Agent Breaking Changes_

← OpenClaw

OpenClaw openclaw 2026.10.5-beta.1

2026-10-11 · official notes

Summary

• Safer updates: updates finish across devices, filesystems, Windows elevation, and interrupted activations, and recover from stale leases or changed evidence instead of stranding the install or blockin
• Restart-safe conversations: interrupted turns, first messages during worktree preparation, and deferred tasks resume after a Gateway restart, and user input and committed session data survive restarts
• Faster, steadier Gateway: session, transcript, history, and metadata reads move onto worker threads with far less SQLite work per turn, and startup maintenance runs after readiness so busy Gateways st

Full notes

## 2026.10.5-beta.1

### Highlights

- **Safer updates:** updates finish across devices, filesystems, Windows elevation, and interrupted activations, and recover from stale leases or changed evidence instead of stranding the install or blocking future updates. (#164636, #164769, #165257, #165863, #166548, #166695, #168043, #166394, #167302) Thanks @hrp6vv9mwr-glitch, @MrJanvar, @Shirleyyyhk, @farisoftfry, @neilofneils404, and @shanselman.
- **Restart-safe conversations:** interrupted turns, first messages during worktree preparation, and deferred tasks resume after a Gateway restart, and user input and committed session data survive restarts, concurrent writes, and failed publications. (#165333, #166042, #165184, #166238, #165502, #167570, #163258, #166010, #167662) Thanks @masatohoshino, @goutamadwant, and @hawkit.
- **Faster, steadier Gateway:** session, transcript, history, and metadata reads move onto worker threads with far less SQLite work per turn, and startup maintenance runs after readiness so busy Gateways stay responsive. (#164744, #165470, #165614, #166587, #167194, #164779, #165028, #166041, #167278, #165993) Thanks @obviyus.
- **Reliable turns and subagents:** turns recover from stalled streams, reused tool-call IDs, and expired ChatGPT websockets, incomplete turns end with a visible notice, and subagent results keep returning through follow-ups, restarts, and expired delivery windows. (#165983, #167013, #165212, #167063, #167972, #164282, #168068, #166846, #166139, #165987) Thanks @cestercian, @Irish-Joseph, @rmyers64, @sszyh2026, @Jackten, @Oldrich333, @obviyus, @stackingrockss, @Yun-0000, @michaeljgood71, and @LifeViwer.
- **X channel:** answer X (Twitter) mentions through a new channel plugin with streaming, guest mode for repository questions, and enforced API cost limits. (#165138, #165337, #165354, #165351)
- **Voice calls:** voice calls gain per-call briefs, call reports, live steering, callbacks, and voicemail detection. (#165716) Thanks @mbelinky and @jacobtomlinson.
- **Smarter model pickers:** pickers lead with each provider's recommended models, show newly listed Claude, ChatGPT, and Ollama models without waiting for an OpenClaw release, and stay responsive while catalogs load. (#167370, #166737, #167658, #167387, #167463, #165989) Thanks @obviyus, @DonnieFi, and @dprev.
- **ClawHub in the Gateway:** browse and search ClawHub plugins and skills from the Gateway, and plugins automatically pick the newest official release your OpenClaw supports. (#163459, #167485, #166588) Thanks @jacobtomlinson and @charlesBerg-ux.

### Changes

- **Sessions:** allow directed sends to a session without granting transcript access. (#164444)
- **Worker-local inference:** add a native worker inference runtime with Gateway dispatch, client placement, required worker policy and destination checks before local inference, and clear setup-failure explanations. (#158902, #163645, #163646, #163647, #166611, #166613, #165960) Thanks @RomneyDa.
- **Public threads:** open public threads at their regular links. (#166049)
- **Subagent progress:** count running subagents on the working line, name launched subagents in the operations group, and continue a resumed answer in the block that handed off. (#165477, #165725, #165542) Thanks @shakkernerd.
- **X channel:** add the X (Twitter) mentions channel plugin with Activity API streaming and backfill, repository-question guest mode with hidden same-agent helpers, GitHub-verified repository writers, and daily and monthly X API cost limits. (#165138, #165337, #165376, #165354, #165543, #168071, #165351) Thanks @obviyus.
- **Automation repair:** let a failing automation's owner conversation repair it before alerting, give a second repair turn when the error changes, and post a clear warning when a repair turn times out. (#161007, #162702, #162772) Thanks @obviyus.
- **Channel progress:** show useful Telegram and Discord progress by default, add per-tool glyphs to Discord progress drafts, restore per-tool emoji on Telegram tool rows, and hide routine Slack reaction rows. (#166861, #168032, #167392, #166880) Thanks @obviyus, @keshavbotagent, and @notmnp.
- **Skills:** keep learned skills focused on repeatable procedures rather than facts or codebase knowledge, and keep longer legacy Workshop skills manageable. (#167404, #167639) Thanks @obviyus.
- **Memory:** explain why trigger recall is skipped and why embedding responses are rejected, and report managed Ollama and LM Studio embedding readiness. (#164409, #168035, #156483) Thanks @Ayushdevo, @wangmiao0668000666, and @obviyus.
- **Models and catalogs:** show each provider's recommended models first in pickers, publish curated per-provider recommendations in catalog v2, lead NVIDIA recommendations with its featured models, and apply downloaded catalogs without a Gateway restart. (#167370, #166737, #167989, #158000) Thanks @obviyus.
- **Anthropic and Claude CLI:** support Claude Haiku 5.5, show newly listed Claude models without waiting for an OpenClaw release, list each Claude CLI model once, and keep logged-out Claude CLI models listed with a login reason. (#166706, #167658, #166311, #166338, #167942) Thanks @RomneyDa and @obviyus.
- **OpenAI:** support custom realtime voice endpoints, show account chat models missing from the manifest, surface new ChatGPT-login models without a release, and stop offering ChatGPT-only or bundled-Codex-rejected models that would fail. (#165632, #162563, #167387, #167633, #167975) Thanks @jacobtomlinson and @obviyus.
- **Tool rows and subagent progress:** show Tool Search calls in native tool rows with shared tool icons across clients, show the subagent wait in place without handoff markers, and guide users after HTTP 400 prompt-size rejections. (#165095, #165378, #159712) Thanks @shakkernerd and @sunlit-deng.
- **Voice calls:** add per-call briefs, call reports, live steering, callbacks, and voicemail detection to voice calls. (#165716) Thanks @mbelinky and @jacobtomlinson.
- **Control UI subagents:** show when a chat is waiting on subagents, open the Subagents panel from the chat's subagent count and names, and surface child failures and attention in the parent chat. (#164190, #166142, #166224, #166312, #166347) Thanks @shakkernerd and @vincentkoc.
- **Control UI customization:** let themes customize Control UI branding, use agent avatars or unlocked Lobsterdex icons for browser tabs, choose favicon shapes, and add seven Lobsterdex character variants. (#168027, #165201, #166325, #167809, #159815) Thanks @vyctorbrzezowski, @jacobtomlinson, and @hannesrudolph.
- **Terminal:** add configurable terminal fonts with built-in Nerd Font icons. (#166180) Thanks @jacobtomlinson.
- **Control UI navigation:** copy file paths from chat tooltips, pin agents directly from the switcher, make agent menus easier to scan, let users hide a session's branch PR row, and simplify optional question cards. (#164431, #165640, #165641, #166366, #168040, #150587) Thanks @jjjhenriksen, @vyctorbrzezowski, and @RomneyDa.
- **Skill Workshop:** show each skill with its changes, files, and history in one view. (#167440) Thanks @obviyus.
- **iOS:** connect the Gateway through native Cloudflare Access with app-owned browser and profile admission. (#147244, #147238) Thanks @vincentkoc, @Solvely-Colin, @Patrick-Erichsen, and @RomneyDa.
- **ClawHub:** browse and search ClawHub plugins and skills through the Gateway. (#163459) Thanks @jacobtomlinson.
- **Plugins:** let plugin tools deliver their finished reply without a second model turn, allow every loaded plugin its own state and ingress queues and queue modes, and select plugin-owned self-hosted executors. (#164558, #165063, #165965, #161609) Thanks @mbelinky and @sjf-oa.
- **Plugins:** pick the newest official plugin release the running OpenClaw supports and keep a working plugin when its matching release is unavailable. (#167485, #166588) Thanks @charlesBerg-ux.
- **Workboard:** pin, unpin, and delete boards from the sidebar, keep card notes selectable with a roomier notes editor, and keep column edits on rename. (#165020, #166625, #167348) Thanks @rogeriochaves, @llmsommelier, and @obviyus.
- **GitHub:** support asynchronous PR merges and compact the Publish PR card. (#163579, #165219) Thanks @vincentkoc.
- **Session performance:** serve per-turn session projections, entry reads, authority checks, compaction reads, and first-turn headers from worker threads to keep the Gateway main thread responsive. (#164779, #165028, #165205, #165406, #165401, #165581, #165819, #165027, #165367, #164747, #164989, #165073)
- **Session list and search performance:** stop Control UI list refresh bursts, bound list materialization, scope and prefilter transcript search, speed up cold suggestion lists, and retain previews across metadata edits. (#162280, #164764, #165080, #165089, #165570, #165150, #165834, #165096, #165932, #166635, #165887, #167909)
- **Turn database performance:** reduce SQLite statements, worker requests, and redundant reads per chat turn, batch snapshot and metadata queries, and reuse admitted schema and reader facts. (#164490, #166041, #166053, #166054, #166074, #166102, #166541, #166503, #166519, #166698, #167278, #167686, #167685, #167690, #167932, #167046, #166966, #166925, #167291, #166703, #167029, #165360, #165193)
- **State database performance:** speed up cold agent database admission and crash recovery, reuse integrity checks on clean restarts, stop reopening executors when switching agents, and release leases promptly during shutdown. (#164846, #165070, #165186, #165293, #165680, #166112, #165993, #167001, #168008, #164788, #164962, #165085, #165910, #166822)
- **Maintenance and history performance:** lighten idle and manual maintenance, lifecycle cleanup, archive, reset, and trajectory retention work, and speed history reads with nested tool activity. (#164851, #164755, #164938, #165081, #165082, #165254, #165090, #165074, #165274, #165678, #167268, #167070, #167549, #167643, #168013, #167449, #165221, #165181, #165093, #165086, #165111, #165377, #165495, #165909, #166069, #166631, #166778, #166804, #167434, #167915, #167959) Thanks @Patrick-Erichsen and @obviyus.
- **Agent performance:** reduce retained heap, per-turn prompt allocations, transcript reads, and main-thread SQLite work during runs, preserve prompt cache across instruction refreshes and image cleanup, and reuse verified history images across turns. (#167454, #167922, #167682, #167547, #167698, #167613, #167355, #167938, #165142, #165404, #167282, #164685, #165012, #165410, #165370, #165552) Thanks @RomneyDa.
- **Model catalog performance:** speed up multi-provider catalog refreshes, avoid discovery on cold account reads and unrequested plugin catalogs, retain account catalogs during refresh, and reduce catalog worker heap. (#167101, #167334, #167359, #167009, #167008, #166007, #166434, #165911, #165708, #165547, #165034, #165491, #166602) Thanks @vincentkoc, @obviyus, and @xialonglee.
- **Subagent and ACP performance:** reduce startup registry restore latency, move bulk registry work off the Gateway thread, batch registry cohorts, and avoid full-session scans when resuming ACP sessions. (#165942, #165684, #165098, #167684, #167010, #167372, #165550, #167086)

### Fixes

- **Session data safety:** preserve user input and committed facts through restart recovery and failed publication, keep accepted locked appends settled before releasing the writer, and fence cross-store worker commits. (#165502, #167570, #165894, #168018, #168029)
- **Session authority and privacy:** check caller authority before restoring cold history for compaction, keep authority current after committed session changes, reject malformed hook session keys, and hide pre-session edits to branch-added files from uncommitted diffs. (#166506, #167875, #166406, #164671) Thanks @yetval and @obviyus.
- **Session cleanup:** remove leftover GitHub publication receipts and managed worktrees on cleanup and Incognito reset, and publish conversation, plugin-state, sandbox, worktree, and GitHub authority receipts. (#163833, #165185, #167731, #168025) Thanks @jayzhou2309 and @obviyus.
- **Turn reliability:** recover agent turns when the database worker exits mid-operation, stop unrelated session writes from failing Codex and chat turns, keep Knowledge calls working while a session publishes its bookkeeping, and stop group turns from failing silently when history cannot load. (#163258, #165196, #166010, #166758, #135253, #166059) Thanks @goutamadwant, @hawkit, @jalehman, and @izshaw.
- **Restart recovery:** settle sessions left running after restart, avoid duplicate recovery after ordinary interruptions, keep recovery reconciliation on the host, and preserve database admission, custody, and hook retries for post-restart and first-session turns. (#165174, #154175, #166395, #166867, #166609, #167629, #165859, #165738, #166891) Thanks @Grynn and @RomneyDa.
- **Agent and session creation:** fix concurrent first requests for a new agent, cold shared-store and fresh-store creation failures, and agent database recovery after orphan session window repair. (#166003, #167257, #167515, #167366, #166860)
- **Windows and path aliases:** canonicalize the shared state database path and compare link-stable identities so Windows and POSIX path aliases share one store, custody, and channel lifecycle. (#166755, #165775, #166062, #166462, #166787) Thanks @taihartman, @donquiche61, @RomneyDa, and @ericcaiwx-star.
- **SQLite deadlocks and stalls:** prevent writer-reader admission and cleanup deadlocks, keep committed reads responsive during writer stalls, stop writer-held transcript reads waiting on readers, and keep foreign changes visible during refresh. (#167662, #167446, #167901, #167687, #166331, #165898, #167332) Thanks @sasan1200 and @vincentkoc.
- **State and updates:** stop leftover update-check caches and completed recovery history from blocking updates, and give one actionable answer for state written by a newer release while keeping status reads read-only. (#165461, #167358, #166963) Thanks @RomneyDa.
- **Startup and integrity checks:** return pending admission during startup index repair, retain integrity proof through startup and idle retirement, stop early lease timers on long delays, avoid false state ownership loss on Bun, and stop healthy starts logging SQLite lock-wait warnings. (#165323, #166972, #166412, #167467, #167669, #167754, #166253, #168310) Thanks @RomneyDa.
- **Session search and history:** search transcripts for configured ACP owners, stop false indexing notices, keep search parallel with accurate indexing, preserve dot-prefixed checkpoint references and CLI history after interrupted progress replies, and keep canonical transcript owners distinct. (#164897, #165879, #167174, #167163, #164920, #166658, #164512) Thanks @sunlit-deng, @obviyus, @techdou, @shakkernerd, and @VACInc.
- **Session display:** stop Markdown link markup leaking into previews, show correct context windows for plugin-discovered models, log failed wakes with their target, keep owning agents in lifecycle commands and trajectory export, and decode UTF-16 BOM text files. (#166653, #159731, #166458, #166415, #165777) Thanks @jayzhou2309, @obviyus, @rudycelekli, @Yigtwxx, and @yetval.
- **Startup ordering:** stop agents with small transcript rebuild backlogs from waiting behind larger agents at startup. (#165207)
- **Security boundaries:** fail closed on unresolved A2A peer token references and when the process census cannot prove a temp root is unused, and reject incompatible worker prompt contexts before launch. (#165021, #165079, #166268) Thanks @eleqtrizit, @Dhotei, @vincentkoc, and @obviyus.
- **Data integrity:** reject malformed UTF-8 backup manifests before verification, preserve malformed UTF-8 and trailing-space connect targets, and keep accents in named legacy text attachments. (#167389, #167399, #167116, #165405) Thanks @Alix-007, @obviyus, and @Chessing234.
- **Restart recovery:** resume Control UI turns interrupted by a Gateway restart, keep a new session's first message when the Gateway restarts during worktree preparation, resume tasks after deferred startup recovery, pause restart recovery while the crash-loop breaker is tripped, and settle restart intents and update reports in workers. (#165333, #166042, #165184, #166238, #167572, #165069, #165670) Thanks @masatohoshino.
- **Turn lifecycle:** publish one terminal event per stopped or runtime-lost run, settle terminal runs before session mutations, keep queued message run ids and replies aligned, and prevent internal recovery errors after queued turns. (#165483, #167383, #166784, #166981, #165996, #164656) Thanks @RomneyDa.
- **Stop and steering:** stop yielded commands with their Gateway request, retire stopped continuations, allow wakes after stopped commands, preserve running tools when steering receipts are uncertain, show accepted steering messages in order, and hold steering during worktree creation until the task finishes. (#166753, #166775, #166968, #166754, #168099, #165462, #165537) Thanks @shakkernerd and @RomneyDa.
- **Queue fairness:** prevent background starvation under sustained traffic, avoid stalled turns when diagnostics throw, keep permit waiters until their real deadline, and cancel queued host callbacks at task deadlines. (#167683, #167733, #165359, #167740) Thanks @Chessing234.
- **Chat delivery:** deliver activity-summary updates after compaction, hide managed media directives in CR-only replies, keep node completion follow-ups in their originating conversation, preserve live node approval handoffs, and stop false Yield failed warnings in group chats. (#165024, #164657, #160675, #166971, #161154, #166396) Thanks @ly85206559, @obviyus, and @brokemac79.
- **Session creation:** keep new sessions working while other local turns start or finish, recognize agents immediately after agents.create, keep parent-only sessions bound to their agent, and bind required worker sessions during workspace binding. (#165984, #167894, #165929, #167162) Thanks @alkor2000, @markstones78, and @RomneyDa.
- **Chat history:** stop endless retries for sessions in skipped agent stores, return anchored history for pre-reset Claude CLI-bound messages, retain tool history details and channel startup context, and keep generated and truncated session titles UTF-16 safe and balanced. (#165408, #166578, #164848, #141240, #167584) Thanks @obviyus, @VACInc, @sjf-oa, @sjf, @hugenshen, and @cursoragent.
- **Claude CLI and helper calls:** keep claude-cli session tools and later CLI bridge calls working after the starting turn ends, route shorthand Anthropic CLI auth refs correctly, keep the session observer working on CLI-backed utility models, and keep OpenClaw helper calls working across runtime changes. (#165432, #165428, #84374, #162067, #166235) Thanks @Oldrich333, @Leit-motif, @nano-richtera, @joshavant, @obviyus, @rogeriochaves, @llmsommelier, and @PollyBot13.
- **Models and catalog:** keep Codex selectable after startup and deferred agent startup, recheck models after failed catalog recovery, stop catalog continuations hanging while models load, and keep OpenRouter and LM Studio thinking levels intact. (#165979, #166081, #162901, #166089, #166705, #164478, #164597) Thanks @scotthuang, @ericcaiwx-star, @obviyus, @ooiuuii, and @VACInc.
- **Usage and metrics:** report usage for silent replies, estimate context when compatible streams omit usage, include background utility completions in token and cost metrics, and keep usage ranges ordered when the host skipped a date. (#152396, #166151, #167986, #165523, #164140) Thanks @ly85206559, @obviyus, @MutenCath, @fede-kamel, @ericcurtin, @etzelm, @SashaMIT, and @DasX.
- **Startup and readiness:** show startup failures even when cleanup fails, stop small agents waiting on larger agents, prevent public chat 503s and stalls after startup, avoid failures during temporary state conten