Notes de version
Added
- iOS: alpha node app + setup-code onboarding. (#11756) Thanks @mbelinky.
- Channels: comprehensive BlueBubbles and channel cleanup. (#11093) Thanks @tyler6204.
- Plugins: device pairing + phone control plugins (Telegram
/pair, iOS/Android node controls). (#11755) Thanks @mbelinky. - Tools: add Grok (xAI) as a
web_searchprovider. (#12419) Thanks @tmchow. - Gateway: add agent management RPC methods for the web UI (
agents.create,agents.update,agents.delete). (#11045) Thanks @advaitpaliwal. - Web UI: show a Compaction divider in chat history. (#11341) Thanks @Takhoffman.
- Agents: include runtime shell in agent envelopes. (#1835) Thanks @Takhoffman.
- Paths: add
OPENCLAW_HOMEfor overriding the home directory used by internal path resolution. (#12091) Thanks @sebslight.
Fixes
- Telegram: harden quote parsing; preserve quote context; avoid QUOTE_TEXT_INVALID; avoid nested reply quote misclassification. (#12156) Thanks @rybnikov.
- Telegram: recover proactive sends when stale topic thread IDs are used by retrying without
message_thread_id. (#11620) - Telegram: render markdown spoilers with
<tg-spoiler>HTML tags. (#11543) Thanks @ezhikkk. - Telegram: truncate command registration to 100 entries to avoid
BOT_COMMANDS_TOO_MUCHfailures on startup. (#12356) Thanks @arosstale. - Telegram: match DM
allowFromagainst sender user id (fallback to chat id) and clarify pairing logs. (#12779) Thanks @liuxiaopai-ai. - Onboarding: QuickStart now auto-installs shell completion (prompt only in Manual).
- Auth: strip embedded line breaks from pasted API keys and tokens before storing/resolving credentials.
- Web UI: make chat refresh smoothly scroll to the latest messages and suppress new-messages badge flash during manual refresh.
- Tools/web_search: include provider-specific settings in the web search cache key, and pass
inlineCitationsfor Grok. (#12419) Thanks @tmchow. - Tools/web_search: normalize direct Perplexity model IDs while keeping OpenRouter model IDs unchanged. (#12795) Thanks @cdorsey.
- Model failover: treat HTTP 400 errors as failover-eligible, enabling automatic model fallback. (#1879) Thanks @orenyomtov.
- Errors: prevent false positive context overflow detection when conversation mentions "context overflow" topic. (#2078) Thanks @sbking.
- Gateway: no more post-compaction amnesia; injected transcript writes now preserve Pi session
parentIdchain so agents can remember again. (#12283) Thanks @Takhoffman. - Gateway: fix multi-agent sessions.usage discovery. (#11523) Thanks @Takhoffman.
- Agents: recover from context overflow caused by oversized tool results (pre-emptive capping + fallback truncation). (#11579) Thanks @tyler6204.
- Subagents/compaction: stabilize announce timing and preserve compaction metrics across retries. (#11664) Thanks @tyler6204.
- Cron: share isolated announce flow and harden scheduling/delivery reliability. (#11641) Thanks @tyler6204.
- Cron tool: recover flat params when LLM omits the
jobwrapper for add requests. (#12124) Thanks @tyler6204. - Gateway/CLI: when
gateway.bind=lan, use a LAN IP for probe URLs and Control UI links. (#11448) Thanks @AnonO6. - Hooks: fix bundled hooks broken since 2026.2.2 (tsdown migration). (#9295) Thanks @patrickshao.
- Routing: refresh bindings per message by loading config at route resolution so binding changes apply without restart. (#11372) Thanks @juanpablodlc.
- Exec approvals: render forwarded commands in monospace for safer approval scanning. (#11937) Thanks @sebslight.
- Config: clamp
maxTokenstocontextWindowto prevent invalid model configs. (#5516) Thanks @lailoo. - Thinking: allow xhigh for
github-copilot/gpt-5.2-codexandgithub-copilot/gpt-5.2. (#11646) Thanks @LatencyTDH. - Discord: support forum/media thread-create starter messages, wire
message thread create --message, and harden routing. (#10062) Thanks @jarvis89757. - Paths: structurally resolve
OPENCLAW_HOME-derived home paths and fix Windows drive-letter handling in tool meta shortening. (#12125) Thanks @mcaxtr. - Memory: set Voyage embeddings
input_typefor improved retrieval. (#10818) Thanks @mcinteerj. - Memory/QMD: reuse default model cache across agents instead of re-downloading per agent. (#12114) Thanks @tyler6204.
- Media understanding: recognize
.cafaudio attachments for transcription. (#10982) Thanks @succ985. - State dir: honor
OPENCLAW_STATE_DIRfor default device identity and canvas storage paths. (#4824) Thanks @kossoy.
Fichiers à télécharger
| Fichier | Taille | Téléchargements | Télécharger |
|---|---|---|---|
| OpenClaw-2026.2.9.dmg | 17.3 MB | 27,429 | Télécharger |
| OpenClaw-2026.2.9.dSYM.zip | 32.3 MB | 3,031 | Télécharger |
| OpenClaw-2026.2.9.zip | 21.8 MB | 22,089 | Télécharger |