Add bounded realtime profile context for Discord realtime voice sessions.
Default to `IDENTITY.md`, `USER.md`, and `SOUL.md`; `voice.realtime.bootstrapContextFiles: []` disables the extra context.
Document the config/SDK surface and refresh generated metadata.
Co-authored-by: FullerStackDev <263060202+fuller-stack-dev@users.noreply.github.com>
Summary:
- The branch caps async diagnostic drains at 100 events per turn, adds pending/full-drain diagnostic helpers, ... rminal diagnostics to inspect pending events, and adds regression coverage plus changelog/baseline updates.
- Reproducibility: yes. from source inspection. Current main drains the entire async diagnostic queue in one s ... ck, and the PR body supplies a focused 250-event after-fix probe showing 100/200/250 delivery across turns.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix: yield diagnostic event drains
Validation:
- ClawSweeper review passed for head 95610934cd.
- Required merge gates passed before the squash merge.
Prepared head SHA: 95610934cd
Review: https://github.com/openclaw/openclaw/pull/82937#issuecomment-4469498220
Co-authored-by: Galin Iliev <galini@microsoft.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Summary:
- The branch adds a close lifecycle for local memory embedding providers, scoped memory search/index teardown for one agent, Active Memory timeout cleanup, focused tests, and a changelog entry.
- Reproducibility: yes. The linked issue gives a concrete OpenClaw 2026.5.18 Telegram Active Memory timeout pa ... current-main source inspection confirms there is no timeout cleanup for that local embedding provider path.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(memory): close local embedding providers on timeout
Validation:
- ClawSweeper review passed for head 8e2e369b5c.
- Required merge gates passed before the squash merge.
Prepared head SHA: 8e2e369b5c
Review: https://github.com/openclaw/openclaw/pull/84048#issuecomment-4485705481
Co-authored-by: brokemac79 <martin_cleary@yahoo.co.uk>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: hxy91819
Co-authored-by: hxy91819 <8814856+hxy91819@users.noreply.github.com>
Keep QMD-exported archived session transcript hits visible by resolving QMD `.md` archive stems back to their live session ids before applying session visibility policy. Preserve normal markdown session ids that only resemble archive names, reject ambiguous slug fallback matches, and keep deleted same-agent QMD archives readable when the live store entry is gone.
Fixes#83506.
Co-authored-by: tanshanshan <tanshanshan@users.noreply.github.com>
OAuth login flow
----------------
- Hard-require refresh_token after the authorization-code exchange in
xai-oauth.ts. Access-only responses persisted credentials that the
downstream usability check later rejected; the new requireRefreshToken
option fails the exchange instead. Error wording explains the missing
refresh_token in OIDC scope terms (offline_access scope rejected),
not a "grant".
- Derive token expiry from the access-token JWT exp claim when
expires_in is missing. id_token exp is intentionally not used as a
fallback because id_token lifetime tracks the OIDC session, not the
access token, and would defer refresh past actual expiry.
- Handle CORS preflight OPTIONS on the loopback OAuth callback in
src/plugin-sdk/provider-auth-runtime.ts. The previous handler treated
any non-callback request as a failed GET, returned "Missing code or
state", and tore the server down before the real GET arrived. The
CORS allowlist is now an optional `corsOriginAllowlist` parameter on
waitForLocalOAuthCallback so the SDK helper stays generic. The xAI
plugin passes ["auth.x.ai", "accounts.x.ai"] from loginXaiOAuth.
Sidecar surfaces
----------------
- speech-provider.ts (POST /v1/tts) honors the xAI OAuth profile in
addition to provider config and XAI_API_KEY. isConfigured now also
reports true when an xAI auth profile is configured (via
isProviderAuthProfileConfigured), so OAuth-only users are no longer
silently filtered out by the selection layer. The bearer resolver
threads req.cfg into resolveApiKeyForProvider so the right xAI auth
profile is picked when a user has multiple.
- realtime-transcription-provider.ts (WSS /stt) gets the same
isConfigured fix, and the lazy headers() resolver threads req.cfg
into the OAuth bearer lookup. createSession stays sync per its
plugin contract.
- stt.ts: drop the plugin-side OAuth fallback. The media-understanding
core already resolves auth (cfg/agentDir-aware) via
resolveProviderExecutionContext before calling transcribeAudio, so
the wrapper was redundant. transcribeAudio is now the registered
hook directly.
User-Agent attribution
----------------------
- New buildXaiAttributionPolicy in src/agents/provider-attribution.ts
injects User-Agent: openclaw/<version>, originator, and version on
/v1/responses and /v1/chat/completions traffic that goes through
resolveProviderRequestHeaders. Gated to xai-native and default
endpoint classes; custom proxy baseUrls remain withheld. reviewNote
is honest about which headers are spec-verified vs mirrored.
- Shared extensions/xai/src/xai-user-agent.ts helper exports
xaiUserAgentHeaderFor(baseUrl) which only emits the User-Agent when
the resolved baseUrl points at the xAI-native API host. Threaded
through TTS and realtime STT (WS upgrade headers) so user-configured
proxy baseUrls do not receive the openclaw identity. OAuth discovery
and token endpoints still send User-Agent unconditionally because
isTrustedXaiOAuthEndpoint already restricts those URLs to *.x.ai.
- Image gen, batch STT, and video gen rely on the attribution policy
alone (no manual User-Agent in defaultHeaders), so attribution
withholding on user-configured proxy baseUrls is preserved
end-to-end.
- UA is bearer-agnostic: same value whether the bearer comes from an
xAI API key or the xAI OAuth flow.
Drop dead api.grok.x.ai alias
-----------------------------
- xAI retired the api.grok.x.ai alias; DNS now returns NXDOMAIN from
xAI's own authoritative nameservers. Drop it from the xai-native
endpoint host set in extensions/xai/openclaw.plugin.json,
extensions/xai/api.ts, extensions/xai/tts.ts, and the
openai-responses payload policy. Update the attribution test to
classify api.grok.x.ai as "custom" (no live user can reach it; the
classification keeps documenting the host's status).
Video generation now matches xAI's actual API behavior
------------------------------------------------------
Previously, real video generation requests failed with
"xAI video generation response malformed" because the poll-status
handler validated against a closed enum that did not match what the
xAI service actually returns. Four fixes:
- Loosen the poll-status handler. xAI returns intermediate strings
outside `["queued", "processing", "done", "failed", "expired"]`
(commonly `submitted`, `pending`, `in_progress`, ...). Treat `done`
as terminal-success, `["failed", "error", "expired", "cancelled"]`
as terminal-failure, and any other string (including empty) as
continue-polling. Also accept `cancelled` as a terminal failure.
- Send default duration/aspect_ratio/resolution on every generate and
reference-image submit. xAI rejects bodies that omit these fields.
Defaults: duration=8s, aspect_ratio="16:9", resolution="720p".
- Accept lowercase resolution input ("480p"/"720p"/"1080p") in
addition to uppercase, normalize to lowercase on the wire.
- Add an `x-idempotency-key` header (fresh `crypto.randomUUID()`) on
every submit so a network retry does not double-charge the user.
Polls intentionally reuse the unmodified `headers` without the key.
Ergonomics
----------
- All "missing xAI credentials" errors (code_execution, lazy
code_execution fallback in extensions/xai/index.ts, x_search,
web_search grok in web-search-provider.runtime.ts, TTS, batch STT,
realtime STT) now mention `openclaw onboard --auth-choice xai-oauth`
first.
- Dedupe the Grok model-id alias table: model-compat.ts re-exports
normalizeXaiModelId from model-id.ts as normalizeNativeXaiModelId.
Test coverage
-------------
- src/plugin-sdk/provider-auth-runtime.test.ts: locks the new pure
buildOAuthCallbackOriginResolver gate (allowlist match,
case-normalization, https-only, non-allowlisted hosts dropped,
multi-Origin handling).
- extensions/xai/xai-oauth.test.ts: locks
XAI_OAUTH_CALLBACK_CORS_ORIGIN_ALLOWLIST so loginXaiOAuth keeps
threading the right hosts to the SDK helper.
- extensions/xai/speech-provider.test.ts: OAuth-only auth profile
flips isConfigured to true; cfg threads into the OAuth fallback
resolver.
- extensions/xai/realtime-transcription-provider.test.ts: same +
upgrade headers carry the OAuth bearer end-to-end.
- extensions/xai/stt.test.ts: explicit assertion that transcribeAudio
trusts the core-resolved apiKey (no plugin-side wrapper).
Verification
------------
- pnpm install: clean
- 154/154 vitest tests pass across 13 touched test files
- pnpm check:changed: typecheck core/ext + tests, oxlint core/ext,
runtime guards, dependency pin guard, package patch guard, runtime
import cycles, sidecar loader guard - all green
- pnpm build: 0 errors, 0 [INEFFECTIVE_DYNAMIC_IMPORT] warnings
* feat(doctor): add --lint mode + structured HealthFinding shape
Adds the core machinery for `openclaw doctor --lint` per the
doctor-lint-and-oc-rules upstream proposal. PR-1 of the proposal:
no new top-level verb, no public plugin SDK; everything internal.
Files:
- src/flows/checks.ts ? HealthFinding / HealthCheck / HealthCheckContext
types. Findings carry severity per-finding; checks return
readonly HealthFinding[]. Mode tag (doctor/lint/fix) lets a check
distinguish the calling posture.
- src/flows/health-check-registry.ts ? module-level registry with
duplicate-id rejection + test reset helper.
- src/flows/doctor-lint-flow.ts ? runner over registered checks.
Catches throws into synthetic error findings (anchored at check id;
message scrubbed of control chars, capped at 256 bytes). Sorts
findings by severity desc, check id, path. Exports
exitCodeFromFindings (1 if any warning/error, 0 otherwise).
- src/flows/doctor-core-checks.ts ? 4 modern HealthChecks rewriting
logic from existing legacy run*Health functions:
core/doctor/gateway-config (warning)
core/doctor/command-owner (info)
core/doctor/workspace-status (info)
core/doctor/final-config-validation (error)
Each was audited safe per the proposal's adapter constraints
(no writes, no repair calls, no prompts, no probes incl. local-bind).
Legacy run*Health contributions in doctor-health-contributions.ts
are unchanged ? doctor mode (no --lint) still runs the existing 35.
- src/commands/doctor-lint.ts ? CLI dispatch for --lint. Reads config
snapshot, builds HealthCheckContext (mode: "lint"), runs the registry,
filters by --severity-min, emits human or JSON output, returns exit
code from unfiltered set so --severity-min hides info findings
without changing CI signal.
- src/cli/program/register.maintenance.ts ? adds --lint, --json,
--severity-min, --skip, --only flags to existing doctor command.
--lint branches to runDoctorLintCli; without --lint, doctor runs
unchanged.
LoC: 382 src across 6 files. Tests + doc + oc-path-side rule packs
follow as separate commits on this branch.
* fix: avoid string spread in doctor errors
* chore: refresh plugin SDK API baseline
* docs: clarify doctor lint usage
* feat(doctor): prepare repairs for dry-run reporting
Summary:
- The PR narrows embedded PI session transcript write-lock scope, adds stale/max-hold config plumbing, and updates affected transcript, doctor, gateway, SDK, Codex mirroring, docs, and regression-test surfaces.
- Reproducibility: yes. Current main source still holds the embedded session write lock from early attempt set ... cksmith Testbox contention proof on unmodified main; I did not rerun the live repro in this read-only pass.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(agents): narrow context engine session lock
- PR branch already contained follow-up commit before automerge: fix session lock runner build types
- PR branch already contained follow-up commit before automerge: Release embedded session write lock before model I/O
- PR branch already contained follow-up commit before automerge: fix(clawsweeper): address review for automerge-openclaw-openclaw-8289…
Validation:
- ClawSweeper review passed for head 4c6dd7ed6e.
- Required merge gates passed before the squash merge.
Prepared head SHA: 4c6dd7ed6e
Review: https://github.com/openclaw/openclaw/pull/82891#issuecomment-4469282923
Co-authored-by: Alex Knight <15041791+amknight@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Summary:
- Add shared SDK helpers for transcript-backed recovery of ellipsis-truncated final text.
- Use the helper in Discord progress preview delivery so long answers fall through to normal chunked delivery with the full transcript text.
- Refactor Telegram to reuse the shared helper.
Verification:
- node scripts/run-vitest.mjs src/plugin-sdk/channel-streaming.test.ts extensions/discord/src/monitor/message-handler.process.test.ts
- pnpm exec oxfmt --check --threads=1 src/plugin-sdk/channel-streaming.ts src/plugin-sdk/channel-streaming.test.ts extensions/telegram/src/lane-delivery-text-deliverer.ts extensions/telegram/src/lane-delivery.ts extensions/telegram/src/bot-message-dispatch.ts extensions/discord/src/monitor/message-handler.process.ts extensions/discord/src/monitor/message-handler.process.test.ts
- node scripts/run-tsgo.mjs -p test/tsconfig/tsconfig.extensions.test.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/extensions-test.tsbuildinfo
- git diff --check
- pnpm check:changed via Blacksmith Testbox tbx_01krsy80a5qgfw790nm45770xt
- GitHub PR checks green on #82862
- codex-review --mode local: clean, no accepted/actionable findings
Fixes#82807.
Fix CLI web search/fetch command SecretRef resolution for provider-scoped plugin credentials.
- Carry command provider overrides through gateway and local secret resolution.
- Mark the selected web provider targets active and unrelated plugin refs inactive.
- Cover Tavily, DuckDuckGo, legacy Firecrawl fetch, protocol overrides, and runtime command-secret behavior.
- Add public plugin-sdk test mock exports needed by existing plugin tests after CI boundary enforcement.
Fixes#82621.
Replacement for #82699.
Co-authored-by: 吴杨帆 <39647285+leno23@users.noreply.github.com>
Restore Omit on public plugin-sdk ReplyPayload; set trustedLocalMedia via
runtime assertion in speech-core and explicitly on dispatch TTS-only finals.
Co-authored-by: Cursor <cursoragent@cursor.com>
WebChat streaming uses kind=block for assistant text; final-mode TTS skipped
those payloads. Mark synthesized audio as trustedLocalMedia and export the
full ReplyPayload type so the gateway can serve local TTS files.
Fixes#82628
Co-authored-by: Cursor <cursoragent@cursor.com>
