OpenClaw v2026.4.14

OpenClaw `2026.4.14` is another broad quality release focused on model provider with explicit turn improvements for GPT-5 family and channel provider issues. Additionally we improved overal performance with refactors to our underlying core codebase. ## Changes - OpenAI Codex/models: add forward-compat support for `gpt-5.4-pro`, including Codex pricing/limits and list/status visibility before the upstream catalog catches up. (#66453) Thanks @jepson-liu. - 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) Thanks @ptahdunbar. ## Fixes - Agents/Ollama: forward the configured embedded-run timeout into the global undici stream timeout tuning so slow local Ollama runs no longer inherit the default stream cutoff instead of the operator-set run timeout. (#63175) Thanks @mindcraftreader and @vincentkoc. - Models/Codex: include `apiKey` in the codex provider catalog output so the Pi ModelRegistry validator no longer rejects the entry and silently drops all custom models from every provider in `models.json`. (#66180) Thanks @hoyyeva. - Tools/image+pdf: normalize configured provider/model refs before media-tool registry lookup so image and PDF tool runs stop rejecting valid Ollama vision models as unknown just because the tool path skipped the usual model-ref normalization step. (#59943) Thanks @yqli2420 and @vincentkoc. - Slack/interactions: apply the configured global `allowFrom` owner allowlist to channel block-action and modal interactive events, require an expected sender id for cross-verification, and reject ambiguous channel types so interactive triggers can no longer bypass the documented allowlist intent in channels without a `users` list. Open-by-default behavior is preserved when no allowlists are configured. (#66028) Thanks @eleqtrizit. - Media-understanding/attachments: fail closed when a local attachment path cannot be canonically resolved via `realpath`, so a `realpath` error can no longer downgrade the canonical-roots allowlist check to a non-canonical comparison; attachments that also have a URL still fall back to the network fetch path. (#66022) Thanks @eleqtrizit. - Agents/gateway-tool: reject `config.patch` and `config.apply` calls from the model-facing gateway tool when they would newly enable any flag enumerated by `openclaw security audit` (for example `dangerouslyDisableDeviceAuth`, `allowInsecureAuth`, `dangerouslyAllowHostHeaderOriginFallback`, `hooks.gmail.allowUnsafeExternalContent`, `tools.exec.applyPatch.workspaceOnly: false`); already-enabled flags pass through unchanged so non-dangerous edits in the same patch still apply, and direct authenticated operator RPC behavior is unchanged. (#62006) Thanks @eleqtrizit. - Google image generation: strip a trailing `/openai` suffix from configured Google base URLs only when calling the native Gemini image API so Gemini image requests stop 404ing without breaking explicit OpenAI-compatible Google endpoints. (#66445) Thanks @dapzthelegend. - Telegram/forum topics: persist learned topic names to the Telegram session sidecar store so agent context can keep using human topic names after a restart instead of relearning from future service metadata. (#66107) Thanks @obviyus. - Doctor/systemd: keep `openclaw doctor --repair` and service reinstall from re-embedding dotenv-backed secrets in user systemd units, while preserving newer inline overrides over stale state-dir `.env` values. (#66249) Thanks @tmimmanuel. - Ollama/OpenAI-compat: send `stream_options.include_usage` for Ollama streaming completions so local Ollama runs report real usage instead of falling back to bogus prompt-token counts that trigger premature compaction. (#64568) Thanks @xchunzhao and @vincentkoc. - Doctor/plugins: cache external `preferOver` catalog lookups within each plugin auto-enable pass so large `agents.list` configs no longer peg CPU and repeatedly reread plugin catalogs during doctor/plugins resolution. (#66246) Thanks @yfge. - GitHub Copilot/thinking: allow `github-copilot/gpt-5.4` to use `xhigh` reasoning so Copilot GPT-5.4 matches the rest of the GPT-5.4 family. (#50168) Thanks @jakepresent and @vincentkoc. - Memory/embeddings: preserve non-OpenAI provider prefixes when normalizing OpenAI-compatible embedding model refs so proxy-backed memory providers stop failing with `Unknown memory embedding provider`. (#66452) Thanks @jlapenna. - 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) Thanks @ImLukeF. - Browser/SSRF: restore hostname navigation under the default browser SSRF policy while keeping explicit strict mode reachable from config, and keep managed loopback CDP `/json/new` fallback requests on the local CDP control policy so browser follow-up fixes stop regressing normal navigation or self-blocking local CDP control. (#66386) Thanks @obviyus. - Models/Codex: canonicalize the legacy `openai-codex/gpt-5.4-codex` runtime alias to `openai-codex/gpt-5.4` while still honoring alias-specific and canonical per-model overrides. (#43060) Thanks @Sapientropic and @vincentkoc. - Browser/SSRF: preserve explicit strict browser navigation mode for legacy `browser.ssrfPolicy.allowPrivateNetwork: false` configs by normalizing the legacy alias to the canonical strict marker instead of silently widening those installs to the default non-strict hostname-navigation path. - Onboarding/custom providers: use `max_tokens=16` for OpenAI-compatible verification probes so stricter custom endpoints stop rejecting onboarding checks that only need a tiny completion. (#66450) Thanks @WuKongAI-CMU. - Agents/subagents: emit the subagent registry lazy-runtime stub on the stable dist path that both source and bundled runtime imports resolve, so the follow-up dist fix no longer still fails with `ERR_MODULE_NOT_FOUND` at runtime. (#66420) Thanks @obviyus. - Media-understanding/proxy env: auto-upgrade provider HTTP helper requests to trusted env-proxy mode only when `HTTP_PROXY`/`HTTPS_PROXY` is active and the target is not bypassed by `NO_PROXY`, so remote media-understanding and transcription requests stop failing local DNS pre-resolution in proxy-only environments without widening SSRF bypasses. (#52162) Thanks @mjamiv and @vincentkoc. - Telegram/media downloads: let Telegram media fetches trust an operator-configured explicit proxy for target DNS resolution after hostname-policy checks, so proxy-backed installs stop failing `could not download media` on Bot API file downloads after the DNS-pinning regression. (#66245) Thanks @dawei41468 and @vincentkoc. - Browser: keep loopback CDP readiness checks reachable under strict SSRF defaults so OpenClaw can reconnect to locally started managed Chrome. (#66354) Thanks @hxy91819. - Agents/context engine: compact engine-owned sessions from the first tool-loop delta and preserve ingest fallback when `afterTurn` is absent, so long-running tool loops can stay bounded without dropping engine state. (#63555) Thanks @Bikkies. - OpenAI Codex/auth: keep malformed Codex CLI auth-file diagnostics on the debug logger instead of stdout so interactive command output stays clean while auth read failures remain traceable. (#66451) Thanks @SimbaKingjoe. - Discord/native commands: return the real status card for native `/status` interactions instead of falling through to the synthetic `✅ Done.` ack when the generic dispatcher produces no visible reply. (#54629) Thanks @tkozzer and @vincentkoc. - Hooks/Ollama: let LLM-backed session-memory slug generation honor an explicit `agents.defaults.timeoutSeconds` override instead of always aborting after 15 seconds, so slow local Ollama runs stop silently dropping back to generic filenames. (#66237) Thanks @dmak and @vincentkoc. - Media/transcription: remap `.aac` filenames to `.m4a` for OpenAI-compatible audio uploads so AAC voice notes stop failing MIME-sensitive transcription endpoints. (#66446) Thanks @ben-z. - UI/chat: replace marked.js with markdown-it so maliciously crafted markdown can no longer freeze the Control UI via ReDoS. (#46707) Thanks @zhangfnf. - 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) Thanks @omarshahine. - 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) Thanks @omarshahine. - Heartbeat/security: force owner downgrade for untrusted `hook:wake` system events [AI-assisted]. (#66031) Thanks @pgondhi987. - Browser/security: enforce SSRF policy on snapshot, screenshot, and tab routes [AI]. (#66040) Thanks @pgondhi987. - Microsoft Teams/security: enforce sender allowlist checks on SSO signin invokes [AI]. (#66033) Thanks @pgondhi987. - Config/security: redact `sourceConfig` and `runtimeConfig` alias fields in `redactConfigSnapshot` [AI]. (#66030) Thanks @pgondhi987. - 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) Thanks @100yenadmin. - 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) Thanks @zhuisDEV. - 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) Thanks @fuller-stack-dev. - 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) Thanks @frankekn. - 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) Thanks @mbelinky. - 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) Thanks @mbelinky. - 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) Thanks @mbelinky. - 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) Thanks @mbelinky. - 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) Thanks @mbelinky. - 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) Thanks @mbelinky. - 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) Thanks @mbelinky. - 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) Thanks @eleqtrizit. - Memory/Ollama: restore the built-in `ollama` embedding adapter in memory-core so explicit `memorySearch.provider: "ollama"` works again, and include endpoint-aware cache keys so different Ollama hosts do not reuse each other's embeddings. (#63429, #66078, #66163) Thanks @nnish16 and @vincentkoc. - 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) Thanks @eleqtrizit. - 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) Thanks @mbelinky. - 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) Thanks @mbelinky. - 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) Thanks @dutifulbob. - 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) Thanks @Takhoffman. - 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) Thanks @mbelinky. - Agents/subagents: ship `dist/agents/subagent-registry.runtime.js` in npm builds so `runtime: "subagent"` runs stop stalling in `queued` after the registry import fails. (#66189) Thanks @yqli2420 and @vincentkoc. - Agents/OpenAI: map `minimal` thinking to OpenAI's supported `low` reasoning effort for GPT-5.4 requests, so embedded runs stop failing request validation. Thanks @steipete. - 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) Thanks @eleqtrizit. - 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) Thanks @eleqtrizit. - Telegram/status commands: let read-only status slash commands bypass busy topic turns, while keeping `/export-session` on the normal lane so it cannot interleave with an in-flight session mutation. (#66226) Thanks @VACInc and @vincentkoc. - 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) Thanks @jetd1. - 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) Thanks @ly85206559 and @vincentkoc. - 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) thanks @jalehman - 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) Thanks @shhtheonlyperson. - 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) Thanks @suboss87 and @vincentkoc. - CLI/approvals: raise the default `openclaw approvals get` gateway timeout and report config-load timeouts explicitly, so slow hosts stop showing a misleading `Config unavailable.` note when the approvals snapshot succeeds but the follow-up config RPC needs more time. (#66239) Thanks @neeravmakwana. - Media/store: honor configured agent media limits when saving generated media and persisting outbound reply media, so the store no longer hard-stops those flows at 5 MB before the configured limit applies. (#66229) Thanks @neeravmakwana and @vincentkoc.