feat: native SAP AI Core support

Add native SAP AI Core provider that handles OAuth token management and deployment discovery automatically. This eliminates the need for the external LLM proxy when running in SAP environments. Changes: - Add AICoreClient with OAuth token caching and deployment URL discovery - Support both Anthropic and OpenAI models via AI Core deployments - Update CI to use native AI Core provider - Update action inputs to accept AI Core credentials - Update README with AI Core configuration examples Model names must match AI Core deployment names (e.g. anthropic--claude-4.6-sonnet, gpt-5).
2026-05-10 08:38:59 -07:00
parent c41c9590b7
commit 7dab35de41
7 changed files with 1070 additions and 33 deletions
@@ -0,0 +1,391 @@
+package llm
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"net/url"
+	"strings"
+	"sync"
+	"time"
+)
+
+// AICoreOpenAIAPIVersion is the API version used for OpenAI models through AI Core.
+// Update this when SAP AI Core releases a new stable version.
+const AICoreOpenAIAPIVersion = "2024-12-01-preview"
+
+// maxErrorBodyLen limits the length of response bodies included in error messages
+// to prevent leaking potentially sensitive upstream details in logs.
+const maxErrorBodyLen = 200
+
+// AICoreConfig holds SAP AI Core authentication and connection settings.
+type AICoreConfig struct {
+	ClientID      string
+	ClientSecret  string
+	AuthURL       string
+	APIURL        string
+	ResourceGroup string
+}
+
+// AICoreClient wraps AI Core authentication and deployment discovery.
+// Thread-safe for concurrent use after construction.
+//
+// Design: The deployment cache is populated once and never invalidated. This is
+// acceptable for short-lived CI runner processes, but longer-lived deployments
+// may want to add a TTL or re-fetch on errors.
+type AICoreClient struct {
+	config AICoreConfig
+	http   *http.Client
+
+	mu          sync.RWMutex
+	token       string
+	tokenExpiry time.Time
+	deployments map[string]string // model name -> deployment URL
+}
+
+// NewAICoreClient creates a new AI Core client with the given configuration.
+// The client uses a default 5-minute timeout; use WithTimeout to customize.
+func NewAICoreClient(cfg AICoreConfig) *AICoreClient {
+	return &AICoreClient{
+		config:      cfg,
+		http:        &http.Client{Timeout: 5 * time.Minute},
+		deployments: make(map[string]string),
+	}
+}
+
+// WithTimeout sets the HTTP request timeout for AI Core calls.
+// This should be called during construction, before concurrent use.
+func (c *AICoreClient) WithTimeout(d time.Duration) *AICoreClient {
+	c.http.Timeout = d
+	return c
+}
+
+// truncateBody truncates a response body for inclusion in error messages.
+// This prevents leaking potentially sensitive upstream response details in logs.
+func truncateBody(body []byte) string {
+	if len(body) <= maxErrorBodyLen {
+		return string(body)
+	}
+	return string(body[:maxErrorBodyLen]) + "..."
+}
+
+// getToken returns a valid OAuth token, refreshing if necessary.
+func (c *AICoreClient) getToken(ctx context.Context) (string, error) {
+	c.mu.RLock()
+	if c.token != "" && time.Now().Add(5*time.Minute).Before(c.tokenExpiry) {
+		token := c.token
+		c.mu.RUnlock()
+		return token, nil
+	}
+	c.mu.RUnlock()
+
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
+	// Double-check after acquiring write lock
+	if c.token != "" && time.Now().Add(5*time.Minute).Before(c.tokenExpiry) {
+		return c.token, nil
+	}
+
+	token, expiry, err := c.fetchToken(ctx)
+	if err != nil {
+		return "", err
+	}
+	c.token = token
+	c.tokenExpiry = expiry
+	return token, nil
+}
+
+func (c *AICoreClient) fetchToken(ctx context.Context) (string, time.Time, error) {
+	tokenURL := strings.TrimRight(c.config.AuthURL, "/") + "/oauth/token"
+
+	data := url.Values{}
+	data.Set("grant_type", "client_credentials")
+	data.Set("client_id", c.config.ClientID)
+	data.Set("client_secret", c.config.ClientSecret)
+
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, tokenURL, strings.NewReader(data.Encode()))
+	if err != nil {
+		return "", time.Time{}, fmt.Errorf("create token request: %w", err)
+	}
+	req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
+
+	resp, err := c.http.Do(req)
+	if err != nil {
+		return "", time.Time{}, fmt.Errorf("token request: %w", err)
+	}
+	defer resp.Body.Close()
+
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return "", time.Time{}, fmt.Errorf("read token response: %w", err)
+	}
+
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		return "", time.Time{}, fmt.Errorf("token request failed (status %d): %s", resp.StatusCode, truncateBody(body))
+	}
+
+	var tokenResp struct {
+		AccessToken string `json:"access_token"`
+		ExpiresIn   int    `json:"expires_in"`
+	}
+	if err := json.Unmarshal(body, &tokenResp); err != nil {
+		return "", time.Time{}, fmt.Errorf("parse token response: %w", err)
+	}
+
+	if tokenResp.AccessToken == "" {
+		return "", time.Time{}, fmt.Errorf("empty access token in response")
+	}
+
+	expiry := time.Now().Add(time.Duration(tokenResp.ExpiresIn) * time.Second)
+	return tokenResp.AccessToken, expiry, nil
+}
+
+// getDeploymentURL returns the deployment URL for a model, fetching deployments if needed.
+// getDeploymentURL returns the deployment URL for a model, fetching deployments if needed.
+// Also returns a valid token for use by the caller, avoiding redundant getToken calls.
+//
+// Note: The token is fetched before acquiring the write lock to avoid holding the lock
+// during network I/O. In rare cases where multiple goroutines race and one waits a long
+// time for the write lock, the token could theoretically expire. The 5-minute refresh
+// buffer in getToken makes this extremely unlikely in practice.
+func (c *AICoreClient) getDeploymentURL(ctx context.Context, model string) (deployURL, token string, err error) {
+	c.mu.RLock()
+	if u, ok := c.deployments[model]; ok {
+		c.mu.RUnlock()
+		// Still need a token for the caller
+		token, err = c.getToken(ctx)
+		if err != nil {
+			return "", "", fmt.Errorf("get token: %w", err)
+		}
+		return u, token, nil
+	}
+	c.mu.RUnlock()
+
+	// Fetch token first (before acquiring write lock to avoid holding lock during I/O)
+	token, err = c.getToken(ctx)
+	if err != nil {
+		return "", "", fmt.Errorf("get token for deployments: %w", err)
+	}
+
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
+	// Double-check after acquiring write lock
+	if u, ok := c.deployments[model]; ok {
+		return u, token, nil
+	}
+
+	if err := c.fetchDeployments(ctx, token); err != nil {
+		return "", "", err
+	}
+
+	if u, ok := c.deployments[model]; ok {
+		return u, token, nil
+	}
+	return "", "", fmt.Errorf("no deployment found for model %q", model)
+}
+
+func (c *AICoreClient) fetchDeployments(ctx context.Context, token string) error {
+	deployURL := strings.TrimRight(c.config.APIURL, "/") + "/v2/lm/deployments"
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, deployURL, nil)
+	if err != nil {
+		return fmt.Errorf("create deployments request: %w", err)
+	}
+	req.Header.Set("Authorization", "Bearer "+token)
+	req.Header.Set("AI-Resource-Group", c.config.ResourceGroup)
+
+	resp, err := c.http.Do(req)
+	if err != nil {
+		return fmt.Errorf("deployments request: %w", err)
+	}
+	defer resp.Body.Close()
+
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return fmt.Errorf("read deployments response: %w", err)
+	}
+
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		return fmt.Errorf("deployments request failed (status %d): %s", resp.StatusCode, truncateBody(body))
+	}
+
+	var deployResp struct {
+		Resources []struct {
+			DeploymentURL string `json:"deploymentUrl"`
+			Status        string `json:"status"`
+			Details       struct {
+				Resources struct {
+					BackendDetails struct {
+						Model struct {
+							Name string `json:"name"`
+						} `json:"model"`
+					} `json:"backend_details"`
+				} `json:"resources"`
+			} `json:"details"`
+		} `json:"resources"`
+	}
+	if err := json.Unmarshal(body, &deployResp); err != nil {
+		return fmt.Errorf("parse deployments response: %w", err)
+	}
+
+	for _, r := range deployResp.Resources {
+		if r.Status != "RUNNING" {
+			continue
+		}
+		modelName := r.Details.Resources.BackendDetails.Model.Name
+		if modelName == "" {
+			continue
+		}
+		c.deployments[modelName] = r.DeploymentURL
+	}
+
+	return nil
+}
+
+// CompleteAnthropic sends a request to an Anthropic model via AI Core.
+func (c *AICoreClient) CompleteAnthropic(ctx context.Context, model string, messages []Message, maxTokens int, temperature float64) (string, error) {
+	deployURL, token, err := c.getDeploymentURL(ctx, model)
+	if err != nil {
+		return "", err
+	}
+
+	// Extract system message
+	var system string
+	var userMessages []anthropicMsg
+	for _, m := range messages {
+		if m.Role == "system" {
+			system = m.Content
+		} else {
+			userMessages = append(userMessages, anthropicMsg{
+				Role:    m.Role,
+				Content: m.Content,
+			})
+		}
+	}
+
+	reqBody := anthropicRequest{
+		AnthropicVersion: "bedrock-2023-05-31", // SAP AI Core uses Bedrock format
+		// Model omitted - AI Core deployment already specifies model
+		MaxTokens: maxTokens,
+		System:    system,
+		Messages:  userMessages,
+	}
+	if temperature > 0 {
+		reqBody.Temperature = temperature
+	}
+
+	data, err := json.Marshal(reqBody)
+	if err != nil {
+		return "", fmt.Errorf("marshal request: %w", err)
+	}
+
+	// AI Core uses /invoke for Anthropic models
+	invokeURL := strings.TrimRight(deployURL, "/") + "/invoke"
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, invokeURL, bytes.NewReader(data))
+	if err != nil {
+		return "", fmt.Errorf("create request: %w", err)
+	}
+	req.Header.Set("Authorization", "Bearer "+token)
+	req.Header.Set("AI-Resource-Group", c.config.ResourceGroup)
+	req.Header.Set("Content-Type", "application/json")
+
+	resp, err := c.http.Do(req)
+	if err != nil {
+		return "", fmt.Errorf("AI Core request: %w", err)
+	}
+	defer resp.Body.Close()
+
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return "", fmt.Errorf("read response: %w", err)
+	}
+
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		return "", fmt.Errorf("AI Core API error (status %d): %s", resp.StatusCode, truncateBody(body))
+	}
+
+	var anthropicResp anthropicResponse
+	if err := json.Unmarshal(body, &anthropicResp); err != nil {
+		return "", fmt.Errorf("parse response: %w", err)
+	}
+
+	if len(anthropicResp.Content) == 0 {
+		return "", fmt.Errorf("no content in response")
+	}
+
+	var sb strings.Builder
+	for _, block := range anthropicResp.Content {
+		if block.Type == "text" {
+			sb.WriteString(block.Text)
+		}
+	}
+	result := sb.String()
+	if result == "" {
+		return "", fmt.Errorf("no text content in response")
+	}
+	return result, nil
+}
+
+// CompleteOpenAI sends a request to an OpenAI model via AI Core.
+func (c *AICoreClient) CompleteOpenAI(ctx context.Context, model string, messages []Message, temperature float64) (string, error) {
+	deployURL, token, err := c.getDeploymentURL(ctx, model)
+	if err != nil {
+		return "", err
+	}
+
+	reqBody := ChatRequest{
+		Model:       model,
+		Temperature: temperature,
+		Messages:    messages,
+	}
+
+	data, err := json.Marshal(reqBody)
+	if err != nil {
+		return "", fmt.Errorf("marshal request: %w", err)
+	}
+
+	// AI Core uses /chat/completions?api-version=<version> for OpenAI models
+	chatURL := strings.TrimRight(deployURL, "/") + "/chat/completions?api-version=" + AICoreOpenAIAPIVersion
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, chatURL, bytes.NewReader(data))
+	if err != nil {
+		return "", fmt.Errorf("create request: %w", err)
+	}
+	req.Header.Set("Authorization", "Bearer "+token)
+	req.Header.Set("AI-Resource-Group", c.config.ResourceGroup)
+	req.Header.Set("Content-Type", "application/json")
+
+	resp, err := c.http.Do(req)
+	if err != nil {
+		return "", fmt.Errorf("AI Core request: %w", err)
+	}
+	defer resp.Body.Close()
+
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return "", fmt.Errorf("read response: %w", err)
+	}
+
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		return "", fmt.Errorf("AI Core API error (status %d): %s", resp.StatusCode, truncateBody(body))
+	}
+
+	var openaiResp ChatResponse
+	if err := json.Unmarshal(body, &openaiResp); err != nil {
+		return "", fmt.Errorf("parse response: %w", err)
+	}
+
+	if len(openaiResp.Choices) == 0 {
+		return "", fmt.Errorf("no choices in response")
+	}
+	return openaiResp.Choices[0].Message.Content, nil
+}
+
+// IsAnthropicModel returns true if the model name indicates an Anthropic model.
+// SAP AI Core uses "anthropic--" prefix for Anthropic models (e.g., "anthropic--claude-3-5-sonnet").
+func IsAnthropicModel(model string) bool {
+	return strings.HasPrefix(model, "anthropic--")
+}
@@ -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) {
+	// baseURL is set after server creation; captured by closure in handlers
+	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)
+	}
+}
@@ -1,6 +1,6 @@
 // Package llm provides clients for LLM chat completion APIs.
 //
-// Supports OpenAI-compatible (default) and Anthropic Messages API providers.
+// Supports OpenAI-compatible (default), Anthropic Messages API, and SAP AI Core providers.
 package llm

 import (
@@ -22,6 +22,8 @@ const (
 	ProviderOpenAI Provider = "openai"
 	// ProviderAnthropic uses the Anthropic Messages API endpoint.
 	ProviderAnthropic Provider = "anthropic"
+	// ProviderAICore uses SAP AI Core with OAuth authentication.
+	ProviderAICore Provider = "aicore"
 )

 // Client calls an LLM chat completion API.
@@ -35,6 +37,7 @@ type Client struct {
 	temperature float64
 	provider    Provider
 	http        *http.Client
+	aicore      *AICoreClient // Only set when provider is aicore
 }

 // NewClient creates a new LLM client. Default provider is OpenAI-compatible.
@@ -49,8 +52,12 @@ func NewClient(baseURL, apiKey, model string) *Client {
 }

 // WithTimeout sets the HTTP request timeout for LLM calls (default 5 minutes).
+// When using AI Core, this also sets the timeout on the AI Core client.
 func (c *Client) WithTimeout(d time.Duration) *Client {
 	c.http.Timeout = d
+	if c.aicore != nil {
+		c.aicore.WithTimeout(d)
+	}
 	return c
 }

@@ -60,12 +67,21 @@ func (c *Client) WithTemperature(t float64) *Client {
 	return c
 }

-// WithProvider sets the API provider format (openai or anthropic).
+// WithProvider sets the API provider format (openai, anthropic, or aicore).
 func (c *Client) WithProvider(p Provider) *Client {
 	c.provider = p
 	return c
 }

+// WithAICore configures the client to use SAP AI Core for authentication.
+// This sets the provider to aicore automatically.
+// The AI Core client inherits the current HTTP timeout from this client.
+func (c *Client) WithAICore(cfg AICoreConfig) *Client {
+	c.provider = ProviderAICore
+	c.aicore = NewAICoreClient(cfg).WithTimeout(c.http.Timeout)
+	return c
+}
+
 // Message represents a chat message.
 type Message struct {
 	Role    string `json:"role"`
@@ -82,6 +98,8 @@ func (c *Client) Complete(ctx context.Context, messages []Message) (string, erro
 		switch c.provider {
 		case ProviderAnthropic:
 			result, err = c.completeAnthropic(ctx, messages)
+		case ProviderAICore:
+			result, err = c.completeAICore(ctx, messages)
 		default:
 			result, err = c.completeOpenAI(ctx, messages)
 		}
@@ -106,6 +124,18 @@ func (c *Client) Complete(ctx context.Context, messages []Message) (string, erro
 	return "", err
 }

+// completeAICore routes to AI Core using the appropriate endpoint based on model type.
+func (c *Client) completeAICore(ctx context.Context, messages []Message) (string, error) {
+	if c.aicore == nil {
+		return "", fmt.Errorf("AI Core client not configured")
+	}
+
+	if IsAnthropicModel(c.model) {
+		return c.aicore.CompleteAnthropic(ctx, c.model, messages, 8192, c.temperature)
+	}
+	return c.aicore.CompleteOpenAI(ctx, c.model, messages, c.temperature)
+}
+
 // isRetryableError returns true for transient errors worth retrying.
 func isRetryableError(err error) bool {
 	if err == nil {
@@ -176,11 +206,12 @@ func (c *Client) completeOpenAI(ctx context.Context, messages []Message) (string
 // --- Anthropic Messages API implementation ---

 type anthropicRequest struct {
-	Model       string            `json:"model"`
-	MaxTokens   int               `json:"max_tokens"`
-	System      string            `json:"system,omitempty"`
-	Messages    []anthropicMsg    `json:"messages"`
-	Temperature float64           `json:"temperature,omitempty"`
+	AnthropicVersion string         `json:"anthropic_version,omitempty"`
+	Model       string         `json:"model,omitempty"`
+	MaxTokens   int            `json:"max_tokens"`
+	System      string         `json:"system,omitempty"`
+	Messages    []anthropicMsg `json:"messages"`
+	Temperature float64        `json:"temperature,omitempty"`
 }

 type anthropicMsg struct {