Added a configurable timeout knob

internal/llm/openai_compatible_client.go

@@ -49,7 +49,7 @@ func NewOpenAICompatibleClient(cfg OpenAICompatibleConfig) (*OpenAICompatibleCli
 
 	timeout := cfg.Timeout
 	if timeout <= 0 {
-		timeout = 30 * time.Second
+		timeout = 10 * time.Minute
 	}
 
 	var client *http.Client
@@ -72,6 +72,10 @@ func NewOpenAICompatibleClient(cfg OpenAICompatibleConfig) (*OpenAICompatibleCli
 }
 
 func (c *OpenAICompatibleClient) Generate(ctx context.Context, req domain.GenerateRequest) (*domain.GenerateResponse, error) {
+	if req.Target.TimeoutSeconds < 0 {
+		return nil, fmt.Errorf("%w: timeout_seconds must be greater than or equal to 0", ErrInvalidRequest)
+	}
+
 	model := strings.TrimSpace(req.Target.Model)
 	if model == "" {
 		model = strings.TrimSpace(c.defaultModel)
@@ -122,7 +126,21 @@ func (c *OpenAICompatibleClient) Generate(ctx context.Context, req domain.Genera
 		httpReq.Header.Set("Authorization", "Bearer "+c.apiKey)
 	}
 
-	httpResp, err := c.httpClient.Do(httpReq)
+	effectiveTimeout := c.timeout
+	if req.Target.TimeoutSeconds > 0 {
+		effectiveTimeout = time.Duration(req.Target.TimeoutSeconds) * time.Second
+	}
+
+	httpClient := c.httpClient
+	if httpClient == nil {
+		httpClient = &http.Client{Timeout: effectiveTimeout}
+	} else if httpClient.Timeout != effectiveTimeout {
+		cloned := *httpClient
+		cloned.Timeout = effectiveTimeout
+		httpClient = &cloned
+	}
+
+	httpResp, err := httpClient.Do(httpReq)
 	if err != nil {
 		return nil, fmt.Errorf("%w: %v", ErrRequestFailed, err)
 	}

internal/llm/openai_compatible_client_test.go

@@ -287,3 +287,52 @@ func TestOpenAICompatibleClientTimeout(t *testing.T) {
 		t.Fatalf("expected ErrRequestFailed, got %v", err)
 	}
 }
+
+func TestOpenAICompatibleClientRequestTimeoutOverride(t *testing.T) {
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		time.Sleep(100 * time.Millisecond)
+		_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"ok"}}]}`))
+	}))
+	defer ts.Close()
+
+	client, err := NewOpenAICompatibleClient(OpenAICompatibleConfig{
+		BaseURL: ts.URL + "/v1",
+		Model:   "m",
+		Timeout: 50 * time.Millisecond,
+	})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	resp, err := client.Generate(context.Background(), domain.GenerateRequest{
+		Prompt: domain.RenderedPrompt{Messages: []domain.RenderedMessage{{Role: "user", Content: "hi"}}},
+		Target: domain.ModelTarget{TimeoutSeconds: 1},
+	})
+	if err != nil {
+		t.Fatalf("expected request-level timeout override to succeed, got %v", err)
+	}
+	if resp.Content != "ok" {
+		t.Fatalf("expected response content ok, got %q", resp.Content)
+	}
+}
+
+func TestOpenAICompatibleClientNegativeTimeoutRejected(t *testing.T) {
+	client, err := NewOpenAICompatibleClient(OpenAICompatibleConfig{
+		BaseURL: "http://example.com/v1",
+		Model:   "m",
+	})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	_, err = client.Generate(context.Background(), domain.GenerateRequest{
+		Prompt: domain.RenderedPrompt{Messages: []domain.RenderedMessage{{Role: "user", Content: "hi"}}},
+		Target: domain.ModelTarget{TimeoutSeconds: -1},
+	})
+	if err == nil {
+		t.Fatal("expected invalid request error")
+	}
+	if !errors.Is(err, ErrInvalidRequest) {
+		t.Fatalf("expected ErrInvalidRequest, got %v", err)
+	}
+}