fix

apps/api/cmd/mock-llm/main.go

@@ -31,14 +31,15 @@ import (
 )
 
 type server struct {
-	apiKey string
-	model  string
-	logReq atomic.Int64
+	apiKey               string
+	model                string
+	categorizeConfidence float64
+	logReq               atomic.Int64
 }
 
 type chatRequest struct {
-	Model       string `json:"model"`
-	Messages    []struct {
+	Model    string `json:"model"`
+	Messages []struct {
 		Role    string `json:"role"`
 		Content string `json:"content"`
 	} `json:"messages"`
@@ -50,11 +51,16 @@ func main() {
 	addr := flag.String("addr", "127.0.0.1:18767", "listen address")
 	key := flag.String("key", envOr("MOCK_LLM_API_KEY", "local-test"), "Bearer API key (non-empty placeholder)")
 	model := flag.String("model", envOr("MOCK_LLM_MODEL", "mock-llm"), "model id returned by /v1/models")
+	// Lets a local run reproduce a low-confidence taxonomy pick (see
+	// processing.DefaultMinCategorizeConfidence).
+	categorizeConfidence := flag.Float64("categorize-confidence", 0,
+		"when > 0, answer categorize calls with this confidence score")
 	flag.Parse()
 
 	s := &server{
-		apiKey: strings.TrimSpace(*key),
-		model:  strings.TrimSpace(*model),
+		apiKey:               strings.TrimSpace(*key),
+		model:                strings.TrimSpace(*model),
+		categorizeConfidence: *categorizeConfidence,
 	}
 	if s.apiKey == "" {
 		log.Fatal("mock-llm: API key must be non-empty (Descrybe Completer.Enabled requires it)")
@@ -77,6 +83,13 @@ func main() {
 	}
 }
 
+func truncTrace(s string, n int) string {
+	if len(s) <= n {
+		return s
+	}
+	return s[:n]
+}
+
 func envOr(k, def string) string {
 	if v := strings.TrimSpace(os.Getenv(k)); v != "" {
 		return v
@@ -140,11 +153,17 @@ func (s *server) handleChatCompletions(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 	system, user := splitMessages(req.Messages)
+	if os.Getenv("MOCK_LLM_TRACE") != "" {
+		log.Printf("mock-llm: roles=%d system_len=%d user_len=%d system_head=%q",
+			len(req.Messages), len(system), len(user), truncTrace(system, 60))
+	}
 	var comp processing.Completion
 	// A category formula in the prompt is answered in that formula's shape, so a
 	// local run proves the formula reached the model and the reply passes the
 	// pipeline's formula gate. Everything else keeps the heuristic fallback.
-	if text, ok := buildFormulaReply(system, user); ok {
+	if text, ok := s.categorizeReply(system, user); ok {
+		comp = processing.Completion{Text: text}
+	} else if text, ok := buildFormulaReply(system, user); ok {
 		comp = processing.Completion{Text: text}
 	} else {
 		var err error
@@ -204,6 +223,39 @@ func (s *server) handleEmbeddings(w http.ResponseWriter, r *http.Request) {
 	})
 }
 
+// categorizeReply overrides the heuristic taxonomy pick so a local run can
+// reproduce a low-confidence answer.
+func (s *server) categorizeReply(system, user string) (string, bool) {
+	if s.categorizeConfidence <= 0 || !strings.Contains(strings.ToLower(system), "categoryid") {
+		return "", false
+	}
+	id := firstCategoryIDFromPrompt(user)
+	if id == "" {
+		return "", false
+	}
+	b, err := json.Marshal(map[string]any{"categoryId": id, "confidence": s.categorizeConfidence})
+	if err != nil {
+		return "", false
+	}
+	return string(b), true
+}
+
+// firstCategoryIDFromPrompt mirrors the "(ID: …)" format of the categorize prompt.
+func firstCategoryIDFromPrompt(user string) string {
+	const marker = "(id:"
+	lower := strings.ToLower(user)
+	at := strings.Index(lower, marker)
+	if at < 0 {
+		return ""
+	}
+	rest := strings.TrimSpace(user[at+len(marker):])
+	end := strings.Index(rest, ")")
+	if end <= 0 {
+		return ""
+	}
+	return strings.TrimSpace(rest[:end])
+}
+
 func splitMessages(msgs []struct {
 	Role    string `json:"role"`
 	Content string `json:"content"`
@@ -211,7 +263,10 @@ func splitMessages(msgs []struct {
 	var users []string
 	for _, m := range msgs {
 		switch strings.ToLower(strings.TrimSpace(m.Role)) {
-		case "system":
+		// Reasoning-model requests send the system message as "developer"
+		// (see processing.OpenAIClient sysRole). Treating it as a user turn made the
+		// mock mis-route every call whose branch depends on the system prompt.
+		case "system", "developer":
 			if system == "" {
 				system = m.Content
 			} else {