feat: add SAP AI Core client for Anthropic models

Implements native AI Core support with: - OAuth2 token refresh - Deployment discovery via /v2/lm/deployments - Anthropic Messages API via /invoke endpoint - Uses bedrock-2023-05-31 API version (AI Core uses Bedrock format) - Model field omitted from body (deployment URL specifies model) - Retry logic with exponential backoff Tested via integration tests against live AI Core endpoint.
2026-05-10 01:02:48 -07:00
parent 2089ca0f2d
commit b62b52aab1
3 changed files with 954 additions and 7 deletions
@@ -0,0 +1,535 @@
+package llm
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"sync/atomic"
+	"testing"
+	"time"
+)
+
+func TestAICoreClient_TokenFetch(t *testing.T) {
+	tokenCalls := int32(0)
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path == "/oauth/token" {
+			atomic.AddInt32(&tokenCalls, 1)
+			if r.Method != http.MethodPost {
+				t.Errorf("expected POST for token, got %s", r.Method)
+			}
+			if r.Header.Get("Content-Type") != "application/x-www-form-urlencoded" {
+				t.Errorf("expected form content type")
+			}
+			w.Header().Set("Content-Type", "application/json")
+			json.NewEncoder(w).Encode(map[string]interface{}{
+				"access_token": "test-token-123",
+				"expires_in":   3600,
+			})
+			return
+		}
+		t.Errorf("unexpected path: %s", r.URL.Path)
+	}))
+	defer server.Close()
+
+	client := NewAICoreClient(AICoreConfig{
+		ClientID:      "test-id",
+		ClientSecret:  "test-secret",
+		AuthURL:       server.URL,
+		APIURL:        server.URL,
+		ResourceGroup: "default",
+	})
+
+	token, err := client.getToken(context.Background())
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if token != "test-token-123" {
+		t.Errorf("expected token 'test-token-123', got %q", token)
+	}
+
+	// Second call should use cached token
+	token2, err := client.getToken(context.Background())
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if token2 != "test-token-123" {
+		t.Errorf("expected cached token")
+	}
+	if atomic.LoadInt32(&tokenCalls) != 1 {
+		t.Errorf("expected 1 token call (cached), got %d", tokenCalls)
+	}
+}
+
+func TestAICoreClient_DeploymentFetch(t *testing.T) {
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path == "/oauth/token" {
+			w.Header().Set("Content-Type", "application/json")
+			json.NewEncoder(w).Encode(map[string]interface{}{
+				"access_token": "test-token",
+				"expires_in":   3600,
+			})
+			return
+		}
+		if r.URL.Path == "/v2/lm/deployments" {
+			if r.Header.Get("Authorization") != "Bearer test-token" {
+				t.Errorf("expected Bearer auth")
+			}
+			if r.Header.Get("AI-Resource-Group") != "default" {
+				t.Errorf("expected resource group header")
+			}
+			w.Header().Set("Content-Type", "application/json")
+			json.NewEncoder(w).Encode(map[string]interface{}{
+				"resources": []map[string]interface{}{
+					{
+						"id":            "deploy-123",
+						"deploymentUrl": "https://example.com/v2/inference/deployments/deploy-123",
+						"status":        "RUNNING",
+						"details": map[string]interface{}{
+							"resources": map[string]interface{}{
+								"backend_details": map[string]interface{}{
+									"model": map[string]interface{}{
+										"name": "anthropic--claude-4.6-sonnet",
+									},
+								},
+							},
+						},
+					},
+					{
+						"id":            "deploy-456",
+						"deploymentUrl": "https://example.com/v2/inference/deployments/deploy-456",
+						"status":        "STOPPED",
+						"details": map[string]interface{}{
+							"resources": map[string]interface{}{
+								"backend_details": map[string]interface{}{
+									"model": map[string]interface{}{
+										"name": "gpt-5",
+									},
+								},
+							},
+						},
+					},
+					{
+						"id":            "deploy-789",
+						"deploymentUrl": "https://example.com/v2/inference/deployments/deploy-789",
+						"status":        "RUNNING",
+						"details": map[string]interface{}{
+							"resources": map[string]interface{}{
+								"backend_details": map[string]interface{}{
+									"model": map[string]interface{}{
+										"name": "gpt-5",
+									},
+								},
+							},
+						},
+					},
+				},
+			})
+			return
+		}
+		t.Errorf("unexpected path: %s", r.URL.Path)
+	}))
+	defer server.Close()
+
+	client := NewAICoreClient(AICoreConfig{
+		ClientID:      "test-id",
+		ClientSecret:  "test-secret",
+		AuthURL:       server.URL,
+		APIURL:        server.URL,
+		ResourceGroup: "default",
+	})
+
+	// Should find running deployment
+	url, err := client.getDeploymentURL(context.Background(), "anthropic--claude-4.6-sonnet")
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if url != "https://example.com/v2/inference/deployments/deploy-123" {
+		t.Errorf("unexpected URL: %s", url)
+	}
+
+	// Should find running gpt-5, not stopped one
+	url, err = client.getDeploymentURL(context.Background(), "gpt-5")
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if url != "https://example.com/v2/inference/deployments/deploy-789" {
+		t.Errorf("unexpected URL: %s", url)
+	}
+
+	// Should error on unknown model
+	_, err = client.getDeploymentURL(context.Background(), "unknown-model")
+	if err == nil {
+		t.Error("expected error for unknown model")
+	}
+}
+
+func TestAICoreClient_CompleteAnthropic(t *testing.T) {
+	// Use a pointer to capture the server URL for use in the handler
+	var baseURL string
+	mux := http.NewServeMux()
+	mux.HandleFunc("/oauth/token", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(map[string]interface{}{
+			"access_token": "test-token",
+			"expires_in":   3600,
+		})
+	})
+	mux.HandleFunc("/v2/lm/deployments", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(map[string]interface{}{
+			"resources": []map[string]interface{}{
+				{
+					"id":            "deploy-anthropic",
+					"deploymentUrl": baseURL + "/deployments/anthropic",
+					"status":        "RUNNING",
+					"details": map[string]interface{}{
+						"resources": map[string]interface{}{
+							"backend_details": map[string]interface{}{
+								"model": map[string]interface{}{
+									"name": "anthropic--claude-4.6-sonnet",
+								},
+							},
+						},
+					},
+				},
+			},
+		})
+	})
+	mux.HandleFunc("/deployments/anthropic/invoke", func(w http.ResponseWriter, r *http.Request) {
+		if r.Header.Get("Authorization") != "Bearer test-token" {
+			t.Errorf("expected Bearer auth on invoke")
+		}
+		var req anthropicRequest
+		if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
+			t.Fatalf("decode request: %v", err)
+		}
+		if req.AnthropicVersion != "bedrock-2023-05-31" {
+			t.Errorf("expected bedrock anthropic_version in request")
+		}
+		if req.System != "You are helpful" {
+			t.Errorf("expected system prompt: %q", req.System)
+		}
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(map[string]interface{}{
+			"content": []map[string]interface{}{
+				{"type": "text", "text": "Hello from AI Core!"},
+			},
+		})
+	})
+
+	server := httptest.NewServer(mux)
+	baseURL = server.URL
+	defer server.Close()
+
+	client := NewAICoreClient(AICoreConfig{
+		ClientID:      "test-id",
+		ClientSecret:  "test-secret",
+		AuthURL:       server.URL,
+		APIURL:        server.URL,
+		ResourceGroup: "default",
+	})
+
+	result, err := client.CompleteAnthropic(context.Background(), "anthropic--claude-4.6-sonnet", []Message{
+		{Role: "system", Content: "You are helpful"},
+		{Role: "user", Content: "Hello"},
+	}, 8192, 0)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if result != "Hello from AI Core!" {
+		t.Errorf("expected 'Hello from AI Core!', got %q", result)
+	}
+}
+
+func TestAICoreClient_CompleteOpenAI(t *testing.T) {
+	var baseURL string
+	mux := http.NewServeMux()
+	mux.HandleFunc("/oauth/token", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(map[string]interface{}{
+			"access_token": "test-token",
+			"expires_in":   3600,
+		})
+	})
+	mux.HandleFunc("/v2/lm/deployments", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(map[string]interface{}{
+			"resources": []map[string]interface{}{
+				{
+					"id":            "deploy-openai",
+					"deploymentUrl": baseURL + "/deployments/openai",
+					"status":        "RUNNING",
+					"details": map[string]interface{}{
+						"resources": map[string]interface{}{
+							"backend_details": map[string]interface{}{
+								"model": map[string]interface{}{
+									"name": "gpt-5",
+								},
+							},
+						},
+					},
+				},
+			},
+		})
+	})
+	mux.HandleFunc("/deployments/openai/chat/completions", func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Query().Get("api-version") != AICoreOpenAIAPIVersion {
+			t.Errorf("expected api-version %s, got %s", AICoreOpenAIAPIVersion, r.URL.Query().Get("api-version"))
+		}
+		var req ChatRequest
+		if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
+			t.Fatalf("decode request: %v", err)
+		}
+		if req.Model != "gpt-5" {
+			t.Errorf("expected model gpt-5, got %s", req.Model)
+		}
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(ChatResponse{
+			Choices: []struct {
+				Message struct {
+					Content string `json:"content"`
+				} `json:"message"`
+			}{
+				{Message: struct {
+					Content string `json:"content"`
+				}{Content: "Hello from GPT-5!"}},
+			},
+		})
+	})
+
+	server := httptest.NewServer(mux)
+	baseURL = server.URL
+	defer server.Close()
+
+	client := NewAICoreClient(AICoreConfig{
+		ClientID:      "test-id",
+		ClientSecret:  "test-secret",
+		AuthURL:       server.URL,
+		APIURL:        server.URL,
+		ResourceGroup: "default",
+	})
+
+	result, err := client.CompleteOpenAI(context.Background(), "gpt-5", []Message{
+		{Role: "user", Content: "Hello"},
+	}, 0)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if result != "Hello from GPT-5!" {
+		t.Errorf("expected 'Hello from GPT-5!', got %q", result)
+	}
+}
+
+func TestIsAnthropicModel(t *testing.T) {
+	tests := []struct {
+		model    string
+		expected bool
+	}{
+		// SAP AI Core uses "anthropic--" prefix for Anthropic models
+		{"anthropic--claude-4.6-sonnet", true},
+		{"anthropic--claude-4.6-opus", true},
+		{"anthropic--claude-3-5-sonnet", true},
+		// Non-prefixed model names are not detected as Anthropic
+		// (SAP AI Core always uses the prefix for Anthropic models)
+		{"claude-sonnet-4", false},
+		{"gpt-5", false},
+		{"gpt-4.1", false},
+		{"llama-3", false},
+		{"my-claude-model", false}, // Avoid false positives on "claude" substring
+	}
+
+	for _, tt := range tests {
+		got := IsAnthropicModel(tt.model)
+		if got != tt.expected {
+			t.Errorf("IsAnthropicModel(%q) = %v, want %v", tt.model, got, tt.expected)
+		}
+	}
+}
+
+func TestAICoreClient_TokenExpiry(t *testing.T) {
+	tokenCalls := int32(0)
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path == "/oauth/token" {
+			call := atomic.AddInt32(&tokenCalls, 1)
+			w.Header().Set("Content-Type", "application/json")
+			json.NewEncoder(w).Encode(map[string]interface{}{
+				"access_token": fmt.Sprintf("token-%d", call),
+				"expires_in":   1, // 1 second expiry
+			})
+			return
+		}
+	}))
+	defer server.Close()
+
+	client := NewAICoreClient(AICoreConfig{
+		ClientID:      "test-id",
+		ClientSecret:  "test-secret",
+		AuthURL:       server.URL,
+		APIURL:        server.URL,
+		ResourceGroup: "default",
+	})
+
+	// First call
+	token1, err := client.getToken(context.Background())
+	if err != nil {
+		t.Fatalf("first getToken: %v", err)
+	}
+
+	// Force token expiry by manipulating expiry time
+	client.mu.Lock()
+	client.tokenExpiry = time.Now().Add(-time.Hour)
+	client.mu.Unlock()
+
+	// Should fetch new token
+	token2, err := client.getToken(context.Background())
+	if err != nil {
+		t.Fatalf("second getToken: %v", err)
+	}
+
+	if token1 == token2 {
+		t.Error("expected different tokens after expiry")
+	}
+	if atomic.LoadInt32(&tokenCalls) != 2 {
+		t.Errorf("expected 2 token calls, got %d", tokenCalls)
+	}
+}
+
+func TestAICoreClient_WithTimeout(t *testing.T) {
+	client := NewAICoreClient(AICoreConfig{
+		ClientID:      "test-id",
+		ClientSecret:  "test-secret",
+		AuthURL:       "https://auth.example.com",
+		APIURL:        "https://api.example.com",
+		ResourceGroup: "default",
+	})
+
+	// Default timeout is 5 minutes
+	if client.http.Timeout != 5*time.Minute {
+		t.Errorf("expected default timeout 5m, got %v", client.http.Timeout)
+	}
+
+	// WithTimeout should update the timeout
+	client.WithTimeout(10 * time.Minute)
+	if client.http.Timeout != 10*time.Minute {
+		t.Errorf("expected timeout 10m, got %v", client.http.Timeout)
+	}
+}
+
+func TestClient_WithAICore(t *testing.T) {
+	client := NewClient("http://example.com", "key", "model")
+	if client.provider != ProviderOpenAI {
+		t.Errorf("expected default provider openai, got %s", client.provider)
+	}
+
+	client.WithAICore(AICoreConfig{
+		ClientID:      "id",
+		ClientSecret:  "secret",
+		AuthURL:       "https://auth.example.com",
+		APIURL:        "https://api.example.com",
+		ResourceGroup: "default",
+	})
+
+	if client.provider != ProviderAICore {
+		t.Errorf("expected provider aicore, got %s", client.provider)
+	}
+	if client.aicore == nil {
+		t.Error("expected aicore client to be set")
+	}
+}
+
+func TestClient_WithTimeout_PropagatestoAICore(t *testing.T) {
+	client := NewClient("http://example.com", "key", "model").
+		WithAICore(AICoreConfig{
+			ClientID:      "id",
+			ClientSecret:  "secret",
+			AuthURL:       "https://auth.example.com",
+			APIURL:        "https://api.example.com",
+			ResourceGroup: "default",
+		})
+
+	// Default should be 5 minutes (inherited from parent client)
+	if client.aicore.http.Timeout != 5*time.Minute {
+		t.Errorf("expected aicore default timeout 5m, got %v", client.aicore.http.Timeout)
+	}
+
+	// WithTimeout should propagate to AI Core client
+	client.WithTimeout(15 * time.Minute)
+	if client.http.Timeout != 15*time.Minute {
+		t.Errorf("expected parent timeout 15m, got %v", client.http.Timeout)
+	}
+	if client.aicore.http.Timeout != 15*time.Minute {
+		t.Errorf("expected aicore timeout 15m, got %v", client.aicore.http.Timeout)
+	}
+}
+
+func TestClient_CompleteAICore(t *testing.T) {
+	var baseURL string
+	mux := http.NewServeMux()
+	mux.HandleFunc("/oauth/token", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(map[string]interface{}{
+			"access_token": "test-token",
+			"expires_in":   3600,
+		})
+	})
+	mux.HandleFunc("/v2/lm/deployments", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(map[string]interface{}{
+			"resources": []map[string]interface{}{
+				{
+					"id":            "deploy-test",
+					"deploymentUrl": baseURL + "/deployments/test",
+					"status":        "RUNNING",
+					"details": map[string]interface{}{
+						"resources": map[string]interface{}{
+							"backend_details": map[string]interface{}{
+								"model": map[string]interface{}{
+									"name": "gpt-5",
+								},
+							},
+						},
+					},
+				},
+			},
+		})
+	})
+	mux.HandleFunc("/deployments/test/chat/completions", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(ChatResponse{
+			Choices: []struct {
+				Message struct {
+					Content string `json:"content"`
+				} `json:"message"`
+			}{
+				{Message: struct {
+					Content string `json:"content"`
+				}{Content: "AI Core via Client works!"}},
+			},
+		})
+	})
+
+	server := httptest.NewServer(mux)
+	baseURL = server.URL
+	defer server.Close()
+
+	client := NewClient("", "", "gpt-5").WithAICore(AICoreConfig{
+		ClientID:      "test-id",
+		ClientSecret:  "test-secret",
+		AuthURL:       server.URL,
+		APIURL:        server.URL,
+		ResourceGroup: "default",
+	})
+
+	result, err := client.Complete(context.Background(), []Message{
+		{Role: "user", Content: "Hello"},
+	})
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if !strings.Contains(result, "AI Core via Client works!") {
+		t.Errorf("unexpected result: %s", result)
+	}
+}