* refactor: extract reusable AI runtime package
* refactor: complete AI provider relocation
* refactor: keep llm core internal
* refactor(ai): make @openclaw/ai self-contained with host policy ports
Move pure transport helpers (tool projections, strict-schema normalization,
prompt-cache boundary, stream guards, anthropic/openai compat, request
activity) from src into packages/ai; move utf16-slice into
normalization-core. Inject host policy (guarded fetch, redaction,
strict-tool defaults, diagnostics logging) through AiTransportHost with
inert library defaults installed by src/llm/stream.ts. Narrow the public
barrel to instance-scoped createApiRegistry/createLlmRuntime; the
process-default runtime moves behind internal/ and
registerBuiltInApiProviders takes an explicit registry. Delete the
src/llm/api-registry re-export facade.
* fix(ai): teach node, jiti, and vite resolvers the @openclaw/ai and utf16-slice subpaths
The workspace alias tables in root-alias.cjs, plugin-sdk-native-resolver,
sdk-alias, the shared vitest config, and the Control UI vite config only
knew @openclaw/llm-core; Node-side plugin loading resolved @openclaw/ai
through the pnpm symlink to the unbuilt dist (checks-node-compact CI
failures), and the Control UI build broke on the new
normalization-core/utf16-slice subpath.
* chore(ui): drop leftover service-worker debug logging
* build(release): ship @openclaw/ai with its own shrinkwrap and honest dependency set
packages/ai declares only its six real runtime deps (kysely, chalk, json5,
tslog, zod, fs-safe, and proxyline were never imported); orphaned root deps
removed. generate-npm-shrinkwrap now treats publishable packages/* like
publishable plugins so the AI tarball pins its transitive tree even though
workspace deps are omitted from the root shrinkwrap. knip learns the
package entry points; the tsdown dts neverBundle option moves to its
documented deps.dts home; the README documents the no-semver internal/*
contract and host ports.
* docs(ai): add minimal external-consumer example app
examples/ai-chat consumes only the public @openclaw/ai surface (built dist
via the workspace link): isolated runtime, built-in provider registration,
one streamed completion. Supports Anthropic/OpenAI via env keys and a
keyless local Ollama target; live-verified against Ollama.
* docs(ai): document the @openclaw/ai package and workspace shrinkwrap boundary
* chore(check): include examples/ in duplicate-scan targets
* fix: emit normalization package subpaths
* fix: complete AI package boundary artifacts
* fix: align AI package boundary contracts
* fix(ci): stabilize package release contracts
* test: align documentation contract checks
* test: keep cron docs guard aligned
* test: align restored docs contract guards
* test: follow upstream docs contracts
* docs: drop superseded talk wording
Allow busy TUI sessions to forward prompts into the configured queue while
keeping queued-turn admission, cancellation, restart, and transcript ownership
consistent across the TUI, Gateway, and followup queue.
Co-authored-by: Sebastien Tardif <sebtardif@ncf.ca>
* feat(gateway): add device.pair.setupCode RPC for connect QR
The OpenClaw mobile/companion app scans a pairing setup code to connect to the gateway, but that code + QR could only be produced by the openclaw qr CLI (ASCII to stdout). Non-terminal clients driving onboarding had no way to display the connect QR.
Add a device.pair.setupCode gateway method that reuses resolvePairingSetupFromConfig + encodePairingSetupCode + renderQrPngDataUrl to return { setupCode, qrDataUrl?, gatewayUrl, auth, urlSource }. The embedded setup code mints a short-lived bootstrap token that hands off broad operator scopes (read/write/approvals/talk.secrets), so the method requires operator.admin (matching the wizard methods a companion already uses) and is not advertised. auth is a label only; the gateway credential is never returned, and an oversized QR is omitted so the response always satisfies the result schema.
Refs #94661.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* feat(ui): pair mobile devices from Control UI
* docs: refresh generated docs map
* docs: clarify mobile QR auto-connect
* docs: clarify mobile QR auto-connect
* docs: clarify mobile QR auto-connect
---------
Co-authored-by: Barbara Kudiess <76582160+bkudiess@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Claude Fable 5 requests on direct Anthropic API keys now opt into Anthropic's server-side fallback (server-side-fallback-2026-06-01): a safety-classifier decline is re-served by claude-opus-4-8 inside the same call instead of failing the turn with "LLM request failed.". Mid-stream boundaries drop the declined model's thinking/tool blocks per Anthropic's replay contract, keep the partial text as the continuation prefix, record a provider_fallback diagnostic, and cost the turn at the serving model's rates. Docs lead with the coupling: using Fable 5 means also using Opus 4.8. OAuth, proxies, Bedrock, Vertex, and Foundry requests are unchanged.
Live-verified: a benign reasoning_extraction classifier decline through the product path returns an Opus-served answer with the provider_fallback diagnostic; exact-head CI green (67 checks).
Related: #98976
Summary:
- The PR changes the docs map generator to escape HTML-significant heading text, regenerates `docs/docs_map.md`, and adds a Vitest regression for HTML-like headings.
- PR surface: Tests +13, Docs 0, Other +10. Total +23 across 3 files.
- Reproducibility: yes. Current main has source headings such as `docs/cli/agents.md:164` with `<id>`, while `docs/docs_map.md:1231` omits it and `scripts/generate-docs-map.mjs:90` strips `<...>` text.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 261466a2a8.
- Required merge gates passed before the squash merge.
Prepared head SHA: 261466a2a8
Review: https://github.com/openclaw/openclaw/pull/99099#issuecomment-4866739708
Co-authored-by: Mason Huang <masonxhuang@tencent.com>
Approved-by: hxy91819
* feat(signal): add target aliases
* fix(signal): canonicalize alias delivery targets
* fix(signal): harden alias target resolution
* test(signal): cover formatted media aliases
* test(signal): align approval alias proof with request shape
* Reuse Signal alias map for directory listing
* 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>
* 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>
