package openai_compat import ( "context" "encoding/json" "fmt" "net/http" "net/http/httptest" "strings" "sync" "testing" "go.uber.org/zap" "iop/apps/node/internal/runtime" "iop/packages/go/config" ) type fakeSink struct { mu sync.Mutex events []runtime.RuntimeEvent } func (s *fakeSink) Emit(_ context.Context, event runtime.RuntimeEvent) error { s.mu.Lock() defer s.mu.Unlock() s.events = append(s.events, event) return nil } func (s *fakeSink) all() []runtime.RuntimeEvent { s.mu.Lock() defer s.mu.Unlock() return append([]runtime.RuntimeEvent(nil), s.events...) } func TestOpenAICompatCapabilitiesQueryModels(t *testing.T) { server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { if r.URL.Path != "/v1/models" { t.Fatalf("unexpected path %s", r.URL.Path) } _, _ = w.Write([]byte(`{"object":"list","data":[{"id":"model-a"},{"id":"model-b"}]}`)) })) defer server.Close() adapter := New(config.OpenAICompatConf{ Provider: "lemonade", Endpoint: server.URL, Capacity: 10, MaxQueue: 20, QueueTimeoutMS: 5000, RequestTimeoutMS: 10000, }, zap.NewNop()) caps, err := adapter.Capabilities(context.Background()) if err != nil { t.Fatalf("Capabilities failed: %v", err) } if caps.AdapterName != Name { t.Fatalf("AdapterName: got %q want %q", caps.AdapterName, Name) } if got := strings.Join(caps.Targets, ","); got != "model-a,model-b" { t.Fatalf("targets: got %q", got) } if caps.MaxConcurrency != 10 { t.Fatalf("expected MaxConcurrency 10, got %d", caps.MaxConcurrency) } if caps.MaxQueue != 20 || caps.QueueTimeoutMS != 5000 || caps.RequestTimeoutMS != 10000 { t.Fatalf("queue config: got %+v", caps) } if caps.ProviderStatus != runtime.ProviderStatusAvailable { t.Fatalf("expected available, got %s", caps.ProviderStatus) } adapterDefault := New(config.OpenAICompatConf{Endpoint: server.URL}, zap.NewNop()) capsDefault, err := adapterDefault.Capabilities(context.Background()) if err != nil { t.Fatalf("Capabilities failed: %v", err) } if capsDefault.MaxConcurrency != 8 { t.Fatalf("expected default MaxConcurrency 8, got %d", capsDefault.MaxConcurrency) } } func TestOpenAICompatProbeProviderAvailability(t *testing.T) { t.Run("200_ok_and_target_hit", func(t *testing.T) { server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { if r.URL.Path != "/v1/models" { t.Fatalf("unexpected path %s", r.URL.Path) } _, _ = w.Write([]byte(`{"object":"list","data":[{"id":"model-a"},{"id":"model-b"}]}`)) })) defer server.Close() adapter := New(config.OpenAICompatConf{Provider: "lemonade", Endpoint: server.URL}, zap.NewNop()) res, err := adapter.ProbeProvider(context.Background(), "model-a") if err != nil { t.Fatalf("ProbeProvider failed: %v", err) } if res.Status != runtime.ProviderStatusAvailable { t.Errorf("expected available, got %s", res.Status) } if len(res.Targets) != 2 || res.Targets[0] != "model-a" { t.Errorf("unexpected Targets: %+v", res.Targets) } if res.Metadata["provider"] != "lemonade" { t.Errorf("expected provider metadata, got %+v", res.Metadata) } }) t.Run("200_ok_and_target_miss", func(t *testing.T) { server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { _, _ = w.Write([]byte(`{"object":"list","data":[{"id":"model-a"}]}`)) })) defer server.Close() adapter := New(config.OpenAICompatConf{Endpoint: server.URL}, zap.NewNop()) res, err := adapter.ProbeProvider(context.Background(), "model-b") if err != nil { t.Fatalf("ProbeProvider failed: %v", err) } if res.Status != runtime.ProviderStatusUnavailable { t.Errorf("expected unavailable, got %s", res.Status) } if !strings.Contains(res.Detail, "not found") { t.Errorf("expected 'not found' in detail, got %s", res.Detail) } }) t.Run("500_internal_error", func(t *testing.T) { server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) { w.WriteHeader(http.StatusInternalServerError) })) defer server.Close() adapter := New(config.OpenAICompatConf{Endpoint: server.URL}, zap.NewNop()) res, err := adapter.ProbeProvider(context.Background(), "model-a") if err != nil { t.Fatalf("ProbeProvider failed: %v", err) } if res.Status != runtime.ProviderStatusUnavailable { t.Errorf("expected unavailable, got %s", res.Status) } }) t.Run("empty_target", func(t *testing.T) { server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) { _, _ = w.Write([]byte(`{"object":"list","data":[{"id":"model-a"}]}`)) })) defer server.Close() adapter := New(config.OpenAICompatConf{Endpoint: server.URL}, zap.NewNop()) res, err := adapter.ProbeProvider(context.Background(), "") if err != nil { t.Fatalf("ProbeProvider failed: %v", err) } if res.Status != runtime.ProviderStatusAvailable { t.Errorf("expected available, got %s", res.Status) } }) } func TestOpenAICompatExecuteStreamsDeltasAndFinishReason(t *testing.T) { server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { if r.URL.Path != "/v1/chat/completions" { t.Fatalf("unexpected path %s", r.URL.Path) } w.Header().Set("Content-Type", "text/event-stream") _, _ = fmt.Fprintf(w, "data: %s\n\n", `{"choices":[{"delta":{"reasoning_content":"think "}}]}`) _, _ = fmt.Fprintf(w, "data: %s\n\n", `{"choices":[{"delta":{"content":"hello "}}]}`) _, _ = fmt.Fprintf(w, "data: %s\n\n", `{"choices":[{"delta":{"content":"world"},"finish_reason":"stop"}],"usage":{"prompt_tokens":5,"completion_tokens":2}}`) _, _ = fmt.Fprintf(w, "data: [DONE]\n\n") })) defer server.Close() adapter := New(config.OpenAICompatConf{Endpoint: server.URL}, zap.NewNop()) sink := &fakeSink{} err := adapter.Execute(context.Background(), runtime.ExecutionSpec{ RunID: "run-1", Target: "lemonade-model", Input: map[string]any{"prompt": "say hello"}, }, sink) if err != nil { t.Fatalf("Execute failed: %v", err) } events := sink.all() // start + reasoning_delta + delta + delta + complete if len(events) != 5 { t.Fatalf("expected 5 events, got %d: %+v", len(events), events) } if events[0].Type != runtime.EventTypeStart { t.Fatalf("expected start, got %+v", events[0]) } if events[1].Type != runtime.EventTypeReasoningDelta || events[1].Delta != "think " { t.Fatalf("expected reasoning delta, got %+v", events[1]) } if events[2].Delta+events[3].Delta != "hello world" { t.Fatalf("unexpected deltas: %q + %q", events[2].Delta, events[3].Delta) } complete := events[4] if complete.Type != runtime.EventTypeComplete { t.Fatalf("expected complete, got %+v", complete) } if complete.Metadata["finish_reason"] != "stop" { t.Fatalf("expected finish_reason stop, got %+v", complete.Metadata) } if complete.Usage == nil || complete.Usage.OutputTokens != 2 || complete.Usage.InputTokens != 5 { t.Fatalf("expected usage from chunk, got %+v", complete.Usage) } } func TestOpenAICompatExecuteSendsHeaders(t *testing.T) { var gotAuth, gotContentType string server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { gotAuth = r.Header.Get("Authorization") gotContentType = r.Header.Get("Content-Type") w.Header().Set("Content-Type", "text/event-stream") _, _ = fmt.Fprintf(w, "data: %s\n\n", `{"choices":[{"delta":{"content":"ok"}}]}`) _, _ = fmt.Fprintf(w, "data: [DONE]\n\n") })) defer server.Close() adapter := New(config.OpenAICompatConf{ Endpoint: server.URL, Headers: map[string]string{ "Authorization": "Bearer secret-token", // A user-provided Content-Type must not override the adapter-owned one. "Content-Type": "text/plain", }, }, zap.NewNop()) sink := &fakeSink{} if err := adapter.Execute(context.Background(), runtime.ExecutionSpec{ RunID: "run-h", Target: "lemonade-model", Input: map[string]any{"prompt": "hi"}, }, sink); err != nil { t.Fatalf("Execute failed: %v", err) } if gotAuth != "Bearer secret-token" { t.Fatalf("expected Authorization header, got %q", gotAuth) } if gotContentType != "application/json" { t.Fatalf("expected adapter-owned content type, got %q", gotContentType) } } func TestOpenAICompatExecutePassesOptionsAsTopLevelFields(t *testing.T) { var body map[string]any server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { if err := json.NewDecoder(r.Body).Decode(&body); err != nil { t.Fatalf("decode: %v", err) } w.Header().Set("Content-Type", "text/event-stream") _, _ = fmt.Fprintf(w, "data: %s\n\n", `{"choices":[{"delta":{"content":"ok"}}]}`) _, _ = fmt.Fprintf(w, "data: [DONE]\n\n") })) defer server.Close() adapter := New(config.OpenAICompatConf{Endpoint: server.URL}, zap.NewNop()) sink := &fakeSink{} if err := adapter.Execute(context.Background(), runtime.ExecutionSpec{ RunID: "run-o", Target: "lemonade-model", Input: map[string]any{ "prompt": "hi", "options": map[string]any{ "temperature": 0.2, "max_tokens": float64(8), // adapter-owned fields must not be overridden by options "model": "evil", "stream": false, }, }, }, sink); err != nil { t.Fatalf("Execute failed: %v", err) } if body["temperature"] != 0.2 { t.Fatalf("expected temperature top-level, got %v", body["temperature"]) } if body["max_tokens"] != float64(8) { t.Fatalf("expected max_tokens top-level, got %v", body["max_tokens"]) } if body["model"] != "lemonade-model" { t.Fatalf("options must not override model, got %v", body["model"]) } if body["stream"] != true { t.Fatalf("options must not override stream, got %v", body["stream"]) } } func TestOpenAICompatExecutePassesToolsAndToolChoice(t *testing.T) { var body map[string]any server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { if err := json.NewDecoder(r.Body).Decode(&body); err != nil { t.Fatalf("decode: %v", err) } w.Header().Set("Content-Type", "text/event-stream") _, _ = fmt.Fprintf(w, "data: %s\n\n", `{"choices":[{"delta":{"content":"ok"}}]}`) _, _ = fmt.Fprintf(w, "data: [DONE]\n\n") })) defer server.Close() adapter := New(config.OpenAICompatConf{Endpoint: server.URL}, zap.NewNop()) sink := &fakeSink{} if err := adapter.Execute(context.Background(), runtime.ExecutionSpec{ RunID: "run-t", Target: "qwen3.6:35b", Input: map[string]any{ "prompt": "hi", "tools": []any{map[string]any{"type": "function"}}, "tool_choice": "none", }, }, sink); err != nil { t.Fatalf("Execute failed: %v", err) } if tools, ok := body["tools"].([]any); !ok || len(tools) != 1 { t.Fatalf("tools not passed: %+v", body["tools"]) } if body["tool_choice"] != "none" { t.Fatalf("tool_choice not passed: %+v", body["tool_choice"]) } } func TestOpenAICompatExecuteRetriesSingleToolWhenAutoUnsupported(t *testing.T) { attempts := 0 var retryBody map[string]any server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { attempts++ if attempts == 1 { w.WriteHeader(http.StatusBadRequest) _, _ = w.Write([]byte(`{"error":{"message":"\"auto\" tool choice requires --enable-auto-tool-choice and --tool-call-parser to be set"}}`)) return } if err := json.NewDecoder(r.Body).Decode(&retryBody); err != nil { t.Fatalf("decode retry: %v", err) } w.Header().Set("Content-Type", "text/event-stream") _, _ = fmt.Fprintf(w, "data: %s\n\n", `{"choices":[{"delta":{"content":"ok"}}]}`) _, _ = fmt.Fprintf(w, "data: [DONE]\n\n") })) defer server.Close() adapter := New(config.OpenAICompatConf{Endpoint: server.URL}, zap.NewNop()) sink := &fakeSink{} if err := adapter.Execute(context.Background(), runtime.ExecutionSpec{ RunID: "run-retry", Target: "qwen3.6:35b", Input: map[string]any{ "prompt": "status", "tools": []any{map[string]any{ "type": "function", "function": map[string]any{ "name": "run_commands", }, }}, }, }, sink); err != nil { t.Fatalf("Execute failed: %v", err) } if attempts != 2 { t.Fatalf("attempts: got %d, want 2", attempts) } choice, ok := retryBody["tool_choice"].(map[string]any) if !ok { t.Fatalf("retry tool_choice missing: %+v", retryBody) } fn := choice["function"].(map[string]any) if choice["type"] != "function" || fn["name"] != "run_commands" { t.Fatalf("retry tool_choice: %+v", choice) } } func TestOpenAICompatExecuteFallsBackToTextToolsWhenNativeToolsUnsupported(t *testing.T) { attempts := 0 var fallbackBody map[string]any server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { attempts++ switch attempts { case 1: w.WriteHeader(http.StatusBadRequest) _, _ = w.Write([]byte(`{"error":{"message":"\"auto\" tool choice requires --enable-auto-tool-choice and --tool-call-parser to be set"}}`)) return case 2: w.WriteHeader(http.StatusBadRequest) _, _ = w.Write([]byte(`{"error":{"message":"tool_choice=\"function=ChatCompletionNamedFunction(name='run_commands') type='function'\" requires --tool-call-parser to be set"}}`)) return } if err := json.NewDecoder(r.Body).Decode(&fallbackBody); err != nil { t.Fatalf("decode fallback: %v", err) } w.Header().Set("Content-Type", "text/event-stream") _, _ = fmt.Fprintf(w, "data: %s\n\n", `{"choices":[{"delta":{"content":"\n\n[\"git status\"]\n\n"}}]}`) _, _ = fmt.Fprintf(w, "data: [DONE]\n\n") })) defer server.Close() adapter := New(config.OpenAICompatConf{Endpoint: server.URL}, zap.NewNop()) sink := &fakeSink{} if err := adapter.Execute(context.Background(), runtime.ExecutionSpec{ RunID: "run-text-fallback", Target: "qwen3.6:35b", Input: map[string]any{ "messages": []any{ map[string]any{"role": "system", "content": "Existing Cline system prompt."}, map[string]any{"role": "user", "content": "status"}, }, "tools": []any{map[string]any{ "type": "function", "function": map[string]any{ "name": "run_commands", "parameters": map[string]any{ "type": "object", "properties": map[string]any{ "commands": map[string]any{"type": "array", "items": map[string]any{"type": "string"}}, }, }, }, }}, }, }, sink); err != nil { t.Fatalf("Execute failed: %v", err) } if attempts != 3 { t.Fatalf("attempts: got %d, want 3", attempts) } if _, ok := fallbackBody["tools"]; ok { t.Fatalf("fallback must omit tools: %+v", fallbackBody["tools"]) } if _, ok := fallbackBody["tool_choice"]; ok { t.Fatalf("fallback must omit tool_choice: %+v", fallbackBody["tool_choice"]) } messages := fallbackBody["messages"].([]any) first := messages[0].(map[string]any) if first["role"] != "system" || !strings.Contains(first["content"].(string), "") || !strings.Contains(first["content"].(string), "run_commands") { t.Fatalf("fallback system instruction missing tool format/name: %+v", first) } if !strings.Contains(first["content"].(string), "client workspace root") || !strings.Contains(first["content"].(string), "Do not prepend cd") { t.Fatalf("fallback system instruction missing workspace-root guidance: %+v", first) } if !strings.Contains(first["content"].(string), "Existing Cline system prompt.") { t.Fatalf("fallback system instruction did not preserve existing system content: %+v", first) } if len(messages) != 2 || messages[1].(map[string]any)["role"] != "user" { t.Fatalf("fallback should keep a single leading system message: %+v", messages) } events := sink.all() complete := events[len(events)-1] if complete.Metadata[runtimeMetadataOpenAITextToolFallback] != "true" { t.Fatalf("fallback metadata missing: %+v", complete.Metadata) } } func TestOpenAICompatExecutePreservesToolCallMessages(t *testing.T) { var body map[string]any server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { if err := json.NewDecoder(r.Body).Decode(&body); err != nil { t.Fatalf("decode: %v", err) } w.Header().Set("Content-Type", "text/event-stream") _, _ = fmt.Fprintf(w, "data: %s\n\n", `{"choices":[{"delta":{"content":"ok"}}]}`) _, _ = fmt.Fprintf(w, "data: [DONE]\n\n") })) defer server.Close() adapter := New(config.OpenAICompatConf{Endpoint: server.URL}, zap.NewNop()) sink := &fakeSink{} if err := adapter.Execute(context.Background(), runtime.ExecutionSpec{ RunID: "run-tool-turn", Target: "qwen3.6:35b", Input: map[string]any{ "messages": []any{ map[string]any{ "role": "assistant", "content": "", "tool_calls": []any{map[string]any{ "id": "call_iop_1", "type": "function", "function": map[string]any{ "name": "run_commands", "arguments": `{"commands":["git status"]}`, }, }}, }, map[string]any{ "role": "tool", "content": "clean", "tool_call_id": "call_iop_1", }, }, }, }, sink); err != nil { t.Fatalf("Execute failed: %v", err) } messages, ok := body["messages"].([]any) if !ok || len(messages) != 2 { t.Fatalf("messages not preserved: %+v", body["messages"]) } assistantMsg := messages[0].(map[string]any) if calls, ok := assistantMsg["tool_calls"].([]any); !ok || len(calls) != 1 { t.Fatalf("assistant tool_calls not preserved: %+v", assistantMsg) } toolMsg := messages[1].(map[string]any) if toolMsg["tool_call_id"] != "call_iop_1" { t.Fatalf("tool_call_id not preserved: %+v", toolMsg) } } func TestOpenAICompatExecutePreservesNativeToolCalls(t *testing.T) { server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) { w.Header().Set("Content-Type", "text/event-stream") _, _ = fmt.Fprintf(w, "data: %s\n\n", `{"choices":[{"delta":{"tool_calls":[{"index":0,"id":"call_1","type":"function","function":{"name":"run_commands","arguments":"{\"commands\":"}}]}}]}`) _, _ = fmt.Fprintf(w, "data: %s\n\n", `{"choices":[{"delta":{"tool_calls":[{"index":0,"function":{"arguments":"[\"git status\"]}"}}]},"finish_reason":"tool_calls"}]}`) _, _ = fmt.Fprintf(w, "data: [DONE]\n\n") })) defer server.Close() adapter := New(config.OpenAICompatConf{Endpoint: server.URL}, zap.NewNop()) sink := &fakeSink{} if err := adapter.Execute(context.Background(), runtime.ExecutionSpec{ RunID: "run-native-tools", Target: "qwen3.6:35b", Input: map[string]any{"prompt": "status"}, }, sink); err != nil { t.Fatalf("Execute failed: %v", err) } events := sink.all() complete := events[len(events)-1] if complete.Metadata["finish_reason"] != "tool_calls" { t.Fatalf("finish_reason: %+v", complete.Metadata) } var toolCalls []map[string]any if err := json.Unmarshal([]byte(complete.Metadata[runtimeMetadataOpenAIToolCalls]), &toolCalls); err != nil { t.Fatalf("tool_calls metadata JSON: %v", err) } if len(toolCalls) != 1 || toolCalls[0]["id"] != "call_1" { t.Fatalf("tool_calls: %+v", toolCalls) } fn := toolCalls[0]["function"].(map[string]any) if fn["name"] != "run_commands" || fn["arguments"] != `{"commands":["git status"]}` { t.Fatalf("function: %+v", fn) } } func TestOpenAICompatExecuteRejectsEmptyEndpointOrModel(t *testing.T) { t.Run("empty_endpoint", func(t *testing.T) { adapter := New(config.OpenAICompatConf{}, zap.NewNop()) err := adapter.Execute(context.Background(), runtime.ExecutionSpec{ RunID: "r", Target: "m", Input: map[string]any{"prompt": "hi"}, }, &fakeSink{}) if err == nil || !strings.Contains(err.Error(), "endpoint is required") { t.Fatalf("expected endpoint error, got %v", err) } }) t.Run("empty_model", func(t *testing.T) { adapter := New(config.OpenAICompatConf{Endpoint: "http://localhost:8000"}, zap.NewNop()) err := adapter.Execute(context.Background(), runtime.ExecutionSpec{ RunID: "r", Input: map[string]any{"prompt": "hi"}, }, &fakeSink{}) if err == nil || !strings.Contains(err.Error(), "target/model is required") { t.Fatalf("expected model error, got %v", err) } }) } func TestOpenAICompatJoinOpenAIPathNoDuplicateV1(t *testing.T) { cases := []struct { endpoint string path string wantTail string }{ {"http://host:8000", "/v1/models", "/v1/models"}, {"http://host:8000/", "/v1/chat/completions", "/v1/chat/completions"}, {"http://host:8000/v1", "/v1/models", "/v1/models"}, {"http://host:8000/v1/", "/v1/chat/completions", "/v1/chat/completions"}, } for _, c := range cases { got := joinOpenAIPath(strings.TrimRight(c.endpoint, "/"), c.path) if !strings.HasSuffix(got, c.wantTail) || strings.Contains(got, "/v1/v1") { t.Errorf("joinOpenAIPath(%q,%q)=%q want suffix %q without /v1/v1", c.endpoint, c.path, got, c.wantTail) } } }