Cyrene_v2/internal/runtime/model/stream.go

package model

// StreamKind enumerates the kinds of structured events produced while a
// completion streams. It mirrors OpenClaw's AssistantMessageEvent segments
// (text / thinking / tool_call) plus a tool-execution progress event, so the
// frontend can render each segment into its own surface (body, collapsed
// thinking block, tool card) rather than accumulating a single opaque token
// stream.
type StreamKind string

const (
	// StreamKindTextStart opens the body-text segment. The single text segment
	// of a response is bracketed by TextStart/TextEnd; deltas fill it.
	StreamKindTextStart StreamKind = "text_start"
	// StreamKindTextDelta is one body-text token fragment.
	StreamKindTextDelta StreamKind = "text_delta"
	// StreamKindTextEnd closes the body-text segment.
	StreamKindTextEnd StreamKind = "text_end"

	// StreamKindThinkingStart opens a chain-of-thought segment (frontend
	// collapsed block). Reserved: adapters that report reasoning emit it.
	StreamKindThinkingStart StreamKind = "thinking_start"
	// StreamKindThinkingDelta is one reasoning token fragment.
	StreamKindThinkingDelta StreamKind = "thinking_delta"
	// StreamKindThinkingEnd closes a reasoning segment.
	StreamKindThinkingEnd StreamKind = "thinking_end"

	// StreamKindToolCallStart opens a tool invocation's streaming form.
	StreamKindToolCallStart StreamKind = "tool_call_start"
	// StreamKindToolCallDelta is a fragment of the tool arguments (e.g. the
	// incremental input_json of an Anthropic tool_use block).
	StreamKindToolCallDelta StreamKind = "tool_call_delta"
	// StreamKindToolCallEnd closes a tool invocation block.
	StreamKindToolCallEnd StreamKind = "tool_call_end"

	// StreamKindToolExecutionStart opens the execution of a tool the model
	// requested (design/04 §1.1: entering execution). It is emitted by the tool
	// loop, not the model adapter; Phase carries the running label.
	StreamKindToolExecutionStart StreamKind = "tool_execution_start"
	// StreamKindToolExecutionUpdate reports intermediate progress or partial
	// output while a requested tool runs (design/04 §1.1). Multiple frames per
	// execution are allowed; the wire mapping is defined, and a producer appears
	// once tools can report mid-execution progress.
	StreamKindToolExecutionUpdate StreamKind = "tool_execution_update"
	// StreamKindToolExecutionEnd closes a tool execution with its terminal
	// phase (done or error). It is emitted by the tool loop after Invoke
	// returns.
	StreamKindToolExecutionEnd StreamKind = "tool_execution_end"

	// StreamKindTurnStart opens an assistant turn at the loop's run boundary
	// (design/04 §1.1 turn.start). It carries no payload: the frame shell's
	// session/turn identity brackets the turn on the client.
	StreamKindTurnStart StreamKind = "turn_start"
	// StreamKindTurnEnd closes an assistant turn at the loop's run boundary,
	// however the run settled (final answer, guardrail stop, terminated tool
	// loop, exhausted rounds or an error).
	StreamKindTurnEnd StreamKind = "turn_end"
)

// 工具执行 phase 标签（design/04 §1.1 细粒度 phase）。取值与 design/19 §1
// 的节点 status 枚举（running/done/error）一致：start/update 帧带 running，
// end 帧带 done 或 error，前端与实时流程图据此驱动工具节点的状态。
const (
	// ToolPhaseRunning 标记工具进入执行或仍在执行中。
	ToolPhaseRunning = "running"
	// ToolPhaseDone 标记工具执行成功结束。
	ToolPhaseDone = "done"
	// ToolPhaseError 标记工具执行失败结束。
	ToolPhaseError = "error"
)

// StreamEvent is a single structured event in a streamed completion. It replaces
// the former plain text delta as the unit delivered by Adapter.ChatStream, so a
// consumer can distinguish body text from tool calls (and, in time, reasoning
// segments) and track each by Index/ID.
type StreamEvent struct {
	// Kind classifies the event (see StreamKind).
	Kind StreamKind
	// Delta carries the incremental payload: body text for TextDelta, reasoning
	// text for ThinkingDelta, or a partial_argument fragment for ToolCallDelta.
	// Tool-execution events never pack their phase or tool name in here —
	// those live in the structured Phase/Tool fields.
	Delta string
	// Index is the zero-based content-block index the event belongs to, when the
	// provider reports one. The frontend uses it to correlate a segment's
	// start/delta/end events.
	Index int
	// ID is the provider block/index identifier for a tool call (e.g. Anthropic's
	// tool_use block id). Empty for text segments. Tool-execution events reuse it
	// so the client can correlate an execution with its tool_call.* frames.
	ID string
	// Tool is the invoked tool's name on a tool_execution.* event. Empty on
	// every other kind.
	Tool string
	// Phase is the fine-grained execution label (ToolPhase*) on a
	// tool_execution.* event: running on start/update, done or error on end.
	// Empty on every other kind.
	Phase string
	// StreamID identifies the single model stream (one ChatStream call) a frame
	// belongs to. The loop stamps it at the stream boundary so every frame of
	// the same streamed message shares it, while a multi-step turn's later
	// model calls get fresh ids; consumers distinguish it from TurnID, which
	// stays constant across the whole turn.
	StreamID string
	// SessionID is the conversation the streamed event belongs to. It is stamped
	// by the loop at the turn boundary (loop.streamStep), which reads the session
	// the Run was started for; a model adapter, running below the loop and with no
	// notion of a session, leaves it zero. A consumer that routes the event (the
	// WS hub) reads it to target the right conversation.
	SessionID string
	// TurnID is the assistant turn the event belongs to. Like SessionID it is
	// stamped by the loop, which reads the turn identity the caller attached with
	// loop.WithTurnID; it is zero when no turn id was attached, so a consumer must
	// treat both fields as best-effort correlation rather than a hard guarantee.
	TurnID string
}