AskaEth
c7b2cd8ae0
- model.go: Response.StopReason; anthropic wire加stop_reason; openai finish_reason映射(两协议统一,原值透传)
- truncation.go(新,159行): effectiveMaxTokens/retryMaxTokens(×2封顶32768)/isTruncatedEmpty(空正文+无tool_use+stop_reason∈{max_tokens,length})/withEmptyBodyHint/callWithTruncationRetry/callStreamWithTruncationRetry/dropThinking/emitTextSegment
- anthropic.go Chat/ChatStream 走重试+兜底; anthropic_encode.go(新)拆编码(anthropic.go 529→357合规); anthropic_stream message_delta落StopReason
- agent/loop: 把模型层StopReason带到llm.call span的model_stop_reason属性(修掉trace硬编码stop的误导); loop.Result.StopReason语义未动
- 触发仅当截断空正文; tool_use空正文永不触发(native_toolcall_test仍过); 至多1次重试; 兜底回'（思考过长，未能生成回复）'绝不用thinking
- 新增7测试(非流式/流式重试+兜底+tool_use不触发+封顶+openai映射), build/vet/test绿+3平台交叉编译
75 lines
2.6 KiB
Go
75 lines
2.6 KiB
Go
package loop
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
|
|
"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/agent"
|
|
"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/model"
|
|
"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/trace"
|
|
)
|
|
|
|
// stepOutcome is the loop's internal view of one model step, normalized from the
|
|
// agent's *agent.StepResult (non-streaming) or the equivalent built by the
|
|
// streaming path.
|
|
type stepOutcome struct {
|
|
final bool
|
|
text string
|
|
toolCalls []agent.ToolCall
|
|
stopReason string
|
|
// modelStopReason is the provider's raw stop/finish reason for the model
|
|
// call (Anthropic max_tokens / end_turn / tool_use), recorded on the llm_call
|
|
// span so a truncation is visible even when the step itself ended normally.
|
|
modelStopReason string
|
|
}
|
|
|
|
// step runs a single model call. When an OnStream callback is configured it
|
|
// drives the adapter's ChatStream directly, threading deltas to OnStream and
|
|
// applying the loop's guardrails; otherwise it delegates to the agent's RunStep,
|
|
// which runs the agent's own guardrails and records its own CallRecord. The whole
|
|
// call is wrapped in an llm_call span so the M9 panel sees each LLM invocation.
|
|
func (l *Loop) step(ctx context.Context, sessionID string, messages []model.Message) (*stepOutcome, error) {
|
|
_, llmSpan := l.span(ctx, "llm.call", trace.SpanKindLLM)
|
|
|
|
var (
|
|
out *stepOutcome
|
|
err error
|
|
)
|
|
// Muted (internal autonomous pass) bypasses streaming: it neither streams to
|
|
// the UI nor pays the streaming path's extra overhead. Normal chat streams.
|
|
if l.onStream != nil && !isMutedBroadcast(ctx) {
|
|
out, err = l.streamStep(ctx, messages)
|
|
} else {
|
|
out, err = l.agentStep(ctx, sessionID, messages)
|
|
}
|
|
if err != nil {
|
|
l.spanProp(llmSpan, "error", err.Error())
|
|
l.finishSpan(llmSpan, trace.SpanStatusError)
|
|
return nil, fmt.Errorf("loop: model step: %w", err)
|
|
}
|
|
|
|
l.spanProp(llmSpan, "stop_reason", out.stopReason)
|
|
if out.modelStopReason != "" {
|
|
l.spanProp(llmSpan, "model_stop_reason", out.modelStopReason)
|
|
}
|
|
l.spanProp(llmSpan, "tool_calls", len(out.toolCalls))
|
|
l.finishSpan(llmSpan, trace.SpanStatusOK)
|
|
return out, nil
|
|
}
|
|
|
|
// agentStep delegates a non-streaming step to the agent, which runs input and
|
|
// output guardrails, calls the model and decodes any tool calls.
|
|
func (l *Loop) agentStep(ctx context.Context, sessionID string, messages []model.Message) (*stepOutcome, error) {
|
|
sr, err := l.agent.RunStep(ctx, sessionID, messages)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("loop: agent step: %w", err)
|
|
}
|
|
return &stepOutcome{
|
|
final: sr.Final,
|
|
text: sr.Text,
|
|
toolCalls: sr.ToolCalls,
|
|
stopReason: sr.StopReason,
|
|
modelStopReason: sr.ModelStopReason,
|
|
}, nil
|
|
}
|