feat: publish sanitized custom.97 source

controller/astra_sampling.go

@@ -139,10 +139,14 @@ func (astraSamplingHandler) Run(parent context.Context, task *model.SystemTask,
 				state.Rounds[index].Reason = reason
 				state.Rounds[index].Usage = usage
 				state.Rounds[index].FinishedAt = time.Now().Unix()
-				if persist() && !payload.Force {
-					if err := model.ApplyDetectionScheduleResult(ctx, id, "modeltrace", state.Rounds[index].ID, state.Rounds[index].FinishedAt, service.FingerprintScheduleOutcome(service.AstraSamplingResultStatus(result))); err != nil {
-						persistErr = err
-						cancel()
+				if persisted := persist(); persisted {
+					service.InvalidateGroupQualityCache()
+					publishGroupStatusChange()
+					if !payload.Force {
+						if err := model.ApplyDetectionScheduleResult(ctx, id, "modeltrace", state.Rounds[index].ID, state.Rounds[index].FinishedAt, service.FingerprintScheduleOutcome(service.AstraSamplingResultStatus(result))); err != nil {
+							persistErr = err
+							cancel()
+						}
 					}
 				}
 				mu.Unlock()
@@ -179,6 +183,7 @@ func runModelDetectionProbe(parent context.Context, channel *model.Channel, inde
 	if err != nil {
 		return fingerprint.ProbeResponse{}, index, err
 	}
+	effort := "low"
 	count, output := probe.Count, fingerprint.OutputTokens
 	messages := []map[string]any{{"role": "user", "content": probe.Prompt}}
 	if kind == "benchmark" {
@@ -189,14 +194,23 @@ func runModelDetectionProbe(parent context.Context, channel *model.Channel, inde
 		count, output = index, benchmark.OutputTokens
 		messages = []map[string]any{{"role": "system", "content": secondary.System}, {"role": "user", "content": secondary.Prompt}}
 	}
-	if kind == "candy" {
-		count, output = 1, service.CandyOutputTokens
-		messages = []map[string]any{{"role": "user", "content": service.CandyPrompt}}
+	if kind == "vision" {
+		count, output = 1, service.VisionOutputTokens
+		effort = "medium"
+		messages = []map[string]any{{"role": "user", "content": []map[string]any{
+			{"type": "input_text", "text": service.VisionPrompt},
+			{"type": "input_image", "image_url": service.VisionImageURL, "detail": "high"},
+		}}}
+	}
+	if kind == "ciallo" {
+		count, output = 1, service.VisionOutputTokens
+		effort = "medium"
+		messages = []map[string]any{{"role": "user", "content": service.CialloPrompt}}
 	}
 	input, _ := common.Marshal(messages)
 	stream := true
 	limit := uint(output)
-	request := &dto.OpenAIResponsesRequest{Model: fingerprint.Model, Input: input, Stream: &stream, MaxOutputTokens: &limit, Store: []byte("false"), Reasoning: &dto.Reasoning{Effort: "low"}}
+	request := &dto.OpenAIResponsesRequest{Model: fingerprint.Model, Input: input, Stream: &stream, MaxOutputTokens: &limit, Store: []byte("false"), Reasoning: &dto.Reasoning{Effort: effort}}
 	encoded, err := common.Marshal(request)
 	if err != nil {
 		return fingerprint.ProbeResponse{}, count, err
@@ -230,6 +244,7 @@ func runModelDetectionProbe(parent context.Context, channel *model.Channel, inde
 		defer boundedCloser.Close()
 		body = bounded
 	}
+	started := time.Now()
 	response, err := adaptor.DoRequest(c, info, body)
 	if err != nil {
 		return fingerprint.ProbeResponse{}, count, errors.New("probe transport failed")
@@ -239,12 +254,19 @@ func runModelDetectionProbe(parent context.Context, channel *model.Channel, inde
 		return fingerprint.ProbeResponse{}, count, errors.New("unsupported probe transport")
 	}
 	defer resp.Body.Close()
+	stopClose := context.AfterFunc(ctx, func() { _ = resp.Body.Close() })
+	defer stopClose()
 	if resp.StatusCode != http.StatusOK {
 		return fingerprint.ProbeResponse{}, count, errors.New("probe HTTP failure")
 	}
 	// Deliberately bypass DoResponse: this is a platform-funded probe, with no
 	// customer token, wallet charge, session binding or generated response relay.
-	answer, err := fingerprint.ReadResponse(resp.Body, resp.Header.Get("Content-Type"))
+	var firstTokenMS *int64
+	answer, err := fingerprint.ReadResponse(resp.Body, resp.Header.Get("Content-Type"), func() {
+		elapsed := time.Since(started).Milliseconds()
+		firstTokenMS = &elapsed
+	})
+	answer.FirstTokenMS = firstTokenMS
 	return answer, count, err
 }