5d87c7ad1f
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). |
||
|---|---|---|
| .. | ||
| bin | ||
| migration/20260511173437_session-metadata | ||
| script | ||
| specs | ||
| src | ||
| test | ||
| .gitignore | ||
| AGENTS.md | ||
| bunfig.toml | ||
| Dockerfile | ||
| git | ||
| package.json | ||
| parsers-config.ts | ||
| README.md | ||
| sst-env.d.ts | ||
| tsconfig.json | ||