OpenClaw corrige falhas em atualizações e reparos
Versão 2026.10.3 trata de atualizações travadas e de situações em que o reparo podia afetar credenciais ou arquivos de memória.
Read news →Tool profile
OpenClaw
OpenClaw's self-hosted gateway for connecting AI agents to messaging channels, model providers, tools, automations, and personal devices.
TOOL TIMELINE
Newest first
Versão 2026.10.3 trata de atualizações travadas e de situações em que o reparo podia afetar credenciais ou arquivos de memória.
Read news →openclaw 2026.10.3
openclaw 2026.10.2
A versão 2026.10.1 adiciona suporte a MCP Apps, melhora a busca por skills instaladas e amplia as opções de backup.
Read news →openclaw 2026.10.1
OpenClaw 2026.9.9
58 commits · 43 pull requests · 21 contributors The release notes and changelog contain the same content, presented in two formats: Release notes — formatted for people, with expandable sections. Changelog — plain Markdown for AI agents and tools. @609NFT @aniketkrs @aniruddhaadak80 @EndeavorPioneer @ericcaiwx-star @fuller-stack-dev @hailongguo0530-alt @jasdeepohri-max @miguelpt2026 @NickM83 @obviyus @Patrick-Erichsen @PennyVibe @RomneyDa @scotthuang @steipete @VACInc @vincentkoc @WG-Mojo @xilopaint @yashas-13 npm package: https://www.npmjs.com/package/openclaw/v/2026.9.8 registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.9.8.tgz integrity: sha512-G+JkNUhtpDE3cXR4AEi2NyyG9fqI/T2WUSl8ZnR8AATH8Dh1kC3qYFL7wwPoZtgHiP/cszA86PEiE0PDysxb9Q== release SHA: fc23bc864e4553c2d215e479eeec47b67a0bf943 full release CI report: https://github.com/openclaw/releases/blob/main/evidence/2026.9.8/release-evidence.md release publish: https://github.com/openclaw/openclaw/actions/runs/37089852299 npm preflight: https://github.com/openclaw/openclaw/actions/runs/37046778498 full release validation: https://github.com/openclaw/openclaw/actions/runs/37045896743 plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/37090141905 plugin ClawHub submission: https://github.com/openclaw/openclaw/actions/runs/37090144556; public artifact verification follows successful release-parent completion plugin ClawHub bootstrap: not needed OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/37087759921/attempts/1 Telegram integration checks: waived by the release owner for 2026.9.8 (source QA, Package Acceptance, published-package E2E); not run. Android APK: skipped — apps/android/version.json is 2026.8.2, release train is 2026.9.8; run pnpm android:version:pin -- --from-gateway before the next tag.
GPT-6.1 Sol support: add the current Sol model across OpenAI routing, discovery, reasoning, harness, and Reef guard-model boundaries. (#161400, #162955) Safer updates and recovery: preserve plugin settings, prevent duplicate Gateways, handle pnpm package updates without terminal failures, and retain plugin inventory through migration. (#160344, #160193, #161920, #161485) Thanks @EndeavorPioneer, @grtninja, @alkor2000, @xilopaint, and @aniruddhaadak80. Reliable agent completion: preserve complete delegated and CLI answers, release suspended child capacity, recover full cron output, and prevent failed requests from consuming steered questions. (#162843, #162368, #160520, #162439) Thanks @zyz619963502zyz, @holgergruenhagen, @armstrongsam25, @davidcittadini, @jayzhou2309, and @obviyus. Security and ownership hardening: keep secret-store kinds stable during rotation, restore admitted secret-egress execution, and retain explicit cron tool allowlists while repairing stale automatic snapshots. (#160926, #160760, #162432) Thanks @zachisfine, @yetval, @VACInc, and @obviyus. Channel and integration reliability: repair Gmail and IMAP watchers, Matrix direct mappings, Telegram progress, remote MCP startup, and managed llama.cpp startup on clean Windows hosts. (#161503, #160413, #161727, #161546, #162376, #163093) Thanks @obviyus, @kazuyuki-eguchi, @Ayushdevo, @addyCooks, @VACInc, @Patrick-Erichsen, and @RomneyDa. Performance and UI continuity: bound model-catalog waits, reduce Codex fleet heap pressure, and keep saved WebChat replies visible across history refresh races. (#161132, #162912, #162763) Thanks @jayzhou2309, @Flakedict, @obviyus, @609NFT, and @VACInc.
Extended-stable correctness rollup: backport 113 audit-selected fix units across upgrades, Doctor, authentication, sessions, channels, plugins, sandboxing, filesystem safety, model runtimes, and release packaging. Complete rescan: re-evaluate the full 2026.8.33 discovery range, large mixed-purpose pull requests, and the 2026.7.35 lineage instead of advancing only from the previous backport cursor. Upgrade and recovery hardening: preserve credentials, agent state, plugin inventory, transcripts, schedules, service ownership, and runtime links through upgrades, restarts, and Doctor repair. Boundary fixes: tighten remote filesystem mutation, plugin and skill scanning, browser authentication, channel reply identity, private skill ingress, and scoped runtime ownership.
Security and credential safety: harden command parsing, browser origin checks, plugin Git installs, diagnostics, service credentials, and webhook logging across Gateway and official plugins. Message and session integrity: preserve queued, imported, streamed, and tool-result messages across retries, hooks, recovery, and channel lifecycle transitions. Gateway reliability: close failed HTTP and Responses streams, bound expensive reads and history queries, and settle shutdown work before reporting completion. Thanks @RomneyDa. Channel delivery: repair Discord, Matrix, Telegram, Slack, WhatsApp, LINE, Feishu, Zalo, and meeting-plugin edge cases that could lose, corrupt, or stall messages. Provider and media robustness: bound provider requests and diagnostics, reject malformed payloads, and preserve valid tool schemas and response lifecycles. Thanks @RomneyDa. Current model families: add GPT-6 Astra, GPT Image 2.5 Flare/Sunburst, Muse Spark 1.3, Claude Opus 5, Gemini 3.6/3.7 Flash, Grok 4.6, Kimi K3, GLM 5.3, Qwen 3.8, DeepSeek V4 Flash Vision Experimental, and Nemotron 3.5 Lightning support across the provider catalogs and runtime policies that ship on extended stable. Fable 5.1 remains deferred because its prefix-bound reasoning contract requires the newer append-only replay lifecycle. GPT-5.6 compatibility: retain and verify the complete GPT-5.6 Sol, Terra, and Luna family across direct OpenAI and Codex OAuth routing, reasoning controls, pricing, context, and vision metadata.
test(release): use entitled Gemini live model (#153189)
OpenClaw 2026.9.5
Security and credential safety: harden command parsing, browser origin checks, plugin Git installs, diagnostics, service credentials, and webhook logging across Gateway and official plugins. Message and session integrity: preserve queued, imported, streamed, and tool-result messages across retries, hooks, recovery, and channel lifecycle transitions. Gateway reliability: close failed HTTP and Responses streams, bound expensive reads and history queries, and settle shutdown work before reporting completion. Thanks @RomneyDa. Channel delivery: repair Discord, Matrix, Telegram, Slack, WhatsApp, LINE, Feishu, Zalo, and meeting-plugin edge cases that could lose, corrupt, or stall messages. Provider and media robustness: bound provider requests and diagnostics, reject malformed payloads, and preserve valid tool schemas and response lifecycles. Thanks @RomneyDa.
20 direct commits · 1,558 pull requests · 294 contributors The release notes and changelog contain the same content, presented in two formats: Release notes — formatted for people, with expandable sections. Changelog — plain Markdown for AI agents and tools. @0xCyda @100yenadmin @1Vision365-PeterTijsma @609NFT @84dnnvbdvp-debug @aaajiao @aatreya @abacha @adinballew @aeoess @aevgeniou @ai-hpc @aim9sour @akagifreeez @aleps001 @alexjpanagis @alexph-dev @Alix-007 @aminekhettat @andrea-kingautomation @anguslogan01 @aniruddhaadak80 @ansxor @anyech @arcabotai @Artemeey @ashawwal @aspalagin @AVCarp @avp717 @ayaangazali @azuretek @barbarhan @Baumus @benjaml4 @BottaniCals @brainatworkharris @bricelb @BsnizND @c0ncatenate @cai-ops @ccaprani @ceckert @chegherian @chelsealong @chl-0537 @ChrisCantwell @chrislro @cjn119-ui @CK-XYZ @Cobblestone-Digital1 @Colton-Harris @Conan-Scott @cp1369 @crash2kx @DasX @dbarbatti @developercrocodiles @Devin-Linux @dh-js @DilapidatedDolphin98 @dillona @dimonnld @DonnieFi @Dreamer-HIT @drobison00 @dw1161 @ejc3 @ekinnee @elbourne12345 @eleqtrizit @elikampf @ElvisIO7 @Enominera @ericcaiwx-star @fabiolr @fahrenhe1t @fanyangCS @fanyuantaier @fede-kamel @Finn763 @FlagshipClaw @fulgerulnegru @fuller-stack-dev @galiniliev @GDXbsv @geekforlife @GitHoubi @glenn-agent @Glucksberg @goutamadwant @gozu @Grynn @guarismo @guojiongming @gwiltschek @hannesrudolph @HAPPYFAPTAIN @harjothkhara @harshitgupta31415 @Hawk5150 @hayden-cc @he-yufeng @Hekzory @HermanZeng @hugenshen @husodrn46 @hxy91819 @igs-rogenlo @ikenraf @infocus13 @islandpreneur007 @itanyplus @IWhatsskill @jackatagenticforce @Jackten @jai-assistant @jailbirt @jalehman @jarvismazz @jason-allen-oneal @jerabinovich @jesse-merhi @jialele @jinngimk-lang @jjjhenriksen @JKamgang @jlacroix82 @jlapenna @jmissig @jodok @JunfXiao @kashivreddy @Kaspnov @kesslerio @kiagentkronos-cell @Kimiyu-186 @KingAkrej @kingkong9817 @KirDE @kopl-blip @kvnloo @laisonamarante @laurencebrown @laurenceputra @leapdragon @legupsystems @lei-happy @leilei3167 @Lendersmark @Leon-SK668 @LightningWareLLC @linhongyu510 @lisheguo @LiuwqGit @lizhengwu @lonexreb @louisfy @lraesly @ly85206559 @MAG-Linares-Andalucia @manumadrigal09 @markthebest12 @martins-oss @Marvinthebored @masatohoshino @MasterSwords1 @matthewmoroz @MaxVidkrytaklishnya @mgabor3141 @miguelbranco80 @mikronn2 @MoerAI @morrow-bluedot @MrNozz @najef1979-code @narbs @Newsstand @NianJiuZst @nissl24 @nkdmike @nocodet888-arch @noelillinger @north-echo @NovaUnboundAi @NullArbitrage @obviyus @Oliverbot26 @omarshahine @ooiuuii @orangejon @OuiOui33 @oywino @pash-openai @Patrick-Erichsen @pbergeot @pcpilot-dev @Peetiegonzalez @pengzh1 @PeterHodl @peterkaynie @pfrederiksen @pgondhi987 @pick-cat @piotx @pollybot13 @postoso @qingminglong @razvangirgiz @rboy1 @rgregg @richard355168 @rico007 @rileyjjy @rjamoul @rlosito @romneyda @rondavis007 @rqlangley @ruel225 @ruicatalao7 @russellweiss @safzanpirani @sallyom @samrrr @sappkevin @schjonhaug @schwanncells @scotthuang @sedrak-hovhannisyan @sercada @seven7763 @shakkernerd @shaozhengkun123 @shojikumaru @skaneta @sloptop-the-terrible @soroyue @spectrl @srikolagani @steipete @stephane-fci @stevenlee-oai @sunlit-deng @sunnyandtec-ak @sunnyiren-max @sunnyshu0925 @syfvb @synthalorian @szqub @takhoffman @teddytennant @theangrypit @thecrazylex @thien-ngn @thomasmoenco @tilor @timetrvlr @todddickerson @tomdailey55 @toneloke @toraiwa @tskerpnext @unknowbug @vacinc @vincentkoc @von8794 @vyctorbrzezowski @wangmiao0668000666 @wenbiyou @wolikimcheng @wpu911 @xialonglee @xiaoguomeiyitian @xueqingli1 @xuxyyy @xx441 @xydigitlybnnnn @xydt-juyaohui @xydt-tanshanshan @yangxiansheng @yanhe1169 @yetval @yigtwxx @ylcn91 @yncubys @youens @yxloveql @zachisfine @zenglingbiao @zhangguiping-xydt @zhuyankarl @zwyhmcn @zyw02 Signed source: 3a9d69db306cd7f081e06254cb89c4bcc14a7107. Full stable validation: passed, attempt 2. Qualification also verified 15 performance measurements and 20 real OpenAI completions across 10 upgrade baselines. C
Safer provider and channel boundaries: bundled providers and channel adapters now bound untrusted response bodies, reject oversized inputs before expensive work, and preserve safe recovery when transports fail. (#119942) Thanks @RomneyDa, @vincentkoc, @Pick-cat, @RileyJJY, @ZengWen-DT, @Monkey-wusky, @chengzhichao-xydt, @mushuiyu886, @masatohoshino, @moguangyu5-design, @sunlit-deng, @ZOOWH, @NianJiuZst, @Alix-007, @aniruddhaadak80, @eleqtrizit, @yetval, @rvdlaar, @litang9, @machine3at, @miorbnli, @sallyom, @obviyus, @hugenshen, @cursoragent, @cxbAsDev, @wangmiao0668000666, @lsr911, and @jalfaro2876. More reliable long-running delivery: agent, gateway, retry, and channel paths now handle cancellation, retries, partial sends, and process-stream failures without losing work or replaying unsafe operations. (#119942) Thanks @RomneyDa, @vincentkoc, @Pick-cat, @RileyJJY, @ZengWen-DT, @Monkey-wusky, @chengzhichao-xydt, @mushuiyu886, @masatohoshino, @moguangyu5-design, @sunlit-deng, @ZOOWH, @NianJiuZst, @Alix-007, @aniruddhaadak80, @eleqtrizit, @yetval, @rvdlaar, @litang9, @machine3at, @miorbnli, @sallyom, @obviyus, @hugenshen, @cursoragent, @cxbAsDev, @wangmiao0668000666, @lsr911, and @jalfaro2876. Stronger bundled-plugin resilience: local-model, browser, media, and collaboration plugins recover cleanly from malformed payloads, timeouts, and transient upstream failures. (#119942) Thanks @RomneyDa, @vincentkoc, @Pick-cat, @RileyJJY, @ZengWen-DT, @Monkey-wusky, @chengzhichao-xydt, @mushuiyu886, @masatohoshino, @moguangyu5-design, @sunlit-deng, @ZOOWH, @NianJiuZst, @Alix-007, @aniruddhaadak80, @eleqtrizit, @yetval, @rvdlaar, @litang9, @machine3at, @miorbnli, @sallyom, @obviyus, @hugenshen, @cursoragent, @cxbAsDev, @wangmiao0668000666, @lsr911, and @jalfaro2876. Safer tool and workspace use: browser automation, local tools, workspace reads, and plugin metadata handling now reject malformed or oversized inputs before they can interrupt an active agent run. (#119942) Thanks @RomneyDa, @vincentkoc, @Pick-cat, @RileyJJY, @ZengWen-DT, @Monkey-wusky, @chengzhichao-xydt, @mushuiyu886, @masatohoshino, @moguangyu5-design, @sunlit-deng, @ZOOWH, @NianJiuZst, @Alix-007, @aniruddhaadak80, @eleqtrizit, @yetval, @rvdlaar, @litang9, @machine3at, @miorbnli, @sallyom, @obviyus, @hugenshen, @cursoragent, @cxbAsDev, @wangmiao0668000666, @lsr911, and @jalfaro2876. More dependable local integrations: local-model discovery, speech, meeting, and collaboration integrations now make bounded requests and surface failures without destabilizing the gateway. (#119942) Thanks @RomneyDa, @vincentkoc, @Pick-cat, @RileyJJY, @ZengWen-DT, @Monkey-wusky, @chengzhichao-xydt, @mushuiyu886, @masatohoshino, @moguangyu5-design, @sunlit-deng, @ZOOWH, @NianJiuZst, @Alix-007, @aniruddhaadak80, @eleqtrizit, @yetval, @rvdlaar, @litang9, @machine3at, @miorbnli, @sallyom, @obviyus, @hugenshen, @cursoragent, @cxbAsDev, @wangmiao0668000666, @lsr911, and @jalfaro2876.
Safer updates: rehearse core and plugin changes in isolated candidate state before activation, support eligible 2026.9.2 migrations, and recover abandoned update records without stopping a healthy matching Gateway. Related #136997. (#138839, #141109, #141175, #141562) Performance: preserve warm prompt caches, reduce unnecessary work during cold session updates and memory search, and reuse worker builds between sessions. Related #140681. (#140449, #140730, #140799, #140840, #141141) Thanks @justinkirklin-gif, @NianJiuZst, and @obviyus. Skill Workshop: keep skills in one persistent agent-owned collection across workspaces, compare complete skill instructions, and retire missing-draft suggestions safely through Doctor. Related #135291. (#135528, #139248, #140300, #141009) Thanks @khaisis and @obviyus. Browser tabs, live and native: watch agent pages repaint and open external links in native Mac tabs that remain with their window across chat switches. (#140988, #141031) Your provider accounts, together: manage connected accounts and supported account priority directly in Models settings. (#132451) Thanks @jesse-merhi. Share selected conversations: explicitly publish a revocable read-only view of a session’s existing and future conversation text, accessible to anyone with its public link. (#139489) A searchable meeting library: browse saved notes, search full transcripts, download complete Markdown or JSONL archives, and manage capture sources from the Control UI. (#139875, #140084) Optional team activity reports: install and enable Team Reports to browse authenticated GitHub activity and explicitly configured Discord discussion, with stored history and optional model summaries. (#139850, #141327)
Faster, more responsive chat: keep chat, dashboards, and session interactions responsive while long transcripts and disk usage are processed, with direct dashboard lookup, less cold-load work, and durable history reads outside the Gateway event loop. (#136862, #138094, #138669, #138888, #138860, #138894) Reliable upgrades and recovery: keep active settings, enabled skills, and default-agent ownership in automatic updates, restore Gateway restarts after Git updates, and report outcomes with actionable recovery guidance. Related #138760. (#138837, #138730, #138781, #136588, #136995) Thanks @fuller-stack-dev and @jason-allen-oneal. GPT-6 Astra support: select openai/gpt-6-astra with an OpenAI API-key profile or an eligible ChatGPT/Codex account, with text and image input, Responses tool calls, and supported reasoning controls; subscription availability follows successful account discovery. Related #137549. (#137550, #137561) Replies survive restarts: recover active, queued, and delegated replies after Gateway restarts without letting one completed reply discard another’s recovery marker, and keep continuation instructions through compaction and retry attempts. Related #138518, #138564. (#138071, #137606, #136236, #138519, #138565) Thanks @vincentkoc. Backups that preserve your data: preserve complete text containing embedded NUL characters in Git backups, support Nix-managed config and credential links, and reject corrupt archive headers instead of accepting an incomplete backup. Related #138306, #136326. (#138327, #136343, #137718) Thanks @obviyus, @ced-cm, @vsumner, and @NianJiuZst. Change settings without restarting: apply more agent, model, tool, channel, browser, node, access, and terminal settings through their running owners; settings that still require a Gateway restart remain marked in the configuration reference. (#138112, #137790, #137412, #137160, #136832) Thanks @NianJiuZst and @ylcn91.
Diagrams in every chat: Mermaid blocks now render as diagrams in the Control UI and in the native macOS, iOS, and Android apps, with enlarge previews and a retry when a diagram fails to render on mobile. (#134913, #135746, #135470, #135342) From install to chat in one prompt: fresh installs (including npx openclaw@latest) get a quick-start lane that detects existing Claude Code or Codex logins and API keys, verifies them live, and opens the web dashboard from a foreground Gateway; the full wizard stays available as Custom setup. (#134221) Thanks @fuller-stack-dev. Personal skill libraries on shared Gateways: keep your own skills beside the workspace set with openclaw skills library, import them from ZIP archives, and share or publish them per identity on team Gateways. Related #133602. (#134068) Updates that leave you working: openclaw update now rolls back the npm candidate when the post-update Doctor fails, preserves your configuration and secret references across a failed upgrade, hands failures to a built-in triage agent, waits for plugin readiness before restarting, accepts npm 12 local archives, lets agent-launched updates finish outside the Gateway process tree, and proceeds without a Gateway service instead of refusing when no service manager exists (users on 2026.8.2 without a service manager should run openclaw update --no-restart once). Related #134204, #135655. (#135462, #134490, #134865, #134699, #134663, #136316, #135701) Thanks @fuller-stack-dev, @Patrick-Erichsen, @vyctorbrzezowski, @jalehman, @devzeroLL, and @obviyus. A Gateway that stays up: startup recovers under load and with large agent rosters, malformed legacy cron rows are quarantined instead of blocking boot, migration warnings degrade the Gateway instead of refusing to start, local model servers become the preferred OOM victims, and Windows Gateways stay online after an agent restart. Related #135743, #134458, #135150, #136275, #120134, #134851. (#132186, #135773, #134704, #135713, #136276, #134549, #134853) Thanks @galiniliev, @LiuwqGit, @obviyus, @609NFT, @Nielsh82, @Zak-Finance, @vincentkoc, @nerclid, @w1130150306, and @cmanrav. Codex approvals that stick: "Allow Always" is durable for MCP tools on OpenClaw-configured servers, tool approvals follow the session's posture, and approvals granted to an active Codex placement are reused instead of asked again. Related #132369. (#136019, #135812, #132370) Thanks @jalehman. Approvals reach your chat: when a delegated system agent proposes a config change or Gateway restart, the approval card is delivered to the originating channel (Telegram topics included) with the requester's title, instead of stalling silently. Related #136083. (#134670, #136091) Thanks @obviyus. Android catches up with the web UI: the chat screen, sidebar navigation, and appearance settings match the Control UI, the composer grows to six lines, and recording is offered when dictation is unavailable. Related #125322. (#134939, #135923, #135794) Thanks @IWhatsskill, @obviyus, @BennyAI2, and @RaviTharuma.
Your Home agent, beside your work: open Home in a right or bottom dock with Cmd/Ctrl+Shift+H, keep your current page in view, and preview or remove its work-context snapshot or attach selected text to your message. Related #133632. (#133676) A desktop companion for Linux: install the .deb or AppImage on x86-64 Linux, connect to a local or remote Gateway, and open Quick Chat from the system tray or an X11 keyboard shortcut. AppImage updates are signature-verified; .deb installs remain under your package manager. See the Linux guide. Start work without switching pages: create and run a background session from New Session, keep its selected local, cloud, or paired-device placement, and open it from the completion notice. Related #128037. (#128050) Thanks @Takhoffman. Safer upgrades: preserve newer configuration, stop incomplete session migrations before claiming success, and recover a stopped Gateway after a failed update when the installed package or rollback is verified safe. Related #118244, #90551, #134206. (#134025, #134228, #119516) Thanks @obviyus, @stuart-minion-ai, @shakkernerd, @zyw02, @Issue-Hunter, @cursoragent, and @sercada. Replies that finish the job: return a final answer after settled tool work and surface failures after an accepted turn, fixing conversations that stopped at tool output or an initial acknowledgement. Related #133960. (#133520, #133979) Thanks @fuller-stack-dev. More dependable voice: keep internal reasoning out of speech, preserve tool-generated audio through delivery, and keep later browser Talk turns working after call setup. Related #90364, #83636, #134081. (#133615, #133324, #134170, #134138) Thanks @camball-strategies, @obviyus, @TurboTheTurtle, @clawSean, @Conan-Scott, and @mastertyko. Browser control without a running Gateway: let supported macOS and Linux Chrome extension builds wake their paired local relay for authenticated CDP clients; this needs the updated native host and an extension build with relay wake-up support. (#128379) Four new looks: personalize the Control UI with CRT, Manuscript, Rosé, or Miami, with theme choices preserved offline and applied without flashing the wrong theme during reload. Related #133416, #132785. (#133495, #133593, #133417, #132789) Thanks @vyctorbrzezowski.
Safer browser and network boundaries: sandboxed browser routes, trusted DNS targets, custom browser origins, and loopback provider endpoints now reject unsafe access paths. (#97958, #38290, #103075, #110693) Thanks @eleqtrizit, @brunowowk, @mosidevv, @pgondhi987, and @lsr911. More resilient agent and provider runs: retained session writes, provider fallbacks, stream progress handling, and stdio failures now recover without silently ending active work. (#96100, #97128, #90908, #99803, #100521) Thanks @xialonglee, @sallyom, @richwilson-bloom, @LiuwqGit, @vincentkoc, @yetval, @shengting, and @cxbAsDev. Stronger channel recovery: pending channel work resumes after recovery, acknowledgements are idempotent, and sustained Discord gateway bursts stay bounded. (#79811, #97041, #104919, #109108, #110954, #103793, #94016) Thanks @indulgeback, @cuiyuxin-gif, @Pick-cat, @Glucksberg, @evan-YM, @zhangguiping-xydt, @yetval, @sheyanmin, and @thomasthelen-kibeauftragter. Safer operator diagnostics: command and status surfaces keep owner-only actions protected and prevent credentials from appearing in account URLs or summaries. (#98260, #107754, #105017) Thanks @eleqtrizit, @joshavant, @ooiuuii, @aniruddhaadak80, and @tzy-17. More robust local runtime state: SQLite checkpoints, workspace reads, gateway process signalling, plugin HTTP responses, and dependency handling no longer turn transient host conditions into failed runs. (#99067, #100910, #102125, #109590, #112406) Thanks @ooiuuii, @masatohoshino, @vincentkoc, @mushuiyu886, and @krissding.