Tianyi Cui
ee6b9d081a
Replace the process-wide adapter-failure WeakSet with a per-call scope bound to the exact AsyncIterable returned by LlmService.stream(). Give every call a unique wrapper so waterfall middleware can reuse an iterable without sharing provenance. Move agent-loop recovery classification to the model-stream boundary. Only the final adapter behind that exact call can become an agent/request-error; nested llm/stream calls remain ordinary outer middleware failures while preserving the original Error. Cover nested calls, reused middleware iterables, and end-to-end agent-loop recovery. Update the package and RFC contracts, bilingual pairing record, and generated API and catalog references.
2.7 KiB
ctx.llm
LlmService — provided by @deepseek-ai/dsh-llm.
The abstract llm service: an adapter registry plus a streaming model-call surface, interceptable via the llm/stream waterfall.
ctx.llm.registerAdapter(providers, adapter)
registerAdapter(providers: string[], adapter: LlmAdapter): () => void
Register an adapter for the given provider routes. Throws LlmError with code DUPLICATE_ADAPTER if any provider already has an adapter (all-or-nothing). Disposed with the fiber.
providers— every provider route this adapter should serve.adapter— the adapter that streams calls for those providers.
Returns the disposer that unregisters all of them.
ctx.llm.listProviders()
listProviders(): LlmProviderInfo[]
Describe provider routes with a registered adapter.
Returns detached provider metadata in registration order.
ctx.llm.listModels(provider)
async listModels(provider: string): Promise<LlmModelInfo[]>
Discover models advertised by one registered provider. Catalog membership is advisory and never changes routing or request validation.
provider— registered provider route to inspect.
Returns detached model metadata in adapter-preferred order.
ctx.llm.stream(options)
stream(options: GenerateOptions): AsyncIterable<StreamChunk>
Stream one model call as raw chunks (token-level deltas). Throws LlmError with code NO_ADAPTER if no adapter is registered for options.provider. Replay state is retained only when the same adapter instance owns its historical provider and the target provider. Final adapter selection, dispatch, and iteration failures retain their original Error identity and are tagged in a call-local scope for narrow agent-loop request recovery; middleware and nested-call failures remain untagged for the outer call.
options— the full request;options.providerselects the adapter.
Returns the chunk stream, possibly wrapped by llm/stream listeners.