feat(loop,gateway): 事件批 — tool_execution 三事件 + streamId + turn.start/end(裁决 01.4.1/01.4.2/01.4.3/01.4.5/03.4.4/1.12)
CI / Backend (build / vet / test / cross-compile) (push) Has been cancelled
CI / Frontend (tsc + vite build) (push) Has been cancelled

执行方案阶段 2 · P2-3(`DevDocs/audit/_plan.md`)。契约 `Docs/api-client.md` → **v0.50**。

- **01.4.1 `tool_execution` 拆三事件**:`model/stream.go` 删旧 `StreamKindToolExecution`,新增
  `tool_execution.start/update/end` + `ToolPhaseRunning/Done/Error`(与 design/19 status 同值);
  `StreamEvent` 增 `Tool`/`Phase`;`loop/tools.go` 的 `emitToolExecution` 重写为结构化字段、
  **Delta 恒空**(断言锁死),`ID` 复用 provider tool call id(可与 `tool_call.*` 关联)。
  ⚠️ **诚实边界**:start/end 有真实生产者;`update` 的 wire 映射已实现并单测锁定,但**工具分发器
  无中途进度上报源 ⇒ loop 暂不产出 update 帧**(已在 api-client §3.1 如实登记)。
- **03.4.4 phase 驱动图节点状态**:`invokeOne` 用**单一 phase 决策**同时决定 end 帧 phase、
  span 的 `phase` prop 与终态;`trace/graph.go` 新增 `FlowStatusForPhase`,`graph_build.go` 的
  `AddSpan` 对 tool 节点**优先消费 phase prop**(缺省回落 span 终态 ⇒ 两路不可能矛盾)。
- **01.4.2 `streamId`**:`StreamEvent` 增 `StreamID`;`loop/stream.go` 每次 ChatStream 生成
  `stream-<hex>`(crypto/rand,降级时间戳),该流所有帧共享、多步工具轮取新 id;`ws_bridge`
  把它并进**模型流帧** `data`(`tool_execution.*`/`turn.*` 不带)。语义区分:`turnId` = 哪轮回答,
  `streamId` = 这条流式消息。
- **01.4.3 `turn.start`/`turn.end`**:`loop/run.go` 入口发 start、defer 发 end,**覆盖全部出口**
  (最终答案/安全网终止/预算耗尽/步骤错误);帧**无 data 载荷**;静音的内部 run(backthink/子代理)
  不发。顺带把 91 行的 `Run` 拆成 `driveTurn` + `settleAndReturn`(清掉一处既有 >80 行违规)。
- **01.4.5**:仅 `Docs/api-client.md` §3.5 补 `graph_update` 三范围(`web`/`web:<uuid>`/`sess-backthink`),
  与 `wire_runtime.go` 的 allow 谓词一致,**零代码变更**。

验证:`go build ./...` 绿;本批四包(loop/model/trace/gateway)vet + 测试绿(含 `-count=1`);
linux/amd64 + darwin/arm64 交叉编译绿;本批 16 文件 ≤500 行、函数 ≤80 行。
**真 WS 帧断言 8 条**:帧序 `turn.start → message.delta → tool_execution.start →
tool_execution.end → message.delta → turn.end`(+`stream_end`)、turn 边界无载荷且整轮 turnId 一致、
两条模型流 `streamId` 互异、tool 帧 `{tool,phase,id}` 且无 `delta`/`streamId` 键、
`turn.end` 在步骤出错时也发出、内部静音 run 不发边界帧。
**变异验证**:把 `ev.StreamID = streamID` 改为赋空 → 两条断言 FAIL(`streamId` 为空/两流同空),
还原后复绿(直接删行会先被编译期 `declared and not used` 拦截)。

未验证:前端未消费这些帧(本轮未动 `frontend/**`,「前端能渲染」待前端批);无真实模型端到端。
This commit is contained in:
AskaEth committed 2026-10-04 11:26:35 +08:00
1 parent afef75f640
commit 6e7ec56f9a
16 files changed
+982 -126

No files matched your search

+18
View File
@@ -23,6 +23,24 @@ const (
FlowStatusError = "error"
)
// FlowStatusForPhase 把工具执行的细粒度 phase(design/04 §1.1,
// loop 随 tool_execution.end 帧一同记在 tool span 上)映射为流程图
// 节点状态:phase 取值与本包状态枚举(design/19 §1 统一枚举)
// 同构(running/done/error)。未知 phase 返回空串,调用方回落到
// span 终态推导,因此缺 phase 的旧 span 不受影响。
func FlowStatusForPhase(phase string) string {
switch phase {
case FlowStatusRunning:
return FlowStatusRunning
case FlowStatusDone:
return FlowStatusDone
case FlowStatusError:
return FlowStatusError
default:
return ""
}
}
// FlowNode is one node in a flow graph. Status/SpanKind mirror the frontier.
type FlowNode struct {
ID string `json:"id"`
+17 -1
View File
@@ -143,17 +143,26 @@ func (g *RunGraph) addEdge(from, to string) {
// AddSpan folds a finished span record into the graph as a node with its final
// status. State-transition spans are the step container and are omitted — but
// their parent link is remembered so lane resolution can walk through them.
// tool 节点的终态优先由其携带的细粒度 phase 驱动(design/04 §1.1 /
// design/19 §1:running/done/error),缺失时回落到 span 终态推导,
// 因此两套来源对同一节点绝不可能得出不同状态。
func (g *RunGraph) AddSpan(rec SpanRecord) {
kind := kindForSpan(rec.Kind)
if kind == "" {
g.rememberParent(rec.ID, rec.ParentID)
return
}
status := statusForFinished(rec.Status)
if kind == nodeKindTool {
if ph := FlowStatusForPhase(spanPhase(rec)); ph != "" {
status = ph
}
}
g.Upsert(NodeSpec{
ID: rec.ID,
Label: labelForSpan(rec),
Kind: kind,
Status: statusForFinished(rec.Status),
Status: status,
StartedAt: rec.StartedAt,
EndedAt: rec.EndedAt,
Props: safeSpanProps(rec),
@@ -162,6 +171,13 @@ func (g *RunGraph) AddSpan(rec SpanRecord) {
})
}
// spanPhase 读取 tool span 上记录的执行 phase;缺失或类型不符时返回
// 空串(调用方据此回落),不区分「没有」与「读不到」。
func spanPhase(rec SpanRecord) string {
ph, _ := rec.Props["phase"].(string)
return ph
}
// AddSpanStart registers a running placeholder for a span that just began, so a
// node appears as "running" before it finishes. State-transition spans are
// omitted (their parent link is still remembered for lane resolution), matching
@@ -0,0 +1,80 @@
package trace
import (
"testing"
"time"
)
// TestFlowStatusForPhase 锁住 phase → 节点状态的映射(design/04 §1.1
// 细粒度 phase、design/19 §1 统一枚举):三个已知 phase 原样通过,
// 未知 phase 返回空串让调用方回落到 span 终态推导。
func TestFlowStatusForPhase(t *testing.T) {
t.Parallel()
cases := map[string]string{
FlowStatusRunning: FlowStatusRunning,
FlowStatusDone: FlowStatusDone,
FlowStatusError: FlowStatusError,
"started": "",
"": "",
}
for phase, want := range cases {
if got := FlowStatusForPhase(phase); got != want {
t.Fatalf("FlowStatusForPhase(%q) = %q, want %q", phase, got, want)
}
}
}
// TestAddSpanToolPhaseDrivesStatus 锁住裁决 03.4.4:tool 节点的终态由
// span 携带的细粒度 phase 驱动(与 WS 的 tool_execution.end 帧同一
// 取值),缺 phase 的 tool span 回落到 span 终态推导,两路绝不矛盾。
func TestAddSpanToolPhaseDrivesStatus(t *testing.T) {
t.Parallel()
now := time.Now()
tool := func(id, phase string, status SpanStatus) SpanRecord {
rec := SpanRecord{ID: id, Name: "tool.echo", Kind: SpanKindTool,
Status: status, StartedAt: now, EndedAt: now}
if phase != "" {
rec.Props = map[string]any{"phase": phase}
}
return rec
}
cases := []struct {
name string
rec SpanRecord
want string
}{
{"phase done", tool("t1", FlowStatusDone, SpanStatusOK), FlowStatusDone},
{"phase error overrides ok status", tool("t2", FlowStatusError, SpanStatusOK), FlowStatusError},
{"no phase falls back to span status", tool("t3", "", SpanStatusOK), FlowStatusDone},
{"no phase falls back to span error", tool("t4", "", SpanStatusError), FlowStatusError},
{"unknown phase falls back to span status", tool("t5", "started", SpanStatusError), FlowStatusError},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
g := NewRunGraph("web")
g.Start(1, now)
g.AddSpan(tc.rec)
if len(g.nodes) != 1 {
t.Fatalf("nodes = %d, want 1", len(g.nodes))
}
if got := g.nodes[tc.rec.ID].Status; got != tc.want {
t.Fatalf("tool node status = %q, want %q", got, tc.want)
}
})
}
}
// TestAddSpanNonToolIgnoresPhase 确保 phase 只驱动 tool 节点:其他
// kind 的 span 即使带 phase prop(未来不该有),也不改变其
// 终态推导路径。
func TestAddSpanNonToolIgnoresPhase(t *testing.T) {
t.Parallel()
now := time.Now()
g := NewRunGraph("web")
g.Start(1, now)
g.AddSpan(SpanRecord{ID: "l1", Name: "llm.call", Kind: SpanKindLLM,
Status: SpanStatusOK, StartedAt: now, EndedAt: now, Props: map[string]any{"phase": FlowStatusError}})
if got := g.nodes["l1"].Status; got != FlowStatusDone {
t.Fatalf("llm node status = %q, want %q (phase must not drive non-tool nodes)", got, FlowStatusDone)
}
}