Verified:
- pnpm install --frozen-lockfile
- pnpm build
- pnpm vitest run extensions/feishu/src/docx.test.ts

Co-authored-by: Tao Xie <7379039+TaoXieSZ@users.noreply.github.com>

…#53115)

When a local run ends with an empty final event while another run is active,
skip history reload to prevent clearing the user's pending message from the
chat log. This fixes the 'message disappears' issue with slow models like Ollama.

…lnishanth)

…workspace, macOS config tree (openclaw#53411) thanks @BunsDev

Co-authored-by: BunsDev <68980965+BunsDev@users.noreply.github.com>
Co-authored-by: Nova <nova@openknot.ai>

…erminal sanitization, URL scheme allowlisting (openclaw#53471) thanks @BunsDev

Co-authored-by: BunsDev <68980965+BunsDev@users.noreply.github.com>
Co-authored-by: Nova <nova@openknot.ai>

…f calls

- SAFE_GO_MODULE: allow uppercase in module paths (A-Z)
- SAFE_BREW_FORMULA: allow @ for versioned formulas (python@3.12)
- SAFE_UV_PACKAGE: allow extras [standard] and equality pins ==
- Cache safeExternalHref result in skills detail API key section

Merged via squash.

Prepared head SHA: e23bde8
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Reviewed-by: @mbelinky

…#50831) (openclaw#50842)

Merged via squash.

Prepared head SHA: 0f743bf
Co-authored-by: Hollychou924 <128659251+Hollychou924@users.noreply.github.com>
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Reviewed-by: @altaywtf

…nt runs

Root cause: Telegram channel monitor captures config at startup before secrets
are resolved and passes it as configOverride into the reply pipeline. Since
getReplyFromConfig() uses configOverride directly (skipping loadConfig() which
reads the resolved runtime snapshot), the unresolved SecretRef objects propagate
into FollowupRun.run.config and crash runEmbeddedPiAgent().

Fix (defense in depth):
- get-reply.ts: detect unresolved SecretRefs in configOverride and fall back to
  loadConfig() which returns the resolved runtime snapshot
- message-tool.ts: try-catch around schema/description building at tool creation
  time so channel discovery errors don't crash the agent
- message-tool.ts: detect unresolved SecretRefs in pre-bound config at tool
  execution time and fall back to gateway secret resolution

Fixes: openclaw#45838

* Discord: use session model for /think autocomplete

* Discord: use cached session store in think autocomplete

* Discord: align think autocomplete with effective bound route

* Discord: fix think autocomplete route-resolution test mocks

* Discord: stabilize think autocomplete CI coverage

* Discord: gate think autocomplete context behind auth

* Discord: share slash auth for think autocomplete

* Discord: localize think autocomplete auth gate

* Discord: drop think autocomplete auth gating

* Discord: align native autocomplete auth and route readiness

* Discord: use effective route for model picker

---------

Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>

* test(memory): lock qmd status counts regression

* feat: make /tools show what the agent can use right now

* fix: sync web ui slash commands with the shared registry

* feat: add profile and unavailable counts to /tools

* refine: keep /tools focused on available tools

* fix: resolve /tools review regressions

* fix: honor model compat in /tools inventory

* fix: sync generated protocol models for /tools

* fix: restore canonical slash command names

* fix: avoid ci lint drift in google helper exports

* perf: stop computing unused /tools unavailable counts

* docs: clarify /tools runtime behavior

…#54184)

…03-25