Struct OpenAIChatStreamingCodec 

pub struct OpenAIChatStreamingCodec { /* private fields */ }

Streaming counterpart to OpenAIChatCodec.

Replays the OpenAI Chat Completions SSE chunk sequence into the same JSON shape returned for a non-streaming request ({id, object, created, model, choices: [{message, finish_reason}], usage}). Once finalized, the assembled JSON can be fed back through OpenAIChatCodec::decode_response to produce the canonical AnnotatedLlmResponse.

Strategy

Chat Completions streams untyped SSE chunks of {choices: [{index, delta: {...}, finish_reason: ...}]}. Each delta may carry a role (typically only on the first chunk), incremental content text, or partial tool_calls whose function.arguments stream as a JSON-encoded string fragment-by-fragment. Top-level fields (id, model, created) are repeated on every chunk; we capture them once. Final-chunk usage is preserved when emitted (only sent when stream_options.include_usage is set on the request).

The OpenAI [DONE] end-of-stream sentinel is dropped by the SSE event decoder before reaching the collector, so this codec never sees it.

Internal state lives behind Arc<Mutex<...>> so the &self-produced collector and finalizer closures share access. Each instance is single-use because LlmFinalizerFn consumes the finalize step.

Implementations

impl OpenAIChatStreamingCodec

pub fn new() -> Self

Creates a fresh streaming codec with empty accumulator state.

Trait Implementations

impl Default for OpenAIChatStreamingCodec

fn default() -> Self

Returns the “default value” for a type.

impl StreamingCodec for OpenAIChatStreamingCodec

fn collector(&self) -> LlmCollectorFn

Returns a closure that consumes one decoded provider event per call.

fn finalizer(&self) -> LlmFinalizerFn

Returns a closure that, when called once at end of stream, produces the assembled response payload in the shape the matching crate::codec::traits::LlmResponseCodec can decode.