Summary:
- The branch adds plugin package live-proof guidance to the testing skill and plugin docs, separating npm-pack package validation from official-trust proof and documenting runtime dependency and compiled-entry checks.
- PR surface: Docs +111. Total +111 across 3 files.
- Reproducibility: not applicable. this is a documentation and skill-guidance clarification PR rather than a bug report. I validated the documented claims against current source, adjacent docs, tests, and live PR checks.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head b56efcffc5.
- Required merge gates passed before the squash merge.
Prepared head SHA: b56efcffc5
Review: https://github.com/openclaw/openclaw/pull/99962#issuecomment-4882084565
Co-authored-by: Mason Huang <masonxhuang@tencent.com>
Approved-by: hxy91819
* fix(interactive): preserve button command values in fallback text for degraded approval UX
* fix(interactive): keep callback values private in fallback text and narrow Feishu interactive detection
- P1: Skip rendering action.type === "callback" values in
renderMessagePresentationFallbackText to avoid leaking opaque
channel/plugin data into user-visible text. Command and legacy
values are still rendered.
- P2: Replace hasMessagePresentationBlocks/hasInteractiveReplyBlocks
with isMessagePresentationInteractiveBlock so Feishu comment
guidance only appears when the presentation actually contains
buttons or selects, not for text-only blocks.
- Update tests: callback button now shows label-only; all 137 tests pass.
* fix(interactive): only render typed command values in fallback text, keep legacy value private
* fix(feishu): gate document-comment command guidance on actual command action
* docs(message-presentation): document command/callback value fallback visibility
* fix(feishu): omit command guidance when URL overrides fallback command text
* docs: regenerate docs_map.md
* fix(interactive): exclude disabled buttons from fallback command rendering and guidance
* fix(interactive): extract hasRenderedCommandAction, exclude disabled buttons from command fallback
* fix(feishu): preserve command guidance marker through core presentation rendering
* fix(feishu): type-narrow channelData.feishu with isRecord before reading rendered-command marker
* fix(feishu): move hasRenderedCommandAction from public SDK into Feishu plugin as local helper
Keep the helper local to the only caller (Feishu outbound) instead of
adding a new public plugin SDK API contract. The shared fallback renderer
in renderMessagePresentationFallbackText already inlines the same
command-visibility logic; a local helper is sufficient for the Feishu
comment-thread guidance gate.
* refactor(feishu): tighten fallback command marker
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* Route LAN pairing URLs by default route
* Advertise route-aware LAN Control UI links
* Fix route-aware LAN test mocks
* Narrow advertised LAN SDK export
Preserve structured tool-result replay text across provider transports while keeping provider-facing redaction and Anthropic media ordering intact.
Thanks @snowzlmbot!
* feat(openai): add GPT-5.6 series support
* docs: refresh map for GPT-5.6
* fix(openai): preserve GPT-5.6 thinking metadata
* fix(codex): sync managed app server version
* fix(codex): sync managed app server version
* fix(openai): account for GPT-5.6 cache writes
---------
Co-authored-by: Peter Steinberger <steipete@golden-gate.local>
* fix(codex): prefer desktop app-server for Computer Use on macOS
* fix(codex): fall back from stale desktop app-server
---------
Co-authored-by: Benjamin Badejo <ben@benbadejo.com>
In resolveAgentDeliveryPlanWithSessionRoute, reserved-literal errors from the
sync outbound target check are no longer treated as fatal. Instead, the path
proceeds to resolveOutboundSessionRoute which calls resolveMessagingTarget,
already fixed to do directory-first lookup before rejecting reserved literals.
This preserves configured Telegram directory entries named like reserved words
(current, self, this, me) through the explicit agent/gateway delivery path.
Update docs to reflect directory-first ordering.
Move Canvas, Discord, Slack, voice-call, and WhatsApp skill docs from the root bundled skill tree into their owning plugin packages, with manifest skills declarations and docs/test path updates.
Validation:
- node --import tsx scripts/sync-plugin-versions.ts --check
- node scripts/run-vitest.mjs src/skills/loading/env-path-guidance.test.ts
- autoreview clean
- Crabbox Azure pnpm check:changed run_59ba76511d57 / lease cbx_cbc6750dad72
- wrapper prepare passed pnpm install --frozen-lockfile, pnpm build, and pnpm check before the oversized full local pnpm test was stopped
Follow-up: #95132 remains as the stacked PR for the rest of the starter-skill/Sherpa/ClawHub work.
The Subagents section of docs/plugins/hooks.md listed subagent_ended
but did not describe its payload. Plugin authors reaching for
agentId (as on subagent_spawned) silently got undefined because
PluginHookSubagentEndedEvent uses targetSessionKey as its identity
field and has no agentId/childSessionKey.
Document all fields from PluginHookSubagentEndedEvent and explicitly
note the missing identity fields so handlers can correlate events
correctly.
Closes#95186
Co-authored-by: MaHaoHao-ch <MaHaoHao-ch@users.noreply.github.com>
