mirror of
https://github.com/openai/codex.git
synced 2026-09-28 08:43:01 +08:00
## Why Interleaved speaker transcripts can fragment handoff context, and delayed final transcripts can overwrite newer speech. ## What changed - Reconcile V3 transcript deltas and finals with the latest entry for the same speaker. - Replace accumulated text only when the final transcript extends it, preserving newer speech when a final arrives late. - Start a new entry after each completed utterance, keeping repeated speech and final-only turns distinct even when empty deltas arrive. - Preserve live transcript notifications and legacy protocol behavior. ## Testing Add unit coverage for interleaved speakers across reconnects, either completion order, repeated utterances, final-only turns, and empty deltas. Add app-server integration coverage for expanded and delayed finals, checking live notifications and reconciled handoff context. GitOrigin-RevId: 961729281f61b95fd3e0c5cc3ec72512987980b3
codex-api
Typed clients for Codex/OpenAI APIs built on top of the generic transport in codex-client.
- Hosts the request/response models and request builders for Responses and related Codex APIs.
- Owns provider configuration (base URLs, headers, query params), auth header injection, retry tuning, and stream idle settings.
- Parses SSE streams into
ResponseEvent/ResponseStream, including rate-limit snapshots and API-specific error mapping. - Serves as the wire-level layer consumed by
codex-core; higher layers handle auth refresh and business logic.
Core interface
The public interface of this crate is intentionally small and uniform:
-
Responses endpoint
- Input:
ResponsesApiRequestfor the request body (model,instructions,input,tools,parallel_tool_calls, reasoning/text controls).ResponsesOptionsfor transport/header concerns (conversation_id,session_source,extra_headers,compression,turn_state).
- Output: a
ResponseStreamofResponseEvent(both re-exported fromcommon).
- Input:
-
Memory summarize endpoint
- Input:
MemorySummarizeInput(re-exported ascodex_api::MemorySummarizeInput):model: String.raw_memories: Vec<RawMemory>(serialized astracesfor wire compatibility).RawMemoryincludesid,metadata.source_path, and normalizeditems.
reasoning: Option<Reasoning>.
- Output:
Vec<MemorySummarizeOutput>. MemoriesClient::summarize_input(&MemorySummarizeInput, extra_headers)wraps JSON encoding and retry/telemetry wiring.
- Input:
All HTTP details (URLs, headers, retry/backoff policies, SSE framing) are encapsulated in codex-api and codex-client. Callers construct prompts/inputs using protocol types and work with typed streams of ResponseEvent or other endpoint-specific response values.