nyrn
/
openclaw
mirror of https://github.com/openclaw/openclaw.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

docs: tune unreleased changelog priorities

This commit is contained in:
Peter Steinberger 2026-03-31 18:02:47 +01:00
parent d794c5ca56
commit b9f8bb6308
No known key found for this signature in database
1 changed files with 5 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
CHANGELOG.md
View File

@ -9,6 +9,10 @@ Docs: https://docs.openclaw.ai
- 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: remove legacy provider compat subpaths plus the old bundled provider setup and channel-specific SDK shims, so plugins and extensions must use the current documented `openclaw/plugin-sdk/*` entrypoints and local `api.ts` / `runtime-api.ts` barrels instead of removed compatibility surfaces.
- Skills/install: fail closed on dangerous-code skill installs by default, so installs that previously succeeded with critical dangerous findings now require an explicit unsafe override to proceed.
- Plugins/install: built-in dangerous-code `critical` findings and install-time scan failures now block plugin installs and gateway-backed skill dependency installs by default unless you explicitly use the dangerous override path, so previously tolerated installs can now fail closed.
- 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. Thanks @zhangning-agent, @jacobtomlinson, and @vincentkoc.
- 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) Thanks @jacobtomlinson.
- 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) Thanks @jacobtomlinson.
### Changes
@ -16,8 +20,8 @@ Docs: https://docs.openclaw.ai
- 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) Thanks @liuy.
- 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) Thanks @ziomancer.
- Android/notifications: add notification-forwarding controls with package filtering, quiet hours, rate limiting, and safer picker behavior for forwarded notification events. (#40175) Thanks @nimbleenigma.
- 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. Thanks @vincentkoc and @mbelinky.
- 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) Thanks @sliverp.
- 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. Thanks @vincentkoc and @mbelinky.
- ClawFlow: add the first linear 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.
- 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) thanks @gumadeiras.
- Flows/tasks: add a minimal SQLite-backed 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.
@ -35,7 +39,6 @@ Docs: https://docs.openclaw.ai
- 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) Thanks @merc1305 and @vincentkoc.
- Plugins/hooks: add a `before_install` hook with structured request provenance, built-in scan status, and install-target metadata so external security scanners and policy engines can review and block skill, plugin package, plugin bundle, and single-file plugin installs. (#56050) thanks @odysseus0.
- Plugins/install: add `--dangerously-force-unsafe-install` as a break-glass override for built-in dangerous-code install false positives while still keeping plugin `before_install` policy blocks and scan-failure blocking intact.
- Skills/install: block gateway-backed skill dependency installs on built-in dangerous-code `critical` findings unless the caller explicitly sets the matching dangerous override, while keeping suspicious findings warn-only and preserving `before_install` hook blocks.
- 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. Thanks @vincentkoc.
- TTS: Add structured provider diagnostics and fallback attempt analytics. (#57954) Thanks @joshavant.
- 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. Thanks @mcaxtr.
@ -92,13 +95,9 @@ Docs: https://docs.openclaw.ai
- Feishu/groups: keep quoted replies and topic bootstrap context aligned with group sender allowlists so only allowlisted thread messages seed agent context. Thanks @AntAISecurityLab and @vincentkoc.
- 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) Thanks @Syysean.
- 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. Thanks @kexinoh and @vincentkoc.
- Gateway/auth: make local-direct `trusted-proxy` fallback require the configured shared token instead of silently authenticating same-host callers, while keeping same-host reverse proxy identity-header flows on the normal trusted-proxy path. Thanks @zhangning-agent and @vincentkoc.
- Gateway/auth: reject mismatched browser `Origin` headers on trusted-proxy HTTP operator requests while keeping origin-less headless proxy clients working. Thanks @AntAISecurityLab and @vincentkoc.
- Gateway/auth: reject mixed trusted-proxy token configs and fail closed for loopback trusted-proxy auth so ambiguous shared-token setups no longer silently authenticate on the wrong path. (#58371) Thanks @jacobtomlinson.
- 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. Thanks @zsxsoft and @vincentkoc.
- 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) Thanks @karesansui-u.
- Gateway/node commands: require node pairing before enabling node-command access, request pairing on initial connect, and filter pending node-pairing commands until trust is established. (#57777) Thanks @jacobtomlinson.
- Gateway/node events: harden node event trust boundaries so node-originated summaries and related session events stay on the intended trusted surface. (#57691) Thanks @jacobtomlinson.
- 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. Thanks @malaiwah and @vincentkoc.
- 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) Thanks @openperf.
- 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. Thanks @davidluzsilva and @vincentkoc.