Delete the provider-error LLMEvent so streams carry output only and every provider-reported failure exits through the typed error channel. Anthropic SSE error events, OpenAI Responses response.failed/error events, and Bedrock exception frames now fail the stream with an LLMError from the shared classifier (carrying the provider code, e.g. rate_limit_exceeded -> LLM.RateLimit). Core follows: the publisher drops its provider-error case, the runner drops held-back overflow events (overflow recovery keys off a thrown LLM.ContextOverflow), compaction and title stop scanning events for failures, and isContextOverflowFailure is deleted with its last consumer. V1 packages/opencode gets minimal compile fixes only (dead switch case, one test stream). |
||
|---|---|---|
| .. | ||
| fixtures | ||
| lib | ||
| provider | ||
| adapter.test.ts | ||
| auth-options.types.ts | ||
| auth.test.ts | ||
| cache-policy.test.ts | ||
| continuation-scenarios.ts | ||
| endpoint.test.ts | ||
| executor.test.ts | ||
| exports.test.ts | ||
| generate-object.test.ts | ||
| llm.test.ts | ||
| prepare.test.ts | ||
| provider-error.test.ts | ||
| provider-package.test.ts | ||
| provider.types.ts | ||
| recorded-golden.ts | ||
| recorded-runner.ts | ||
| recorded-scenarios.ts | ||
| recorded-test.ts | ||
| recorded-utils.ts | ||
| response.test.ts | ||
| route.test.ts | ||
| schema.test.ts | ||
| tool-runtime.test.ts | ||
| tool-schema-projection.test.ts | ||
| tool-stream.test.ts | ||
| tool.types.ts | ||