- Modify edge openai chat/stream handlers for priority routing - Update responses_handler and run_result - Add model queue test updates - Add node provider first config surface task - Archive inflight accounting recovery docs
116 lines
3.6 KiB
Go
116 lines
3.6 KiB
Go
package openai
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"errors"
|
|
"fmt"
|
|
"strings"
|
|
"time"
|
|
|
|
edgeservice "iop/apps/edge/internal/service"
|
|
)
|
|
|
|
const (
|
|
runtimeMetadataOpenAIToolCalls = "openai_tool_calls"
|
|
runtimeMetadataOpenAITextToolFallback = "openai_text_tool_fallback"
|
|
)
|
|
|
|
// errRunTimedOut is returned by collectRunResult and the direct streaming
|
|
// loop when handle.WaitTimeout() elapses without a terminal run event.
|
|
var errRunTimedOut = errors.New("run timed out")
|
|
|
|
// isCancelWorthyRunError reports whether err means the HTTP caller gave up
|
|
// (context cancellation/deadline or a WaitTimeout expiry) before the run
|
|
// reached a terminal state, so Edge should propagate CancelRun to Node.
|
|
// Terminal run outcomes (complete/error/cancelled events, closed stream,
|
|
// node disconnect) are not cancel-worthy: Node already reached a terminal
|
|
// state or is unreachable, so sending CancelRun would be redundant or futile.
|
|
func isCancelWorthyRunError(err error) bool {
|
|
return errors.Is(err, context.Canceled) || errors.Is(err, context.DeadlineExceeded) || errors.Is(err, errRunTimedOut)
|
|
}
|
|
|
|
func collectRunResult(ctx context.Context, stream edgeservice.RunStream, timeout time.Duration) (string, string, string, []any, *openAIUsage, bool, error) {
|
|
if stream.Events == nil {
|
|
return "", "", "", nil, nil, false, fmt.Errorf("run stream unavailable")
|
|
}
|
|
var contentBuilder strings.Builder
|
|
var reasoningBuilder strings.Builder
|
|
finishReason := "stop"
|
|
var usage *openAIUsage
|
|
timer := time.NewTimer(timeout)
|
|
defer timer.Stop()
|
|
for {
|
|
select {
|
|
case <-ctx.Done():
|
|
return "", "", "", nil, nil, false, ctx.Err()
|
|
case <-timer.C:
|
|
return "", "", "", nil, nil, false, errRunTimedOut
|
|
case nodeEvent, ok := <-stream.NodeEvents:
|
|
if !ok {
|
|
stream.NodeEvents = nil
|
|
continue
|
|
}
|
|
if edgeservice.IsNodeDisconnected(nodeEvent) {
|
|
return "", "", "", nil, nil, false, fmt.Errorf("node disconnected")
|
|
}
|
|
case event, ok := <-stream.Events:
|
|
if !ok {
|
|
return "", "", "", nil, nil, false, fmt.Errorf("run stream closed")
|
|
}
|
|
if event == nil {
|
|
continue
|
|
}
|
|
switch event.GetType() {
|
|
case "delta":
|
|
contentBuilder.WriteString(event.GetDelta())
|
|
case "reasoning_delta":
|
|
reasoningBuilder.WriteString(event.GetDelta())
|
|
case "complete":
|
|
if reason := event.GetMetadata()["finish_reason"]; reason != "" {
|
|
finishReason = reason
|
|
}
|
|
toolCalls := toolCallsFromRunMetadata(event.GetMetadata())
|
|
if len(toolCalls) > 0 {
|
|
finishReason = "tool_calls"
|
|
}
|
|
if u := event.GetUsage(); u != nil {
|
|
usage = &openAIUsage{
|
|
PromptTokens: int(u.GetInputTokens()),
|
|
CompletionTokens: int(u.GetOutputTokens()),
|
|
TotalTokens: int(u.GetInputTokens() + u.GetOutputTokens()),
|
|
}
|
|
}
|
|
return contentBuilder.String(), reasoningBuilder.String(), finishReason, toolCalls, usage, isTextToolFallback(event.GetMetadata()), nil
|
|
case "error", "cancelled":
|
|
msg := event.GetError()
|
|
if msg == "" {
|
|
msg = event.GetMessage()
|
|
}
|
|
if msg == "" {
|
|
msg = "run failed"
|
|
}
|
|
return "", "", "", nil, nil, false, fmt.Errorf("%s", msg)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
func toolCallsFromRunMetadata(metadata map[string]string) []any {
|
|
raw := strings.TrimSpace(metadata[runtimeMetadataOpenAIToolCalls])
|
|
if raw == "" {
|
|
return nil
|
|
}
|
|
var toolCalls []any
|
|
if err := json.Unmarshal([]byte(raw), &toolCalls); err != nil {
|
|
return nil
|
|
}
|
|
if len(toolCalls) == 0 {
|
|
return nil
|
|
}
|
|
return toolCalls
|
|
}
|
|
|
|
func isTextToolFallback(metadata map[string]string) bool {
|
|
return strings.EqualFold(strings.TrimSpace(metadata[runtimeMetadataOpenAITextToolFallback]), "true")
|
|
}
|