3fceb86048
* fix(workers): preserve failure causes and fallback runtime Keep implicit fallback candidates on the runtime owned by their worker placement. Preserve bounded, redacted provider status and classification, retain failure and usage after oversized partial responses, and show actionable error copy in chat history. * fix(chat): preserve recorded context overflow errors * fix: distinguish provider failures in saved chat history * test: reconcile runtime and SQLite fixtures after main updates |
||
|---|---|---|
| .. | ||
| src | ||
| test/fixtures/provider-transport-parity | ||
| LICENSE | ||
| package.json | ||
| README.md | ||
| tsconfig.json | ||
@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, google-model-family, openai,
openai-completions-compat, openai-responses-payload-policy, retry-after, runtime, shared, and
tool-schema 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.