OpenClaw Official Changelog

Changes

• ·OpenAI/images: default the bundled image-generation provider and live media smoke tests to `gpt-image-2`, and advertise the newer 2K/4K OpenAI size hints in image-generation docs and tool metadata.

Fixes

• ·Plugins/doctor: repair bundled plugin runtime dependencies from doctor paths so packaged installs can recover missing channel/provider dependencies without broad core dependency installs.
• ·Image generation: log failed provider/model candidates at warn level before automatic provider fallback, so OpenAI image failures are visible in the gateway log even when a later provider succeeds.
• ·Auth/commands: require owner identity (an owner-candidate match or internal `operator.admin`) for owner-enforced commands instead of treating wildcard channel `allowFrom` or empty owner-candidate lists as sufficient, so non-owner senders can no longer reach owner-only commands through a permissive fallback when `enforceOwnerForCommands=true` and `commands.ownerAllowFrom` is unset. (#69774)
• ·Slack: preserve thread aliases in runtime outbound sends so generic runtime sends stay in the intended Slack thread when the caller supplies `threadTs`. (#62947)
• ·Browser: reject invalid `ax<N>` accessibility refs in act paths immediately instead of waiting for the browser action timeout. (#69924)
• ·npm/install: mirror the `node-domexception` alias into root `package.json` `overrides`, so npm installs stop surfacing the deprecated `google-auth-library -> gaxios -> node-fetch -> fetch-blob -> node-domexception` chain pulled through Pi/Google runtime deps.

Changes

• ·Onboard/wizard: restyle the setup security disclaimer with a single yellow warning banner, section headings and bulleted checklists, and un-dim the note body so key guidance is easy to scan; add a loading spinner during the initial model catalog load so the wizard no longer goes blank while it runs; add an "API key" placeholder to provider API key prompts. (#69553)
• ·Agents/prompts: strengthen the default system prompt and OpenAI GPT-5 overlay with clearer completion bias, live-state checks, weak-result recovery, and verification-before-final guidance.
• ·Models/costs: support tiered model pricing from cached catalogs and configured models, and include bundled Moonshot Kimi K2.6/K2.5 cost estimates for token-usage reports. (#67605)
• ·Sessions/Maintenance: enforce the built-in entry cap and age prune by default, and prune oversized stores at load time so accumulated cron/executor session backlogs cannot OOM the gateway before the write path runs. (#69404)
• ·Plugins/tests: reuse plugin loader alias and Jiti config resolution across repeated same-context loads, reducing import-heavy test overhead. (#69316)
• ·Cron: split runtime execution state into `jobs-state.json` so `jobs.json` stays stable for git-tracked job definitions. (#63105)
• ·Agents/compaction: send opt-in start and completion notices during context compaction. (#67830)
• ·Moonshot/Kimi: default bundled Moonshot setup, web search, and media-understanding surfaces to `kimi-k2.6` while keeping `kimi-k2.5` available for compatibility. (#69477)
• ·Moonshot/Kimi: allow `thinking.keep = "all"` on `moonshot/kimi-k2.6`, and strip it for other Moonshot models or requests where pinned `tool_choice` disables thinking. (#68816)
• ·BlueBubbles/groups: forward per-group `systemPrompt` config into inbound context `GroupSystemPrompt` so configured group-specific behavioral instructions (for example threaded-reply and tapback conventions) are injected on every turn. Supports `"*"` wildcard fallback matching the existing `requireMention` pattern. Closes #60665. (#69198)
• ·Plugins/tasks: add a detached runtime registration contract so plugin executors can own detached task lifecycle and cancellation without reaching into core task internals. (#68915)
• ·Terminal/logging: optimize `sanitizeForLog()` by replacing the iterative control-character stripping loop with a single regex pass while preserving the existing ANSI-first sanitization behavior. (#67205)
• ·QA/CI: make `openclaw qa suite` and `openclaw qa telegram` fail by default when scenarios fail, add `--allow-failures` for artifact-only runs, and tighten live-lane defaults for CI automation. (#69122)
• ·Mattermost: stream thinking, tool activity, and partial reply text into a single draft preview post that finalizes in place when safe. (#47838)

Fixes

• ·Exec/YOLO: stop rejecting gateway-host exec in `security=full` plus `ask=off` mode via the Python/Node script preflight hardening path, so promptless YOLO exec once again runs direct interpreter stdin and heredoc forms such as `node <<'NODE' ... NODE`.
• ·OpenAI Codex: normalize legacy `openai-completions` transport overrides on default OpenAI/Codex and GitHub Copilot-compatible hosts back to the native Codex Responses transport while leaving custom proxies untouched. (#45304, #42194)
• ·Anthropic/plugins: scope Anthropic `api: "anthropic-messages"` defaulting to Anthropic-owned providers, so `openai-codex` and other providers without an explicit `api` no longer get rewritten to the wrong transport. Fixes #64534.
• ·fix(qqbot): add SSRF guard to direct-upload URL paths in uploadC2CMedia and uploadGroupMedia [AI-assisted]. (#69595)
• ·fix(gateway): enforce allowRequestSessionKey gate on template-rendered mapping sessionKeys. (#69381)
• ·Browser/Chrome MCP: surface `DevToolsActivePort` attach failures as browser-connectivity errors instead of a generic "waiting for tabs" timeout, and point signed-out fallbacks toward the managed `openclaw` profile.
• ·Webchat/images: treat inline image attachments as media for empty-turn gating while still ignoring metadata-only blank turns. (#69474)
• ·Discord/think: only show `adaptive` in `/think` autocomplete for provider/model pairs that actually support provider-managed adaptive thinking, so GPT/OpenAI models no longer advertise an Anthropic-only option.
• ·Thinking: only expose `max` for models that explicitly support provider max reasoning, and remap stored `max` settings to the largest supported thinking mode when users switch to another model.
• ·Gateway/usage: bound the cost usage cache with FIFO eviction so date/range lookups cannot grow unbounded. (#68842)
• ·OpenAI/Responses: resolve `/think` levels against each GPT model's supported reasoning efforts so `/think off` no longer becomes high reasoning or sends unsupported `reasoning.effort: "none"` payloads.
• ·Lobster/TaskFlow: allow managed approval resumes to use `approvalId` without a resume token, and persist that id in approval wait state. (#69559)
• ·Plugins/startup: install bundled runtime dependencies into each plugin's own runtime directory, reuse source-checkout repair caches after rebuilds, and log only packages that were actually installed so repeated Gateway starts stay quiet once deps are present.
• ·Plugins/startup: ignore pnpm's `npm_execpath` when repairing bundled plugin runtime dependencies and skip workspace-only package specs so npm-only install flags or local workspace links do not break packaged plugin startup.
• ·MCP: block interpreter-startup env keys such as `NODE_OPTIONS` for stdio servers while preserving ordinary credential and proxy env vars. (#69540)
• ·Agents/shell: ignore non-interactive placeholder shells like `/usr/bin/false` and `/sbin/nologin`, falling back to `sh` so service-user exec runs no longer exit immediately. (#69308)
• ·Setup/TUI: relaunch the setup hatch TUI in a fresh process while preserving the configured gateway target and auth source, so onboarding recovers terminal state cleanly without exposing gateway secrets on command-line args. (#69524)
• ·Codex: avoid re-exposing the image-generation tool on native vision turns with inbound images, and keep bare image-model overrides on the configured image provider. (#65061)
• ·Sessions/reset: clear auto-sourced model, provider, and auth-profile overrides on `/new` and `/reset` while preserving explicit user selections, so channel sessions stop staying pinned to runtime fallback choices. (#69419)
• ·Sessions/costs: snapshot `estimatedCostUsd` like token counters so repeated persist paths no longer compound the same run cost by up to dozens of times. (#69403)
• ·OpenAI Codex: route ChatGPT/Codex OAuth Responses requests through the `/backend-api/codex` endpoint so `openai-codex/gpt-5.4` no longer hits the removed `/backend-api/responses` alias. (#69336)
• ·OpenAI/Responses: omit disabled reasoning payloads when `/think off` is active, so GPT reasoning models no longer receive unsupported `reasoning.effort: "none"` requests. (#61982)
• ·Gateway/pairing: treat loopback shared-secret node-host, TUI, and gateway clients as local for pairing decisions, so trusted local tools no longer reconnect as remote clients and fail with `pairing required`. (#69431)
• ·Active Memory: degrade gracefully when memory recall fails during prompt building, logging a warning and letting the reply continue without memory context instead of failing the whole turn. (#69485)
• ·Ollama: add provider-policy defaults for `baseUrl` and `models` so implicit local discovery can run before config validation rejects a minimal Ollama provider config. (#69370)
• ·Agents/model selection: clear transient auto-failover session overrides before each turn so recovered primary models are retried immediately without emitting user-override reset warnings. (#69365)
• ·Auto-reply: apply silent `NO_REPLY` policy per conversation type, so direct chats get a helpful rewritten reply while groups and internal deliveries can remain quiet. (#68644)
• ·Telegram/status reactions: honor `messages.removeAckAfterReply` when lifecycle status reactions are enabled, clearing or restoring the reaction after success/error using the configured hold timings. (#68067)
• ·Web search/plugins: resolve plugin-scoped SecretRef API keys for bundled Exa, Firecrawl, Gemini, Kimi, Perplexity, Tavily, and Grok web-search providers when they are selected through the shared web-search config. (#68424)
• ·Telegram/polling: raise the default polling watchdog threshold from 90s to 120s and add configurable `channels.telegram.pollingStallThresholdMs` (also per-account) so long-running Telegram work gets more room before polling is treated as stalled. (#57737)
• ·Telegram/polling: bound the persisted-offset confirmation `getUpdates` probe with a client-side timeout so a zombie socket cannot hang polling recovery before the runner watchdog starts. (#50368)
• ·Agents/Pi runner: retry silent `stopReason=error` turns with no output when no side effects ran, so non-frontier providers that briefly return empty error turns get another chance instead of ending the session early. (#68310)
• ·Plugins/memory: preserve the active memory capability when read-only snapshot plugin loads run, so status and provider discovery paths no longer wipe memory public artifacts. (#69219)
• ·Plugins: keep only the highest-precedence manifest when distinct discovered plugins share an id, so lower-precedence global or workspace duplicates no longer load beside bundled or config-selected plugins. (#41626)
• ·fix(security): block MINIMAX_API_HOST workspace env injection and remove env-driven URL routing [AI-assisted]. (#67300)
• ·Cron/delivery: treat explicit `delivery.mode: "none"` runs as not requested even if the runner reports `delivered: false`, so no-delivery cron jobs no longer persist false delivery failures or errors. (#69285)
• ·Plugins/install: repair active and default-enabled bundled plugin runtime dependencies before import in packaged installs, so bundled Discord, WhatsApp, Slack, Telegram, and provider plugins work without putting their dependency trees in core.
• ·BlueBubbles: raise the outbound `/api/v1/message/text` send timeout default from 10s to 30s, and add a configurable `channels.bluebubbles.sendTimeoutMs` (also per-account) so macOS 26 setups where Private API iMessage sends stall for 60+ seconds no longer silently lose messages at the 10s abort. Probes, chat lookups, and health checks keep the shorter 10s default. Fixes #67486. (#69193)
• ·Agents/bootstrap: budget truncation markers against per-file caps, preserve source content instead of silently wasting bootstrap bytes, and avoid marker-only output in tiny-budget truncation cases. (#69114)
• ·Context engine/plugins: stop rejecting third-party context engines whose `info.id` differs from the registered plugin slot id. The strict-match contract added in 2026.4.14 broke `lossless-claw` and other plugins whose internal engine id does not equal the slot id they are registered under, producing repeated `info.id must match registered id` lane failures on every turn. Fixes #66601. (#66678)
• ·Agents/compaction: rename embedded Pi compaction lifecycle events to `compaction_start` / `compaction_end` so OpenClaw stays aligned with `pi-coding-agent` 0.66.1 event naming. (#67713)
• ·Security/dotenv: block all `OPENCLAW_*` keys from untrusted workspace `.env` files so workspace-local env loading fails closed for new runtime-control variables instead of silently inheriting them. (#473)
• ·Gateway/device pairing: restrict non-admin paired-device sessions (device-token auth) to their own pairing list, approve, and reject actions so a paired device cannot enumerate other devices or approve/reject pairing requests authored by another device. Admin and shared-secret operator sessions retain full visibility. (#69375)
• ·Agents/gateway tool: extend the agent-facing `gateway` tool's config mutation guard so model-driven `config.patch` and `config.apply` cannot rewrite operator-trusted paths (sandbox, plugin trust, gateway auth/TLS, hook routing and tokens, SSRF policy, MCP servers, workspace filesystem hardening) and cannot bypass the guard by editing per-agent sandbox, tools, or embedded-Pi overrides in place under `agents.list[]`. (#69377)
• ·Gateway/websocket broadcasts: require `operator.read` (or higher) for chat, agent, and tool-result event frames so pairing-scoped and node-role sessions no longer passively receive session chat content, and scope-gate unknown broadcast events by default. Plugin-defined `plugin.*` broadcasts are scoped to operator.write/admin, and status/transport events (`heartbeat`, `presence`, `tick`, etc.) remain unrestricted. Per-client sequence numbers preserve per-connection monotonicity. (#69373)
• ·Agents/compaction: always reload embedded Pi resources through an explicit loader and reapply reserve-token overrides so runs without extension factories no longer silently lose compaction settings before session start. (#67146)
• ·Memory-core/dreaming: normalize sweep timestamps and reuse hashed narrative session keys for fallback cleanup so Dreaming narrative sub-sessions stop leaking. (#67023)
• ·Gateway/startup: delay HTTP bind until websocket handlers are attached, so immediate post-startup websocket health/connect probes no longer hit the startup race window. (#43392)
• ·Codex/app-server: release the session lane when a downstream consumer throws while draining the `turn/completed` notification, so follow-up messages after a Codex plugin reply stop queueing behind a stale lane lock. Fixes #67996. (#69072)
• ·Codex/app-server: default approval handling to `on-request` so Codex harness sessions do not start with overly permissive tool approvals. (#68721)
• ·Cron/delivery: keep isolated cron chat delivery tools available, resolve `channel: "last"` targets from the gateway, show delivery previews in `cron list/show`, and avoid duplicate fallback sends after direct message-tool delivery. (#69587)
• ·Cron/Telegram: key isolated direct-delivery dedupe to each cron execution instead of the reused session id, so recurring Telegram announce runs no longer report delivered while silently skipping later sends. (#69000)
• ·Models/Kimi: default bundled Kimi thinking to off and normalize Anthropic-compatible `thinking` payloads so stale session `/think` state no longer silently re-enables reasoning on Kimi runs. (#68907)
• ·Control UI/cron: keep the runtime-only `last` delivery sentinel from being materialized into persisted cron delivery and failure-alert channel configs when jobs are created or edited. (#68829)
• ·OpenAI/Responses: strip orphaned reasoning blocks before outbound Responses API calls so compacted or restored histories no longer fail on standalone reasoning items. (#55787)
• ·Cron/CLI: parse PowerShell-style `--tools` allow-lists the same way as comma-separated input, so `cron add` and `cron edit` no longer persist `exec read write` as one combined tool entry on Windows. (#68858)
• ·Browser/user-profile: let existing-session `profile="user"` tool calls auto-route to a connected browser node or use explicit `target="node"`, while still honoring explicit `target="host"` pinning. (#48677)
• ·Discord/slash commands: tolerate partial Discord channel metadata in slash-command and model-picker flows so partial channel objects no longer crash when channel names, topics, or thread parent metadata are unavailable. (#68953)
• ·BlueBubbles: consolidate outbound HTTP through a typed `BlueBubblesClient` that resolves the SSRF policy once at construction so image attachments stop getting blocked on localhost and reactions stop getting blocked on private-IP BB deployments. Fixes #34749 and #59722. (#68234)
• ·Cron/gateway: reject ambiguous announce delivery config at add/update time so invalid multi-channel or target-id provider settings fail early instead of persisting broken cron jobs. (#69015)
• ·Cron/main-session delivery: preserve `heartbeat.target="last"` through deferred wake queuing, gateway wake forwarding, and same-target wake coalescing so queued cron replies still return to the last active chat. (#69021)
• ·Cron/gateway: ignore disabled channels when announce delivery ambiguity is checked, and validate main-session delivery patches against the live cron service default agent so hot-reloaded agent config does not falsely reject valid updates. (#69040)
• ·Matrix/allowlists: hot-reload `dm.allowFrom` and `groupAllowFrom` entries on inbound messages while keeping config removals authoritative, so Matrix allowlist changes no longer require a channel restart to add or revoke a sender. (#68546)
• ·BlueBubbles: always set `method` explicitly on outbound text sends (`"private-api"` when available, `"apple-script"` otherwise), and prefer Private API on macOS 26 even for plain text. Fixes silent delivery failure on macOS setups without Private API where an omitted `method` let BB Server fall back to version-dependent default behavior that silently drops the message (#64480), and the AppleScript `-1700` error on macOS 26 Tahoe plain text sends (#53159). (#69070)
• ·Matrix/commands: recognize slash commands that are prefixed with the bot's Matrix mention, so room messages like `@bot:server /new` trigger the command path without requiring custom mention regexes. (#68570)
• ·Gateway/pairing: return reason-specific `PAIRING_REQUIRED` details, remediation hints, and request ids so unapproved-device and scope-upgrade failures surface actionable recovery guidance in the CLI and Control UI. (#69227)
• ·Agents/subagents: include requested role and runtime timing on subagent failure payloads so parent agents can correlate failed or timed-out child work. (#68726)
• ·Gateway/sessions: reject stale agent-scoped sessions after an agent is removed from config while preserving legacy default-agent main-session aliases. (#65986)
• ·Doctor/gateway: surface pending device pairing requests, scope-upgrade approval drift, and stale device-token mismatch repair steps so `openclaw doctor --fix` no longer leaves pairing/auth setup failures unexplained. (#69210)
• ·Cron/isolated-agent: preserve explicit `delivery.mode: "none"` message targets for isolated runs without inheriting implicit `last` routing, so agent-initiated Telegram sends keep their authored destination while bare `mode:none` jobs stay targetless. (#69153)
• ·Cron/isolated-agent: keep `delivery.mode: "none"` account-only or thread-only configs from inheriting a stale implicit recipient, so isolated runs only resolve message routing when the job authored an explicit `to` target. (#69163)
• ·Gateway/TUI: retry session history while the local gateway is still finishing startup, so `openclaw tui` reconnects no longer fail on transient `chat.history unavailable during gateway startup` errors. (#69164)
• ·BlueBubbles/reactions: fall back to `love` when an agent reacts with an emoji outside the iMessage tapback set (`love`/`like`/`dislike`/`laugh`/`emphasize`/`question`), so wider-vocabulary model reactions like `👀` still produce a visible tapback instead of failing the whole reaction request. Configured ack reactions still validate strictly via the new `normalizeBlueBubblesReactionInputStrict` path. (#64693)
• ·BlueBubbles: prefer iMessage over SMS when both chats exist for the same handle, honor explicit `sms:` targets, and never silently downgrade iMessage-available recipients. (#61781)
• ·Telegram/setup: require numeric `allowFrom` user IDs during setup instead of offering unsupported `@username` DM resolution, and point operators to `from.id`/`getUpdates` for discovery. (#69191)
• ·GitHub Copilot/onboarding: default GitHub Copilot setup to `claude-opus-4.6` and keep the bundled default model list aligned, so new Copilot setups no longer start on the older `gpt-4o` default. (#69207)
• ·Gateway/status: separate reachability, capability, and read-probe reporting so connect-only or scope-limited sessions no longer look fully healthy, and normalize SSH targets entered as `ssh user@host`. (#69215)
• ·Slack: fix outbound replies failing with "unresolved SecretRef" for accounts configured via `file` or `exec` secret sources; the send path now tolerates the runtime snapshot retaining an unresolved channel SecretRef when a boot-resolved token override is already available. (#68954)
• ·Control UI/device pairing: explain scope and role approval upgrades during reconnects, and show requested versus approved access in the Control UI and `openclaw devices` so broader reconnects no longer look like lost pairings. (#69221)
• ·Gateway/Control UI: surface pending scope, role, and device-metadata pairing approvals in auth errors and Control UI hints so broader reconnects no longer look like random auth breakage. (#69226)

Changes

• ·Onboard/wizard: restyle the setup security disclaimer with a single yellow warning banner, section headings and bulleted checklists, and un-dim the note body so key guidance is easy to scan; add a loading spinner during the initial model catalog load so the wizard no longer goes blank while it runs; add an "API key" placeholder to provider API key prompts. (#69553)
• ·Agents/prompts: strengthen the default system prompt and OpenAI GPT-5 overlay with clearer completion bias, live-state checks, weak-result recovery, and verification-before-final guidance.
• ·Models/costs: support tiered model pricing from cached catalogs and configured models, and include bundled Moonshot Kimi K2.6/K2.5 cost estimates for token-usage reports. (#67605)
• ·Sessions/Maintenance: enforce the built-in entry cap and age prune by default, and prune oversized stores at load time so accumulated cron/executor session backlogs cannot OOM the gateway before the write path runs. (#69404)
• ·Plugins/tests: reuse plugin loader alias and Jiti config resolution across repeated same-context loads, reducing import-heavy test overhead. (#69316)
• ·Cron: split runtime execution state into `jobs-state.json` so `jobs.json` stays stable for git-tracked job definitions. (#63105)
• ·Agents/compaction: send opt-in start and completion notices during context compaction. (#67830)
• ·Moonshot/Kimi: default bundled Moonshot setup, web search, and media-understanding surfaces to `kimi-k2.6` while keeping `kimi-k2.5` available for compatibility. (#69477)
• ·Moonshot/Kimi: allow `thinking.keep = "all"` on `moonshot/kimi-k2.6`, and strip it for other Moonshot models or requests where pinned `tool_choice` disables thinking. (#68816)
• ·BlueBubbles/groups: forward per-group `systemPrompt` config into inbound context `GroupSystemPrompt` so configured group-specific behavioral instructions (for example threaded-reply and tapback conventions) are injected on every turn. Supports `"*"` wildcard fallback matching the existing `requireMention` pattern. Closes #60665. (#69198)
• ·Plugins/tasks: add a detached runtime registration contract so plugin executors can own detached task lifecycle and cancellation without reaching into core task internals. (#68915)
• ·Terminal/logging: optimize `sanitizeForLog()` by replacing the iterative control-character stripping loop with a single regex pass while preserving the existing ANSI-first sanitization behavior. (#67205)
• ·QA/CI: make `openclaw qa suite` and `openclaw qa telegram` fail by default when scenarios fail, add `--allow-failures` for artifact-only runs, and tighten live-lane defaults for CI automation. (#69122)
• ·Mattermost: stream thinking, tool activity, and partial reply text into a single draft preview post that finalizes in place when safe. (#47838)

Fixes

• ·Exec/YOLO: stop rejecting gateway-host exec in `security=full` plus `ask=off` mode via the Python/Node script preflight hardening path, so promptless YOLO exec once again runs direct interpreter stdin and heredoc forms such as `node <<'NODE' ... NODE`.
• ·OpenAI Codex: normalize legacy `openai-completions` transport overrides on default OpenAI/Codex and GitHub Copilot-compatible hosts back to the native Codex Responses transport while leaving custom proxies untouched. (#45304, #42194)
• ·Anthropic/plugins: scope Anthropic `api: "anthropic-messages"` defaulting to Anthropic-owned providers, so `openai-codex` and other providers without an explicit `api` no longer get rewritten to the wrong transport. Fixes #64534.
• ·fix(qqbot): add SSRF guard to direct-upload URL paths in uploadC2CMedia and uploadGroupMedia [AI-assisted]. (#69595)
• ·fix(gateway): enforce allowRequestSessionKey gate on template-rendered mapping sessionKeys. (#69381)
• ·Browser/Chrome MCP: surface `DevToolsActivePort` attach failures as browser-connectivity errors instead of a generic "waiting for tabs" timeout, and point signed-out fallbacks toward the managed `openclaw` profile.
• ·Webchat/images: treat inline image attachments as media for empty-turn gating while still ignoring metadata-only blank turns. (#69474)
• ·Discord/think: only show `adaptive` in `/think` autocomplete for provider/model pairs that actually support provider-managed adaptive thinking, so GPT/OpenAI models no longer advertise an Anthropic-only option.
• ·Thinking: only expose `max` for models that explicitly support provider max reasoning, and remap stored `max` settings to the largest supported thinking mode when users switch to another model.
• ·Gateway/usage: bound the cost usage cache with FIFO eviction so date/range lookups cannot grow unbounded. (#68842)
• ·OpenAI/Responses: resolve `/think` levels against each GPT model's supported reasoning efforts so `/think off` no longer becomes high reasoning or sends unsupported `reasoning.effort: "none"` payloads.
• ·Lobster/TaskFlow: allow managed approval resumes to use `approvalId` without a resume token, and persist that id in approval wait state. (#69559)
• ·Plugins/startup: install bundled runtime dependencies into each plugin's own runtime directory, reuse source-checkout repair caches after rebuilds, and log only packages that were actually installed so repeated Gateway starts stay quiet once deps are present.
• ·Plugins/startup: ignore pnpm's `npm_execpath` when repairing bundled plugin runtime dependencies and skip workspace-only package specs so npm-only install flags or local workspace links do not break packaged plugin startup.
• ·MCP: block interpreter-startup env keys such as `NODE_OPTIONS` for stdio servers while preserving ordinary credential and proxy env vars. (#69540)
• ·Agents/shell: ignore non-interactive placeholder shells like `/usr/bin/false` and `/sbin/nologin`, falling back to `sh` so service-user exec runs no longer exit immediately. (#69308)
• ·Setup/TUI: relaunch the setup hatch TUI in a fresh process while preserving the configured gateway target and auth source, so onboarding recovers terminal state cleanly without exposing gateway secrets on command-line args. (#69524)
• ·Codex: avoid re-exposing the image-generation tool on native vision turns with inbound images, and keep bare image-model overrides on the configured image provider. (#65061)
• ·Sessions/reset: clear auto-sourced model, provider, and auth-profile overrides on `/new` and `/reset` while preserving explicit user selections, so channel sessions stop staying pinned to runtime fallback choices. (#69419)
• ·Sessions/costs: snapshot `estimatedCostUsd` like token counters so repeated persist paths no longer compound the same run cost by up to dozens of times. (#69403)
• ·OpenAI Codex: route ChatGPT/Codex OAuth Responses requests through the `/backend-api/codex` endpoint so `openai-codex/gpt-5.4` no longer hits the removed `/backend-api/responses` alias. (#69336)
• ·OpenAI/Responses: omit disabled reasoning payloads when `/think off` is active, so GPT reasoning models no longer receive unsupported `reasoning.effort: "none"` requests. (#61982)
• ·Gateway/pairing: treat loopback shared-secret node-host, TUI, and gateway clients as local for pairing decisions, so trusted local tools no longer reconnect as remote clients and fail with `pairing required`. (#69431)
• ·Active Memory: degrade gracefully when memory recall fails during prompt building, logging a warning and letting the reply continue without memory context instead of failing the whole turn. (#69485)
• ·Ollama: add provider-policy defaults for `baseUrl` and `models` so implicit local discovery can run before config validation rejects a minimal Ollama provider config. (#69370)
• ·Agents/model selection: clear transient auto-failover session overrides before each turn so recovered primary models are retried immediately without emitting user-override reset warnings. (#69365)
• ·Auto-reply: apply silent `NO_REPLY` policy per conversation type, so direct chats get a helpful rewritten reply while groups and internal deliveries can remain quiet. (#68644)
• ·Telegram/status reactions: honor `messages.removeAckAfterReply` when lifecycle status reactions are enabled, clearing or restoring the reaction after success/error using the configured hold timings. (#68067)
• ·Web search/plugins: resolve plugin-scoped SecretRef API keys for bundled Exa, Firecrawl, Gemini, Kimi, Perplexity, Tavily, and Grok web-search providers when they are selected through the shared web-search config. (#68424)
• ·Telegram/polling: raise the default polling watchdog threshold from 90s to 120s and add configurable `channels.telegram.pollingStallThresholdMs` (also per-account) so long-running Telegram work gets more room before polling is treated as stalled. (#57737)
• ·Telegram/polling: bound the persisted-offset confirmation `getUpdates` probe with a client-side timeout so a zombie socket cannot hang polling recovery before the runner watchdog starts. (#50368)
• ·Agents/Pi runner: retry silent `stopReason=error` turns with no output when no side effects ran, so non-frontier providers that briefly return empty error turns get another chance instead of ending the session early. (#68310)
• ·Plugins/memory: preserve the active memory capability when read-only snapshot plugin loads run, so status and provider discovery paths no longer wipe memory public artifacts. (#69219)
• ·Plugins: keep only the highest-precedence manifest when distinct discovered plugins share an id, so lower-precedence global or workspace duplicates no longer load beside bundled or config-selected plugins. (#41626)
• ·fix(security): block MINIMAX_API_HOST workspace env injection and remove env-driven URL routing [AI-assisted]. (#67300)
• ·Cron/delivery: treat explicit `delivery.mode: "none"` runs as not requested even if the runner reports `delivered: false`, so no-delivery cron jobs no longer persist false delivery failures or errors. (#69285)
• ·Plugins/install: repair active and default-enabled bundled plugin runtime dependencies before import in packaged installs, so bundled Discord, WhatsApp, Slack, Telegram, and provider plugins work without putting their dependency trees in core.
• ·BlueBubbles: raise the outbound `/api/v1/message/text` send timeout default from 10s to 30s, and add a configurable `channels.bluebubbles.sendTimeoutMs` (also per-account) so macOS 26 setups where Private API iMessage sends stall for 60+ seconds no longer silently lose messages at the 10s abort. Probes, chat lookups, and health checks keep the shorter 10s default. Fixes #67486. (#69193)
• ·Agents/bootstrap: budget truncation markers against per-file caps, preserve source content instead of silently wasting bootstrap bytes, and avoid marker-only output in tiny-budget truncation cases. (#69114)
• ·Context engine/plugins: stop rejecting third-party context engines whose `info.id` differs from the registered plugin slot id. The strict-match contract added in 2026.4.14 broke `lossless-claw` and other plugins whose internal engine id does not equal the slot id they are registered under, producing repeated `info.id must match registered id` lane failures on every turn. Fixes #66601. (#66678)
• ·Agents/compaction: rename embedded Pi compaction lifecycle events to `compaction_start` / `compaction_end` so OpenClaw stays aligned with `pi-coding-agent` 0.66.1 event naming. (#67713)
• ·Security/dotenv: block all `OPENCLAW_*` keys from untrusted workspace `.env` files so workspace-local env loading fails closed for new runtime-control variables instead of silently inheriting them. (#473)
• ·Gateway/device pairing: restrict non-admin paired-device sessions (device-token auth) to their own pairing list, approve, and reject actions so a paired device cannot enumerate other devices or approve/reject pairing requests authored by another device. Admin and shared-secret operator sessions retain full visibility. (#69375)
• ·Agents/gateway tool: extend the agent-facing `gateway` tool's config mutation guard so model-driven `config.patch` and `config.apply` cannot rewrite operator-trusted paths (sandbox, plugin trust, gateway auth/TLS, hook routing and tokens, SSRF policy, MCP servers, workspace filesystem hardening) and cannot bypass the guard by editing per-agent sandbox, tools, or embedded-Pi overrides in place under `agents.list[]`. (#69377)
• ·Gateway/websocket broadcasts: require `operator.read` (or higher) for chat, agent, and tool-result event frames so pairing-scoped and node-role sessions no longer passively receive session chat content, and scope-gate unknown broadcast events by default. Plugin-defined `plugin.*` broadcasts are scoped to operator.write/admin, and status/transport events (`heartbeat`, `presence`, `tick`, etc.) remain unrestricted. Per-client sequence numbers preserve per-connection monotonicity. (#69373)
• ·Agents/compaction: always reload embedded Pi resources through an explicit loader and reapply reserve-token overrides so runs without extension factories no longer silently lose compaction settings before session start. (#67146)
• ·Memory-core/dreaming: normalize sweep timestamps and reuse hashed narrative session keys for fallback cleanup so Dreaming narrative sub-sessions stop leaking. (#67023)
• ·Gateway/startup: delay HTTP bind until websocket handlers are attached, so immediate post-startup websocket health/connect probes no longer hit the startup race window. (#43392)
• ·Codex/app-server: release the session lane when a downstream consumer throws while draining the `turn/completed` notification, so follow-up messages after a Codex plugin reply stop queueing behind a stale lane lock. Fixes #67996. (#69072)
• ·Codex/app-server: default approval handling to `on-request` so Codex harness sessions do not start with overly permissive tool approvals. (#68721)
• ·Cron/delivery: keep isolated cron chat delivery tools available, resolve `channel: "last"` targets from the gateway, show delivery previews in `cron list/show`, and avoid duplicate fallback sends after direct message-tool delivery. (#69587)
• ·Cron/Telegram: key isolated direct-delivery dedupe to each cron execution instead of the reused session id, so recurring Telegram announce runs no longer report delivered while silently skipping later sends. (#69000)
• ·Models/Kimi: default bundled Kimi thinking to off and normalize Anthropic-compatible `thinking` payloads so stale session `/think` state no longer silently re-enables reasoning on Kimi runs. (#68907)
• ·Control UI/cron: keep the runtime-only `last` delivery sentinel from being materialized into persisted cron delivery and failure-alert channel configs when jobs are created or edited. (#68829)
• ·OpenAI/Responses: strip orphaned reasoning blocks before outbound Responses API calls so compacted or restored histories no longer fail on standalone reasoning items. (#55787)
• ·Cron/CLI: parse PowerShell-style `--tools` allow-lists the same way as comma-separated input, so `cron add` and `cron edit` no longer persist `exec read write` as one combined tool entry on Windows. (#68858)
• ·Browser/user-profile: let existing-session `profile="user"` tool calls auto-route to a connected browser node or use explicit `target="node"`, while still honoring explicit `target="host"` pinning. (#48677)
• ·Discord/slash commands: tolerate partial Discord channel metadata in slash-command and model-picker flows so partial channel objects no longer crash when channel names, topics, or thread parent metadata are unavailable. (#68953)
• ·BlueBubbles: consolidate outbound HTTP through a typed `BlueBubblesClient` that resolves the SSRF policy once at construction so image attachments stop getting blocked on localhost and reactions stop getting blocked on private-IP BB deployments. Fixes #34749 and #59722. (#68234)
• ·Cron/gateway: reject ambiguous announce delivery config at add/update time so invalid multi-channel or target-id provider settings fail early instead of persisting broken cron jobs. (#69015)
• ·Cron/main-session delivery: preserve `heartbeat.target="last"` through deferred wake queuing, gateway wake forwarding, and same-target wake coalescing so queued cron replies still return to the last active chat. (#69021)
• ·Cron/gateway: ignore disabled channels when announce delivery ambiguity is checked, and validate main-session delivery patches against the live cron service default agent so hot-reloaded agent config does not falsely reject valid updates. (#69040)
• ·Matrix/allowlists: hot-reload `dm.allowFrom` and `groupAllowFrom` entries on inbound messages while keeping config removals authoritative, so Matrix allowlist changes no longer require a channel restart to add or revoke a sender. (#68546)
• ·BlueBubbles: always set `method` explicitly on outbound text sends (`"private-api"` when available, `"apple-script"` otherwise), and prefer Private API on macOS 26 even for plain text. Fixes silent delivery failure on macOS setups without Private API where an omitted `method` let BB Server fall back to version-dependent default behavior that silently drops the message (#64480), and the AppleScript `-1700` error on macOS 26 Tahoe plain text sends (#53159). (#69070)
• ·Matrix/commands: recognize slash commands that are prefixed with the bot's Matrix mention, so room messages like `@bot:server /new` trigger the command path without requiring custom mention regexes. (#68570)
• ·Gateway/pairing: return reason-specific `PAIRING_REQUIRED` details, remediation hints, and request ids so unapproved-device and scope-upgrade failures surface actionable recovery guidance in the CLI and Control UI. (#69227)
• ·Agents/subagents: include requested role and runtime timing on subagent failure payloads so parent agents can correlate failed or timed-out child work. (#68726)
• ·Gateway/sessions: reject stale agent-scoped sessions after an agent is removed from config while preserving legacy default-agent main-session aliases. (#65986)
• ·Doctor/gateway: surface pending device pairing requests, scope-upgrade approval drift, and stale device-token mismatch repair steps so `openclaw doctor --fix` no longer leaves pairing/auth setup failures unexplained. (#69210)
• ·Cron/isolated-agent: preserve explicit `delivery.mode: "none"` message targets for isolated runs without inheriting implicit `last` routing, so agent-initiated Telegram sends keep their authored destination while bare `mode:none` jobs stay targetless. (#69153)
• ·Cron/isolated-agent: keep `delivery.mode: "none"` account-only or thread-only configs from inheriting a stale implicit recipient, so isolated runs only resolve message routing when the job authored an explicit `to` target. (#69163)
• ·Gateway/TUI: retry session history while the local gateway is still finishing startup, so `openclaw tui` reconnects no longer fail on transient `chat.history unavailable during gateway startup` errors. (#69164)
• ·BlueBubbles/reactions: fall back to `love` when an agent reacts with an emoji outside the iMessage tapback set (`love`/`like`/`dislike`/`laugh`/`emphasize`/`question`), so wider-vocabulary model reactions like `👀` still produce a visible tapback instead of failing the whole reaction request. Configured ack reactions still validate strictly via the new `normalizeBlueBubblesReactionInputStrict` path. (#64693)
• ·BlueBubbles: prefer iMessage over SMS when both chats exist for the same handle, honor explicit `sms:` targets, and never silently downgrade iMessage-available recipients. (#61781)
• ·Telegram/setup: require numeric `allowFrom` user IDs during setup instead of offering unsupported `@username` DM resolution, and point operators to `from.id`/`getUpdates` for discovery. (#69191)
• ·GitHub Copilot/onboarding: default GitHub Copilot setup to `claude-opus-4.6` and keep the bundled default model list aligned, so new Copilot setups no longer start on the older `gpt-4o` default. (#69207)
• ·Gateway/status: separate reachability, capability, and read-probe reporting so connect-only or scope-limited sessions no longer look fully healthy, and normalize SSH targets entered as `ssh user@host`. (#69215)
• ·Slack: fix outbound replies failing with "unresolved SecretRef" for accounts configured via `file` or `exec` secret sources; the send path now tolerates the runtime snapshot retaining an unresolved channel SecretRef when a boot-resolved token override is already available. (#68954)
• ·Control UI/device pairing: explain scope and role approval upgrades during reconnects, and show requested versus approved access in the Control UI and `openclaw devices` so broader reconnects no longer look like lost pairings. (#69221)
• ·Gateway/Control UI: surface pending scope, role, and device-metadata pairing approvals in auth errors and Control UI hints so broader reconnects no longer look like random auth breakage. (#69226)

Changes

• ·Onboard/wizard: restyle the setup security disclaimer with a single yellow warning banner, section headings and bulleted checklists, and un-dim the note body so key guidance is easy to scan; add a loading spinner during the initial model catalog load so the wizard no longer goes blank while it runs; add an "API key" placeholder to provider API key prompts. (#69553)
• ·Agents/prompts: strengthen the default system prompt and OpenAI GPT-5 overlay with clearer completion bias, live-state checks, weak-result recovery, and verification-before-final guidance.
• ·Models/costs: support tiered model pricing from cached catalogs and configured models, and include bundled Moonshot Kimi K2.6/K2.5 cost estimates for token-usage reports. (#67605)
• ·Sessions/Maintenance: enforce the built-in entry cap and age prune by default, and prune oversized stores at load time so accumulated cron/executor session backlogs cannot OOM the gateway before the write path runs. (#69404)
• ·Plugins/tests: reuse plugin loader alias and Jiti config resolution across repeated same-context loads, reducing import-heavy test overhead. (#69316)
• ·Cron: split runtime execution state into `jobs-state.json` so `jobs.json` stays stable for git-tracked job definitions. (#63105)
• ·Agents/compaction: send opt-in start and completion notices during context compaction. (#67830)
• ·Moonshot/Kimi: default bundled Moonshot setup, web search, and media-understanding surfaces to `kimi-k2.6` while keeping `kimi-k2.5` available for compatibility. (#69477)
• ·Moonshot/Kimi: allow `thinking.keep = "all"` on `moonshot/kimi-k2.6`, and strip it for other Moonshot models or requests where pinned `tool_choice` disables thinking. (#68816)
• ·BlueBubbles/groups: forward per-group `systemPrompt` config into inbound context `GroupSystemPrompt` so configured group-specific behavioral instructions (for example threaded-reply and tapback conventions) are injected on every turn. Supports `"*"` wildcard fallback matching the existing `requireMention` pattern. Closes #60665. (#69198)
• ·Plugins/tasks: add a detached runtime registration contract so plugin executors can own detached task lifecycle and cancellation without reaching into core task internals. (#68915)
• ·Terminal/logging: optimize `sanitizeForLog()` by replacing the iterative control-character stripping loop with a single regex pass while preserving the existing ANSI-first sanitization behavior. (#67205)
• ·QA/CI: make `openclaw qa suite` and `openclaw qa telegram` fail by default when scenarios fail, add `--allow-failures` for artifact-only runs, and tighten live-lane defaults for CI automation. (#69122)
• ·Mattermost: stream thinking, tool activity, and partial reply text into a single draft preview post that finalizes in place when safe. (#47838)

Fixes

• ·Exec/YOLO: stop rejecting gateway-host exec in `security=full` plus `ask=off` mode via the Python/Node script preflight hardening path, so promptless YOLO exec once again runs direct interpreter stdin and heredoc forms such as `node <<'NODE' ... NODE`.
• ·OpenAI Codex: normalize legacy `openai-completions` transport overrides on default OpenAI/Codex and GitHub Copilot-compatible hosts back to the native Codex Responses transport while leaving custom proxies untouched. (#45304, #42194)
• ·Anthropic/plugins: scope Anthropic `api: "anthropic-messages"` defaulting to Anthropic-owned providers, so `openai-codex` and other providers without an explicit `api` no longer get rewritten to the wrong transport. Fixes #64534.
• ·fix(qqbot): add SSRF guard to direct-upload URL paths in uploadC2CMedia and uploadGroupMedia [AI-assisted]. (#69595)
• ·fix(gateway): enforce allowRequestSessionKey gate on template-rendered mapping sessionKeys. (#69381)
• ·Browser/Chrome MCP: surface `DevToolsActivePort` attach failures as browser-connectivity errors instead of a generic "waiting for tabs" timeout, and point signed-out fallbacks toward the managed `openclaw` profile.
• ·Webchat/images: treat inline image attachments as media for empty-turn gating while still ignoring metadata-only blank turns. (#69474)
• ·Discord/think: only show `adaptive` in `/think` autocomplete for provider/model pairs that actually support provider-managed adaptive thinking, so GPT/OpenAI models no longer advertise an Anthropic-only option.
• ·Thinking: only expose `max` for models that explicitly support provider max reasoning, and remap stored `max` settings to the largest supported thinking mode when users switch to another model.
• ·Gateway/usage: bound the cost usage cache with FIFO eviction so date/range lookups cannot grow unbounded. (#68842)
• ·OpenAI/Responses: resolve `/think` levels against each GPT model's supported reasoning efforts so `/think off` no longer becomes high reasoning or sends unsupported `reasoning.effort: "none"` payloads.
• ·Lobster/TaskFlow: allow managed approval resumes to use `approvalId` without a resume token, and persist that id in approval wait state. (#69559)
• ·Plugins/startup: install bundled runtime dependencies into each plugin's own runtime directory, reuse source-checkout repair caches after rebuilds, and log only packages that were actually installed so repeated Gateway starts stay quiet once deps are present.
• ·Plugins/startup: ignore pnpm's `npm_execpath` when repairing bundled plugin runtime dependencies and skip workspace-only package specs so npm-only install flags or local workspace links do not break packaged plugin startup.
• ·MCP: block interpreter-startup env keys such as `NODE_OPTIONS` for stdio servers while preserving ordinary credential and proxy env vars. (#69540)
• ·Agents/shell: ignore non-interactive placeholder shells like `/usr/bin/false` and `/sbin/nologin`, falling back to `sh` so service-user exec runs no longer exit immediately. (#69308)
• ·Setup/TUI: relaunch the setup hatch TUI in a fresh process while preserving the configured gateway target and auth source, so onboarding recovers terminal state cleanly without exposing gateway secrets on command-line args. (#69524)
• ·Codex: avoid re-exposing the image-generation tool on native vision turns with inbound images, and keep bare image-model overrides on the configured image provider. (#65061)
• ·Sessions/reset: clear auto-sourced model, provider, and auth-profile overrides on `/new` and `/reset` while preserving explicit user selections, so channel sessions stop staying pinned to runtime fallback choices. (#69419)
• ·Sessions/costs: snapshot `estimatedCostUsd` like token counters so repeated persist paths no longer compound the same run cost by up to dozens of times. (#69403)
• ·OpenAI Codex: route ChatGPT/Codex OAuth Responses requests through the `/backend-api/codex` endpoint so `openai-codex/gpt-5.4` no longer hits the removed `/backend-api/responses` alias. (#69336)
• ·OpenAI/Responses: omit disabled reasoning payloads when `/think off` is active, so GPT reasoning models no longer receive unsupported `reasoning.effort: "none"` requests. (#61982)
• ·Gateway/pairing: treat loopback shared-secret node-host, TUI, and gateway clients as local for pairing decisions, so trusted local tools no longer reconnect as remote clients and fail with `pairing required`. (#69431)
• ·Active Memory: degrade gracefully when memory recall fails during prompt building, logging a warning and letting the reply continue without memory context instead of failing the whole turn. (#69485)
• ·Ollama: add provider-policy defaults for `baseUrl` and `models` so implicit local discovery can run before config validation rejects a minimal Ollama provider config. (#69370)
• ·Agents/model selection: clear transient auto-failover session overrides before each turn so recovered primary models are retried immediately without emitting user-override reset warnings. (#69365)
• ·Auto-reply: apply silent `NO_REPLY` policy per conversation type, so direct chats get a helpful rewritten reply while groups and internal deliveries can remain quiet. (#68644)
• ·Telegram/status reactions: honor `messages.removeAckAfterReply` when lifecycle status reactions are enabled, clearing or restoring the reaction after success/error using the configured hold timings. (#68067)
• ·Web search/plugins: resolve plugin-scoped SecretRef API keys for bundled Exa, Firecrawl, Gemini, Kimi, Perplexity, Tavily, and Grok web-search providers when they are selected through the shared web-search config. (#68424)
• ·Telegram/polling: raise the default polling watchdog threshold from 90s to 120s and add configurable `channels.telegram.pollingStallThresholdMs` (also per-account) so long-running Telegram work gets more room before polling is treated as stalled. (#57737)
• ·Telegram/polling: bound the persisted-offset confirmation `getUpdates` probe with a client-side timeout so a zombie socket cannot hang polling recovery before the runner watchdog starts. (#50368)
• ·Agents/Pi runner: retry silent `stopReason=error` turns with no output when no side effects ran, so non-frontier providers that briefly return empty error turns get another chance instead of ending the session early. (#68310)
• ·Plugins/memory: preserve the active memory capability when read-only snapshot plugin loads run, so status and provider discovery paths no longer wipe memory public artifacts. (#69219)
• ·Plugins: keep only the highest-precedence manifest when distinct discovered plugins share an id, so lower-precedence global or workspace duplicates no longer load beside bundled or config-selected plugins. (#41626)
• ·fix(security): block MINIMAX_API_HOST workspace env injection and remove env-driven URL routing [AI-assisted]. (#67300)
• ·Cron/delivery: treat explicit `delivery.mode: "none"` runs as not requested even if the runner reports `delivered: false`, so no-delivery cron jobs no longer persist false delivery failures or errors. (#69285)
• ·Plugins/install: repair active and default-enabled bundled plugin runtime dependencies before import in packaged installs, so bundled Discord, WhatsApp, Slack, Telegram, and provider plugins work without putting their dependency trees in core.
• ·BlueBubbles: raise the outbound `/api/v1/message/text` send timeout default from 10s to 30s, and add a configurable `channels.bluebubbles.sendTimeoutMs` (also per-account) so macOS 26 setups where Private API iMessage sends stall for 60+ seconds no longer silently lose messages at the 10s abort. Probes, chat lookups, and health checks keep the shorter 10s default. Fixes #67486. (#69193)
• ·Agents/bootstrap: budget truncation markers against per-file caps, preserve source content instead of silently wasting bootstrap bytes, and avoid marker-only output in tiny-budget truncation cases. (#69114)
• ·Context engine/plugins: stop rejecting third-party context engines whose `info.id` differs from the registered plugin slot id. The strict-match contract added in 2026.4.14 broke `lossless-claw` and other plugins whose internal engine id does not equal the slot id they are registered under, producing repeated `info.id must match registered id` lane failures on every turn. Fixes #66601. (#66678)
• ·Agents/compaction: rename embedded Pi compaction lifecycle events to `compaction_start` / `compaction_end` so OpenClaw stays aligned with `pi-coding-agent` 0.66.1 event naming. (#67713)
• ·Security/dotenv: block all `OPENCLAW_*` keys from untrusted workspace `.env` files so workspace-local env loading fails closed for new runtime-control variables instead of silently inheriting them. (#473)
• ·Gateway/device pairing: restrict non-admin paired-device sessions (device-token auth) to their own pairing list, approve, and reject actions so a paired device cannot enumerate other devices or approve/reject pairing requests authored by another device. Admin and shared-secret operator sessions retain full visibility. (#69375)
• ·Agents/gateway tool: extend the agent-facing `gateway` tool's config mutation guard so model-driven `config.patch` and `config.apply` cannot rewrite operator-trusted paths (sandbox, plugin trust, gateway auth/TLS, hook routing and tokens, SSRF policy, MCP servers, workspace filesystem hardening) and cannot bypass the guard by editing per-agent sandbox, tools, or embedded-Pi overrides in place under `agents.list[]`. (#69377)
• ·Gateway/websocket broadcasts: require `operator.read` (or higher) for chat, agent, and tool-result event frames so pairing-scoped and node-role sessions no longer passively receive session chat content, and scope-gate unknown broadcast events by default. Plugin-defined `plugin.*` broadcasts are scoped to operator.write/admin, and status/transport events (`heartbeat`, `presence`, `tick`, etc.) remain unrestricted. Per-client sequence numbers preserve per-connection monotonicity. (#69373)
• ·Agents/compaction: always reload embedded Pi resources through an explicit loader and reapply reserve-token overrides so runs without extension factories no longer silently lose compaction settings before session start. (#67146)
• ·Memory-core/dreaming: normalize sweep timestamps and reuse hashed narrative session keys for fallback cleanup so Dreaming narrative sub-sessions stop leaking. (#67023)
• ·Gateway/startup: delay HTTP bind until websocket handlers are attached, so immediate post-startup websocket health/connect probes no longer hit the startup race window. (#43392)
• ·Codex/app-server: release the session lane when a downstream consumer throws while draining the `turn/completed` notification, so follow-up messages after a Codex plugin reply stop queueing behind a stale lane lock. Fixes #67996. (#69072)
• ·Codex/app-server: default approval handling to `on-request` so Codex harness sessions do not start with overly permissive tool approvals. (#68721)
• ·Cron/delivery: keep isolated cron chat delivery tools available, resolve `channel: "last"` targets from the gateway, show delivery previews in `cron list/show`, and avoid duplicate fallback sends after direct message-tool delivery. (#69587)
• ·Cron/Telegram: key isolated direct-delivery dedupe to each cron execution instead of the reused session id, so recurring Telegram announce runs no longer report delivered while silently skipping later sends. (#69000)
• ·Models/Kimi: default bundled Kimi thinking to off and normalize Anthropic-compatible `thinking` payloads so stale session `/think` state no longer silently re-enables reasoning on Kimi runs. (#68907)
• ·Control UI/cron: keep the runtime-only `last` delivery sentinel from being materialized into persisted cron delivery and failure-alert channel configs when jobs are created or edited. (#68829)
• ·OpenAI/Responses: strip orphaned reasoning blocks before outbound Responses API calls so compacted or restored histories no longer fail on standalone reasoning items. (#55787)
• ·Cron/CLI: parse PowerShell-style `--tools` allow-lists the same way as comma-separated input, so `cron add` and `cron edit` no longer persist `exec read write` as one combined tool entry on Windows. (#68858)
• ·Browser/user-profile: let existing-session `profile="user"` tool calls auto-route to a connected browser node or use explicit `target="node"`, while still honoring explicit `target="host"` pinning. (#48677)
• ·Discord/slash commands: tolerate partial Discord channel metadata in slash-command and model-picker flows so partial channel objects no longer crash when channel names, topics, or thread parent metadata are unavailable. (#68953)
• ·BlueBubbles: consolidate outbound HTTP through a typed `BlueBubblesClient` that resolves the SSRF policy once at construction so image attachments stop getting blocked on localhost and reactions stop getting blocked on private-IP BB deployments. Fixes #34749 and #59722. (#68234)
• ·Cron/gateway: reject ambiguous announce delivery config at add/update time so invalid multi-channel or target-id provider settings fail early instead of persisting broken cron jobs. (#69015)
• ·Cron/main-session delivery: preserve `heartbeat.target="last"` through deferred wake queuing, gateway wake forwarding, and same-target wake coalescing so queued cron replies still return to the last active chat. (#69021)
• ·Cron/gateway: ignore disabled channels when announce delivery ambiguity is checked, and validate main-session delivery patches against the live cron service default agent so hot-reloaded agent config does not falsely reject valid updates. (#69040)
• ·Matrix/allowlists: hot-reload `dm.allowFrom` and `groupAllowFrom` entries on inbound messages while keeping config removals authoritative, so Matrix allowlist changes no longer require a channel restart to add or revoke a sender. (#68546)
• ·BlueBubbles: always set `method` explicitly on outbound text sends (`"private-api"` when available, `"apple-script"` otherwise), and prefer Private API on macOS 26 even for plain text. Fixes silent delivery failure on macOS setups without Private API where an omitted `method` let BB Server fall back to version-dependent default behavior that silently drops the message (#64480), and the AppleScript `-1700` error on macOS 26 Tahoe plain text sends (#53159). (#69070)
• ·Matrix/commands: recognize slash commands that are prefixed with the bot's Matrix mention, so room messages like `@bot:server /new` trigger the command path without requiring custom mention regexes. (#68570)
• ·Gateway/pairing: return reason-specific `PAIRING_REQUIRED` details, remediation hints, and request ids so unapproved-device and scope-upgrade failures surface actionable recovery guidance in the CLI and Control UI. (#69227)
• ·Agents/subagents: include requested role and runtime timing on subagent failure payloads so parent agents can correlate failed or timed-out child work. (#68726)
• ·Gateway/sessions: reject stale agent-scoped sessions after an agent is removed from config while preserving legacy default-agent main-session aliases. (#65986)
• ·Doctor/gateway: surface pending device pairing requests, scope-upgrade approval drift, and stale device-token mismatch repair steps so `openclaw doctor --fix` no longer leaves pairing/auth setup failures unexplained. (#69210)
• ·Cron/isolated-agent: preserve explicit `delivery.mode: "none"` message targets for isolated runs without inheriting implicit `last` routing, so agent-initiated Telegram sends keep their authored destination while bare `mode:none` jobs stay targetless. (#69153)
• ·Cron/isolated-agent: keep `delivery.mode: "none"` account-only or thread-only configs from inheriting a stale implicit recipient, so isolated runs only resolve message routing when the job authored an explicit `to` target. (#69163)
• ·Gateway/TUI: retry session history while the local gateway is still finishing startup, so `openclaw tui` reconnects no longer fail on transient `chat.history unavailable during gateway startup` errors. (#69164)
• ·BlueBubbles/reactions: fall back to `love` when an agent reacts with an emoji outside the iMessage tapback set (`love`/`like`/`dislike`/`laugh`/`emphasize`/`question`), so wider-vocabulary model reactions like `👀` still produce a visible tapback instead of failing the whole reaction request. Configured ack reactions still validate strictly via the new `normalizeBlueBubblesReactionInputStrict` path. (#64693)
• ·BlueBubbles: prefer iMessage over SMS when both chats exist for the same handle, honor explicit `sms:` targets, and never silently downgrade iMessage-available recipients. (#61781)
• ·Telegram/setup: require numeric `allowFrom` user IDs during setup instead of offering unsupported `@username` DM resolution, and point operators to `from.id`/`getUpdates` for discovery. (#69191)
• ·GitHub Copilot/onboarding: default GitHub Copilot setup to `claude-opus-4.6` and keep the bundled default model list aligned, so new Copilot setups no longer start on the older `gpt-4o` default. (#69207)
• ·Gateway/status: separate reachability, capability, and read-probe reporting so connect-only or scope-limited sessions no longer look fully healthy, and normalize SSH targets entered as `ssh user@host`. (#69215)
• ·Slack: fix outbound replies failing with "unresolved SecretRef" for accounts configured via `file` or `exec` secret sources; the send path now tolerates the runtime snapshot retaining an unresolved channel SecretRef when a boot-resolved token override is already available. (#68954)
• ·Control UI/device pairing: explain scope and role approval upgrades during reconnects, and show requested versus approved access in the Control UI and `openclaw devices` so broader reconnects no longer look like lost pairings. (#69221)
• ·Gateway/Control UI: surface pending scope, role, and device-metadata pairing approvals in auth errors and Control UI hints so broader reconnects no longer look like random auth breakage. (#69226)

Fixes

• ·Agents/openai-completions: always send `stream_options.include_usage` on streaming requests, so local and custom OpenAI-compatible backends report real context usage instead of showing 0%. (#68746)
• ·Agents/nested lanes: scope nested agent work per target session so a long-running nested run on one session no longer head-of-line blocks unrelated sessions across the gateway. (#67785)
• ·Agents/status: preserve carried-forward session token totals for providers that omit usage metadata, so `/status` and `openclaw sessions` keep showing the last known context usage instead of dropping back to unknown/0%. (#67695)
• ·Install/update: keep legacy update verification compatible with the QA Lab runtime shim, so updating older global installs to beta no longer fails after npm installs the package successfully.

Fixes

• ·Agents/channels: route cross-agent subagent spawns through the target agent's bound channel account while preserving peer and workspace/role-scoped bindings, so child sessions no longer inherit the caller's account in shared rooms, workspaces, or multi-account setups. (#67508)
• ·Telegram/callbacks: treat permanent callback edit errors as completed updates so stale command pagination buttons no longer wedge the update watermark and block newer Telegram updates. (#68588)
• ·Browser/CDP: allow the selected remote CDP profile host for CDP health and control checks without widening browser navigation SSRF policy, so WSL-to-Windows Chrome endpoints no longer appear offline under strict defaults. Fixes #68108. (#68207)
• ·Codex: stop cumulative app-server token totals from being treated as fresh context usage, so session status no longer reports inflated context percentages after long Codex threads. (#64669)
• ·Browser/CDP: add phase-specific CDP readiness diagnostics and normalize loopback WebSocket host aliases, so Windows browser startup failures surface whether HTTP discovery, WebSocket discovery, SSRF validation, or the `Browser.getVersion` health check failed.

Changes

• ·Anthropic/models: default Anthropic selections, `opus` aliases, Claude CLI defaults, and bundled image understanding to Claude Opus 4.7.
• ·Google/TTS: add Gemini text-to-speech support to the bundled `google` plugin, including provider registration, voice selection, WAV reply output, PCM telephony output, and setup/docs guidance. (#67515)
• ·Control UI/Overview: add a Model Auth status card showing OAuth token health and provider rate-limit pressure at a glance, with attention callouts when OAuth tokens are expiring or expired. Backed by a new `models.authStatus` gateway method that strips credentials and caches for 60s. (#66211)
• ·Memory/LanceDB: add cloud storage support to `memory-lancedb` so durable memory indexes can run on remote object storage instead of local disk only. (#63502)
• ·GitHub Copilot/memory search: add a GitHub Copilot embedding provider for memory search, and expose a dedicated Copilot embedding host helper so plugins can reuse the transport while honoring remote overrides, token refresh, and safer payload validation. (#61718)
• ·Agents/local models: add experimental `agents.defaults.experimental.localModelLean: true` to drop heavyweight default tools like `browser`, `cron`, and `message`, reducing prompt size for weaker local-model setups without changing the normal path. (#66495)
• ·Packaging/plugins: localize bundled plugin runtime deps to their owning extensions, trim the published docs payload, and tighten install/package-manager guardrails so published builds stay leaner and core stops carrying extension-owned runtime baggage. (#67099)
• ·QA/Matrix: split Matrix live QA into a source-linked `qa-matrix` runner and keep repo-private `qa-*` surfaces out of packaged and published builds. (#66723)
• ·Docs/showcase: add a scannable hero, complete section jump links, and a responsive video grid for community examples. (#48493)

Fixes

• ·Gateway/tools: anchor trusted local `MEDIA:` tool-result passthrough on the exact raw name of this run's registered built-in tools, and reject client tool definitions whose names normalize-collide with a built-in or with another client tool in the same request (`400 invalid_request_error` on both JSON and SSE paths), so a client-supplied tool named like a built-in can no longer inherit its local-media trust. (#67303)
• ·Agents/replay recovery: classify the provider wording `401 input item ID does not belong to this connection` as replay-invalid, so users get the existing `/new` session reset guidance instead of a raw 401-style failure. (#66475)
• ·Gateway/webchat: enforce localRoots containment on webchat audio embedding path [AI-assisted]. (#67298)
• ·Matrix/pairing: block DM pairing-store entries from authorizing room control commands [AI-assisted]. (#67294)
• ·Docker/build: verify `@matrix-org/matrix-sdk-crypto-nodejs` native bindings with `find` under `node_modules` instead of a hardcoded `.pnpm/...` path so pnpm v10+ virtual-store layouts no longer fail the image build. (#67143)
• ·Matrix/E2EE: keep startup bootstrap conservative for passwordless token-auth bots, still attempt the guarded repair pass without requiring `channels.matrix.password`, and document the remaining password-UIA limitation. (#66228)
• ·Cron/announce delivery: suppress mixed-content isolated cron announce replies that end with `NO_REPLY` so trailing silent sentinels no longer leak summary text to the target channel. (#65004)
• ·Plugins/bundled channels: partition bundled channel lazy caches by active bundled root so `OPENCLAW_BUNDLED_PLUGINS_DIR` flips stop reusing stale plugin, setup, secrets, and runtime state. (#67200)
• ·Packaging/plugins: prune common test/spec cargo from bundled plugin runtime dependencies and fail npm release validation if packaged test cargo reappears, keeping published tarballs leaner without plugin-specific special cases. (#67275)
• ·Agents/context + Memory: trim default startup/skills prompt budgets, cap `memory_get` excerpts by default with explicit continuation metadata, and keep QMD reads aligned with the same bounded excerpt contract so long sessions pull less context by default without losing deterministic follow-up reads.
• ·Matrix/commands: skip DM pairing-store reads on room traffic now that room control-command authorization ignores pairing-store entries, keeping the room path narrower without changing room auth behavior. (#67325)
• ·Memory-core/dreaming: skip dreaming narrative transcripts from session-store metadata before bootstrap records land so dream diary prompt/prose lines do not pollute session ingestion. (#67315)
• ·Agents/local models: clarify low-context preflight hints for self-hosted models, point config-backed caps at the relevant OpenClaw setting, and stop suggesting larger models when `agents.defaults.contextTokens` is the real limit. (#66236)
• ·Dreaming/memory-core: change the default `dreaming.storage.mode` from `inline` to `separate` so Dreaming phase blocks (`## Light Sleep`, `## REM Sleep`) land in `memory/dreaming/{phase}/YYYY-MM-DD.md` instead of being injected into `memory/YYYY-MM-DD.md`. Daily memory files no longer get dominated by structured candidate output, and the daily-ingestion scanner that already strips dream marker blocks no longer has to compete with hundreds of phase-block lines on every run. Operators who want the previous behavior can opt in by setting `plugins.entries.memory-core.config.dreaming.storage.mode: "inline"`. (#66412)
• ·Control UI/Overview: fix false-positive "missing" alerts on the Model Auth status card for aliased providers, env-backed OAuth with auth.profiles, and unresolvable env SecretRefs. (#67253)
• ·Dashboard: constrain exec approval modal overflow on desktop so long command content no longer pushes action buttons out of view. (#67082)
• ·Agents/CLI transcripts: persist successful CLI-backed turns into the OpenClaw session transcript so google-gemini-cli replies appear in session history and the Control UI again. (#67490)
• ·Discord/tool-call text: strip standalone Gemma-style `<function>...</function>` tool-call payloads from visible assistant text without truncating prose examples or trailing replies. (#67318)
• ·WhatsApp/web-session: drain the pending per-auth creds save queue before reopening sockets so reconnect-time auth bootstrap no longer races in-flight `creds.json` writes and falsely restores from backup. (#67464)
• ·BlueBubbles/catchup: add a per-message retry ceiling (`catchup.maxFailureRetries`, default 10) so a persistently-failing message with a malformed payload no longer wedges the catchup cursor forever. After N consecutive `processMessage` failures against the same GUID, catchup logs a WARN, skips that message on subsequent sweeps, and lets the cursor advance past it. Transient failures still retry from the same point as before. Also fixes a lost-update race in the persistent dedupe file lock that silently dropped inbound GUIDs on concurrent writes, a dedupe file naming migration gap on version upgrade, and a balloon-event bypass that let catchup replay debouncer-coalesced events as standalone messages. (#67426, #66870)
• ·Ollama/chat: strip the `ollama/` provider prefix from Ollama chat request model ids so configured refs like `ollama/qwen3:14b-q8_0` stop 404ing against the Ollama API. (#67457)
• ·Agents/tools: resolve non-workspace host tilde paths against the OS home directory and keep edit recovery aligned with that same path target, so `~/...` host edit/write operations stop failing or reading back the wrong file when `OPENCLAW_HOME` differs. (#62804)
• ·Speech/TTS: auto-enable the bundled Microsoft and ElevenLabs speech providers, and route generic TTS directive tokens through the explicit or active provider first so overrides like `[[tts:speed=1.2]]` stop silently landing on the wrong provider. (#62846)
• ·OpenAI Codex/models: normalize stale native transport metadata in both runtime resolution and discovery/listing so legacy `openai-codex` rows with missing `api` or `https://chatgpt.com/backend-api/v1` self-heal to the canonical Codex transport instead of routing requests through broken HTML/Cloudflare paths, combining the original fixes proposed in #66969 (saamuelng601-pixel) and #67159 (hclsys). (#67635)
• ·Agents/failover: treat HTML provider error pages as upstream transport failures for CDN-style 5xx responses without misclassifying embedded body text as API rate limits, while still preserving auth remediation for HTML 401/403 pages and proxy remediation for HTML 407 pages. (#67642)
• ·Gateway/skills: bump the cached skills-snapshot version whenever a config write touches `skills.*` (for example `skills.allowBundled`, `skills.entries.<id>.enabled`, or `skills.profile`). Existing agent sessions persist a `skillsSnapshot` in `sessions.json` that reuses the skill list frozen at session creation; without this invalidation, removing a bundled skill from the allowlist left the old snapshot live and the model kept calling the disabled tool, producing `Tool <name> not found` loops that ran until the embedded-run timeout. (#67401)
• ·Agents/tool-loop: enable the unknown-tool stream guard by default. Previously `resolveUnknownToolGuardThreshold` returned `undefined` unless `tools.loopDetection.enabled` was explicitly set to `true`, which left the protection off in the default configuration. A hallucinated or removed tool (for example `himalaya` after it was dropped from `skills.allowBundled`) would then loop "Tool X not found" attempts until the full embedded-run timeout. The guard has no false-positive surface because it only triggers on tools that are objectively not registered in the run, so it now stays on regardless of `tools.loopDetection.enabled` and still accepts `tools.loopDetection.unknownToolThreshold` as a per-run override (default 10). (#67401)
• ·TUI/streaming: add a client-side streaming watchdog to `tui-event-handlers` so the `streaming · Xm Ys` activity indicator resets to `idle` after 30s of delta silence on the active run. Guards against lost or late `state: "final"` chat events (WS reconnects, gateway restarts, etc.) leaving the TUI stuck on `streaming` indefinitely; a new system log line surfaces the reset so users know to send a new message to resync. The window is configurable via the new `streamingWatchdogMs` context option (set to `0` to disable), and the handler now exposes a `dispose()` that clears the pending timer on shutdown. (#67401)
• ·Extensions/lmstudio: add exponential backoff to the inference-preload wrapper so an LM Studio model-load failure (for example the built-in memory guardrail rejecting a load because the swap is saturated) no longer produces a WARN line every ~2s for every chat request. The wrapper now records consecutive preload failures per `(baseUrl, modelKey, contextLength)` tuple with a 5s → 10s → 20s → … → 5min cooldown and skips the preload step entirely while a cooldown is active, letting chat requests proceed directly to the stream (the model is often already loaded via the LM Studio UI). The combined `preload failed` log line now reports consecutive-failure count and remaining cooldown so operators can act on the real issue instead of drowning in repeated warnings. (#67401)
• ·Agents/replay: re-run tool/result pairing after strict replay tool-call ID sanitization on outbound requests so Anthropic-compatible providers like MiniMax no longer receive malformed orphan tool-result IDs such as `...toolresult1` during compaction and retry flows. (#67620)
• ·Gateway/startup: fix spurious SIGUSR1 restart loop on Linux/systemd when plugin auto-enable is the only startup config write; the config hash guard was not captured for that write path, causing chokidar to treat each boot write as an external change and trigger a reload → restart cycle that corrupts manifest.db after repeated cycles. Fixes #67436. (#67557)
• ·Codex/harness: auto-enable the Codex plugin when `codex` is selected as an embedded agent harness runtime, including forced default, per-agent, and `OPENCLAW_AGENT_RUNTIME` paths. (#67474)
• ·OpenAI Codex/CLI: keep resumed `codex exec resume` runs on the safe non-interactive path without reintroducing the removed dangerous bypass flag by passing the supported `--skip-git-repo-check` resume arg plus Codex's native `sandbox_mode="workspace-write"` config override. (#67666)
• ·Codex/app-server: parse Desktop-originated app-server user agents such as `Codex Desktop/0.118.0`, keeping the version gate working when the Codex CLI inherits a multi-word originator. (#64666)
• ·Cron/announce delivery: keep isolated announce `NO_REPLY` stripping case-insensitive across direct and text delivery, preserve structured media-only sends when a caption strips silent, and derive main-session awareness from the cleaned payloads so silent captions no longer leak stale `NO_REPLY` text. (#65016)
• ·Sessions/Codex: skip redundant `delivery-mirror` transcript appends only when the latest assistant message has the same visible text, preventing duplicate visible replies on Codex-backed turns without suppressing repeated answers across turns. (#67185)
• ·Auto-reply/prompt-cache: keep volatile inbound chat IDs out of the stable system prompt so task-scoped adapters can reuse prompt caches across runs, while preserving conversation metadata for the user turn and media-only messages. (#65071)
• ·BlueBubbles/inbound: restore inbound image attachment downloads on Node 22+ by stripping incompatible bundled-undici dispatchers from the non-SSRF fetch path, accept `updated-message` webhooks carrying attachments, use event-type-aware dedup keys so attachment follow-ups are not rejected as duplicates, and retry attachment fetch from the BB API when the initial webhook arrives with an empty array. (#64105, #61861, #65430, #67510)
• ·Agents/skills: sort prompt-facing `available_skills` entries by skill name after merging sources so `skills.load.extraDirs` order no longer changes prompt-cache prefixes. (#64198)
• ·Agents/OpenAI Responses: add `models.providers.*.models.*.compat.supportsPromptCacheKey` so OpenAI-compatible proxies that forward `prompt_cache_key` can keep prompt caching enabled while incompatible endpoints can still force stripping. (#67427)
• ·Agents/context engines: keep loop-hook and final `afterTurn` prompt-cache touch metadata aligned with the current assistant turn so cache-aware context engines retain accurate cache TTL state during tool loops. (#67767)
• ·Memory/dreaming: strip AI-facing inbound metadata envelopes from session-corpus user turns before normalization so REM topic extraction sees the user's actual message text, including array-shaped split envelopes. (#66548)
• ·Agents/errors: detect standalone Cloudflare/CDN HTML challenge pages before transport DNS classification so provider block pages no longer appear as local DNS lookup failures. (#67704)
• ·Security/approvals: redact secrets in exec approval prompts so inline approval review can no longer leak credential material in rendered prompt content. (#61077, #64790)
• ·CLI/configure: re-read the persisted config hash after writes so config updates stop failing with stale-hash races. (#64188, #66528)
• ·CLI/update: prune stale packaged `dist` chunks after npm upgrades and keep downgrade/verify inventory checks compat-safe so global upgrades stop failing on stale chunk imports. (#66959)
• ·Onboarding/CLI: fix channel-selection crashes on globally installed CLI setups during onboarding. (#66736)
• ·Video generation/live tests: bound provider polling for live video smoke, default to the fast non-FAL text-to-video path, and use a one-second lobster prompt so release validation no longer waits indefinitely on slow provider queues.
• ·Memory-core/QMD `memory_get`: reject reads of arbitrary workspace markdown paths and only allow canonical memory files (`MEMORY.md`, `memory.md`, `DREAMS.md`, `dreams.md`, `memory/**`) plus exact paths of active indexed QMD workspace documents, so the QMD memory backend can no longer be used as a generic workspace-file read shim that bypasses `read` tool-policy denials. (#66026)
• ·Cron/agents: forward embedded-run tool policy and internal event params into the attempt layer so `--tools` allowlists, cron-owned message-tool suppression, explicit message targeting, and command-path internal events all take effect at runtime again. (#62675)
• ·Setup/providers: guard preferred-provider lookup during setup so malformed plugin metadata with a missing provider id no longer crashes the wizard with `Cannot read properties of undefined (reading 'trim')`. (#66649)
• ·Matrix/security: normalize sandboxed profile avatar params, preserve `mxc://` avatar URLs, and surface gmail watcher stop failures during reload. (#64701)
• ·Telegram/documents: drop leaked binary caption bytes from inbound Telegram text handling so document uploads like `.mobi` or `.epub` no longer explode prompt token counts. (#66663)
• ·Gateway/auth: resolve the active gateway bearer per-request on the HTTP server and the HTTP upgrade handler via `getResolvedAuth()`, mirroring the WebSocket path, so a secret rotated through `secrets.reload` or config hot-reload stops authenticating on `/v1/*`, `/tools/invoke`, plugin HTTP routes, and the canvas upgrade path immediately instead of remaining valid on HTTP until gateway restart. (#66651)
• ·Agents/compaction: cap the compaction reserve-token floor to the model context window so small-context local models (e.g. Ollama with 16K tokens) no longer trigger context-overflow errors or infinite compaction loops on every prompt. (#65671)
• ·Agents/OpenAI Responses: classify the exact `Unknown error (no error details in response)` transport failure as failover reason `unknown` so assistant/model fallback still runs for that no-details failure path. (#65254)
• ·Models/probe: surface invalid-model probe failures as `format` instead of `unknown` in `models list --probe`, and lock the invalid-model fallback path in with regression coverage. (#50028)
• ·Agents/failover: classify OpenAI-compatible `finish_reason: network_error` stream failures as timeout so model fallback retries continue instead of stopping with an unknown failover reason. (#61784)
• ·Onboarding/channels: normalize channel setup metadata before discovery and validation so malformed or mixed-shape channel plugin metadata no longer breaks setup and onboarding channel lists. (#66706)
• ·Slack/native commands: fix option menus for slash commands such as `/verbose` when Slack renders native buttons by giving each button a unique action ID while still routing them through the shared `openclaw_cmdarg*` listener.
• ·Feishu/webhook: harden the webhook transport and card-action replay guards to fail closed on missing `encryptKey` and blank callback tokens — refuse to start the webhook transport without an `encryptKey`, reject unsigned requests when no key is present instead of accepting them, and drop blank card-action tokens before the dedupe claim and dispatcher. Defense-in-depth over the already-closed monitor-account layer. (#66707)
• ·Agents/workspace files: route `agents.files.get`, `agents.files.set`, and workspace listing through the shared `fs-safe` helpers (`openFileWithinRoot`/`readFileWithinRoot`/`writeFileWithinRoot`), reject symlink aliases for allowlisted agent files, and have `fs-safe` resolve opened-file real paths from the file descriptor before falling back to path-based `realpath` so a symlink swap between `open` and `realpath` can no longer redirect the validated path off the intended inode. (#66636)
• ·Gateway/MCP loopback: switch the `/mcp` bearer comparison from plain `!==` to constant-time `safeEqualSecret` (matching the convention every other auth surface in the codebase uses), and reject non-loopback browser-origin requests via `checkBrowserOrigin` before the auth gate runs. Loopback origins (`127.0.0.1:*`, `localhost:*`, same-origin) still go through, including the `localhost`↔`127.0.0.1` host mismatch that browsers flag as `Sec-Fetch-Site: cross-site`. (#66665)
• ·Auto-reply/billing: classify pure billing cooldown fallback summaries from structured fallback reasons so users see billing guidance instead of the generic failure reply. (#66363)
• ·Agents/fallback: preserve the original prompt body on model fallback retries with session history so the retrying model keeps the active task instead of only seeing a generic continue message. (#66029)
• ·Reply/secrets: resolve active reply channel/account SecretRefs before reply-run message-action discovery so channel token SecretRefs (for example Discord) do not degrade into discovery-time unresolved-secret failures. (#66796)
• ·Agents/Anthropic: ignore non-positive Anthropic Messages token overrides and fail locally when no positive token budget remains, so invalid `max_tokens` values no longer reach the provider API. (#66664)
• ·Agents/context engines: preserve prompt-only token counts, not full request totals, when deferred maintenance reuses after-turn runtime context so background compaction bookkeeping matches the active prompt window. (#66820)
• ·BlueBubbles/inbound: add a persistent file-backed GUID dedupe so MessagePoller webhook replays after BB Server restart or reconnect no longer cause the agent to re-reply to already-handled messages. (#19176, #12053, #66816)
• ·Secrets/plugins/status: align SecretRef inspect-vs-strict handling across plugin preload, read-only status/agents surfaces, and runtime auth paths so unresolved refs no longer crash read-only CLI flows while runtime-required non-env refs stay strict. (#66818)
• ·Memory/dreaming: stop ordinary transcripts that merely quote the dream-diary prompt from being classified as internal dreaming runs and silently dropped from session recall ingestion. (#66852)
• ·Telegram/documents: sanitize binary reply context and ZIP-like archive extraction so `.epub` and `.mobi` uploads can no longer leak raw binary into prompt context through reply metadata or archive-to-`text/plain` coercion. (#66877)
• ·Telegram/native commands: restore plugin-registry-backed auto defaults for native commands and native skills so Telegram slash commands keep registering when `commands.native` and `commands.nativeSkills` stay on `auto`. (#66843)
• ·OpenRouter/Qwen3: parse `reasoning_details` stream deltas as thinking content without skipping same-chunk tool calls, so Qwen3 replies no longer fail empty on OpenRouter and mixed reasoning/tool-call chunks still execute normally. (#66905)
• ·BlueBubbles/catchup: replay missed webhook messages after gateway restart via a persistent per-account cursor and `/api/v1/message/query?after=<ts>` pass, so messages delivered while the gateway was down no longer disappear. Uses the existing `processMessage` path and is deduped by #66816's inbound GUID cache. (#66857, #66721)
• ·Telegram/native commands: keep Telegram command-sync cache process-local so gateway restarts re-register the menu instead of trusting stale on-disk sync state after Telegram cleared commands out-of-band. (#66730)
• ·Audio/self-hosted STT: restore `models.providers.*.request.allowPrivateNetwork` for audio transcription so private or LAN speech-to-text endpoints stop tripping SSRF blocks after the v2026.4.14 regression. (#66692)
• ·Auto-reply/media: allow workspace-rooted absolute media paths in auto-reply send flows so valid local media references no longer fail path validation. (#66689)
• ·WhatsApp/Baileys media upload: harden encrypted upload handling so large outbound media sends avoid buffer spikes and reliability regressions. (#65966)
• ·QQBot/cron: guard against undefined `event.content` in `parseFaceTags` and `filterInternalMarkers` so cron-triggered agent turns with no content payload no longer crash with `TypeError: Cannot read properties of undefined (reading 'startsWith')`. (#66302)
• ·CLI/plugins: stop `--dangerously-force-unsafe-install` plugin installs from falling back to hook-pack installs after security scan failures, while still preserving non-security fallback behavior for real hook packs. (#58909)
• ·Claude CLI/sessions: classify `No conversation found with session ID` as `session_expired` so expired CLI-backed conversations clear the stale binding and recover on the next turn. (#65028)
• ·Context Engine: gracefully fall back to the legacy engine when a third-party context engine plugin fails at resolution time (unregistered id, factory throw, or contract violation), preventing a full gateway outage on every channel. (#66930)
• ·Control UI/chat: keep optimistic user message cards visible during active sends by deferring same-session history reloads until the active run ends, including aborted and errored runs. (#66997)
• ·Media/Slack: allow host-local CSV and Markdown uploads only when the fallback buffer actually decodes as text, so real plain-text files work without letting opaque non-text blobs renamed to `.csv` or `.md` slip past the host-read guard. (#67047)
• ·Ollama/onboarding: split setup into `Cloud + Local`, `Cloud only`, and `Local only`, support direct `OLLAMA_API_KEY` cloud setup without a local daemon, and keep Ollama web search on the local-host path. (#67005)
• ·Webchat/security: reject remote-host `file://` URLs in the media embedding path. (#67293)
• ·Dreaming/memory-core: use the ingestion day, not the source file day, for daily recall dedupe so repeat sweeps of the same daily note can increment `dailyCount` across days instead of stalling at `1`. (#67091)
• ·Node-host/tools.exec: let approval binding distinguish known native binaries from mutable shell payload files, while still fail-closing unknown or racy file probes so absolute-path node-host commands like `/usr/bin/whoami` no longer get rejected as unsafe interpreter/runtime commands. (#66731)

Changes

• ·Anthropic/models: default Anthropic selections, `opus` aliases, Claude CLI defaults, and bundled image understanding to Claude Opus 4.7.
• ·Google/TTS: add Gemini text-to-speech support to the bundled `google` plugin, including provider registration, voice selection, WAV reply output, PCM telephony output, and setup/docs guidance. (#67515)

Fixes

• ·Gateway/tools: anchor trusted local `MEDIA:` tool-result passthrough on the exact raw name of this run's registered built-in tools, and reject client tool definitions whose names normali

Changes

• ·Control UI/Overview: add a Model Auth status card showing OAuth token health and provider rate-limit pressure at a glance, with attention callouts when OAuth tokens are expiring or expired. Backed by a new `models.authStatus` gateway method that strips credentials and caches for 60s. (#66211)
• ·Memory/LanceDB: add cloud storage support to `memory-lancedb` so durable memory indexes can run on remote object storage instead of local disk only. (#63502)
• ·GitHub Copilot/memory search: add a GitHub Copilot embedding provider for memory search, and expose a dedicated Copilot embedding host helper so plugins can reuse the transport while honoring remote overrides, token refresh, and safer payload validation. (#61718)
• ·Agents/local models: add experimental `agents.defaults.experimental.localModelLean: true` to drop heavyweight default tools like `browser`, `cron`, and `message`, reducing prompt size for weaker local-model setups without changing the normal path. (#66495)
• ·Packaging/plugins: localize bundled plugin runtime deps to their owning extensions, trim the published docs payload, and tighten install/package-manager guardrails so published builds stay leaner and core stops carrying extension-owned runtime baggage. (#67099)
• ·QA/Matrix: split Matrix live QA into a source-linked `qa-matrix` runner and keep repo-private `qa-*` surfaces out of packaged and published builds. (#66723)
• ·Docs/showcase: add a scannable hero, complete section jump links, and a responsive video grid for community examples. (#48493)

Fixes

• ·Security/approvals: redact secrets in exec approval prompts so inline approval review can no longer leak credential material in rendered prompt content. (#61077, #64790)
• ·CLI/configure: re-read the persisted config hash after writes so config updates stop failing with stale-hash races. (#64188, #66528)
• ·CLI/update: prune stale packaged `dist` chunks after npm upgrades and keep downgrade/verify inventory checks compat-safe so global upgrades stop failing on stale chunk imports. (#66959)
• ·Onboarding/CLI: fix channel-selection crashes on globally installed CLI setups during onboarding. (#66736)
• ·Video generation/live tests: bound provider polling for live video smoke, default to the fast non-FAL text-to-video path, and use a one-second lobster prompt so release validation no longer waits indefinitely on slow provider queues.
• ·Memory-core/QMD `memory_get`: reject reads of arbitrary workspace markdown paths and only allow canonical memory files (`MEMORY.md`, `memory.md`, `DREAMS.md`, `dreams.md`, `memory/**`) plus exact paths of active indexed QMD workspace documents, so the QMD memory backend can no longer be used as a generic workspace-file read shim that bypasses `read` tool-policy denials. (#66026)
• ·Cron/agents: forward embedded-run tool policy and internal event params into the attempt layer so `--tools` allowlists, cron-owned message-tool suppression, explicit message targeting, and command-path internal events all take effect at runtime again. (#62675)
• ·Setup/providers: guard preferred-provider lookup during setup so malformed plugin metadata with a missing provider id no longer crashes the wizard with `Cannot read properties of undefined (reading 'trim')`. (#66649)
• ·Matrix/security: normalize sandboxed profile avatar params, preserve `mxc://` avatar URLs, and surface gmail watcher stop failures during reload. (#64701)
• ·Telegram/documents: drop leaked binary caption bytes from inbound Telegram text handling so document uploads like `.mobi` or `.epub` no longer explode prompt token counts. (#66663)
• ·Gateway/auth: resolve the active gateway bearer per-request on the HTTP server and the HTTP upgrade handler via `getResolvedAuth()`, mirroring the WebSocket path, so a secret rotated through `secrets.reload` or config hot-reload stops authenticating on `/v1/*`, `/tools/invoke`, plugin HTTP routes, and the canvas upgrade path immediately instead of remaining valid on HTTP until gateway restart. (#66651)
• ·Agents/compaction: cap the compaction reserve-token floor to the model context window so small-context local models (e.g. Ollama with 16K tokens) no longer trigger context-overflow errors or infinite compaction loops on every prompt. (#65671)
• ·Agents/OpenAI Responses: classify the exact `Unknown error (no error details in response)` transport failure as failover reason `unknown` so assistant/model fallback still runs for that no-details failure path. (#65254)
• ·Models/probe: surface invalid-model probe failures as `format` instead of `unknown` in `models list --probe`, and lock the invalid-model fallback path in with regression coverage. (#50028)
• ·Agents/failover: classify OpenAI-compatible `finish_reason: network_error` stream failures as timeout so model fallback retries continue instead of stopping with an unknown failover reason. (#61784)
• ·Onboarding/channels: normalize channel setup metadata before discovery and validation so malformed or mixed-shape channel plugin metadata no longer breaks setup and onboarding channel lists. (#66706)
• ·Slack/native commands: fix option menus for slash commands such as `/verbose` when Slack renders native buttons by giving each button a unique action ID while still routing them through the shared `openclaw_cmdarg*` listener.
• ·Feishu/webhook: harden the webhook transport and card-action replay guards to fail closed on missing `encryptKey` and blank callback tokens — refuse to start the webhook transport without an `encryptKey`, reject unsigned requests when no key is present instead of accepting them, and drop blank card-action tokens before the dedupe claim and dispatcher. Defense-in-depth over the already-closed monitor-account layer. (#66707)
• ·Agents/workspace files: route `agents.files.get`, `agents.files.set`, and workspace listing through the shared `fs-safe` helpers (`openFileWithinRoot`/`readFileWithinRoot`/`writeFileWithinRoot`), reject symlink aliases for allowlisted agent files, and have `fs-safe` resolve opened-file real paths from the file descriptor before falling back to path-based `realpath` so a symlink swap between `open` and `realpath` can no longer redirect the validated path off the intended inode. (#66636)
• ·Gateway/MCP loopback: switch the `/mcp` bearer comparison from plain `!==` to constant-time `safeEqualSecret` (matching the convention every other auth surface in the codebase uses), and reject non-loopback browser-origin requests via `checkBrowserOrigin` before the auth gate runs. Loopback origins (`127.0.0.1:*`, `localhost:*`, same-origin) still go through, including the `localhost`↔`127.0.0.1` host mismatch that browsers flag as `Sec-Fetch-Site: cross-site`. (#66665)
• ·Auto-reply/billing: classify pure billing cooldown fallback summaries from structured fallback reasons so users see billing guidance instead of the generic failure reply. (#66363)
• ·Agents/fallback: preserve the original prompt body on model fallback retries with session history so the retrying model keeps the active task instead of only seeing a generic continue message. (#66029)
• ·Reply/secrets: resolve active reply channel/account SecretRefs before reply-run message-action discovery so channel token SecretRefs (for example Discord) do not degrade into discovery-time unresolved-secret failures. (#66796)
• ·Agents/Anthropic: ignore non-positive Anthropic Messages token overrides and fail locally when no positive token budget remains, so invalid `max_tokens` values no longer reach the provider API. (#66664)
• ·Agents/context engines: preserve prompt-only token counts, not full request totals, when deferred maintenance reuses after-turn runtime context so background compaction bookkeeping matches the active prompt window. (#66820)
• ·BlueBubbles/inbound: add a persistent file-backed GUID dedupe so MessagePoller webhook replays after BB Server restart or reconnect no longer cause the agent to re-reply to already-handled messages. (#19176, #12053, #66816)
• ·Secrets/plugins/status: align SecretRef inspect-vs-strict handling across plugin preload, read-only status/agents surfaces, and runtime auth paths so unresolved refs no longer crash read-only CLI flows while runtime-required non-env refs stay strict. (#66818)
• ·Memory/dreaming: stop ordinary transcripts that merely quote the dream-diary prompt from being classified as internal dreaming runs and silently dropped from session recall ingestion. (#66852)
• ·Telegram/documents: sanitize binary reply context and ZIP-like archive extraction so `.epub` and `.mobi` uploads can no longer leak raw binary into prompt context through reply metadata or archive-to-`text/plain` coercion. (#66877)
• ·Telegram/native commands: restore plugin-registry-backed auto defaults for native commands and native skills so Telegram slash commands keep registering when `commands.native` and `commands.nativeSkills` stay on `auto`. (#66843)
• ·OpenRouter/Qwen3: parse `reasoning_details` stream deltas as thinking content without skipping same-chunk tool calls, so Qwen3 replies no longer fail empty on OpenRouter and mixed reasoning/tool-call chunks still execute normally. (#66905)
• ·fix(bluebubbles): replay missed webhook messages after gateway restart via a persistent per-account cursor and `/api/v1/message/query?after=<ts>` pass, so messages delivered while the gateway was down no longer disappear. Uses the existing `processMessage` path and is deduped by #66816's inbound GUID cache. (#66857, #66721)
• ·Telegram/native commands: keep Telegram command-sync cache process-local so gateway restarts re-register the menu instead of trusting stale on-disk sync state after Telegram cleared commands out-of-band. (#66730)
• ·Audio/self-hosted STT: restore `models.providers.*.request.allowPrivateNetwork` for audio transcription so private or LAN speech-to-text endpoints stop tripping SSRF blocks after the v2026.4.14 regression. (#66692)
• ·Auto-reply/media: allow workspace-rooted absolute media paths in auto-reply send flows so valid local media references no longer fail path validation. (#66689)
• ·WhatsApp/Baileys media upload: harden encrypted upload handling so large outbound media sends avoid buffer spikes and reliability regressions. (#65966)
• ·QQBot/cron: guard against undefined `event.content` in `parseFaceTags` and `filterInternalMarkers` so cron-triggered agent turns with no content payload no longer crash with `TypeError: Cannot read properties of undefined (reading 'startsWith')`. (#66302)
• ·CLI/plugins: stop `--dangerously-force-unsafe-install` plugin installs from falling back to hook-pack installs after security scan failures, while still preserving non-security fallback behavior for real hook packs. (#58909)
• ·Claude CLI/sessions: classify `No conversation found with session ID` as `session_expired` so expired CLI-backed conversations clear the stale binding and recover on the next turn. (#65028)
• ·Context Engine: gracefully fall back to the legacy engine when a third-party context engine plugin fails at resolution time (unregistered id, factory throw, or contract violation), preventing a full gateway outage on every channel. (#66930)
• ·Control UI/chat: keep optimistic user message cards visible during active sends by deferring same-session history reloads until the active run ends, including aborted and errored runs. (#66997)
• ·Media/Slack: allow host-local CSV and Markdown uploads only when the fallback buffer actually decodes as text, so real plain-text files work without letting opaque non-text blobs renamed to `.csv` or `.md` slip past the host-read guard. (#67047)
• ·Ollama/onboarding: split setup into `Cloud + Local`, `Cloud only`, and `Local only`, support direct `OLLAMA_API_KEY` cloud setup without a local daemon, and keep Ollama web search on the local-host path. (#67005)
• ·Docker/build: verify `@matrix-org/matrix-sdk-crypto-nodejs` native bindings with `find` under `node_modules` instead of a hardcoded `.pnpm/...` path so pnpm v10+ virtual-store layouts no longer fail the image build. (#67143)
• ·Matrix/E2EE: keep startup bootstrap conservative for passwordless token-auth bots, still attempt the guarded repair pass without requiring `channels.matrix.password`, and document the remaining password-UIA limitation. (#66228)
• ·Cron/announce delivery: suppress mixed-content isolated cron announce replies that end with `NO_REPLY` so trailing silent sentinels no longer leak summary text to the target channel. (#65004)
• ·Plugins/bundled channels: partition bundled channel lazy caches by active bundled root so `OPENCLAW_BUNDLED_PLUGINS_DIR` flips stop reusing stale plugin, setup, secrets, and runtime state. (#67200)
• ·Packaging/plugins: prune common test/spec cargo from bundled plugin runtime dependencies and fail npm release validation if packaged test cargo reappears, keeping published tarballs leaner without plugin-specific special cases. (#67275)
• ·Agents/context + Memory: trim default startup/skills prompt budgets, cap `memory_get` excerpts by default with explicit continuation metadata, and keep QMD reads aligned with the same bounded excerpt contract so long sessions pull less context by default without losing deterministic follow-up reads.
• ·Matrix/commands: skip DM pairing-store reads on room traffic now that room control-command authorization ignores pairing-store entries, keeping the room path narrower without changing room auth behavior. (#67325)
• ·Matrix/security: block DM pairing-store entries from authorizing room control commands. (#67294)
• ·Gateway/security: enforce `localRoots` containment on the webchat audio embedding path. (#67298)
• ·Webchat/security: reject remote-host `file://` URLs in the media embedding path. (#67293)
• ·Dreaming/memory-core: use the ingestion day, not the source file day, for daily recall dedupe so repeat sweeps of the same daily note can increment `dailyCount` across days instead of stalling at `1`. (#67091)

Changes

• ·Telegram/forum topics: surface human topic names in agent context, prompt metadata, and plugin hook metadata by learning names from Telegram forum service messages. (#65973)

Fixes

• ·UI/chat: replace marked.js with markdown-it so maliciously crafted markdown can no longer freeze the Control UI via ReDoS. (#46707)
• ·Auto-reply/send policy: keep `sendPolicy: "deny"` from blocking inbound message processing, so the agent still runs its turn while all outbound delivery is suppressed for observer-style setups. (#65461, #53328)
• ·BlueBubbles: lazy-refresh the Private API server-info cache on send when reply threading or message effects are requested but status is unknown, so sends no longer silently degrade to plain messages when the 10-minute cache expires. (#65447, #43764)
• ·Heartbeat/security: force owner downgrade for untrusted `hook:wake` system events [AI-assisted]. (#66031)
• ·Browser/security: enforce SSRF policy on snapshot, screenshot, and tab routes [AI]. (#66040)
• ·Microsoft Teams/security: enforce sender allowlist checks on SSO signin invokes [AI]. (#66033)
• ·Config/security: redact `sourceConfig` and `runtimeConfig` alias fields in `redactConfigSnapshot` [AI]. (#66030)
• ·Agents/context engines: run opt-in turn maintenance as idle-aware background work so the next foreground turn no longer waits on proactive maintenance. (#65233)
• ·Plugins/status: report the registered context-engine IDs in `plugins inspect` instead of the owning plugin ID, so non-matching engine IDs and multi-engine plugins are classified correctly. (#58766)
• ·Context engines: reject resolved plugin engines whose reported `info.id` does not match their registered slot id, so malformed engines fail fast before id-based runtime branches can misbehave. (#63222)
• ·WhatsApp: patch installed Baileys media encryption writes during OpenClaw postinstall so the default npm/install.sh delivery path waits for encrypted media files to finish flushing before readback, avoiding transient `ENOENT` crashes on image sends. (#65896)
• ·Gateway/update: unify service entrypoint resolution around the canonical bundled gateway entrypoint so update, reinstall, and doctor repair stop drifting between stale `dist/entry.js` and current `dist/index.js` paths. (#65984)
• ·Heartbeat/Telegram topics: keep isolated heartbeat replies on the bound forum topic when `target=last`, instead of dropping them into the group root chat. (#66035)
• ·Browser/CDP: let managed local Chrome readiness, status probes, and managed loopback CDP control bypass browser SSRF policy for their own loopback control plane, so OpenClaw no longer misclassifies a healthy child browser as "not reachable after start". (#65695, #66043)
• ·Gateway/sessions: stop heartbeat, cron-event, and exec-event turns from overwriting shared-session routing and origin metadata, preventing synthetic `heartbeat` targets from poisoning later cron or user delivery. (#66073, #63733, #35300)
• ·Browser/CDP: let local attach-only `manual-cdp` profiles reuse the local loopback CDP control plane under strict default policy and remote-class probe timeouts, so tabs/snapshot stop falsely reporting a live local browser session as not running. (#65611, #66080)
• ·Cron/scheduler: stop inventing short retries when cron next-run calculation returns no valid future slot, and keep a maintenance wake armed so enabled unscheduled jobs recover without entering a refire loop. (#66019, #66083)
• ·Cron/scheduler: preserve the active error-backoff floor when maintenance repair recomputes a missing cron next-run, so recurring errored jobs do not resume early after a transient next-run resolution failure. (#66019, #66083, #66113)
• ·Outbound/delivery-queue: persist the originating outbound `session` context on queued delivery entries and replay it during recovery, so write-ahead-queued sends keep their original outbound media policy context after restart instead of evaluating against a missing session. (#66025)
• ·Auto-reply/queue: split collect-mode followup drains into contiguous groups by per-message authorization context (sender id, owner status, exec/bash-elevated overrides), so queued items from different senders or exec configs no longer execute under the last queued run's owner-only and exec-approval context. (#66024)
• ·Dreaming/memory-core: require a live queued Dreaming cron event before the heartbeat hook runs the sweep, so managed Dreaming no longer replays on later heartbeats after the scheduled run was already consumed. (#66139)
• ·Control UI/Dreaming: stop Imported Insights and Memory Palace from calling optional `memory-wiki` gateway methods when the plugin is off, and refresh config before wiki reloads so the Dreaming tab stops showing misleading unknown-method failures. (#66140)
• ·Agents/tools: only mark streamed unknown-tool retries as counted when a streamed message actually classifies an unavailable tool, and keep incomplete streamed tool names from resetting the retry streak before the final assistant message arrives. (#66145)
• ·Memory/active-memory: move recalled memory onto the hidden untrusted prompt-prefix path instead of system prompt injection, label the visible Active Memory status line fields, and include the resolved recall provider/model in gateway debug logs so trace/debug output matches what the model actually saw. (#66144)
• ·Memory/QMD: stop treating legacy lowercase `memory.md` as a second default root collection, so QMD recall no longer searches phantom `memory-alt-*` collections and builtin/QMD root-memory fallback stays aligned. (#66141)
• ·Agents/OpenAI: map `minimal` thinking to OpenAI's supported `low` reasoning effort for GPT-5.4 requests, so embedded runs stop failing request validation.
• ·Voice-call/media-stream: resolve the source IP from trusted forwarding headers for per-IP pending-connection limits when `webhookSecurity.trustForwardingHeaders` and `trustedProxyIPs` are configured, and reserve `maxConnections` capacity for in-flight WebSocket upgrades so concurrent handshakes can no longer momentarily exceed the operator-set cap. (#66027)
• ·Feishu/allowlist: canonicalize allowlist entries by explicit `user`/`chat` kind, strip repeated `feishu:`/`lark:` provider prefixes, and stop folding opaque Feishu IDs to lowercase, so allowlist matching no longer crosses user/chat namespaces or widens to case-insensitive ID matches the operator did not intend. (#66021)
• ·TTS/reply media: persist OpenClaw temp voice outputs into managed outbound media and allow them through reply-media normalization, so voice-note replies stop silently dropping. (#63511)
• ·Agents/tools: treat Windows drive-letter paths (`C:\\...`) as absolute when resolving sandbox and read-tool paths so workspace root is not prepended under POSIX path rules. (#54039)
• ·Agents/OpenAI: recover embedded GPT-style runs when reasoning-only or empty turns need bounded continuation, with replay-safe retry gating and incomplete-turn fallback when no visible answer arrives. (#66167)
• ·Outbound/relay-status: suppress internal relay-status placeholder payloads (`No channel reply.`, `Replied in-thread.`, `Replied in #...`, wiki-update status variants ending in `No channel reply.`) before channel delivery so internal housekeeping text does not leak to users.
• ·Slack/doctor: add a dedicated doctor-contract sidecar so config warmup paths such as `openclaw cron` no longer fall back to Slack's broader contract surface, which could trigger Slack-related config-read crashes on affected setups. (#63192)
• ·Hooks/session-memory: pass the resolved agent workspace into gateway `/new` and `/reset` session-memory hooks so reset snapshots stay scoped to the right agent workspace instead of leaking into the default workspace. (#64735)

Changes

• ·Plugins/loading: narrow CLI, provider, and channel activation to manifest-declared needs, preserve explicit scope and trust boundaries, and centralize manifest-owner policy so startup, command discovery, and runtime activation avoid loading unrelated plugin runtime. (#65120, #65259, #65298, #65429, #65459)
• ·Memory/active-memory: default QMD recall to search and surface better search-path telemetry so memory-backed recall works more predictably out of the box. (#65068)
• ·Docs/providers: expand bundled provider docs with richer capability, env-var, and setup guidance across provider pages.
• ·Docs/memory-wiki: add the recommended QMD + bridge-mode hybrid recipe plus zero-artifact troubleshooting guidance for `memory-wiki` bridge setups. (#63165)

Fixes

• ·CLI/update: respawn tracked plugin refresh from the updated entrypoint after package self-updates so `openclaw update` stops failing on stale hashed `dist/install.runtime-*.js` chunk imports. (#65471)
• ·Memory/active-memory: keep recall runs on the resolved channel when wrappers like `mx-claw` are enabled, improve lexical fallback ranking, and keep lexical boosts out of hybrid search so recall finds the right memories more consistently. (#65049, #65395)
• ·Dreaming: consume managed heartbeat events exactly once, stage light-sleep confidence from all recorded short-term signals, wake scheduled jobs immediately, raise dreaming-only promotion enough to cross the durable-memory gate, and stop dreaming from re-ingesting its own narrative transcripts.
• ·Dreaming/narrative: harden transient narrative cleanup by retrying timed-out deletes, scrubbing stale dreaming session artifacts through the lock-aware session-store path, and isolating transient narrative session keys per workspace. (#65320, #61674)
• ·Memory/wiki: preserve Unicode letters, digits, and combining marks in wiki slugs and contradiction clustering, and cap Unicode filename segments to safe byte lengths so non-ASCII titles stop collapsing or overflowing path limits. (#64742)
• ·Memory/short-term recall: allow nested daily notes under `memory/**/YYYY-MM-DD.md` to feed short-term recall, while still excluding generated dream reports under `memory/dreaming/**` so dreaming does not promote its own output. (#64682)
• ·UI/WebChat: hide synthetic transcript-repair tool results from chat history reloads so internal recovery markers do not leak into visible chat after reconnects. (#65247)
• ·WhatsApp/outbound: fall back to the first `mediaUrls` entry when `mediaUrl` is empty so gateway media sends stop silently dropping attachments that already have a resolved media list. (#64394)
• ·Doctor/Discord: stop `openclaw doctor --fix` from rewriting legacy Discord preview-streaming config into the nested modern shape, so downgrades can still recover without hand-editing `channels.discord.streaming`. (#65035)
• ·Gateway/auth: blank the shipped example gateway credential in `.env.example` and fail startup when a copied placeholder token or password is still configured, so operators cannot accidentally launch with a publicly known secret. (#64586)
• ·Memory/active-memory+dreaming: keep active-memory recall runs on the strongest resolved channel, consume managed dreaming heartbeat events exactly once, stop dreaming from re-ingesting its own narrative transcripts, and add explicit repair/dedupe recovery flows in CLI, doctor, and the Dreams UI.
• ·Agents/queueing: carry orphaned active-turn user text into the next prompt before repairing transcript ordering, so follow-up messages that arrive mid-run are no longer silently dropped. (#65388)
• ·Gateway/keepalive: stop marking WebSocket tick broadcasts as droppable so slow or backpressured clients do not self-disconnect with `tick timeout` while long-running work is still alive. (#65256)
• ·Matrix/mentions: keep room mention gating strict while accepting visible `@displayName` Matrix URI labels, so `requireMention` works for non-OpenClaw Matrix clients again. (#64796)
• ·Doctor: warn when on-disk agent directories still exist under `~/.openclaw/agents/<id>/agent` but the matching `agents.list[]` entries are missing from config. (#65113)
• ·Telegram: route approval button callback queries onto a separate sequentializer lane so plugin approval clicks can resolve immediately instead of deadlocking behind the blocked agent turn. (#64979)
• ·Telegram/direct sessions: keep commentary-only assistant fallback payloads out of visible direct delivery, so Codex planning chatter cannot leak into Telegram DMs when a run has no `final_answer` text.
• ·Gateway/keepalive: stop marking WebSocket tick broadcasts as droppable so slow or backpressured clients do not self-disconnect with `tick timeout` while long-running work is still alive. (#65436)
• ·Gateway/plugins: always send a non-empty `idempotencyKey` for plugin subagent runs, so dreaming narrative jobs stop failing gateway schema validation. (#65354)
• ·Gateway/auth: blank the shipped example gateway credential in `.env.example` and fail startup when a copied placeholder token or password is still configured, so operators cannot accidentally launch with a publicly known secret. (#64586)
• ·Plugins/memory-core dreaming: keep bundled `memory-core` loaded alongside an explicit external memory slot owner only when that owner enables dreaming, while preserving `plugins.slots.memory = "none"` disable semantics. (#65411)
• ·Doctor/Discord: stop `openclaw doctor --fix` from rewriting legacy Discord preview-streaming config into the nested modern shape, so downgrades can still recover without hand-editing `channels.discord.streaming`.
• ·Doctor: warn when on-disk agent directories still exist under `~/.openclaw/agents/<id>/agent` but the matching `agents.list[]` entries are missing from config. (#65113)
• ·CLI/plugins: honor `memory-wiki` when `plugins.allow` is set for `openclaw wiki`, and pass the active app config into the metadata registrar so plugin-owned wiki commands resolve the live plugin config instead of falling back to defaults. (#64779, #65012)
• ·QA/packaging: stop packaged QA helpers from crashing when optional scenario execution config is unavailable, so npm distributions can skip the repo-only scenario pack without breaking completion-cache and startup paths. (#65118)
• ·Media/audio transcription: surface the real provider failure when every audio transcription attempt fails, so status output and the CLI stop collapsing those errors into generic skips. (#65096)
• ·Infra/net: fix multipart FormData fields (including `model`) being silently dropped when a guarded runtime fetch body crosses a FormData implementation boundary, restoring OpenAI audio transcription requests that failed with HTTP 400. (#64349)
• ·Dreaming/diary: use the host local timezone for diary timestamps when `dreaming.timezone` is unset, and include the timezone abbreviation so `DREAMS.md` and the UI make local or UTC time explicit. (#65034, #65057)
• ·Dreaming/promotion: raise phase reinforcement enough for repeated dreaming-only revisits to clear the default durable-memory gate after multiple days, instead of stalling just below the score threshold. (#64068)
• ·Dreaming/light-sleep: compute staged candidate confidence from all recorded short-term signals instead of recall-only counts, so dreaming-only entries stop rendering as `confidence: 0.00`. (#64599)
• ·Plugins/memory: restore cached memory capability public artifacts on plugin-registry cache hits so memory-backed artifact surfaces stay visible after warm loads.
• ·Gateway/cron: preserve requested isolated-agent config across runtime reloads so subagent jobs and heartbeat overrides keep the right workspace and heartbeat settings when the hot-loaded snapshot is stale.
• ·Cron/isolated sessions: persist the right transcript path for each isolated run, including fresh session rollovers, so cron runs stop appending to stale session files.
• ·Discord/gateway: clear stale heartbeat timers before reconnecting so zombie gateway callbacks cannot crash the process and drop in-flight replies. (#65009)
• ·Matrix/mentions: keep room mention gating strict while accepting visible `@displayName` Matrix URI labels, so `requireMention` works for non-OpenClaw Matrix clients again. (#64796)
• ·Agents/Anthropic replay: preserve immutable signed-thinking replay safety across stored and live reruns, keep non-thinking embedded `tool_result` user blocks intact, and drop conflicting preserved tool IDs before validation so retries stop degrading into omitted tool calls. (#65126)
• ·Memory/QMD: allow channel sessions in the shipped default QMD scope, while still denying groups.
• ·Memory/QMD: stop registering the legacy lowercase root memory file as a separate default collection, so QMD now prefers `MEMORY.md` and the `memory/` tree without duplicate collection-add warnings.
• ·Memory/memory-core: watch the `memory` directory directly and ignore non-markdown churn so nested note changes still sync on macOS + Node 25 environments where recursive `memory/**/*.md` glob watching fails. (#64711)
• ·WhatsApp: centralize per-account connection ownership so reconnects, login recovery, and outbound readiness stay attached to the live socket instead of drifting across monitor and login paths. (#65290)
• ·iMessage: retry transient `watch.subscribe` startup failures before tearing down the monitor, and sanitize startup error logging so brief local transport stalls do not immediately bounce the channel or leak raw imsg RPC payloads into logs. (#65393)
• ·CLI/audio providers: report env-authenticated providers as configured in `openclaw infer audio providers --json`, while keeping trusted workspace provider env lookup defaults stable during auth setup. (#65491)
• ·Plugins/install: reinstall bundled runtime packages when the matching platform native optional child is missing, so packaged Windows installs can recover dependencies that were packed on another host OS.

Changes

• ·Dreaming/memory-wiki: add ChatGPT import ingestion plus new `Imported Insights` and `Memory Palace` diary subtabs so Dreaming can inspect imported source chats, compiled wiki pages, and full source pages directly from the UI. (#64505)
• ·Control UI/webchat: render assistant media/reply/voice directives as structured chat bubbles, add the `[embed ...]` rich output tag, and gate external embed URLs behind config. (#64104)
• ·Tools/video_generate: add URL-only generated asset delivery, typed `providerOptions`, reference audio inputs, per-asset role hints, `adaptive` aspect-ratio support, and a higher image-input cap so video providers can expose richer generation modes without forcing large files into memory. (#61987, #61988)
• ·Feishu: improve document comment sessions with richer context parsing, comment reactions, and typing feedback so document-thread conversations behave more like chat conversations. (#63785)
• ·Microsoft Teams: add reaction support, reaction listing, Graph pagination, and delegated OAuth setup for sending reactions while preserving application-auth read paths. (#51646)
• ·Plugins: allow plugin manifests to declare activation and setup descriptors so plugin setup flows can describe required auth, pairing, and configuration steps without hardcoded core special cases. (#64780)
• ·Ollama: cache `/api/show` context-window and capability metadata during model discovery so repeated picker refreshes stop refetching unchanged models, while still retrying after empty responses and invalidating on digest changes. (#64753)
• ·Models/providers: surface how configured OpenAI-compatible endpoints are classified in embedded-agent debug logs, so local and proxy routing issues are easier to diagnose. (#64754)
• ·QA/parity: add the GPT-5.4 vs Opus 4.6 agentic parity report gate with shared scenario coverage checks, stricter evidence heuristics, and skipped-scenario accounting for maintainer review. (#64441)

Fixes

• ·OpenAI/Codex OAuth: stop rewriting the upstream authorize URL scopes so new Codex sign-ins do not fail with `invalid_scope` before returning an authorization code. (#64713)
• ·Audio transcription: disable pinned DNS only for OpenAI-compatible multipart requests, while still validating hostnames, so OpenAI, Groq, and Mistral transcription works again without weakening other request paths. (#64766)
• ·macOS/Talk Mode: after granting microphone permission on first enable, continue starting Talk Mode instead of requiring a second toggle. (#62459)
• ·Control UI/webchat: persist agent-run TTS audio replies into webchat history and preserve interleaved tool card pairing so generated audio and mixed tool output stay attached to the right messages. (#63514)
• ·WhatsApp: honor the configured default account when the active listener helper is used without an explicit account id, so named default accounts do not get registered under `default`. (#53918)
• ·ACP/agents: suppress commentary-phase child assistant relay text in ACP parent stream updates, so spawned child runs stop leaking internal progress chatter into the parent session.
• ·Agents/timeouts: honor explicit run timeouts in the LLM idle watchdog and align default timeout config so slow models can keep working until the configured limit instead of using the wrong idle window.
• ·Config: include `asyncCompletion` in the generated zod schema so documented async completion config no longer fails with an unrecognized-key error. (#63618)
• ·Google/Veo: stop sending the unsupported `numberOfVideos` request field so Gemini Developer API Veo runs do not fail before OpenClaw can complete the intended Google video generation path. (#64723)
• ·QA/packaging: stop packaged CLI startup and completion cache generation from reading repo-only QA scenario markdown, ship the bundled QA scenario pack in npm releases, and keep `openclaw completion --write-state` working even if QA setup is broken. (#64648)
• ·Codex/QA: keep Codex app-server coordination chatter out of visible replies, add a live QA leak scenario, and classify leaked harness meta text as a QA failure instead of a successful reply.
• ·WhatsApp: route `message react` through the gateway-owned action path so reactions use the live WhatsApp listener in both DM and group chats, matching `message send` and `message poll`.
• ·Auto-reply/WhatsApp: preserve inbound image attachment notes after media understanding so image edits keep the real saved media path instead of hallucinating a missing local path. (#64918)
• ·Telegram/sessions: keep topic-scoped session initialization on the canonical topic transcript path when inbound turns omit `MessageThreadId`, so one topic session no longer alternates between bare and topic-qualified transcript files. (#64869)
• ·Agents/failover: scope assistant-side fallback classification and surfaced provider errors to the current attempt instead of stale session history, so cross-provider fallback runs stop inheriting the previous provider's failure. (#62907)
• ·MiniMax/OAuth: write `api: "anthropic-messages"` and `authHeader: true` into the `minimax-portal` config patch during `openclaw configure`, so re-authenticated portal setups keep Bearer auth routing working. (#64964)

Changes

• ·Dreaming/memory-wiki: add ChatGPT import ingestion plus new `Imported Insights` and `Memory Palace` diary subtabs so Dreaming can inspect imported source chats, compiled wiki pages, and full source pages directly from the UI. (#64505)
• ·Control UI/webchat: render assistant media/reply/voice directives as structured chat bubbles, add the `[embed ...]` rich output tag, and gate external embed URLs behind config. (#64104)
• ·Tools/video_generate: add URL-only generated asset delivery, typed `providerOptions`, reference audio inputs, per-asset role hints, `adaptive` aspect-ratio support, and a higher image-input cap so video providers can expose richer generation modes without forcing large files into memory. (#61987, #61988)
• ·Feishu: improve document comment sessions with richer context parsing, comment reactions, and typing feedback so document-thread conversations behave more like chat conversations. (#63785)
• ·Microsoft Teams: add reaction support, reaction listing, Graph pagination, and delegated OAuth setup for sending reactions while preserving application-auth read paths. (#51646)
• ·Plugins: allow plugin manifests to declare activation and setup descriptors so plugin setup flows can describe required auth, pairing, and configuration steps without hardcoded core special cases. (#64780)
• ·Ollama: cache `/api/show` context-window and capability metadata during model discovery so repeated picker refreshes stop refetching unchanged models, while still retrying after empty responses and invalidating on digest changes. (#64753)
• ·Models/providers: surface how configured OpenAI-compatible endpoints are classified in embedded-agent debug logs, so local and proxy routing issues are easier to diagnose. (#64754)
• ·QA/parity: add the GPT-5.4 vs Opus 4.6 agentic parity report gate with shared scenario coverage checks, stricter evidence heuristics, and skipped-scenario accounting for maintainer review. (#64441)

Fixes

• ·OpenAI/Codex OAuth: stop rewriting the upstream authorize URL scopes so new Codex sign-ins do not fail with `invalid_scope` before returning an authorization code. (#64713)
• ·Audio transcription: disable pinned DNS only for OpenAI-compatible multipart requests, while still validating hostnames, so OpenAI, Groq, and Mistral transcription works again without weakening other request paths. (#64766)
• ·macOS/Talk Mode: after granting microphone permission on first enable, continue starting Talk Mode instead of requiring a second toggle. (#62459)
• ·Control UI/webchat: persist agent-run TTS audio replies into webchat history and preserve interleaved tool card pairing so generated audio and mixed tool output stay attached to the right messages. (#63514)
• ·WhatsApp: honor the configured default account when the active listener helper is used without an explicit account id, so named default accounts do not get registered under `default`. (#53918)
• ·ACP/agents: suppress commentary-phase child assistant relay text in ACP parent stream updates, so spawned child runs stop leaking internal progress chatter into the parent session.
• ·Agents/timeouts: honor explicit run timeouts in the LLM idle watchdog and align default timeout config so slow models can keep working until the configured limit instead of using the wrong idle window.
• ·Config: include `asyncCompletion` in the generated zod schema so documented async completion config no longer fails with an unrecognized-key error. (#63618)
• ·Google/Veo: stop sending the unsupported `numberOfVideos` request field so Gemini Developer API Veo runs do not fail before OpenClaw can complete the intended Google video generation path. (#64723)
• ·QA/packaging: stop packaged CLI startup and completion cache generation from reading repo-only QA scenario markdown, ship the bundled QA scenario pack in npm releases, and keep `openclaw completion --write-state` working even if QA setup is broken. (#64648)
• ·Codex/QA: keep Codex app-server coordination chatter out of visible replies, add a live QA leak scenario, and classify leaked harness meta text as a QA failure instead of a successful reply.
• ·WhatsApp: route `message react` through the gateway-owned action path so reactions use the live WhatsApp listener in both DM and group chats, matching `message send` and `message poll`.

Changes

• ·Models/Codex: add the bundled Codex provider and plugin-owned app-server harness so `codex/gpt-*` models use Codex-managed auth, native threads, model discovery, and compaction while `openai/gpt-*` stays on the normal OpenAI provider path. (#64298)
• ·Memory/Active Memory: add a new optional Active Memory plugin that gives OpenClaw a dedicated memory sub-agent right before the main reply, so ongoing chats can automatically pull in relevant preferences, context, and past details without making users remember to manually say "remember this" or "search memory" first. Includes configurable message/recent/full context modes, live `/verbose` inspection, advanced prompt/thinking overrides for tuning, and opt-in transcript persistence for debugging. Docs: https://docs.openclaw.ai/concepts/active-memory. (#63286)
• ·macOS/Talk: add an experimental local MLX speech provider for Talk Mode, with explicit provider selection, local utterance playback, interruption handling, and system-voice fallback. (#63539)
• ·Tools/video generation: add Seedance 2.0 model refs to the bundled fal provider and submit the provider-specific duration, resolution, audio, and seed metadata fields needed for live Seedance 2.0 runs.
• ·Microsoft Teams: add message actions for pin, unpin, read, react, and listing reactions. (#53432)
• ·QA/Matrix: add a live `openclaw qa matrix` lane backed by a disposable Matrix homeserver, shared live-transport seams, and Matrix-specific transport coverage for threading, reactions, restart, and allowlist behavior. (#64489)
• ·QA/Telegram: add a live `openclaw qa telegram` lane for private-group bot-to-bot checks, harden its artifact handling, and preserve native Telegram command reply threading for QA verification. (#64303)
• ·QA/testing: add a `--runner multipass` lane for `openclaw qa suite` so repo-backed QA scenarios can run inside a disposable Linux VM and write back the usual report, summary, and VM logs. (#63426)
• ·CLI/exec policy: add a local `openclaw exec-policy` command with `show`, `preset`, and `set` subcommands for synchronizing requested `tools.exec.*` config with the local exec approvals file, plus follow-up hardening for node-host rejection, rollback safety, and sync conflict detection. (#64050)
• ·Gateway: add a `commands.list` RPC so remote gateway clients can discover runtime-native, text, skill, and plugin commands with surface-aware naming and serialized argument metadata. (#62656)
• ·Models/providers: add per-provider `models.providers.*.request.allowPrivateNetwork` for trusted self-hosted OpenAI-compatible endpoints, keep the opt-in scoped to model request surfaces, and refresh cached WebSocket managers when request transport overrides change. (#63671)
• ·Feishu: standardize request user agents and register the bot as an AI agent so Feishu deployments identify OpenClaw consistently. (#63835)
• ·Matrix/partial streaming: add MSC4357 live markers to draft preview sends and edits so supporting Matrix clients can render a live/typewriter animation and stop it when the final edit lands. (#63513)
• ·Control UI/dreaming: simplify the Scene and Diary surfaces, preserve unknown phase state for partial status payloads, and stabilize waiting-entry recency ordering so Dreaming status and review lists stay clear and deterministic. (#64035)
• ·Agents: add an opt-in strict-agentic embedded Pi execution contract for GPT-5-family runs so plan-only or filler turns keep acting until they hit a real blocker. (#64241)
• ·Agents/OpenAI: add provider-owned OpenAI/Codex tool schema compatibility and surface embedded-run replay/liveness state for long-running runs. (#64300)
• ·Docs i18n: chunk raw doc translation, reject truncated tagged outputs, avoid ambiguous body-only wrapper unwrapping, and recover from terminated Pi translation sessions without changing the default `openai/gpt-5.4` path. (#62969, #63808)

Fixes

• ·Browser/security: tighten browser and sandbox navigation defenses across strict SSRF defaults, hostname allowlists, interaction-driven redirects, subframes, CDP discovery, existing sessions, tab actions, noVNC, marker-span sanitization, and Docker CDP source-range enforcement. (#61404, #63332, #63882, #63885, #63889, #64367, #64370, #64371)
• ·Security/tools: harden exec preflight reads, host env denylisting, node output boundaries, outbound host-media reads, profile-mutation authorization, plugin install dependency scanning, ACPX tool hooks, Gmail watcher token redaction, and oversized realtime WebSocket frame handling. (#62333, #62661, #62662, #63277, #63551, #63553, #63886, #63890, #63891, #64459)
• ·OpenAI/Codex: add required Codex OAuth scopes, classify provider/runtime failures more clearly, stop suggesting `/elevated full` when auto-approved host exec is unavailable, add OpenAI/Codex tool-schema compatibility, and preserve embedded-run replay/liveness truth across compaction retries and mutating side effects. (#64300, #64439)
• ·CLI/WhatsApp media sends: route gateway-mode outbound sends with `--media` through the channel `sendMedia` path and preserve media access context, so WhatsApp document and attachment sends stop silently dropping the file while still delivering the caption. (#64478, #64492)
• ·Microsoft Teams: restore media downloads for personal DMs, Bot Framework `a:` conversations, OneDrive/SharePoint shared files, and Graph-backed chat IDs; accept Bot Framework audience tokens; prevent feedback-learning filename collisions; keep long tool chains alive with typing indicators; add SSO sign-in callbacks; inject parent context for thread replies; and deliver cron announcements to Teams conversation IDs. (#54932, #55383, #55386, #58001, #58249, #58774, #59731, #60956, #62219, #62674, #63063, #63942, #63945, #63949, #63951, #63953, #64087, #64088, #64089)
• ·Gateway/tailscale: start Tailscale exposure and the gateway update check before awaiting channel and plugin sidecar startup so remote operators are not locked out when startup sidecars stall.
• ·Gateway/startup: keep WebSocket RPC available while channels and plugin sidecars start, hold `chat.history` unavailable until startup sidecars finish so synchronous history reads cannot stall startup (reported in #63450), refresh advertised gateway methods after deferred plugin reloads, and enforce the pre-auth WebSocket upgrade budget before the no-handler 503 path so upgrade floods cannot bypass connection limits during that window. (#63480)
• ·WhatsApp: keep inbound replies, media, composing indicators, and queued outbound deliveries attached to the current socket across reconnect gaps, including fresh retry-eligible sends after the listener comes back. (#30806, #46299, #62892, #63916)
• ·Gateway/thread routing: preserve Slack, Telegram, Mattermost, Matrix, ACP, restart-sentinel, and agent announce delivery targets so subagent, cron, stream-relay, session fallback, and restart messages land back in the originating thread, topic, or room casing. (#54840, #57056, #63143, #63228, #63506, #64343, #64391)
• ·Models/fallback: preserve `/models` selection across transient primary-model failures and config reloads, allow timeout cooldown probes, classify OpenRouter no-endpoints responses, detect llama.cpp context overflows, and keep provider/runtime context metadata stable through reloads. (#61472, #64196, #64471)
• ·Agents/BTW: keep `/btw` side questions working after tool-use turns by stripping replayed tool blocks, hidden reasoning, and malformed image payloads, omitting empty tool arrays, allowing Bedrock `auth: "aws-sdk"`, and routing Feishu `/btw` plus `/stop` through bounded out-of-band lanes. (#64218, #64219, #64225, #64324)
• ·Control UI/BTW: render `/btw` side results as dismissible ephemeral cards in the browser, send `/btw` immediately during active runs, and clear stale BTW cards on reset flows so webchat matches the intended detached side-question behavior. (#64290)
• ·Commands/targeting: use the selected agent or session for command output, send policy, usage/cost, context reports, model lists, bash sandbox hints, BTW/compact working directories, plugin commands, and session exports so multi-agent commands describe and mutate the intended target instead of the requester.
• ·Conversation bindings: normalize focused/current conversation ids, preserve binding metadata on account and Discord rebinds, avoid stale Discord lifecycle windows, and keep generic activity touches persisted so reply routing survives rebinds and restarts.
• ·iMessage/self-chat: distinguish normal DM outbound rows from true self-chat using `destination_caller_id` plus chat participants, preserve multi-handle self-chat aliases, drop ambiguous reflected echoes, and strip wrapped imsg RPC text fields. (#61619, #63868, #63980, #63989, #64000)
• ·Matrix: keep multi-account room scoping consistent, keep packaged crypto migrations warning-only when appropriate, preserve ordered block streaming, add explicit Matrix block-streaming opt-in, and resolve verification/bootstrap from the packaged runtime entry. (#58449, #59249, #59266, #64373)
• ·Telegram/security: tighten Telegram `allowFrom` sender validation and keep `/whoami` allowlist reporting in sync with command auth checks.
• ·Agents/timeouts: extend the default LLM idle window to 120s and keep silent no-token idle timeouts on recovery paths, so slow models can retry or fall back before users see an error.
• ·Gateway/agents: preserve configured model selection and richer `IDENTITY.md` content across agent create/update flows and workspace moves, and fail safely instead of silently overwriting unreadable identity files. (#61577)
• ·Skills/TaskFlow: restore valid frontmatter fences for the bundled `taskflow` and `taskflow-inbox-triage` skills and copy bundled `SKILL.md` files as hard dist-runtime copies so skills stay discoverable and loadable after updates. (#64166, #64469)
• ·Skills: respect overridden home directories when loading personal skills so service, test, and custom launch environments read the intended user skill directory instead of the process home.
• ·Windows/exec: settle supervisor waits from child exit state after stdout and stderr drain even when `close` never arrives, so CLI commands stop hanging or dying with forced `SIGKILL` on Windows. (#64072)
• ·Browser/sandbox: prevent sandbox browser CDP startup hangs by recreating containers when the browser security hash changes and by waiting on the correct sandbox browser lifecycle. (#62873)
• ·QQBot/streaming: make block streaming configurable per QQ bot account via `streaming.mode` (`"partial"` | `"off"`, default `"partial"`) instead of hardcoding it off, so responses can be delivered incrementally. (#63746)
• ·QQBot/config: allow extra fields in `channels.qqbot` and `channels.qqbot.accounts.*` so extended qqbot builds can add new config options without gateway startup failing on schema validation. (#64075)
• ·Dreaming/gateway: require `operator.admin` for persistent `/dreaming on|off` changes and treat missing gateway client scopes as unprivileged instead of silently allowing config writes. (#63872)
• ·Gateway/pairing: prefer explicit QR bootstrap auth over earlier Tailscale auth classification so iOS `/pair qr` silent bootstrap pairing does not fall through to `pairing required`. (#59232)
• ·Browser/control: auto-generate browser-control auth tokens for `none` and `trusted-proxy` modes, and route browser auth/profile/doctor helpers through the public browser plugin facades. (#63280, #63957)
• ·Browser/act: centralize `/act` request normalization and execution dispatch while adding stable machine-readable route-level error codes for invalid requests, selector misuse, evaluate-disabled gating, target mismatch, and existing-session unsupported actions. (#63977)
• ·Security/QQBot: enforce media storage boundaries for all outbound local file paths and route image-size probes through SSRF-guarded media fetching instead of raw `fetch()`. (#63271, #63495)
• ·Channel setup: ignore workspace plugin shadows when resolving trusted channel setup catalog entries so onboarding and setup flows keep using the bundled, trusted setup contract.
• ·Gateway/memory startup: load the explicitly selected memory-slot plugin during gateway startup, while keeping restrictive allowlists and implicit default memory slots from auto-starting unrelated memory plugins. (#64423)
• ·Config/plugins: let config writes keep disabled plugin entries without forcing required plugin config schemas or crashing raw plugin validation, and avoid re-activating plugin registry state during schema checks. (#54971, #63296)
• ·Config validation: surface the actual offending field for strict-schema union failures in bindings, including top-level unexpected keys on the matching ACP branch. (#40841)
• ·Wizard/plugin config: coerce integer-typed plugin config fields from interactive text input so integer schema values persist as numbers instead of failing validation. (#63346)
• ·Daemon/gateway install: preserve safe custom service env vars on forced reinstall, merge prior custom PATH segments behind the managed service PATH, and stop removed managed env keys from persisting as custom carryover. (#63136)
• ·Cron/scheduling: treat `nextRunAtMs <= 0` as invalid across cron update, maintenance, timer, and stale-delivery paths so corrupted zero timestamps self-heal instead of causing immediate runs or skipped deliveries. (#63507)
• ·Cron/auth: resolve auth profiles consistently for isolated cron jobs so scheduled runs use the same configured provider credentials as interactive sessions. (#62797)
• ·Tasks: let `openclaw tasks cancel` cancel stuck background tasks that never reached a normal terminal state. (#62506)
• ·Sessions/model selection: preserve catalog-backed session model labels, provider-qualified context limits, and already-qualified session model refs when catalog metadata is unavailable, so model selection and memory/context budgets survive reloads without bogus provider prefixes. (#61382, #62493)
• ·Status: show configured fallback models in `/status` and shared session status cards so per-agent fallback configuration is visible before a live failover happens. (#33111)
• ·`/context detail` now compares the tracked prompt estimate with cached context usage and surfaces untracked provider/runtime overhead when present. (#28391)
• ·Gateway/sessions: scope bare `sessions.create` aliases like `main` to the requested agent while preserving the canonical `global` and `unknown` sentinel keys. (#58207)
• ·Gateway/session reset: emit the typed `before_reset` hook for gateway `/new` and `/reset`, preserving reset-hook behavior even when the previous transcript has already been archived. (#53872)
• ·Plugins/commands: pass the active host `sessionKey` into plugin command contexts, and include `sessionId` when it is already available from the active session entry, so bundled and third-party commands can resolve the current conversation reliably. (#59044)
• ·Agents/auth: honor `models.providers.*.authHeader` for pi embedded runner model requests by injecting `Authorization: Bearer <apiKey>` when requested. (#54390)
• ·Claude CLI: clear inherited Anthropic auth/header environment aliases before spawning Claude Code and add sanitized CLI backend auth-env diagnostics for debugging gateway-run provider selection.
• ·Agents/failover: classify AbortError and stream-abort messages as timeout so Ollama NDJSON stream aborts stop showing `reason=unknown` in model fallback logs. (#58324)
• ·Fireworks/FirePass: disable Kimi K2.5 Turbo reasoning output by forcing thinking off on the FirePass path and hardening the provider wrapper so hidden reasoning no longer leaks into visible replies. (#63607)
• ·Discord: update Carbon to v0.15.0.
• ·Config/Discord: coerce safe integer numeric Discord IDs to strings during config validation, keep unsafe or precision-losing numeric snowflakes rejected, and align `openclaw doctor` repair guidance with the same fail-closed behavior. (#45125)
• ·BlueBubbles/config: accept `enrichGroupParticipantsFromContacts` in the core strict config schema so gateways no longer fail validation or startup when the BlueBubbles plugin writes that field. (#56889)
• ·Feishu/webhooks: read webhook bodies through the pre-auth guard so unauthenticated webhook traffic stays under the same body budget as other protected channel ingress paths.
• ·Tools/web_fetch: add an opt-in `tools.web.fetch.ssrfPolicy.allowRfc2544BenchmarkRange` config so fake-IP proxy environments that resolve public sites into `198.18.0.0/15` can use `web_fetch` without weakening the default SSRF block. (#61830)
• ·Dreaming/cron: reconcile managed dreaming cron from startup config and runtime lifecycle changes, but only recover managed dreaming cron state during heartbeat-triggered dreaming checks so ordinary chat traffic does not recreate removed jobs. (#63873, #63929, #63938)
• ·Memory/lancedb: accept `dreaming` config when `memory-lancedb` owns the memory slot so Dreaming surfaces can read slot-owner settings without schema rejection. (#63874)
• ·Control UI/dreaming: keep the Dreaming trace area contained and scrollable so overlays no longer cover tabs or blow out the page layout. (#63875)
• ·Dreaming/narrative: harden request-scoped diary fallback so scheduled dreaming only falls back on the dedicated subagent-runtime error, stop trusting spoofable raw error-code objects, and avoid leaking workspace paths when local fallback writes fail. (#64156)
• ·Dreaming/diary: add idempotent narrative subagent runs, preserve restrictive `DREAMS.md` permissions during atomic writes, and surface temp cleanup failures so repeated sweeps do not double-run the same narrative request or silently weaken diary safety. (#63876)
• ·Heartbeats/sessions: remove stale accumulated isolated heartbeat session keys when the next tick converges them back to the canonical sibling, so repaired sessions stop showing orphaned `:heartbeat:heartbeat` variants in session listings. (#59606)
• ·Gateway/run cleanup: fix stale run-context TTL cleanup so the new maintenance sweep resets orphaned run sequence state and prevents unbounded run-context growth. (#52731)
• ·UI/compaction: keep the compaction indicator in a retry-pending state until the run actually finishes, so the UI does not show `Context compacted` before compaction actually finishes. (#55132)
• ·Cron/tool schemas: keep cron tool schemas strict-model-friendly while still preserving `failureAlert=false`, nullable `agentId`/`sessionKey`, and flattened add/update recovery for the newly exposed cron job fields. (#55043)
• ·Git metadata: read commit ids from packed refs as well as loose refs so version and status metadata stay accurate after repository maintenance. (#63943)
• ·Gateway: keep `commands.list` skill entries categorized under tools and include provider-aware plugin `nativeName` metadata even when `scope=text`, so remote clients can group skills correctly and map text-surface plugin commands back to native aliases. (#64147)
• ·TUI: reset footer activity to idle when switching sessions so a stale streaming indicator cannot persist after the selection changes. (#63988)
• ·Claude CLI: stop marking spawned Claude Code runs as host-managed so they keep using normal CLI subscription behavior. (#64023)
• ·Codex auth: brand Codex OAuth flows as OpenClaw in user-visible auth prompts and diagnostics.
• ·Gateway/pairing: fail closed for paired device records that have no device tokens, and reject pairing approvals whose requested scopes do not match the requested device roles.
• ·ACP/gateway chat: classify lifecycle errors before forwarding them to ACP clients so refusals use ACP's refusal stop reason while transient backend errors continue to finish as normal turns.
• ·Claude CLI/skills: pass eligible OpenClaw skills into CLI runs, including native Claude Code skill resolution via a temporary plugin plus per-run skill env/API key injection. (#62686, #62723)
• ·Discord: keep generated auto-thread names working with reasoning models by giving title generation enough output budget for thinking plus visible title text. (#64172)
• ·Heartbeat: ignore doc-only Markdown fence markers in the default `HEARTBEAT.md` template so comment-only heartbeat scaffolds skip API calls again. (#61690, #63434)
• ·Reply/skills: keep resolved skill and memory secret config stable through embedded reply runs so raw SecretRefs in secondary skill settings no longer crash replies when the gateway already has the live env. (#64249)
• ·Dreaming/startup: keep plugin-registered startup hooks alive across workspace hook reloads and include dreaming startup owners in the gateway startup plugin scope, so managed Dreaming cron registration comes back reliably after gateway boot. (#62327, #64258)
• ·Plugins: treat duplicate `registerService` calls from the same plugin id as idempotent so snapshot and activation loads no longer emit spurious `service already registered` diagnostics. (#62033, #64128)
• ·Discord/TTS: route auto voice replies through the native voice-note path so Discord receives Opus voice messages instead of regular audio attachments. (#64096)
• ·Config/plugins: use plugin-owned command alias metadata when `plugins.allow` contains runtime command names like `dreaming`, and point users at the owning plugin instead of stale plugin-not-found guidance. (#64191, #64242)
• ·Agents/Gemini: strip orphaned `required` entries from Gemini tool schemas so provider validation no longer rejects tools after schema cleanup or union flattening. (#64284)
• ·Assistant text: strip Qwen-style XML tool call payloads from visible replies so web and channel messages no longer show raw `<tool_call><function=...>` output. (#63999, #64214)
• ·Daemon/gateway: prevent systemd restart storms on configuration errors by exiting with `EX_CONFIG` and adding generated unit restart-prevention guards. (#63913)
• ·Agents/exec: prevent gateway crash ("Agent listener invoked outside active run") when a subagent exec tool produces stdout/stderr after the agent run has ended or been aborted. (#62821)
• ·Gateway/OpenAI compat: return real `usage` for non-stream `/v1/chat/completions` responses, emit the final usage chunk when `stream_options.include_usage=true`, and bound usage-gated stream finalization after lifecycle end. (#62986)
• ·Agents/subagents: deduplicate delivered completion announces so retry or re-entry cleanup does not inject duplicate internal-context completion turns into the parent session. (#61525)
• ·Agents/exec: keep sandboxed `tools.exec.host=auto` sessions from honoring per-call `host=node` or `host=gateway` overrides while a sandbox runtime is active, and stop advertising node routing in that state so exec stays on the sandbox host. (#63880)
• ·Agents/subagents: preserve archived delete-mode runs until `sessions.delete` succeeds and prevent overlapping archive sweeps from duplicating in-flight cleanup attempts. (#61801)
• ·Cron/isolated agent: run scheduled agent turns as non-owner senders so owner-only tools stay unavailable during cron execution. (#63878)
• ·Discord/sandbox: include `image` in sandbox media param normalization so Discord event cover images cannot bypass sandbox path rewriting. (#64377)
• ·Agents/exec: extend exec completion detection to cover local background exec formats so the owner-downgrade fires correctly for all exec paths. (#64376)
• ·Hooks/security: mark agent hook system events as untrusted and sanitize hook display names before cron metadata reuse. (#64372)
• ·Daemon/launchd: keep `openclaw gateway stop` persistent without uninstalling the macOS LaunchAgent, re-enable it on explicit restart or repair, and harden launchd label handling. (#64447)
• ·Plugins/context engines: preserve `plugins.slots.contextEngine` through normalization and keep explicitly selected workspace context-engine plugins enabled, so loader diagnostics and plugin activation stop dropping that slot selection. (#64192)
• ·Heartbeat: stop top-level `interval:` and `prompt:` fields outside the `tasks:` block from bleeding into the last parsed heartbeat task. (#64488)
• ·Agents/OpenAI replay: preserve malformed function-call arguments in stored assistant history, avoid double-encoding preserved raw strings on replay, and coerce replayed string args back to objects at Anthropic and Google provider boundaries. (#61956)
• ·Heartbeat/config: accept and honor `agents.defaults.heartbeat.timeoutSeconds` and per-agent heartbeat timeout overrides for heartbeat agent turns. (#64491)
• ·CLI/devices: make implicit `openclaw devices approve` selection preview-only and require approving the exact request ID, preventing latest-request races during device pairing. (#64160)
• ·Media/security: honor sender-scoped `toolsBySender` policy for outbound host-media reads so denied senders cannot trigger host file disclosure via attachment hydration. (#64459)
• ·Browser/security: reject strict-policy hostname navigation unless the hostname is an explicit allowlist exception or IP literal, and route CDP HTTP discovery through the pinned SSRF fetch path. (#64367)
• ·Models/vLLM: ignore empty `tool_calls` arrays from reasoning-model OpenAI-compatible replies, reset false `toolUse` stop reasons when no actual tool calls were parsed, and stop sending `tool_choice` unless tools are present so vLLM reasoning responses no longer hang indefinitely. (#61197, #61534)

Changes

• ·Memory/dreaming: add a grounded REM backfill lane with historical `rem-harness --path`, diary commit/reset flows, cleaner durable-fact extraction, and live short-term promotion integration so old daily notes can replay into Dreams and durable memory without a second memory stack.
• ·Control UI/dreaming: add a structured diary view with timeline navigation, backfill/reset controls, traceable dreaming summaries, and a grounded Scene lane with promotion hints plus a safe clear-grounded action for staged backfill signals. (#63395)
• ·QA/lab: add character-vibes evaluation reports with model selection and parallel runs so live QA can compare candidate behavior faster.
• ·Plugins/provider-auth: let provider manifests declare `providerAuthAliases` so provider variants can share env vars, auth profiles, config-backed auth, and API-key onboarding choices without core-specific wiring.
• ·iOS: pin release versioning to an explicit CalVer in `apps/ios/version.json`, keep TestFlight iteration on the same short version until maintainers intentionally promote the next gateway version, and add the documented `pnpm ios:version:pin -- --from-gateway` workflow for release trains. (#63001)

Fixes

• ·Browser/security: re-run blocked-destination safety checks after interaction-driven main-frame navigations from click, evaluate, hook-triggered click, and batched action flows, so browser interactions cannot bypass the SSRF quarantine when they land on forbidden URLs. (#63226)
• ·Security/dotenv: block runtime-control env vars plus browser-control override and skip-server env vars from untrusted workspace `.env` files, and reject unsafe URL-style browser control override specifiers before lazy loading. (#62660, #62663)
• ·Gateway/node exec events: mark remote node `exec.started`, `exec.finished`, and `exec.denied` summaries as untrusted system events and sanitize node-provided command/output/reason text before enqueueing them, so remote node output cannot inject trusted `System:` content into later turns. (#62659)
• ·Plugins/onboarding auth choices: prevent untrusted workspace plugins from colliding with bundled provider auth-choice ids during non-interactive onboarding, so bundled provider setup keeps operator secrets out of untrusted workspace plugin handlers unless those plugins are explicitly trusted. (#62368)
• ·Security/dependency audit: force `basic-ftp` to `5.2.1` for the CRLF command-injection fix and bump Hono plus `@hono/node-server` in production resolution paths.
• ·Android/pairing: clear stale setup-code auth on new QR scans, bootstrap operator and node sessions from fresh pairing, prefer stored device tokens after bootstrap handoff, and pause pairing auto-retry while the app is backgrounded so scan-once Android pairing recovers reliably again. (#63199)
• ·Matrix/gateway: wait for Matrix sync readiness before marking startup successful, keep Matrix background handler failures contained, and route fatal Matrix sync stops through channel-level restart handling instead of crashing the whole gateway. (#62779)
• ·Slack/media: preserve bearer auth across same-origin `files.slack.com` redirects while still stripping it on cross-origin Slack CDN hops, so `url_private_download` image attachments load again. (#62960)
• ·Reply/doctor: use the active runtime snapshot for queued reply runs, resolve reply-run SecretRefs before preflight helpers touch config, surface gateway OAuth reauth failures to users, and make `openclaw doctor` call out exact reauth commands. (#62693, #63217)
• ·Control UI: guard stale session-history reloads during fast session switches so the selected session and rendered transcript stay in sync. (#62975)
• ·Gateway/chat: suppress exact and streamed `ANNOUNCE_SKIP` / `REPLY_SKIP` control replies across live chat updates and history sanitization so internal agent-to-agent control tokens no longer leak into user-facing gateway chat surfaces. (#51739)
• ·Auto-reply/NO_REPLY: strip glued leading `NO_REPLY` tokens before reply normalization and ACP-visible streaming so silent sentinel text no longer leaks into user-visible replies while preserving substantive `NO_REPLY ...` text.
• ·Sessions/routing: preserve established external routes on inter-session announce traffic so `sessions_send` follow-ups do not steal delivery from Telegram, Discord, or other external channels. (#58013)
• ·Gateway/sessions: clear auto-fallback-pinned model overrides on `/reset` and `/new` while still preserving explicit user model selections, including legacy sessions created before override-source tracking existed. (#63155)
• ·Slack/ACP: treat Slack ACP block replies as visible delivered output so OpenClaw stops re-sending the final fallback text after Slack already rendered the reply. (#62858)
• ·Slack/partial streaming: key turn-local dedupe by dispatch kind and keep the final fallback reply path active when preview finalization fails so stale preview text cannot suppress the actual final answer. (#62859)
• ·Matrix/doctor: migrate legacy `channels.matrix.dm.policy: "trusted"` configs back to compatible DM policies during `openclaw doctor --fix`, preserving explicit `allowFrom` boundaries as `allowlist` and defaulting empty legacy configs to `pairing`. (#62942)
• ·npm packaging: mirror bundled channel runtime deps, stage Nostr runtime deps, derive required root mirrors from manifests and built chunks, and test packed release tarballs without repo `node_modules` so fresh installs fail fast on missing plugin deps instead of crashing at runtime. (#63065)
• ·QA/live auth: fail fast when live QA scenarios hit classified auth or runtime failure replies, including raw scenario wait paths, and sanitize missing-key guidance so gateway auth problems surface as actionable errors instead of timeouts. (#63333)
• ·Providers/OpenAI: default missing reasoning effort to `high` on OpenAI Responses, WebSocket, and compatible completions transports, while still honoring explicit per-run reasoning levels.
• ·Providers/Ollama: allow Ollama models using the native `api: "ollama"` path to optionally display thinking output when `/think` is set to a non-off level. (#62712)
• ·Codex CLI: pass OpenClaw's system prompt through Codex's `model_instructions_file` config override so fresh Codex CLI sessions receive the same prompt guidance as Claude CLI sessions.
• ·Auth/profiles: persist explicit auth-profile upserts directly and skip external CLI sync for local writes so profile changes are saved without stale external credential state.
• ·Agents/timeouts: make the LLM idle timeout inherit `agents.defaults.timeoutSeconds` when configured, disable the unconfigured idle watchdog for cron runs, and point idle-timeout errors at `agents.defaults.llm.idleTimeoutSeconds`.
• ·Agents/failover: classify Z.ai vendor code `1311` as billing and `1113` as auth, including long wrapped `1311` payloads, so these errors stop falling through to generic failover handling. (#49552)
• ·QQBot/media-tags: support HTML entity-encoded angle brackets (`&lt;`/`&gt;`), URL slashes in attributes, and self-closing media tags so upstream `<qqimg>` payloads are correctly parsed and normalized. (#60493)
• ·Memory/dreaming: harden grounded backfill inputs, diary writes, status payloads, and diary action classification by preserving source-day labels, rejecting missing or symlinked targets cleanly, normalizing diary headings in gateway backfills, and tightening claim splitting plus diary source metadata.
• ·Memory/dreaming: accept embedded heartbeat trigger tokens so light and REM dreaming still run when runtime wrappers include extra heartbeat text.
• ·Android/manual connect: allow blank port input only for TLS manual gateway endpoints so standard HTTPS Tailscale hosts default to `443` without silently changing cleartext manual connects. (#63134)
• ·Windows/update: add heap headroom to Windows `pnpm build` steps during dev updates so update preflight builds stop failing on low default Node memory.
• ·Plugin SDK: export the channel plugin base and web-search config contract through the public package so plugins can use them without private imports.
• ·Plugins/contracts: keep test-only helpers out of production contract barrels, load shared contract harnesses through bundled test surfaces, and harden guardrails so indirect re-exports and canonical `*.test.ts` files stay blocked. (#63311)
• ·Control UI/models: preserve provider-qualified refs for OpenRouter catalog models whose ids already contain slashes so picker selections submit allowlist-compatible model refs instead of dropping the `openrouter/` prefix. (#63416)
• ·Plugin SDK/command auth: split command status builders onto the lightweight `openclaw/plugin-sdk/command-status` subpath while preserving deprecated `command-auth` compatibility exports, so auth-only plugin imports no longer pull status/context warmup into CLI onboarding paths. (#63174)

Changes

• ·Memory/dreaming: add a grounded REM backfill lane with historical `rem-harness --path`, diary commit/reset flows, cleaner durable-fact extraction, and live short-term promotion integration so old daily notes can replay into Dreams and durable memory without a second memory stack.
• ·Control UI/dreaming: add a structured diary view with timeline navigation, backfill/reset controls, traceable dreaming summaries, and a grounded Scene lane with promotion hints plus a safe clear-grounded action for staged backfill signals. (#63395)
• ·QA/lab: add character-vibes evaluation reports with model selection and parallel runs so live QA can compare candidate behavior faster.
• ·Plugins/provider-auth: let provider manifests declare `providerAuthAliases` so provider variants can share env vars, auth profiles, config-backed auth, and API-key onboarding choices without core-specific wiring.
• ·iOS: pin release versioning to an explicit CalVer in `apps/ios/version.json`, keep TestFlight iteration on the same short version until maintainers intentionally promote the next gateway version, and add the documented `pnpm ios:version:pin -- --from-gateway` workflow for release trains. (#63001)

Fixes

• ·Browser/security: re-run blocked-destination safety checks after interaction-driven main-frame navigations from click, evaluate, hook-triggered click, and batched action flows, so browser interactions cannot bypass the SSRF quarantine when they land on forbidden URLs. (#63226)
• ·Security/dotenv: block runtime-control env vars plus browser-control override and skip-server env vars from untrusted workspace `.env` files, and reject unsafe URL-style browser control override specifiers before lazy loading. (#62660, #62663)
• ·Gateway/node exec events: mark remote node `exec.started`, `exec.finished`, and `exec.denied` summaries as untrusted system events and sanitize node-provided command/output/reason text before enqueueing them, so remote node output cannot inject trusted `System:` content into later turns. (#62659)
• ·Plugins/onboarding auth choices: prevent untrusted workspace plugins from colliding with bundled provider auth-choice ids during non-interactive onboarding, so bundled provider setup keeps operator secrets out of untrusted workspace plugin handlers unless those plugins are explicitly trusted. (#62368)
• ·Security/dependency audit: force `basic-ftp` to `5.2.1` for the CRLF command-injection fix and bump Hono plus `@hono/node-server` in production resolution paths.
• ·Android/pairing: clear stale setup-code auth on new QR scans, bootstrap operator and node sessions from fresh pairing, prefer stored device tokens after bootstrap handoff, and pause pairing auto-retry while the app is backgrounded so scan-once Android pairing recovers reliably again. (#63199)
• ·Matrix/gateway: wait for Matrix sync readiness before marking startup successful, keep Matrix background handler failures contained, and route fatal Matrix sync stops through channel-level restart handling instead of crashing the whole gateway. (#62779)
• ·Slack/media: preserve bearer auth across same-origin `files.slack.com` redirects while still stripping it on cross-origin Slack CDN hops, so `url_private_download` image attachments load again. (#62960)
• ·Reply/doctor: use the active runtime snapshot for queued reply runs, resolve reply-run SecretRefs before preflight helpers touch config, surface gateway OAuth reauth failures to users, and make `openclaw doctor` call out exact reauth commands. (#62693, #63217)
• ·Control UI: guard stale session-history reloads during fast session switches so the selected session and rendered transcript stay in sync. (#62975)
• ·Gateway/chat: suppress exact and streamed `ANNOUNCE_SKIP` / `REPLY_SKIP` control replies across live chat updates and history sanitization so internal agent-to-agent control tokens no longer leak into user-facing gateway chat surfaces. (#51739)
• ·Auto-reply/NO_REPLY: strip glued leading `NO_REPLY` tokens before reply normalization and ACP-visible streaming so silent sentinel text no longer leaks into user-visible replies while preserving substantive `NO_REPLY ...` text.
• ·Sessions/routing: preserve established external routes on inter-session announce traffic so `sessions_send` follow-ups do not steal delivery from Telegram, Discord, or other external channels. (#58013)
• ·Gateway/sessions: clear auto-fallback-pinned model overrides on `/reset` and `/new` while still preserving explicit user model selections, including legacy sessions created before override-source tracking existed. (#63155)
• ·Slack/ACP: treat Slack ACP block replies as visible delivered output so OpenClaw stops re-sending the final fallback text after Slack already rendered the reply. (#62858)
• ·Slack/partial streaming: key turn-local dedupe by dispatch kind and keep the final fallback reply path active when preview finalization fails so stale preview text cannot suppress the actual final answer. (#62859)
• ·Matrix/doctor: migrate legacy `channels.matrix.dm.policy: "trusted"` configs back to compatible DM policies during `openclaw doctor --fix`, preserving explicit `allowFrom` boundaries as `allowlist` and defaulting empty legacy configs to `pairing`. (#62942)
• ·npm packaging: mirror bundled channel runtime deps, stage Nostr runtime deps, derive required root mirrors from manifests and built chunks, and test packed release tarballs without repo `node_modules` so fresh installs fail fast on missing plugin deps instead of crashing at runtime. (#63065)
• ·QA/live auth: fail fast when live QA scenarios hit classified auth or runtime failure replies, including raw scenario wait paths, and sanitize missing-key guidance so gateway auth problems surface as actionable errors instead of timeouts. (#63333)
• ·Providers/OpenAI: default missing reasoning effort to `high` on OpenAI Responses, WebSocket, and compatible completions transports, while still honoring explicit per-run reasoning levels.
• ·Providers/Ollama: allow Ollama models using the native `api: "ollama"` path to optionally display thinking output when `/think` is set to a non-off level. (#62712)
• ·Codex CLI: pass OpenClaw's system prompt through Codex's `model_instructions_file` config override so fresh Codex CLI sessions receive the same prompt guidance as Claude CLI sessions.
• ·Auth/profiles: persist explicit auth-profile upserts directly and skip external CLI sync for local writes so profile changes are saved without stale external credential state.
• ·Agents/timeouts: make the LLM idle timeout inherit `agents.defaults.timeoutSeconds` when configured, disable the unconfigured idle watchdog for cron runs, and point idle-timeout errors at `agents.defaults.llm.idleTimeoutSeconds`.
• ·Agents/failover: classify Z.ai vendor code `1311` as billing and `1113` as auth, including long wrapped `1311` payloads, so these errors stop falling through to generic failover handling. (#49552)
• ·QQBot/media-tags: support HTML entity-encoded angle brackets (`&lt;`/`&gt;`), URL slashes in attributes, and self-closing media tags so upstream `<qqimg>` payloads are correctly parsed and normalized. (#60493)
• ·Memory/dreaming: harden grounded backfill inputs, diary writes, status payloads, and diary action classification by preserving source-day labels, rejecting missing or symlinked targets cleanly, normalizing diary headings in gateway backfills, and tightening claim splitting plus diary source metadata.
• ·Memory/dreaming: accept embedded heartbeat trigger tokens so light and REM dreaming still run when runtime wrappers include extra heartbeat text.
• ·Android/manual connect: allow blank port input only for TLS manual gateway endpoints so standard HTTPS Tailscale hosts default to `443` without silently changing cleartext manual connects. (#63134)
• ·Windows/update: add heap headroom to Windows `pnpm build` steps during dev updates so update preflight builds stop failing on low default Node memory.
• ·Plugin SDK: export the channel plugin base and web-search config contract through the public package so plugins can use them without private imports.
• ·Plugins/contracts: keep test-only helpers out of production contract barrels, load shared contract harnesses through bundled test surfaces, and harden guardrails so indirect re-exports and canonical `*.test.ts` files stay blocked. (#63311)
• ·Control UI/models: preserve provider-qualified refs for OpenRouter catalog models whose ids already contain slashes so picker selections submit allowlist-compatible model refs instead of dropping the `openrouter/` prefix. (#63416)
• ·Plugin SDK/command auth: split command status builders onto the lightweight `openclaw/plugin-sdk/command-status` subpath while preserving deprecated `command-auth` compatibility exports, so auth-only plugin imports no longer pull status/context warmup into CLI onboarding paths. (#63174)

Fixes

• ·Telegram/setup: load setup and secret contracts through packaged top-level sidecars so installed npm builds no longer try to import missing `dist/extensions/telegram/src/*` files during gateway startup.
• ·Bundled channels/setup: load shared secret contracts through packaged top-level sidecars across BlueBubbles, Feishu, Google Chat, IRC, Matrix, Mattermost, Microsoft Teams, Nextcloud Talk, Slack, and Zalo so installed npm builds no longer rely on missing `dist/extensions/*/src/*` files during gateway startup.
• ·Bundled plugins: align packaged plugin compatibility metadata with the release version so bundled channels and providers load on OpenClaw 2026.4.8.
• ·Agents/progress: keep `update_plan` available for OpenAI-family runs while returning compact success payloads and allowing `tools.experimental.planTool=false` to opt out.
• ·Agents/exec: keep `/exec` current-default reporting aligned with real runtime behavior so `host=auto` sessions surface the correct host-aware fallback policy (`full/off` on gateway or node, `deny/off` on sandbox) instead of stale stricter defaults.
• ·Slack: honor ambient HTTP(S) proxy settings for Socket Mode WebSocket connections, including NO_PROXY exclusions, so proxy-only deployments can connect without a monkey patch. (#62878)
• ·Slack/actions: pass the already resolved read token into `downloadFile` so SecretRef-backed bot tokens no longer fail after a raw config re-read. (#62097)
• ·Network/fetch guard: skip target DNS pinning when trusted env-proxy mode is active so proxy-only sandboxes can let the trusted proxy resolve outbound hosts. (#59007)

Changes

• ·CLI/infer: add a first-class `openclaw infer ...` hub for provider-backed inference workflows across model, media, web, and embedding tasks.
• ·Tools/media generation: auto-fallback across auth-backed image, music, and video providers by default, preserve intent during provider switches, remap size/aspect/resolution/duration hints to the closest supported option, and surface provider capabilities plus mode-aware video-to-video support.
• ·Memory/wiki: restore the bundled `memory-wiki` stack with plugin, CLI, sync/query/apply tooling, memory-host integration, structured claim/evidence fields, compiled digest retrieval, claim-health linting, contradiction clustering, staleness dashboards, and freshness-weighted search.
• ·Plugins/webhooks: add a bundled webhook ingress plugin so external automation can create and drive bound TaskFlows through per-route shared-secret endpoints. (#61892)
• ·Gateway/sessions: add persisted compaction checkpoints plus Sessions UI branch/restore actions so operators can inspect and recover pre-compaction session state. (#62146)
• ·Compaction: add pluggable compaction provider registry so plugins can replace the built-in summarization pipeline. Configure via `agents.defaults.compaction.provider`; falls back to LLM summarization on provider failure. (#56224)
• ·Agents/system prompt: add `agents.defaults.systemPromptOverride` for controlled prompt experiments plus heartbeat prompt-section controls so heartbeat runtime behavior can stay enabled without injecting heartbeat instructions every turn.
• ·Providers/Google: add Gemma 4 model support and keep Google fallback resolution on the requested provider path so native Google Gemma routes work again. (#61507)
• ·Providers/Google: preserve explicit thinking-off semantics for Gemma 4 while still enabling Gemma reasoning support in compatibility wrappers. (#62127)
• ·Providers/Arcee AI: add a bundled Arcee AI provider plugin with Trinity catalog entries, OpenRouter support, and updated onboarding/auth guidance. (#62068)
• ·Providers/Anthropic: restore Claude CLI as the preferred local Anthropic path in onboarding, model-auth guidance, doctor flows, and Docker Claude CLI live lanes again.
• ·Providers/Ollama: detect vision capability from the `/api/show` response and set image input on models that support it so Ollama vision models accept image attachments. (#62193)
• ·Memory/dreaming: ingest redacted session transcripts into the dreaming corpus with per-day session-corpus notes, cursor checkpointing, and promotion/doctor support. (#62227)
• ·Providers/inferrs: add string-content compatibility for stricter OpenAI-compatible chat backends, document `inferrs` setup with a full config example, and add troubleshooting guidance for local backends that pass direct probes but fail on full agent-runtime prompts.
• ·Agents/context engine: expose prompt-cache runtime context to context engines and keep current-turn prompt-cache usage aligned with the active attempt instead of stale prior-turn assistant state. (#62179)
• ·Plugin SDK/context engines: pass `availableTools` and `citationsMode` into `assemble()`, and expose memory-artifact and memory-prompt seams so companion plugins and non-legacy context engines can consume active memory state without reaching into internals.
• ·ACP/ACPX plugin: bump the bundled `acpx` pin to `0.5.1` so plugin-local installs and strict version checks pick up the latest published runtime release. (#62148)
• ·Discord/events: allow `event-create` to accept a cover image URL or local file path, load and validate PNG/JPG/GIF event cover media, and pass the encoded image payload through Discord admin action/runtime paths. (#60883)

Fixes

• ·CLI/infer: keep provider-backed infer behavior aligned with actual runtime execution by fixing explicit TTS override handling, profile-aware gateway TTS prefs resolution, per-request transcription `prompt`/`language` overrides, image output MIME/extension mismatches, configured web-search fallback behavior, and agent-vs-CLI web-search execution drift.
• ·Plugins/media: when `plugins.allow` is set, capability fallback now merges bundled capability plugin ids into the allowlist (not only `plugins.entries`), so media understanding providers such as OpenAI-compatible STT load for voice transcription without requiring `openai` in `plugins.allow`. (#62205)
• ·Agents/history and replies: buffer phaseless OpenAI WS text until a real assistant phase arrives, keep replay and SSE history sequence tracking aligned, hide commentary and leaked tool XML from user-visible history, and keep history-based follow-up replies on `final_answer` text only. (#61729, #61747, #61829, #61855, #61954)
• ·Control UI: show `/tts` audio replies in webchat, detect mistaken `?token=` auth links with the correct `#token=` hint, and keep Copy, Canvas, and mobile exec-approval UI from covering chat content on narrow screens. (#54842, #61514, #61598)
• ·iOS/gateway: replace string-matched connection error UI with structured gateway connection problems, preserve actionable pairing/auth failures over later generic disconnect noise, and surface reusable problem banners and details across onboarding, settings, and root status surfaces. (#62650)
• ·TUI: route `/status` through the shared session-status command, keep commentary hidden in history, strip raw envelope metadata from async command notices, preserve fallback streaming before per-attempt failures finalize, and restore Kitty keyboard state on exit or fatal crashes. (#49130, #59985, #60043, #61463)
• ·iOS/Watch exec approvals: keep Apple Watch review and approval recovery working while the iPhone is locked or backgrounded, including reconnect recovery, pending approval persistence, notification cleanup, and APNs-backed watch refresh recovery. (#61757)
• ·Agents/context overflow: combine oversized and aggregate tool-result recovery in one pass and restore a total-context overflow backstop so recoverable sessions retry instead of failing early. (#61651)
• ·Auth/OpenAI Codex OAuth: reload fresh on-disk credentials inside the locked refresh path and retry once after `refresh_token_reused` rotates only the stored refresh token, so relogin/restart recovery stops getting stuck on stale cached auth state.
• ·Auth/OpenAI Codex OAuth: keep native `/model ...@profile` selections on the target session and honor explicit user-locked auth profiles even when per-agent auth order excludes them. (#62744)
• ·Providers/Anthropic: preserve thinking blocks for Claude Opus 4.5+, Sonnet 4.5+, and newer Claude 4-family models so prompt-cache prefixes keep matching, and skip `service_tier` injection on OAuth-authenticated stream wrapper requests so Claude OAuth streaming stops failing with HTTP 401. (#60356, #61793)
• ·Agents/Claude CLI: surface nested API error messages from structured CLI output so billing/auth/provider failures show the real provider error instead of an opaque CLI failure.
• ·Agents/exec: preserve explicit `host=node` routing under elevated defaults when `tools.exec.host=auto`, fail loud on invalid elevated cross-host overrides, and keep `strictInlineEval` commands blocked after approval timeouts instead of falling through to automatic execution. (#61739)
• ·Nodes/exec approvals: keep `host=node` POSIX transport shell wrappers (`/bin/sh -lc ...`) aligned with inner-command allowlist analysis so allowlisted scripts stop prompting unnecessarily, while Windows `cmd.exe` wrapper runs stay approval-gated. (#62401)
• ·Nodes/exec approvals: keep Windows `cmd.exe /c` wrapper runs approval-gated even when `env` carriers, including env-assignment carriers, wrap the shell invocation. (#62439)
• ·Gateway tool/exec config: block model-facing `gateway config.apply` and `config.patch` writes from changing exec approval paths such as `safeBins`, `safeBinProfiles`, `safeBinTrustedDirs`, and `strictInlineEval`, while still allowing unchanged structured values through. (#62001)
• ·Host exec/env sanitization: block dangerous Java, Rust, Cargo, Git, Kubernetes, cloud credential, config-path, and Helm env overrides so host-run tools cannot be redirected to attacker-chosen code, config, credentials, or repository state. (#59119, #62002, #62291)
• ·Commands/allowlist: require owner authorization for `/allowlist add` and `/allowlist remove` before channel resolution, so non-owner but command-authorized senders can no longer persistently rewrite allowlist policy state. (#62383)
• ·Feishu/docx uploads: honor `tools.fs.workspaceOnly` for local `upload_file` and `upload_image` paths by forwarding workspace-constrained `localRoots` into the media loader, so docx uploads can no longer read host-local files outside the workspace when workspace-only mode is active. (#62369)
• ·Network/fetch guard: drop request bodies and body-describing headers on cross-origin `307` and `308` redirects by default, so attacker-controlled redirect hops cannot receive secret-bearing POST payloads from SSRF-guarded fetch flows unless a caller explicitly opts in. (#62357)
• ·Browser/SSRF: treat main-frame `document` redirect hops as navigations even when Playwright does not flag them as `isNavigationRequest()`, so strict private-network blocking still stops forbidden redirect pivots before the browser reaches the internal target. (#62355)
• ·Browser/node invoke: block persistent browser profile create, reset, and delete mutations through `browser.proxy` on both gateway-forwarded `node.invoke` and the node-host proxy path, even when no profile allowlist is configured. (#60489)
• ·Gateway/node pairing: require a fresh pairing request when a previously paired node reconnects with additional declared commands, and keep the live session pinned to the earlier approved command set until the upgrade is approved. (#62658)
• ·Gateway/auth: invalidate existing shared-token and password WebSocket sessions when the configured secret rotates, so stale authenticated sockets cannot stay attached after token or password changes. (#62350)
• ·MS Teams/security: validate file-consent upload URLs against HTTPS, Microsoft/SharePoint host allowlists, and private-IP DNS checks before uploading attachments, blocking SSRF-style consent-upload abuse. (#23596)
• ·Media/base64 decode guards: enforce byte limits before decoding missed base64-backed Teams, Signal, QQ Bot, and image-tool payloads so oversized inbound media and data URLs no longer bypass pre-decode size checks. (#62007)
• ·Runtime event trust: mark background `notifyOnExit` summaries, ACP parent-stream relays, and wake-hook payloads as untrusted system events so lower-trust runtime output no longer re-enters later turns as trusted `System:` text. (#62003)
• ·Auto-reply/media: allow managed generated-media `MEDIA:` paths from normal reply text again while still blocking arbitrary host-local media and document paths, so generated media keep delivering without reopening host-path injection holes.
• ·Gateway/status and containers: auto-bind to `0.0.0.0` inside Docker and Podman environments, and probe local TLS gateways over `wss://` with self-signed fingerprint forwarding so container startup and loopback TLS status checks work again. (#61818, #61935)
• ·Gateway/OpenAI-compatible HTTP: abort in-flight `/v1/chat/completions` and `/v1/responses` turns when clients disconnect so abandoned HTTP requests stop wasting agent runtime. (#54388)
• ·macOS/gateway version: strip trailing commit metadata from CLI version output before semver parsing so the Mac app recognizes installed gateway versions like `OpenClaw 2026.4.2 (d74a122)` again. (#61111)
• ·Sessions/model selection: resolve the explicitly selected session model separately from runtime fallback resolution so session status and live model switching stay aligned with the chosen model.
• ·Discord/ACP bindings: canonicalize DM conversation identity across inbound messages, component interactions, native commands, and current-conversation binding resolution so `--bind here` in Discord DMs keeps routing follow-up replies to the bound agent instead of falling back to the default agent.
• ·Discord: recover forwarded referenced message text and attachments when snapshots are missing, use `ws://` again for gateway monitor sockets, stop forcing a hardcoded temperature for Codex-backed auto-thread titles, and harden voice receive recovery so rapid speaker restarts keep their next utterance. (#41536, #61670)
• ·Slack/thread mentions: add `channels.slack.thread.requireExplicitMention` so Slack channels that already require mentions can also require explicit `@bot` mentions inside bot-participated threads. (#58276)
• ·Slack/threading: keep legacy thread stickiness for real replies when older callers omit `isThreadReply`, while still honoring `replyToMode` for Slack's auto-created top-level `thread_ts`. (#61835)
• ·Slack/media: keep attachment downloads on the SSRF-guarded dispatcher path so Slack media fetching works on Node 22 without dropping pinned transport enforcement. (#62239)
• ·Matrix/onboarding: add an invite auto-join setup step with explicit off warnings and strict stable-target validation so new Matrix accounts stop silently ignoring invited rooms and fresh DM-style invites unless operators opt in. (#62168)
• ·Matrix/formatting: preserve multi-paragraph and loose-list rendering in Element so numbered and bulleted Markdown keeps their content attached to the correct list item. (#60997)
• ·Telegram/doctor: keep top-level access-control fallback in place during multi-account normalization while still promoting legacy default auth into `accounts.default`, so existing named bots keep inherited allowlists without dropping the legacy default bot. (#62263)
• ·Plugins/loaders: centralize bundled `dist/**` Jiti native-load policy and keep channel, public-surface, facade, and config-metadata loader seams off native Jiti on Windows so onboarding and configure flows stop tripping `ERR_UNSUPPORTED_ESM_URL_SCHEME`. (#62286)
• ·Plugins/channels: keep bundled channel artifact and secret-contract loading stable under lazy loading, preserve plugin-schema defaults during install, and fix Windows `file://` plus native-Jiti plugin loader paths so onboarding, doctor, `openclaw secret`, and bundled plugin installs work again. (#61832, #61836, #61853, #61856)
• ·Plugins/ClawHub: verify downloaded plugin archives against version metadata SHA-256, fail closed when archive integrity metadata is missing or malformed, and tighten fallback ZIP verification so plugin installs cannot proceed on mismatched or incomplete ClawHub package metadata. (#60517)
• ·Plugins/provider hooks: stop recursive provider snapshot loads from overflowing the stack during plugin initialization, while still preserving cached nested provider-hook results. (#61922, #61938, #61946, #61951)
• ·Docker/plugins: stop forcing bundled plugin discovery to `/app/extensions` in runtime images so packaged installs use compiled `dist/extensions` artifacts again and Node 24 containers do not boot through source-only plugin entry paths. Fixes #62044. (#62316)
• ·Providers/Ollama: honor the selected provider's `baseUrl` during streaming so multi-Ollama setups stop routing every stream to the first configured Ollama endpoint. (#61678)
• ·Providers/Ollama: stop warning that Ollama could not be reached when discovery only sees empty default local stubs, while still keeping real explicit Ollama overrides loud when the endpoint is unreachable.
• ·Providers/xAI: recognize `api.grok.x.ai` as an xAI-native endpoint again and keep legacy `x_search` auth resolution working so older xAI web-search configs continue to load. (#61377)
• ·Providers/Mistral: send `reasoning_effort` for `mistral/mistral-small-latest` (Mistral Small 4) with thinking-level mapping, and mark the catalog entry as reasoning-capable so adjustable reasoning matches Mistral’s Chat Completions API. (#62162)
• ·OpenAI TTS/Groq: send `wav` to Groq-compatible speech endpoints, honor explicit `responseFormat` overrides on OpenAI-compatible paths, and only mark voice-note output as voice-compatible when the actual format is `opus`. (#62233)
• ·Tools/web_fetch and web_search: fix `TypeError: fetch failed` caused by undici 8.0 enabling HTTP/2 by default; pinned SSRF-guard dispatchers now explicitly set `allowH2: false` to restore HTTP/1.1 behavior and keep the custom DNS-pinning lookup compatible. (#61738, #61777)
• ·Tools/web search/Exa: show Exa Search in onboarding and configure provider pickers again by marking the bundled Exa provider as setup-visible.
• ·Memory/vector recall: surface explicit warnings when `sqlite-vec` is unavailable or vector writes are degraded, and strip managed Light Sleep and REM blocks before daily-note ingestion so memory indexing and dreaming stop reporting false-success or re-ingesting staged output. (#61720)
• ·Memory/dreaming: make Dreams config reads and writes respect the selected memory slot plugin instead of always targeting `memory-core`. (#62275)
• ·QQ Bot/media: route gateway-side attachment and fallback downloads through guarded QQ/Tencent HTTPS fetches so QQ media handling no longer follows arbitrary remote hosts.
• ·Browser/remote CDP: retry the DevTools websocket once after remote browser restarts so healthy remote browser profiles do not fail availability checks during CDP warm-up. (#57397)
• ·UI/light mode: target both root and nested WebKit scrollbar thumbs in the light theme so page-level and container scrollbars stay visible on light backgrounds. (#61753)
• ·Agents/subagents: honor `sessions_spawn(lightContext: true)` for spawned subagent runs by preserving lightweight bootstrap context through the gateway and embedded runner instead of silently falling back to full workspace bootstrap injection. (#62264)
• ·Cron: load `jobId` into `id` when the on-disk store omits `id`, matching doctor migration and fixing `unknown cron job id` for hand-edited `jobs.json`. (#62246)
• ·Agents/model fallback: classify minimal HTTP 404 API errors (for example `404 status code (no body)`) as `model_not_found` so assistant failures throw into the fallback chain instead of stopping at the first fallback candidate. (#62119)
• ·BlueBubbles/network: respect explicit private-network opt-out for loopback and private `serverUrl` values across account resolution, status probes, monitor startup, and attachment downloads, while keeping public-host attachment hostname pinning intact. (#59373)
• ·Agents/heartbeat: keep heartbeat runs pinned to the main session so active subagent transcripts are not overwritten by heartbeat status messages. (#61803)
• ·Agents/heartbeat: respect disabled heartbeat prompt guidance so operators can suppress heartbeat prompt instructions without disabling heartbeat runtime behavior.
• ·Agents/compaction: stop compaction-wait aborts from re-entering prompt failover and replaying completed tool turns. (#62600)
• ·Approvals/runtime: move native approval lifecycle assembly into shared core bootstrap/runtime seams driven by channel capabilities and runtime contexts, and remove the legacy bundled approval fallback wiring. (#62135)
• ·Security/fetch-guard: stop rejecting operator-configured proxy hostnames against the target-scoped hostname allowlist in SSRF-guarded fetches, restoring proxy-based media downloads for Telegram and other channels. (#62312)
• ·Logging: make `logging.level` and `logging.consoleLevel` honor the documented severity threshold ordering again, and keep child loggers inheriting the parent `minLevel`. (#44646)
• ·Agents/sessions_send: pass `threadId` through announce delivery so cross-session notifications land in the correct Telegram forum topic instead of the group's general thread. (#62758)
• ·Daemon/systemd: keep sudo systemctl calls scoped to the invoking user when machine-scoped systemctl fails, while still avoiding machine fallback for permission-denied user bus errors. (#62337)
• ·Docs/i18n: relocalize final localized-page links after translation and remove the zh-CN homepage redirect override so localized Mintlify pages resolve to the correct language roots again. (#61796)
• ·Agents/exec: keep timed-out shell-backgrounded commands on the failed path and point long-running jobs to exec background/yield sessions so process polling is only suggested for registered sessions.

Breaking

• ·Config: remove legacy public config aliases such as `talk.voiceId` / `talk.apiKey`, `agents.*.sandbox.perSession`, `browser.ssrfPolicy.allowPrivateNetwork`, `hooks.internal.handlers`, and channel/group/room `allow` toggles in favor of the canonical public paths and `enabled`, while keeping load-time compatibility and `openclaw doctor --fix` migration support for existing configs. (#60726)

Changes

• ·Agents/video generation: add the built-in `video_generate` tool so agents can create videos through configured providers and return the generated media directly in the reply.
• ·Agents/music generation: ignore unsupported optional hints such as `durationSeconds` with a warning instead of hard-failing requests on providers like Google Lyria.
• ·Providers/ComfyUI: add a bundled `comfy` workflow media plugin for local ComfyUI and Comfy Cloud workflows, including shared `image_generate`, `video_generate`, and workflow-backed `music_generate` support, with prompt injection, optional reference-image upload, live tests, and output download.
• ·Tools/music generation: add the built-in `music_generate` tool with bundled Google (Lyria) and MiniMax providers plus workflow-backed Comfy support, including async task tracking and follow-up delivery of finished audio.
• ·Providers: add bundled Qwen, Fireworks AI, and StepFun providers, plus MiniMax TTS, Ollama Web Search, and MiniMax Search integrations for chat, speech, and search workflows. (#60032, #55921, #59318, #54648)
• ·Providers/Amazon Bedrock: add bundled Mantle support plus inference-profile discovery and automatic request-region injection so Bedrock-hosted Claude, GPT-OSS, Qwen, Kimi, GLM, and similar routes work with less manual setup. (#61296, #61299)
• ·Control UI/multilingual: add localized control UI support for Simplified Chinese, Traditional Chinese, Brazilian Portuguese, German, Spanish, Japanese, Korean, French, Turkish, Indonesian, Polish, and Ukrainian.
• ·Plugins: add plugin-config TUI prompts to guided onboarding/setup flows, and add `openclaw plugins install --force` so existing plugin and hook-pack targets can be replaced without using the dangerous-code override flag. (#60590, #60544)
• ·Control UI/skills: add ClawHub search, detail, and install flows directly in the Skills panel. (#60134)
• ·iOS/exec approvals: add generic APNs approval notifications that open an in-app exec approval modal, fetch command details only after authenticated operator reconnect, and clear stale notification state when the approval resolves. (#60239)
• ·Matrix/exec approvals: add Matrix-native exec approval prompts with account-scoped approvers, channel-or-DM delivery, and room-thread aware resolution handling. (#58635)
• ·Channels/context visibility: add configurable `contextVisibility` per channel (`all`, `allowlist`, `allowlist_quote`) so supplemental quote, thread, and fetched history context can be filtered by sender allowlists instead of always passing through as received.
• ·Providers/request overrides: add shared model and media request transport overrides across OpenAI-, Anthropic-, Google-, and compatible provider paths, including headers, auth, proxy, and TLS controls. (#60200)
• ·Providers/OpenAI: add forward-compat `openai-codex/gpt-5.4-mini`, an opt-in GPT personality, and provider-owned GPT-5 prompt contributions so Codex/GPT runs stay cache-stable and compatible with bundled catalog lag.
• ·Agents/Claude CLI: expose OpenClaw tools to background Claude CLI runs through a loopback MCP bridge and switch bundled runs to stdin + `stream-json` partial-message streaming so prompts stop riding argv, long replies show live progress, and final session/usage metadata still land cleanly. (#35676)
• ·ACPX/runtime: embed the ACP runtime directly in the bundled `acpx` plugin, remove the extra external ACP CLI hop, harden live ACP session binding and reuse, and add a generic `reply_dispatch` hook so bundled plugins like ACPX can own reply interception without hardcoded ACP paths in core auto-reply routing. (#61319)
• ·Agents/progress: add experimental structured plan updates and structured execution item events so compatible UIs can show clearer step-by-step progress during long-running runs.
• ·Providers/Anthropic: remove the Claude CLI backend and setup-token from new onboarding, keep existing configured legacy profiles runnable, and have `openclaw doctor` repair or remove stale `anthropic:claude-cli` state during migration.
• ·Tools/video generation: add bundled xAI (`grok-imagine-video`), Alibaba Model Studio Wan, and Runway video providers, plus live-test/default model wiring for all three.
• ·Memory/search: add Amazon Bedrock embeddings for Titan, Cohere, Nova, and TwelveLabs models, with AWS credential-chain auto-detection for `provider: "auto"` and provider-specific dimension controls.
• ·Providers/Amazon Bedrock Mantle: generate bearer tokens from the AWS credential chain so Mantle auto-discovery can use IAM auth without manually exporting `AWS_BEARER_TOKEN_BEDROCK`.
• ·Memory/dreaming (experimental): add weighted short-term recall promotion, a `/dreaming` command, Dreams UI, multilingual conceptual tagging, and doctor/status repair support, while refactoring dreaming from competing modes into three cooperative phases (light, deep, REM) with independent schedules and recovery behavior so durable memory promotion can run in the background with less manual setup. (#60569, #60697)
• ·Memory/dreaming: add configurable aging controls (`recencyHalfLifeDays`, `maxAgeDays`) plus optional verbose logging so operators can tune recall decay and inspect promotion decisions more easily.
• ·Memory/dreaming: add REM preview tooling (`openclaw memory rem-harness`, `promote-explain`), surface possible lasting truths during REM staging, and make deep promotion replay-safe so reruns reconcile instead of duplicating `MEMORY.md` entries.
• ·Memory/dreaming: write dreaming trail content to top-level `dreams.md` instead of daily memory notes, update `/dreaming` help text to point there, and keep `dreams.md` available for explicit reads without pulling it into default recall.
• ·Memory/dreaming: add the Dream Diary surface in Dreams, simplify user-facing dreaming config to `enabled` plus optional `frequency`, treat phases as implementation detail in docs/UI, and keep the lobster animation visible above diary content.
• ·Prompt caching: keep prompt prefixes more reusable across transport fallback, deterministic MCP tool ordering, compaction, embedded image history, normalized system-prompt fingerprints, `openclaw status --verbose` cache diagnostics, and the removal of duplicate in-band tool inventories from agent system prompts so follow-up turns hit cache more reliably. (#58036, #58037, #58038, #59054, #60603, #60691)
• ·Agents/cache: diagnostics: add prompt-cache break diagnostics, trace live cache scenarios through embedded runner paths, and show cache reuse explicitly in `openclaw status --verbose`.
• ·Agents/cache: stabilize cache-relevant system prompt fingerprints by normalizing equivalent structured prompt whitespace, line endings, hook-added system context, and runtime capability ordering so semantically unchanged prompts reuse KV/cache more reliably.
• ·Agents/tool prompts: remove the duplicate in-band tool inventory from agent system prompts so tool-calling models rely on the structured tool definitions as the single source of truth, improving prompt stability and reducing stale tool guidance.
• ·Config/schema: enrich the exported `openclaw config schema` JSON Schema with field titles and descriptions so editors, agents, and other schema consumers receive the same config help metadata. (#60067)
• ·Providers/CLI: remove bundled CLI text-provider backends and the `agents.defaults.cliBackends` surface, while keeping ACP harness sessions and Gemini media understanding on the native bundled providers.
• ·Matrix/exec approvals: clarify unavailable-approval replies so Matrix no longer claims chat approvals are unsupported when native exec approvals are merely unconfigured. (#61424)
• ·Docs/IRC: replace public IRC hostname examples with `irc.example.com` and recommend private servers for bot coordination while listing common public networks for intentional use.
• ·Memory/dreaming: group nearby daily-note lines into short coherent chunks before staging them for dreaming, so one-off context from recent notes reaches REM/deep with better evidence and less line-level noise.
• ·Memory/dreaming: drop generic date/day headings from daily-note chunk prefixes while keeping meaningful section labels, so staged snippets stay cleaner and more reusable. (#61597)
• ·Plugins/Lobster: run bundled Lobster workflows in process instead of spawning the external CLI, reducing transport overhead and unblocking native runtime integration. (#61523)
• ·Plugins/Lobster: harden managed resume validation so invalid TaskFlow resume calls fail earlier, and memoize embedded runtime loading per runner while keeping failed loads retryable. (#61566)

Fixes

• ·Security: preserve restrictive plugin-only tool allowlists, require owner access for `/allowlist add` and `/allowlist remove`, fail closed when `before_tool_call` hooks crash, block browser SSRF redirect bypasses earlier, and keep non-interactive auth-choice inference scoped to bundled and already-trusted plugins. (#58476, #59836, #59822, #58771, #59120)
• ·Providers/OpenAI: make GPT-5 and Codex runs act sooner with lower-verbosity defaults, visible progress during tool work, and a one-shot retry when a turn only narrates the plan instead of taking action.
• ·Providers/OpenAI and reply delivery: preserve native `reasoning.effort: "none"` and strict schemas where supported, add GPT-5.4 assistant `phase` metadata across replay and the Gateway `/v1/responses` layer, and keep commentary buffered until `final_answer` so web chat, session previews, embedded replies, and Telegram partials stop leaking planning text. Fixes #59150, #59643, #61282.
• ·Telegram: fix current-model checks in the model picker, HTML-format non-default `/model` confirmations, explicit topic replies, persisted reaction ownership across restarts, caption-media placeholder and `file_id` preservation on download failure, and upgraded-install inbound image reads. (#60384, #60042, #59634, #59207, #59948, #59971)
• ·Telegram: restore DM voice-note preflight transcription so direct-message audio stops arriving as raw `<media:audio>` placeholders. (#61008)
• ·Telegram/reasoning: only create a Telegram reasoning preview lane when the session is explicitly `reasoning:stream`, so hidden `<think>` traces from streamed replies stop surfacing as chat previews on normal sessions.
• ·Telegram/native command menu: trim long menu descriptions before dropping commands so sub-100 command sets can still fit Telegram's payload budget and keep more `/` entries visible. (#61129)
• ·Discord: keep REST, webhook, and monitor traffic on the configured proxy, preserve component-only media sends, honor `@everyone` and `@here` mention gates, keep ACK reactions on the active account, and split voice connect/playback timeouts so auto-join is more reliable. (#57465, #60361, #60345)
• ·Discord/reply tags: strip leaked `[[reply_to_current]]` control tags from preview text and honor explicit reply-tag threading during final delivery, so Discord replies stay attached to the triggering message instead of printing reply metadata into chat.
• ·Discord/replies: replace the unshipped `replyToOnlyWhenBatched` flag with `replyToMode: "batched"` so native reply references only attach on debounced multi-message turns while explicit reply tags still work.
• ·Discord/image generation: include the real generated `MEDIA:` paths in tool output, avoid duplicate plain-output media requeueing, and persist volatile workspace-generated media into durable outbound media before final reply delivery so generated image replies stop pointing at missing local files.
• ·Slack: route live DM replies back to the concrete inbound DM channel while keeping persisted routing metadata user-scoped, so normal assistant replies stop disappearing when pairing and system messages still arrive. (#59030)
• ·WhatsApp: restore `channels.whatsapp.blockStreaming` and reset watchdog timeouts after reconnect so quiet chats stop falling into reconnect loops. (#60007, #60069)
• ·Android/Talk Mode: cancel in-flight `talk.speak` playback when speech is explicitly stopped, and restore spoken replies on both node-scoped and gateway-backed sessions by keeping reply routing and embedded transport overrides aligned with the current playback path. (#60306, #61164, #61214)
• ·Voice-call/OpenAI: pass full plugin config into realtime transcription provider resolution so streaming calls can discover the bundled OpenAI realtime transcription provider again. Fixes #60936.
• ·Matrix/exec approvals: anchor seeded approval reactions to the primary Matrix prompt event, resolve them from event metadata instead of prompt text, and clean up chunked approval prompts correctly. (#60931)
• ·Matrix: recover more reliably when secret storage or recovery keys are missing by recreating secret storage during repair and backup reset, hold crypto snapshot locks during persistence, and surface explicit too-large attachment markers. (#59846, #59851, #60599, #60289)
• ·Matrix/DM sessions: add `channels.matrix.dm.sessionScope`, shared-session collision notices, and aligned outbound session reuse so separate Matrix DM rooms can keep distinct context when configured. (#61373)
• ·Matrix: move legacy top-level `avatarUrl` into the default account during multi-account promotion and keep env-backed account setup avatar config persisted. (#61437)
• ·MS Teams: download inline DM images via Graph API and preserve channel reply threading in proactive fallback. (#52212, #55198)
• ·MS Teams: replace the deprecated Teams SDK HttpPlugin stub with `httpServerAdapter` so recurring gateway deprecation warnings stop firing and the Express 5 compatibility workaround stays on the supported SDK path. (#60939)
• ·Control UI/chat: add a per-session thinking-level picker in the chat header and mobile chat settings, and keep the browser bundle on UI-local thinking/session-key helpers so Safari no longer crashes on Node-only imports before rendering chat controls.
• ·Sandbox/SSH: reject hardlinked files during cross-device rename fallback so EXDEV file copies preserve the same pinned file-boundary checks as direct reads.
• ·Control UI: keep Stop visible during tool-only execution, preserve pending-send busy state, and clear stale ClawHub search results as soon as the query changes. (#54528, #59800, #60267)
• ·Control UI/avatar: honor `ui.assistant.avatar` when serving `/avatar/:agentId` so Appearance UI avatar paths stop falling back to initials placeholders. (#60778)
• ·Control UI/cron: highlight the Cron refresh button while refresh is in flight so the page's loading state stays visible even when prior data remains on screen. (#60394)
• ·Control UI/Overview: prevent gateway access token/password visibility toggle buttons from overlapping their inputs at narrow widths. (#56924)
• ·Auto-reply: unify reply lifecycle ownership across preflight compaction, session rotation, CLI-backed runs, and gateway restart handling so `/stop` and same-session overlap checks target the right active turn and restart-interrupted turns return the restart notice instead of being silently dropped. (#61267)
• ·Reply delivery: prevent duplicate block replies on `text_end` channels so providers that emit explicit text-end boundaries no longer double-send the same final message. (#61530)
• ·Gateway/startup: default `gateway.mode` to `local` when unset, detect PID recycling in gateway lock files on Windows and macOS, and show startup progress so healthy restarts stop getting blocked by stale locks. (#54801, #60085, #59843)
• ·Gateway/macOS: let launchd `KeepAlive` own in-process gateway restarts again, adding a short supervised-exit delay so rapid restarts avoid launchd crash-loop unloads while `openclaw gateway restart` still reports real LaunchAgent errors synchronously.
• ·Gateway/macOS: re-bootstrap the LaunchAgent if `launchctl kickstart -k` unloads it during restart so failed restarts do not leave the gateway unmanaged until manual repair.
• ·Gateway/macOS: recover installed-but-unloaded LaunchAgents during `openclaw gateway start` and `restart`, while still preferring live unmanaged gateways during restart recovery. (#43766)
• ·Gateway/Windows scheduled tasks: preserve Task Scheduler settings on reinstall, fail loudly when `/Run` does not start, and report fast failed restarts accurately instead of pretending they timed out after 60 seconds. (#59335)
• ·Windows/restart: fall back to the installed Startup-entry launcher when the scheduled task was never registered, so `/restart` can relaunch the gateway on Windows setups where `schtasks` install fell back during onboarding. (#58943)
• ·Windows/restart: clean up stale gateway listeners before Windows self-restart and treat listener and argv probe failures as inconclusive, so scheduled-task relaunch no longer falls into an `EADDRINUSE` retry loop. (#60480)
• ·Update/npm: prefer the npm binary that owns the installed global OpenClaw prefix so mixed Homebrew-plus-nvm setups update the right install. (#60153)
• ·Agents/music and video generation: add `tools.media.asyncCompletion.directSend` as an opt-in direct-delivery path for finished async media tasks, while keeping the legacy requester-session wake/model-delivery flow as the default.
• ·CLI/skills JSON: route `skills list --json`, `skills info --json`, and `skills check --json` output to stdout instead of stderr so machine-readable consumers receive JSON on the expected stream again. (#60914; fixes #57599; landed from contributor PR #57611 by @Aftabbs)
• ·CLI/Commander: preserve Commander-computed exit codes for argument and help-error paths, and cover the user-argv parse mode in the regression tests so invalid CLI invocations no longer report success when exits are intercepted. (#60923)
• ·Cron: replay interrupted recurring jobs on the first gateway restart instead of waiting for a second restart. (#60583)
• ·Cron: send failure notifications through the job's primary delivery channel using the same session context as successful delivery when no explicit `failureDestination` is configured. (#60622)
• ·Exec/remote skills: stop advertising `exec host=node` when the current exec policy cannot route to a node, and clarify blocked exec-host override errors with both the requested host and allowed config path.
• ·Agents/Claude CLI/security: clear inherited Claude Code config-root and plugin-root env overrides like `CLAUDE_CONFIG_DIR` and `CLAUDE_CODE_PLUGIN_*`, so OpenClaw-launched Claude CLI runs cannot be silently pointed at an alternate Claude config/plugin tree with different hooks, plugins, or auth context.
• ·Agents/Claude CLI/security: clear inherited Claude Code provider-routing and managed-auth env overrides, and mark OpenClaw-launched Claude CLI runs as host-managed, so Claude CLI backdoor sessions cannot be silently redirected to proxy, Bedrock, Vertex, Foundry, or parent-managed token contexts.
• ·Agents/Claude CLI/security: force host-managed Claude CLI backdoor runs to `--setting-sources user`, even under custom backend arg overrides, so repo-local `.claude` project/local settings, hooks, and plugin discovery do not silently execute inside non-interactive OpenClaw sessions.
• ·Agents/Claude CLI: treat malformed bare `--permission-mode` backend overrides as missing and fail safe back to `bypassPermissions`, so custom `cliBackends.claude-cli.args` security config cannot accidentally consume the next flag as a bogus permission mode.
• ·Gateway/device pairing: require non-admin paired-device sessions to manage only their own device for token rotate/revoke and paired-device removal, blocking cross-device token theft inside pairing-scoped sessions. (#50627)
• ·Gateway/plugin routes: keep gateway-auth plugin runtime routes on write-only fallback scopes unless a trusted-proxy caller explicitly declares narrower `x-openclaw-scopes`, so plugin HTTP handlers no longer mint admin-level runtime scopes on missing or untrusted HTTP scope headers. (#59815)
• ·Build/types: fix the Node `createRequire(...)` helper typing so provider-runtime lazy loads compile cleanly again and `pnpm build` no longer fails in the Pi embedded provider error-pattern path.
• ·Gateway/security: scope loopback browser-origin auth throttling by normalized origin so one localhost Control UI tab cannot lock out a different localhost browser origin after repeated auth failures.
• ·Gateway/auth: serialize async shared-secret auth attempts per client so concurrent Tailscale-capable failures cannot overrun the intended auth rate-limit budget.
• ·Device pairing/security: keep non-operator device scope checks bound to the requested role prefix so bootstrap verification cannot redeem `operator.*` scopes through `node` auth. (#57258)
• ·Device pairing: reject rotating device tokens into roles that were never approved during pairing, and keep reconnect role checks bounded to the paired device's approved role set. (#60462)
• ·Gateway/device auth: reuse cached device-token scopes only for cached-token reconnects, while keeping explicit `deviceToken` scope requests and empty-cache fallbacks intact so reconnects preserve `operator.read` without breaking explicit auth flows. (#46032)
• ·Mobile pairing/security: fail closed for internal `/pair` setup-code issuance, cleanup, and approval paths when gateway pairing scopes are missing, and keep approval-time requested-scope enforcement on the internal command path. (#55996)
• ·Mobile pairing/bootstrap: keep QR bootstrap handoff tokens bounded to the mobile-safe contract so node handoff stays unscoped and operator handoff drops mixed `node.*`, `operator.admin`, and `operator.pairing` scopes.
• ·Mobile pairing/Android: tighten secure endpoint handling so Tailscale and public remote setup reject cleartext endpoints, private LAN pairing still works, merged-role approvals mint both node and operator device tokens, and bootstrap tokens survive node auto-pair until operator approval finishes. (#60128, #60208, #60221)
• ·Android/canvas security: require exact normalized A2UI URL matches before forwarding canvas bridge actions, rejecting query mismatches and descendant paths while still allowing fragment-only A2UI navigation.
• ·Synology Chat/security: default low-level HTTPS helper TLS verification to on so helper/API defaults match the shipped safe account default, and only explicit `allowInsecureSsl: true` opts out.
• ·Synology Chat/security: route webhook token comparison through the shared constant-time secret helper for consistency with other bundled plugins.
• ·Plugins/marketplace: block remote marketplace symlink escapes without breaking ordinary local marketplace install paths. (#60556)
• ·Telegram/local Bot API: honor `channels.telegram.apiRoot` for buffered media downloads, add `channels.telegram.network.dangerouslyAllowPrivateNetwork` for trusted fake-IP setups, and require `channels.telegram.trustedLocalFileRoots` before reading absolute Bot API `file_path` values. (#59544, #60705)
• ·Outbound/sanitizer: strip leaked `<tool_call>`, `<function_calls>`, and model special tokens from shared user-visible assistant text, including truncated tool-call streams, so internal scaffolding no longer bleeds into replies across surfaces. (#60619)
• ·Agents/errors: surface an explicit disk-full message when local session or transcript writes fail with `ENOSPC`/`disk full`, so those runs stop degrading into opaque `NO_REPLY`-style failures.
• ·Exec approvals: remove heuristic command-obfuscation gating from host exec so gateway and node runs rely on explicit policy, allowlist, and strict inline-eval rules only.
• ·Agents/tool results: cap live tool-result persistence and overflow-recovery truncation at 40k characters so oversized tool output stays bounded without discarding recent context entirely.
• ·Discord/video replies: split text-plus-video deliveries into a text reply followed by a media-only send, and let live provider auth checks honor manifest-declared API key env vars like `MODELSTUDIO_API_KEY`.
• ·Config/All Settings: keep the raw config view intact when sensitive fields are blank instead of corrupting or dropping the rendered snapshot. (#28214)
• ·Plugin SDK/facades: back-fill bundled plugin facade sentinels before plugin-id tracking re-enters config loading, so CLI/provider startup no longer crashes with `shouldNormalizeGoogleProviderConfig is not a function` or other empty-facade reads during bundled plugin re-entry.
• ·Plugins/facades: back-fill facade sentinels before tracked-plugin resolution re-enters config loading, so facade exports stay defined during circular provider normalization. (#61180)
• ·QA lab: restore typed mock OpenAI gateway config wiring so QA-lab config helpers compile cleanly again and `pnpm check` / `pnpm build` stay green.
• ·Discord/image generation: include the real generated `MEDIA:` paths in tool output and avoid duplicate plain-output media requeueing so Discord image replies stop pointing at missing local files.
• ·Slack: route live DM replies back to the concrete inbound DM channel while keeping persisted routing metadata user-scoped, so normal assistant replies stop disappearing when pairing and system messages still arrive. (#59030)
• ·Discord/reply tags: strip leaked `[[reply_to_current]]` control tags from preview text and honor explicit reply-tag threading during final delivery, so Discord replies stay attached to the triggering message instead of printing reply metadata into chat.
• ·Telegram: fix current-model checks in the model picker, HTML-format non-default `/model` confirmations, explicit topic replies, persisted reaction ownership across restarts, caption-media placeholder and `file_id` preservation on download failure, and upgraded-install inbound image reads. (#60384, #60042, #59634, #59207, #59948, #59971)
• ·Telegram: restore DM voice-note preflight transcription so direct-message audio stops arriving as raw `<media:audio>` placeholders. (#61008)
• ·Telegram/reasoning: only create a Telegram reasoning preview lane when the session is explicitly `reasoning:stream`, so hidden `<think>` traces from streamed replies stop surfacing as chat previews on normal sessions.
• ·Telegram/native command menu: trim long menu descriptions before dropping commands so sub-100 command sets can still fit Telegram's payload budget and keep more `/` entries visible. (#61129)
• ·Feishu/reasoning: only expose streamed reasoning previews when the session is explicitly `reasoning:stream`, so hidden reasoning traces do not surface on normal streaming sessions.
• ·Discord: keep REST, webhook, and monitor traffic on the configured proxy, preserve component-only media sends, honor `@everyone` and `@here` mention gates, keep ACK reactions on the active account, and split voice connect/playback timeouts so auto-join is more reliable. (#57465, #60361, #60345)
• ·WhatsApp: restore `channels.whatsapp.blockStreaming` and reset watchdog timeouts after reconnect so quiet chats stop falling into reconnect loops. (#60007, #60069)
• ·Memory: keep `memory-core` builtin embedding registration on the already-registered path so selecting `memory-core` no longer recurses through plugin discovery and crashes during startup. (#61402)
• ·Agents/tool results: keep large `read` outputs visible longer, preserve the latest `read` output when older tool output can absorb the overflow budget, and fall back to Pi's normal overflow compaction/retry path before replacing a fresh `read` with a compacted stub.
• ·Memory/QMD: prefer modern `qmd collection add --glob`, accept newer single-line JSON hit metadata while keeping legacy line fields, refresh QMD docs/doctor install guidance and model-override guidance, and keep older QMD releases working.
• ·MS Teams: download inline DM images via Graph API and preserve channel reply threading in proactive fallback. (#52212, #55198)
• ·MS Teams: replace the deprecated Teams SDK HttpPlugin stub with `httpServerAdapter` so recurring gateway deprecation warnings stop firing and the Express 5 compatibility workaround stays on the supported SDK path. (#60939)
• ·Matrix/exec approvals: anchor seeded approval reactions to the primary Matrix prompt event, resolve them from event metadata instead of prompt text, and clean up chunked approval prompts correctly. (#60931)
• ·Matrix: recover more reliably when secret storage or recovery keys are missing by recreating secret storage during repair and backup reset, hold crypto snapshot locks during persistence, and surface explicit too-large attachment markers. (#59846, #59851, #60599, #60289)
• ·Android/Talk Mode: cancel in-flight `talk.speak` playback when speech is explicitly stopped, so stale replies stop starting after barge-in or manual stop. (#61164)
• ·Android/Talk Mode: restore spoken assistant replies on node-scoped sessions by keeping reply routing synced to the resolved node session key and pausing mic capture during reply playback. (#60306)
• ·Android/Talk Mode: restore voice replies on gateway-backed talk mode sessions by updating embedded runner transport overrides to the current agent transport API. (#61214)
• ·Voice-call/OpenAI: pass full plugin config into realtime transcription provider resolution so streaming calls can discover the bundled OpenAI realtime transcription provider again. Fixes #60936.
• ·Control UI/chat: add a per-session thinking-level picker in the chat header and mobile chat settings, and keep the browser bundle on UI-local thinking/session-key helpers so Safari no longer crashes on Node-only imports before rendering chat controls.
• ·Control UI: keep Stop visible during tool-only execution, preserve pending-send busy state, and clear stale ClawHub search results as soon as the query changes. (#54528, #59800, #60267)
• ·Control UI/avatar: honor `ui.assistant.avatar` when serving `/avatar/:agentId` so Appearance UI avatar paths stop falling back to initials placeholders. (#60778)
• ·Control UI/cron: highlight the Cron refresh button while refresh is in flight so the page's loading state stays visible even when prior data remains on screen. (#60394)
• ·Control UI/Overview: prevent gateway access token/password visibility toggle buttons from overlapping their inputs at narrow widths. (#56924)
• ·CLI/skills JSON: route `skills list --json`, `skills info --json`, and `skills check --json` output to stdout instead of stderr so machine-readable consumers receive JSON on the expected stream again. (#60914; fixes #57599; landed from contributor PR #57611 by @Aftabbs)
• ·CLI/Commander: preserve Commander-computed exit codes for argument and help-error paths, and cover the user-argv parse mode in the regression tests so invalid CLI invocations no longer report success when exits are intercepted. (#60923)
• ·Cron: replay interrupted recurring jobs on the first gateway restart instead of waiting for a second restart. (#60583)
• ·Cron: send failure notifications through the job's primary delivery channel using the same session context as successful delivery when no explicit `failureDestination` is configured. (#60622)
• ·Live model switching: only treat explicit user-driven model changes as pending live switches, so fallback rotation, heartbeat overrides, and compaction no longer trip `LiveSessionModelSwitchError` before making an API call. (#60266)
• ·Exec approvals: reuse durable exact-command `allow-always` approvals in allowlist mode so identical reruns stop prompting, and tighten Windows interpreter/path approval handling so wrapper and malformed-path cases fail closed more consistently. (#59880, #59780, #58040, #59182)
• ·Node exec approvals: keep node-host `system.run` approvals bound to the prepared execution plan across async forwarding, so mutable script operands still get approval-time binding and drift revalidation instead of dropping back to unbound execution.
• ·Agents/exec approvals: let `exec-approvals.json` agent security override stricter gateway tool defaults so approved subagents can use `security: “full”` without falling back to allowlist enforcement again. (#60310)
• ·Agents/exec: restore `host=node` routing for node-pinned and `host=auto` sessions, while still blocking sandboxed `auto` sessions from jumping to gateway. (#60788)
• ·Exec/heartbeat: use the canonical `exec-event` wake reason for `notifyOnExit` so background exec completions still trigger follow-up turns when `HEARTBEAT.md` is empty or comments-only. (#41479)
• ·Heartbeat: skip wake delivery when the target session lane is already busy so the pending event is retried instead of getting drained too early. (#40526)
• ·Group chats/agent prompts: tell models to minimize empty lines and use normal chat-style spacing so group replies avoid document-style blank-line formatting.
• ·Providers/OpenAI GPT: treat short approval turns like `ok do it` and `go ahead` as immediate action turns, and trim overly memo-like GPT-5 chat confirmations so OpenAI replies stay shorter and more conversational by default.
• ·Providers/OpenAI Codex: split native `contextWindow` from runtime `contextTokens`, keep the default effective cap at `272000`, and expose a per-model `contextTokens` override on `models.providers.*.models[]`.
• ·Providers/OpenAI-compatible WS: compute fallback token totals from normalized usage when providers omit or zero `total_tokens`, so DashScope-compatible sessions stop storing zero totals after alias normalization. (#54940)
• ·Agents/OpenAI: mark Claude-compatible file tool schemas as `additionalProperties: false` so direct OpenAI GPT-5 routes stop rejecting the `read` tool with invalid strict-schema errors.
• ·Agents/OpenAI: fall back to `strict: false` for native OpenAI tool calls when a tool schema is not strict-compatible, and normalize empty-object tool schemas to include `required: []`, so direct GPT-5 routes stop failing with invalid strict-schema errors like missing `path` in `required`.
• ·Agents/GPT: add explicit work-item lifecycle events for embedded runs, use them to surface real progress more reliably, and stop counting tool-started turns as planning-only retries.
• ·Plugins/OpenAI: enable `gpt-image-1` reference-image edits through `/images/edits` multipart uploads, and stop inferring unsupported resolution overrides when no explicit `size` or `resolution` is provided.
• ·Agents/replay: remove the malformed assistant-content canonicalization repair from replay history sanitization instead of extending that legacy repair path into replay validation.
• ·Plugins/OpenAI: tune the OpenAI prompt overlay for live-chat cadence so GPT replies stay shorter, more human, and less wall-of-text by default.
• ·Providers/compat: stop forcing OpenAI-only defaults on proxy and custom OpenAI-compatible routes, preserve native vendor-specific reasoning/tool/streaming behavior across Anthropic-compatible, Moonshot, Mistral, ModelStudio, OpenRouter, xAI, and Z.ai endpoints, and route GitHub Copilot Claude models through Anthropic Messages instead of OpenAI Responses.
• ·Providers/GitHub Copilot: send IDE identity headers on runtime model requests and GitHub token exchange so IDE-authenticated Copilot runs stop failing with missing `Editor-Version`. (#60641)
• ·Providers/OpenRouter failover: classify `403 “Key limit exceeded”` spending-limit responses as billing so model fallback continues instead of stopping on generic auth. (#59892)
• ·Providers/Anthropic: keep `claude-cli/*` auth on live Claude CLI credentials at runtime, avoid persisting stale bearer-token profiles, and suppress macOS Keychain prompts during non-interactive Claude CLI setup. (#61234)
• ·Providers/Anthropic: when Claude CLI auth becomes the default, write a real `claude-cli` auth profile so local and gateway agent runs can use Claude CLI immediately without missing-API-key failures.
• ·Providers/Anthropic Vertex: honor `cacheRetention: “long”` with the real 1-hour prompt-cache TTL on Vertex AI endpoints, and default `anthropic-vertex` cache retention like direct Anthropic. (#60888)
• ·Agents/Anthropic: preserve native `toolu_*` replay ids on direct Anthropic and Anthropic Vertex paths so cache-sensitive history stops rewriting known-valid Anthropic tool-use ids. (#52612)
• ·Providers/Google: add model-level `cacheRetention` support for direct Gemini system prompts by creating, reusing, and refreshing `cachedContents` automatically on Google AI Studio runs. (#51372)
• ·Google Gemini CLI auth: detect bundled npm installs by scanning packaged bundle files for the Gemini OAuth client config, so `npm install -g @google/gemini-cli` layouts work again. (#60486)
• ·Google Gemini CLI auth: detect personal OAuth mode from local Gemini settings and skip Code Assist project discovery for those logins, so personal Google accounts stop failing with `loadCodeAssist 400 Bad Request`. (#49226)
• ·Google Gemini CLI auth: improve OAuth credential discovery across Windows nvm and Homebrew libexec installs, and align Code Assist metadata so Gemini login stops failing on packaged CLI layouts. (#40729)
• ·Google Gemini CLI models: add forward-compat support for stable `gemini-2.5-*` model ids by letting the bundled CLI provider clone them from Google templates, so `gemini-2.5-flash-lite` and related configured models stop showing up as missing. (#35274)
• ·Google image generation: disable pinned DNS for Gemini image requests and honor explicit `pinDns` overrides in shared provider HTTP helpers so proxy-backed image generation works again. (#59873)
• ·Providers/Microsoft Foundry: preserve explicit image capability on normalized Foundry deployments, repair stale GPT/o-series text-only model metadata across gateway and runtime paths, and keep unknown fallback models from borrowing unrelated image support.
• ·Providers/Model Studio: preserve native streaming usage reporting for DashScope-compatible endpoints even when they are configured under a generic provider key, so streamed token totals stop sticking at zero. (#52395)
• ·Providers/Z.AI: preserve explicitly registered `glm-5-*` variants like `glm-5-turbo` instead of intercepting them with the generic GLM-5 forward-compat shim. (#48185)
• ·Amazon Bedrock/aws-sdk auth: stop injecting the fake `AWS_PROFILE` apiKey marker when no AWS auth env vars exist, so instance-role and other default-chain setups keep working without poisoning provider config. (#61194)
• ·Agents/Kimi tool-call repair: preserve tool arguments that were already present on streamed tool calls when later malformed deltas fail reevaluation, while still dropping stale repair-only state before `toolcall_end`.
• ·Plugins/Kimi Coding: parse tagged tool calls and keep Anthropic-native tool payloads so Kimi coding endpoints execute tools instead of echoing raw markup. (#60051, #60391)
• ·Media understanding: auto-register image-capable config providers for vision routing, so custom GLM-style provider ids with image models stop failing with “no media-understanding provider registered”. (#51418)
• ·Plugins/media understanding: enable bundled Groq and Deepgram providers by default so configured transcription models work without extra plugin activation config. (#59982)
• ·MiniMax/pricing: keep bundled MiniMax highspeed pricing distinct in provider catalogs and preserve the lower M2.5 cache-read pricing when onboarding older MiniMax models. (#54214)
• ·MiniMax: advertise image input on bundled `MiniMax-M2.7` and `MiniMax-M2.7-highspeed` model definitions so image-capable flows can route through the M2.7 family correctly. (#54843)
• ·Models/MiniMax: honor `MINIMAX_API_HOST` for implicit bundled MiniMax provider catalogs so China-hosted API-key setups pick `api.minimaxi.com/anthropic` without manual provider config. (#34524)
• ·Usage/MiniMax: invert remaining-style `usage_percent` fields when MiniMax reports only remaining percentage data, so usage bars stop showing nearly-full remaining quota as nearly-exhausted usage. (#60254)
• ·Usage/MiniMax: let usage snapshots treat `minimax-portal` and MiniMax CN aliases as the same MiniMax quota surface, and prefer stored MiniMax OAuth before falling back to Coding Plan keys.
• ·Usage/MiniMax: prefer the chat-model `model_remains` entry and derive Coding Plan window labels from MiniMax interval timestamps so MiniMax usage snapshots stop picking zero-budget media rows and misreporting 4h windows as `5h`. (#52349)
• ·Model picker/providers: treat bundled BytePlus and Volcengine plan aliases as their native providers during setup, and expose their bundled standard/coding catalogs before auth so setup can suggest the right models. (#58819)
• ·Tools/web_search (Kimi): when `tools.web.search.kimi.baseUrl` is unset, inherit native Moonshot chat `baseUrl` (`.ai` / `.cn`) so China console keys authenticate on the same host as chat. Fixes #44851. (#56769)
• ·Agents/Claude CLI: keep non-interactive `--permission-mode bypassPermissions` when custom `cliBackends.claude-cli.args` override defaults, including fallback resolution before the runtime plugin registry is active, so cron and heartbeat Claude CLI runs do not regress to interactive approval mode. (#61114)
• ·Agents/Claude CLI: persist explicit `openclaw agent --session-id` runs under a stable session key so follow-ups can reuse the stored CLI binding and resume the same underlying Claude session.
• ·Agents/Claude CLI: persist routed Claude session bindings, rotate them on `/new` and `/reset`, and keep live Claude CLI model switches moving across the configured Claude family so resumed sessions follow the real active thread and model.
• ·Agents/CLI backends: invalidate stored CLI session reuse when local CLI login state or the selected auth profile credential changes, so relogin and token rotation stop resuming stale sessions.
• ·Agents/Claude CLI/images: reuse stable hydrated image file paths and preserve shared media extensions like HEIC when passing image refs to local CLI runs, so Claude CLI image prompts stop thrashing KV cache prefixes and oddball image formats do not fall back to `.bin`.
• ·Agents/compaction: keep assistant tool calls and displaced tool results in the same compaction chunk so strict summarization providers stop rejecting orphaned tool pairs. (#58849)
• ·Agents/failover: scope Anthropic `An unknown error occurred` failover matching by provider so generic internal unknown-error text no longer triggers retryable timeout fallback. (#59325)
• ·Agents/subagents: honor allowlist validation, auth-profile handoff, and session override state when a subagent retries after `LiveSessionModelSwitchError`. (#58178)
• ·Agents/runtime: make default subagent allowlists, inherited skills/workspaces, and duplicate session-id resolution behave more predictably, and include value-shape hints in missing-parameter tool errors. (#59944, #59992, #59858, #55317)
• ·Agents/pairing: merge completion announce delivery context with the requester session fallback so missing `to` still reaches the original channel, and include `operator.talk.secrets` in CLI default operator scopes for node-role device pairing approvals. (#56481)
• ·Agents/scheduling: steer background-now work toward automatic completion wake and treat `process` polling as on-demand inspection or intervention instead of default completion handling. (#60877)
• ·Agents/skills: skip `.git` and `node_modules` when mirroring skills into sandbox workspaces so read-only sandboxes do not copy repo history or dependency trees. (#61090)
• ·ACP/agents: inherit the target agent workspace for cross-agent ACP spawns and fall back safely when the inherited workspace no longer exists. (#58438)
• ·ACPX/Windows: preserve backslashes and absolute `.exe` paths in Claude CLI parsing, and fail fast on wrapper-script targets with guidance to use `cmd.exe /c`, `powershell.exe -File`, or `node <script>`. (#60689)
• ·Auth/failover: persist selected fallback overrides before retrying, shorten `auth_permanent` lockouts, and refresh websocket/shared-auth sessions only when real auth changes occur so retries and secret rotations behave predictably. (#60404, #60323, #60387)
• ·Gateway/channels: pin the initial startup channel registry before later plugin-registry churn so configured channels stay visible and `channels.status` stops falling back to empty `channelOrder` / `channels` payloads after runtime plugin loads.
• ·Prompt caching: order stable workspace project-context files before `HEARTBEAT.md` and keep `HEARTBEAT.md` below the system-prompt cache boundary so heartbeat churn does not invalidate the stable project-context prefix. (#58979)
• ·Prompt caching: route Codex Responses and Anthropic Vertex through boundary-aware cache shaping, and report the actual outbound system prompt in cache traces so cache reuse and misses line up with what providers really receive.
• ·Agents/cache: preserve the full 3-turn prompt-cache image window across tool loops, keep colliding bundled MCP tool definitions deterministic, and reapply Anthropic Vertex cache shaping after payload hook replacements so KV/cache reuse stays stable.
• ·Status/cache: restore `cacheRead` and `cacheWrite` in transcript fallback so `/status` keeps showing cache hit percentages when session logs are the only complete usage source. (#59247)
• ·Status/usage: let `/status` and `session_status` fall back to transcript token totals when the session meta store stayed at zero, so LM Studio, Ollama, DashScope, and similar OpenAI-compatible providers stop showing `Context: 0/...`. (#55041)
• ·Mattermost/config schema: accept `groups.*.requireMention` again so existing Mattermost configs no longer fail strict validation after upgrade. (#58271)
• ·Doctor/config: compare normalized `talk` configs by deep structural equality instead of key-order-sensitive serialization so `openclaw doctor --fix` stops repeatedly reporting/applying no-op `talk.provider/providers` normalization. (#59911)
• ·Anthropic CLI onboarding: rewrite migrated fallback model refs during non-interactive Claude CLI setup too, so onboarding and scripted setup no longer keep stale `anthropic/*` fallbacks after switching the primary model to `claude-cli/*`.
• ·Models/Anthropic CLI auth: replace migrated `agents.defaults.models` allowlists when `openclaw models auth login --provider anthropic --method cli --set-default` switches to `claude-cli/*`, so stale `anthropic/*` entries do not linger beside the migrated Claude CLI defaults.
• ·Doctor/Claude CLI: add dedicated Claude CLI health checks so `openclaw doctor` can spot missing local installs or broken auth before agent runs fail.
• ·Plugins/auth-choice: apply provider-owned auth config patches without recursively preserving replaced default-model maps, so Anthropic Claude CLI and similar migrations can intentionally swap model allowlists during onboarding and setup instead of accumulating stale entries.
• ·Plugins/onboarding: write dotted plugin uiHint paths like Brave `webSearch.mode` as nested plugin config so `llm-context` setup stops failing validation. (#61159)
• ·Plugins/install: preserve unsafe override flags across linked plugin and hook-pack probes so local `--link` installs honor the documented override behavior. (#60624)
• ·Plugins/cache: inherit the active gateway workspace for provider, web-search, and web-fetch snapshot loads when callers omit `workspaceDir`, so compatible plugin registries and snapshot caches stop missing on gateway-owned runtime paths. (#61138)
• ·Plugin SDK/context engines: export the missing context-engine result and subagent lifecycle types from `openclaw/plugin-sdk` so context engine plugins can type `ContextEngine` implementations without local workarounds. (#61251)
• ·Tasks/maintenance: reconcile stale cron and chat-backed CLI task rows against live cron-job and agent-run ownership instead of treating any persisted session key as proof that the task is still running. (#60310)
• ·Plugins: suppress trust-warning noise during non-activating snapshot and CLI metadata loads. (#61427)
• ·Agents/video generation: accept `agents.defaults.videoGenerationModel` in strict config validation and `openclaw config set/get`, so gateways using `video_generate` no longer fail to boot after enabling a video model.
• ·Matrix/streaming: add a quiet preview mode for streamed Matrix replies, keep legacy `partial` preview-first behavior, and finalize quiet media captions correctly so previews stop notifying early without dropping final text semantics. (#61450)
• ·Gateway/shutdown: bound websocket-server shutdown even when no tracked clients remain, so gateway restarts stop hanging until the watchdog kills the process. (#61565)
• ·Control UI/multilingual: localize the remaining shared channel, instances, nodes, and gateway-confirmation strings so the dashboard stops mixing translated UI with hardcoded English labels.
• ·Discord/media: raise the default inbound and outbound media cap to `100MB` so Discord matches Telegram more closely and larger attachments stop failing on the old low default.
• ·Matrix: keep direct transport requests on the pinned dispatcher by routing them through undici runtime fetch, so Matrix clients resume syncing on newer runtimes without dropping the validated address binding. (#61595)
• ·Plugins/facades: resolve globally installed bundled-plugin runtime facades from registry roots so bundled channels like LINE still boot when the winning plugin install lives under the global extensions directory with an encoded scoped folder name. (#61297)

Breaking

• ·Plugins/xAI: move `x_search` settings from the legacy core `tools.web.x_search.*` path to the plugin-owned `plugins.entries.xai.config.xSearch.*` path, standardize `x_search` auth on `plugins.entries.xai.config.webSearch.apiKey` / `XAI_API_KEY`, and migrate legacy config with `openclaw doctor --fix`. (#59674)
• ·Plugins/web fetch: move Firecrawl `web_fetch` config from the legacy core `tools.web.fetch.firecrawl.*` path to the plugin-owned `plugins.entries.firecrawl.config.webFetch.*` path, route `web_fetch` fallback through the new fetch-provider boundary instead of a Firecrawl-only core branch, and migrate legacy config with `openclaw doctor --fix`. (#59465)

Changes

• ·Tasks/Task Flow: restore the core Task Flow substrate with managed-vs-mirrored sync modes, durable flow state/revision tracking, and `openclaw flows` inspection/recovery primitives so background orchestration can persist and be operated separately from plugin authoring layers. (#58930)
• ·Tasks/Task Flow: add managed child task spawning plus sticky cancel intent, so external orchestrators can stop scheduling immediately and let parent Task Flows settle to `cancelled` once active child tasks finish. (#59610)
• ·Plugins/Task Flow: add a bound `api.runtime.taskFlow` seam so plugins and trusted authoring layers can create and drive managed Task Flows from host-resolved OpenClaw context without passing owner identifiers on each call. (#59622)
• ·Android/assistant: add assistant-role entrypoints plus Google Assistant App Actions metadata so Android can launch OpenClaw from the assistant trigger and hand prompts into the chat composer. (#59596)
• ·Exec defaults: make gateway/node host exec default to YOLO mode by requesting `security=full` with `ask=off`, and align host approval-file fallbacks plus docs/doctor reporting with that no-prompt default.
• ·Providers/runtime: add provider-owned replay hook surfaces for transcript policy, replay cleanup, and reasoning-mode dispatch. (#59143)
• ·Plugins/hooks: add `before_agent_reply` so plugins can short-circuit the LLM with synthetic replies after inline actions. (#20067)
• ·Channels/session routing: move provider-specific session conversation grammar into plugin-owned session-key surfaces, preserving Telegram topic routing and Feishu scoped inheritance across bootstrap, model override, restart, and tool-policy paths.
• ·Feishu/comments: add a dedicated Drive comment-event flow with comment-thread context resolution, in-thread replies, and `feishu_drive` comment actions for document collaboration workflows. (#58497)
• ·Matrix/plugin: emit spec-compliant `m.mentions` metadata across text sends, media captions, edits, poll fallback text, and action-driven edits so Matrix mentions notify reliably in clients like Element. (#59323)
• ·Diffs: add plugin-owned `viewerBaseUrl` so viewer links can use a stable proxy/public origin without passing `baseUrl` on every tool call. (#59341) Related #59227.
• ·Agents/compaction: resolve `agents.defaults.compaction.model` consistently for manual `/compact` and other context-engine compaction paths, so engine-owned compaction uses the configured override model across runtime entrypoints. (#56710)
• ·Agents/compaction: add `agents.defaults.compaction.notifyUser` so the `🧹 Compacting context...` start notice is opt-in instead of always being shown. (#54251)
• ·WhatsApp/reactions: add `reactionLevel` guidance for agent reactions.
• ·Exec approvals/channels: auto-enable DM-first native chat approvals when supported channels can infer approvers from existing owner config, while keeping channel fanout explicit and clarifying forwarding versus native approval client config.

Fixes

• ·Providers/transport policy: centralize request auth, proxy, TLS, and header shaping across shared HTTP, stream, and websocket paths, block insecure TLS/runtime transport overrides, and keep proxy-hop TLS separate from target mTLS settings. (#59682)
• ·Providers/Copilot: classify native GitHub Copilot API hosts in the shared provider endpoint resolver and harden token-derived proxy endpoint parsing so Copilot base URL routing stays centralized and fails closed on malformed hints. (#59644)
• ·Providers/streaming headers: centralize default and attribution header merging across OpenAI websocket, embedded-runner, and proxy stream paths so provider-specific headers stay consistent and caller overrides only win where intended. (#59542)
• ·Providers/media HTTP: centralize base URL normalization, default auth/header injection, and explicit header override handling across shared OpenAI-compatible audio, Deepgram audio, Gemini media/image, and Moonshot video request paths. (#59469)
• ·Providers/OpenAI-compatible routing: centralize native-vs-proxy request policy so hidden attribution and related OpenAI-family defaults only apply on verified native endpoints across stream, websocket, and shared audio HTTP paths. (#59433)
• ·Providers/Anthropic routing: centralize native-vs-proxy endpoint classification for direct Anthropic `service_tier` handling so spoofed or proxied hosts do not inherit native Anthropic defaults. (#59608)
• ·Gateway/exec loopback: restore legacy-role fallback for empty paired-device token maps and allow silent local role upgrades so local exec and node clients stop failing with pairing-required errors after `2026.3.31`. (#59092)
• ·Agents/subagents: pin admin-only subagent gateway calls to `operator.admin` while keeping `agent` at least privilege, so `sessions_spawn` no longer dies on loopback scope-upgrade pairing with `close(1008) "pairing required"`. (#59555)
• ·Exec approvals/config: strip invalid `security`, `ask`, and `askFallback` values from `~/.openclaw/exec-approvals.json` during normalization so malformed policy enums fall back cleanly to the documented defaults instead of corrupting runtime policy resolution. (#59112)
• ·Exec approvals/doctor: report host policy sources from the real approvals file path and ignore malformed host override values when attributing effective policy conflicts. (#59367)
• ·Exec/runtime: treat `tools.exec.host=auto` as routing-only, keep implicit no-config exec on sandbox when available or gateway otherwise, and reject per-call host overrides that would bypass the configured sandbox or host target. (#58897)
• ·Slack/mrkdwn formatting: add built-in Slack mrkdwn guidance in inbound context so Slack replies stop falling back to generic Markdown patterns that render poorly in Slack. (#59100)
• ·WhatsApp/presence: send `unavailable` presence on connect in self-chat mode so personal-phone users stop losing all push notifications while the gateway is running. (#59410)
• ·WhatsApp/media: add HTML, XML, and CSS to the MIME map and fall back gracefully for unknown media types instead of dropping the attachment. (#51562)
• ·Matrix/onboarding: restore guided setup in `openclaw channels add` and `openclaw configure --section channels`, while keeping custom plugin wizards on the shared `setupWizard` seam. (#59462)
• ·Matrix/streaming: keep live partial previews for the current assistant block while preserving completed block updates as separate messages when `channels.matrix.blockStreaming` is enabled. (#59384)
• ·Feishu/comment threads: harden document comment-thread delivery so whole-document comments fall back to `add_comment`, delayed reply lookups retry more reliably, and user-visible replies avoid reasoning/planning spillover. (#59129)
• ·MS Teams/streaming: strip already-streamed text from fallback block delivery when replies exceed the 4000-character streaming limit so long responses stop duplicating content. (#59297)
• ·Slack/thread context: filter thread starter and history by the effective conversation allowlist without dropping valid open-room, DM, or group DM context. (#58380)
• ·Mattermost/probes: route status probes through the SSRF guard and honor `allowPrivateNetwork` so connectivity checks stay safe for self-hosted Mattermost deployments. (#58529)
• ·Zalo/webhook replay: scope replay dedupe key by chat and sender so reused message IDs across different chats or senders no longer collide, and harden metadata reads for partially missing payloads. (#58444)
• ·QQBot/structured payloads: restrict local file paths to QQ Bot-owned media storage, block traversal outside that root, reduce path leakage in logs, and keep inline image data URLs working. (#58453)
• ·Image generation/providers: route OpenAI, MiniMax, and fal image requests through the shared provider HTTP transport path so custom base URLs, guarded private-network routing, and provider request defaults stay aligned with the rest of provider HTTP.
• ·Image generation/providers: stop inferring private-network access from configured OpenAI, MiniMax, and fal image base URLs, and cap shared HTTP error-body reads so hostile or misconfigured endpoints fail closed without relaxing SSRF policy or buffering unbounded error payloads.
• ·Browser/host inspection: keep static Chrome inspection helpers out of the activated browser runtime so `openclaw doctor browser` and related checks do not eagerly load the bundled browser plugin. (#59471)
• ·Browser/CDP: normalize trailing-dot localhost absolute-form hosts before loopback checks so remote CDP websocket URLs like `ws://localhost.:...` rewrite back to the configured remote host. (#59236)
• ·Agents/output sanitization: strip namespaced `antml:thinking` blocks from user-visible text so Anthropic-style internal monologue tags do not leak into replies. (#59550)
• ·Kimi Coding/tools: normalize Anthropic tool payloads into the OpenAI-compatible function shape Kimi Coding expects so tool calls stop losing required arguments. (#59440)
• ·Image tool/paths: resolve relative local media paths against the agent `workspaceDir` instead of `process.cwd()` so inputs like `inbox/receipt.png` pass the local-path allowlist reliably. (#57222) Thanks Priyansh Gupta.
• ·Podman/launch: remove noisy container output from `scripts/run-openclaw-podman.sh` and align the Podman install guidance with the quieter startup flow. (#59368)
• ·Plugins/runtime: keep LINE reply directives and browser-backed cleanup/reset flows working even when those plugins are disabled while tightening bundled plugin activation guards. (#59412)
• ·ACP/gateway reconnects: keep ACP prompts alive across transient websocket drops while still failing boundedly when reconnect recovery does not complete. (#59473)
• ·ACP/gateway reconnects: reject stale pre-ack ACP prompts after reconnect grace expiry so callers fail cleanly instead of hanging indefinitely when the gateway never confirms the run.
• ·Gateway/session kill: enforce HTTP operator scopes on session kill requests and gate authorization before session lookup so unauthenticated callers cannot probe session existence. (#59128)
• ·MS Teams/logging: format non-`Error` failures with the shared unknown-error helper so logs stop collapsing caught SDK or Axios objects into `[object Object]`. (#59321)
• ·Channels/setup: ignore untrusted workspace channel plugins during setup resolution so a shadowing workspace plugin cannot override built-in channel setup/login flows unless explicitly trusted in config. (#59158)
• ·Exec/Windows: restore allowlist enforcement with quote-aware `argPattern` matching across gateway and node exec, and surface accurate dynamic pre-approved executable hints in the exec tool description. (#56285)
• ·Gateway: prune empty `node-pending-work` state entries after explicit acknowledgments and natural expiry so the per-node state map no longer grows indefinitely. (#58179)
• ·Webhooks/secret comparison: replace ad-hoc timing-safe secret comparisons across BlueBubbles, Feishu, Mattermost, Telegram, Twilio, and Zalo webhook handlers with the shared `safeEqualSecret` helper and reject empty auth tokens in BlueBubbles. (#58432)
• ·OpenShell/mirror: constrain `remoteWorkspaceDir` and `remoteAgentWorkspaceDir` to the managed `/sandbox` and `/agent` roots, and keep mirror sync from overwriting or removing user-added shell roots during config synchronization. (#58515)
• ·Plugins/activation: preserve explicit, auto-enabled, and default activation provenance plus reason metadata across CLI, gateway bootstrap, and status surfaces so plugin enablement state stays accurate after auto-enable resolution. (#59641)
• ·Exec/env: block additional host environment override pivots for package roots, language runtimes, compiler include paths, and credential/config locations so request-scoped exec cannot redirect trusted toolchains or config lookups. (#59233)
• ·Dotenv/workspace overrides: block workspace `.env` files from overriding `OPENCLAW_PINNED_PYTHON` and `OPENCLAW_PINNED_WRITE_PYTHON` so trusted helper interpreters cannot be redirected by repo-local env injection. (#58473)
• ·Plugins/install: accept JSON5 syntax in `openclaw.plugin.json` and bundle `plugin.json` manifests during install/validation, so third-party plugins with trailing commas, comments, or unquoted keys no longer fail to install. (#59084)
• ·Telegram/exec approvals: rewrite shared `/approve … allow-always` callback payloads to `/approve … always` before Telegram button rendering so plugin approval IDs still fit Telegram's `callback_data` limit and keep the Allow Always action visible. (#59217)
• ·Cron/exec timeouts: surface timed-out `exec` and `bash` failures in isolated cron runs even when `verbose: off`, including custom session-target cron jobs, so scheduled runs stop failing silently. (#58247)
• ·Telegram/exec approvals: fall back to the origin session key for async approval followups and keep resume-failure status delivery sanitized so Telegram followups still land without leaking raw exec metadata. (#59351)
• ·Node-host/exec approvals: bind `pnpm dlx` invocations through the approval planner's mutable-script path so the effective runtime command is resolved for approval instead of being left unbound. (#58374)
• ·Exec/node hosts: stop forwarding the gateway workspace cwd to remote node exec when no workdir was explicitly requested, so cross-platform node approvals fall back to the node default cwd instead of failing with `SYSTEM_RUN_DENIED`. (#58977)
• ·Exec approvals/channels: decouple initiating-surface approval availability from native delivery enablement so Telegram, Slack, and Discord still expose approvals when approvers exist and native target routing is configured separately. (#59776)

Changes

• ·Tasks/chat: add `/tasks` as a chat-native background task board for the current session, with recent task details and agent-local fallback counts when no linked tasks are visible. Related #54226.
• ·Web search/SearXNG: add the bundled SearXNG provider plugin for `web_search` with configurable host support. (#57317)
• ·Amazon Bedrock/Guardrails: add Bedrock Guardrails support to the bundled provider. (#58588)
• ·macOS/Voice Wake: add the Voice Wake option to trigger Talk Mode. (#58490)
• ·Feishu/comments: add a dedicated Drive comment-event flow with comment-thread context resolution, in-thread replies, and `feishu_drive` comment actions for document collaboration workflows. (#58497)
• ·Gateway/webchat: make `chat.history` text truncation configurable with `gateway.webchat.chatHistoryMaxChars` and per-request `maxChars`, while preserving silent-reply filtering and existing default payload limits. (#58900)
• ·Agents/default params: add `agents.defaults.params` for global default provider parameters. (#58548)
• ·Agents/failover: cap prompt-side and assistant-side same-provider auth-profile retries for rate-limit failures before cross-provider model fallback, add the `auth.cooldowns.rateLimitedProfileRotations` knob, and document the new fallback behavior. (#58707)
• ·Cron/tools allowlist: add `openclaw cron --tools` for per-job tool allowlists. (#58504)
• ·Channels/session routing: move provider-specific session conversation grammar into plugin-owned session-key surfaces, preserving Telegram topic routing and Feishu scoped inheritance across bootstrap, model override, restart, and tool-policy paths.
• ·WhatsApp/reactions: add `reactionLevel` guidance for agent reactions.
• ·Telegram/errors: add configurable `errorPolicy` and `errorCooldownMs` controls so Telegram can suppress repeated delivery errors per account, chat, and topic without muting distinct failures. (#51914)
• ·ZAI/models: add `glm-5.1` and `glm-5v-turbo` to the bundled Z.AI provider catalog. (#58793)
• ·Agents/compaction: resolve `agents.defaults.compaction.model` consistently for manual `/compact` and other context-engine compaction paths, so engine-owned compaction uses the configured override model across runtime entrypoints. (#56710)

Fixes

• ·Chat/error replies: stop leaking raw provider/runtime failures into external chat channels, return a friendly retry message instead, and add a specific `/new` hint for Bedrock toolResult/toolUse session mismatches. (#58831)
• ·Gateway/reload: ignore startup config writes by persisted hash in the config reloader so generated auth tokens and seeded Control UI origins do not trigger a restart loop, while real `gateway.auth.*` edits still require restart. (#58678)
• ·Tasks/gateway: keep the task registry maintenance sweep from stalling the gateway event loop under synchronous SQLite pressure, so upgraded gateways stop hanging about a minute after startup. (#58670)
• ·Tasks/status: hide stale completed background tasks from `/status` and `session_status`, prefer live task context, and show recent failures only when no active work remains. (#58661)
• ·Tasks/gateway: re-check the current task record before maintenance marks runs lost or prunes them, so a task heartbeat or cleanup update that lands during a sweep no longer gets overwritten by stale snapshot state.
• ·Exec/approvals: honor `exec-approvals.json` security defaults when inline or configured tool policy is unset, and keep Slack and Discord native approval handling aligned with inferred approvers and real channel enablement so remote exec stops falling into false approval timeouts and disabled states.
• ·Exec/approvals: make `allow-always` persist as durable user-approved trust instead of behaving like `allow-once`, reuse exact-command trust on shell-wrapper paths that cannot safely persist an executable allowlist entry, keep static allowlist entries from silently bypassing `ask:"always"`, and require explicit approval when Windows cannot build an allowlist execution plan instead of hard-dead-ending remote exec.
• ·Exec/cron: resolve isolated cron no-route approval dead-ends from the effective host fallback policy when trusted automation is allowed, and make `openclaw doctor` warn when `tools.exec` is broader than `~/.openclaw/exec-approvals.json` so stricter host-policy conflicts are explicit.
• ·Sessions/model switching: keep `/model` changes queued behind busy runs instead of interrupting the active turn, and retarget queued followups so later work picks up the new model as soon as the current turn finishes.
• ·Gateway/HTTP: skip failing HTTP request stages so one broken facade no longer forces every HTTP endpoint to return 500. (#58746)
• ·Gateway/nodes: stop pinning live node commands to the approved node-pair record. Node pairing remains a trust/token flow, while per-node `system.run` policy stays in that node's exec approvals config. Fixes #58824.
• ·WebChat/exec approvals: use native approval UI guidance in agent system prompts instead of telling agents to paste manual `/approve` commands in webchat sessions.
• ·Web UI/OpenResponses: preserve rewritten stream snapshots in webchat and keep OpenResponses final streamed text aligned when models rewind earlier output. (#58641)
• ·Discord/inbound media: pass Discord attachment and sticker downloads through the shared idle-timeout and worker-abort path so slow or stuck inbound media fetches stop hanging message processing. (#58593)
• ·Telegram/retries: keep non-idempotent sends on the strict safe-send path, retry wrapped pre-connect failures, and preserve `429` / `retry_after` backoff for safe delivery retries. (#51895)
• ·Telegram/exec approvals: route topic-aware exec approval followups through Telegram-owned threading and approval-target parsing, so forum-topic approvals stay in the originating topic instead of falling back to the root chat. (#58783)
• ·Telegram/local Bot API: preserve media MIME types for absolute-path downloads so local audio files still trigger transcription and other MIME-based handling. (#54603)
• ·Channels/WhatsApp: pass inbound message timestamp to model context so the AI can see when WhatsApp messages were sent. (#58590)
• ·Channels/QQ Bot: keep `/bot-logs` export gated behind a truly explicit QQBot allowlist, rejecting wildcard and mixed wildcard entries while preserving the real framework command path.
• ·Channels/plugins: keep bundled channel plugins loadable from legacy `channels.<id>` config even under restrictive plugin allowlists, and make `openclaw doctor` warn only on real plugin blockers instead of misleading setup guidance. (#58873)
• ·Plugins/bundled runtimes: restore externalized bundled plugin runtime dependency staging across packed installs, Docker builds, and local runtime staging so bundled plugins keep their declared runtime deps after the 2026.3.31 externalization change. (#58782)
• ·LINE/runtime: resolve the packaged runtime contract from the built `dist/plugins/runtime` layout so LINE channels start correctly again after global npm installs on `2026.3.31`. (#58799)
• ·MiniMax/plugins: auto-enable the bundled MiniMax plugin for API-key auth/config so MiniMax image generation and other plugin-owned capabilities load without manual plugin allowlisting. (#57127)
• ·Ollama/model picker: show only Ollama models after provider selection in the CLI picker. (#55290)
• ·CDP/profiles: prefer `cdpPort` over stale WebSocket URLs so browser automation reconnects cleanly. (#58499)
• ·Media/paths: resolve relative `MEDIA` paths against the agent workspace so local attachment references keep working. (#58624)
• ·Memory/session indexing: keep full reindexes from skipping session transcripts when sync is triggered by `session-start` or `watch`, so restart-driven reindexes preserve session memory. (#39732)
• ·Memory/QMD: prefer `--mask` over `--glob` when creating QMD collections so default memory collections keep their intended patterns and stop colliding on restart. (#58643)
• ·Subagents/tasks: keep subagent completion and cleanup from crashing when task-registry writes fail, so a corrupt or missing task row no longer takes down the gateway during lifecycle finalization.
• ·Sandbox/browser: compare browser runtime inspection against `agents.defaults.sandbox.browser.image` so `openclaw sandbox list --browser` stops reporting healthy browser containers as image mismatches. (#58759)
• ·Plugins/install: forward `--dangerously-force-unsafe-install` through archive and npm-spec plugin installs so the documented override reaches the security scanner on those install paths. (#58879)
• ·Auto-reply/commands: strip inbound metadata before slash command detection so wrapped `/model`, `/new`, and `/status` commands are recognized. (#58725)
• ·Agents/Anthropic: preserve thinking blocks and signatures across replay, cache-control patching, and context pruning so compacted Anthropic sessions continue working instead of failing on later turns. (#58916)
• ·Agents/failover: unify structured and raw provider error classification so provider-specific `400`/`422` payloads no longer get forced into generic format failures before retry, billing, or compaction logic can inspect them. (#58856)
• ·Auth profiles/store: coerce misplaced SecretRef objects out of plaintext `key` and `token` fields during store load so agents without ACP runtime stop crashing on `.trim()` after upgrade. (#58923)
• ·ACPX/runtime: repair `queue owner unavailable` session recovery by replacing dead named sessions and resuming the backend session when ACPX exposes a stable session id, so the first ACP prompt no longer inherits a dead handle. (#58669)
• ·ACPX/runtime: retry dead-session queue-owner repair without `--resume-session` when the reported ACPX session id is stale, so recovery still creates a fresh named session instead of failing session init.
• ·Auth/OpenAI Codex: persist plugin-refreshed OAuth credentials to `auth-profiles.json` before returning them, so rotated Codex refresh tokens survive restart and stop falling into `refresh_token_reused` loops. (#53082)
• ·Discord/gateway: hand reconnect ownership back to Carbon, keep runtime status aligned with close/reconnect state, and force-stop sockets that open without reaching READY so Discord monitors recover promptly instead of waiting on stale health timeouts. (#59019)
• ·Config/Telegram: migrate removed `channels.telegram.groupMentionsOnly` into `channels.telegram.groups["*"].requireMention` on load so legacy configs no longer crash at startup. (#55336)

Changes

• ·Tasks/chat: add `/tasks` as a chat-native background task board for the current session, with recent task details and agent-local fallback counts when no linked tasks are visible. Related #54226.
• ·Web search/SearXNG: add the bundled SearXNG provider plugin for `web_search` with configurable host support. (#57317)
• ·Amazon Bedrock/Guardrails: add Bedrock Guardrails support to the bundled provider. (#58588)
• ·macOS/Voice Wake: add the Voice Wake option to trigger Talk Mode. (#58490)
• ·Feishu/comments: add a dedicated Drive comment-event flow with comment-thread context resolution, in-thread replies, and `feishu_drive` comment actions for document collaboration workflows. (#58497)
• ·Gateway/webchat: make `chat.history` text truncation configurable with `gateway.webchat.chatHistoryMaxChars` and per-request `maxChars`, while preserving silent-reply filtering and existing default payload limits. (#58900)
• ·Agents/default params: add `agents.defaults.params` for global default provider parameters. (#58548)
• ·Agents/failover: cap prompt-side and assistant-side same-provider auth-profile retries for rate-limit failures before cross-provider model fallback, add the `auth.cooldowns.rateLimitedProfileRotations` knob, and document the new fallback behavior. (#58707)
• ·Cron/tools allowlist: add `openclaw cron --tools` for per-job tool allowlists. (#58504)
• ·Channels/session routing: move provider-specific session conversation grammar into plugin-owned session-key surfaces, preserving Telegram topic routing and Feishu scoped inheritance across bootstrap, model override, restart, and tool-policy paths.
• ·WhatsApp/reactions: add `reactionLevel` guidance for agent reactions.
• ·Telegram/errors: add configurable `errorPolicy` and `errorCooldownMs` controls so Telegram can suppress repeated delivery errors per account, chat, and topic without muting distinct failures. (#51914)
• ·ZAI/models: add `glm-5.1` and `glm-5v-turbo` to the bundled Z.AI provider catalog. (#58793)
• ·Agents/compaction: resolve `agents.defaults.compaction.model` consistently for manual `/compact` and other context-engine compaction paths, so engine-owned compaction uses the configured override model across runtime entrypoints. (#56710)

Fixes

• ·Chat/error replies: stop leaking raw provider/runtime failures into external chat channels, return a friendly retry message instead, and add a specific `/new` hint for Bedrock toolResult/toolUse session mismatches. (#58831)
• ·Gateway/reload: ignore startup config writes by persisted hash in the config reloader so generated auth tokens and seeded Control UI origins do not trigger a restart loop, while real `gateway.auth.*` edits still require restart. (#58678)
• ·Tasks/gateway: keep the task registry maintenance sweep from stalling the gateway event loop under synchronous SQLite pressure, so upgraded gateways stop hanging about a minute after startup. (#58670)
• ·Tasks/status: hide stale completed background tasks from `/status` and `session_status`, prefer live task context, and show recent failures only when no active work remains. (#58661)
• ·Tasks/gateway: re-check the current task record before maintenance marks runs lost or prunes them, so a task heartbeat or cleanup update that lands during a sweep no longer gets overwritten by stale snapshot state.
• ·Exec/approvals: honor `exec-approvals.json` security defaults when inline or configured tool policy is unset, and keep Slack and Discord native approval handling aligned with inferred approvers and real channel enablement so remote exec stops falling into false approval timeouts and disabled states.
• ·Exec/approvals: make `allow-always` persist as durable user-approved trust instead of behaving like `allow-once`, reuse exact-command trust on shell-wrapper paths that cannot safely persist an executable allowlist entry, keep static allowlist entries from silently bypassing `ask:"always"`, and require explicit approval when Windows cannot build an allowlist execution plan instead of hard-dead-ending remote exec.
• ·Exec/cron: resolve isolated cron no-route approval dead-ends from the effective host fallback policy when trusted automation is allowed, and make `openclaw doctor` warn when `tools.exec` is broader than `~/.openclaw/exec-approvals.json` so stricter host-policy conflicts are explicit.
• ·Sessions/model switching: keep `/model` changes queued behind busy runs instead of interrupting the active turn, and retarget queued followups so later work picks up the new model as soon as the current turn finishes.
• ·Gateway/HTTP: skip failing HTTP request stages so one broken facade no longer forces every HTTP endpoint to return 500. (#58746)
• ·Gateway/nodes: stop pinning live node commands to the approved node-pair record. Node pairing remains a trust/token flow, while per-node `system.run` policy stays in that node's exec approvals config. Fixes #58824.
• ·WebChat/exec approvals: use native approval UI guidance in agent system prompts instead of telling agents to paste manual `/approve` commands in webchat sessions.
• ·Web UI/OpenResponses: preserve rewritten stream snapshots in webchat and keep OpenResponses final streamed text aligned when models rewind earlier output. (#58641)
• ·Discord/inbound media: pass Discord attachment and sticker downloads through the shared idle-timeout and worker-abort path so slow or stuck inbound media fetches stop hanging message processing. (#58593)
• ·Telegram/retries: keep non-idempotent sends on the strict safe-send path, retry wrapped pre-connect failures, and preserve `429` / `retry_after` backoff for safe delivery retries. (#51895)
• ·Telegram/exec approvals: route topic-aware exec approval followups through Telegram-owned threading and approval-target parsing, so forum-topic approvals stay in the originating topic instead of falling back to the root chat. (#58783)
• ·Telegram/local Bot API: preserve media MIME types for absolute-path downloads so local audio files still trigger transcription and other MIME-based handling. (#54603)
• ·Channels/WhatsApp: pass inbound message timestamp to model context so the AI can see when WhatsApp messages were sent. (#58590)
• ·Channels/QQ Bot: keep `/bot-logs` export gated behind a truly explicit QQBot allowlist, rejecting wildcard and mixed wildcard entries while preserving the real framework command path.
• ·Channels/plugins: keep bundled channel plugins loadable from legacy `channels.<id>` config even under restrictive plugin allowlists, and make `openclaw doctor` warn only on real plugin blockers instead of misleading setup guidance. (#58873)
• ·Plugins/bundled runtimes: restore externalized bundled plugin runtime dependency staging across packed installs, Docker builds, and local runtime staging so bundled plugins keep their declared runtime deps after the 2026.3.31 externalization change. (#58782)
• ·LINE/runtime: resolve the packaged runtime contract from the built `dist/plugins/runtime` layout so LINE channels start correctly again after global npm installs on `2026.3.31`. (#58799)
• ·MiniMax/plugins: auto-enable the bundled MiniMax plugin for API-key auth/config so MiniMax image generation and other plugin-owned capabilities load without manual plugin allowlisting. (#57127)
• ·Ollama/model picker: show only Ollama models after provider selection in the CLI picker. (#55290)
• ·CDP/profiles: prefer `cdpPort` over stale WebSocket URLs so browser automation reconnects cleanly. (#58499)
• ·Media/paths: resolve relative `MEDIA` paths against the agent workspace so local attachment references keep working. (#58624)
• ·Memory/session indexing: keep full reindexes from skipping session transcripts when sync is triggered by `session-start` or `watch`, so restart-driven reindexes preserve session memory. (#39732)
• ·Memory/QMD: prefer `--mask` over `--glob` when creating QMD collections so default memory collections keep their intended patterns and stop colliding on restart. (#58643)
• ·Subagents/tasks: keep subagent completion and cleanup from crashing when task-registry writes fail, so a corrupt or missing task row no longer takes down the gateway during lifecycle finalization.
• ·Sandbox/browser: compare browser runtime inspection against `agents.defaults.sandbox.browser.image` so `openclaw sandbox list --browser` stops reporting healthy browser containers as image mismatches. (#58759)
• ·Plugins/install: forward `--dangerously-force-unsafe-install` through archive and npm-spec plugin installs so the documented override reaches the security scanner on those install paths. (#58879)
• ·Auto-reply/commands: strip inbound metadata before slash command detection so wrapped `/model`, `/new`, and `/status` commands are recognized. (#58725)
• ·Agents/Anthropic: preserve thinking blocks and signatures across replay, cache-control patching, and context pruning so compacted Anthropic sessions continue working instead of failing on later turns. (#58916)
• ·Agents/failover: unify structured and raw provider error classification so provider-specific `400`/`422` payloads no longer get forced into generic format failures before retry, billing, or compaction logic can inspect them. (#58856)
• ·Auth profiles/store: coerce misplaced SecretRef objects out of plaintext `key` and `token` fields during store load so agents without ACP runtime stop crashing on `.trim()` after upgrade. (#58923)
• ·ACPX/runtime: repair `queue owner unavailable` session recovery by replacing dead named sessions and resuming the backend session when ACPX exposes a stable session id, so the first ACP prompt no longer inherits a dead handle. (#58669)
• ·ACPX/runtime: retry dead-session queue-owner repair without `--resume-session` when the reported ACPX session id is stale, so recovery still creates a fresh named session instead of failing session init.
• ·Auth/OpenAI Codex: persist plugin-refreshed OAuth credentials to `auth-profiles.json` before returning them, so rotated Codex refresh tokens survive restart and stop falling into `refresh_token_reused` loops. (#53082)
• ·Discord/gateway: hand reconnect ownership back to Carbon, keep runtime status aligned with close/reconnect state, and force-stop sockets that open without reaching READY so Discord monitors recover promptly instead of waiting on stale health timeouts. (#59019)

Breaking

• ·Nodes/exec: remove the duplicated `nodes.run` shell wrapper from the CLI and agent `nodes` tool so node shell execution always goes through `exec host=node`, keeping node-specific capabilities on `nodes invoke` and the dedicated media/location/notify actions.
• ·Plugin SDK: deprecate the legacy provider compat subpaths plus the older bundled provider setup and channel-runtime compatibility shims, emit migration warnings, and keep the current documented `openclaw/plugin-sdk/*` entrypoints plus local `api.ts` / `runtime-api.ts` barrels as the forward path ahead of a future major-release removal.
• ·Skills/install and Plugins/install: built-in dangerous-code `critical` findings and install-time scan failures now fail closed by default, so plugin installs and gateway-backed skill dependency installs that previously succeeded may now require an explicit dangerous override such as `--dangerously-force-unsafe-install` to proceed.
• ·Gateway/auth: `trusted-proxy` now rejects mixed shared-token configs, and local-direct fallback requires the configured token instead of implicitly authenticating same-host callers.
• ·Gateway/node commands: node commands now stay disabled until node pairing is approved, so device pairing alone is no longer enough to expose declared node commands. (#57777)
• ·Gateway/node events: node-originated runs now stay on a reduced trusted surface, so notification-driven or node-triggered flows that previously relied on broader host/session tool access may need adjustment. (#57691)

Changes

• ·ACP/plugins: add an explicit default-off ACPX plugin-tools MCP bridge config, document the trust boundary, and harden the built-in bridge packaging/logging path so global installs and stdio MCP sessions work reliably. (#56867)
• ·Agents/LLM: add a configurable idle-stream timeout for embedded runner requests so stalled model streams abort cleanly instead of hanging until the broader run timeout fires. (#55072)
• ·Agents/MCP: materialize bundle MCP tools with provider-safe names (`serverName__toolName`), support optional `streamable-http` transport selection plus per-server connection timeouts, and preserve real tool results from aborted/error turns unless truncation explicitly drops them. (#49505)
• ·Android/notifications: add notification-forwarding controls with package filtering, quiet hours, rate limiting, and safer picker behavior for forwarded notification events. (#40175)
• ·Background tasks: turn tasks into a real shared background-run control plane instead of ACP-only bookkeeping by unifying ACP, subagent, cron, and background CLI execution under one SQLite-backed ledger, routing detached lifecycle updates through the executor seam, adding audit/maintenance/status visibility, tightening auto-cleanup and lost-run recovery, improving task awareness in internal status/tool surfaces, and clarifying the split between heartbeat/main-session automation and detached scheduled runs.
• ·Background tasks: add the first linear task flow control surface with `openclaw flows list|show|cancel`, keep manual multi-task flows separate from one-task auto-sync flows, and surface doctor recovery hints for obviously orphaned or broken flow/task linkage.
• ·Channels/QQ Bot: add QQ Bot as a bundled channel plugin with multi-account setup, SecretRef-aware credentials, slash commands, reminders, and media send/receive support. (#52986)
• ·Diffs: skip unused viewer-versus-file SSR preload work so `diffs` view-only and file-only runs do less render work while keeping mode outputs aligned. (#57909)
• ·Tasks: add a minimal SQLite-backed task flow registry plus task-to-flow linkage scaffolding, so orchestrated work can start gaining a first-class parent record without changing current task delivery behavior.
• ·Tasks: persist blocked state on one-task task flows and let the same flow reopen cleanly on retry, so blocked detached work can carry a parent-level reason and continue without fragmenting into a new job.
• ·Tasks: route one-task ACP and subagent updates through a parent task-flow owner context, so detached work can emerge back through the intended parent thread/session instead of speaking only as a raw child task.
• ·LINE/outbound media: add LINE image, video, and audio outbound sends on the LINE-specific delivery path, including explicit preview/tracking handling for videos while keeping generic media sends on the existing image-only route. (#45826)
• ·Matrix/history: add optional room history context for Matrix group triggers via `channels.matrix.historyLimit`, with per-agent watermarks and retry-safe snapshots so failed trigger retries do not drift into newer room messages. (#57022)
• ·Matrix/network: add explicit `channels.matrix.proxy` config for routing Matrix traffic through an HTTP(S) proxy, including account-level overrides and matching probe/runtime behavior. (#56931)
• ·Matrix/streaming: add draft streaming so partial Matrix replies update the same message in place instead of sending a new message for each chunk. (#56387)
• ·Matrix/threads: add per-DM `threadReplies` overrides and keep thread session isolation aligned with the effective room or DM thread policy from the triggering message onward. (#57995)
• ·MCP: add remote HTTP/SSE server support for `mcp.servers` URL configs, including auth headers and safer config redaction for MCP credentials. (#50396)
• ·Memory/QMD: add per-agent `memorySearch.qmd.extraCollections` so agents can opt into cross-agent session search without flattening every transcript collection into one shared QMD namespace.
• ·Microsoft Teams/member info: add a Graph-backed member info action so Teams automations and tools can resolve channel member details directly from Microsoft Graph. (#57528)
• ·Nostr/inbound DMs: verify inbound event signatures before pairing or sender-authorization side effects, so forged DM events no longer create pairing requests or trigger reply attempts.
• ·OpenAI/Responses: forward configured `text.verbosity` across Responses HTTP and WebSocket transports, surface it in `/status`, and keep per-agent verbosity precedence aligned with runtime behavior. (#47106)
• ·Pi/Codex: add native Codex web search support for embedded Pi runs, including config/docs/wizard coverage and managed-tool suppression when native Codex search is active. (#46579)
• ·Slack/exec approvals: add native Slack approval routing and approver authorization so exec approval prompts can stay in Slack instead of falling back to the Web UI or terminal.
• ·TTS: Add structured provider diagnostics and fallback attempt analytics. (#57954)
• ·WhatsApp/reactions: agents can now react with emoji on incoming WhatsApp messages, enabling more natural conversational interactions like acknowledging a photo with ❤️ instead of typing a reply.
• ·Agents/BTW: force `/btw` side questions to disable provider reasoning so Anthropic adaptive-thinking sessions stop failing with `No BTW response generated`. Fixes #55376.
• ·CLI/onboarding: reset the remote gateway URL prompt to the safe loopback default after declining a discovered endpoint, so onboarding does not keep a previously rejected remote URL. (#57828)
• ·Agents/exec defaults: honor per-agent `tools.exec` defaults when no inline directive or session override is present, so configured exec host, security, ask, and node settings actually apply. (#57689)
• ·Sandbox/networking: sanitize SSH subprocess env vars through the shared sandbox policy and route marketplace archive downloads plus Ollama discovery, auth, and pull requests through the guarded fetch path so sandboxed execution and remote fetches follow the repo's trust boundaries. (#57848, #57850)

Fixes

• ·Slack: stop retry-driven duplicate replies when draft-finalization edits fail ambiguously, and log configured allowlisted users/channels by readable name instead of raw IDs.
• ·Agents/OpenAI Responses: normalize raw bundled MCP tool schemas on the WebSocket/Responses path so bare-object, object-ish, and top-level union MCP tools no longer get rejected by OpenAI during tool registration. (#58299)
• ·ACP/security: replace ACP's dangerous-tool name override with semantic approval classes, so only narrow readonly reads/searches can auto-approve while indirect exec-capable and control-plane tools always require explicit prompt approval.
• ·ACP/sessions_spawn: register ACP child runs for completion tracking and lifecycle cleanup, and make registration-failure cleanup explicitly best-effort so callers do not assume an already-started ACP turn was fully aborted. (#40885)
• ·ACP/tasks: mark cleanly exited ACP runs as blocked when they end on deterministic write or authorization blockers, and wake the parent session with a follow-up instead of falsely reporting success.
• ·ACPX/runtime: derive the bundled ACPX expected version from the extension package metadata instead of hardcoding a separate literal, so plugin-local ACPX installs stop drifting out of health-check parity after version bumps. (#49089)
• ·Agents/Anthropic failover: treat Anthropic `api_error` payloads with `An unexpected error occurred while processing the response` as transient so retry/fallback can engage instead of surfacing a terminal failure. (#57441)
• ·Agents/compaction: keep late compaction-retry completions from double-resolving finished compaction futures, so interrupted or timed-out compactions stop surfacing spurious second-completion races. (#57796)
• ·Agents/disabled providers: make disabled providers disappear from default model selection and embedded provider fallback, while letting explicitly pinned disabled providers fail with a clear config error instead of silently taking traffic. (#57735)
• ·Agents/OAuth output: force exec-host OAuth output readers through the gateway fs policy so embedded gateway runs stop crashing when provider auth writes land outside the current sandbox workspace. (#58249)
• ·Agents/system prompt: fix `agent.name` interpolation in the embedded runtime system prompt and make provider/model fallback text reflect the effective runtime selection after start. (#57625)
• ·Android/device info: read the app's version metadata from the package manager instead of hidden APIs so Android 15+ onboarding and device info no longer fail to compile or report placeholder values. (#58126)
• ·Android/pairing: stop appending duplicate push receiver entries to `gateway-service.conf` on repeated QR pairing and keep push registration bounded to the current successful pairing, so Android push delivery stays healthy across re-pair and token rotation. (#58256)
• ·App install smoke: pin the latest-release lookup to `latest`, cache the first stable install version across the rerun, and relax prerelease package assertions so the Parallels smoke lane can validate stable-to-main upgrades even when `beta` moves ahead or the guest starts from an older stable. (#58177)
• ·Auth/profiles: keep the last successful config load in memory for the running process and refresh that snapshot on successful writes/reloads, so hot paths stop reparsing `openclaw.json` between watcher-driven swaps.
• ·Config/SecretRef + Control UI: harden SecretRef redaction round-trip restore, block unsafe raw fallback (force Form mode when raw is unavailable), and preflight submitted-config SecretRefs before config write RPC persistence. (#58044)
• ·Config/Telegram: migrate removed `channels.telegram.groupMentionsOnly` into `channels.telegram.groups[\"*\"].requireMention` on load so legacy configs no longer crash at startup. (#55336)
• ·Config/update: stop `openclaw doctor` write-backs from persisting plugin-injected channel defaults, so `openclaw update` no longer seeds config keys that later break service refresh validation. (#56834)
• ·Control UI/agents: auto-load agent workspace files on initial Files panel open, and populate overview model/workspace/fallbacks from effective runtime agent metadata so defaulted models no longer show as `Not set`. (#56637)
• ·Control UI/slash commands: make `/steer` and `/redirect` work from the chat command palette with visible pending state for active-run `/steer`, correct redirected-run tracking, and a single canonical `/steer` entry in the command menu. (#54625)
• ·Cron/announce: preserve all deliverable text payloads for announce mode instead of collapsing to the last chunk, so multi-line cron reports deliver in full to Telegram forum topics.
• ·Cron/isolated sessions: carry the full live-session provider, model, and auth-profile selection across retry restarts so cron jobs with model overrides no longer fail or loop on mid-run model-switch requests. (#57972)
• ·Diffs/config: preserve schema-shaped plugin config parsing from `diffsPluginConfigSchema.safeParse()`, so direct callers keep `defaults` and `security` sections instead of receiving flattened tool defaults. (#57904)
• ·Diffs: fall back to plain text when `lang` hints are invalid during diff render and viewer hydration, so bad or stale language values no longer break the diff viewer. (#57902)
• ·Discord/voice: enforce the same guild channel and member allowlist checks on spoken voice ingress before transcription, so joined voice channels no longer accept speech from users outside the configured Discord access policy.
• ·Docker/setup: force BuildKit for local image builds (including sandbox image builds) so `./docker-setup.sh` no longer fails on `RUN --mount=...` when hosts default to Docker's legacy builder. (#56681)
• ·Docs/anchors: fix broken English docs links and make Mint anchor audits run against the English-source docs tree. (#57039)
• ·Doctor/plugins: skip false Matrix legacy-helper warnings when no migration plans exist, and keep bundled `enabledByDefault` plugins in the gateway startup set. (#57931)
• ·Exec approvals/macOS: unwrap `arch` and `xcrun` before deriving shell payloads and allow-always patterns, so wrapper approvals stay bound to the carried command instead of the outer carrier.
• ·Exec approvals: unwrap `caffeinate` and `sandbox-exec` before persisting allow-always trust so later shell payload changes still require a fresh approval.
• ·Exec/approvals: infer Discord and Telegram exec approvers from existing owner config when `execApprovals.approvers` is unset, extend the default approval window to 30 minutes, and clarify approval-unavailable guidance so approvals do not appear to silently disappear.
• ·Pi/TUI: flush message-boundary replies at `message_end` so turns stop looking stuck until the next nudge when the final reply was already ready.
• ·Exec/approvals: keep `awk` and `sed` family binaries out of the low-risk `safeBins` fast path, and stop doctor profile scaffolding from treating them like ordinary custom filters.
• ·Exec/env: block proxy, TLS, and Docker endpoint env overrides in host execution so request-scoped commands cannot silently reroute outbound traffic or trust attacker-supplied certificate settings.
• ·Exec/env: block Python package index override variables from request-scoped host exec environment sanitization so package fetches cannot be redirected through a caller-supplied index.
• ·Exec/node: stop gateway-side workdir fallback from rewriting explicit `host=node` cwd values to the gateway filesystem, so remote node exec approval and runs keep using the intended node-local directory. (#50961)
• ·Exec/runtime: default implicit exec to `host=auto`, resolve that target to sandbox only when a sandbox runtime exists, keep explicit `host=sandbox` fail-closed without sandbox, and show `/exec` effective host state in runtime status/docs.
• ·Exec: fail closed when the implicit sandbox host has no sandbox runtime, and stop denied async approval followups from reusing prior command output from the same session. (#56800)
• ·Feishu/groups: keep quoted replies and topic bootstrap context aligned with group sender allowlists so only allowlisted thread messages seed agent context.
• ·Gateway/attachments: offload large inbound images without leaking `media://` markers into text-only runs, preserve mixed attachment order for model input/transcripts, and fail closed when model image capability cannot be resolved. (#55513)
• ·Gateway/auth: keep shared-auth rate limiting active during WebSocket handshake attempts even when callers also send device-token candidates, so bogus device-token fields no longer suppress shared-secret brute-force tracking.
• ·Gateway/auth: reject mismatched browser `Origin` headers on trusted-proxy HTTP operator requests while keeping origin-less headless proxy clients working.
• ·Gateway/device tokens: disconnect active device sessions after token rotation so newly rotated credentials revoke existing live connections immediately instead of waiting for those sockets to close naturally.
• ·Gateway/health: carry webhook-vs-polling account mode from channel descriptors into runtime snapshots so passive channels like LINE and BlueBubbles skip false stale-socket health failures. (#47488)
• ·Gateway/pairing: restore QR bootstrap onboarding handoff so fresh `/pair qr` iPhone setup can auto-approve the initial node pairing, receive a reusable node device token, and stop retrying with spent bootstrap auth. (#58382)
• ·Gateway/OpenAI compatibility: accept flat Responses API function tool definitions on `/v1/responses` and preserve `strict` when normalizing hosted tools into the embedded runner, so spec-compliant clients like Codex no longer fail validation or silently lose strict tool enforcement.
• ·Gateway/OpenAI HTTP: restore default operator scopes for bearer-authenticated requests that omit `x-openclaw-scopes`, so headless `/v1/chat/completions` and session-history callers work again after the recent method-scope hardening. (#57596)
• ·Gateway/plugins: scope plugin-auth HTTP route runtime clients to read-only access and keep gateway-authenticated plugin routes on write scope, so plugin-owned webhook handlers do not inherit write-capable runtime access by default.
• ·Gateway/SecretRef: resolve restart token drift checks with merged service/runtime env sources and hard-fail unsupported mutable SecretRef plus OAuth-profile combinations so restart warnings and policy enforcement match runtime behavior. (#58141)
• ·Gateway/tools HTTP: tighten HTTP tool-invoke authorization so owner-only tools stay off HTTP invoke paths. (#57773)
• ·Harden async approval followup delivery in webchat-only sessions (#57359)
• ·Heartbeat/auth: prevent exec-event heartbeat runs from inheriting owner-only tool access from the session delivery target, so node exec output stays on the non-owner tool surface even when the target session belongs to the owner.
• ·Hooks/config: accept runtime channel plugin ids in `hooks.mappings[].channel` (for example `feishu`) instead of rejecting non-core channels during config validation. (#56226)
• ·Hooks/session routing: rebind hook-triggered `agent:` session keys to the actual target agent before isolated dispatch so dedicated hook agents keep their own session-scoped tool and plugin identity.
• ·Host exec/env: block additional request-scoped env overrides that can redirect Docker endpoints, trust roots, compiler include paths, package resolution, or Python environment roots during approved host runs.
• ·Image generation/build: write stable runtime alias files into `dist/` and route provider-auth runtime lookups through those aliases so image-generation providers keep resolving auth/runtime modules after rebuilds instead of crashing on missing hashed chunk files.
• ·iOS/Live Activities: mark the `ActivityKit` import in `LiveActivityManager.swift` as `@preconcurrency` so Xcode 26.4 / Swift 6 builds stop failing on strict concurrency checks. (#57180)
• ·LINE/ACP: add current-conversation binding and inbound binding-routing parity so `/acp spawn ... --thread here`, configured ACP bindings, and active conversation-bound ACP sessions work on LINE like the other conversation channels.
• ·LINE/markdown: preserve underscores inside Latin, Cyrillic, and CJK words when stripping markdown, while still removing standalone `_italic_` markers on the shared text-runtime path used by LINE and TTS. (#47465)
• ·Agents/failover: make overloaded same-provider retry count and retry delay configurable via `auth.cooldowns`, default to one retry with no delay, and document the model-fallback behavior.

Breaking

• ·Nodes/exec: remove the duplicated `nodes.run` shell wrapper from the CLI and agent `nodes` tool so node shell execution always goes through `exec host=node`, keeping node-specific capabilities on `nodes invoke` and the dedicated media/location/notify actions.
• ·Plugin SDK: deprecate the legacy provider compat subpaths plus the older bundled provider setup and channel-runtime compatibility shims, emit migration warnings, and keep the current documented `openclaw/plugin-sdk/*` entrypoints plus local `api.ts` / `runtime-api.ts` barrels as the forward path ahead of a future major-release removal.
• ·Skills/install and Plugins/install: built-in dangerous-code `critical` findings and install-time scan failures now fail closed by default, so plugin installs and gateway-backed skill dependency installs that previously succeeded may now require an explicit dangerous override such as `--dangerously-force-unsafe-install` to proceed.
• ·Gateway/auth: `trusted-proxy` now rejects mixed shared-token configs, and local-direct fallback requires the configured token instead of implicitly authenticating same-host callers.
• ·Gateway/node commands: node commands now stay disabled until node pairing is approved, so device pairing alone is no longer enough to expose declared node commands. (#57777)
• ·Gateway/node events: node-originated runs now stay on a reduced trusted surface, so notification-driven or node-triggered flows that previously relied on broader host/session tool access may need adjustment. (#57691)

Changes

• ·ACP/plugins: add an explicit default-off ACPX plugin-tools MCP bridge config, document the trust boundary, and harden the built-in bridge packaging/logging path so global installs and stdio MCP sessions work reliably. (#56867)
• ·Agents/LLM: add a configurable idle-stream timeout for embedded runner requests so stalled model streams abort cleanly instead of hanging until the broader run timeout fires. (#55072)
• ·Agents/MCP: materialize bundle MCP tools with provider-safe names (`serverName__toolName`), support optional `streamable-http` transport selection plus per-server connection timeouts, and preserve real tool results from aborted/error turns unless truncation explicitly drops them. (#49505)
• ·Android/notifications: add notification-forwarding controls with package filtering, quiet hours, rate limiting, and safer picker behavior for forwarded notification events. (#40175)
• ·Background tasks: turn tasks into a real shared background-run control plane instead of ACP-only bookkeeping by unifying ACP, subagent, cron, and background CLI execution under one SQLite-backed ledger, routing detached lifecycle updates through the executor seam, adding audit/maintenance/status visibility, tightening auto-cleanup and lost-run recovery, improving task awareness in internal status/tool surfaces, and clarifying the split between heartbeat/main-session automation and detached scheduled runs.
• ·Background tasks: add the first linear task flow control surface with `openclaw flows list|show|cancel`, keep manual multi-task flows separate from one-task auto-sync flows, and surface doctor recovery hints for obviously orphaned or broken flow/task linkage.
• ·Channels/QQ Bot: add QQ Bot as a bundled channel plugin with multi-account setup, SecretRef-aware credentials, slash commands, reminders, and media send/receive support. (#52986)
• ·Diffs: skip unused viewer-versus-file SSR preload work so `diffs` view-only and file-only runs do less render work while keeping mode outputs aligned. (#57909)
• ·Tasks: add a minimal SQLite-backed task flow registry plus task-to-flow linkage scaffolding, so orchestrated work can start gaining a first-class parent record without changing current task delivery behavior.
• ·Tasks: persist blocked state on one-task task flows and let the same flow reopen cleanly on retry, so blocked detached work can carry a parent-level reason and continue without fragmenting into a new job.
• ·Tasks: route one-task ACP and subagent updates through a parent task-flow owner context, so detached work can emerge back through the intended parent thread/session instead of speaking only as a raw child task.
• ·LINE/outbound media: add LINE image, video, and audio outbound sends on the LINE-specific delivery path, including explicit preview/tracking handling for videos while keeping generic media sends on the existing image-only route. (#45826)
• ·Matrix/history: add optional room history context for Matrix group triggers via `channels.matrix.historyLimit`, with per-agent watermarks and retry-safe snapshots so failed trigger retries do not drift into newer room messages. (#57022)
• ·Matrix/network: add explicit `channels.matrix.proxy` config for routing Matrix traffic through an HTTP(S) proxy, including account-level overrides and matching probe/runtime behavior. (#56931)
• ·Matrix/streaming: add draft streaming so partial Matrix replies update the same message in place instead of sending a new message for each chunk. (#56387)
• ·Matrix/threads: add per-DM `threadReplies` overrides and keep thread session isolation aligned with the effective room or DM thread policy from the triggering message onward. (#57995)
• ·MCP: add remote HTTP/SSE server support for `mcp.servers` URL configs, including auth headers and safer config redaction for MCP credentials. (#50396)
• ·Memory/QMD: add per-agent `memorySearch.qmd.extraCollections` so agents can opt into cross-agent session search without flattening every transcript collection into one shared QMD namespace.
• ·Microsoft Teams/member info: add a Graph-backed member info action so Teams automations and tools can resolve channel member details directly from Microsoft Graph. (#57528)
• ·Nostr/inbound DMs: verify inbound event signatures before pairing or sender-authorization side effects, so forged DM events no longer create pairing requests or trigger reply attempts.
• ·OpenAI/Responses: forward configured `text.verbosity` across Responses HTTP and WebSocket transports, surface it in `/status`, and keep per-agent verbosity precedence aligned with runtime behavior. (#47106)
• ·Pi/Codex: add native Codex web search support for embedded Pi runs, including config/docs/wizard coverage and managed-tool suppression when native Codex search is active. (#46579)
• ·Slack/exec approvals: add native Slack approval routing and approver authorization so exec approval prompts can stay in Slack instead of falling back to the Web UI or terminal.
• ·TTS: Add structured provider diagnostics and fallback attempt analytics. (#57954)
• ·WhatsApp/reactions: agents can now react with emoji on incoming WhatsApp messages, enabling more natural conversational interactions like acknowledging a photo with ❤️ instead of typing a reply.
• ·Agents/BTW: force `/btw` side questions to disable provider reasoning so Anthropic adaptive-thinking sessions stop failing with `No BTW response generated`. Fixes #55376.
• ·CLI/onboarding: reset the remote gateway URL prompt to the safe loopback default after declining a discovered endpoint, so onboarding does not keep a previously rejected remote URL. (#57828)
• ·Agents/exec defaults: honor per-agent `tools.exec` defaults when no inline directive or session override is present, so configured exec host, security, ask, and node settings actually apply. (#57689)
• ·Sandbox/networking: sanitize SSH subprocess env vars through the shared sandbox policy and route marketplace archive downloads plus Ollama discovery, auth, and pull requests through the guarded fetch path so sandboxed execution and remote fetches follow the repo's trust boundaries. (#57848, #57850)

Fixes

• ·Agents/OpenAI Responses: normalize raw bundled MCP tool schemas on the WebSocket/Responses path so bare-object, object-ish, and top-level union MCP tools no longer get rejected by OpenAI during tool registration. (#58299)
• ·ACP/security: replace ACP's dangerous-tool name override with semantic approval classes, so only narrow readonly reads/searches can auto-approve while indirect exec-capable and control-plane tools always require explicit prompt approval.
• ·ACP/sessions_spawn: register ACP child runs for completion tracking and lifecycle cleanup, and make registration-failure cleanup explicitly best-effort so callers do not assume an already-started ACP turn was fully aborted. (#40885)
• ·ACP/tasks: mark cleanly exited ACP runs as blocked when they end on deterministic write or authorization blockers, and wake the parent session with a follow-up instead of falsely reporting success.
• ·ACPX/runtime: derive the bundled ACPX expected version from the extension package metadata instead of hardcoding a separate literal, so plugin-local ACPX installs stop drifting out of health-check parity after version bumps. (#49089)
• ·Agents/Anthropic failover: treat Anthropic `api_error` payloads with `An unexpected error occurred while processing the response` as transient so retry/fallback can engage instead of surfacing a terminal failure. (#57441)
• ·Agents/compaction: keep late compaction-retry rejections handled after the aggregate timeout path wins without swallowing real pre-timeout wait failures, so timed-out retries no longer surface an unhandled rejection on later unsubscribe. (#57451)
• ·Agents/context pruning: count supplementary-plane CJK characters with the shared code-point-aware estimator so context pruning stops underestimating Japanese and Chinese text that uses Extension B ideographs. (#39985)
• ·Agents/Kimi: preserve already-valid Anthropic-compatible tool call argument objects while still clearing cached repairs when later trailing junk exceeds the repair allowance. (#54491)
• ·Agents/MCP: dispose bundled MCP runtimes after one-shot `openclaw agent --local` runs finish, while preserving bundled MCP state across in-run retries so local JSON runs exit cleanly without restarting stateful MCP tools mid-run.
• ·Agents/MCP: reuse bundled MCP runtimes across turns in the same session, while recreating them when MCP config changes and disposing stale runtimes cleanly on session rollover. (#55090)
• ·Agents/memory flush: keep daily memory flush files append-only during embedded attempts so compaction writes do not overwrite earlier notes. (#53725)
• ·Agents/sandbox: honor `tools.sandbox.tools.alsoAllow`, let explicit sandbox re-allows remove matching built-in default-deny tools, and keep sandbox explain/error guidance aligned with the effective sandbox tool policy. (#54492)
• ·Agents/sandbox: make remote FS bridge reads pin the parent path and open the file atomically in the helper so read access cannot race path resolution.
• ·Agents/silent turns: fail closed on silent memory-flush runs so narrated `NO_REPLY` self-talk cannot stream or finalize into external replies even when block streaming is enabled. (#52593)
• ·Agents/subagents: fix interim subagent runtime display so `/subagents list` and `/subagents info` stop inflating short runtimes and show second-level durations correctly. (#57739)
• ·Anthropic/OAuth: inject `/fast` `service_tier` hints for direct `sk-ant-oat-*` requests so OAuth-authenticated Anthropic runs stop missing the same overload-routing signal as API-key traffic. Fixes #55758.
• ·Anthropic/service tiers: support explicit `serviceTier` model params for direct Anthropic requests and let them override `/fast` defaults when both are set. (#45453)
• ·Auto-reply/fast: accept `/fast status` on the directive-only path, align help/status text with the documented `status|on|off` syntax, and keep current-state replies consistent across command surfaces. Fixes #46095.
• ·Azure OpenAI/custom providers: use the `azure-openai-responses` path for Azure custom providers so Azure OpenAI endpoints stay on the correct Responses integration surface. (#50851)
• ·BlueBubbles/iMessage: coalesce URL-only inbound messages with their link-preview balloon again so sharing a bare link no longer drops the URL from agent context.
• ·Browser/plugins: auto-enable the bundled browser plugin when browser config or browser tool policy already references it, and show a clearer CLI error when `plugins.allow` excludes `browser`.
• ·CI/dev checks: default local `pnpm check` to a lower-memory typecheck/lint path while keeping CI on the normal parallel path, and harden Telegram test typing/literals around native TypeScript-Go tooling crashes.
• ·Tasks: add a small task-flow runtime substrate for authoring layers with persisted wait targets and output bags, plus bundled skills/Lobster examples and richer `flows show` / `doctor` recovery hints for multi-task flow state. (#58336)
• ·Config/legacy cleanup: stop probing obsolete alternate legacy config names and service labels during local config/service detection, while keeping the active `~/.openclaw/openclaw.json` path canonical.
• ·Config/runtime: pin the first successful config load in memory for the running process and refresh that snapshot on successful writes/reloads, so hot paths stop reparsing `openclaw.json` between watcher-driven swaps.
• ·Config/SecretRef + Control UI: harden SecretRef redaction round-trip restore, block unsafe raw fallback (force Form mode when raw is unavailable), and preflight submitted-config SecretRefs before config write RPC persistence. (#58044)
• ·Config/Telegram: migrate removed `channels.telegram.groupMentionsOnly` into `channels.telegram.groups["*"].requireMention` on load so legacy configs no longer crash at startup. (#55336)
• ·Config/update: stop `openclaw doctor` write-backs from persisting plugin-injected channel defaults, so `openclaw update` no longer seeds config keys that later break service refresh validation. (#56834)
• ·Control UI/agents: auto-load agent workspace files on initial Files panel open, and populate overview model/workspace/fallbacks from effective runtime agent metadata so defaulted models no longer show as `Not set`. (#56637)
• ·Control UI/slash commands: make `/steer` and `/redirect` work from the chat command palette with visible pending state for active-run `/steer`, correct redirected-run tracking, and a single canonical `/steer` entry in the command menu. (#54625)
• ·Cron/announce: preserve all deliverable text payloads for announce mode instead of collapsing to the last chunk, so multi-line cron reports deliver in full to Telegram forum topics.
• ·Cron/isolated sessions: carry the full live-session provider, model, and auth-profile selection across retry restarts so cron jobs with model overrides no longer fail or loop on mid-run model-switch requests. (#57972)
• ·Diffs/config: preserve schema-shaped plugin config parsing from `diffsPluginConfigSchema.safeParse()`, so direct callers keep `defaults` and `security` sections instead of receiving flattened tool defaults. (#57904)
• ·Diffs: fall back to plain text when `lang` hints are invalid during diff render and viewer hydration, so bad or stale language values no longer break the diff viewer. (#57902)
• ·Discord/voice: enforce the same guild channel and member allowlist checks on spoken voice ingress before transcription, so joined voice channels no longer accept speech from users outside the configured Discord access policy.
• ·Docker/setup: force BuildKit for local image builds (including sandbox image builds) so `./docker-setup.sh` no longer fails on `RUN --mount=...` when hosts default to Docker's legacy builder. (#56681)
• ·Docs/anchors: fix broken English docs links and make Mint anchor audits run against the English-source docs tree. (#57039)
• ·Doctor/plugins: skip false Matrix legacy-helper warnings when no migration plans exist, and keep bundled `enabledByDefault` plugins in the gateway startup set. (#57931)
• ·Exec approvals/macOS: unwrap `arch` and `xcrun` before deriving shell payloads and allow-always patterns, so wrapper approvals stay bound to the carried command instead of the outer carrier.
• ·Exec approvals: unwrap `caffeinate` and `sandbox-exec` before persisting allow-always trust so later shell payload changes still require a fresh approval.
• ·Exec/approvals: infer Discord and Telegram exec approvers from existing owner config when `execApprovals.approvers` is unset, extend the default approval window to 30 minutes, and clarify approval-unavailable guidance so approvals do not appear to silently disappear.
• ·Exec/approvals: keep `awk` and `sed` family binaries out of the low-risk `safeBins` fast path, and stop doctor profile scaffolding from treating them like ordinary custom filters.
• ·Exec/env: block proxy, TLS, and Docker endpoint env overrides in host execution so request-scoped commands cannot silently reroute outbound traffic or trust attacker-supplied certificate settings.
• ·Exec/env: block Python package index override variables from request-scoped host exec environment sanitization so package fetches cannot be redirected through a caller-supplied index.
• ·Exec/node: stop gateway-side workdir fallback from rewriting explicit `host=node` cwd values to the gateway filesystem, so remote node exec approval and runs keep using the intended node-local directory. (#50961)
• ·Exec/runtime: default implicit exec to `host=auto`, resolve that target to sandbox only when a sandbox runtime exists, keep explicit `host=sandbox` fail-closed without sandbox, and show `/exec` effective host state in runtime status/docs.
• ·Exec: fail closed when the implicit sandbox host has no sandbox runtime, and stop denied async approval followups from reusing prior command output from the same session. (#56800)
• ·Feishu/groups: keep quoted replies and topic bootstrap context aligned with group sender allowlists so only allowlisted thread messages seed agent context.
• ·Gateway/attachments: offload large inbound images without leaking `media://` markers into text-only runs, preserve mixed attachment order for model input/transcripts, and fail closed when model image capability cannot be resolved. (#55513)
• ·Gateway/auth: keep shared-auth rate limiting active during WebSocket handshake attempts even when callers also send device-token candidates, so bogus device-token fields no longer suppress shared-secret brute-force tracking.
• ·Gateway/auth: reject mismatched browser `Origin` headers on trusted-proxy HTTP operator requests while keeping origin-less headless proxy clients working.
• ·Gateway/device tokens: disconnect active device sessions after token rotation so newly rotated credentials revoke existing live connections immediately instead of waiting for those sockets to close naturally.
• ·Gateway/health: carry webhook-vs-polling account mode from channel descriptors into runtime snapshots so passive channels like LINE and BlueBubbles skip false stale-socket health failures. (#47488)
• ·Gateway/pairing: restore QR bootstrap onboarding handoff so fresh `/pair qr` iPhone setup can auto-approve the initial node pairing, receive a reusable node device token, and stop retrying with spent bootstrap auth. (#58382)
• ·Gateway/OpenAI compatibility: accept flat Responses API function tool definitions on `/v1/responses` and preserve `strict` when normalizing hosted tools into the embedded runner, so spec-compliant clients like Codex no longer fail validation or silently lose strict tool enforcement.
• ·Gateway/OpenAI HTTP: restore default operator scopes for bearer-authenticated requests that omit `x-openclaw-scopes`, so headless `/v1/chat/completions` and session-history callers work again after the recent method-scope hardening. (#57596)
• ·Gateway/plugins: scope plugin-auth HTTP route runtime clients to read-only access and keep gateway-authenticated plugin routes on write scope, so plugin-owned webhook handlers do not inherit write-capable runtime access by default.
• ·Gateway/SecretRef: resolve restart token drift checks with merged service/runtime env sources and hard-fail unsupported mutable SecretRef plus OAuth-profile combinations so restart warnings and policy enforcement match runtime behavior. (#58141)
• ·Gateway/tools HTTP: tighten HTTP tool-invoke authorization so owner-only tools stay off HTTP invoke paths. (#57773)
• ·Harden async approval followup delivery in webchat-only sessions (#57359)
• ·Heartbeat/auth: prevent exec-event heartbeat runs from inheriting owner-only tool access from the session delivery target, so node exec output stays on the non-owner tool surface even when the target session belongs to the owner.
• ·Hooks/config: accept runtime channel plugin ids in `hooks.mappings[].channel` (for example `feishu`) instead of rejecting non-core channels during config validation. (#56226)
• ·Hooks/session routing: rebind hook-triggered `agent:` session keys to the actual target agent before isolated dispatch so dedicated hook agents keep their own session-scoped tool and plugin identity.
• ·Host exec/env: block additional request-scoped env overrides that can redirect Docker endpoints, trust roots, compiler include paths, package resolution, or Python environment roots during approved host runs.
• ·Image generation/build: write stable runtime alias files into `dist/` and route provider-auth runtime lookups through those aliases so image-generation providers keep resolving auth/runtime modules after rebuilds instead of crashing on missing hashed chunk files.
• ·iOS/Live Activities: mark the `ActivityKit` import in `LiveActivityManager.swift` as `@preconcurrency` so Xcode 26.4 / Swift 6 builds stop failing on strict concurrency checks. (#57180)
• ·LINE/ACP: add current-conversation binding and inbound binding-routing parity so `/acp spawn ... --thread here`, configured ACP bindings, and active conversation-bound ACP sessions work on LINE like the other conversation channels.
• ·LINE/markdown: preserve underscores inside Latin, Cyrillic, and CJK words when stripping markdown, while still removing standalone `_italic_` markers on the shared text-runtime path used by LINE and TTS. (#47465)
• ·LINE/status: stop `openclaw status` from warning about missing credentials when sanitized LINE snapshots are already configured, while still surfacing whether the missing field is the token or secret. (#45701)
• ·macOS/local gateway: stop OpenClaw.app from killing healthy local gateway listeners after startup by recognizing the current `openclaw-gateway` process title and using the current `openclaw gateway` launch shape.
• ·macOS/wide-area discovery: switch gateway discovery to Tailscale MagicDNS names so Mac clients recover more reliably across changing tailnet IPs. (#57833)
• ·Matrix/CLI send: start one-off Matrix send clients before outbound delivery so `openclaw message send --channel matrix` restores E2EE in encrypted rooms instead of sending plain events. (#57936)
• ·Matrix/context: filter fetched room context by sender allowlists so reply and thread context lookup no longer pulls non-allowlisted messages into agent context. (#58376)
• ·Matrix/delivery recovery: treat Synapse `User not in room` replay failures as permanent during startup recovery so poisoned queued messages move to `failed/` instead of crash-looping Matrix after restart. (#57426)
• ·Matrix/direct rooms: recover fresh auto-joined 1:1 DMs without eagerly persisting invite-only `m.direct` mappings, while keeping named, aliased, and explicitly configured rooms on the room path. (#58024)
• ·Matrix/direct rooms: stop trusting remote `is_direct`, honor explicit local `is_direct: false` for discovered DM candidates, and avoid extra member-state lookups for shared rooms so DM routing and repair stay aligned. (#57124)
• ·Matrix/DM threads: keep strict unnamed fresh-invite rooms promotable even when Matrix omits the optional direct hint, preserve repair-failed local DM promotions while still revalidating later room metadata, and keep both bound and thread-isolated Matrix sessions reporting the correct route policy. (#58099)
• ·Matrix/plugin loading: ship and source-load the crypto bootstrap runtime sidecar correctly so current `main` stops warning about failed Matrix bootstrap loads and `matrix/index` plugin-id mismatches on every invocation. (#53298)
• ·Mattermost/websocket: detect stale Mattermost WebSocket sessions after bot disable/enable cycles so monitoring reconnects cleanly instead of silently staying stale. (#53604)
• ·Media/downloads: stop forwarding auth and cookie headers across cross-origin redirects during media saves, while preserving safe request headers for same-origin redirect chains.
• ·Media/images: reject oversized decoded image inputs before metadata and resize backends run, so tiny compressed image bombs fail early instead of exhausting gateway memory. (#58226)
• ·Memory/doctor: probe QMD availability from the agent workspace too, so `openclaw doctor` no longer falsely reports relative `memory.qmd.command` configs as broken while runtime search still works.
• ·Memory/doctor: suppress the orphan transcript cleanup warning when QMD session indexing is enabled, so doctor no longer suggests deleting transcript history that QMD still uses for recall. (#40584)
• ·Memory/FTS: add configurable trigram tokenization plus short-CJK substring fallback so memory search can find Chinese, Japanese, and Korean text without breaking mixed long-and-short queries.
• ·Memory/FTS: keep provider-less keyword hits visible at the default memory-search threshold, so FTS-only recall works without requiring `--min-score 0`. (#56473)
• ·Memory/LanceDB: resolve runtime dependency manifest lookup from the bundled `extensions/memory-lancedb` path (including flattened dist chunks) so startup no longer fails with a missing `@lancedb/lancedb` dependency error. (#56623)
• ·Memory/QMD: add `memory.qmd.searchTool` as an exact mcporter tool override, so custom QMD MCP tools such as `hybrid_search` can be used without weakening the validated `searchMode` config surface. (#27801)
• ·Memory/QMD: honor `memory.qmd.update.embedInterval` even when regular QMD update cadence is disabled or slower by arming a dedicated embed-cadence maintenance timer, while avoiding redundant timers when regular updates are already frequent enough. (#37326)
• ·Memory/QMD: include deduplicated default plus per-agent `memorySearch.extraPaths` when building QMD custom collections, so shared and agent-specific extra roots both get indexed consistently. (#57315)
• ·Memory/QMD: keep `memory_search` session-hit paths roundtrip-safe when exported session markdown lives under the workspace `qmd/` directory, so `memory_get` can read the exact returned path instead of failing on the generic `qmd/sessions/...` alias. (#43519)
• ·Memory/QMD: keep `qmd embed` active in `search` mode too, so BM25-first setups still build a complete index for later vector and hybrid retrieval. (#54509)
• ·Memory/QMD: keep reset and deleted session transcripts in QMD session export so daily session resets do not silently drop most historical recall from `memory_search`. (#30220)
• ·Memory/QMD: pass a direct-session key on `openclaw memory search` so CLI QMD searches no longer get denied as `session=<none>` under direct-only scope defaults. (#43517)
• ·Memory/QMD: point `QMD_CONFIG_DIR` at the nested `xdg-config/qmd` directory so per-agent collection config resolves correctly. (#39078)
• ·Memory/QMD: preserve explicit `start_line` and `end_line` metadata from mcporter query results so `memory search` hits keep the real snippet offsets instead of falling back to the snippet header. (#47960)
• ·Memory/QMD: rebind collections when QMD reports a changed pattern but omits path metadata, so config pattern changes stop being silently ignored on restart. (#49897)
• ·Memory/QMD: resolve slugified `memory_search` file hints back to the indexed filesystem path before returning search hits, so `memory_get` works again for mixed-case and spaced paths. (#50313)
• ·Memory/QMD: send MCP `query` collection filters as the upstream `collections` array instead of the legacy singular `collection` field, so mcporter-backed QMD 1.1+ searches still scope correctly after the unified `query` tool migration. (#54728)
• ·Memory/QMD: serialize cross-process `qmd embed` runs behind a shared lock and stagger periodic embed timers so multi-agent QMD collections stop thundering-herding on startup and every maintenance interval.
• ·Memory/QMD: stop rewriting Han/CJK BM25 queries before `qmd search`, so OpenClaw search semantics match direct QMD results for mixed and spaced Chinese queries.
• ·Memory/QMD: surface degraded vector status from `qmd status` so `openclaw memory status --deep` warns when semantic search is unavailable because the index still has `0` vectors. Fixes #28169.
• ·Memory/QMD: treat null-byte collection corruption the same when QMD surfaces it as `ENOENT`, so managed-collection repair still rebuilds and retries instead of leaving QMD stuck on a broken path.
• ·Memory/QMD: warn explicitly when `memory.backend=qmd` is configured but the `qmd` binary is missing, so doctor and runtime fallback no longer fail as a silent builtin downgrade. (#50439)
• ·Memory/QMD: weight CJK-heavy text correctly when estimating chunk sizes, preserve surrogate-pair characters during fine splits, and keep long Latin lines on the old chunk boundaries so memory indexing produces better-sized chunks for CJK notes. (#40271)
• ·Memory/session indexer: include `.jsonl.reset.*` and `.jsonl.deleted.*` transcripts in the memory host session scan while still excluding `.jsonl.bak.*` compaction backups and lock files, so memory search sees archived session history without duplicating stale snapshots.
• ·Microsoft Teams/threads: filter fetched thread history by sender allowlists so thread context seeding no longer pulls messages from disallowed users. (#57723)
• ·OpenAI/Codex fast mode: map `/fast` to priority processing on native OpenAI and Codex Responses endpoints instead of rewriting reasoning settings, and document the exact endpoint and override behavior.
• ·Outbound media/local files: piggyback host-local `MEDIA:` reads on the configured fs policy instead of a separate media-root check, so generated files outside the workspace can send when `tools.fs.workspaceOnly=false` while plaintext-like host files stay blocked by the outbound media allowlist.
• ·Pairing: enforce pending request limits per account instead of per shared channel queue, so one account's outstanding pairing challenges no longer block new pairing on other accounts.
• ·Plugins/ClawHub: sanitize temporary archive filenames for scoped package names and slash-containing skill slugs so `openclaw plugins install @scope/name` no longer fails with `ENOENT` during archive download. (#56452)
• ·Plugins/CLI: add descriptor-backed lazy plugin CLI registration so Matrix can keep its CLI module lazy-loaded without dropping `openclaw matrix ...` from parse-time command registration. (#57165)
• ·Plugins/CLI: collect root-help plugin descriptors through a dedicated non-activating CLI metadata path so enabled plugins keep validated config semantics without triggering runtime-only plugin registration work, while preserving runtime CLI command registration for legacy channel plugins that still wire commands from full registration. (#57294)
• ·Plugins/facades: guard bundled plugin facade loads with a cache-first sentinel so circular re-entry stops crashing `xai`, `sglang`, and `vllm` during gateway plugin startup. (#57508)
• ·Plugins/Matrix: mirror the Matrix crypto WASM runtime dependency into the root packaged install and enforce root/plugin dependency parity so bundled Matrix E2EE crypto resolves correctly in shipped builds. (#57163)
• ·Plugins/startup: block workspace `.env` from overriding `OPENCLAW_BUNDLED_PLUGINS_DIR`, so bundled plugin trust roots only come from inherited runtime env or package resolution instead of repo-local dotenv files.
• ·Sandbox/browser: install `fonts-noto-cjk` in the sandbox browser image so screenshots render Chinese, Japanese, and Korean text correctly instead of tofu boxes. Fixes #35597.
• ·Security/LINE: make webhook signature validation run the timing-safe compare even when the supplied signature length is wrong, closing a small timing side-channel. (#55663)
• ·Sessions/Feishu: preserve conversation ids that legitimately embed `:topic:` in shared session helper parsing, while keeping Telegram topic session parsing intact. (#58100)
• ·Slack/status reactions: add a reaction lifecycle for queued, thinking, tool, done, and error phases in Slack monitors, with safer cleanup so queued ack reactions stay correct across silent runs, pre-reply failures, and delayed transitions. (#56430)
• ·Status/node-only hosts: teach `openclaw status` to handle node-only hosts on current `main` without the old mixed gateway assumptions. (#56718)
• ·Status: fix cache hit rate exceeding 100% by deriving denominator from prompt-side token fields instead of potentially undersized totalTokens. Fixes #26643.
• ·Telegram/audio: transcode Telegram voice-note `.ogg` attachments before the local `whisper-cli` auto fallback runs, and keep mention-preflight transcription enabled in auto mode when `tools.media.audio` is unset.
• ·Telegram/forum topics: restore reply routing to the active topic and keep ACP `sessions_spawn(..., thread=true, mode="session")` bound to that same topic instead of falling back to root chat or losing follow-up routing. (#56060)
• ·Telegram/media: allow RFC 2544 benchmark-range Telegram CDN resolutions during media downloads, so voice messages, PDFs, and other attachments no longer fail with `Failed to download media`. (#57624)
• ·Telegram/native commands: prefix native command menu callback payloads and preserve `CommandSource: "native"` when Telegram replays them through callback queries, so `/fast` and other native command menus keep working even when text-command routing is disabled.
• ·Telegram/polling: keep the watchdog from aborting long-running reply delivery by treating recent non-polling API activity as bounded liveness instead of a hard stall. (#56343)
• ·Tools/web_fetch: add an explicit trusted env-proxy path for proxy-only installs while keeping strict SSRF fetches on the pinned direct path, so trusted proxy routing does not weaken strict destination binding. (#50650)
• ·Tools/web_search: localize the shared search cache to module scope so same-process global symbol lookups can no longer inspect or mutate cached web-search responses.
• ·TTS/Microsoft: auto-switch the default Edge voice to Chinese for CJK-dominant text without overriding explicitly selected Microsoft voices. (#52355)
• ·TTS: Restore 3.28 schema compatibility and fallback observability. (#57953)
• ·TUI/chat: keep optimistic outbound user messages visible during active runs by deferring local-run binding until the first gateway chat event reveals the real run id, preventing premature history reloads from wiping pending local sends. (#54722)
• ·TUI/model picker: keep searchable `/model` and `/models` input mode from hijacking `j`/`k` as navigation keys, and harden width bounds under `m`-filtered model lists so search no longer crashes on long rows. (#30156)
• ·Voice Call/media stream: cap inbound WebSocket frame size before `start` validation so oversized pre-start frames are dropped before JSON parsing.
• ·Voice call/Plivo: pin stored callback bases to the configured public webhook URL so later call-control redirects stay on the intended origin even if webhook transport metadata differs.
• ·Web UI/markdown: stop bare auto-links from swallowing adjacent CJK text while preserving valid mixed-script path and query characters in rendered links. (#48410)
• ·Approvals/UI: keep the newest pending approval at the front of the Control UI queue so approving one request does not accidentally target an older expired id.
• ·Auth profiles/OAuth: refresh runtime auth snapshots when saving rotated credentials so OAuth providers do not reuse consumed refresh tokens after the first token rotation. Fixes #55389.
• ·Browser/screenshot: use `fromSurface: false` in raw CDP screenshots to avoid a Chromium compositor bug that drops cross-origin image textures (QR codes, CDN assets), and preserve pre-existing device emulation state across full-page viewport expansion. (#54358)
• ·ClawDock/docs: move the helper scripts to `scripts/clawdock`, publish ClawDock as a first-class docs page on the docs site, and document reinstalling local helper copies from the new raw GitHub path. (#23912)
• ·Control UI/gateway: clear queued browser connect timeouts on client stop so aborted or replaced gateway clients do not send delayed connect requests after shutdown. (#57338)
• ·Control UI/gateway: reconnect the browser client when gateway event sequence gaps are detected, so stale non-chat state recovers automatically instead of only telling the user to refresh. (#23912)
• ·Exec approvals/channels: unify Discord and Telegram exec approval runtime handling, move approval buttons onto the shared interactive reply model, and fix Telegram approval buttons and typed `/approve` commands so configured approvers can resolve requests reliably again. (#57516)
• ·Gateway/SQLite transient handling: keep unhandled `SQLITE_CANTOPEN`, `SQLITE_BUSY`, `SQLITE_LOCKED`, and `SQLITE_IOERR` failures non-fatal in the global rejection handler so macOS LaunchAgent restarts do not enter a crash-throttle loop. (#57018)
• ·Hooks/plugins/skills: block workspace `.env` overrides for bundled root directories so workspace startup cannot redirect bundled trust roots away from the packaged defaults.
• ·LINE/webhooks: cap shared concurrent pre-verify webhook body reads so excess requests are rejected before entering the LINE body handler.
• ·Memory/QMD: preserve explicit custom collection names for shared paths outside the agent workspace so `memory_search` stops appending `-<agentId>` to externally managed QMD collections. (#52539)
• ·Memory/builtin: keep memory-file indexing active in FTS-only mode (no embedding provider) so forced reindexes no longer swap in an empty index and wipe existing memory chunks. (#42714)
• ·Nostr/config: redact `channels.nostr.privateKey` in config snapshots and Control UI config views, so Nostr signing keys no longer appear in plain text.
• ·Plugin approvals: accept unique short approval-id prefixes on `plugin.approval.resolve`, matching exec approvals and restoring `/approve` fallback flows on chat approval surfaces.
• ·SSH sandbox/upload: reject workspace symlinks that resolve outside the uploaded tree before syncing to the remote sandbox, so later agent writes cannot be redirected through escaped links.
• ·Slack/interactive replies: resolve Slack Block Kit reply delivery from both authored `channelData.slack.blocks` payloads and directive-generated interactive replies, and keep Slack button styles mapped onto valid Block Kit button rendering so interactive replies stop dropping on Slack-specific delivery paths.
• ·Subagents/announcements: preserve the requester agent id for inline deterministic tool spawns so named agents without channel bindings can still announce completions through the correct owner session. (#55437)
• ·Telegram/Anthropic streaming: replace raw invalid stream-order provider errors with a safe retry message so internal `message_start/message_stop` failures do not leak into chats. (#55408)
• ·Tlon/media: route inbound image downloads through the shared media store, cap each download at 6 MB, and stop after 8 images per message so large Tlon posts no longer balloon local media storage.
• ·Agents/live switch: stop transient cron and subagent model overrides from being misread as persisted live-session switches, so isolated runs no longer fail with `LiveSessionModelSwitchError`.
• ·Agents/tool-call repair: recover malformed Kimi/OpenRouter tool-call argument streams when provider preambles appear before JSON payloads, and fail closed on non-tool leading text so fragment strings do not leak into filesystem path arguments during sub-agent runs. (#56560)
• ·Gateway/startup: keep configured primary-model warmup on the static model path so container boots do not snapshot-load provider runtime graphs just to validate a configured model.
• ·OpenAI/Responses: omit disabled reasoning payloads across OpenAI, Codex, and Azure OpenAI request builders so GPT-5 endpoints no longer reject `reasoning.effort: "none"`. (#58208)
• ·WhatsApp/outbound: restore runtime send/action routing and outbound compatibility after the recent channel seam refactor so outbound sends, reactions, and related media actions keep reaching the active session.
• ·xAI/Responses: normalize image-bearing tool results for xAI responses payloads, including OpenResponses-style `input_image.source` parts, so image tool replays no longer 422 on the follow-up turn. (#58017)
• ·Zalo/webhooks: scope replay dedupe to the authenticated target so one configured account can no longer cause same-id inbound events for another target to be dropped.
• ·Plugins/prompt build: preserve the highest-priority `systemPrompt` when merging `before_prompt_build` hook results instead of letting lower-priority hooks overwrite it. (#58375)
• ·Tlon/settings migration: preserve explicit empty-array settings during migration so restart-time reseeding no longer restores older file-config values. (#58370)
• ·Plugins/marketplace: harden marketplace archive installs by surfacing guarded download failures as structured install errors and deriving temp filenames from the final resolved URL. (#58267)
• ·UI/DOM safety: build the chat delete-confirm popover and Canvas Host fallback status line with DOM nodes instead of injected HTML strings. (#58269, #58266)
• ·Media/file handling: create image temp work directories under the shared OpenClaw temp root and stop widening allowed local media roots from reply or tool source paths, keeping local media access limited to configured and agent-scoped roots. (#58270, #57770)
• ·Telegram/security: migrate legacy pairing `allowFrom` state to the `default` account only and gate group voice-message preflight transcription on sender authorization so unauthorized senders cannot trigger paid transcription before being dropped. (#58165, #57566)
• ·Exec approvals: stop shell init-file flags from matching persisted script-path approvals, detect command-carrier inline eval in tools like `awk`, `find`, `xargs`, `make`, and `sed`, and treat the awk family as interpreter-like so allow-always decisions no longer persist interpreter paths. (#58369, #57842, #57772)
• ·Voice call/Telnyx: canonicalize verified webhook signatures before deriving replay keys so equivalent Base64 and Base64URL encodings dedupe correctly. (#57829)
• ·Gateway/HTTP trust boundaries: ignore self-declared bearer scopes, deny dangerous HTTP tool-invoke paths by default, require write scope on `/v1/embeddings`, and bind OpenAI-compatible `/v1/chat/completions` plus `/v1/responses` ingress as non-owner so external HTTP callers cannot self-upgrade access. (#57783, #57771, #57721, #57769, #57778)
• ·Gateway/trusted config and bootstrap: clear self-declared scopes for device-less `trusted-proxy` WebSocket connects and trim the Control UI bootstrap payload to only the fields needed before the normal handshake. (#57692, #57727)
• ·Skills and workspace safety: replace raw skill-file reads with a symlink-safe, root-confined loader and pin workspace-only `apply_patch` delete and directory-creation mutations to verified workspace roots so path rebind races fail closed. (#57519, #56016)
• ·Env and filesystem hardening: block credential and gateway auth env vars from workspace `.env` files, always strip dangerous inherited host env vars such as `BROWSER` and `GIT_EDITOR`, and keep sensitive host paths and OpenClaw state roots blocked even when external sandbox bind sources are allowed. (#57767, #57559, #56024)
• ·OpenShell and ACP file boundaries: skip symlinks and preserve trusted host-only directories during OpenShell mirror sync, and route ACP attachment reads through the shared attachment cache so local files outside allowed roots are no longer forwarded. (#57693, #57690)
• ·Channel/webhook authorization: skip Discord audio preflight transcription for unauthorized guild senders, add a shared pre-auth in-flight guard to Synology Chat webhooks, and validate Microsoft Teams bearer auth before JSON body parsing. (#57695, #57722, #57686)
• ·Infra/randomness: replace `Math.random()` in affected identifier and delay-jitter paths with shared secure-random helpers, including UI UUID generation. (#57744)

Breaking

• ·Providers/Qwen: remove the deprecated `qwen-portal-auth` OAuth integration for `portal.qwen.ai`; migrate to Model Studio with `openclaw onboard --auth-choice modelstudio-api-key`. (#52709)
• ·Config/Doctor: drop automatic config migrations older than two months; very old legacy keys now fail validation instead of being rewritten on load or by `openclaw doctor`.

Changes

• ·xAI/tools: move the bundled xAI provider to the Responses API, add first-class `x_search`, and auto-enable the xAI plugin from owned web-search and tool config so bundled Grok auth/configured search flows work without manual plugin toggles. (#56048)
• ·xAI/onboarding: let the bundled Grok web-search plugin offer optional `x_search` setup during `openclaw onboard` and `openclaw configure --section web`, including an x_search model picker with the shared xAI key.
• ·MiniMax: add image generation provider for `image-01` model, supporting generate and image-to-image editing with aspect ratio control. (#54487)
• ·Plugins/hooks: add async `requireApproval` to `before_tool_call` hooks, letting plugins pause tool execution and prompt the user for approval via the exec approval overlay, Telegram buttons, Discord interactions, or the `/approve` command on any channel. The `/approve` command now handles both exec and plugin approvals with automatic fallback. (#55339)
• ·ACP/channels: add current-conversation ACP binds for Discord, BlueBubbles, and iMessage so `/acp spawn codex --bind here` can turn the current chat into a Codex-backed workspace without creating a child thread, and document the distinction between chat surface, ACP session, and runtime workspace.
• ·OpenAI/apply_patch: enable `apply_patch` by default for OpenAI and OpenAI Codex models, and align its sandbox policy access with `write` permissions.
• ·Plugins/CLI backends: move bundled Claude CLI, Codex CLI, and Gemini CLI inference defaults onto the plugin surface, add bundled Gemini CLI backend support, and replace `gateway run --claude-cli-logs` with generic `--cli-backend-logs` while keeping the old flag as a compatibility alias.
• ·Plugins/startup: auto-load bundled provider and CLI-backend plugins from explicit config refs, so bundled Claude CLI, Codex CLI, and Gemini CLI message-provider setups no longer need manual `plugins.allow` entries.
• ·Podman: simplify the container setup around the current rootless user, install the launch helper under `~/.local/bin`, and document the host-CLI `openclaw --container <name> ...` workflow instead of a dedicated `openclaw` service user.
• ·Slack/tool actions: add an explicit `upload-file` Slack action that routes file uploads through the existing Slack upload transport, with optional filename/title/comment overrides for channels and DMs.
• ·Message actions/files: start unifying file-first sends on the canonical `upload-file` action by adding explicit support for Microsoft Teams and Google Chat, and by exposing BlueBubbles file sends through `upload-file` while keeping the legacy `sendAttachment` alias.
• ·Plugins/Matrix TTS: send auto-TTS replies as native Matrix voice bubbles instead of generic audio attachments. (#37080)
• ·CLI: add `openclaw config schema` to print the generated JSON schema for `openclaw.json`. (#54523)
• ·Config/TTS: auto-migrate legacy speech config on normal reads and secret resolution, keep legacy diagnostics for Doctor, and remove regular-mode runtime fallback for old bundled `tts.<provider>` API-key shapes.
• ·Memory/plugins: move the pre-compaction memory flush plan behind the active memory plugin contract so `memory-core` owns flush prompts and target-path policy instead of hardcoded core logic.
• ·MiniMax: trim model catalog to M2.7 only, removing legacy M2, M2.1, M2.5, and VL-01 models. (#54487)
• ·Plugins/runtime: expose `runHeartbeatOnce` in the plugin runtime `system` namespace so plugins can trigger a single heartbeat cycle with an explicit delivery target override (e.g. `heartbeat: { target: "last" }`). (#40299)
• ·Agents/compaction: preserve the post-compaction AGENTS refresh on stale-usage preflight compaction for both immediate replies and queued followups. (#49479)
• ·Agents/compaction: surface safeguard-specific cancel reasons and relabel benign manual `/compact` no-op cases as skipped instead of failed. (#51072)
• ·Docs: add `pnpm docs:check-links:anchors` for Mintlify anchor validation while keeping `scripts/docs-link-audit.mjs` as the stable link-audit entrypoint. (#55912)
• ·Tavily: mark outbound API requests with `X-Client-Source: openclaw` so Tavily can attribute OpenClaw-originated traffic. (#55335)

Fixes

• ·Agents/Anthropic: recover unhandled provider stop reasons (e.g. `sensitive`) as structured assistant errors instead of crashing the agent run. (#56639)
• ·Google/models: resolve Gemini 3.1 pro, flash, and flash-lite for all Google provider aliases by passing the actual runtime provider ID and adding a template-provider fallback; fix flash-lite prefix ordering. (#56567)
• ·OpenAI Codex/image tools: register Codex for media understanding and route image prompts through Codex instructions so image analysis no longer fails on missing provider registration or missing `instructions`. (#54829)
• ·Agents/image tool: restore the generic image-runtime fallback when no provider-specific media-understanding provider is registered, so image analysis works again for providers like `openrouter` and `minimax-portal`. (#54858)
• ·WhatsApp: fix infinite echo loop in self-chat DM mode where the bot's own outbound replies were re-processed as new inbound user messages. (#54570)
• ·Telegram/splitting: replace proportional text estimate with verified HTML-length search so long messages split at word boundaries instead of mid-word; gracefully degrade when tag overhead exceeds the limit. (#56595)
• ·Telegram/delivery: skip whitespace-only and hook-blanked text replies in bot delivery to prevent GrammyError 400 empty-text crashes. (#56620)
• ·Telegram/send: validate `replyToMessageId` at all four API sinks with a shared normalizer that rejects non-numeric, NaN, and mixed-content strings. (#56587)
• ·Mistral: normalize OpenAI-compatible request flags so official Mistral API runs no longer fail with remaining `422 status code (no body)` chat errors.
• ·Control UI/config: keep sensitive raw config hidden by default, replace the blank blocked editor with an explicit reveal-to-edit state, and restore raw JSON editing without auto-exposing secrets. Fixes #55322.
• ·CLI/zsh: defer `compdef` registration until `compinit` is available so zsh completion loads cleanly with plugin managers and manual setups. (#56555)
• ·BlueBubbles/debounce: guard debounce flush against null message text by sanitizing at the enqueue boundary and adding an independent combiner guard. (#56573)
• ·Auto-reply: suppress JSON-wrapped `{"action":"NO_REPLY"}` control envelopes before channel delivery with a strict single-key detector; preserves media when text is only a silent envelope. (#56612)
• ·ACP/ACPX agent registry: align OpenClaw's ACPX built-in agent mirror with the latest `openclaw/acpx` command defaults and built-in aliases, pin versioned `npx` built-ins to exact versions, and stop unknown ACP agent ids from falling through to raw `--agent` command execution on the MCP-proxy path. (#28321)
• ·Security/audit: extend web search key audit to recognize Gemini, Grok/xAI, Kimi, Moonshot, and OpenRouter credentials via a boundary-safe bundled-web-search registry shim. (#56540)
• ·Docs/FAQ: remove broken Xfinity SSL troubleshooting cross-links from English and zh-CN FAQ entries — both sections already contain the full workaround inline. (#56500)
• ·Telegram: deliver verbose tool summaries inside forum topic sessions again, so threaded topic chats now match DM verbose behavior. (#43236)
• ·BlueBubbles/CLI agents: restore inbound prompt image refs for CLI routed turns, reapply embedded runner image size guardrails, and cover both CLI image transport paths with regression tests. (#51373)
• ·BlueBubbles/groups: optionally enrich unnamed participant lists with local macOS Contacts names after group gating passes, so group member context can show names instead of only raw phone numbers.
• ·Discord/reconnect: drain stale gateway sockets, clear cached resume state before forced fresh reconnects, and fail closed when old sockets refuse to die so Discord recovery stops looping on poisoned resume state. (#54697)
• ·iMessage: stop leaking inline `[[reply_to:...]]` tags into delivered text by sending `reply_to` as RPC metadata and stripping stray directive tags from outbound messages. (#39512)
• ·CLI/plugins: make routed commands use the same auto-enabled bundled-channel snapshot as gateway startup, so configured bundled channels like Slack load without requiring a prior config rewrite. (#54809)
• ·CLI/message send: write manual `openclaw message send` deliveries into the resolved agent session transcript again by always threading the default CLI agent through outbound mirroring. (#54187)
• ·CLI/onboarding: show the Kimi Code API key option again in the Moonshot setup menu so the interactive picker includes all Kimi setup paths together. Fixes #54412
• ·Agents/status: use provider-aware context window lookup for fresh Anthropic 4.6 model overrides so `/status` shows the correct 1.0m window instead of an underreported shared-cache minimum. (#54796)
• ·OpenAI/WebSocket: preserve reasoning replay metadata and tool-call item ids on WebSocket tool turns, and start a fresh response chain when full-context resend is required. (#53856)
• ·OpenAI/WS: restore reasoning blocks for Responses WebSocket runs and keep reasoning/tool-call replay metadata intact so resumed sessions do not lose or break follow-up reasoning-capable turns. (#53856)
• ·Agents/errors: surface provider quota/reset details when available, but keep HTML/Cloudflare rate-limit pages on the generic fallback so raw error pages are not shown to users. (#54512)
• ·Claude CLI: switch the bundled Claude CLI backend to `stream-json` output so watchdogs see progress on long runs, and keep session/usage metadata even when Claude finishes with an empty result line. (#49698)
• ·Claude CLI/MCP: always pass a strict generated `--mcp-config` overlay for background Claude CLI runs, including the empty-server case, so Claude does not inherit ambient user/global MCP servers. (#54961)
• ·Agents/embedded replies: surface mid-turn 429 and overload failures when embedded runs end without a user-visible reply, while preserving successful media-only replies that still use legacy `mediaUrl`. (#50930)
• ·Chat/UI: move the chat send button onto the shared ghost-button theme styling, while keeping the stop button icon readable on the danger state. (#55075)
• ·WhatsApp/allowFrom: show a specific allowFrom policy error for valid blocked targets instead of the misleading `<E.164|group JID>` format hint.
• ·Agents/cooldowns: scope rate-limit cooldowns per model so one 429 no longer blocks every model on the same auth profile, replace the exponential 1 min -> 1 h escalation with a stepped 30 s / 1 min / 5 min ladder, and surface a user-facing countdown message when all models are rate-limited. (#49834)
• ·Agents/embedded transport errors: distinguish common network failures like connection refused, DNS lookup failure, and interrupted sockets from true timeouts in embedded-run user messaging and lifecycle diagnostics. (#51419)
• ·Telegram/pairing: ignore self-authored DM `message` updates so bot-pinned status cards and similar service updates do not trigger bogus pairing requests or re-enter inbound dispatch. (#54530)
• ·Mattermost/replies: keep pairing replies, slash-command fallback replies, and model-picker messages on the resolved config path so `exec:` SecretRef bot tokens work across all outbound reply branches. (#48347)
• ·Microsoft Teams/config: accept the existing `welcomeCard`, `groupWelcomeCard`, `promptStarters`, and feedback/reflection keys in strict config validation so already-supported Teams runtime settings stop failing schema checks. (#54679)
• ·MCP/channels: add a Gateway-backed channel MCP bridge with Codex/Claude-facing conversation tools, Claude channel notifications, and safer stdio bridge lifecycle handling for reconnects and routed session discovery.
• ·Plugins/SDK: thread `moduleUrl` through plugin-sdk alias resolution so user-installed plugins outside the openclaw directory (e.g. `~/.openclaw/extensions/`) correctly resolve `openclaw/plugin-sdk/*` subpath imports, and gate `plugin-sdk:check-exports` in `release:check`. (#54283)
• ·Config/web fetch: allow the documented `tools.web.fetch.maxResponseBytes` setting in runtime schema validation so valid configs no longer fail with unrecognized-key errors. (#53401)
• ·Message tool/buttons: keep the shared `buttons` schema optional in merged tool definitions so plain `action=send` calls stop failing validation when no buttons are provided. (#54418)
• ·Agents/openai-compatible tool calls: deduplicate repeated tool call ids across live assistant messages and replayed history so OpenAI-compatible backends no longer reject duplicate `tool_call_id` values with HTTP 400. (#40996)
• ·Models/openai-completions: default non-native OpenAI-compatible providers to omit tool-definition `strict` fields unless users explicitly opt back in, so tool calling keeps working on providers that reject that option. (#45497)
• ·Plugins/context engines: retry strict legacy `assemble()` calls without the new `prompt` field when older engines reject it, preserving prompt-aware retrieval compatibility for pre-prompt plugins. (#50848)
• ·CLI/update status: explicitly say `up to date` when the local version already matches npm latest, while keeping the availability logic unchanged. (#51409)
• ·Daemon/Linux: stop flagging non-gateway systemd services as duplicate gateways just because their unit files mention OpenClaw, reducing false-positive doctor/log noise. (#45328)
• ·Feishu: close WebSocket connections on monitor stop/abort so ghost connections no longer persist, preventing duplicate event processing and resource leaks across restart cycles. (#52844)
• ·Feishu: use the original message `create_time` instead of `Date.now()` for inbound timestamps so offline-retried messages carry the correct authoring time, preventing mis-targeted agent actions on stale instructions. (#52809)
• ·Control UI/Skills: open skill detail dialogs with the browser modal lifecycle so clicking a skill row keeps the panel centered instead of rendering it off-screen at the bottom of the page.
• ·Matrix/replies: include quoted poll question/options in inbound reply context so the agent sees the original poll content when users reply to Matrix poll messages. (#55056)
• ·Matrix/plugins: keep plugin bootstrap from crashing when built runtime mixes bare and deep `matrix-js-sdk` entrypoints, so unrelated channels do not get taken down during plugin load. (#56273)
• ·Agents/sandbox: honor `tools.sandbox.tools.alsoAllow`, let explicit sandbox re-allows remove matching built-in default-deny tools, and keep sandbox explain/error guidance aligned with the effective sandbox tool policy. (#54492)
• ·Agents/sandbox: make blocked-tool guidance glob-aware again, redact/sanitize session-specific explain hints for safer copy-paste, and avoid leaking control-character session keys in those hints. (#54684)
• ·Agents/compaction: trigger timeout recovery compaction before retrying high-context LLM timeouts so embedded runs stop repeating oversized requests. (#46417)
• ·Agents/compaction: reconcile `sessions.json.compactionCount` after a late embedded auto-compaction success so persisted session counts catch up once the handler reports completion. (#45493)
• ·Agents/failover: classify Codex accountId token extraction failures as auth errors so model fallback continues to the next configured candidate. (#55206)
• ·Plugins/runtime: reuse only compatible active plugin registries across tools, providers, web search, and channel bootstrap, align `/tools/invoke` plugin loading with the session workspace, and retry outbound channel recovery when the pinned channel surface changes so plugin tools and channels stop disappearing or re-registering from mismatched runtime loads.
• ·Talk/macOS: stop direct system-voice failures from replaying system speech, use app-locale fallback for shared watchdog timing, and add regression coverage for the macOS fallback route and language-aware timeout policy. (#53511)
• ·Discord/gateway cleanup: keep late Carbon reconnect-exhausted errors suppressed through startup/dispose cleanup so Discord monitor shutdown no longer crashes on late gateway close events. (#55373)
• ·Discord/gateway shutdown: treat expected reconnect-exhausted events during intentional lifecycle stop as clean shutdowns so startup-abort cleanup no longer surfaces false gateway failures. (#55324)
• ·Discord/gateway shutdown: suppress reconnect-exhausted events that were already buffered before teardown flips `lifecycleStopping`, so stale-socket Discord restarts no longer crash the whole gateway. Fixes #55403 and #55421.
• ·GitHub Copilot/auth refresh: treat large `expires_at` values as seconds epochs and clamp far-future runtime auth refresh timers so Copilot token refresh cannot fall into a `setTimeout` overflow hot loop. (#55360)
• ·Agents/status: use the persisted runtime session model in `session_status` when no explicit override exists, and honor per-agent `thinkingDefault` in both `session_status` and `/status`. (#55425)
• ·Heartbeat/runner: guarantee the interval timer is re-armed after heartbeat runs and unexpected runner errors so scheduled heartbeats do not silently stop after an interrupted cycle. (#52270)
• ·Config/Doctor: rewrite stale bundled plugin load paths from legacy `extensions/*` locations to the packaged bundled path, including directory-name mismatches and slash-suffixed config entries. (#55054)
• ·WhatsApp/mentions: stop treating mentions embedded in quoted messages as direct mentions so replying to a message that @mentioned the bot no longer falsely triggers mention gating. (#52711)
• ·Matrix: keep separate 2-person rooms out of DM routing after `m.direct` seeds successfully, while still honoring explicit `is_direct` state and startup fallback recovery. (#54890)
• ·Agents/ollama fallback: surface non-2xx Ollama HTTP errors with a leading status code so HTTP 503 responses trigger model fallback again. (#55214)
• ·Feishu/tools: stop synthetic agent ids like `agent-spawner` from being treated as Feishu account ids during tool execution, so tools fall back to the configured/default Feishu account unless the contextual id is a real enabled Feishu account. (#55627)
• ·Google/tools: strip empty `required: []` arrays from Gemini tool schemas so optional-only tool parameters no longer trigger Google validator 400s. (#52106)
• ·Onboarding/TUI/local gateways: show the resolved gateway port in setup output, clarify no-daemon local health/dashboard messaging, and preserve loopback Control UI auth on reruns and explicit local gateway URLs so local quickstart flows recover cleanly. (#55730)
• ·TUI/chat log: keep system messages as single logical entries and prune overflow at whole-message boundaries so wrapped system spacing stays intact. (#55732)
• ·TUI/activation: validate `/activation` arguments in the TUI and reject invalid values instead of silently coercing them to `mention`. (#55733)
• ·Agents/model switching: apply `/model` changes to active embedded runs at the next safe retry boundary, so overloaded or retrying turns switch to the newly selected model instead of staying pinned to the old provider.
• ·Agents/Codex fallback: classify Codex `server_error` payloads as failoverable, sanitize `Codex error:` payloads before they reach chat, preserve context-overflow guidance for prefixed `invalid_request_error` payloads, and omit provider `request_id` values from user-facing UI copy. (#42892)
• ·Memory/search: share memory embedding provider registrations across split plugin runtimes so memory search no longer fails with unknown provider errors after memory-core registers built-in adapters. (#55945)
• ·Discord/Carbon beta: update `@buape/carbon` to the latest beta and pass the new `RateLimitError` request argument so Discord stays compatible with the upstream beta constructor change. (#55980)
• ·Plugins/inbound claims: pass full inbound attachment arrays through `inbound_claim` hook metadata while keeping the legacy singular media attachment fields for compatibility. (#55452)
• ·Plugins/Matrix: preserve sender filenames for inbound media by forwarding `originalFilename` to `saveMediaBuffer`. (#55692)
• ·Matrix/mentions: recognize `matrix.to` mentions whose visible label uses the bot's room display name, so `requireMention: true` rooms respond correctly in modern Matrix clients. (#55393)
• ·Ollama/thinking off: route `thinkingLevel=off` through the live Ollama extension request path so thinking-capable Ollama models now receive top-level `think: false` instead of silently generating hidden reasoning tokens. (#53200)
• ·Plugins/diffs: stage bundled `@pierre/diffs` runtime dependencies during packaged updates so the bundled diff viewer keeps loading after global installs and updates. (#56077)
• ·Plugins/diffs: load bundled Pierre themes without JSON module imports so diff rendering keeps working on newer Node builds. (#45869)
• ·Plugins/uninstall: remove owned `channels.<id>` config when uninstalling channel plugins, and keep the uninstall preview aligned with explicit channel ownership so built-in channels and shared keys stay intact. (#35915)
• ·Plugins/Matrix: prefer explicit DM signals when choosing outbound direct rooms and routing unmapped verification summaries, so strict 2-person fallback rooms do not outrank the real DM. (#56076)
• ·Plugins/Matrix: resolve env-backed `accessToken` and `password` SecretRefs against the active Matrix config env path during startup, and officially accept SecretRef `accessToken` config values. (#54980)
• ·Microsoft Teams/proactive DMs: prefer the freshest personal conversation reference for `user:<aadObjectId>` sends when multiple stored references exist, so replies stop targeting stale DM threads. (#54702)
• ·Gateway/plugins: reuse the session workspace when building HTTP `/tools/invoke` tool lists and harden tool construction to infer the session agent workspace by default, so workspace plugins do not re-register on repeated HTTP tool calls. (#56101)
• ·Brave/web search: normalize unsupported Brave `country` filters to `ALL` before request and cache-key generation so locale-derived values like `VN` stop failing with upstream 422 validation errors. (#55695)
• ·Discord/replies: preserve leading indentation when stripping inline reply tags so reply-tagged plain text and fenced code blocks keep their formatting. (#55960)
• ·Daemon/status: surface immediate gateway close reasons from lightweight probes and prefer those concrete auth or pairing failures over generic timeouts in `openclaw daemon status`. (#56282)
• ·Agents/failover: classify HTTP 410 errors as retryable timeouts by default while still preserving explicit session-expired, billing, and auth signals from the payload. (#55201)
• ·Agents/subagents: restore completion announce delivery for extension channels like BlueBubbles. (#56348)
• ·Plugins/Matrix: load bundled `@matrix-org/matrix-sdk-crypto-nodejs` through `createRequire(...)` so E2EE media send and receive keep the package-local native binding lookup working in packaged ESM builds. (#54566)
• ·Plugins/Matrix: encrypt E2EE image thumbnails with `thumbnail_file` while keeping unencrypted-room previews on `thumbnail_url`, so encrypted Matrix image events keep thumbnail metadata without leaking plaintext previews. (#54711)
• ·Telegram/forum topics: keep native `/new` and `/reset` routed to the active topic by preserving the topic target on forum-thread command context. (#35963)

Breaking

• ·Providers/Qwen: remove the deprecated `qwen-portal-auth` OAuth integration for `portal.qwen.ai`; migrate to Model Studio with `openclaw onboard --auth-choice modelstudio-api-key`. (#52709)
• ·Config/Doctor: drop automatic config migrations older than two months; very old legacy keys now fail validation instead of being rewritten on load or by `openclaw doctor`.

Changes

• ·xAI/tools: move the bundled xAI provider to the Responses API, add first-class `x_search`, and auto-enable the xAI plugin from owned web-search and tool config so bundled Grok auth/configured search flows work without manual plugin toggles. (#56048)
• ·MiniMax: add image generation provider for `image-01` model, supporting generate and image-to-image editing with aspect ratio control. (#54487)
• ·Plugins/hooks: add async `requireApproval` to `before_tool_call` hooks, letting plugins pause tool execution and prompt the user for approval via the exec approval overlay, Telegram buttons, Discord interactions, or the `/approve` command on any channel. The `/approve` command now handles both exec and plugin approvals with automatic fallback. (#55339)
• ·ACP/channels: add current-conversation ACP binds for Discord, BlueBubbles, and iMessage so `/acp spawn codex --bind here` can turn the current chat into a Codex-backed workspace without creating a child thread, and document the distinction between chat surface, ACP session, and runtime workspace.
• ·OpenAI/apply_patch: enable `apply_patch` by default for OpenAI and OpenAI Codex models, and align its sandbox policy access with `write` permissions.
• ·Plugins/CLI backends: move bundled Claude CLI, Codex CLI, and Gemini CLI inference defaults onto the plugin surface, add bundled Gemini CLI backend support, and replace `gateway run --claude-cli-logs` with generic `--cli-backend-logs` while keeping the old flag as a compatibility alias.
• ·Plugins/startup: auto-load bundled provider and CLI-backend plugins from explicit config refs, so bundled Claude CLI, Codex CLI, and Gemini CLI message-provider setups no longer need manual `plugins.allow` entries.
• ·Podman: simplify the container setup around the current rootless user, install the launch helper under `~/.local/bin`, and document the host-CLI `openclaw --container <name> ...` workflow instead of a dedicated `openclaw` service user.
• ·Slack/tool actions: add an explicit `upload-file` Slack action that routes file uploads through the existing Slack upload transport, with optional filename/title/comment overrides for channels and DMs.
• ·Message actions/files: start unifying file-first sends on the canonical `upload-file` action by adding explicit support for Microsoft Teams and Google Chat, and by exposing BlueBubbles file sends through `upload-file` while keeping the legacy `sendAttachment` alias.
• ·Plugins/Matrix TTS: send auto-TTS replies as native Matrix voice bubbles instead of generic audio attachments. (#37080)
• ·CLI: add `openclaw config schema` to print the generated JSON schema for `openclaw.json`. (#54523)
• ·Config/TTS: auto-migrate legacy speech config on normal reads and secret resolution, keep legacy diagnostics for Doctor, and remove regular-mode runtime fallback for old bundled `tts.<provider>` API-key shapes.
• ·Memory/plugins: move the pre-compaction memory flush plan behind the active memory plugin contract so `memory-core` owns flush prompts and target-path policy instead of hardcoded core logic.
• ·MiniMax: trim model catalog to M2.7 only, removing legacy M2, M2.1, M2.5, and VL-01 models. (#54487)
• ·Plugins/runtime: expose `runHeartbeatOnce` in the plugin runtime `system` namespace so plugins can trigger a single heartbeat cycle with an explicit delivery target override (e.g. `heartbeat: { target: "last" }`). (#40299)
• ·Agents/compaction: preserve the post-compaction AGENTS refresh on stale-usage preflight compaction for both immediate replies and queued followups. (#49479)
• ·Agents/compaction: surface safeguard-specific cancel reasons and relabel benign manual `/compact` no-op cases as skipped instead of failed. (#51072)
• ·Docs: add `pnpm docs:check-links:anchors` for Mintlify anchor validation while keeping `scripts/docs-link-audit.mjs` as the stable link-audit entrypoint. (#55912)
• ·Tavily: mark outbound API requests with `X-Client-Source: openclaw` so Tavily can attribute OpenClaw-originated traffic. (#55335)

Fixes

• ·Google/models: resolve Gemini 3.1 pro, flash, and flash-lite for all Google provider aliases by passing the actual runtime provider ID and adding a template-provider fallback; fix flash-lite prefix ordering. (#56567)
• ·OpenAI Codex/image tools: register Codex for media understanding and route image prompts through Codex instructions so image analysis no longer fails on missing provider registration or missing `instructions`. (#54829)
• ·Agents/image tool: restore the generic image-runtime fallback when no provider-specific media-understanding provider is registered, so image analysis works again for providers like `openrouter` and `minimax-portal`. (#54858)
• ·WhatsApp: fix infinite echo loop in self-chat DM mode where the bot's own outbound replies were re-processed as new inbound user messages. (#54570)
• ·Telegram/splitting: replace proportional text estimate with verified HTML-length search so long messages split at word boundaries instead of mid-word; gracefully degrade when tag overhead exceeds the limit. (#56595)
• ·Telegram/delivery: skip whitespace-only and hook-blanked text replies in bot delivery to prevent GrammyError 400 empty-text crashes. (#56620)
• ·Telegram/send: validate `replyToMessageId` at all four API sinks with a shared normalizer that rejects non-numeric, NaN, and mixed-content strings. (#56587)
• ·Mistral: normalize OpenAI-compatible request flags so official Mistral API runs no longer fail with remaining `422 status code (no body)` chat errors.
• ·Control UI/config: keep sensitive raw config hidden by default, replace the blank blocked editor with an explicit reveal-to-edit state, and restore raw JSON editing without auto-exposing secrets. Fixes #55322.
• ·CLI/zsh: defer `compdef` registration until `compinit` is available so zsh completion loads cleanly with plugin managers and manual setups. (#56555)
• ·BlueBubbles/debounce: guard debounce flush against null message text by sanitizing at the enqueue boundary and adding an independent combiner guard. (#56573)
• ·Auto-reply: suppress JSON-wrapped `{"action":"NO_REPLY"}` control envelopes before channel delivery with a strict single-key detector; preserves media when text is only a silent envelope. (#56612)
• ·ACP/ACPX agent registry: align OpenClaw's ACPX built-in agent mirror with the latest `openclaw/acpx` command defaults and built-in aliases, pin versioned `npx` built-ins to exact versions, and stop unknown ACP agent ids from falling through to raw `--agent` command execution on the MCP-proxy path. (#28321)
• ·Security/audit: extend web search key audit to recognize Gemini, Grok/xAI, Kimi, Moonshot, and OpenRouter credentials via a boundary-safe bundled-web-search registry shim. (#56540)
• ·Docs/FAQ: remove broken Xfinity SSL troubleshooting cross-links from English and zh-CN FAQ entries — both sections already contain the full workaround inline. (#56500)
• ·Telegram: deliver verbose tool summaries inside forum topic sessions again, so threaded topic chats now match DM verbose behavior. (#43236)
• ·BlueBubbles/CLI agents: restore inbound prompt image refs for CLI routed turns, reapply embedded runner image size guardrails, and cover both CLI image transport paths with regression tests. (#51373)
• ·BlueBubbles/groups: optionally enrich unnamed participant lists with local macOS Contacts names after group gating passes, so group member context can show names instead of only raw phone numbers.
• ·Discord/reconnect: drain stale gateway sockets, clear cached resume state before forced fresh reconnects, and fail closed when old sockets refuse to die so Discord recovery stops looping on poisoned resume state. (#54697)
• ·iMessage: stop leaking inline `[[reply_to:...]]` tags into delivered text by sending `reply_to` as RPC metadata and stripping stray directive tags from outbound messages. (#39512)
• ·CLI/plugins: make routed commands use the same auto-enabled bundled-channel snapshot as gateway startup, so configured bundled channels like Slack load without requiring a prior config rewrite. (#54809)
• ·CLI/message send: write manual `openclaw message send` deliveries into the resolved agent session transcript again by always threading the default CLI agent through outbound mirroring. (#54187)
• ·CLI/onboarding: show the Kimi Code API key option again in the Moonshot setup menu so the interactive picker includes all Kimi setup paths together. Fixes #54412
• ·Agents/status: use provider-aware context window lookup for fresh Anthropic 4.6 model overrides so `/status` shows the correct 1.0m window instead of an underreported shared-cache minimum. (#54796)
• ·OpenAI/WebSocket: preserve reasoning replay metadata and tool-call item ids on WebSocket tool turns, and start a fresh response chain when full-context resend is required. (#53856)
• ·OpenAI/WS: restore reasoning blocks for Responses WebSocket runs and keep reasoning/tool-call replay metadata intact so resumed sessions do not lose or break follow-up reasoning-capable turns. (#53856)
• ·Agents/errors: surface provider quota/reset details when available, but keep HTML/Cloudflare rate-limit pages on the generic fallback so raw error pages are not shown to users. (#54512)
• ·Claude CLI: switch the bundled Claude CLI backend to `stream-json` output so watchdogs see progress on long runs, and keep session/usage metadata even when Claude finishes with an empty result line. (#49698)
• ·Claude CLI/MCP: always pass a strict generated `--mcp-config` overlay for background Claude CLI runs, including the empty-server case, so Claude does not inherit ambient user/global MCP servers. (#54961)
• ·Agents/embedded replies: surface mid-turn 429 and overload failures when embedded runs end without a user-visible reply, while preserving successful media-only replies that still use legacy `mediaUrl`. (#50930)
• ·Chat/UI: move the chat send button onto the shared ghost-button theme styling, while keeping the stop button icon readable on the danger state. (#55075)
• ·WhatsApp/allowFrom: show a specific allowFrom policy error for valid blocked targets instead of the misleading `<E.164|group JID>` format hint.
• ·Agents/cooldowns: scope rate-limit cooldowns per model so one 429 no longer blocks every model on the same auth profile, replace the exponential 1 min -> 1 h escalation with a stepped 30 s / 1 min / 5 min ladder, and surface a user-facing countdown message when all models are rate-limited. (#49834)
• ·Agents/embedded transport errors: distinguish common network failures like connection refused, DNS lookup failure, and interrupted sockets from true timeouts in embedded-run user messaging and lifecycle diagnostics. (#51419)
• ·Telegram/pairing: ignore self-authored DM `message` updates so bot-pinned status cards and similar service updates do not trigger bogus pairing requests or re-enter inbound dispatch. (#54530)
• ·Mattermost/replies: keep pairing replies, slash-command fallback replies, and model-picker messages on the resolved config path so `exec:` SecretRef bot tokens work across all outbound reply branches. (#48347)
• ·Microsoft Teams/config: accept the existing `welcomeCard`, `groupWelcomeCard`, `promptStarters`, and feedback/reflection keys in strict config validation so already-supported Teams runtime settings stop failing schema checks. (#54679)
• ·MCP/channels: add a Gateway-backed channel MCP bridge with Codex/Claude-facing conversation tools, Claude channel notifications, and safer stdio bridge lifecycle handling for reconnects and routed session discovery.
• ·Plugins/SDK: thread `moduleUrl` through plugin-sdk alias resolution so user-installed plugins outside the openclaw directory (e.g. `~/.openclaw/extensions/`) correctly resolve `openclaw/plugin-sdk/*` subpath imports, and gate `plugin-sdk:check-exports` in `release:check`. (#54283)
• ·Config/web fetch: allow the documented `tools.web.fetch.maxResponseBytes` setting in runtime schema validation so valid configs no longer fail with unrecognized-key errors. (#53401)
• ·Message tool/buttons: keep the shared `buttons` schema optional in merged tool definitions so plain `action=send` calls stop failing validation when no buttons are provided. (#54418)
• ·Agents/openai-compatible tool calls: deduplicate repeated tool call ids across live assistant messages and replayed history so OpenAI-compatible backends no longer reject duplicate `tool_call_id` values with HTTP 400. (#40996)
• ·Models/openai-completions: default non-native OpenAI-compatible providers to omit tool-definition `strict` fields unless users explicitly opt back in, so tool calling keeps working on providers that reject that option. (#45497)
• ·Plugins/context engines: retry strict legacy `assemble()` calls without the new `prompt` field when older engines reject it, preserving prompt-aware retrieval compatibility for pre-prompt plugins. (#50848)
• ·CLI/update status: explicitly say `up to date` when the local version already matches npm latest, while keeping the availability logic unchanged. (#51409)
• ·Daemon/Linux: stop flagging non-gateway systemd services as duplicate gateways just because their unit files mention OpenClaw, reducing false-positive doctor/log noise. (#45328)
• ·Feishu: close WebSocket connections on monitor stop/abort so ghost connections no longer persist, preventing duplicate event processing and resource leaks across restart cycles. (#52844)
• ·Feishu: use the original message `create_time` instead of `Date.now()` for inbound timestamps so offline-retried messages carry the correct authoring time, preventing mis-targeted agent actions on stale instructions. (#52809)
• ·Control UI/Skills: open skill detail dialogs with the browser modal lifecycle so clicking a skill row keeps the panel centered instead of rendering it off-screen at the bottom of the page.
• ·Matrix/replies: include quoted poll question/options in inbound reply context so the agent sees the original poll content when users reply to Matrix poll messages. (#55056)
• ·Matrix/plugins: keep plugin bootstrap from crashing when built runtime mixes bare and deep `matrix-js-sdk` entrypoints, so unrelated channels do not get taken down during plugin load. (#56273)
• ·Agents/sandbox: honor `tools.sandbox.tools.alsoAllow`, let explicit sandbox re-allows remove matching built-in default-deny tools, and keep sandbox explain/error guidance aligned with the effective sandbox tool policy. (#54492)
• ·Agents/sandbox: make blocked-tool guidance glob-aware again, redact/sanitize session-specific explain hints for safer copy-paste, and avoid leaking control-character session keys in those hints. (#54684)
• ·Agents/compaction: trigger timeout recovery compaction before retrying high-context LLM timeouts so embedded runs stop repeating oversized requests. (#46417)
• ·Agents/compaction: reconcile `sessions.json.compactionCount` after a late embedded auto-compaction success so persisted session counts catch up once the handler reports completion. (#45493)
• ·Agents/failover: classify Codex accountId token extraction failures as auth errors so model fallback continues to the next configured candidate. (#55206)
• ·Plugins/runtime: reuse only compatible active plugin registries across tools, providers, web search, and channel bootstrap, align `/tools/invoke` plugin loading with the session workspace, and retry outbound channel recovery when the pinned channel surface changes so plugin tools and channels stop disappearing or re-registering from mismatched runtime loads.
• ·Talk/macOS: stop direct system-voice failures from replaying system speech, use app-locale fallback for shared watchdog timing, and add regression coverage for the macOS fallback route and language-aware timeout policy. (#53511)
• ·Discord/gateway cleanup: keep late Carbon reconnect-exhausted errors suppressed through startup/dispose cleanup so Discord monitor shutdown no longer crashes on late gateway close events. (#55373)
• ·Discord/gateway shutdown: treat expected reconnect-exhausted events during intentional lifecycle stop as clean shutdowns so startup-abort cleanup no longer surfaces false gateway failures. (#55324)
• ·Discord/gateway shutdown: suppress reconnect-exhausted events that were already buffered before teardown flips `lifecycleStopping`, so stale-socket Discord restarts no longer crash the whole gateway. Fixes #55403 and #55421.
• ·GitHub Copilot/auth refresh: treat large `expires_at` values as seconds epochs and clamp far-future runtime auth refresh timers so Copilot token refresh cannot fall into a `setTimeout` overflow hot loop. (#55360)
• ·Agents/status: use the persisted runtime session model in `session_status` when no explicit override exists, and honor per-agent `thinkingDefault` in both `session_status` and `/status`. (#55425)
• ·Heartbeat/runner: guarantee the interval timer is re-armed after heartbeat runs and unexpected runner errors so scheduled heartbeats do not silently stop after an interrupted cycle. (#52270)
• ·Config/Doctor: rewrite stale bundled plugin load paths from legacy `extensions/*` locations to the packaged bundled path, including directory-name mismatches and slash-suffixed config entries. (#55054)
• ·WhatsApp/mentions: stop treating mentions embedded in quoted messages as direct mentions so replying to a message that @mentioned the bot no longer falsely triggers mention gating. (#52711)
• ·Matrix: keep separate 2-person rooms out of DM routing after `m.direct` seeds successfully, while still honoring explicit `is_direct` state and startup fallback recovery. (#54890)
• ·Agents/ollama fallback: surface non-2xx Ollama HTTP errors with a leading status code so HTTP 503 responses trigger model fallback again. (#55214)
• ·Feishu/tools: stop synthetic agent ids like `agent-spawner` from being treated as Feishu account ids during tool execution, so tools fall back to the configured/default Feishu account unless the contextual id is a real enabled Feishu account. (#55627)
• ·Google/tools: strip empty `required: []` arrays from Gemini tool schemas so optional-only tool parameters no longer trigger Google validator 400s. (#52106)
• ·Onboarding/TUI/local gateways: show the resolved gateway port in setup output, clarify no-daemon local health/dashboard messaging, and preserve loopback Control UI auth on reruns and explicit local gateway URLs so local quickstart flows recover cleanly. (#55730)
• ·TUI/chat log: keep system messages as single logical entries and prune overflow at whole-message boundaries so wrapped system spacing stays intact. (#55732)
• ·TUI/activation: validate `/activation` arguments in the TUI and reject invalid values instead of silently coercing them to `mention`. (#55733)
• ·Agents/model switching: apply `/model` changes to active embedded runs at the next safe retry boundary, so overloaded or retrying turns switch to the newly selected model instead of staying pinned to the old provider.
• ·Agents/Codex fallback: classify Codex `server_error` payloads as failoverable, sanitize `Codex error:` payloads before they reach chat, preserve context-overflow guidance for prefixed `invalid_request_error` payloads, and omit provider `request_id` values from user-facing UI copy. (#42892)
• ·Memory/search: share memory embedding provider registrations across split plugin runtimes so memory search no longer fails with unknown provider errors after memory-core registers built-in adapters. (#55945)
• ·Discord/Carbon beta: update `@buape/carbon` to the latest beta and pass the new `RateLimitError` request argument so Discord stays compatible with the upstream beta constructor change. (#55980)
• ·Plugins/inbound claims: pass full inbound attachment arrays through `inbound_claim` hook metadata while keeping the legacy singular media attachment fields for compatibility. (#55452)
• ·Plugins/Matrix: preserve sender filenames for inbound media by forwarding `originalFilename` to `saveMediaBuffer`. (#55692)
• ·Matrix/mentions: recognize `matrix.to` mentions whose visible label uses the bot's room display name, so `requireMention: true` rooms respond correctly in modern Matrix clients. (#55393)
• ·Ollama/thinking off: route `thinkingLevel=off` through the live Ollama extension request path so thinking-capable Ollama models now receive top-level `think: false` instead of silently generating hidden reasoning tokens. (#53200)
• ·Plugins/diffs: stage bundled `@pierre/diffs` runtime dependencies during packaged updates so the bundled diff viewer keeps loading after global installs and updates. (#56077)
• ·Plugins/diffs: load bundled Pierre themes without JSON module imports so diff rendering keeps working on newer Node builds. (#45869)
• ·Plugins/uninstall: remove owned `channels.<id>` config when uninstalling channel plugins, and keep the uninstall preview aligned with explicit channel ownership so built-in channels and shared keys stay intact. (#35915)
• ·Plugins/Matrix: prefer explicit DM signals when choosing outbound direct rooms and routing unmapped verification summaries, so strict 2-person fallback rooms do not outrank the real DM. (#56076)
• ·Plugins/Matrix: resolve env-backed `accessToken` and `password` SecretRefs against the active Matrix config env path during startup, and officially accept SecretRef `accessToken` config values. (#54980)
• ·Microsoft Teams/proactive DMs: prefer the freshest personal conversation reference for `user:<aadObjectId>` sends when multiple stored references exist, so replies stop targeting stale DM threads. (#54702)
• ·Gateway/plugins: reuse the session workspace when building HTTP `/tools/invoke` tool lists and harden tool construction to infer the session agent workspace by default, so workspace plugins do not re-register on repeated HTTP tool calls. (#56101)
• ·Brave/web search: normalize unsupported Brave `country` filters to `ALL` before request and cache-key generation so locale-derived values like `VN` stop failing with upstream 422 validation errors. (#55695)
• ·Discord/replies: preserve leading indentation when stripping inline reply tags so reply-tagged plain text and fenced code blocks keep their formatting. (#55960)
• ·Daemon/status: surface immediate gateway close reasons from lightweight probes and prefer those concrete auth or pairing failures over generic timeouts in `openclaw daemon status`. (#56282)
• ·Agents/failover: classify HTTP 410 errors as retryable timeouts by default while still preserving explicit session-expired, billing, and auth signals from the payload. (#55201)
• ·Agents/subagents: restore completion announce delivery for extension channels like BlueBubbles. (#56348)
• ·Plugins/Matrix: load bundled `@matrix-org/matrix-sdk-crypto-nodejs` through `createRequire(...)` so E2EE media send and receive keep the package-local native binding lookup working in packaged ESM builds. (#54566)

Breaking

Changes

• ·Gateway/OpenAI compatibility: add `/v1/models` and `/v1/embeddings`, and forward explicit model overrides through `/v1/chat/completions` and `/v1/responses` for broader client and RAG compatibility.
• ·Agents/tools: make `/tools` show the tools the current agent can actually use right now, add a compact default view with an optional detailed mode, and add a live "Available Right Now" section in the Control UI so it is easier to see what will work before you ask.
• ·Microsoft Teams: migrate to the official Teams SDK and add AI-agent UX best practices including streaming 1:1 replies, welcome cards with prompt starters, feedback/reflection, informative status updates, typing indicators, and native AI labeling. (#51808)
• ·Microsoft Teams: add message edit and delete support for sent messages, including in-thread fallbacks when no explicit target is provided. (#49925)
• ·Skills/install metadata: add one-click install recipes to bundled skills (coding-agent, gh-issues, openai-whisper-api, session-logs, tmux, trello, weather) so the CLI and Control UI can offer dependency installation when requirements are missing. (#53411)
• ·Control UI/skills: add status-filter tabs (All / Ready / Needs Setup / Disabled) with counts, replace inline skill cards with a click-to-detail dialog showing requirements, toggle switch, install action, API key entry, source metadata, and homepage link. (#53411)
• ·Slack/interactive replies: restore rich reply parity for direct deliveries, auto-render simple trailing `Options:` lines as buttons/selects, improve Slack interactive setup defaults, and isolate reply controls from plugin interactive handlers. (#53389)
• ·CLI/containers: add `--container` and `OPENCLAW_CONTAINER` to run `openclaw` commands inside a running Docker or Podman OpenClaw container. (#52651)
• ·Discord/auto threads: add optional `autoThreadName: "generated"` naming so new auto-created threads can be renamed asynchronously with concise LLM-generated titles while keeping the existing message-based naming as the default. (#43366)
• ·Plugins/hooks: add `before_dispatch` with canonical inbound metadata and route handled replies through the normal final-delivery path, preserving TTS and routed delivery semantics. (#50444)
• ·Control UI/agents: convert agent workspace file rows to expandable `<details>` with lazy-loaded inline markdown preview, and add comprehensive `.sidebar-markdown` styles for headings, lists, code blocks, tables, blockquotes, and details/summary elements. (#53411)
• ·Control UI/markdown preview: restyle the agent workspace file preview dialog with a frosted backdrop, sized panel, and styled header, and integrate `@create-markdown/preview` v2 system theme for rich markdown rendering (headings, tables, code blocks, callouts, blockquotes) that auto-adapts to the app's light/dark design tokens. (#53411)
• ·macOS app/config: replace horizontal pill-based subsection navigation with a collapsible tree sidebar using disclosure chevrons and indented subsection rows. (#53411)
• ·CLI/skills: soften missing-requirements label from "missing" to "needs setup" and surface API key setup guidance (where to get a key, CLI save command, storage path) in `openclaw skills info` output. (#53411)
• ·macOS app/skills: add "Get your key" homepage link and storage-path hint to the API key editor dialog, and show the config path in save confirmation messages. (#53411)
• ·Control UI/agents: add a "Not set" placeholder to the default agent model selector dropdown. (#53411)
• ·Runtime/install: lower the supported Node 22 floor to `22.14+` while continuing to recommend Node 24, so npm installs and self-updates do not strand Node 22.14 users on older releases.
• ·CLI/update: preflight the target npm package `engines.node` before `openclaw update` runs a global package install, so outdated Node runtimes fail with a clear upgrade message instead of attempting an unsupported latest release.

Fixes

• ·Outbound media/local files: align outbound media access with the configured fs policy so host-local files and inbound-media paths keep sending when `workspaceOnly` is off, while strict workspace-only agents remain sandboxed.
• ·Security/sandbox media dispatch: close the `mediaUrl`/`fileUrl` alias bypass so outbound tool and message actions cannot escape media-root restrictions. (#54034)
• ·Gateway/restart sentinel: wake the interrupted agent session via heartbeat after restart instead of only sending a best-effort restart note, retry outbound delivery once on transient failure, and preserve explicit thread/topic routing through the wake path so replies land in the correct Telegram topic or Slack thread. (#53940)
• ·Docker/setup: avoid the pre-start `openclaw-cli` shared-network namespace loop by routing setup-time onboard/config writes through `openclaw-gateway`, so fresh Docker installs stop failing before the gateway comes up. (#53385)
• ·Gateway/channels: keep channel startup sequential while isolating per-channel boot failures, so one broken channel no longer blocks later channels from starting. (#54215)
• ·Embedded runs/secrets: stop unresolved `SecretRef` config from crashing embedded agent runs by falling back to the resolved runtime snapshot when needed. Fixes #45838.
• ·WhatsApp/groups: track recent gateway-sent message IDs and suppress only matching group echoes, preserving owner `/status`, `/new`, and `/activation` commands from linked-account `fromMe` traffic. (#53624)
• ·WhatsApp/reply-to-bot detection: restore implicit group reply detection by unwrapping `botInvokeMessage` payloads and reading `selfLid` from `creds.json`, so reply-based mentions reach the bot again in linked-account group chats.
• ·Telegram/forum topics: recover `#General` topic `1` routing when Telegram omits forum metadata, including native commands, interactive callbacks, inbound message context, and fallback error replies. (#53699)
• ·Discord/gateway supervision: centralize gateway error handling behind a lifetime-owned supervisor so early, active, and late-teardown Carbon gateway errors stay classified consistently and stop surfacing as process-killing teardown crashes.
• ·Discord/timeouts: send a visible timeout reply when the inbound Discord worker times out before a final reply starts, including created auto-thread targets and queued-run ordering. (#53823)
• ·ACP/direct chats: always deliver a terminal ACP result when final TTS does not yield audio, even if block text already streamed earlier, and skip redundant empty-text final synthesis. (#53692)
• ·Telegram/outbound errors: preserve actionable 403 membership/block/kick details and treat `bot not a member` as a permanent delivery failure so Telegram sends stop retrying doomed chats. (#53635)
• ·Telegram/photos: preflight Telegram photo dimension and aspect-ratio rules, and fall back to document sends when image metadata is invalid or unavailable so photo uploads stop failing with `PHOTO_INVALID_DIMENSIONS`. (#52545)
• ·Slack/runtime defaults: trim Slack DM reply overhead, restore Codex auto transport, and tighten Slack/web-search runtime defaults around DM preview threading, cache scoping, warning dedupe, and explicit web-search opt-in. (#53957)

Fixes

• ·Outbound media/local files: align outbound media access with the configured fs policy so host-local files and inbound-media paths keep sending when `workspaceOnly` is off, while strict workspace-only agents remain sandboxed.
• ·Runtime/install: lower the supported Node 22 floor to `22.14+` while continuing to recommend Node 24, so npm installs and self-updates do not strand Node 22.14 users on older releases.
• ·CLI/update: preflight the target npm package `engines.node` before `openclaw update` runs a global package install, so outdated Node runtimes fail with a clear upgrade message instead of attempting an unsupported latest release.
• ·Tests/security audit: isolate audit-test home and personal skill resolution so local `~/.agents/skills` installs no longer make maintainer prep runs fail nondeterministically. (#54473)