Peter Steinberger
5ebbc3c003
* fix(agents): keep stalled turns visible after Responses streams settle A bare-continue turn in live QA (goal-followthrough-live, gpt-5.4 via openai-responses) completed its SSE requests and then produced no terminal result, delivery, timeout, or error for 6+ minutes until SIGTERM. Root cause: turn liveness is enforced only while awaiting provider stream events (llm-idle watchdog); queued subscription handlers are fire-and-forget during the turn and finalize joined them unbounded and un-abortable, backed only by the 48h default run budget. One hung delivery handler silently dead-ended the whole turn. - Bound the pending-events join in attempt-stream-finalize with a 120s liveness deadline plus the run-abort signal; on expiry, warn with the runId and proceed to settlement so the run always yields a visible terminal outcome. - Responses transports now report every SSE event via notifyLlmRequestActivity (parity with completions/anthropic), so bookkeeping-only events keep the idle watchdog quiet instead of counting as network silence. * fix(agents): bound the settlement block-reply flush with the shared liveness join ClawSweeper P1 on #120426: after the finalize-phase join times out, settlement still awaited onBlockReplyFlush on the same wedged delivery chain (unbounded on the supported blockReplyTimeoutMs: 0 path). Generalize the bounded join into joinWithRunLivenessDeadline in run/abortable.ts (owner of abort/liveness racing) and use it for both the pending-events join and the settle flush; timeout and abort resolve with a recorded warning so the turn always reaches a visible terminal outcome. New coverage: helper tests (hang, abort, rejection) and a real-settle-path regression holding the flush past the deadline.
@openclaw/ai
Reusable model API contracts, provider adapters, and streaming primitives from OpenClaw. The package supports isolated runtime instances; importing it does not register providers globally.
import { createLlmRuntime } from "@openclaw/ai";
import { registerBuiltInApiProviders } from "@openclaw/ai/providers";
const runtime = createLlmRuntime();
registerBuiltInApiProviders(runtime.registry);
Provider-neutral contracts, validation, diagnostics, and event streams are
available from the package root and focused subpaths such as
@openclaw/ai/event-stream, @openclaw/ai/transports, and
@openclaw/ai/validation. No second OpenClaw runtime package is required.
Provider ids, credentials, model catalogs, retries, and failover remain
application concerns. OpenClaw supplies those policies around this package.
Host policy (request fetch guarding, secret redaction, strict-tool defaults,
provider plugin hooks, and diagnostics logging) can be injected with
configureAiTransportHost; the defaults are inert.
The explicit @openclaw/ai/internal/anthropic, openai, retry-after,
runtime, and shared subpaths exist for the OpenClaw application itself.
They carry no semver guarantee and can change or disappear in any release; do
not depend on them outside OpenClaw.