* feat: node-hosted plugins — dynamic tools, MCP servers, and skills
Nodes become declarative plugin hosts:
- node.pluginTools.update: node hosts publish plugin-registered agent tool
descriptors; gateway materializes them as agent tools executing via
node.invoke under the node command allowlist, with tools.effective
invalidation and node online/offline removal.
- Trusted paired-node descriptors: no gateway-side plugin registration
required; gateway.nodes.pluginTools.enabled off-switch (default on);
description/count caps; deterministic node-prefixed collision names.
- Declarative node-hosted MCP: nodeHost.mcp.servers (McpServerConfig shape)
starts MCP clients on the node host, publishes tools as pluginId node-mcp,
executes via built-in mcp.tools.call.v1 with per-layer timeouts, failure
isolation, and orphan-safe shutdown. No re-pairing when servers change.
- Node-hosted skills: node.skills.update publishes ~/.openclaw/skills
content (64 skills/64KB/512KB caps both sides); gateway merges them into
the skills snapshot while connected and exec host=node is available, with
node:// locators, node-prefixed collisions, disabled command dispatch,
and gateway.nodes.skills.enabled + nodeHost.skills.enabled switches.
- Security: node-supplied pluginIds cannot satisfy pluginId-scoped tool
allowlists unless gateway-registered; reserved node-mcp id requires the
core MCP descriptor shape; protocol registry kept out of public
plugin-sdk dts.
- E2E: pond harness proves publication, MCP round-trip, skills locator, and
disconnect/reconnect for all three surfaces.
* style: format node-plugin-tools test
* fix(skills): keep status loader unfiltered when eligibility is passed
skills.status started passing eligibility for the node-skill merge, which
flipped loadWorkspaceSkillEntries into filtered mode and dropped disabled
skills from status reports (QA plugin-lifecycle-hot-reload timeout). Status
now merges node skills explicitly around an unfiltered load. Also: regen
docs_map for new node docs sections; add the intentional node-host MCP
onclose suppression to the lint-suppression allowlist.
* feat(mattermost): add opt-in DM threading via dmReplyToMode
Resolves#93203.
Mattermost direct messages are hardcoded non-threaded: resolveMattermostReplyToMode
returns "off" for direct chats before consulting config, and the reply-root /
effective-reply resolvers short-circuit for direct chats. So every DM accretes into
one ever-growing session with unbounded per-session token usage, with no way to
isolate each DM topic the way groups/channels (and Slack) can.
Add channels.mattermost.dmReplyToMode (same enum as replyToMode), default "off" so
existing flat-DM deployments are unchanged. When set to "first"/"all", a DM @mention
starts an independent, thread-scoped session:
- resolveMattermostReplyToMode: direct chats return config.dmReplyToMode ?? "off".
- resolveMattermostEffectiveReplyToId: direct early-return gated on replyToMode "off"
(the value already reflects dmReplyToMode for direct chats).
- resolveMattermostReplyRootId: direct early-return gated on the absence of a thread
root (a DM carries one only when DM threading is enabled).
- New DM threads start fresh (no parent-session inheritance) so each topic is isolated;
a threaded DM keeps its own history key while a flat DM root keeps none.
Default-off preserves the documented flat-DM contract, so this changes no existing
behavior. Adds unit coverage and documents the opt-in. The only open question is the
knob shape (dmReplyToMode enum vs a boolean dmThreading) — happy to adjust.
Refs #65729.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(mattermost): register dmReplyToMode in config schema
dmReplyToMode was wired into the account config type and reply
resolution but never added to MattermostConfigSchema, so setting it in
openclaw.json failed config validation ("must not have additional
properties: dmReplyToMode") and the gateway refused to start — the knob
could not actually be enabled. Register it in the schema, regenerate the
bundled channel config metadata and doc baseline, and add a
config-schema test.
* fix(mattermost): thread direct reply transport when dmReplyToMode is on
resolveReplyTransport nulled the direct reply root/thread id
unconditionally, so routed replies and message-tool follow-ups in an
opted-in DM thread were still sent flat even when the effective
replyToMode was first/all. Keep direct transport flat only when the mode
is off (the historical contract) and preserve the thread root otherwise,
matching the monitor-level DM threading gates. Adds channel.test.ts
coverage for resolveReplyTransport.
* fix(mattermost): use per-chat reply mode overrides
* fix(mattermost): bound direct thread history
* chore(config): refresh docs baseline
---------
Co-authored-by: leon <leon@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* fix(anthropic): don't crash models list when a configured Sonnet 5 model has no cost
applyAnthropicSonnet5Cost read params.model.cost.input unconditionally, so
'openclaw models list' aborted with 'Cannot read properties of undefined
(reading input)' whenever config supplied an anthropic Sonnet 5 model row
without cost metadata (e.g. an agents.defaults.models runtime binding).
Guard with optional chaining — a costless model now falls through and gets
the canonical Sonnet 5 cost applied.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(models): normalize missing Sonnet 5 costs
Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com>
* chore(plugin-sdk): refresh API baseline
* ci(plugin-sdk): update surface budgets
---------
Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* feat: correlate native search outcomes in audit history
Metadata-only audit ledger for agent runs and tool actions in the shared
state DB: stable event identity, closed action/status/error vocabularies,
one-way-hashed tool-call ids, never-inferred terminal outcomes for native
web-search (explicit completed/failed only; otherwise unknown), bounded
retention, audit.list gateway RPC and openclaw audit CLI. Squashed from
the 82-commit audit stack for replay onto current main.
* feat(audit): add audit.enabled config gate (default on)
The metadata-only audit ledger records by default: an audit trail enabled
only after an incident cannot explain the incident, and the rows are
strictly less sensitive than the transcripts every install already
stores. audit.enabled=false stops new writes at the gateway subscription
seam; audit.list and openclaw audit keep serving existing records until
they expire. Documented in the configuration reference, protocol page,
and CLI reference.
* fix: repair full-matrix CI findings after rebase
- break the dynamic-tools/dynamic-tool-execution import cycle by
extracting resolveCodexToolAbortTerminalReason into a leaf module
- restore main's session-worktree protocol exports lost in the
index.ts auto-merge
- register the audit event writer worker as a knip entry point
- docs table formatting; subagent wait-cancellation test scoped to its
audit intent (outcome + timing) and advanced past main's new
lifecycle-timeout retry grace
* feat(slack): add ignoreOtherMentions channel config
Mirrors the existing Discord `ignoreOtherMentions` option for Slack
channels. When set on a channel entry, drop channel/group/MPIM messages
that mention another user or subteam but not this bot — the inverse of
`requireMention`. Useful in busy channels where the bot would otherwise
reply to side conversations.
Implementation lives in `prepareSlackMessage` right after the
`allowBots: "mentions"` bot-drop gate and before the `shouldRequireMention`
non-mention drop, so it integrates with the new `messageIngress` ingress
pipeline. The gate is conditional on `canDetectMention` (botUserId
resolvable via `auth.test` or explicit mention regexes configured) to
avoid false drops when we have no reliable way to tell bot vs non-bot
mentions apart.
Slack implicit mentions (thread participation) are intentionally NOT
respected here — they fire for every message in a bot-participated
thread, so honoring them would defeat the feature in any active thread.
The gate matches on `wasMentioned` (explicit) and `hasAnyMention`, with
the existing `shouldBypassMention` override (e.g. authorized commands)
also respected.
Includes config types, zod schema, channel-config resolution,
prepare-message implementation, full test coverage in
`prepare.test.ts`, regenerated channel + docs baselines, and Slack
docs entry.
* refactor(slack): harden other-mention filtering
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
