fix: propagate LLM timeout to AI Core client

Address review feedback:

MAJOR:
- AICoreClient now defaults to 5min timeout (matching Client)
- Add AICoreClient.WithTimeout() for explicit timeout control
- Client.WithAICore() inherits parent client's timeout
- Client.WithTimeout() propagates to aicore client if set

MINOR:
- Extract AICoreOpenAIAPIVersion constant for the hardcoded api-version
- Tighten IsAnthropicModel to only match 'anthropic--' prefix
  (SAP AI Core always uses this prefix for Anthropic models)

NIT:
- Use fmt.Sprintf for token generation in tests (robust for >9 calls)
- Add error checking in TestAICoreClient_TokenExpiry
- Add tests for WithTimeout propagation

llm/aicore_test.go

@@ -3,6 +3,7 @@ package llm
 import (
 	"context"
 	"encoding/json"
+	"fmt"
 	"net/http"
 	"net/http/httptest"
 	"strings"
@@ -275,8 +276,8 @@ func TestAICoreClient_CompleteOpenAI(t *testing.T) {
 		})
 	})
 	mux.HandleFunc("/deployments/openai/chat/completions", func(w http.ResponseWriter, r *http.Request) {
-		if r.URL.Query().Get("api-version") != "2024-12-01-preview" {
-			t.Errorf("expected api-version query param")
+		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 {
@@ -327,12 +328,17 @@ func TestIsAnthropicModel(t *testing.T) {
 		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},
-		{"claude-sonnet-4", 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 {
@@ -350,7 +356,7 @@ func TestAICoreClient_TokenExpiry(t *testing.T) {
 			call := atomic.AddInt32(&tokenCalls, 1)
 			w.Header().Set("Content-Type", "application/json")
 			json.NewEncoder(w).Encode(map[string]interface{}{
-				"access_token": "token-" + string(rune('0'+call)),
+				"access_token": fmt.Sprintf("token-%d", call),
 				"expires_in":   1, // 1 second expiry
 			})
 			return
@@ -367,7 +373,10 @@ func TestAICoreClient_TokenExpiry(t *testing.T) {
 	})
 
 	// First call
-	token1, _ := client.getToken(context.Background())
+	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()
@@ -375,7 +384,10 @@ func TestAICoreClient_TokenExpiry(t *testing.T) {
 	client.mu.Unlock()
 
 	// Should fetch new token
-	token2, _ := client.getToken(context.Background())
+	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")
@@ -385,6 +397,27 @@ func TestAICoreClient_TokenExpiry(t *testing.T) {
 	}
 }
 
+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 {
@@ -407,6 +440,31 @@ func TestClient_WithAICore(t *testing.T) {
 	}
 }
 
+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()