely to be falsely stopped as stalled while valid provider events are still arriving#97128 Thanks @liuwqgit, @vincentkoc, @yetval.
  644. 644OpenRouter's DeepSeek V4 Flash and Pro models can answer with thinking enabled without failing with an HTTP 400#97208 Related #97196. Thanks @nianjiuzst, @patelmm79.
  645. 645Direct mistral-medium-3-5 requests now send the user-selected adjustable reasoning level to Mistral as reasoningEffort#100688 Thanks @aniruddhaadak80, @wm0018.
  646. 646Realtime voice sessions now omit an individual custom tool with an invalid provider-specific name and warn about it instead of letting that tool break the entire OpenAI, Azure, or Google session#89175 Thanks @vincentkoc.
  647. 647Switching from thinking-off mode to a reasoning-required model now selects its lowest supported effort rather than silently choosing the most expensive level#93335 Thanks @obuchowski.
  648. 648OpenAI Realtime voice and transcription sessions now start behind Clash, Surge, sing-box, and similar TUN proxy setups that resolve api.openai.com into fake-IP ranges#86526 Thanks @shushushv.
  649. 649OpenAI and Azure realtime voice connections now close inbound messages above 16 MiB, limiting avoidable gateway memory pressure#99450 Thanks @sunlit-deng.
  650. 650OpenAI realtime voice sessions now default to `gpt-realtime-2OpenAI realtime voice sessions now default to gpt-realtime-2.1 when no model is specified, while explicit model pins continue to work. #101390 Thanks @vincentkoc.
  651. 651OpenAI image generation and reference-image editing no longer crash when credentials or a custom base URL are ready before the provider model catalog finishes loading#105518 Thanks @vincentkoc.
  652. 652OpenAI video generation now stops oversized or endless submission responses with a bounded provider error before they can hang the request or exhaust memory#96905 Thanks @alix-007.
  653. 653Gemini CLI media analysis now returns its description even when the valid response also contains nested usage or other metadata#96432 Thanks @lin-hongkuan.
  654. 654Google Veo video generation now ends oversized create or status responses early with a clear bounded error, preventing a broken endpoint from hanging OpenClaw or consuming memory indefinitely#96605 Thanks @alix-007.
  655. 655Reference-image edits through Fal-hosted Grok Imagine and Nano Banana 2 Lite now reach the correct service, while mixed-model fallbacks honor each candidate's supported resolution and reference limits#98688 Thanks @davenicoll, @vincentkoc.
  656. 656MiniMax TTS now accurately explains that volume must be greater than 0 and may be as high as 10 when a directive is invalid#101359 Thanks @quratulain-bilal.
  657. 657MiniMax VLM and native PDF provider errors now remain readable when emoji or other supplementary characters land at the diagnostic snippet limit#101728 Thanks @wings1029.
  658. 658MiniMax video generation now rejects oversized task, status, or file-metadata responses before unbounded memory use or binary download begins, while normal responses continue to work#96889 Thanks @alix-007.
  659. 659xAI video generation now stops oversized create or status responses with a clear size-limit error instead of buffering until OpenClaw hangs or consumes excessive memory#96903 Thanks @alix-007, @vincentkoc.
  660. 660MiniMax image understanding now stops oversized or malformed successful responses at a bounded limit, protecting memory while returning a useful diagnostic#100694 Thanks @zhangguiping-xydt.
  661. 661Moonshot video understanding now returns a predictable error for oversized or malformed responses instead of hanging or consuming memory indefinitely, including with custom base URLs#96502 Thanks @hugenshen.
  662. 662Qwen video understanding now stops oversized or malformed endpoint responses with a clear error instead of hanging or reading without limit, while normal descriptions continue unchanged#96604 Thanks @alix-007.
  663. 663BytePlus video generation now stops oversized task-submission or status responses with a clear error before they can stall OpenClaw or exhaust memory, while normal responses continue unchanged#96606 Thanks @alix-007.
  664. 664DashScope-compatible video submission and polling now reject oversized JSON responses with a bounded error instead of risking memory pressure or process instability, while ordinary responses continue normally#96782 Thanks @wangmiao0668000666.
  665. 665OpenRouter video generation now rejects oversized submit and polling responses before they can hang OpenClaw or consume runaway memory, while normal-sized malformed responses retain their established error handling#96873 Thanks @alix-007.
  666. 666Vydra image, video, and speech generation now fails with a bounded error on oversized or endless control responses instead of hanging or exhausting memory, while valid responses continue normally#96875 Thanks @alix-007.
  667. 667fal music and video generation now stops oversized successful responses with a clear size-limit error before they can hang or exhaust memory, while normal generation continues as before#96886 Thanks @alix-007.
  668. 668Together and PixVerse video generation now returns a provider-labelled size error for oversized successful responses instead of continuing until severe memory pressure or process failure#96904 Thanks @alix-007.
  669. 669Runway video generation now stops oversized create and status responses instead of continuing to consume memory or stall, while normal polling and provider-specific errors remain intact#96907 Thanks @alix-007.
  670. 670Comfy image-generation workflows now stop oversized ComfyUI responses with the actual size-limit error instead of risking memory exhaustion or misreporting the response as malformed JSON#96927 Thanks @wangmiao0668000666.
  671. 671DeepInfra video generation now rejects oversized successful responses with a bounded error instead of risking an out-of-memory crash#97486 Thanks @hugenshen.
  672. 672Configured Voice Call transcription providers such as xAI remain selectable when another provider registry is active, allowing Talk sessions to start normally#97170 Thanks @solavrc.
  673. 673Missing official media providers now produce errors with the exact recovery commands needed to restore transcription and other media workflows#97484 Thanks @wangmiao0668000666.
  674. 674A malformed Inworld voices response now produces a clear provider-specific error instead of an unhelpful parsing exception or process crash#98660 Thanks @solodmd.
  675. 675Short non-English audio now keeps the configured language hint without an unrelated English prompt, reducing accidental translation when users expect a transcript in the spoken language#99023 Thanks @flyveryhigh, @nianjiuzst.
  676. 676Image and video tools can now automatically select configured provider-plugin models authenticated through environment variables#98623 Thanks @medns.
  677. 677Automatically configured video understanding now uses provider defaults such as Moonshot's intended video model unless the user selected a model explicitly#99791 Thanks @vincentkoc, @zhangguiping-xydt.
  678. 678Image generation now stops with a clear size-limit error when a provider or custom endpoint sends an oversized or endless response, preventing hangs and runaway memory use while valid images and edits continue normally#96495 Thanks @hugenshen, @sallyom.
  679. 679Google Gemini TTS now rejects oversized responses before buffering them into memory, while normal speech results continue through the existing audio workflow#96984 Thanks @mushuiyu886.
  680. 680Inworld text-to-speech and voice-list requests now fail safely on oversized, malformed, or never-ending responses instead of hanging or consuming unbounded Gateway memory#95416 Thanks @alix-007, @vincentkoc.
  681. 681Azure Speech, Microsoft Speech, ElevenLabs, MiniMax TTS, OpenRouter transcription, and xAI transcription now stop oversized or endless responses before they can stall speech work or strain Gateway memory, while ordinary responses remain unchanged#96496 Thanks @hugenshen.
  682. 682Volcengine, BytePlus Seed Speech, and Xiaomi TTS now stop oversized provider responses before one speech request can stall or destabilize OpenClaw#96874 Thanks @alix-007.
  683. 683Google audio and video understanding now stops oversized provider responses at the shared 16 MiB limit with a clear error instead of allowing them to consume excessive memory#96920 Thanks @mushuiyu886, @vincentkoc.
  684. 684Gemini memory-embedding batch uploads, creation, and status checks now fail safely when a compatible endpoint returns an oversized control response#97535 Thanks @hugenshen.
  685. 685OpenAI-compatible embedding requests now close oversized responses early with a clear provider error instead of buffering until OpenClaw stalls or runs out of memory, while normal embeddings continue working#96868 Thanks @alix-007.
  686. 686OpenAI embedding batch polling and Realtime setup now cancel oversized successful responses early and return a bounded error instead of growing memory without limit#97533 Thanks @hugenshen.
  687. 687OpenAI-compatible embedding batch downloads now process valid large outputs while stopping oversized files or JSONL records before they can exhaust memory#98554 Thanks @sunlit-deng, @vincentkoc.
  688. 688GitHub Copilot model discovery and memory search now reject oversized or malformed responses instead of buffering them without limit, while valid catalog and embedding results continue normally#96499 Thanks @hugenshen, @sallyom.
  689. 689Voyage embedding batch jobs now stop oversized status, failure, and error-file responses before they can hang or exhaust worker memory, while oversized diagnostics degrade safely and ordinary responses remain unchanged#96608 Thanks @alix-007.
  690. 690LM Studio embedding preload now respects the configured context limit, reducing GPU out-of-memory failures during memory search on constrained hardware#100750 Thanks @hxz398, @zak-li, @zoowh.
  691. 691Malformed Voyage embedding batches now close their download connections after parsing fails, reducing resource buildup during repeated or large workloads#98840 Thanks @solodmd.
  692. 692Google Meet document processing now rejects oversized Google Drive exports before they can destabilize OpenClaw, while ordinary documents still export as text#97620 Thanks @alix-007, @vincentkoc.
  693. 693Parallel web search now returns a bounded error when an upstream response is malformed, oversized, or never-ending instead of risking a hang or out-of-memory crash#96035 Thanks @alix-007.
  694. 694Exa searches now reject responses above the supported limit, preventing excessive provider output from hanging OpenClaw or creating memory pressure#96038 Thanks @alix-007.
  695. 695Anthropic-compatible requests now fail promptly with a bounded transport error when an upstream stream sends an oversized partial event instead of hanging and consuming memory#100686 Thanks @zhangguiping-xydt.
  696. 696OpenAI ChatGPT Responses streaming now cancels oversized or endless provider bodies with a clear error before they can consume excessive process memory, while normal responses keep using the existing parser#96762 Thanks @vincentkoc, @wangmiao0668000666.
  697. 697OpenAI-compatible provider and proxy streams now stop oversized malformed or never-ending bodies at the affected request instead of letting them destabilize or crash the OpenClaw process#96989 Thanks @vincentkoc, @wangmiao0668000666.
  698. 698OpenAI-compatible Chat Completions now use OpenClaw's guarded network path, adding the same response safety controls used by other protected model calls#97228 Thanks @vincentkoc, @wangmiao0668000666.
  699. 699Azure OpenAI Responses now bound oversized streaming and error bodies, protecting memory while preserving normal errors and cancellation#97349 Thanks @wangmiao0668000666.
  700. 700Anthropic-compatible model requests now consistently use OpenClaw's guarded transport, response normalization, and managed stream cleanup rather than bypassing them through the SDK#101357 Thanks @wangmiao0668000666.
  701. 701When an OpenAI or OpenAI-compatible chat-completions model refuses a request, users now see the provider's explanation instead of a blank assistant reply#102344 Thanks @wuqxuan, @yetval.
  702. 702Proxy-backed model streams now fail with bounded, clearer errors when responses are oversized, malformed, incomplete, or idle instead of hanging or consuming unbounded data#97235 Thanks @vincentkoc, @zhangguiping-xydt.
  703. 703Mistral-compatible endpoints now stop oversized streaming responses with a labeled error before OpenClaw can run out of memory#97648 Thanks @wangmiao0668000666.
  704. 704Abnormally large Google Meet, Calendar, or OAuth responses now stop with an error before they can consume uncontrolled Gateway memory#98850 Thanks @pandah97.
  705. 705Request-format and schema failures now show the relevant diagnostic without sending users through unnecessary provider login or reconfiguration steps#95779 Thanks @pick-cat.
  706. 706Codex users can route both codex/* and openai/* models through the bundled runtime, and older conversations resume without unnecessary context reprojection#105034
  707. 707The bundled Codex plugin can complete backend requests again after updating its managed app-server runtime, with no model-picker or configuration migration required#106098
  708. 708OpenClaw's managed Codex workflow now uses app-server 0OpenClaw's managed Codex workflow now uses app-server 0.143.0, and self-managed installations must use 0.143.0 or newer for protocol compatibility. 366258d Thanks @vincentkoc.
  709. 709The managed Codex harness now surfaces supported GPT-5The managed Codex harness now surfaces supported GPT-5.6 Sol, Terra, and Luna models returned by the account catalog and gives self-managed users current version guidance. f80ce21 Thanks @vincentkoc.
  710. 710Managed Codex users on macOS, Linux, and Windows now receive app-server 0Managed Codex users on macOS, Linux, and Windows now receive app-server 0.144.1 instead of 0.144.0. 5dcba9f Thanks @vincentkoc.
  711. 711Codex-native delegation from OpenClaw threads now creates native task records again, while unsupported custom Codex app-server versions fail startup with a clear minimum-version error#101221
  712. 712Codex sessions using `gpt-5Codex sessions using gpt-5.5-pro or gpt-5.4-pro now clamp unsupported reasoning levels before the first turn, avoiding an immediate request rejection when live metadata is unavailable. #101484 Thanks @zhangguiping-xydt.
  713. 713Scheduled and CLI Codex runs with an explicit timeout longer than 30 minutes can now use that full budget instead of being stopped by the terminal-idle guard#85296 Thanks @alkor2000, @vincentkoc.
  714. 714A missing or hung local Codex tool result no longer switches the active session to another provider that cannot resolve the local failure#95543 Thanks @mikasa0818.
  715. 715Codex app-server runs with an invalid ChatGPT OAuth session now surface the real sign-in error promptly instead of waiting for a misleading ten-second authentication timeout#100713 Thanks @lin-hongkuan.
  716. 716Codex runs stopped by the guardian rejection limit now say why they ended, so operators do not have to mistake the result for a crash, cancellation, or generic interruption#101220 Thanks @darren2030.
  717. 717Crestodian setup and repair chats on Codex-backed runs can now access the status and repair tool they need instead of stopping with a missing-tool response#101281
  718. 718Shared Codex app-server clients now keep usage limits, auth cooldowns, thread subscriptions, and resumed connections tied to the account and conversation that actually owns them#101376
  719. 719Codex app-server stdout failures now end affected requests cleanly, while a diagnostics-only stderr failure no longer interrupts an otherwise healthy turn#101505 Thanks @mushuiyu886, @vincentkoc.
  720. 720Anthropic usage checks now cap unusually large error responses so a CDN, firewall, or proxy page cannot exhaust OpenClaw's memory#97614 Thanks @cxbasdev.
  721. 721OpenAI and Codex users authenticated through the app server can again see their five-hour and weekly quota windows in chat, CLI, and JSON status output#92520 Thanks @brokemac79.
  722. 722OpenAI OAuth usage checks now cap oversized WHAM rate-limit responses before they can destabilize the process#97702 Thanks @cxbasdev.
  723. 723GitHub Copilot usage checks now contain oversized or endless endpoint responses as a usage error instead of buffering them indefinitely, while normal usage data still loads#96607 Thanks @alix-007.
  724. 724OpenRouter cost tracking now caps unexpectedly large metadata responses and keeps the original streamed estimate instead of disrupting the agent turn#97490 Thanks @hugenshen.
  725. 725MiniMax and other shared provider usage checks now fail safely on oversized or malformed replies instead of buffering them without limit#97659 Thanks @cxbasdev, @vincentkoc.
  726. 726OpenRouter completions that the provider bills at $0 now stay recorded as free in transcripts, summaries, logs, and usage totals instead of being replaced with estimated catalog pricing#101177
  727. 727Amazon Bedrock adaptive-thinking Claude and Fable runs now honor configured high output-token limits for longer answers, reasoning, and tool calls#97343 Thanks @lilan0125, @prasithg.
  728. 728Long, tool-heavy or media-heavy embedded-agent conversations now retain more prompt-cache reuse between turns, reducing repeated token processing, latency, and cost on prefix-cached providers#102610 Thanks @ugiezzz.
  729. 729Nemotron 3 Super now exposes its full 1,048,576-token context budget in OpenClaw's bundled NVIDIA fallback catalog instead of compacting at the stale 262,144-token limit#98726 Thanks @eleqtrizit.
  730. 730ChatGPT OAuth-backed Responses sessions now retain backend affinity across turns, improving prompt-cache reuse and reducing repeated processing of the same conversation context#100233 Thanks @marvinthebored, @obviyus, @peetiegonzalez.
  731. 731After /model changes a session's provider, /status and session_status now report that provider's usage, authentication, runtime, and context details rather than stale defaults#93384 Thanks @obviyus, @osolmaz, @rollingshmily, @samiralibabic, @zhangguiping-xydt.
  732. 732Model-call traces now include prompt-size and per-call token usage details, helping operators investigate cost and prompt growth without capturing raw content#95770 Thanks @amknight.
  733. 733The diagnostics timeline now shows when provider model calls ran, how long they took, and whether they succeeded without recording prompt or response content. 7253552 Thanks @vincentkoc
  734. 734QMD search and vsearch modes now skip the LLM reranker, reducing latency and avoiding unnecessary GPU failures while full query mode keeps reranking#88887 Thanks @potterdigital.
  735. 735Memory-wiki pages titled Index now remain stored, searchable, and retrievable instead of being hidden or overwritten by generated directory pages#94326 Thanks @vincentkoc, @yetval.
  736. 736Active Memory now warns when recalled operational details may be outdated and clearly marks clipped summaries, so old or incomplete status is less likely to look current#95888 Thanks @spencer2211.
  737. 737Memory-wiki pages in subfolders now appear in search, lookup, compiled indexes, digests, and vault counts just like pages at the top level#96022 Thanks @machine3at, @vincentkoc.
  738. 738Large memory indexes can now return filtered matches beyond sqlite-vec's first 4,096 candidates without failing or silently missing valid results#96157 Thanks @itsuzef, @vincentkoc.
  739. 739Repeated QMD-backed memory_search and openclaw memory search requests can return faster after the first lookup, while diagnostics separate setup time from search time and missing collections still trigger repair#96655 Thanks @bek91.
  740. 740Memory search now works with installed generic embedding plugins such as local llama.cpp, including their default model and connection details#97095 Thanks @849261680.
  741. 741One memory-wiki page with broken YAML no longer blocks healthy pages from being searched, compiled, linted, counted, or updated#97177 Related #96125. Thanks @cow11023, @sunnyshu0925.
  742. 742Memory Wiki now marks claims with malformed explicit freshness timestamps as unknown instead of masking the bad metadata with the page date#97465 Thanks @ly-wang19.
  743. 743Detailed /status plugins now warns when a configured memory embedding provider is unavailable and semantic recall has fallen back to keyword search#97968 Thanks @masatohoshino.
  744. 744QMD memory recall now turns malformed or warning-filled mcporter output into a clear, filtered error instead of exposing raw subprocess text#98381 Thanks @miorbnli.
  745. 745memory_get with corpus=all can now return an available wiki supplement when the requested memory file is missing instead of stopping with an empty result#100904 Thanks @mushuiyu886, @vincentkoc.
  746. 746With `memorySearch.providerNone`, OpenClaw now starts FTS-only memory without an unnecessary plugin capability scan. fbf574a
  747. 747Interactive QMD memory searches with no matches now return an empty result promptly instead of appearing stuck during unnecessary index maintenance#90030 Related #90023. Thanks @ruben2000de, @sahibzada-allahyar.
  748. 748openclaw doctor --fix can now carry legacy Memory Core indexes from 2026Openclaw doctor --fix can now carry legacy Memory Core indexes from 2026.6.9 upgrades into the current store without forcing a full re-embed. #95631 Thanks @mushuiyu886, @vincentkoc.
  749. 749openclaw memory status now warns when session transcripts still need indexing instead of incorrectly reporting memory as current#97857 Related #97814. Thanks @che10x, @zw-xysk.
  750. 750Memory Core now preserves short standalone concepts such as kv and s3 in tags, improving recall without matching them inside unrelated words#96304 Thanks @ly-wang19.
  751. 751Memory-wiki bridge status now returns a usable warning instead of crashing on malformed plugin artifacts, and readMemoryArtifacts: false now reliably prevents those reads#100900 Thanks @huveewomg.
  752. 752Wiki search and retrieval now explain when an older or partial memory plugin lacks shared-search support and offer a practical workaround instead of exposing a raw TypeError#100902 Thanks @huveewomg, @vincentkoc, @xuanmingguo.
  753. 753Memories containing emoji or supplementary CJK characters can now be indexed without malformed text stalling the operation#101574 Thanks @jensenwang560-blip.
  754. 754When both a primary memory read and its wiki supplement fail, memory_get corpus=all now returns the original structured read error instead of crashing the tool call#101902 Thanks @aniruddhaadak80, @vincentkoc, @zw-xysk.
  755. 755Memory-index debug logs now show whether an embedding batch completed or failed, making indexing problems easier to trace#94732 Thanks @doubleji817-lang, @xydt-tanshanshan.
  756. 756openclaw memory status --fix now repairs session-corpus state without mistaking healthy daily-memory records for stale data#93389 Thanks @alix-007, @vincentkoc.
  757. 757openclaw memory status no longer shows impossible session indexing totals where the indexed file count exceeds the total file count#95452 Thanks @buyitsydney, @liuhao1024.
  758. 758Durable memory promotion now keeps OpenClaw's managed dreaming markers and adjacent managed content out of MEMORY.md when a recalled range touches a block boundary#83718 Thanks @grifjef.
  759. 759Inferred follow-up commitments now return to the queue after temporary model or network extraction failures, reducing missed reminders without duplicate processing#89817 Thanks @masatohoshino.
  760. 760Memory-core light dreaming no longer repeats an unchanged work-summary block in DREAMS.md, while genuine daily-note updates can still appear later#97446 Thanks @aaajiao, @qingminglong.
  761. 761Memory Wiki lint now ignores link-looking text inside inline and fenced code while continuing to report genuine broken links in prose#98095 Thanks @durambar, @vincentkoc, @zhangqueping.
  762. 762Memory-wiki source updates now preserve hand-written Notes when a temporary read failure prevents OpenClaw from safely loading the existing page#98360 Related #98345. Thanks @qingminglong, @vincentkoc, @yetval.
  763. 763Memory-wiki source sync can now recover when a page is missing or collides with a non-file, while preserving existing content when a retry remains unsafe#99276 Thanks @obviyus.
  764. 764Memory Wiki imports now continue when a source page collides with a protected vault entry instead of stopping the whole import. 76db9a3 Thanks @vincentkoc
  765. 765Newly promoted long-term memories now omit raw transcript, summary, session-header, flush-prompt, and scoring clutter so useful notes are easier to find#94636 Thanks @josephur, @pinghe-learn, @tayoun.
  766. 766Dreaming now keeps deleted or reset transcript archives and cron-created child conversations out of its learned session set, reducing duplicate history and automation noise without removing retained archives from historical search#96517 Thanks @adam-researchh, @jalehman, @xialonglee.
  767. 767Memory Wiki import summaries now shorten ChatGPT text containing emoji without leaving corrupted replacement characters#97362 Thanks @mushuiyu886.
  768. 768Rerunning memory-wiki synthesis or ChatGPT imports no longer risks erasing handwritten notes, frontmatter, or import state when an existing page cannot be read briefly#98787 Thanks @vincentkoc, @yetval.
  769. 769Memory dreaming now records structured success or failure outcomes for light, REM, and deep phases so dashboards and health checks can monitor them reliably#97723 Thanks @lg320531124, @momothemage.
  770. 770openclaw wiki lint now ignores wikilink-like patterns inside code examples so real broken Memory Wiki links are easier to spot#97954 Thanks @durambar, @liuhao1024, @vincentkoc.
  771. 771openclaw wiki lint now recognizes valid imported Obsidian links by title, slug, fragment-free path, or source-path suffix, reducing false broken-link warnings#100017 Thanks @ishangodawatta, @k-kerrigan, @vincentkoc.
  772. 772Archived memories around user messages that begin with `cron]` remain searchable after a session reset or deletion, while genuine cron-generated archives stay hidden. #101322 Thanks @ly-wang19.
  773. 773After /new or /reset, the previous conversation remains available for daily memory summaries and full-history searches through the session-logs skill#71537 Thanks @injinj.
  774. 774A group chat or Gateway session can now resume on the next visible request after a failed, timed-out, or killed turn without requiring /new or manual session-file edits#89045 Thanks @jerry-xin.
  775. 775Aborted or timed-out embedded runs now release their session write lock, so the next message can proceed without minutes of waiting or manual file cleanup#96100 Thanks @richwilson-bloom, @sallyom, @xialonglee.
  776. 776Replies that span an automatic daily or idle reset now remain together in one accessible transcript instead of losing later output#97164 Thanks @joshavant, @yetval.
  777. 777Resuming work from a project now opens only that project's saved agent session, preventing unrelated transcripts from being mixed together#97785 Related #96542. Thanks @qingminglong, @yetval.
  778. 778Recurring provider-CLI cron jobs and local openclaw agent runs now keep their existing provider conversation across the daily reset boundary instead of silently losing context#98356 Thanks @yetval.
  779. 779Discord, WebChat, and other ongoing conversations can keep receiving replies when background activity touches the same session during reply startup, without a false initialization conflict or dropped message#98835 Related #98672. Thanks @aaronfaby, @jalehman, @moguangyu5-design.
  780. 780Resetting a multi-agent room now restores message delivery promptly instead of blocking most agents' acknowledgement and queued replies for several minutes#99091 Thanks @gorkem2020, @zengwen-dt.
  781. 781Rapid follow-ups in the same chat no longer freeze both messages while the first automatic reply is finishing#99549 Thanks @shagrat2.
  782. 782Claude CLI-backed interactive replies now keep their saved session more consistently, preserving continuity and reducing repeated full-history replay#99595 Related #99372. Thanks @obviyus.
  783. 783CLI-backed agents in multi-person group chats now retain conversational context when participants alternate, without expanding non-owner tool permissions#99640 Related #99633. Thanks @obviyus.
  784. 784CLI-backed group agents now keep one warm conversation across mentioned and unmentioned follow-ups instead of resetting and losing context#99722 Related #99696. Thanks @obviyus.
  785. 785CLI-backed agents now keep conversation continuity across prompt-only changes, avoiding needless cold starts while still resetting when security or runtime conditions require it#99822 Related #99729. Thanks @obviyus.
  786. 786Temporary memory-maintenance failures no longer replace the agent reply, and persistently oversized sessions can recover in a fresh session while preserving the previous transcript#100618 Thanks @jerry-xin, @rhclaw.
  787. 787A first command-only interaction in an auto-reply flow now keeps its session update even when no session row existed beforehand. 76d686c
  788. 788Sessions renamed with /name now keep that custom name in session lists instead of reverting to an automatic title or UUID-like label#98841 Related #98742. Thanks @bsg2000, @sunnyshu0925.
  789. 789A successfully completed main-agent conversation now continues in the same session on the next message instead of unexpectedly resetting and archiving its transcript#99985 Thanks @sunnyshu0925.
  790. 790Dashboard session labels and display names now remain attached when a session rolls over after a day or idle period#101576 Thanks @merlin-zhou, @zengwen-dt.
  791. 791Claude CLI conversations that exhaust their context now recover into a fresh reseeded session automatically, and timeout retries retain the temporary files they need to complete#98934 Related #98897. Thanks @obviyus.
  792. 792Local Ollama-backed CLI agent turns can now continue when the context engine reports an already-compacted transcript, allowing the assistant or MCP tool result to reach the user#99136 Thanks @mushuiyu886, @peterskwang, @pkoserowski, @psedd.
  793. 793Existing Codex sessions can resume their bound threads more reliably after upgrades, resets, and compaction without depending on leftover transcript-side JSON files#101210
  794. 794A Codex reply delivered through `sourceReplyDeliveryMode"message_tool_only"` now completes its turn promptly instead of later ending as an incomplete reply. #95942 Thanks @omarshahine.
  795. 795Codex app-server installations using the retired on-failure approval policy now upgrade to the supported on-request behavior without losing saved bindings. 70153f7 Thanks @vincentkoc
  796. 796Existing Codex app-server conversations with dynamic tools can resume through the tool-fingerprint format upgrade instead of starting an avoidable replacement thread. 3051748 Thanks @vincentkoc
  797. 797Legacy Codex bindings with large tool or MCP configurations can now migrate without overflowing plugin-state records or copying raw configuration secrets. 23228b6 Thanks @vincentkoc
  798. 798Upgraded Codex installations can now finish legacy binding migration and archive old sidecars instead of repeatedly retaining them after an earlier partial import. 39fac06 Thanks @vincentkoc
  799. 799Codex sessions created in beta 5 can keep their existing conversation after upgrade when the user MCP configuration is unchanged, without retaining its authorization token. 272750d Thanks @vincentkoc
  800. 800Provider-owned CLI conversations now keep the same session and transcript across the daily default reset boundary unless an explicit reset policy or /reset applies#97931 Thanks @yetval.
  801. 801New Codex-backed threads now preserve configured plugin apps, can activate remote curated plugins, and run Guardian on the first eligible native OpenAI turn#98042 Thanks @kevinslin.
  802. 802A stuck Claude CLI startup now fails only the affected turn instead of exiting the Gateway, and heartbeat activity no longer causes the next user turn to lose its CLI conversation history#98933 Related #98894, #98895. Thanks @obviyus.
  803. 803Claude CLI agent runs now fail clearly when messaging tools are unavailable, recover when Claude exits without a result, retain more long-session continuity, and clean up prompt images and failed preparation files#99159 Related #98946. Thanks @obviyus.
  804. 804The same-release Codex session-continuity work now covers app-server thread start and resume, with binding fingerprints kept bounded throughout. 78edf1c Thanks @vincentkoc
  805. 805Shared group and channel transcripts now retain the sender ID, display name, and username for each durable user turn, making later history and memory processing correctly attribute participants#90552 Thanks @pick-cat.
  806. 806/export-session now warns when a CLI- or ACP-backed export contains only user messages and points users to the backend transcript for missing assistant, tool, usage, and cost details#90867 Thanks @tank-x3, @vincentkoc, @xydigit-sj.
  807. 807openclaw export-trajectory and /export-trajectory now include redacted messages from older version 1 sessions instead of producing a successful but empty transcript#93814 Thanks @yetval.
  808. 808Session-memory files created around /new and /reset now keep one copy of each assistant reply instead of duplicating reasoning-model responses#94401 Thanks @sallyom, @sunnyshu0925.
  809. 809Compacted agent history now lists genuine tool failures instead of repeatedly mislabeling successful subagent launches, including when older transcript records contain the incorrect error flag#96842 Thanks @nxmxbbd.
  810. 810Invalid transcript entries now raise a visible write error instead of becoming undefined JSONL lines that silently vanish after reload#97356 Thanks @miorbnli.
  811. 811openclaw sessions cleanup --fix-missing now preserves fresh cron sessions with valid transcripts and clearly reports repaired entries#97495 Thanks @qingminglong.
  812. 812Automatic recovery from provider role-ordering conflicts now archives the complete prior transcript as a timestamped JSONL file before replaying a shorter tail#97544 Thanks @yungchentang.
  813. 813Compacted group conversations now retain identical long messages from different participants while still removing accidental duplicate retries from the same sender#98336 Thanks @sunnyshu0925, @yetval.
  814. 814Transcript summary and import reads now close files reliably after malformed data, preventing long-running processes from gradually exhausting file handles#98493 Related #98467. Thanks @wangmiao0668000666, @zhanglei99586.
  815. 815Older or imported sessions with plain-string assistant messages now replay correctly across provider and streaming paths instead of sending malformed conversation history#98908 Thanks @obviyus.
  816. 816Claude CLI chat history reloads no longer display OpenClaw's internal reseed wrapper as if it were a message the user typed#99653 Related #99646. Thanks @harjothkhara, @jeehut, @vincentkoc, @zoowh.
  817. 817Transcript-backed history now treats a missing file as empty while reporting real access, directory, or stream failures cleanly instead of leaving partial or unhandled results#100524 Thanks @cxbasdev, @zhanglei99586.
  818. 818Transient transcript read failures no longer destabilize session-log diagnostics or let an incomplete usage scan overwrite the last complete cost cache as though it were current#101062 Thanks @cxbasdev, @vincentkoc.
  819. 819Malformed transcript rows now produce an aggregate warning with skipped and loaded counts while the remaining usable session history continues to load#98669 Thanks @cxbasdev.
  820. 820Transcript tools can now identify channel delivery mirrors as OpenClaw bookkeeping rather than mistaking them for OpenAI Responses output#99855 Thanks @vincentkoc.
  821. 821Debug-proxy ACP runs now shut down cleanly, mark capture sessions finished, and close their capture databases without reporting a spurious database error#100827 Thanks @amknight.
  822. 822openclaw sessions tail now rejects oversized trajectory snapshots and updates with a clear limit error before they can exhaust memory#101450 Thanks @cxbasdev, @vincentkoc.
  823. 823Long usage and session log messages now truncate emoji cleanly instead of displaying malformed character artifacts#101517 Thanks @maweibin.
  824. 824Reopened sessions can now replay older string or single-object tool results correctly instead of treating successful output as empty or failing on its stored shape#98891 Related #98825. Thanks @obviyus.
  825. 825Agents in long-running WebChat, Discord, and other direct sessions can keep reading fresh command, file, browser, and status output instead of seeing it disappear or turn into an image placeholder#98955 Related #98874. Thanks @lamkan0210, @momothemage.
  826. 826Imported Claude CLI history now keeps image-only and attachment-bearing turns visible when removing empty legacy reseed text#99839 Thanks @vincentkoc.
  827. 827Claude CLI model fallback now carries the prior tool-call trail alongside tool results, giving the replacement model enough context to continue coherently#99851 Thanks @vincentkoc.
  828. 828Long-running agents can now recover full command output and truncated web_fetch content after history cleanup, reducing repeated expensive work and lost page context#100135 Thanks @obviyus.
  829. 829Embedded agents now receive well-formed summaries of long media or JSON values instead of broken characters at Unicode truncation boundaries#101311 Thanks @alix-007.
  830. 830Media-provider audit details containing emoji now remain valid and readable when shortened, instead of ending with malformed characters#101298 Thanks @alix-007.
  831. 831Long agent prompt data containing emoji or other paired Unicode characters now stays well-formed when capped, avoiding broken text in agent and automation context#101303 Thanks @alix-007.
  832. 832Embedded agents now retain configured compaction reserve limits when runtime safeguards save settings, reducing unexpected context-budget shrinkage during long work#92237 Thanks @sercada.
  833. 833Telling an agent to remember a preference no longer triggers the unrelated warning used for promises to schedule an automatic reminder#93862 Thanks @arkyu2077.
  834. 834Sessions with large command output or summaries now compact before exceeding the model context, avoiding failed provider requests and misleading token budgets#97861 Thanks @yetval.
  835. 835Long tool-heavy or compacted sessions now budget the real size of command output and summaries before sending a prompt, reducing context overflow failures#97928 Related #97927. Thanks @liuhao1024, @yetval.
  836. 836Edge-case fixes now preserve literal memory text and valid Unicode, improve voice-call cleanup and port checks, report Claude models and context limits accurately, and retain useful ClickClack connection errors#100204 Thanks @cxbasdev, @harjothkhara, @lilan0125, @lin-hongkuan, @liuhao1024, @mikasa0818, @pandah97, @sunlit-deng, @zoowh.
  837. 837Fresh Claude CLI workspaces now run a pending `BOOTSTRAPFresh Claude CLI workspaces now run a pending BOOTSTRAP.md on the first reply so required identity, memory, and setup steps are completed before normal conversation. #100560 Thanks @bill-starfoundry, @kruegerb, @vincentkoc.
  838. 838Long-running agents are less likely to lose workspace instructions such as AGENTS.md, SOUL.md, or MEMORY.md for a turn during a temporary filesystem error#100910 Thanks @masatohoshino.
  839. 839Embedded agent runs that omit a session key now retain the intended fallback session context more reliably. 31a65e0 Thanks @vincentkoc
  840. 840A malformed custom tool in realtime Talk no longer removes the built-in consult tool or other valid custom tools from the session. 170150a Thanks @vincentkoc
  841. 841Local-model conversations now retain reusable prompt work when switching between interactive chats and background jobs, avoiding repeated multi-minute warm-up delays#98267 Related #98261. Thanks @headbouyjb.
  842. 842A response interrupted mid-tool-call no longer runs or saves that incomplete action, preventing accidental child sessions and other unintended side effects#97140 Thanks @galiniliev.
  843. 843Agents running on macOS 26 now receive the macOS product version in their runtime prompt instead of the Darwin kernel version#95225 Thanks @sunlit-deng.
  844. 844Level directives such as /verbose and /think no longer remove the first word of the user's message when both are sent together#97929 Thanks @yetval.
  845. 845Malformed surrogate HTML entities in provider output no longer corrupt agent tool arguments, transcripts, or URLs, while legitimate entities and emoji still decode normally#99564 Thanks @mikasa0818.
  846. 846Leaving one answer blank in a multi-question prompt no longer shifts the remaining typed answers onto the wrong questions#100832 Thanks @machine3at.
  847. 847ACP runtime controls can now truly clear saved model, thinking, working-directory, permission, timeout, mode, and backend-extra settings so later turns do not reuse stale values#101044 Thanks @mushuiyu886.
  848. 848Skill Workshop sessions now carry a clearer prompt with about 1Skill Workshop sessions now carry a clearer prompt with about 1.8KB less repeated prompt and schema overhead while retaining the same reviewable proposal flow. #100481
  849. 849Prompt caching and cache traces now fingerprint malformed incoming text consistently with the cleaned text providers receive, avoiding needless cache misses and misleading diagnostics#101009 Thanks @qingminglong.
  850. 850Operators now receive `payloadOperators now receive payload.large or truncated diagnostics and an accurate count whenever chat.history omits older messages, making hidden history trimming visible without changing client responses. #96788 Thanks @zengwen-dt.
  851. 851With memory flush enabled, important conversation context now gets a chance to reach durable memory before automatic compaction, reducing silent gaps in saved notes#84792 Thanks @turbotheturtle.
  852. 852Long CJK-heavy sessions using a context engine such as lossless-claw no longer stop on a false prompt too large precheck after the engine has already managed the prompt#95342 Thanks @jalehman, @mpz4life.
  853. 853Large Chinese, Japanese, and Korean tool results are now estimated more accurately, reducing false context-overflow interruptions and premature compaction#95447 Thanks @moguangyu5-design, @vincentkoc.
  854. 854Prompts containing fullwidth East Asian characters now receive more accurate size estimates, allowing context management to start before an oversized request reaches the model#96442 Thanks @lin-hongkuan.
  855. 855Long conversations now recover compaction after transient provider disconnects instead of replacing useful history with a degraded placeholder summary#97504 Thanks @hugenshen.
  856. 856Long conversations using historyLimit or dmHistoryLimit now retain their saved earlier summary after compaction, helping the assistant remember prior context#97591 Thanks @liuhao1024, @yetval.
  857. 857Long Codex conversations with heavy tool use can now compact at a real history boundary and continue with relevant tool results summarized instead of retaining the full transcript#99391 Related #99375. Thanks @imchloe92, @lzy3538.
  858. 858Local-model sessions now retain auto-compaction bookkeeping, reducing repeated context refills and the unresponsive behavior they could cause#99678 Related #99677. Thanks @headbouyjb, @vincentkoc.
  859. 859Long, tool-heavy agent sessions now preserve the newest command, file, or browser result for the model while shortening older history first#99756 Thanks @acosx.
  860. 860Long cached Anthropic tool sessions now compact near the configured context threshold instead of interrupting work early because cumulative cache tokens looked like live context#99864 Thanks @jrex-jooni, @lzy3538, @vincentkoc.
  861. 861Long-lived agents with large context windows now retain fresh tool output, compact under aggregate pressure, and warn users to run /compact or /new if pressure persists#100077 Thanks @obviyus.
  862. 862Small-context local models can now begin and continue conversations without immediately entering an overflow-compaction loop before useful prompt space is available#100621 Thanks @vincentkoc.
  863. 863Long sessions that compact in stages now preserve clearer older-to-newer ordering when summaries are combined, reducing the chance that stale context appears equally recent#100684 Thanks @vincentkoc, @zw-xysk.
  864. 864Context-engine plugins can now identify the exact session that continues after compaction while older integrations using sessionFile remain compatible#101182 Thanks @jalehman.
  865. 865Preparing a reset for a long-running session now avoids scanning the entire transcript, reducing startup file activity and memory use as history grows#99335 Thanks @gmschasiepen, @momothemage.
  866. 866Gateway and embedded TUI startup now reclaim old session temporary files left by hard shutdowns, reducing hidden disk growth while preserving fresh or potentially recoverable state#90503 Thanks @sahibzada-allahyar.
  867. 867Long-running gateways can clear stale one-shot model-check sessions before they crowd out real conversation history, with dedicated CLI reporting for review#91057 Thanks @jalehman, @wangwllu.
  868. 868Mac users now get stronger protection for local OpenClaw SQLite data after abrupt power loss or an operating-system crash, with no configuration change#99067 Thanks @ooiuuii.
  869. 869Session-memory diagnostics now show the correct workspace and memory-file paths for sibling directories whose names merely resemble the user's home path#101577 Thanks @cxbasdev.
  870. 870Timed-out cron jobs, expired agent requests, and disconnected HTTP clients now stop promptly instead of spending more time and provider calls on model fallback#62682 Thanks @altaywtf, @cinapbot, @simonusa.
  871. 871Channel replies can now continue as soon as an embedded-agent turn finishes instead of waiting roughly 50 seconds for post-run authentication bookkeeping#85829 Thanks @turbotheturtle.
  872. 872Anthropic sessions stuck on a thinking-signature replay error can now retry once without invalid thinking blocks and continue without /new or transcript repair#95430 Related #95429. Thanks @alexelgier, @lzyyzznl, @vincentkoc.
  873. 873Codex-backed runs can now deliver a completed final answer instead of timing out or appearing aborted when the final completion event is missing#99217 Thanks @100yenadmin, @fuller-stack-dev, @sedrak-hovhannisyan.
  874. 874Interactive chat requests that end in a terminal failure now receive one visible error response instead of appearing to be ignored#99304 Thanks @grox2012, @moeedahmed.
  875. 875Agent sessions are less likely to lose output, alter unrelated formatting, stall after temporary provider errors, reject BMP images, or drop longer ChatGPT connections#99949
  876. 876Long Claude CLI-backed runs now show honest `ThinkingLong Claude CLI-backed runs now show honest Thinking... (~N tokens) activity for direct and queued work instead of appearing stalled when readable reasoning text is unavailable. #100148 Thanks @obviyus.
  877. 877Interactive turns that truly end without visible output now send a clear failure reply, while intentional silence and already-completed actions remain quiet#100474
  878. 878Completed answers from tool-using tasks now reach the user instead of being replaced by an incomplete-turn error, with run metadata attached to the same final response#100655 Thanks @liuwqgit.
  879. 879Using /stop during a late-aborting prompt no longer leaves a stale session lock that blocks the next turn in the same conversation. f8016c4
  880. 880Long agent runs can now resume from a valid conversation boundary after compaction recovery instead of wedging or incorrectly demoting the selected model. 486033b Thanks @mettlyz11, @neltomw, @obviyus
  881. 881Embedded agent jobs with an explicitly longer timeout now keep their lane until that requested deadline instead of being recovered at the default limit. 1437512 Thanks @vincentkoc
  882. 882Mobile, WebChat, consult, and other `chatMobile, WebChat, consult, and other chat.send clients can apply a one-time thinking level without losing the assistant reply or having the message mistaken for a text command. #98855 Thanks @jesse-merhi.
  883. 883A wedged provider call now releases its embedded agent lane on a bounded watchdog instead of indefinitely blocking queued work when run timeouts are disabled. ec28935 Thanks @arismontclair, @obviyus, @patelmm79
  884. 884Gateway conversations with an orphaned active task can now recover through diagnostics instead of leaving later turns blocked until restart. b1da734 Thanks @arismontclair, @obviyus, @ralf003
  885. 885An agent no longer stays silent after compaction when a plugin's final-answer hook hangs; OpenClaw times out the hook and still delivers the response. b2baf79 Thanks @dserious, @obviyus, @villa-feng
  886. 886Very long agent conversations are less likely to loop through failed overflow recovery because compaction now reflects the prompt OpenClaw actually prepared#101181 Thanks @jalehman.
  887. 887With `messagesWith messages.suppressToolErrors enabled, tool failures no longer leak into chat as progress updates while normal progress and final replies continue. #98063 Thanks @amittell, @moeedahmed.
  888. 888Interactive and queued turns that finish without a visible answer now return a clear, sanitized failure message instead of leaving the chat looking stuck#100456 Thanks @mushuiyu886.
  889. 889Legacy subagent sessions now follow their actual nesting level, so nested-agent limits and controls no longer fall back to top-level behavior#54593 Thanks @ruanrrn.
  890. 890Subagent completion notices now arrive once instead of being repeated when the requesting session changes during delivery#92274 Related #91527. Thanks @fsdwen, @obviyus, @zackchiutw.
  891. 891Successful embedded-agent subagent launches now remain successful in transcripts and later compaction summaries instead of being recorded as tool failures, while real launch failures stay visible#96851 Thanks @neomail2, @parveshsaini.
  892. 892Codex-runtime transcripts and compaction summaries now keep successful subagent launches and goal operations out of failure records, while genuine failures remain visible and accepted-launch hooks can run#96856 Thanks @nxmxbbd.
  893. 893Successfully started subagents now remain visible in /subagents list and subagents(action="list"), including when different sessions own control and completion#99410 Related #75593. Thanks @aaajiao, @sheyanmin.
  894. 894Codex app-server agents can again list allowed agents, spawn OpenClaw or ACP subagents, and yield during delegated work without resumed heartbeats hitting incompatible tool definitions#99561 Related #99464. Thanks @100yenadmin, @joshavant.
  895. 895Requester agents now receive a follow-up when an accepted sessions_send delivery later fails because the target session is locked, so they can retry or choose another route#99907 Thanks @849261680, @alex-heyuqing.
  896. 896Sub-agents and other HTTP loopback MCP clients can again receive browser screenshots and valid image or embedded-resource results without schema failures#100336 Thanks @tzy-17.
  897. 897A yielded Codex native subagent's completion now reaches its parent run before the shared app-server connection is cleaned up. 2f89de8 Thanks @vincentkoc
  898. 898Large agent and subagent workloads now place less memory pressure on the Gateway because completed run snapshots are bounded while results still remain available to active waiters#77973 Related #77976. Thanks @fede-kamel, @vincentkoc.
  899. 899Parent sessions waiting on a subagent now receive the subagent's actual hard-timeout phase and timestamps instead of a generic timeout#89367 Thanks @pick-cat.
  900. 900Malformed cyclic attachments can no longer crash subagent delivery-evidence collection, so the reply handoff completes and still returns reachable media URLs#97041 Thanks @pick-cat.
  901. 901A parent session waiting on several subagents now resumes and returns their combined results when the last outstanding work finishes, without requiring the user to send another message#97090 Thanks @galiniliev.
  902. 902Manually spawned ACP child runs now appear once in the task ledger instead of creating duplicate requester-visible rows#97131 Thanks @moeedahmed.
  903. 903Cancelling an ACP task from the CLI now reaches the live Gateway-owned run, reports real failures, and avoids duplicate active task rows#97352 Thanks @aliahnaf2013-max.
  904. 904Stopping a subagent now clears its running task reliably and prevents late completion races from reviving or overwriting the canceled state#99806 Thanks @masatohoshino, @timofa.
  905. 905After a Gateway restart, a redirected subagent now continues the user's newest instruction instead of returning to stale work. 7b5d86e Thanks @amittell
  906. 906ACP run-to-session lookups now return the current active run instead of a stale association from an older run#96427 Thanks @lin-hongkuan.
  907. 907Parent sessions no longer repeat an earlier child-agent progress message when the child later reports completion#101042 Thanks @mushuiyu886.
  908. 908Isolated cron jobs can announce a cross-session result without feeding the recipient's reply back into the cron run and creating duplicate message loops#92283 Related #92257. Thanks @harjothkhara, @nailujac, @vincentkoc.
  909. 909Agents can now read structured JSON and resource tool results during provider replay instead of receiving an empty result or generic media placeholder#97742 Thanks @obviyus.
  910. 910Images attached to a CLI-backed prompt now survive embedded-model fallback, preserving the visual context needed to answer#99891 Thanks @vincentkoc.
  911. 911Messages mixing inline and offloaded images now preserve every attachment position so model instructions that depend on sequence remain accurate#99902 Thanks @vincentkoc.
  912. 912Images from the current prompt now reach CLI fallback attempts in the right order, without pulling stale image references from earlier retries or history#100035 Thanks @vincentkoc.
  913. 913Batched media replies can now finish successfully after delivery without a misleading session-change failure, while active conversation ownership checks remain enforced#100490 Thanks @scotthuang.
  914. 914Sandboxed auto-replies now wait for remote media copied over SCP to finish and report transfer failures without crashing or cleaning up too early#100861 Thanks @cxbasdev.
  915. 915Useful JSON, resource data, and CLI tool results now remain visible in transcripts instead of disappearing behind an attachment placeholder#97268
  916. 916An empty non-image tool result no longer becomes (see attached image) in OpenAI-compatible agent context, avoiding misleading follow-up behavior#97423 Thanks @scribe-dandelion-cult.
  917. 917Gateway event-delivery failures now produce actionable warnings instead of unexplained process-level promise rejections, while unrelated subscriptions keep running#100401 Thanks @cxbasdev.
  918. 918Discord now presents commentary, reasoning, and tool activity in a clearer sequence across queued turns, while loopback MCP clients can attach to one Gateway session with an expiring, revocable token. 35af831 Thanks @dwc1997, @lsr911, @ooiuuii, @romneyda, @solodmd, @vincentkoc, @wendy-chsy, @yeager, @zenglingbiao
  919. 919Successful agent tools that return safe plain text now show that output instead of leaving users with an apparently empty result#99526 Related #99523. Thanks @snowzlm.
  920. 920A successfully delivered heartbeat notification no longer leaves stale recovery state that can block later heartbeat alerts or check-ins#83187 Thanks @agocs.
  921. 921Restarting the Gateway during a deferred channel reload no longer starts the same channel twice, avoiding webhook port conflicts and repeated restart failures#94964 Related #79487. Thanks @lzyyzznl, @tseller.
  922. 922A damaged SQLite delivery-queue entry no longer blocks recovery of every other valid queued session or outbound delivery after restart#98354 Thanks @pick-cat.
  923. 923Gateway startup lock failures now clean up partial files and open handles, allowing a later startup to acquire the lock normally#99291 Related #98958. Thanks @chenyangjun-xy, @zhanglei99586.
  924. 924Gateway status now reports unavailable SSH cleanly and promptly instead of crashing or waiting indefinitely when tunnel startup fails#99800 Thanks @cxbasdev, @vincentkoc.
  925. 925Heartbeat and cron work on macOS and Linux is less likely to fail with Unknown system error -11 when reconnects overlap session or workspace updates#100389 Thanks @ogarciarevett.
  926. 926Gateway startup no longer performs unsolicited provider-auth discovery across every configured agent, helping channels and local commands remain responsive while authentication loads on demand#100667 Thanks @vincentkoc.
  927. 927Unexpected SSH tunnel diagnostic-stream closure no longer crashes the Gateway during tunnel checks or shutdown#100855 Thanks @cxbasdev, @vincentkoc.
  928. 928A disconnected or failing session-history stream no longer crashes the Gateway and interrupts service for everyone else#101571 Thanks @vincentkoc, @zengwen-dt.
  929. 929Gateway startup can now be retried immediately after a configuration-change rejection instead of being blocked for up to five minutes by a stale migration lease#103157
  930. 930Gateway startup channel warnings now use the same plugin manifests as the running startup process, reducing inconsistent warnings and repeated discovery. 10ca94e Thanks @vincentkoc
  931. 931Gateway startup now skips unnecessary provider thinking-policy work when an explicit setting or model catalog already determines the banner result. b18af41
  932. 932Gateway connection failures now identify the last completed handshake phase, helping operators distinguish upgrade, credential, authentication, session, and ready-state stalls#93402 Thanks @849261680, @bzelones, @vincentkoc, @youngting520.
  933. 933Control UI and other Gateway clients now show the correct pairing or protocol-version guidance even when detail codes contain extra whitespace#99555 Thanks @ly85206559.
  934. 934Gateway override authentication errors now tell CLI and TUI users whether to add a token or password, remove --url, or pair the relevant environment variables#100418 Thanks @gmays.
  935. 935Standalone ACP clients now close the shared SQLite state database during shutdown so hot reloads and immediate restarts can reopen it without stale locks or callbacks#100691 Thanks @lzy3538.
  936. 936Voice-call webhook setup through ngrok or Tailscale now fails cleanly on tunnel stream errors instead of crashing the Gateway, and shutdown avoids waiting on an already-ended tunnel#101394 Thanks @cxbasdev.
  937. 937Provider failures that contain BigInt, circular objects, or other unusual values now produce the intended structured transport error instead of crashing the error-reporting path#88401 Thanks @pluviobyte.
  938. 938OpenClaw no longer crashes when a supervised child output stream fails immediately after launch#99802 Thanks @cxbasdev, @vincentkoc.
  939. 939MCP stdio sessions now report stderr pipe failures as transport errors without taking down OpenClaw or losing available diagnostics#99803 Thanks @cxbasdev, @vincentkoc.
  940. 940ACPX MCP proxies now turn closed input or output pipes into a clear proxy failure instead of an uncaught Node stream crash#99852 Thanks @sunlit-deng, @vincentkoc.
  941. 941Shell snapshot capture and validation no longer crash OpenClaw when an unused helper-process output pipe reports a stream error#100744 Thanks @lsr911, @vincentkoc.
  942. 942A node-host `systemA node-host system.run stream failure now returns a clear failed result instead of crashing the node host, and a child that will not stop is terminated after one second. #100849 Thanks @cxbasdev.
  943. 943Docker-backed sandbox file and shell commands now fail promptly with the original input-stream error instead of crashing, hanging, or remaining pending#101032 Thanks @cxbasdev.
  944. 944APNs relay pushes now reject oversized response bodies as RelayResponseTooLarge instead of exhausting Gateway memory or reporting false delivery#97550 Thanks @alix-007.
  945. 945An ACP Gateway event-handler failure now produces a concise diagnostic instead of terminating the ACP process or corrupting protocol output#100558 Thanks @ajwan8998.
  946. 946A runaway tool_search_code subprocess can no longer grow Gateway memory without limit through stderr, while failure reports retain the latest useful diagnostic detail#101007 Thanks @hugenshen, @vincentkoc.
  947. 947Built-in grep stream failures now become ordinary tool errors instead of crashing the agent runtime, hanging the search, or leaving incomplete results unexplained#101014 Thanks @cxbasdev.
  948. 948SSH-backed sandbox commands and uploads now stop cleanly, clean up child processes, and preserve the useful error when an input or output stream fails#101031 Thanks @cxbasdev.
  949. 949Experimental local-model lean mode now offers a smaller default tool menu for constrained models, while operators can explicitly retain media, voice, or PDF tools through allowlists#88881 Thanks @vincentkoc.
  950. 950Operators can now set OPENCLAW_SANDBOX_IMAGE to build revision-specific sandbox image tags for controlled rollout and rollback#99915
  951. 951Lean local-model agents can now choose the familiar exec tool directly when policy permits it, while existing allowlists, sandboxing, approvals, and hooks still govern command execution#101607 Thanks @vincentkoc.
  952. 952Busy or slower hosts now give Codex native permission checks and pre-tool hooks more time to finish, reducing dropped policy decisions. 123ec16 Thanks @vincentkoc
  953. 953Completed or expired exec approvals no longer add misleading follow-up warnings, making the remaining dispatch warnings more useful for spotting real delivery failures#66685 Thanks @pfrederiksen.
  954. 954Local Gateway approval read or write failures now return a consistent UNAVAILABLE response instead of a generic handler error#79861 Thanks @martins-oss.
  955. 955Agent requests with several MCP servers now initialize those servers concurrently, shortening the wait before the model begins while isolating slow or failed servers#94230 Thanks @mmyzwl, @vincentkoc.
  956. 956External tools can now receive session-scoped Gateway access without process-wide credentials or permission to impersonate another session, forming the secure base for openclaw attach#96351 Thanks @anagnorisis2peripeteia, @obviyus.
  957. 957Operators can inspect the effective tools for global sessions assigned to any configured agent, not only the default one#97265 Thanks @pick-cat.
  958. 958Agent runs, Doctor, and Gateway tool views now describe access using the same policy that actually governs the run, reducing confusing permission mismatches#99817
  959. 959Bounded write-scope clients can now rename, pin, archive, categorize, and mark sessions unread without admin access, while user labels and stable list ordering survive refreshes#100964
  960. 960Embedded terminals can now open, resize, stream output, and close consistently across the Gateway, Control UI, and native apps. 6601576
  961. 961Developers can build against and consume managed-worktree session results from the Gateway protocol package without duplicate-name failures. 8ce620f Thanks @vincentkoc
  962. 962Embedded openclaw agent --local runs using OpenAI-compatible providers now report and save streamed token usage instead of showing zero, improving session, context, cost, and monitoring records#96523 Thanks @ly85206559, @vincentkoc.
  963. 963Unusual ACP failure causes now produce stable, readable diagnostic details instead of a missing or invalid explanation#96270 Thanks @ly-wang19.
  964. 964Normally completed agent and subagent runs no longer appear as error-level log entries, reducing false alarms while genuine failures remain elevated#101703 Thanks @zengwen-dt.
  965. 965Gateway logs now reveal when OpenClaw cannot save a terminal session's final lifecycle state, making silent persistence failures diagnosable#97839 Related #97795. Thanks @aniruddhaadak80, @lzy3538.
  966. 966Gateway MCP logs are now quieter and identify the responsible tool when schema problems occur, while distinct conflicts remain visible#98821 Thanks @alvelda, @harjothkhara.
  967. 967Malformed Gateway MCP tools/call arguments now return a clear invalid-parameters response before any hook or tool can process them#99180 Thanks @vectorpeak.
  968. 968MCP attach requests without a valid session key now return the intended validation error instead of crashing the Gateway with a TypeError#99488 Thanks @zhanglei99586.
  969. 969Starting a new Codex session no longer emits a false history warning before its transcript exists, while genuine history failures remain visible#100484 Thanks @litang9, @vincentkoc.
  970. 970Gateway usage reports now label start and end dates in the requested timezone, including correct calendar-day handling across local daylight-saving transitions#100567 Thanks @nianjiuzst.
  971. 971Session usage details now recover malformed transcript dates from available message timestamps and return finite, consistently ordered values instead of nulls#100687 Thanks @sheyanmin.
  972. 972Truncated agent logs and diagnostic previews now keep emoji and other extended Unicode characters intact at the cutoff#96296 Thanks @ly-wang19.
  973. 973Long agent grep lines now truncate emoji and uncommon CJK characters cleanly instead of ending with corrupted replacement symbols#97559 Thanks @zenglingbiao.
  974. 974Emoji and other supplementary characters now remain intact when long agent progress or active-memory recall text is shortened#100244 Thanks @vincentkoc, @xialonglee, @zengwen-dt.
  975. 975Shortened text across CLI output, diagnostics, plugin messages, previews, errors, task summaries, and Zalo sends now preserves complete emoji and other supplementary characters#101654 Thanks @lsr911, @maweibin, @wm0018.
  976. 976Long names, labels, summaries, previews, titles, and diagnostics across OpenClaw now truncate without splitting emoji or other supplementary Unicode characters#101685 Thanks @lsr911, @ly85206559, @maweibin, @wings1029.
  977. 977Bounded text in Parallel searches, compaction, telemetry, presence, Workboard, badges, and Control UI metadata now keeps or omits whole Unicode characters instead of leaving malformed fragments#101711
  978. 978Long streamed replies now split only between complete Unicode characters, preserving emoji in plain text and fenced Markdown even at tight message limits#104441 Thanks @mushuiyu886.
  979. 979Long status messages and command output now stay readable when shortened, without splitting emoji or non-English characters into corrupted text. 2e7ffca Thanks @vincentkoc
  980. 980Codex usage-limit previews and plan status labels now truncate emoji and uncommon Unicode cleanly at their display boundaries#97299 Thanks @zenglingbiao.
  981. 981/subagents list now shortens long names and task descriptions containing emoji or uncommon CJK characters without displaying broken glyphs#97557 Thanks @zenglingbiao.
  982. 982Compact subagent lists now keep long labels and task text within their display budget without splitting emoji or breaking alignment#100013 Thanks @qingminglong.
  983. 983Shortened web, media, TTS, status, transport, and voice-call text now preserves complete Unicode characters instead of producing replacement symbols or malformed downstream content#101355 Thanks @alix-007, @vincentkoc.
  984. 984Codex desktop notifications now shorten long assistant previews containing emoji or CJK text without malformed characters#101534 Thanks @lsr911.
  985. 985ACP tool titles, permission prompts, warnings, and errors now keep long emoji or CJK argument previews readable when shortened#101535 Thanks @lsr911.
  986. 986Suppressed auto-reply previews in verbose logs now preserve complete emoji and other supplementary characters instead of showing corrupted text at the length limit#101575 Thanks @wm0018.
  987. 987Oversized agent tool results now preserve complete emoji and similar Unicode characters when shortened before being sent to the model#102087 Thanks @chengzhichao-xydt.
  988. 988Gateway WebSocket failures now keep non-ASCII close reasons readable and within the byte limit instead of cutting characters into garbled text#100047 Thanks @narahariraghava.
  989. 989Model-provider keys stored with SecretRefs now receive additional protection against accidental exposure in logs, errors, proxy captures, SDK setup, and runtime inspection, with a compatibility switch for secret sentinels#102009
  990. 990Operators can use targeted Doctor lint to detect credential residue in historical config-audit.jsonl entries and preview redaction before running openclaw doctor --fix#84450 Thanks @giodl73-repo.
  991. 991Gateway service regeneration now keeps environment-backed secrets out of Linux unit definitions and preserves resolved provider and channel credentials on macOS#96065 Thanks @darren2030, @obviyus.
  992. 992openclaw doctor --fix now preserves separate OAuth accounts for the same provider, including each account reference and saved display name#97541 Thanks @liuhao1024, @yetval.
  993. 993Bare Fireworks API keys are now masked in logs, provider errors, command details, tool output, and Control UI diagnostics even without a nearby sensitive-field label#98226 Related #98225. Thanks @ooiuuii.
  994. 994Failed OpenAI or Codex credential refreshes now report that reauthentication is required and privately identify the affected profile instead of appearing healthy until model turns fail#99134 Related #99120. Thanks @100yenadmin, @fuller-stack-dev.
  995. 995A temporary output-stream read failure from an exec-based SecretRef provider no longer crashes OpenClaw during credential resolution#100521 Thanks @cxbasdev.
  996. 996Agent payload logs and cache traces now redact provider keys even when those credentials appear inside free-text diagnostic values. d8ee630 Thanks @joshavant
  997. 997Failed cron webhooks no longer forward raw command summaries or diagnostics that may contain setup prompts, codes, or secret-like output. 1d17263 Thanks @joshavant
  998. 998Secret target discovery now works consistently for both scoped requests and the full compiled registry instead of failing when no allowed subset is supplied. e490171
  999. 999/login codex now switches the active chat to the account just authenticated without overwriting a newer manual profile choice, and gives recovery guidance if the switch fails. 02c3de9 Thanks @vincentkoc
  1000. 1000Profile changes made through /login now use the standard session save path, preserving newer concurrent selections and existing recovery behavior. f07c478 Thanks @vincentkoc
  1001. 1001Codex session bindings now keep large MCP configurations and rotated Authorization credentials in bounded fingerprints without persisting readable bearer values. 491e42e Thanks @100yenadmin
  1002. 1002Copied provider keys and tokens now have hidden terminal control characters removed before request headers are prepared, while intentional spaces remain intact#96444 Thanks @lin-hongkuan.
  1003. 1003Masked malformed credentials now stay on one safe line in setup and authentication diagnostics even when the original input contains newlines or other control bytes#96445 Thanks @lin-hongkuan.
  1004. 1004Security audits no longer mistake bundled placeholder keys for LM Studio, Ollama, and other keyless local providers as exposed plaintext credentials#97622 Thanks @xydigit-sj.
  1005. 1005Control UI Activity previews now conceal API keys stored under dotted configuration names or returned in structured tool output#99460 Related #99459. Thanks @ooiuuii.
  1006. 1006Custom ACP error redactors now keep OpenClaw's built-in secret cleanup, preventing known tokens, credentials, and private-key material from leaking into formatted errors#100191 Thanks @lin-hongkuan.
  1007. 1007When another OpenClaw process is refreshing OpenAI OAuth credentials, operators now see one useful contention error without duplicated wording or exposed local file paths#101573 Thanks @vincentkoc.
  1008. 1008Running a read-only local Gateway check no longer leaves stale pairing permissions that block a later agent, admin, write, or device-approval command#96002 Thanks @vincentkoc.
  1009. 1009/pair now refuses setup codes that point to non-routable `0/pair now refuses setup codes that point to non-routable 0.0.0.0 or :: addresses and gives operators secure Gateway URL guidance instead. #98617 Thanks @crh-code.
  1010. 1010Gateway authentication retries now send stored device tokens only to true loopback endpoints, not remote hostnames that merely resemble 127.* addresses#99859 Thanks @ly85206559.
  1011. 1011The /pair mobile setup flow now accepts local IPv6 ULA and link-local Gateway addresses without requiring TLS or a different advertised host, while public cleartext URLs remain blocked#101008 Thanks @zhangguiping-xydt.
  1012. 1012Device owners can approve the request ID most recently shown by openclaw devices list after a reconnect, without weakening protection against newly expanded scopes#98145 Thanks @romneyda.
  1013. 1013Swift native clients now support device-scoped skill approvals, with the reviewer-device field encoded in their generated Gateway models. 1403c64
  1014. 1014Gateway sign-in tracking now keeps bounded memory use during floods of failed attempts from many addresses while preserving existing lockouts#96224 Thanks @eleqtrizit.
  1015. 1015Browser control now requires the same administrator permission through direct node invocation as through the standard browser request path, preventing write-only credentials or third-party plugins from gaining elevated access#85916 Thanks @eleqtrizit, @laphilosophie.
  1016. 1016Only the configured owner can now change whether a group responds to mentions or every message through /activation#97838 Thanks @pgondhi987.
  1017. 1017Starting or changing native Codex sessions now requires owner or `operatorStarting or changing native Codex sessions now requires owner or operator.admin access, while other authorized senders retain read-only inspection. #97952 Thanks @eleqtrizit.
  1018. 1018ACP session lifecycle and runtime controls now require an owner or internal Gateway administrator instead of being available to any authorized channel user#97953 Thanks @eleqtrizit.
  1019. 1019Approving a node that can handle sensitive browser traffic now requires administrator permission, matching the security level already required to use that capability#104491 Thanks @yetval.
  1020. 1020Authorized non-owner chat participants can no longer inspect or change owner-controlled MCP server configuration through /mcp. ad5a26c Thanks @joshavant
  1021. 1021Auto-reply diagnostics now remain owner-only instead of allowing non-owner participants to run the command. 170bf72 Thanks @joshavant
  1022. 1022After an agent is removed, its leftover sessions can no longer start new model runs through the Gateway#97260 Thanks @obviyus, @pick-cat.
  1023. 1023Non-owner Gateway chat users are no longer offered the protected cron, gateway, or nodes control tools, even when those tools are otherwise allowlisted#102030 Thanks @pgondhi987.
  1024. 1024Trajectory exports from chat now require owner authority, preventing other command-authorized channel users from retrieving sensitive session artifacts#97840 Thanks @pgondhi987.
  1025. 1025Gateway-wide Active Memory can now be changed only by owners or administrators, while other authorized users retain session-level controls#97841 Thanks @pgondhi987.
  1026. 1026Only owners and administrative Gateway clients can now turn Memory Core dreaming on or off through /dreaming, while status and help remain available to others#97869 Thanks @eleqtrizit.
  1027. 1027Non-admin Telegram and Discord users can no longer change the Gateway's Talk voice, though they can still view the current and available voices#97874 Thanks @eleqtrizit.
  1028. 1028Installing or reconfiguring Codex Computer Use resources now requires owner or administrator access, while other authorized senders can still inspect status#97955 Thanks @eleqtrizit.
  1029. 1029Authenticated owners can use their already-granted shell, file, process, Skill Workshop, and plugin tools in WebChat without extending those permissions to guests or external senders#101271 Thanks @fuller-stack-dev.
  1030. 1030With strictInlineEval enabled, versioned Python and PyPy commands plus additional PHP and R inline forms now require fresh explicit approval rather than inheriting executable trust#96216 Thanks @eleqtrizit.
  1031. 1031In shared channels, only the person who started a Claude Code command can approve or deny its tool permission requests#98256 Thanks @eleqtrizit.
  1032. 1032Running /prose now shows operators the transitive remote imports and asks for consent before OpenProse fetches those code dependencies. 259877d Thanks @joshavant
  1033. 1033Codex plugin users can allow read-only app actions while requiring a fresh approval for every write or destructive action#97123 Thanks @kevinslin.
  1034. 1034Codex plugin apps now avoid approval prompts for read-only actions, preserve per-app write policies across recovery, and refresh their app inventory after upgrades#97327 Thanks @kevinslin.
  1035. 1035Windows exact-path execution approvals now launch the approved executable rather than a same-named program from the working directory#98260 Thanks @eleqtrizit.
  1036. 1036The Codex plugin now names per-action destructive approval mode ask, making it clear that each write or destructive action remains available but requires confirmation#98501 Related #98499. Thanks @kevinslin.
  1037. 1037Exec approval prompts now display and transmit long command text containing emoji or malformed Unicode without broken characters or encoding failures#99566 Thanks @mikasa0818.
  1038. 1038The Control UI terminal is now explicit opt-in, opens tabs under the selected agent's workspace and policy, and closes affected shells when accepted access restrictions tighten#100081 Thanks @rayncc.
  1039. 1039Windows companion-node exec policies can now be viewed and updated through node-aware approvals commands and displayed correctly in Control UI#101669 Thanks @vincentkoc.
  1040. 1040Using jq through exec now requires an explicit trusted allowlist entry or approval instead of being treated as a harmless stdin-only safe binary#102032 Thanks @pgondhi987.
  1041. 1041Always-allow approvals for npm exec, npx, pnpm, and yarn wrappers now apply to the actual command rather than unintentionally trusting different future payloads#102035 Thanks @pgondhi987.
  1042. 1042Skills created by agents now remain pending for Skill Workshop review and approval instead of becoming active immediately without the expected safeguards#98346 Related #96054. Thanks @momothemage, @xianshishan.
  1043. 1043Status and diagnostic tools can now identify stale exec approval follow-ups intentionally suppressed after /new or /reset instead of treating them as unexplained delivery failures#98293 Thanks @bsniznd.
  1044. 1044Codex /btw side conversations now preserve an ask-mode plugin app's requirement to obtain approval before destructive actions#98812
  1045. 1045Long Codex app-server approval details and command previews now preserve emoji and extended Unicode characters instead of showing corrupted text#100177 Thanks @xialonglee.
  1046. 1046Strict exec approval now keeps joined or clustered interpreter inline-code commands such as python3 -xcprint as one-time approvals rather than reusable allowlist entries#101353 Thanks @pgondhi987.
  1047. 1047Long exec auto-review explanations containing emoji or supplementary CJK characters now shorten cleanly instead of showing a broken replacement symbol#101513 Thanks @wm0018.
  1048. 1048Plugin approval titles and descriptions now remain readable when emoji or supplementary CJK characters fall at the Gateway's text limit#101580 Thanks @wm0018.
  1049. 1049Agents using OpenClaw's cron tools are now limited to their own scheduled jobs and session targets, while operator-managed cron remains unchanged and mixed-version setups fail closed with an openclaw gateway restart instruction#96883 Thanks @joshavant.
  1050. 1050Cron wake actions started by an agent now remain within that agent's own session lanes, reducing the chance of waking another agent's conversation#97949 Thanks @eleqtrizit.
  1051. 1051Write-scoped Gateway clients can still perform supported message actions but can no longer supply identity fields that masquerade as a trusted requester or owner#102031 Thanks @pgondhi987.
  1052. 1052Multi-user bridges using `openclaw agent --agentMulti-user bridges using openclaw agent --agent ... --channel ... --to ... now keep recipients in separate sessions when per-recipient isolation is configured. #101507 Thanks @pingfanfan, @vincentkoc.
  1053. 1053Read-only voice-call status now omits phone numbers, transcripts, routing details, processed event IDs, and raw metadata#97870 Thanks @eleqtrizit.
  1054. 1054ClawHub now checks community plugin and skill releases before download, blocking prohibited releases and requiring explicit acknowledgement for suspicious ones while leaving existing installs in place when an update is skipped#81364 Thanks @jesse-merhi.
  1055. 1055Authorized operators now have a durable audit history for agent and tool activity, with filters, stable paging, bounded JSON export, configurable recording, and automatic retention limits#98704
  1056. 1056Operators using workspace repairs can now run doctor --fix to disable policy-denied Gateway HTTP endpoints without removing nested URL-fetch settings#99731 Thanks @giodl73-repo.
  1057. 1057openclaw security audit now warns that per-agent skill allowlists do not prevent shell-capable agents from reaching globally configured MCP servers#98352 Thanks @momothemage.
  1058. 1058Managed deployments can now require entries such as `systemManaged deployments can now require entries such as system.run in gateway.nodes.denyCommands, and Policy doctor warns when configuration drift leaves a privileged node command available. #99121 Thanks @giodl73-repo.
  1059. 1059policy check --json now tells administrators whether each finding is automatically repairable, needs review or manual work, is validation-only, or is unsupported#99686 Thanks @giodl73-repo.
  1060. 1060Operators who explicitly enable Policy workspace repairs can now automatically narrow several unsafe settings, while OpenClaw remains read-only without that opt-in#99690 Thanks @giodl73-repo, @omarshahine.
  1061. 1061Policy workspace repairs can now add required tools to the affected deny list while preserving existing entries and avoiding unintended root-policy widening#99700 Thanks @giodl73-repo.
  1062. 1062Policy workspace repairs can now move reported open channel groups to allowlist mode and require mentions without changing inherited defaults#99720 Thanks @giodl73-repo, @omarshahine.
  1063. 1063doctor --fix now shows the exact `gatewayDoctor --fix now shows the exact gateway.bind=loopback or gateway.nodes.denyCommands change needed for sensitive findings without applying it automatically. #99776 Thanks @giodl73-repo.
  1064. 1064openclaw security audit now reports Browser exposure only when plugin policy actually allows the Browser plugin to run#97732 Thanks @amtellezfernandez.
  1065. 1065Provider, channel, media, and web requests can now reach public destinations through a managed proxy even when local DNS is unavailable or differs from the proxy's DNS#98951 Related #98925. Thanks @momothemage, @sandl99.
  1066. 1066Malformed MCP OAuth failures now return a bounded HTTP-status diagnostic instead of allowing an unbounded error response to exhaust agent memory#98143 Thanks @pick-cat.
  1067. 1067Under strict SSRF policy, remote-browser discovery can no longer redirect OpenClaw from the configured CDP endpoint to a different host, port, or security mode. cbc833a Thanks @vincentkoc
  1068. 1068Oversized or never-ending responses from supported external providers now stop at a fixed limit with a labeled error instead of consuming memory until the full body arrives. 0a14444 Thanks @joshavant
  1069. 1069Web fetch and provider integrations now enforce response-size caps without allocating an entire nonstandard response in memory#99884 Thanks @zenglingbiao.
  1070. 1070Trusted custom provider hosts are now protected from DNS rebinding into local services; intentional loopback aliases must use an explicit local origin or enable allowPrivateNetwork#100835 Thanks @machine3at.
  1071. 1071Browser-control requests now reject oversized successful JSON responses with a BrowserServiceError before they can consume excessive memory, while supported large browser results still work#100889 Thanks @mushuiyu886.
  1072. 1072Browser automation now keeps Chrome control traffic tied to the configured or explicitly allowed CDP host, reducing the risk that a discovered debugger address redirects credentials or control elsewhere#101171
  1073. 1073Hidden control characters can no longer break terminal hyperlink boundaries or inject control behavior through documentation link text#96440 Thanks @lin-hongkuan.
  1074. 1074MCP include and exclude filters with many wildcard segments now reject nonmatches quickly instead of stalling tool discovery for minutes#100330 Thanks @lsr911.
  1075. 1075Anthropic and Gemini PDF analysis now blocks unsafe private-network redirects and oversized responses by default while still supporting configured local endpoints#97872 Thanks @eleqtrizit.
  1076. 1076Anthropic requests through Cloudflare AI Gateway now receive OpenClaw's standard private-address blocking, timeouts, retry guidance, and managed response safeguards#98003 Thanks @wangmiao0668000666.
  1077. 1077Sandboxed agents with host browser control disabled can no longer reach a signed-in host browser through a paired browser node#97958 Thanks @eleqtrizit.
  1078. 1078Hooks and skills no longer activate from unsafe inherited configuration values, while ordinary configured paths and explicit defaults continue to work#59694 Thanks @yonganzhang.
  1079. 1079Unsafe, malformed, or unexpectedly large fd and ripgrep helper archives now fail early and clean up after themselves instead of putting agent setup at risk#98988 Thanks @leonidaslux, @vincentkoc.
  1080. 1080Config show, set, and unset now operate only on values truly stored in the user's configuration, preventing inherited object state from masquerading as saved settings#99846 Thanks @vincentkoc, @zenglingbiao.
  1081. 1081Terminal requests with an unknown agent ID now fail clearly instead of falling back to global defaults and potentially opening a host shell outside the intended agent boundary. 3601dca
  1082. 1082The Windows installer now accepts patched SQLite runtimes, rejects unsafe or unreadable ones, and reports the detected version when another Node.js upgrade is required. 28db140 Thanks @vincentkoc
  1083. 1083Managed host tools no longer inherit the active Conda environment from the shell that launched OpenClaw, avoiding unintended Python and package-manager behavior#99425 Related #99424. Thanks @krissding, @ooiuuii.
  1084. 1084OpenShell workspace file operations now stay inside the validated local sandbox mirror, with unsafe symlink, hard-link, cross-root, and changing-directory cases failing cleanly. c6f5725 Thanks @joshavant
  1085. 1085Config recovery now warns when the file was repaired but its final permissions could not be hardened, preserving the recovery while exposing the security issue#95348 Thanks @hugenshen.
  1086. 1086Installing or updating ClawHub skills, plugins, and packages on Linux no longer risks changing shared /tmp permissions and disrupting unrelated services#101246 Thanks @ch3ch2cho2021, @yangxiansheng.
  1087. 1087The Diffs viewer now provides a multi-file overview and direct file navigation, while PNG and PDF exports omit controls that cannot be used#100753
  1088. 1088After the Diffs viewer is reopened or refreshed, its toolbar controls now act only on the currently displayed diff cards#96138 Thanks @brokemac79, @davinci282828.
  1089. 1089Session tools now display the correct absolute path for projects beside the home directory instead of turning a shared text prefix into a misleading ~... path#96562 Thanks @he-yufeng.
  1090. 1090Realtime Talk consult calls acknowledge as soon as the embedded agent run is accepted, rather than waiting for it to finish#101091 Thanks @romneyda.
  1091. 1091Authorized remote clients can now request playable speech for an individual assistant message using the existing Gateway TTS configuration without accessing server-local files#100770
  1092. 1092Trusted Gateway clients can now browse workspace directories and preview supported files, enabling the iOS and Android apps to inspect and share agent output without SSH#100738
  1093. 1093iOS and Android users can create empty session groups, rename them once across their sessions, and remove a group without deleting the conversations inside it#101234
  1094. 1094Android and iOS now explain which side needs an update when app and Gateway protocol versions differ and avoid offering reconnect attempts that cannot succeed#98385 Related #98384. Thanks @joshavant.
  1095. 1095Mobile camera clips and screen recordings longer than 30 seconds can now finish within the existing duration limit without the request expiring early#99455 Thanks @nianjiuzst.
  1096. 1096The iOS and Android terminal pages now receive the operator credential from the connected device session, so authenticated users do not land on a terminal that cannot connect. 451190d Thanks @vincentkoc
  1097. 1097iOS and Android can now show the Gateway terminal as a focused full-screen view with stored credentials and a clear unavailable state instead of embedding the full desktop Control UI. 9c78489
  1098. 1098Android and iOS Gateway setup now clearly requires Secure TLS for remote hosts, warns before trusted LAN use without encryption, and offers actionable update guidance for protocol mismatches#101325 Thanks @joshavant.
  1099. 1099iOS and macOS chat now show a context-usage ring that changes warning color near the limit, helping users anticipate compaction or truncation in long conversations#101183
  1100. 1100Apple native app users across 21 supported non-English locales now see translated Listen and speech-playback status controls. 0146534
  1101. 1101Swift clients can now decode skill curator actions and status details such as pinned state, use counts, timestamps, archived reasons, and overlaps. ad833d7
  1102. 1102Apple chat now presents fenced code with theme-aware highlighting and GitHub-style tables as aligned native tables on iOS and macOS#100207
  1103. 1103Apple chat now restores the visible in-progress state after backgrounding or reconnecting, preventing overlapping sends and reconciling one correct final reply#100277
  1104. 1104iOS chat now shows and switches the active model, while iOS and macOS model pickers support pinned favorites and the five most recent choices#100774
  1105. 1105Display equations in iOS and macOS chats now appear as readable, accessible typeset math, with horizontal scrolling for wide formulas and raw text retained for malformed expressions#100829
  1106. 1106iOS and macOS hide the thinking-level control for models that cannot use it, avoid sending stale unsupported settings, and restore the previous level when a reasoning-capable model is selected again#100875
  1107. 1107Streaming replies in iOS and macOS chats now reveal text more smoothly word by word, while reduced-motion users still receive immediate text and completed messages remain unchanged#100884
  1108. 1108iOS and macOS users can preview a safe link's title and description inside chat before deciding whether to open it#101198
  1109. 1109Expanded link previews on iOS and macOS can now show a safe page thumbnail, with the existing text card retained when image loading fails#101387
  1110. 1110Finished iOS and macOS chat replies now typeset inline LaTeX formulas while streaming text, code, currency, and invalid math remain readable as plain text#101388
  1111. 1111iOS chat and macOS webchat users can search, pin, rename, archive, restore, and reopen sessions from the in-chat switcher instead of scrolling a simple recent list#101053
  1112. 1112Transcript export controls, chat actions, and export failure messages are now translated across 21 supported native app locales. 45f561a
  1113. 1113Supported non-English native apps now translate newer app information, support links, and message retry, delete, and waiting-to-send states. 82f5ac1
  1114. 1114Broader native app setup, chat, Talk, permission, connection, session, provider, and status text now uses the selected language across the language packs updated in this releaseSources: a39b07b, f8e1e0c, db27d2e, 28a8414, e8e96bf, 6ea407d, 0011a18, 8c5adbf, 019603d, d3d7282, 267898c, 55ed57a, c54dc67, fd0355d, 49726a5, 2ffeedf, #98043, beca2b1, 4078dc7, e7e98f6, 3020f78, 0c82908, 8a3935f, 3f289fd, 203a896, 6afef15. Thanks @yeager.
  1115. 1115New-chat and worktree-chat entry points now appear in the selected language across supported Android and Apple app locales. 24bca38
  1116. 1116Supported non-English native apps now cover more Gateway setup, session, provider, health, messaging, terminal, and device text without English gaps. 52f1e05
  1117. 1117Refreshed native language packs now cover workspace files, sharing actions, folder states, Android SMS guidance, message delivery states, and related branding. a9b0a9a
  1118. 1118Supported non-English native apps now translate the new Terminal destination, Gateway setup guidance, Back action, connection messages, and OpenClaw branding. e069cb2
  1119. 1119Native app onboarding and AI connection guidance now reflects Crestodian and the current setup flow across supported non-English localesSources: ad4809f, f0ecc16.
  1120. 1120Native app command search now translates loading, unavailable, retry, and no-result states across the languages updated in this releaseSources: 745d2d0, 7f7bec7, 35be1c8, 7db67ab, 4bc5766, 0672720, 2a8cd44, fd648fb, 00b0b40, a67990a, 7640f67, 15f4819, 4d1d720, d1d3a27, c2737d5, bd3263d, 127ce63, 0c960cd, e6c3ad9, 84c86f7, e7aea60.
  1121. 1121Native chat controls for jumping to the latest message or reply now use the selected language across the translations in this releaseSources: e31fa36, 375def8, aabe44f, 48c3f4b, 3db6fb9, a4b51e5, a60686d, 12e17ec, 6c4ac0c, bdc6258, a775f9f, a1f6acc, ee9f61d, f188c66, 2525078, ed5ccda, a6a4792, 0924bee, 0420aef, d23c4fd, 37f0067.
  1122. 1122Native prompts for starting work, checking status, using phone and voice controls, pairing, and returning to Chat now use the selected language across the translations in this releaseSources: dd050bc, db72ffd, 4997802, 2dc7bd1, 4381c29, 9eb1a05, 7838bc8, 4352eaf, 43fe5cc, 6bd1a4b, 531af42, 305715c, 8f9e163, 2abad57.
  1123. 1123Native app status and appearance choices now use the selected language across the translations in this releaseSources: 58d199b, c15348b, c047a3a, e191685, b1e173d, 50fecf8, 5211afe, 4c43cf5, fb394de, ba8c1fa, 7bee4f6, 77ab268, 2417d94, 9b6ef34, 9c4274f, 2671bcc, b21153b, 117e8e1, cc0d7e1, e6f3f54, dd64f66, 4c16e66, 3a8375c, 3e3b6d6, c356245, d506201.
  1124. 1124Native app license notices, acknowledgements, and unavailable-file explanations now use the selected language across the translations in this releaseSources: 34bf5a9, 068088c, a623ac7, 71374d3, a9b0de8, 8f495e2, 436dd39, f917e89, 2c8b97c, ace162b, e60cccf, 359ea4c, b7bc860, 49ea27e, 99cbc58, 204526a, 3821c36, 030d184, 24f639c, 499feb2, 591d099.
  1125. 1125Native photo-permission controls now explain limited, selected, and recent-photo access in the selected language across the translations in this releaseSources: c360f92, 4dd027e, 9cde1ca, 328fb70, 71e5fcc, b11d710, 55a2a9b, c4b40d0, 3a1b983, dea40a5, 4b1fab8, 44ca739, d36452c, a50a59e, 49b68e1, 122e4ba, 4086d35, 547a563, 538f28a, c5afa92, 32a986d.
  1126. 1126Native skill availability, Gateway setup, diagnostics, privacy, and access guidance now use the selected language across the translations in this releaseSources: fdcd5c0, 26f6735, 5220eff, bb7dbda, 952245b, edb1e74, f7bad57, 0602930, e779b8f, 0400be7, 851d0ad, 1e0dd95, 703e1ad, 1c93e50, 37c45f2, 8fe917b, da21e4b, f4f63b1, 3e4febb, a82cd35, 52323b6.
  1127. 1127Native Gateway connection, diagnostics, permissions, onboarding, Chat, and Talk guidance now uses the selected language across the translations in this releaseSources: 3b27bb4, e296d14, 5516775, 6ec4962, 291f2a4, 7e2d41b, 81bc96f, 574556c, 8bb44e6, ae09908, 42fc19d, 28bbb43, 6ff9185, 4be0be6, 0f1fbbe, d893a72, f5cb29b.
  1128. 1128Wake Words and Discovery Logs now use current, natural labels across supported non-English native app locales. de30d2f
  1129. 1129Supported non-English native apps now translate workspace file browsing and sharing, image preview failures, offline status, and custom Gateway header controls. 6b99fd9
  1130. 1130OpenClaw's mascot now uses the same float, blink, antenna, and claw animations across web, iOS, and Android surfaces while respecting reduced-motion preferences. 851156a
  1131. 1131New Android users now get a guided first-run path through setup-code or QR entry, Gateway pairing, node approval, permissions, recovery steps, and confirmed phone readiness before onboarding completes#98752 Thanks @jesse-merhi.
  1132. 1132Android users can open an agent-workspace shell from Settings &gtAndroid users can open an agent-workspace shell from Settings > Terminal, with clear connection guidance and Gateway credentials passed without placing the token in the URL when supported. fcd7eb6
  1133. 1133Android users can sideload the official signed `OpenClaw-AndroidAndroid users can sideload the official signed OpenClaw-Android.apk from a stable GitHub release and verify it with the published SHA-256 checksums. #101212
  1134. 1134Android node reconnects now point users from a failed devices approve attempt to the correct openclaw nodes approve <requestId> command, including a reminder to reuse connection flags#98115 Thanks @welfo-beo.
  1135. 1135Android SMS commands now clearly distinguish phone permission from the Gateway's separate opt-in, allowing read-only sms.search without also enabling sms.send#100993 Thanks @narcissus0702.
  1136. 1136Android notification forwarding now leaves WhatsApp, Telegram, Discord, and Signal messages with their dedicated channel sessions, preventing duplicate or wrong-conversation replies while other selected apps continue to follow forwarding rules#101170
  1137. 1137Android Canvas content can no longer navigate to device-local web services, while normal remote and Gateway-hosted pages continue to work#99874 Thanks @ly85206559.
  1138. 1138Android release builds no longer expose detailed `cameraAndroid release builds no longer expose detailed camera.clip settings, device data, temporary paths, and recording events in production logs. #99484 Thanks @nianjiuzst.
  1139. 1139Android Back navigation now returns users from Gateway or Talk settings, Sessions, and Providers to the Voice, Chat, or command-palette tab where they started#98914 Thanks @lokimorty.
  1140. 1140Android now presents evenly spaced bottom tabs and avoids the chat-cache startup crash that could block entry to the post-onboarding shell#100382 Thanks @iwhatsskill.
  1141. 1141Android's Home overview now uses more consistent card, Talk, and recent-session spacing for a calmer, easier-to-tap first screen#100059 Thanks @iwhatsskill.
  1142. 1142Android's command palette now keeps action and session rows visually aligned, with consistent icons, navigation spacing, and clean truncation for long labels#101072 Thanks @iwhatsskill.
  1143. 1143Android users can open a scheduled job to inspect its timing, payload, delivery state, recent results, errors, and exact ID#95107 Thanks @tosko4.
  1144. 1144The Android Files card now lets users browse the active agent workspace, preview text and images, and share output directly from their phone#100776
  1145. 1145Android users can now read bundled third-party and open-source license notices directly from Settings > Licenses#99299 Thanks @joshavant.
  1146. 1146Android's About screen now clearly identifies OpenClaw and provides direct links to the website, documentation, source repository, and Discord community#100994
  1147. 1147Android Chat now includes a New chat action and a / command browser that filters the current agent's advertised commands without dropping command arguments#98796 Thanks @iwhatsskill, @solvely-colin.
  1148. 1148Android Chat now lets users choose and verify the configured agent for new messages, with Chat, Talk mode, and the home canvas staying aligned to that selection#80422 Thanks @bcperry.
  1149. 1149Android chats now render links, lists, quotes, emphasis, code, and plain text consistently through the shared Markdown renderer#88899 Related #88014. Thanks @iman-sharif, @pluviobyte.
  1150. 1150Android chat now adds light- and dark-mode syntax highlighting to supported fenced code, making code-heavy replies easier to scan without delaying partial or oversized messages#100217
  1151. 1151Android chat now restores an active response with buffered text after reconnecting or reopening, and recovers missed event gaps without duplicating transcript rows#100384
  1152. 1152Android chat now keeps sent messages and active replies stable through reconnects, reconciling delayed history without duplicate turns or stale composer activity#100551
  1153. 1153Android chats now keep internal reasoning, tool results, and raw operational details out of both live conversations and reopened offline caches#100826 Thanks @iman-sharif.
  1154. 1154Android users can long-press a completed chat message to copy all text, select an excerpt, share it, or quote it in a reply without losing their current draft#100879 Thanks @bdhwan.
  1155. 1155Android chat users can preview a link's destination and summary before opening it, without messages triggering background lookups and with a clear unavailable state when inspection fails#100898
  1156. 1156Android's model picker now stays aligned with the active chat and agent, and a failed model change no longer sends the next message with the previous model#100985
  1157. 1157Android hides thinking controls for models that do not support configurable reasoning, prevents unsupported settings from breaking live or queued sends, and restores the user's preference on compatible models#101002
  1158. 1158Android users can search sessions by name, label, or key beyond the currently loaded Recent or Archived window, with cached active-session matches still available during a temporary Gateway outage#101102
  1159. 1159Android users with a physical keyboard can press Enter to send a chat message while modified Enter combinations remain available for multiline text#101321 Thanks @3ninyt3nin-creator.
  1160. 1160Android users can now see safe page thumbnails in expanded link previews, while bad or blocked images quietly leave the text preview intact#101396
  1161. 1161Android users can now archive a chat session and delete it from the Archived view even with the app's bounded operator permissions#101522
  1162. 1162Android users with a hardware keyboard can now send from the chat composer with Enter, while an unaccepted send still preserves the draft. de8db74 Thanks @vincentkoc
  1163. 1163Android users can switch the current chat's model from the composer, pin favorites, revisit recent choices, and return to the default without leaving the conversation; older pairings may need to be renewed#100798
  1164. 1164Android chat now renders top-level display LaTeX as readable equations while invalid or still-streaming math remains visible as text#101435
  1165. 1165Android's thread picker now prioritizes real conversations, hides internal setup and device sessions, and still makes valid older chats available through All#99557 Thanks @ly85206559.
  1166. 1166Returning to an already loaded Android chat no longer flashes a loading screen, and the Overview recent-session list stays deduplicated and steadier during refreshes#100966 Thanks @solvely-colin.
  1167. 1167Android Home's Recent Sessions section now keeps recently active rows in a stable order, collapses duplicates, and preserves labels and timestamps during partial live refreshes#101161 Thanks @solvely-colin.
  1168. 1168Android physical-keyboard users can press or hold Enter to send once without leaving a stray newline, while Shift+Enter and in-progress input-method composition keep working#101360 Thanks @3ninyt3nin-creator, @joshavant.
  1169. 1169Expanded Android link previews now keep thumbnail memory within a byte budget, reducing excessive memory retention during long chats#101560
  1170. 1170Android can now keep multiple Gateways paired and switch among them without repeating setup, while each Gateway retains its own credentials, chat state, queued messages, and removable local data#100947
  1171. 1171Android Gateway actions now stop promptly when their connection closes, while requests started after reconnect are not cancelled by old cleanup#98067 Thanks @nianjiuzst.
  1172. 1172Android connection recovery now identifies expired setup codes, stale credentials, and missing or invalid authentication with the appropriate next step#98094 Thanks @qingminglong.
  1173. 1173Android can reconnect to the same Gateway without erasing saved access when credential fields are blank, while endpoint and setup-code changes avoid carrying stale credentials silently#98277 Thanks @solvely-colin.
  1174. 1174Android now gives clearer TLS verification guidance for reachable remote and Tailnet Gateways and allows slow valid handshakes more time to show the trust prompt#98366 Related #98365. Thanks @joshavant.
  1175. 1175Android can now pair with local Gateways advertised by standard cleartext `Android can now pair with local Gateways advertised by standard cleartext .local names while continuing to reject unsafe remote or ambiguous cleartext addresses. #98439 Thanks @joshavant.
  1176. 1176Scanning a valid Gateway setup QR code on Android now starts pairing immediately and advances to recovery or approval instead of leaving users on setup#98483 Thanks @joshavant.
  1177. 1177Android Gateway setup now replaces a generic authentication warning with specific recovery labels for expired setup codes, missing or invalid credentials, stale saved authentication, and required device identity#98698 Related #98046. Thanks @ccaprani, @masatohoshino.
  1178. 1178Android gateway setup now gives specific recovery actions for expired codes, stale credentials, pending node approval, and terminal authentication failures#99414 Related #98045, #98046. Thanks @ccaprani.
  1179. 1179Android manual Gateway setup now defaults blank ports to 18789 for ordinary TLS and cleartext hosts while retaining port 443 for Tailscale MagicDNS#99865 Thanks @ly85206559.
  1180. 1180Saved Android Gateway sessions now reconnect promptly when validated internet access returns, without unnecessary retries during captive or partial network changes#100347 Thanks @ly85206559.
  1181. 1181Android Gateway settings now give connection details, setup fields, and helper text more stable space on phone-sized screens, reducing clipping and crowding#100363 Thanks @iwhatsskill.
  1182. 1182Android now isolates cached conversations and queued commands when users re-pair, sign out, or replace Gateway credentials, preventing a new identity from inheriting the previous one's data#100454
  1183. 1183Android onboarding now finishes after permission-triggered node approval instead of trapping users in a loop between the Permissions and approval screens#100959
  1184. 1184Android users can now connect to Gateways behind Cloudflare Access or another authenticating reverse proxy by saving the required credential headers in Advanced manual-connection settings#100765
  1185. 1185When Android Chat cannot reach the Gateway, users can open Gateway Settings or copy connection diagnostics directly from the blocked screen#94566 Thanks @tosko4.
  1186. 1186Android manual Gateway setup now accepts IPv6 hosts such as `:1` directly instead of rejecting an address that works only when entered as a bracketed WebSocket URL. #99107 Thanks @ly85206559.
  1187. 1187Android manual setup now accepts and preserves complete `ws//, wss://`, and HTTP Gateway addresses, including embedded ports, so private-LAN onboarding reaches the intended server. #99110 Related #87216. Thanks @cursoragent, @ly85206559, @ruben2000de.
  1188. 1188Android setup now rejects gateway URLs with unsupported IPv6 interface zones and directs users to an unscoped address or LAN hostname before saving#99570 Thanks @ly85206559.
  1189. 1189Android now preserves specific Gateway and A2UI error codes containing numbers, such as A2UI_HOST_UNAVAILABLE, instead of replacing them with a generic failure#99591 Thanks @ly85206559.
  1190. 1190Android Gateway settings now show both setup actions as full-width buttons, keeping Pair New Gateway readable and easy to tap#100090 Thanks @iwhatsskill.
  1191. 1191The Android app now respects a user's disconnect, connect, or gateway-switch choice during startup and reports final disconnect failures to fire-and-forget callers#101799
  1192. 1192Android users can record and send a voice note of up to three minutes from the chat composer without entering live Talk mode#101193
  1193. 1193Android background push-to-talk requests now return NODE_BACKGROUND_UNAVAILABLE instead of attempting a microphone start that the operating system may reject#98055 Thanks @nianjiuzst.
  1194. 1194Android now reports Realtime Talk and Dictation readiness separately, opens setup only for the mode that needs it, and keeps useful provider failure details visible#98269 Related #98268. Thanks @solvely-colin.
  1195. 1195Android Talk and Dictation now use a connected Bluetooth headset microphone for hands-free capture and fall back cleanly when it disconnects#99259 Related #96241. Thanks @gwtaylor.
  1196. 1196Android push-to-talk now takes exclusive microphone control during Talk Mode and resumes the correct realtime listener afterward, preventing duplicate capture#99986 Thanks @nianjiuzst.
  1197. 1197Android push-to-talk now cleans up backgrounded, cancelled, or retried captures without reopening the microphone or stopping a newer voice session, and overlapping requests return busy#100552 Thanks @xialonglee.
  1198. 1198Android users can now long-press an assistant reply and choose Listen, with visible playback status, tap-to-stop, and on-device speech fallback#100772
  1199. 1199Android Talk Mode now keeps push-to-talk busy until the active turn is safely handed off, preventing overlapping microphones, stale playback, or the wrong relay resuming#100786
  1200. 1200Android voice features now speak only chat events explicitly identified as assistant replies, preventing user, tool, system, or role-less text from being read aloud#99123 Thanks @ly85206559.
  1201. 1201Android Talk now applies supported directive values even when generated or dictated JSON uses different capitalization for keys such as Voice or Language_Code#99592 Thanks @ly85206559.
  1202. 1202Android Talk Mode now delivers agent-consult answers even when realtime completion events arrive out of order, preventing sessions from remaining stuck on Thinking#100049 Thanks @qingminglong.
  1203. 1203Android Voice and Talk setup text now truncates cleanly on narrow screens and at larger accessibility font sizes instead of appearing clipped#100060 Thanks @iwhatsskill, @solvely-colin.
  1204. 1204The Android Voice tab now gives Realtime Talk and Dictation text and controls enough room to remain readable on phones and at larger font sizes#100491 Thanks @iwhatsskill.
  1205. 1205Third-party Android builds can allow Gateway-requested location checks while the app is in the background by selecting Location > Always and granting Android's persistent location permission#100967 Thanks @ioridev.
  1206. 1206Android notification automations now queue accepted events during Gateway connection or reconnection and deliver them in order once the link is ready#92602 Related #79552. Thanks @ashishpatel26, @hectorrp13.
  1207. 1207Android one-shot camera captures now turn the camera and privacy indicator off promptly after success, failure, or cancellation#98040 Thanks @nianjiuzst.
  1208. 1208Android's selected-photos permission now counts as usable access, allowing photos.latest while clearly showing how to manage the limited selection#98059 Thanks @nianjiuzst.
  1209. 1209Android onboarding now marks Contacts and Calendar ready only after both read and write access are available, including when those permissions arrive in separate prompts#99158 Thanks @nianjiuzst.
  1210. 1210Android now reports Contacts and Calendar access as granted only when both reading and adding entries are authorized, preventing misleading setup results#99204 Thanks @nianjiuzst.
  1211. 1211The Android companion no longer forwards OpenClaw's own notifications back to the Gateway, even when older allowlists still include the app package#99568 Thanks @ly85206559.
  1212. 1212Android third-party onboarding now recognizes SMS access when send and read permissions are granted in separate prompts, while genuinely missing permissions remain unauthorized#99147 Thanks @nianjiuzst.
  1213. 1213Cancelled, timed-out, failed, or interrupted Android `cameraCancelled, timed-out, failed, or interrupted Android camera.clip requests now release the camera and remove unfinished temporary files before later camera commands run. #99153 Thanks @nianjiuzst.
  1214. 1214Android node commands now honor common boolean values such as yes, no, 1, and 0 for app filters and camera audio options#99873 Thanks @ly85206559.
  1215. 1215Tapping an Android notification created by `systemTapping an Android notification created by system.notify now brings OpenClaw to the foreground. #100888
  1216. 1216Android's "New chat in worktree" action is now translated across supported non-English locales instead of appearing with a missing resource#100805 Thanks @amknight.
  1217. 1217Android users in supported languages now see key Gateway setup, connection, trust, shell, and recovery prompts in their device language#97111 Thanks @vincentkoc.
  1218. 1218Indonesian Android strings ship under Android's recognized localeIndonesian Android strings ship under Android's recognized locale; the same prior-release work also prepared the 2026.6.11 Play version and store text. 3412318 Thanks @joshavant.
  1219. 1219Traditional Chinese users now see localized wording for common native app actions, permissions, connection messages, and mobile states. f0d2066
  1220. 1220Android now explains in the selected language how to keep a saved token or replace an existing Gateway setupSources: 32f3eb3, 6336762, eeb0682, ed72b86, e376f28, a6631fe, 283bd82, 6d5a1db, d3087fc, 8bab3f7, dfb7bc8, 7780e30, b109b88, c1b7bf2, dedb17c, 6f84c10, a8358e8, 2501ca3, 1b40eb9, d47308f, 3a2baef.
  1221. 1221Android pairing and connection failures now provide localized next steps for expired codes, credentials, approvals, and retriesSources: 48eae1b, f095eb9, 714c2b0, d2b5bb7, d2551bd, 6b91507, f1c4476, 5ef6fb4, e2e0312, 7fb70b2, d702f5c, 24e6b9f, 7cb41cc, a6040c3, 5e61da3, 18360ac, 17a1e3b, adafb56, 5b5fadb, 9b30570, d331a36.
  1222. 1222Android Gateway discovery, QR and manual setup, connection checks, approvals, and permission guidance now use the selected language across the translations in this releaseSources: 28062c8, 3d43858, ad74b32, 1b07620, 4fa4c9e, 1dd5230, 9db7ec5, e6f8788, e5cf67e, b52d988, cd3b4ee, c3bcb9f, 8af3aa0, c34e79e, c9c8f6c, 255e251, 0e98ba4, 0cc9927, 97955d9, ba449f2, 0e22e54, ae65251, d957f5a.
  1223. 1223Android now explains in the selected language when a scoped IPv6 address must be replaced with an unscoped address or LAN hostnameSources: 5793f73, 066e697, bf35947, 3385817, a0a5054, 66cb9a9, 3da73a7, df659ec, 57a3975, 141b2cf, b043adf, dcc4fa8, eade8f1, 72a8098, 355fa77, 8cc1786, a3ef37b, cb9ac50, cab8147, 7cc3cb0, ca258fb.
  1224. 1224Android license notices, acknowledgements, empty states, and open-license actions now use the selected language across the translations in this releaseSources: 4b8b60f, 3b16c41, c4966e8, 116e9db, 1617233, a598c97, 3b9e0c8, eebbf6c, 4c08ea4, 21be45c, b415072, 9eec24d, de23987, 898564e, 7af800b, a47ec8d, fac9e58, 61e4ef0, 399f9d6, 9069f69, 2e049f5.
  1225. 1225Android Talk, dictation, speech-provider setup, readiness, and failure guidance now use the selected language across the translations in this releaseSources: c785196, 9edb906, da67520, 88f13ca, e878efe, 662d127, 5002a0e, fe57718, ebcf8dc, 4e7ca8e, 9863ceb, 768da09, ff5d986, 005ebd1, 2824796, 4eaec93, f99fdc9, 555f601, d2af689, 81e92de, 8ed6c78.
  1226. 1226Android command search and New Chat labels now use the selected language across the translations in this releaseSources: b81c58b, 8929118, 1eee853, a5c9662, 9035729, 2e359d4, 91f4d0a, e785c4a, 2c5a076, 02250d9, bf23194, 603502f, a837a1a, 26df1fa, c926610, c312f9f, f4275fa, 69d4657, 3e66eb9, db5057e, 1fee4a5.
  1227. 1227Supported non-English Android builds now localize offline Gateway queue guidance and the Retry and Delete actions for text messages. 660d752
  1228. 1228Supported non-English Android builds now translate more cron inspection, delivery error, copy feedback, default-state, and agent request details. d83ee4c
  1229. 1229Android model organization, default-model, and pinning controls now use the selected languageSources: 41bea62, bdc98f4.
  1230. 1230Android link-preview controls and status messages now appear in the selected language across refreshed locales. 9997c53
  1231. 1231The Android background-location explanation, settings action, and Not Now choice now appear in the selected language when Always location mode is offered. 4c38d89
  1232. 1232Opening Control -&gtOpening Control -> Terminal on iOS now goes directly to the terminal without briefly showing the general Web UI login screen during connection. #100727
  1233. 1233iOS users can open Terminal directly from the Control hub, see a Gateway setup prompt when disconnected, and keep active shell sessions running through unrelated screen updates. 211e0d7
  1234. 1234The iOS Control, Chat, Talk, Agent, Settings, Gateway, and Overview screens now use clearer navigation, status cues, controls, and a compact expanding chat composer#98452 Thanks @joelnishanth.
  1235. 1235The iOS Control, Agents, and Settings screens are now easier to scan, with fewer duplicate destinations, more compact controls, standard navigation, and a direct Gateway shortcut from detail views#98811 Related #98803.
  1236. 1236Chat, Talk, Settings, navigation, and onboarding on iPhone and iPad now use more consistent native controls, appearance, and back behavior#99231 Related #99195. Thanks @marvkr.
  1237. 1237On iPad, selecting Overview, Chat, Talk, or another sidebar destination now leaves the current Settings detail and opens the requested screen#94991 Thanks @solvely-colin.
  1238. 1238The iOS app now opens to Chat for normal launches while preserving direct navigation to Control, Settings, Agent, Talk, and nested destinations#98353 Thanks @bsniznd.
  1239. 1239iOS Control, Talk, and Settings are easier to scan with clearer status emphasis, safer action styling, calmer idle visuals, and improved large-text support#98423 Related #98397.
  1240. 1240iOS connection, warning, and information text is now easier to read in light and dark modes, and Appearance settings accurately describe the selected behavior#98443 Related #98440.
  1241. 1241iOS users who open Gateway, Voice, or Notifications settings from another screen now return to the Chat, Talk, Agent, Control, or Approvals screen they came from#98898 Thanks @lokimorty.
  1242. 1242The iOS app now applies OpenClaw's palette consistently across Talk, settings, Gateway, privacy, usage, and workboard views while retaining accessible contrast#98930 Thanks @joelnishanth.
  1243. 1243iPhone users who open Chat from a Control detail can now return to that same Overview, Activity, Workboard, or Sessions screen without losing their place#99245 Thanks @solvely-colin.
  1244. 1244iOS users can now read OpenClaw's bundled third-party license acknowledgements from Settings > Licenses#99290 Thanks @joshavant.
  1245. 1245On iOS 26, affected Settings switches now respond when users tap anywhere on the labeled row, with accessibility labels and values preserved#99888 Thanks @ly85206559.
  1246. 1246Talk and Settings rows on iOS now use consistent title sizing and typography, making adjacent options easier to scan#100515
  1247. 1247The iOS About screen now presents OpenClaw branding, license information, and direct links to the website, documentation, GitHub repository, and Discord community#100531
  1248. 1248Equivalent rows in the iPhone Control and Settings tabs now use the same rounded icon treatment, making both lists easier to scan#98936 Related #98916. Thanks @sahilsatralkar.
  1249. 1249The iOS About screen now shows a concise app, device-family, and iOS summary without duplicated identity or a raw hardware identifier#98985 Related #98943. Thanks @sahilsatralkar.
  1250. 1250The iOS appearance setting now sits in the normal Settings list, shows the current System, Light, or Dark choice at a glance, and behaves consistently on iPad#99052 Related #98995. Thanks @sahilsatralkar.
  1251. 1251The iPhone Control destination list is now denser and easier to scan without changing navigation or status information#99468 Related #99439. Thanks @sahilsatralkar.
  1252. 1252Already-paired iPhone users now return to Chat, Talk, and Settings instead of being trapped in setup when older onboarding flags are stale#101481
  1253. 1253Images shared from iOS or through node `agentImages shared from iOS or through node agent.request now remain attached to the correct conversation turn after history reload, so later messages can still use them. #86936 Thanks @peterdsp.
  1254. 1254iPhone and iPad users can now browse an agent workspace, preview generated files, logs, and configuration, and share a file without returning to the host computer#100767
  1255. 1255Native iOS Chat now follows Larger Text and Dynamic Type settings for messages, the intro, and composer text with less clipping#97552 Thanks @jmcte.
  1256. 1256Native iOS Chat now gives the conversation more room, uses a compact composer that grows with longer drafts, and keeps attachment, Talk, and send controls comfortably tappable#98953 Related #98929.
  1257. 1257iOS Chat now keeps one final assistant reply per turn instead of briefly showing a duplicate that disappears after history refreshes#98117 Related #98116. Thanks @joshavant, @ooiuuii.
  1258. 1258iOS Chat now preserves intentional line breaks in assistant responses and other multiline messages without disrupting normal Markdown rendering#98304 Related #98028. Thanks @jabato01, @joshavant.
  1259. 1259The iOS chat experience now offers useful starting prompts, clearer pairing and setup actions, better agent placeholders, and steadier message ordering during refreshes#99243 Thanks @jcooley8.
  1260. 1260iOS chat now lets users browse, filter, and select available commands and skills from the composer instead of memorizing exact slash commands#99426 Thanks @solvely-colin, @viczhang6.
  1261. 1261iOS chat now provides tactile feedback for accepted sends and most completed or failed runs, though some abort paths may still omit or misclassify failure feedback#100416
  1262. 1262iOS users can export the current conversation as a named, readable Markdown file and save or send it through the system share sheet#100417
  1263. 1263Offline iOS messages now survive relaunch, remain tied to their original Gateway and conversation, and send once only when delivery can be confirmed, with clear uncertain-delivery status when it cannot#100942
  1264. 1264Tapping the iPhone status bar now leaves the chat at the top for reading older messages until the user chooses Jump to latest#100502
  1265. 1265Translated Gateway controls on iOS and approval actions on Apple Watch no longer fall back to English in supported locales#97112 Thanks @vincentkoc.
  1266. 1266iOS voice notes now stay with the intended chat and recover more reliably across offline queues, app recreation, uncertain sends, and competing microphone use#101236
  1267. 1267The iPhone app now presents a compact Talk control bar, a cleaner Appearance picker, and a properly aligned realtime-audio button beside the resting Chat composer#98736
  1268. 1268Apple Watch users can dictate a message and hear OpenClaw's final reply on the Watch, with separate silent-send, cancel, and stop controls#100283
  1269. 1269iOS users can record and send a voice note of up to three minutes from the chat composer, optionally add text, and see the recording's duration in chat#100946
  1270. 1270Paired iOS users can start native ElevenLabs Talk with a SecretRef-backed Gateway key without copying the credential into plaintext mobile configuration#98210 Related #98209. Thanks @joshavant, @ooiuuii.
  1271. 1271iOS Talk's Gateway Default now uses the configured Gateway speech provider, and stopping a reply prevents delayed audio from leaking into later turns#98376 Related #98153. Thanks @jraxworthy, @tony-ooo.
  1272. 1272OpenAI Realtime Talk on iPhone now uses native WebRTC by default, recovers continuous sessions from provider disconnects, and respects speaker, Bluetooth, and AirPlay output choices#98563 Thanks @pollybot13.
  1273. 1273The iOS Talk fallback banner now opens Voice & Talk settings directly instead of sending users to unrelated Gateway settings#98602 Related #98593. Thanks @pollybot13.
  1274. 1274Voice Wake on iOS can now pause while Talk, camera audio, or another feature uses the microphone and resume without crashing the app#99137 Thanks @pollybot13.
  1275. 1275Apple Watch pairing and companion status now refresh without restarting the iPhone app, while cold-launch actions wait for readiness or return a clear WATCH_UNAVAILABLE error#100732
  1276. 1276iPhone users can now choose Listen on an assistant reply, follow preparation and playback status, stop at any time, and fall back to on-device speech when needed#100771
  1277. 1277Apple Watch quick replies now survive an unavailable iPhone and reconnect later to the intended Gateway without being lost, duplicated, or misrouted#100372 Thanks @nianjiuzst.
  1278. 1278OpenClaw now uses consistent branded typography throughout its iOS, Watch, and Live Activity interfaces while retaining Dynamic Type and accessibility support#99246 Thanks @joelnishanth, @joshavant.
  1279. 1279iOS users can pair multiple Gateways once and switch among them while keeping credentials, trust, chats, preferences, device access, and push registration attached to the correct Gateway#100948
  1280. 1280iPhone users pairing with a LAN Gateway now stay authenticated after the one-time bootstrap so Chat and the node connection do not immediately disconnect#98066 Related #98064. Thanks @ooiuuii.
  1281. 1281After scanning an iOS pairing QR code, users now move to a live connection-progress screen instead of returning to Welcome while pairing continues invisibly#98302 Related #98297. Thanks @joelnishanth.
  1282. 1282iOS now explains secure Gateway connection and certificate-verification failures precisely and reliably presents the fingerprint trust prompt for first-time HTTPS connections#98429 Thanks @joshavant.
  1283. 1283New iPhone users now get clearer QR, setup-code, and manual Gateway choices, better nearby and connection status, and a direct handoff to Chat after connecting#98868 Thanks @solvely-colin, @thats2easyyy.
  1284. 1284iOS users can correct gateway details after a failed manual setup and retry immediately with the values currently on screen#99220 Related #99219. Thanks @abdullahtas0.
  1285. 1285iOS gateway QR pairing now stays open through trust and approval, avoids scanner crashes, and keeps credentials and pending actions with the correct gateway during switches#99572 Thanks @pollybot13.
  1286. 1286Repeated iOS Gateway setup links now update the visible settings screen with the newest connection instead of being consumed by a hidden view or replaying stale details#100328
  1287. 1287The iOS app can now connect through Cloudflare Access, Basic authentication, and similar proxies by storing per-Gateway credential headers for the next reconnect#100768
  1288. 1288iOS pairing codes can now advertise both local and Tailnet Gateway routes, allowing the phone to save the first reachable address when it is away from the private LAN#100317
  1289. 1289iOS Gateway connection errors now appear as one dismissible toast that returns for a later failure and visibly reacts instead of stacking when the same problem repeats#98856 Thanks @lokimorty.
  1290. 1290The iOS QR setup scanner is less likely to crash or become unstable when users open, cancel, or close the camera during onboarding#101235 Thanks @joshavant, @solvely-colin.
  1291. 1291iOS location settings now explain Off, While Using, Always, Precise Location, restrictions, and permission mismatches in the selected language across the translations in this releaseSources: 3542585, 261d79a, ef1474d, cc1d61b, 2a1e118, 748bfee, e0b2dda, f371a2f, ee00cc7, 27f9ae0, 51a07ae, ba9d167, 576169e, 10500a6, a344252, d7d280f, cb2547f, 2191c2e, c63e9f9, 4b1e0de, 525c4c7.
  1292. 1292iOS location settings now show the permission that is actually in effect, including Precise Location and mismatches between OpenClaw's selected mode and the iOS grant#99247 Thanks @pollybot13.
  1293. 1293iOS users can now add contacts and search affected records without crashing the app or disconnecting the node#99475 Thanks @abdullahtas0.
  1294. 1294iOS Calendar, Reminders, and Contacts commands now return an immediate permission-required result instead of opening a prompt that leaves the agent request waiting#99477 Thanks @nianjiuzst.
  1295. 1295Choosing While Using for location access on iOS now remains selected after approval and after the app is relaunched#100512
  1296. 1296The iOS `screenThe iOS screen.record command now finishes more reliably with a nonempty MP4 instead of crashing the app and disconnecting the node as recording stops. #101550 Thanks @tony-ooo.
  1297. 1297The iOS app now recovers when a location permission prompt returns without a clear decision instead of waiting indefinitely. 75c8753 Thanks @vincentkoc
  1298. 1298Cancelling or interrupting an iOS `screenCancelling or interrupting an iOS screen.record request now stops the system recorder instead of letting capture continue after the tool call fails. #99155 Thanks @nianjiuzst.
  1299. 1299iOS now recognizes Limited Photos access as usable, offers in-app controls for requesting or managing the grant, and avoids interrupting gateway requests with a surprise prompt#99350 Related #99046. Thanks @tony-ooo.
  1300. 1300The iOS camera permission prompt now clearly connects access to Gateway setup and assistant-requested photo, video, document, screen, or workspace capture. e77994e Thanks @joshavant
  1301. 1301Localized macOS builds now translate the new GitHub link label, including its accessibility-facing text, instead of falling back to English. 8be1d36
  1302. 1302macOS onboarding now translates local Gateway installation, checks, repairs, retries, paused setup, and resume guidance across the languages updated in this releaseSources: 7a717b7, 85d31e1, 27778a7, cffc6ad, ab0d604, 972d394, edbbdf6, 863a054, ef5650f, 5f2e51f, 5769416, a3aa917, 2f7bd01, c54a6f3, 9c3ffc5, 469e707, d066a81, 72a3b71, 63aa909, b68e2e7.
  1303. 1303macOS users can run Codex Computer Use desktop controls through managed installation without a manual appServer.command, and an outdated Codex Desktop app-server no longer blocks a supported plugin-local binary#96730 Thanks @bdjben.
  1304. 1304New Mac users can now open the app and reach a working local agent without Terminal, Homebrew, administrator access, or an extra approval prompt for the app's own node#99767 Related #99764.
  1305. 1305macOS onboarding now verifies the chosen AI connection before first chat, presents clearer local and remote setup choices, and offers friendly recovery or a verified manual API-key path when authentication fails#100288
  1306. 1306macOS onboarding now offers the Gateway's supported text-inference provider catalog instead of only Anthropic, OpenAI, and Google, and tests credentials before saving them#101132
  1307. 1307First-run macOS setup now recognizes a successfully saved Codex login and is less likely to finish with a stale Gateway or bundled-skills warning#101218
  1308. 1308After openclaw doctor --fix archives a legacy sidecar, the macOS app no longer recreates it or triggers the same migration conflict warning on every command or Gateway start#99039 Related #98917. Thanks @momothemage, @p51moustache.
  1309. 1309Repeated pairing repair attempts now produce one usable macOS approval prompt per device instead of stacking stale alerts that cannot complete approval#100976
  1310. 1310On macOS, an explicit OPENCLAW_STATE_DIR now stays isolated from the machine's existing App Group pairing identity and device tokens#101779
  1311. 1311macOS remote mode can now connect through explicitly selected managed SSH aliases and recover app-owned tunnels when SSH multiplexing or backgrounding is enabled#99661
  1312. 1312Finder-launched macOS sessions can now use SSH aliases backed by common user-installed ProxyCommand helpers without losing agent state or failing Gateway readiness checks#100214
  1313. 1313Multiple macOS app instances now preserve shared SSH tunnel tracking and clean up stale processes more reliably, reducing port conflicts after a crash#100601
  1314. 1314The macOS Dashboard now follows a restarted remote SSH tunnel to its new local port automatically and keeps authentication tokens out of logged URLs#100488
  1315. 1315After a macOS crash or force quit, OpenClaw now reclaims confirmed orphaned remote-mode SSH tunnels so relaunches can reuse the preferred local Gateway port#100489
  1316. 1316The macOS menu-bar app now uses fewer idle CPU wakeups and less repeated configuration and permission work, reducing background battery use without changing active status behavior#100463
  1317. 1317Long-running `systemLong-running system.run commands on the macOS app node no longer make the node appear offline or block unrelated Gateway traffic. #100842 Thanks @lvan185, @vincentkoc.
  1318. 1318The macOS app no longer mistakes a valid launchd-managed local Gateway for an unexpected listener and terminates active assistant or channel work#100867 Thanks @lsr911, @vincentkoc.
  1319. 1319The macOS app now keeps the same paired device and node identity across upgrades, restarts, and Gateway reconnects instead of repeatedly asking for approval or creating stale duplicates#101105 Thanks @yetval.
  1320. 1320The Mac app now shows the animated OpenClaw mascot in onboarding and About, while Reduce Motion keeps it still. f052a2f
  1321. 1321The macOS onboarding and About mascot now more closely matches openclawThe macOS onboarding and About mascot now more closely matches openclaw.ai with theme-aware colors, glow, hover scaling, and smoother motion that keeps its antennae visible. 05c9dcc
  1322. 1322The Mac About screen now links directly to the OpenClaw website, documentation, GitHub project, and Discord community, matching the other native apps. 6e7ef63
  1323. 1323Opening OpenClaw again from the macOS Dock or Finder now brings up the dashboard or its failure window even when the menu-bar app is already running#97637 Thanks @solvely-colin.
  1324. 1324openclaw tui now finds the custom port of an active local Gateway automatically, so users usually do not need to repeat its URL with --url#73338 Thanks @haishmg, @vincentkoc.
  1325. 1325Gateway-backed and local TUI sessions now display assistant text as it arrives instead of appearing quiet until the final response#83000 Thanks @flashosophy.
  1326. 1326The TUI now explains when repeated invalid tool arguments abort a run, giving users a useful correction clue without exposing sensitive inputs#91002 Thanks @taerlandsen, @wsyjh8.
  1327. 1327Typing indicators now remain active during long Codex model, tool, command, recovery, and queued follow-up work instead of making the reply appear idle#95844 Thanks @jalehman.
  1328. 1328Shortened exec and bash summaries now keep emoji and other supplementary characters intact around the ellipsis instead of displaying a broken replacement glyph#96963 Thanks @bartok9, @ly-wang19, @vincentkoc.
  1329. 1329Replies triggered through Telegram or another external channel now appear only once in the terminal UI after history refreshes, while resets, session switches, delayed events, and in-progress recovery continue normally#96980 Thanks @xialonglee.
  1330. 1330Long assistant and provider errors now end cleanly when emoji or rare Unicode characters land near the display limit#97289 Thanks @zenglingbiao.
  1331. 1331The TUI now directs users to the pending device or scope-upgrade approval command instead of incorrectly sending them through chat-DM pairing#98144 Thanks @romneyda.
  1332. 1332Embedded and local TUI sessions now contain event-consumer errors instead of terminating the terminal#100117 Thanks @cxbasdev.
  1333. 1333TUI users can now submit prompts while an agent is working and receive the configured followup, collect, or interrupt behavior, with Esc and /stop canceling only the intended work#100123 Thanks @kevinlp, @sebtardif.
  1334. 1334TUI /new now performs a real session transition with the expected lifecycle hooks and prevents a new session from racing an active turn#100241 Thanks @caopulan.
  1335. 1335Terminal Hatch onboarding and other TUI connections now show starting up until session loading finishes, with accurate running indicators after reconnects#93999 Thanks @ml12580.
  1336. 1336Repeated submits while the TUI agent is busy now update one warning instead of flooding the conversation with duplicate notices#99879 Thanks @vincentkoc.
  1337. 1337openclaw tui --local now explains when a known slash command requires the Gateway instead of sending that command to the model as an unwanted prompt#100188 Thanks @goslingmanagment.
  1338. 1338Workspace skill approvals started in the TUI now appear in that terminal, so users can review and unblock the run without switching to Telegram#100251 Thanks @vincentkoc.
  1339. 1339The terminal UI now stays open and shows a safe, useful error when a local shell command, slash command, or message submission fails#100340 Thanks @cxbasdev.
  1340. 1340Codex CLI session lists now shorten long last-message previews without splitting emoji or similar characters into broken text#96582 Thanks @llagy007, @weeli-009.
  1341. 1341Users can turn a conversation, file path, URL, or pasted note into a reviewable Skill Workshop proposal with one message instead of starting from a blank draft#100442
  1342. 1342Long-running agents can automatically retire unused Skill Workshop skills from future context, pin important ones, restore archives, and surface possible overlaps without deleting the underlying skills#101214
  1343. 1343The opt-in Logbook lets users review a model-organized workday timeline, generate standups, and ask questions about captured activity, with owner-only local storage and configurable retention#99930
  1344. 1344Skill archive validation and upload hashing errors now identify the missing or unreadable file while preserving the original filesystem error#101085 Thanks @cxbasdev, @vincentkoc.
  1345. 1345The bundled xurl skill now shows a working Node/npm installation path, and the github skill no longer advertises an unsupported Linux apt option#102158 Thanks @not-stbenjam.
  1346. 1346Owner-operated native Codex agents can now use selected apps already connected to the operator's Codex account, with a bounded per-thread allowlist and existing approval controls preserved#100973 Thanks @pash-openai.
  1347. 1347Updated integration runtimes keep Codex, ACP, Copilot, Telegram, and diff rendering aligned with compatible upstream behavior, while reconnect recovery no longer floods operator logs with duplicate messages#100027
  1348. 1348Configured and accessible native Codex plugin apps now remain available when a new OpenClaw thread starts during an app-inventory and activation-state transition instead of disappearing silently#96872 Thanks @kevinslin.
  1349. 1349Changes made by plugin hooks now reach agent and child-run context, including replacements or removals made by agent:bootstrap#97281 Thanks @outdog-hwh.
  1350. 1350Embedded context-engine plugins now see the current turn in the transcript during afterTurn, preventing missing first messages and duplicate imports#97342 Thanks @gorkem2020, @iwhatsskill, @sgh6688, @udjin79.
  1351. 1351Windows can now load valid inbound media when configured roots and runtime file paths differ only in letter casing#97630 Thanks @vectorpeak.
  1352. 1352Plugins can now react when a new DM pairing request is created, enabling owner alerts, audit records, tickets, and approval integrations without polling#97733 Thanks @clawsean, @omarshahine, @trupe-rs.
  1353. 1353Provider plugins that mask text now restore intended values inside tool-call inputs before messages, file operations, and other external actions run#97769 Related #97761. Thanks @get-viti, @zoowh.
  1354. 1354Plugin and media workflows now handle malformed or truncated ffprobe output without crashing while continuing to read valid video dimensions normally#98613 Thanks @pick-cat.
  1355. 1355Ordinary Lobster run and resume approvals no longer fail TaskFlow-only validation simply because unused default flow fields were present#102036 Thanks @arthurnie, @lilan0125, @vincentkoc.
  1356. 1356Operators can run openclaw plugins marketplace refresh to verify and save a hosted feed, enforce a SHA-256 match, and see whether live, saved, or bundled data was used#96155 Thanks @giodl73-repo.
  1357. 1357openclaw plugins init can now scaffold a model-provider plugin with authentication, model setup, tests, packaging, validation, and ClawHub publishing structure#94352 Thanks @patrick-erichsen.
  1358. 1358Existing plugin discovery keeps the same bundled official catalog while gaining a versioned, fail-closed fallback format for the hosted marketplace work#95846 Thanks @giodl73-repo.
  1359. 1359ClawHub marketplace reads now fail back to OpenClaw's bundled plugin catalog when hosted data is unsafe or unusable, providing a guarded base for the new marketplace workflow#95868 Thanks @giodl73-repo.
  1360. 1360A hosted marketplace can keep serving its last verified catalog when the feed is unchanged or briefly unavailable, without trusting stale or invalid saved data#95877 Thanks @giodl73-repo.
  1361. 1361The latest verified hosted marketplace catalog can survive a restart and remain available through unchanged responses or temporary feed failures, with persistence still optional#95964 Thanks @giodl73-repo.
  1362. 1362Hosted marketplace entries become installable only when they match approved local sources and trusted ClawHub packages, preventing unknown or untrusted choices from slipping into installation#95969 Thanks @giodl73-repo.
  1363. 1363Administrators can configure named hosted marketplace feeds and the trusted local package sources those feeds may reference, while unsupported trust settings are rejected#95981 Thanks @giodl73-repo.
  1364. 1364The new openclaw plugins marketplace entries command lists available hosted plugins, versions, and install choices while showing whether results came from live, saved, or bundled data#96158 Thanks @giodl73-repo.
  1365. 1365Marketplace diagnostics now show whether refresh and entries commands used a hosted feed, a saved snapshot, or a fallback without logging feed secrets#96194 Thanks @giodl73-repo.
  1366. 1366Plugin authors can now import shared textResult and jsonResult helpers from openclaw/plugin-sdk/tool-results instead of recreating common response shapes#99740 Thanks @romneyda.
  1367. 1367Plugin authors now have a shared formatByteSize helper for consistent byte labels, while existing labels across OpenClaw remain unchanged#99768 Thanks @romneyda.
  1368. 1368Migration agentDir values beginning with ~ now resolve against OpenClaw's effective home#99901
  1369. 1369Starting QR login without a required official channel plugin now returns the exact installation command or openclaw doctor --fix instead of only saying the provider is unavailable#90517 Related #83277. Thanks @carol-iung, @tuaran.
  1370. 1370Plugin update failures now report the real npm metadata or registry problem instead of disguising it as an unsupported package specification#96143 Thanks @brokemac79, @romneyda, @slideshow-dingo.
  1371. 1371Operators can install a pinned older ClawHub plugin when that version is compatible with their OpenClaw deployment, without the latest release's requirements incorrectly blocking it; incompatible or unverifiable versions remain blocked#96506 Thanks @isaiahstapleton.
  1372. 1372openclaw plugins update --all now realigns trusted official plugins with the current stable or beta catalog after a core upgrade, without manual force installs or overwriting intentional targeted pins#96831 Thanks @ooiuuii, @velvet-shark.
  1373. 1373`openclaw plugins update &ltOpenclaw plugins update <id> --dry-run now tells operators when a newer default release exists even if the installed plugin is pinned exactly. #97282 Thanks @yungchentang.
  1374. 1374Windows plugin updates no longer create managed paths so long that official Codex-backed agents fail before they can start and reply#97488 Thanks @ooiuuii.
  1375. 1375openclaw update now accepts valid bundle-format marketplace and ClawHub plugins without package.json, preventing plugin sync from aborting and leaving the Gateway stopped#98010 Related #97985. Thanks @herove, @lilan0125.
  1376. 1376openclaw/memory-lancedb can now install and update under normal npm dependency resolution, keeping LanceDB-backed memory active without version pinning or bypass flags#99118 Related #90295. Thanks @allenhurff, @joshavant.
  1377. 1377Installing a managed npm plugin no longer makes workspace plugins from plugins.load.paths disappear after startup or restart#99196 Thanks @leonidaslux.
  1378. 1378Git-backed plugin installs and updates now work when `~/Git-backed plugin installs and updates now work when ~/.openclaw and the system temp directory are on different filesystems, without a TMPDIR workaround. #99896 Thanks @bartok9, @carelvanheerden, @vincentkoc.
  1379. 1379Extended-stable users can install, repair, and update eligible official plugins at the exact OpenClaw core version instead of drifting onto the regular stable line#100448 Thanks @kevinslin.
  1380. 1380openclaw update no longer retries a plugin after successfully moving it to ClawHub, preventing a redundant transient failure from disabling the migrated plugin. 3ce26d6 Thanks @vincentkoc
  1381. 1381openclaw doctor can continue legacy dedupe migration when a retired cache file contains malformed JSON instead of stopping with a parsing error#98125 Thanks @pick-cat.
  1382. 1382Plugin install and update failures now show whether npm exited, was killed, or timed out instead of presenting a blank error that makes valid packages look invalid#98497 Thanks @sanjays2402, @vincentkoc.
  1383. 1383Failed plugin installations now show the useful plugin error without adding a false Also not a valid hook pack diagnosis, while genuine hook-pack failures remain visible#100554 Thanks @vincentkoc.
  1384. 1384Declared plugin tools now remain callable in subagent sessions after plugin registry changes, avoiding repeated plugin tool runtime missing failures and Gateway restarts#82562 Thanks @luoyanglang, @vincentkoc.
  1385. 1385Plugin metadata cache hits no longer flood diagnostics with repeated full-scan entries, leaving smaller timelines where real scans are easier to identify#86796 Thanks @galiniliev, @vincentkoc.
  1386. 1386Plugin loading no longer evaluates OpenClaw's own package code twice, reducing startup work and avoiding duplicate module, class, singleton, or registry identities in one process#88384 Thanks @vincentkoc.
  1387. 1387openclaw plugins inspect now shows the bundled document-extract plugin's PDF extractor as an available capability instead of reporting none#91597 Thanks @xydt-tanshanshan.
  1388. 1388Configured context-engine plugins such as lossless-claw now stay active after discovery instead of being silently replaced by the built-in legacy engine#96357 Thanks @vincentkoc.
  1389. 1389Gateway startup now reports configured channels that failed to load, so operators can fix plugin trust, enablement, or installation before messages go missing#96397 Thanks @849261680.
  1390. 1390Plugin-heavy startup and configuration checks, especially on Windows, now repeat fewer package-path lookups while rebuilding installed-plugin fingerprints, making those paths more responsive#96710 Thanks @211-lee, @sheyanmin, @vincentkoc.
  1391. 1391/status plugins now labels a plugin as loaded only when it is actually running, while still showing healthy installed inventory#97479 Thanks @masatohoshino.
  1392. 1392Raising a running Gateway's log level to debug now immediately enables Mattermost, Matrix, Microsoft Teams, IRC, Nextcloud Talk, and other plugin diagnostics without a restart#97617 Thanks @amknight, @vincentkoc.
  1393. 1393Detailed /status plugins now flags a plugin that was configured to run but did not load, separating runtime drift from ordinary inactive inventory#97878 Thanks @masatohoshino.
  1394. 1394Plugin loading now honors operator-configured Jiti native-module exceptions while retaining protection against duplicate OpenClaw package evaluation#100344
  1395. 1395Bundled channel setup plugins now load correctly through current-release symlinks and mixed source/dist layouts without false outside-package warnings#100758
  1396. 1396Source checkouts with a partial bundled plugin tree now retain complete built-in metadata for plugin health checks and provider endpoint discovery. 26c0285 Thanks @vincentkoc
  1397. 1397The GitHub Copilot plugin no longer breaks openclaw plugins list or openclaw status during metadata-only loading before full runtime state is available#95229 Related #94516. Thanks @cuihaijun, @sunlit-deng.
  1398. 1398/status plugins now groups disabled plugins by reason, including allowlist, denylist, default, and override decisions, without changing activation behavior#99598 Thanks @masatohoshino.
  1399. 1399Bundled channel runtime and setup plugins now load from valid source-only registry roots in mixed source/dist checkouts instead of silently disappearing#100737
  1400. 1400Duplicate plugin-request scopes now normalize consistently, and genuine plugin scan access failures are surfaced#99932
  1401. 1401Official OpenClaw container images are now available from Docker Hub as well as GHCR, reducing reliance on unofficial mirrors#97122 Thanks @vincentkoc.
  1402. 1402Docker users now get a more complete bundled AI runtime, reducing startup and runtime failures caused by package links removed during image trimming. 57ca1b0 Thanks @vincentkoc
  1403. 1403Affected npm installations can once again start the Gateway and produce replies because speech now loads only through its supported package-backed TTS path#89899 Thanks @zhangguiping-xydt.
  1404. 1404OpenClaw npm packages are now about 3OpenClaw npm packages are now about 3.18 MB smaller unpacked and 371 KB smaller compressed, with plugin SDK entrypoints and runtime behavior unchanged. #98758 Related #98757. Thanks @romneyda.
  1405. 1405Source and macOS package builds no longer fail when the tsdown configuration is loaded from a temporary directory that cannot resolve the runtime package#100499
  1406. 1406Global npm upgrades can continue as OpenClaw's packaged files grow without hitting InstalledDistScanLimitError, while runaway scans remain bounded#101206
  1407. 1407Source builds now work on supported NodeSource builds now work on supported Node.js distributions without native TypeScript stripping, avoiding a late failure tied to --experimental-strip-types. #91262 Thanks @smoe, @vincentkoc.
  1408. 1408openclaw onboard now explains up front what setup covers, why full onboarding can take longer, and which optional steps can be postponed#97482 Thanks @ly85206559.
  1409. 1409Crestodian on Claude Code or Gemini CLI can now hold multi-turn setup conversations, inspect state, request exact approval for changes, and verify writes instead of falling back immediately to a single-turn planner#100029
  1410. 1410Crestodian setup and repair chats no longer destabilize the local TUI when a terminal event consumer fails during response delivery#100341 Thanks @cxbasdev, @vincentkoc.
  1411. 1411Crestodian now distinguishes ordinary questions from operational requests, accepts natural approval phrases, clears stale proposals, and keeps sensitive configuration out of the conversation model#100656
  1412. 1412Fresh git installs now lead users through setup, or give the exact command to finish later, before missing configuration or Gateway authentication can break first use#101901 Thanks @fuller-stack-dev.
  1413. 1413Setup now checks the configured custom agent or auth directory for credentials instead of reporting the wrong bootstrap state from a default location. 0fd69dc Thanks @vincentkoc
  1414. 1414openclaw config now recommends a Gateway restart only when the changed settings require one, so hot-loadable agent, model, and provider edits no longer prompt unnecessary restarts#80823 Thanks @kiranmagic7.
  1415. 1415Removing a visible built-in model alias now explains that the alias is automatic and shows how to shadow it, while genuinely absent aliases still report as not found#81641 Thanks @scientificprogrammer, @vincentkoc.
  1416. 1416openclaw config unset now explains when a visible value is an inherited runtime default that is not stored in the user's config, avoiding an unproductive loop between config get and config unset while leaving failed attempts unchanged#96557 Thanks @moeghashim.
  1417. 1417Configuration and plugin-schema validation hints now show clear allowed values instead of the misleading literal label undefined#99045 Thanks @lzyyzznl.
  1418. 1418Valid `openclawValid openclaw.json files with a BOM, PowerShell formatting, or deep indentation can now save authentication, model, repair, and other configuration changes without manual reformatting. #100591 Thanks @vincentkoc.
  1419. 1419Upgrades from the legacy config-health store no longer repeat a permanent conflict warning, and existing recovery backups remain available without overwriting newer observations#99728 Related #99280. Thanks @ccbridle, @jalehman, @joshavant.
  1420. 1420Repeated configuration warnings are now suppressed between meaningful recurrences, keeping long-running Gateway logs readable without hiding new diagnostics#100569 Thanks @vincentkoc.
  1421. 1421Gateway settings marked as no-restart now take effect in live and heartbeat-driven turns without requiring a manual restart#100586 Thanks @obviyus, @sedrak-hovhannisyan.
  1422. 1422Gateway `configGateway config.patch now accepts unrelated configuration updates when a bundled provider uses its default endpoint, without saving empty runtime-only provider fields. #98396 Related #98270. Thanks @momothemage, @weltmaister.
  1423. 1423Gateway configuration updates now reject missing redacted values for keys such as toString or constructor instead of restoring an inherited JavaScript function#99152 Thanks @zenglingbiao.
  1424. 1424Manual Gateway setup now rejects port entries such as 1e3 or 0x1000 instead of silently saving a different port, while valid decimal ports remain unchanged#98689 Related #98681. Thanks @qingminglong.
  1425. 1425openclaw doctor now warns when QMD session search is enabled without transcript export and provides commands and documentation to correct the missing recall setup#80947 Thanks @anyech.
  1426. 1426openclaw doctor now gives a missing-transcript preview command that actually shows the entries eligible for removal before users choose to enforce cleanup#83630 Thanks @yuanhanzhong.
  1427. 1427openclaw doctor now evaluates the default agent's actual per-agent bootstrap limits, producing accurate truncation warnings and remediation guidance#84424 Thanks @kasangyong, @vincentkoc.
  1428. 1428Gateway-managed skill checks can now find commands installed through pnpm 11 and common npm-global layouts, reducing false missing-tool warnings and unnecessary reinstalls#85238 Thanks @shbernal, @vincentkoc.
  1429. 1429openclaw doctor on Windows now detects supported Chrome versions accurately instead of warning that a working installation could not be identified#87937 Thanks @mukundakatta.
  1430. 1430openclaw doctor no longer aborts when a configured agent workspace has not been created yet, while real file operations still enforce workspace boundaries#89226 Thanks @sasan1200, @shifengwang333-ai.
  1431. 1431Gateway status, Doctor, and onboarding diagnostics now read large logs within fixed bounds and surface recent useful failures instead of stale noise#99407 Thanks @sunlit-deng.
  1432. 1432Terminal notes, Doctor output, and diagnostics now wrap long runs of CJK, full-width, or emoji characters within the requested width instead of spilling across columns#96746 Thanks @ly-wang19.
  1433. 1433Default doctor --lint results now focus on actionable configuration and runtime problems, with optional backup and memory advice available only when requested#99249 Thanks @giodl73-repo.
  1434. 1434openclaw doctor --fix now completes successfully in locked-down environments when only shell-completion installation is blocked, while still reporting genuine write failures#99540 Related #99237. Thanks @hunglp6d, @rballiance.
  1435. 1435doctor --lint --all can now explain the path or permission that would block a configuration repair before operators run doctor --fix#100093 Thanks @giodl73-repo.
  1436. 1436openclaw health now warns when gateway configuration hot reload has stopped, so operators know a restart is needed instead of unknowingly running stale settings#99267 Thanks @masatohoshino, @vincentkoc.
  1437. 1437Operators can inspect stale session write locks with openclaw doctor --lint --json --only core/doctor/session-locks and preview which locks a repair would remove or preserve#84366 Thanks @giodl73-repo.
  1438. 1438Optional Doctor lint can now report missing, unsafe, unwritable, cloud-synced, removable, volatile, or incomplete OpenClaw state storage with paths and repair guidance#95979 Thanks @giodl73-repo.
  1439. 1439An opt-in Doctor lint check now explains which configured plugin installation is broken and previews the repair before operators run the existing fix workflow#96171 Thanks @giodl73-repo.
  1440. 1440Operators can run openclaw doctor --lint --all to include every opt-in diagnostic check without changing the behavior of existing doctor --lint automation#96471 Thanks @giodl73-repo.
  1441. 1441Operators can run openclaw doctor --lint --only core/doctor/gateway-health, --only core/doctor/gateway-daemon, or --all for structured, credential-safe warnings about Gateway reachability and local service health without changing service state#97075 Thanks @giodl73-repo.
  1442. 1442Operators can use the focused auth-profile Doctor lint check to find expired, missing, malformed, cooled-down, disabled, or legacy credentials with structured repair guidance#97125 Thanks @giodl73-repo.
  1443. 1443A focused memory-search Doctor lint check now reports provider, credential, backend, and QMD setup problems with structured paths and fixes#97137 Thanks @giodl73-repo.
  1444. 1444The workspace-status Doctor lint check now reports plugin drift, compatibility, loading diagnostics, and recoverable TaskFlow state in machine-readable form#97358 Thanks @giodl73-repo.
  1445. 1445A focused device-pairing Doctor lint check now provides structured warnings and repair guidance for pending requests, stale authentication, missing scopes, and unreadable stores#97366 Thanks @giodl73-repo.
  1446. 1446Operators can request a structured Doctor lint check for configured channels whose backing plugins are blocked, including the unmet requirement and suggested fix#97496 Thanks @giodl73-repo.
  1447. 1447A focused tool-result-cap Doctor lint check now identifies settings below model-aware defaults or above the runtime ceiling with actionable paths#97500 Thanks @giodl73-repo.
  1448. 1448Linux operators can use the systemd-linger Doctor lint check to learn when logout may stop the Gateway and get the exact loginctl enable-linger remedy#97514 Thanks @giodl73-repo.
  1449. 1449Doctor lint can now identify legacy fenced `HEARTBEATDoctor lint can now identify legacy fenced HEARTBEAT.md templates and distinguish files suitable for automatic cleanup from those containing custom content. #98400 Thanks @giodl73-repo.
  1450. 1450Doctor lint can now flag the combination of WhatsApp, a strained Gateway event loop, and active local TUI sessions that is associated with delayed replies#98406 Thanks @giodl73-repo.
  1451. 1451Structured Doctor lint can now report stale global plugin-runtime symlinks, including the obsolete link, its target, and the openclaw doctor --fix cleanup command#98729 Thanks @giodl73-repo.
  1452. 1452Operators can use targeted Doctor lint to inspect legacy session transcripts and stale snapshot paths, preview the cleanup, and choose whether to apply it#95976 Thanks @giodl73-repo.
  1453. 1453WhatsApp and Telegram default-account routing warnings are now available through selectable structured Doctor lint while normal Doctor output remains unchanged#96147 Thanks @pick-cat, @vincentkoc.
  1454. 1454Optional Doctor lint can now identify stale or missing plugin registry data, shadowed bundled plugins, stale install records, and broken OpenClaw peer links#96169 Thanks @giodl73-repo.
  1455. 1455Structured Doctor lint can now report low or critical disk space for the OpenClaw state directory, including the affected path, available space, requirement, and remediation#98391 Thanks @giodl73-repo.
  1456. 1456Plugin operators can run doctor --lint --only core/doctor/legacy-plugin-manifests or --all to identify legacy manifest keys and see the affected plugin, path, and repair command#98695 Thanks @giodl73-repo.
  1457. 1457Operators can use openclaw doctor --lint --only core/doctor/legacy-plugin-dependencies or --all to find stale plugin dependency state and receive a path plus safe repair guidance without changing the installation#98725 Thanks @giodl73-repo.
  1458. 1458Channel setup warnings are now available as structured Doctor lint findings with stable paths and repair guidance for operators and automation#99238 Thanks @giodl73-repo.
  1459. 1459openclaw attach now launches Claude Code with temporary access to the main or selected Gateway session, keeps credentials out of arguments, and revokes the grant when the session ends#96454 Thanks @anagnorisis2peripeteia, @obviyus.
  1460. 1460Owner-controlled agents can opt into `appServer.homeScope"user"` to inspect and safely fork the same Codex threads available in Desktop and the CLI. #99821
  1461. 1461openclaw sessions --json now includes available subagent lineage and runtime details such as parent linkage, workspace, depth, role, timestamps, and status#87917 Related #80286. Thanks @islandpreneur007, @zhangguiping-xydt.
  1462. 1462status and status --json now build session model labels with less unnecessary normalization, improving readback speed for larger session sets and incident checks#87831 Thanks @acskamloops.
  1463. 1463`usageUsage.cost and sessions.usage now reject a start date later than the end date with a clear INVALID_REQUEST instead of returning a misleading empty report. #94096 Thanks @alix-007.
  1464. 1464Session cost summaries now estimate a real charge when a transcript records zero dollars despite token use and known model pricing. c5260a3 Thanks @nianjiuzst
  1465. 1465Session logs and cached cost views now preserve provider-reconciled zero-dollar totals while recalculating genuinely missing costs from stored provider and model details. c45124a
  1466. 1466openclaw sessions tail --tail now rejects counts too large to represent safely instead of applying an imprecise history limit#99398 Thanks @qingminglong.
  1467. 1467A malformed transcript timestamp no longer corrupts session usage and cost records with invalid values#99420 Thanks @krissding.
  1468. 1468Session maintenance warnings now say 1 minute, 1 hour, or 1 day at rounded boundaries instead of awkward values such as 60 seconds#100096 Thanks @narahariraghava, @vincentkoc.
  1469. 1469Session maintenance warnings now show more accurate wait estimates near unit boundaries, so a roughly 90-second delay is not inflated to two minutes. 58d707f Thanks @vincentkoc
  1470. 1470openclaw logs --follow can bridge a brief local Gateway outage with journal output and automatically return to normal Gateway logs after recovery#88159 Thanks @anyech, @vincentkoc.
  1471. 1471Debug proxy capture now keeps oversized or endless response bodies from crashing the agent, while retaining useful status and header metadata#97551 Thanks @alix-007.
  1472. 1472The first Gateway status check after a restart now reports the selected model's actual context window instead of briefly showing a generic 200k limit#97576 Thanks @turbotheturtle.
  1473. 1473openclaw health now surfaces permanently failed deliveries with queue counts and oldest-failure age instead of reporting an all-green state#99842 Thanks @masatohoshino.
  1474. 1474Timing displays now roll rounded sub-second values over to 1s instead of showing the awkward 1000ms#100006 Thanks @qingminglong.
  1475. 1475openclaw logs now reports log-tail stream failures cleanly instead of crashing, hanging, or leaving journalctl running#100850 Thanks @cxbasdev, @vincentkoc.
  1476. 1476Trimmed OpenClaw CLI logs now remain valid UTF-8 when the retained byte range begins inside an emoji or other multibyte character#101029 Thanks @ly85206559.
  1477. 1477Langfuse, OpenTelemetry, and Prometheus can now capture usage, cost, model, provider, timing, and session data for runs started through /v1/responses and /v1/chat/completions#96152 Thanks @rocke2020, @xialonglee.
  1478. 1478File-backed usage-bar templates now keep watcher and file-descriptor use bounded in long-running OpenClaw processes while still reloading templates when needed#98990 Thanks @chenyangjun-xy, @vincentkoc, @zhanglei99586.
  1479. 1479Compact /status no longer shows the ambiguous `PluginsOK` row, while warnings and detailed plugin diagnostics remain available. #100143
  1480. 1480Failed OpenClaw and plugin-harness traces now include useful redacted error details in OpenTelemetry instead of only a generic failure label#101244 Thanks @amknight.
  1481. 1481OpenTelemetry trace viewers can now display captured tool results alongside tool inputs in standard GenAI fields, making failed-run investigation more complete#101371 Thanks @amknight.
  1482. 1482openclaw status --all now keeps shortened channel issue messages readable when an emoji falls at the display boundary#101503 Thanks @wm0018.
  1483. 1483OTLP traces, metrics, and logs now follow HTTP_PROXY, HTTPS_PROXY, and NO_PROXY, keeping diagnostics exports on the configured network path#100616 Thanks @jesse-merhi.
  1484. 1484The bounded openclaw hooks commands now return control promptly after printing their output, so terminals, scripts, and CI jobs no longer remain stuck#76922 Thanks @dorukardahan.
  1485. 1485Non-interactive openclaw models list and openclaw models status now exit normally after printing their results, allowing scripts and SSH diagnostics to finish without an external timeout#77904 Thanks @dorukardahan, @vincentkoc.
  1486. 1486TUI links now leave malformed fragments and stray punctuation as plain text while keeping valid parenthetical, IPv6, and line-wrapped URLs clickable at the correct target#100780
  1487. 1487openclaw docs now rejects oversized search responses with a clear error before they can destabilize the CLI or exhaust memory#98188 Thanks @cxbasdev.
  1488. 1488Several edge cases now preserve transcript and voice text, surface MCP failures, bound oversized responses, show current session time, choose the right Linux package manager, and use port 443 for secure Gateway links without an explicit port#100258 Thanks @connermo, @cxbasdev, @gfaerny, @hailory, @harjothkhara, @ly85206559, @mushuiyu886, @simon-xydt, @sunlit-deng, @uditdewan.
  1489. 1489Failed openclaw --help and openclaw --version startup now returns exit code 1 promptly instead of leaving the terminal process stuck#97807 Thanks @aniruddhaadak80, @maweibin.
  1490. 1490CLI tables now shorten only the actual home directory and its descendants, so sibling paths such as /home/alice2/project no longer appear as misleading home-relative paths#98876 Related #98872. Thanks @qingminglong.
  1491. 1491Message read, pinned-message, and search commands can now display more than 25 returned rows when a higher --limit is requested and warn when additional provider results remain#99089 Thanks @jerrytao-ai, @wm0018.
  1492. 1492openclaw --help now matches command-specific help and completions, with config patch and config schema visible from the main command list#100670 Thanks @amirf194, @vincentkoc.
  1493. 1493Terminal-rendered links containing balanced parentheses now remain clickable through the complete intended URL instead of being shortened or misdirected#100697 Thanks @aniruddhaadak80, @zoowh.
  1494. 1494Generated shell completion now suggests accepted OpenClaw command aliases and continues completing their options and subcommands#99419 Thanks @amirf194, @jack-dev-ops, @vincentkoc.
  1495. 1495Terminal and setup documentation links now resolve correctly when relative paths begin with http or absolute HTTP schemes use uppercase letters#96439 Thanks @lin-hongkuan.
  1496. 1496Long IDs and scopes no longer push openclaw commitments columns out of alignment, keeping the table readable at a glance#95923 Thanks @parveshsaini.
  1497. 1497Built-in openclaw nodes status, openclaw nodes list, and related node commands now start quickly without unnecessary plugin initialization, while plugin-provided node commands still load when requested#96702 Thanks @erhhung, @qijian-zhang, @zengwen-dt.
  1498. 1498Failed openclaw devices approve attempts now explain whether to approve a scope upgrade elsewhere or refresh the pending request ID and retry#98146 Thanks @romneyda.
  1499. 1499An invalid `openclaw nodes approve &ltAn invalid openclaw nodes approve <requestId> now shows available pending IDs and the openclaw nodes pending recovery command instead of a raw client error. #94452 Thanks @mushuiyu886.
  1500. 1500openclaw pairing list now gives a useful device-approval next step when no chat DM pairing channels exist instead of displaying a broken empty-choice error#98142 Thanks @romneyda.