refactor: merge main and resolve conflicts

enterprise/integrations/github/github_view.py

@@ -97,6 +97,9 @@ class GithubUserContext(UserContext):
         user_secrets = await self.secrets_store.load()
         return dict(user_secrets.custom_secrets) if user_secrets else {}
 
+    async def get_mcp_api_key(self) -> str | None:
+        raise NotImplementedError()
+
 
 async def get_user_proactive_conversation_setting(user_id: str | None) -> bool:
     """Get the user's proactive conversation setting.

enterprise/server/auth/saas_user_auth.py

@@ -203,6 +203,15 @@ class SaasUserAuth(UserAuth):
         self.settings_store = settings_store
         return settings_store
 
+    async def get_mcp_api_key(self) -> str:
+        api_key_store = ApiKeyStore.get_instance()
+        mcp_api_key = api_key_store.retrieve_mcp_api_key(self.user_id)
+        if not mcp_api_key:
+            mcp_api_key = api_key_store.create_api_key(
+                self.user_id, 'MCP_API_KEY', None
+            )
+        return mcp_api_key
+
     @classmethod
     async def get_instance(cls, request: Request) -> UserAuth:
         logger.debug('saas_user_auth_get_instance')
@@ -243,7 +252,12 @@ def get_api_key_from_header(request: Request):
     # This is a temp hack
     # Streamable HTTP MCP Client works via redirect requests, but drops the Authorization header for reason
     # We include `X-Session-API-Key` header by default due to nested runtimes, so it used as a drop in replacement here
-    return request.headers.get('X-Session-API-Key')
+    session_api_key = request.headers.get('X-Session-API-Key')
+    if session_api_key:
+        return session_api_key
+
+    # Fallback to X-Access-Token header as an additional option
+    return request.headers.get('X-Access-Token')
 
 
 async def saas_user_auth_from_bearer(request: Request) -> SaasUserAuth | None:

enterprise/server/routes/auth.py

@@ -31,7 +31,6 @@ from openhands.server.services.conversation_service import create_provider_token
 from openhands.server.shared import config
 from openhands.server.user_auth import get_access_token
 from openhands.server.user_auth.user_auth import get_user_auth
-from openhands.utils.posthog_tracker import track_user_signup_completed
 
 with warnings.catch_warnings():
     warnings.simplefilter('ignore')
@@ -370,12 +369,6 @@ async def accept_tos(request: Request):
 
     logger.info(f'User {user_id} accepted TOS')
 
-    # Track user signup completion in PostHog
-    track_user_signup_completed(
-        user_id=user_id,
-        signup_timestamp=user_settings.accepted_tos.isoformat(),
-    )
-
     response = JSONResponse(
         status_code=status.HTTP_200_OK, content={'redirect_url': redirect_url}
     )

enterprise/server/routes/billing.py

@@ -28,7 +28,6 @@ from storage.subscription_access import SubscriptionAccess
 
 from openhands.server.user_auth import get_user_id
 from openhands.utils.http_session import httpx_verify_option
-from openhands.utils.posthog_tracker import track_credits_purchased
 
 stripe.api_key = STRIPE_API_KEY
 billing_router = APIRouter(prefix='/api/billing')
@@ -458,20 +457,6 @@ async def success_callback(session_id: str, request: Request):
             )
             session.commit()
 
-            # Track credits purchased in PostHog
-            try:
-                track_credits_purchased(
-                    user_id=billing_session.user_id,
-                    amount_usd=amount_subtotal / 100,  # Convert cents to dollars
-                    credits_added=add_credits,
-                    stripe_session_id=session_id,
-                )
-            except Exception as e:
-                logger.warning(
-                    f'Failed to track credits purchase: {e}',
-                    extra={'user_id': billing_session.user_id, 'error': str(e)},
-                )
-
     return RedirectResponse(
         f'{request.base_url}settings/billing?checkout=success', status_code=302
     )

enterprise/tests/unit/test_saas_user_auth.py

@@ -535,3 +535,115 @@ def test_get_api_key_from_header_with_invalid_authorization_format():
 
     # Assert that None was returned
     assert api_key is None
+
+
+def test_get_api_key_from_header_with_x_access_token():
+    """Test that get_api_key_from_header extracts API key from X-Access-Token header."""
+    # Create a mock request with X-Access-Token header
+    mock_request = MagicMock(spec=Request)
+    mock_request.headers = {'X-Access-Token': 'access_token_key'}
+
+    # Call the function
+    api_key = get_api_key_from_header(mock_request)
+
+    # Assert that the API key was correctly extracted
+    assert api_key == 'access_token_key'
+
+
+def test_get_api_key_from_header_priority_authorization_over_x_access_token():
+    """Test that Authorization header takes priority over X-Access-Token header."""
+    # Create a mock request with both headers
+    mock_request = MagicMock(spec=Request)
+    mock_request.headers = {
+        'Authorization': 'Bearer auth_api_key',
+        'X-Access-Token': 'access_token_key',
+    }
+
+    # Call the function
+    api_key = get_api_key_from_header(mock_request)
+
+    # Assert that the API key from Authorization header was used
+    assert api_key == 'auth_api_key'
+
+
+def test_get_api_key_from_header_priority_x_session_over_x_access_token():
+    """Test that X-Session-API-Key header takes priority over X-Access-Token header."""
+    # Create a mock request with both headers
+    mock_request = MagicMock(spec=Request)
+    mock_request.headers = {
+        'X-Session-API-Key': 'session_api_key',
+        'X-Access-Token': 'access_token_key',
+    }
+
+    # Call the function
+    api_key = get_api_key_from_header(mock_request)
+
+    # Assert that the API key from X-Session-API-Key header was used
+    assert api_key == 'session_api_key'
+
+
+def test_get_api_key_from_header_all_three_headers():
+    """Test header priority when all three headers are present."""
+    # Create a mock request with all three headers
+    mock_request = MagicMock(spec=Request)
+    mock_request.headers = {
+        'Authorization': 'Bearer auth_api_key',
+        'X-Session-API-Key': 'session_api_key',
+        'X-Access-Token': 'access_token_key',
+    }
+
+    # Call the function
+    api_key = get_api_key_from_header(mock_request)
+
+    # Assert that the API key from Authorization header was used (highest priority)
+    assert api_key == 'auth_api_key'
+
+
+def test_get_api_key_from_header_invalid_authorization_fallback_to_x_access_token():
+    """Test that invalid Authorization header falls back to X-Access-Token."""
+    # Create a mock request with invalid Authorization header and X-Access-Token
+    mock_request = MagicMock(spec=Request)
+    mock_request.headers = {
+        'Authorization': 'InvalidFormat api_key',
+        'X-Access-Token': 'access_token_key',
+    }
+
+    # Call the function
+    api_key = get_api_key_from_header(mock_request)
+
+    # Assert that the API key from X-Access-Token header was used
+    assert api_key == 'access_token_key'
+
+
+def test_get_api_key_from_header_empty_headers():
+    """Test that empty header values are handled correctly."""
+    # Create a mock request with empty header values
+    mock_request = MagicMock(spec=Request)
+    mock_request.headers = {
+        'Authorization': '',
+        'X-Session-API-Key': '',
+        'X-Access-Token': 'access_token_key',
+    }
+
+    # Call the function
+    api_key = get_api_key_from_header(mock_request)
+
+    # Assert that the API key from X-Access-Token header was used
+    assert api_key == 'access_token_key'
+
+
+def test_get_api_key_from_header_bearer_with_empty_token():
+    """Test that Bearer header with empty token falls back to other headers."""
+    # Create a mock request with Bearer header with empty token
+    mock_request = MagicMock(spec=Request)
+    mock_request.headers = {
+        'Authorization': 'Bearer ',
+        'X-Access-Token': 'access_token_key',
+    }
+
+    # Call the function
+    api_key = get_api_key_from_header(mock_request)
+
+    # Assert that empty string from Bearer is returned (current behavior)
+    # This tests the current implementation behavior
+    assert api_key == ''

frontend/package-lock.json

@@ -39,7 +39,7 @@
         "jose": "^6.1.0",
         "lucide-react": "^0.544.0",
         "monaco-editor": "^0.53.0",
-        "posthog-js": "^1.290.0",
+        "posthog-js": "^1.298.1",
         "react": "^19.1.1",
         "react-dom": "^19.1.1",
         "react-highlight": "^0.15.0",
@@ -3910,9 +3910,9 @@
       "license": "MIT"
     },
     "node_modules/@posthog/core": {
-      "version": "1.5.2",
-      "resolved": "https://registry.npmjs.org/@posthog/core/-/core-1.5.2.tgz",
-      "integrity": "sha512-iedUP3EnOPPxTA2VaIrsrd29lSZnUV+ZrMnvY56timRVeZAXoYCkmjfIs3KBAsF8OUT5h1GXLSkoQdrV0r31OQ==",
+      "version": "1.6.0",
+      "resolved": "https://registry.npmjs.org/@posthog/core/-/core-1.6.0.tgz",
+      "integrity": "sha512-Tbh8UACwbb7jFdDC7wwXHtfNzO+4wKh3VbyMHmp2UBe6w1jliJixexTJNfkqdGZm+ht3M10mcKvGGPnoZ2zLBg==",
       "license": "MIT",
       "dependencies": {
         "cross-spawn": "^7.0.6"
@@ -14711,12 +14711,12 @@
       "license": "MIT"
     },
     "node_modules/posthog-js": {
-      "version": "1.290.0",
-      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.290.0.tgz",
-      "integrity": "sha512-zavBwZkf+3JeiSDVE7ZDXBfzva/iOljicdhdJH+cZoqp0LsxjKxjnNhGOd3KpAhw0wqdwjhd7Lp1aJuI7DXyaw==",
+      "version": "1.298.1",
+      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.298.1.tgz",
+      "integrity": "sha512-MynFhC2HO6sg5moUfpkd0s6RzAqcqFX75kjIi4Xrj2Gl0/YQWYvFUgvv8FCpWPKPs2mdvNWYhs+oqJg0BVVHPw==",
       "license": "SEE LICENSE IN LICENSE",
       "dependencies": {
-        "@posthog/core": "1.5.2",
+        "@posthog/core": "1.6.0",
         "core-js": "^3.38.1",
         "fflate": "^0.4.8",
         "preact": "^10.19.3",

frontend/package.json

@@ -38,7 +38,7 @@
     "jose": "^6.1.0",
     "lucide-react": "^0.544.0",
     "monaco-editor": "^0.53.0",
-    "posthog-js": "^1.290.0",
+    "posthog-js": "^1.298.1",
     "react": "^19.1.1",
     "react-dom": "^19.1.1",
     "react-highlight": "^0.15.0",

frontend/src/api/conversation-service/v1-conversation-service.types.ts

@@ -3,15 +3,19 @@ import { Provider } from "#/types/settings";
 import { V1SandboxStatus } from "../sandbox-service/sandbox-service.types";
 
 // V1 API Types for requests
-// Note: This represents the serialized API format, not the internal TextContent/ImageContent types
-export interface V1MessageContent {
-  type: "text" | "image_url";
-  text?: string;
-  image_url?: {
-    url: string;
-  };
+// These types match the SDK's TextContent and ImageContent formats
+export interface V1TextContent {
+  type: "text";
+  text: string;
 }
 
+export interface V1ImageContent {
+  type: "image";
+  image_urls: string[];
+}
+
+export type V1MessageContent = V1TextContent | V1ImageContent;
+
 type V1Role = "user" | "system" | "assistant" | "tool";
 
 export interface V1SendMessageRequest {

frontend/src/components/features/chat/change-agent-button.tsx

@@ -12,20 +12,15 @@ import { USE_PLANNING_AGENT } from "#/utils/feature-flags";
 import { useAgentState } from "#/hooks/use-agent-state";
 import { AgentState } from "#/types/agent-state";
 import { useActiveConversation } from "#/hooks/query/use-active-conversation";
-import { useCreateConversation } from "#/hooks/mutation/use-create-conversation";
-import { displaySuccessToast } from "#/utils/custom-toast-handlers";
 import { useUnifiedWebSocketStatus } from "#/hooks/use-unified-websocket-status";
 import { useSubConversationTaskPolling } from "#/hooks/query/use-sub-conversation-task-polling";
+import { useHandlePlanClick } from "#/hooks/use-handle-plan-click";
 
 export function ChangeAgentButton() {
   const [contextMenuOpen, setContextMenuOpen] = useState<boolean>(false);
 
-  const {
-    conversationMode,
-    setConversationMode,
-    setSubConversationTaskId,
-    subConversationTaskId,
-  } = useConversationStore();
+  const { conversationMode, setConversationMode, subConversationTaskId } =
+    useConversationStore();
 
   const webSocketStatus = useUnifiedWebSocketStatus();
 
@@ -40,8 +35,6 @@ export function ChangeAgentButton() {
   const isAgentRunning = curAgentState === AgentState.RUNNING;
 
   const { data: conversation } = useActiveConversation();
-  const { mutate: createConversation, isPending: isCreatingConversation } =
-    useCreateConversation();
 
   // Poll sub-conversation task and invalidate parent conversation when ready
   useSubConversationTaskPolling(
@@ -49,6 +42,9 @@ export function ChangeAgentButton() {
     conversation?.conversation_id || null,
   );
 
+  // Get handlePlanClick and isCreatingConversation from custom hook
+  const { handlePlanClick, isCreatingConversation } = useHandlePlanClick();
+
   // Close context menu when agent starts running
   useEffect(() => {
     if ((isAgentRunning || !isWebSocketConnected) && contextMenuOpen) {
@@ -56,45 +52,6 @@ export function ChangeAgentButton() {
     }
   }, [isAgentRunning, contextMenuOpen, isWebSocketConnected]);
 
-  const handlePlanClick = (
-    event: React.MouseEvent<HTMLButtonElement> | KeyboardEvent,
-  ) => {
-    event.preventDefault();
-    event.stopPropagation();
-
-    // Set conversation mode to "plan" immediately
-    setConversationMode("plan");
-
-    // Check if sub_conversation_ids is not empty
-    if (
-      (conversation?.sub_conversation_ids &&
-        conversation.sub_conversation_ids.length > 0) ||
-      !conversation?.conversation_id
-    ) {
-      // Do nothing if both conditions are true
-      return;
-    }
-
-    // Create a new sub-conversation if we have a current conversation ID
-    createConversation(
-      {
-        parentConversationId: conversation.conversation_id,
-        agentType: "plan",
-      },
-      {
-        onSuccess: (data) => {
-          displaySuccessToast(
-            t(I18nKey.PLANNING_AGENTT$PLANNING_AGENT_INITIALIZED),
-          );
-          // Track the task ID to poll for sub-conversation creation
-          if (data.v1_task_id) {
-            setSubConversationTaskId(data.v1_task_id);
-          }
-        },
-      },
-    );
-  };
-
   const isButtonDisabled =
     isAgentRunning ||
     isCreatingConversation ||

frontend/src/components/features/chat/chat-message.tsx

@@ -1,15 +1,9 @@
 import React from "react";
-import Markdown from "react-markdown";
-import remarkGfm from "remark-gfm";
-import remarkBreaks from "remark-breaks";
-import { code } from "../markdown/code";
 import { cn } from "#/utils/utils";
-import { ul, ol } from "../markdown/list";
 import { CopyToClipboardButton } from "#/components/shared/buttons/copy-to-clipboard-button";
-import { anchor } from "../markdown/anchor";
 import { OpenHandsSourceType } from "#/types/core/base";
-import { paragraph } from "../markdown/paragraph";
 import { TooltipButton } from "#/components/shared/buttons/tooltip-button";
+import { MarkdownRenderer } from "../markdown/markdown-renderer";
 
 interface ChatMessageProps {
   type: OpenHandsSourceType;
@@ -116,18 +110,7 @@ export function ChatMessage({
           wordBreak: "break-word",
         }}
       >
-        <Markdown
-          components={{
-            code,
-            ul,
-            ol,
-            a: anchor,
-            p: paragraph,
-          }}
-          remarkPlugins={[remarkGfm, remarkBreaks]}
-        >
-          {message}
-        </Markdown>
+        <MarkdownRenderer includeStandard>{message}</MarkdownRenderer>
       </div>
       {children}
     </article>

frontend/src/components/features/chat/error-message.tsx

@@ -1,13 +1,9 @@
 import React from "react";
-import Markdown from "react-markdown";
-import remarkGfm from "remark-gfm";
-import remarkBreaks from "remark-breaks";
 import { useTranslation } from "react-i18next";
-import { code } from "../markdown/code";
-import { ol, ul } from "../markdown/list";
 import ArrowDown from "#/icons/angle-down-solid.svg?react";
 import ArrowUp from "#/icons/angle-up-solid.svg?react";
 import i18n from "#/i18n";
+import { MarkdownRenderer } from "../markdown/markdown-renderer";
 
 interface ErrorMessageProps {
   errorId?: string;
@@ -40,18 +36,7 @@ export function ErrorMessage({ errorId, defaultMessage }: ErrorMessageProps) {
         </button>
       </div>
 
-      {showDetails && (
-        <Markdown
-          components={{
-            code,
-            ul,
-            ol,
-          }}
-          remarkPlugins={[remarkGfm, remarkBreaks]}
-        >
-          {defaultMessage}
-        </Markdown>
-      )}
+      {showDetails && <MarkdownRenderer>{defaultMessage}</MarkdownRenderer>}
     </div>
   );
 }

frontend/src/components/features/chat/expandable-message.tsx

@@ -1,9 +1,6 @@
 import { useEffect, useState } from "react";
 import { Trans, useTranslation } from "react-i18next";
-import Markdown from "react-markdown";
 import { Link } from "react-router";
-import remarkGfm from "remark-gfm";
-import remarkBreaks from "remark-breaks";
 import { useConfig } from "#/hooks/query/use-config";
 import { I18nKey } from "#/i18n/declaration";
 import ArrowDown from "#/icons/angle-down-solid.svg?react";
@@ -13,9 +10,7 @@ import XCircle from "#/icons/x-circle-solid.svg?react";
 import { OpenHandsAction } from "#/types/core/actions";
 import { OpenHandsObservation } from "#/types/core/observations";
 import { cn } from "#/utils/utils";
-import { code } from "../markdown/code";
-import { ol, ul } from "../markdown/list";
-import { paragraph } from "../markdown/paragraph";
+import { MarkdownRenderer } from "../markdown/markdown-renderer";
 import { MonoComponent } from "./mono-component";
 import { PathComponent } from "./path-component";
 
@@ -192,17 +187,7 @@ export function ExpandableMessage({
         </div>
         {showDetails && (
           <div className="text-sm">
-            <Markdown
-              components={{
-                code,
-                ul,
-                ol,
-                p: paragraph,
-              }}
-              remarkPlugins={[remarkGfm, remarkBreaks]}
-            >
-              {details}
-            </Markdown>
+            <MarkdownRenderer includeStandard>{details}</MarkdownRenderer>
           </div>
         )}
       </div>

frontend/src/components/features/chat/generic-event-message.tsx

@@ -1,13 +1,9 @@
 import React from "react";
-import Markdown from "react-markdown";
-import remarkGfm from "remark-gfm";
-import remarkBreaks from "remark-breaks";
-import { code } from "../markdown/code";
-import { ol, ul } from "../markdown/list";
 import ArrowDown from "#/icons/angle-down-solid.svg?react";
 import ArrowUp from "#/icons/angle-up-solid.svg?react";
 import { SuccessIndicator } from "./success-indicator";
 import { ObservationResultStatus } from "./event-content-helpers/get-observation-result";
+import { MarkdownRenderer } from "../markdown/markdown-renderer";
 
 interface GenericEventMessageProps {
   title: React.ReactNode;
@@ -49,16 +45,7 @@ export function GenericEventMessage({
 
       {showDetails &&
         (typeof details === "string" ? (
-          <Markdown
-            components={{
-              code,
-              ul,
-              ol,
-            }}
-            remarkPlugins={[remarkGfm, remarkBreaks]}
-          >
-            {details}
-          </Markdown>
+          <MarkdownRenderer>{details}</MarkdownRenderer>
         ) : (
           details
         ))}

frontend/src/components/features/conversation-panel/conversation-card/conversation-card-footer.tsx

@@ -39,7 +39,7 @@ export function ConversationCardFooter({
       {(createdAt ?? lastUpdatedAt) && (
         <p className="text-xs text-[#A3A3A3] flex-1 text-right">
           <time>
-            {`${formatTimeDelta(new Date(lastUpdatedAt ?? createdAt))} ${t(I18nKey.CONVERSATION$AGO)}`}
+            {`${formatTimeDelta(lastUpdatedAt ?? createdAt)} ${t(I18nKey.CONVERSATION$AGO)}`}
           </time>
         </p>
       )}

frontend/src/components/features/conversation-panel/start-task-card/start-task-card-footer.tsx

@@ -31,7 +31,7 @@ export function StartTaskCardFooter({
         {createdAt && (
           <p className="text-xs text-[#A3A3A3] flex-1 text-right">
             <time>
-              {`${formatTimeDelta(new Date(createdAt))} ${t(I18nKey.CONVERSATION$AGO)}`}
+              {`${formatTimeDelta(createdAt)} ${t(I18nKey.CONVERSATION$AGO)}`}
             </time>
           </p>
         )}

frontend/src/components/features/home/recent-conversations/recent-conversation.tsx

@@ -67,12 +67,14 @@ export function RecentConversation({ conversation }: RecentConversationProps) {
               </div>
             ) : null}
           </div>
-          <span>
-            {formatTimeDelta(
-              new Date(conversation.created_at || conversation.last_updated_at),
-            )}{" "}
-            {t(I18nKey.CONVERSATION$AGO)}
-          </span>
+          {(conversation.created_at || conversation.last_updated_at) && (
+            <span>
+              {formatTimeDelta(
+                conversation.created_at || conversation.last_updated_at,
+              )}{" "}
+              {t(I18nKey.CONVERSATION$AGO)}
+            </span>
+          )}
         </div>
       </button>
     </Link>

frontend/src/components/features/markdown/markdown-renderer.tsx

@@ -0,0 +1,80 @@
+import Markdown, { Components } from "react-markdown";
+import remarkGfm from "remark-gfm";
+import remarkBreaks from "remark-breaks";
+import { code } from "./code";
+import { ul, ol } from "./list";
+import { paragraph } from "./paragraph";
+import { anchor } from "./anchor";
+import { h1, h2, h3, h4, h5, h6 } from "./headings";
+
+interface MarkdownRendererProps {
+  /**
+   * The markdown content to render. Can be passed as children (string) or content prop.
+   */
+  children?: string;
+  content?: string;
+  /**
+   * Additional or override components for markdown elements.
+   * Default components (code, ul, ol) are always included unless overridden.
+   */
+  components?: Partial<Components>;
+  /**
+   * Whether to include standard components (anchor, paragraph).
+   * Defaults to false.
+   */
+  includeStandard?: boolean;
+  /**
+   * Whether to include heading components (h1-h6).
+   * Defaults to false.
+   */
+  includeHeadings?: boolean;
+}
+
+/**
+ * A reusable Markdown renderer component that provides consistent
+ * markdown rendering across the application.
+ *
+ * By default, includes:
+ * - code, ul, ol components
+ * - remarkGfm and remarkBreaks plugins
+ *
+ * Can be extended with:
+ * - includeStandard: adds anchor and paragraph components
+ * - includeHeadings: adds h1-h6 heading components
+ * - components prop: allows custom overrides or additional components
+ */
+export function MarkdownRenderer({
+  children,
+  content,
+  components: customComponents,
+  includeStandard = false,
+  includeHeadings = false,
+}: MarkdownRendererProps) {
+  // Build the components object with defaults and optional additions
+  const components: Components = {
+    code,
+    ul,
+    ol,
+    ...(includeStandard && {
+      a: anchor,
+      p: paragraph,
+    }),
+    ...(includeHeadings && {
+      h1,
+      h2,
+      h3,
+      h4,
+      h5,
+      h6,
+    }),
+    ...customComponents, // Custom components override defaults
+  };
+
+  const markdownContent = content ?? children ?? "";
+
+  return (
+    <Markdown components={components} remarkPlugins={[remarkGfm, remarkBreaks]}>
+      {markdownContent}
+    </Markdown>
+  );
+}

frontend/src/components/features/microagent-management/microagent-management-view-microagent-content.tsx

@@ -1,16 +1,10 @@
 import { useTranslation } from "react-i18next";
 import { Spinner } from "@heroui/react";
-import Markdown from "react-markdown";
-import remarkGfm from "remark-gfm";
-import remarkBreaks from "remark-breaks";
-import { code } from "../markdown/code";
-import { ul, ol } from "../markdown/list";
-import { paragraph } from "../markdown/paragraph";
-import { anchor } from "../markdown/anchor";
 import { useMicroagentManagementStore } from "#/state/microagent-management-store";
 import { useRepositoryMicroagentContent } from "#/hooks/query/use-repository-microagent-content";
 import { I18nKey } from "#/i18n/declaration";
 import { extractRepositoryInfo } from "#/utils/utils";
+import { MarkdownRenderer } from "../markdown/markdown-renderer";
 
 export function MicroagentManagementViewMicroagentContent() {
   const { t } = useTranslation();
@@ -49,18 +43,9 @@ export function MicroagentManagementViewMicroagentContent() {
         </div>
       )}
       {microagentData && !isLoading && !error && (
-        <Markdown
-          components={{
-            code,
-            ul,
-            ol,
-            a: anchor,
-            p: paragraph,
-          }}
-          remarkPlugins={[remarkGfm, remarkBreaks]}
-        >
+        <MarkdownRenderer includeStandard>
           {microagentData.content}
-        </Markdown>
+        </MarkdownRenderer>
       )}
     </div>
   );

frontend/src/components/v1/chat/event-content-helpers/get-observation-content.ts

@@ -184,7 +184,22 @@ const getFinishObservationContent = (
   event: ObservationEvent<FinishObservation>,
 ): string => {
   const { observation } = event;
-  return observation.message || "";
+
+  // Extract text content from the observation
+  const textContent = observation.content
+    .filter((c) => c.type === "text")
+    .map((c) => c.text)
+    .join("\n");
+
+  let content = "";
+
+  if (observation.is_error) {
+    content += `**Error:**\n${textContent}`;
+  } else {
+    content += textContent;
+  }
+
+  return content;
 };
 
 export const getObservationContent = (event: ObservationEvent): string => {

frontend/src/components/v1/chat/event-message-components/generic-event-message-wrapper.tsx

@@ -9,6 +9,7 @@ import {
 } from "../event-content-helpers/create-skill-ready-event";
 import { V1ConfirmationButtons } from "#/components/shared/buttons/v1-confirmation-buttons";
 import { ObservationResultStatus } from "../../../features/chat/event-content-helpers/get-observation-result";
+import { MarkdownRenderer } from "#/components/features/markdown/markdown-renderer";
 
 interface GenericEventMessageWrapperProps {
   event: OpenHandsEvent | SkillReadyEvent;
@@ -23,11 +24,17 @@ export function GenericEventMessageWrapper({
 
   // SkillReadyEvent is not an observation event, so skip the observation checks
   if (!isSkillReadyEvent(event)) {
-    if (
-      isObservationEvent(event) &&
-      event.observation.kind === "TaskTrackerObservation"
-    ) {
-      return <div>{details}</div>;
+    if (isObservationEvent(event)) {
+      if (event.observation.kind === "TaskTrackerObservation") {
+        return <div>{details}</div>;
+      }
+      if (event.observation.kind === "FinishObservation") {
+        return (
+          <MarkdownRenderer includeStandard includeHeadings>
+            {details as string}
+          </MarkdownRenderer>
+        );
+      }
     }
   }
 

frontend/src/contexts/conversation-websocket-context.tsx

@@ -505,7 +505,6 @@ export function ConversationWebSocketProvider({
                   },
                   {
                     onSuccess: (fileContent) => {
-                      console.log("File content:", fileContent);
                       setPlanContent(fileContent);
                     },
                     onError: (error) => {

frontend/src/hooks/use-handle-plan-click.ts

@@ -0,0 +1,71 @@
+import { useCallback } from "react";
+import { useTranslation } from "react-i18next";
+import { I18nKey } from "#/i18n/declaration";
+import { useConversationStore } from "#/state/conversation-store";
+import { useActiveConversation } from "#/hooks/query/use-active-conversation";
+import { useCreateConversation } from "#/hooks/mutation/use-create-conversation";
+import { displaySuccessToast } from "#/utils/custom-toast-handlers";
+
+/**
+ * Custom hook that encapsulates the logic for handling plan creation.
+ * Returns a function that can be called to create a plan conversation and
+ * the pending state of the conversation creation.
+ *
+ * @returns An object containing handlePlanClick function and isCreatingConversation boolean
+ */
+export const useHandlePlanClick = () => {
+  const { t } = useTranslation();
+  const { setConversationMode, setSubConversationTaskId } =
+    useConversationStore();
+  const { data: conversation } = useActiveConversation();
+  const { mutate: createConversation, isPending: isCreatingConversation } =
+    useCreateConversation();
+
+  const handlePlanClick = useCallback(
+    (event?: React.MouseEvent<HTMLButtonElement> | KeyboardEvent) => {
+      event?.preventDefault();
+      event?.stopPropagation();
+
+      // Set conversation mode to "plan" immediately
+      setConversationMode("plan");
+
+      // Check if sub_conversation_ids is not empty
+      if (
+        (conversation?.sub_conversation_ids &&
+          conversation.sub_conversation_ids.length > 0) ||
+        !conversation?.conversation_id
+      ) {
+        // Do nothing if both conditions are true
+        return;
+      }
+
+      // Create a new sub-conversation if we have a current conversation ID
+      createConversation(
+        {
+          parentConversationId: conversation.conversation_id,
+          agentType: "plan",
+        },
+        {
+          onSuccess: (data) => {
+            displaySuccessToast(
+              t(I18nKey.PLANNING_AGENTT$PLANNING_AGENT_INITIALIZED),
+            );
+            // Track the task ID to poll for sub-conversation creation
+            if (data.v1_task_id) {
+              setSubConversationTaskId(data.v1_task_id);
+            }
+          },
+        },
+      );
+    },
+    [
+      conversation,
+      createConversation,
+      setConversationMode,
+      setSubConversationTaskId,
+      t,
+    ],
+  );
+
+  return { handlePlanClick, isCreatingConversation };
+};

frontend/src/hooks/use-send-message.ts

@@ -41,13 +41,11 @@ export function useSendMessage() {
             },
           ];
 
-          // Add images if present
+          // Add images if present - using SDK's ImageContent format
           if (args.image_urls && args.image_urls.length > 0) {
-            args.image_urls.forEach((url) => {
-              content.push({
-                type: "image_url",
-                image_url: { url },
-              });
+            content.push({
+              type: "image",
+              image_urls: args.image_urls,
             });
           }
 

frontend/src/routes/billing.tsx

@@ -30,11 +30,12 @@ function BillingSettingsScreen() {
       }
 
       displaySuccessToast(t(I18nKey.PAYMENT$SUCCESS));
+
+      setSearchParams({});
     } else if (checkoutStatus === "cancel") {
       displayErrorToast(t(I18nKey.PAYMENT$CANCELLED));
+      setSearchParams({});
     }
-
-    setSearchParams({});
   }, [checkoutStatus, searchParams, setSearchParams, t, trackCreditsPurchased]);
 
   return <PaymentForm />;

frontend/src/routes/llm-settings.tsx

@@ -28,6 +28,7 @@ import { KeyStatusIcon } from "#/components/features/settings/key-status-icon";
 import { DEFAULT_SETTINGS } from "#/services/settings";
 import { getProviderId } from "#/utils/map-provider";
 import { DEFAULT_OPENHANDS_MODEL } from "#/utils/verified-models";
+import { USE_V1_CONVERSATION_API } from "#/utils/feature-flags";
 
 interface OpenHandsApiKeyHelpProps {
   testId: string;
@@ -118,6 +119,9 @@ function LlmSettingsScreen() {
   const isSaasMode = config?.APP_MODE === "saas";
   const shouldUseOpenHandsKey = isOpenHandsProvider && isSaasMode;
 
+  // Determine if we should hide the agent dropdown when V1 conversation API feature flag is enabled
+  const isV1Enabled = USE_V1_CONVERSATION_API();
+
   React.useEffect(() => {
     const determineWhetherToToggleAdvancedSettings = () => {
       if (resources && settings) {
@@ -612,21 +616,23 @@ function LlmSettingsScreen() {
                     href="https://tavily.com/"
                   />
 
-                  <SettingsDropdownInput
-                    testId="agent-input"
-                    name="agent-input"
-                    label={t(I18nKey.SETTINGS$AGENT)}
-                    items={
-                      resources?.agents.map((agent) => ({
-                        key: agent,
-                        label: agent, // TODO: Add i18n support for agent names
-                      })) || []
-                    }
-                    defaultSelectedKey={settings.AGENT}
-                    isClearable={false}
-                    onInputChange={handleAgentIsDirty}
-                    wrapperClassName="w-full max-w-[680px]"
-                  />
+                  {!isV1Enabled && (
+                    <SettingsDropdownInput
+                      testId="agent-input"
+                      name="agent-input"
+                      label={t(I18nKey.SETTINGS$AGENT)}
+                      items={
+                        resources?.agents.map((agent) => ({
+                          key: agent,
+                          label: agent, // TODO: Add i18n support for agent names
+                        })) || []
+                      }
+                      defaultSelectedKey={settings.AGENT}
+                      isClearable={false}
+                      onInputChange={handleAgentIsDirty}
+                      wrapperClassName="w-full max-w-[680px]"
+                    />
+                  )}
                 </>
               )}
 

frontend/src/routes/planner-tab.tsx

@@ -1,24 +1,11 @@
 import React from "react";
 import { useTranslation } from "react-i18next";
-import Markdown from "react-markdown";
-import remarkGfm from "remark-gfm";
-import remarkBreaks from "remark-breaks";
 import { I18nKey } from "#/i18n/declaration";
 import LessonPlanIcon from "#/icons/lesson-plan.svg?react";
 import { useConversationStore } from "#/state/conversation-store";
-import { code } from "#/components/features/markdown/code";
-import { ul, ol } from "#/components/features/markdown/list";
-import { paragraph } from "#/components/features/markdown/paragraph";
-import { anchor } from "#/components/features/markdown/anchor";
-import {
-  h1,
-  h2,
-  h3,
-  h4,
-  h5,
-  h6,
-} from "#/components/features/markdown/headings";
 import { useScrollToBottom } from "#/hooks/use-scroll-to-bottom";
+import { MarkdownRenderer } from "#/components/features/markdown/markdown-renderer";
+import { useHandlePlanClick } from "#/hooks/use-handle-plan-click";
 
 function PlannerTab() {
   const { t } = useTranslation();
@@ -26,7 +13,8 @@ function PlannerTab() {
     React.useRef<HTMLDivElement>(null),
   );
 
-  const { planContent, setConversationMode } = useConversationStore();
+  const { planContent } = useConversationStore();
+  const { handlePlanClick } = useHandlePlanClick();
 
   if (planContent !== null && planContent !== undefined) {
     return (
@@ -35,24 +23,9 @@ function PlannerTab() {
         onScroll={(e) => onChatBodyScroll(e.currentTarget)}
         className="flex flex-col w-full h-full p-4 overflow-auto"
       >
-        <Markdown
-          components={{
-            code,
-            ul,
-            ol,
-            a: anchor,
-            p: paragraph,
-            h1,
-            h2,
-            h3,
-            h4,
-            h5,
-            h6,
-          }}
-          remarkPlugins={[remarkGfm, remarkBreaks]}
-        >
+        <MarkdownRenderer includeStandard includeHeadings>
           {planContent}
-        </Markdown>
+        </MarkdownRenderer>
       </div>
     );
   }
@@ -65,7 +38,7 @@ function PlannerTab() {
       </span>
       <button
         type="button"
-        onClick={() => setConversationMode("plan")}
+        onClick={handlePlanClick}
         className="flex w-[164px] h-[40px] p-2 justify-center items-center shrink-0 rounded-lg bg-white overflow-hidden text-black text-ellipsis font-sans text-[16px] not-italic font-normal leading-[20px] hover:cursor-pointer hover:opacity-80"
       >
         {t(I18nKey.COMMON$CREATE_A_PLAN)}

frontend/src/types/v1/core/base/observation.ts

@@ -25,9 +25,13 @@ export interface MCPToolObservation
 export interface FinishObservation
   extends ObservationBase<"FinishObservation"> {
   /**
-   * Final message sent to the user
+   * Content returned from the finish action as a list of TextContent/ImageContent objects.
    */
-  message: string;
+  content: Array<TextContent | ImageContent>;
+  /**
+   * Whether the finish action resulted in an error
+   */
+  is_error: boolean;
 }
 
 export interface ThinkObservation extends ObservationBase<"ThinkObservation"> {

frontend/src/utils/format-time-delta.ts

@@ -1,16 +1,45 @@
+/**
+ * Parses a date string as UTC if it doesn't have a timezone indicator.
+ * This fixes the issue where ISO strings without timezone info are interpreted as local time.
+ * @param dateString ISO 8601 date string
+ * @returns Date object parsed as UTC
+ *
+ * @example
+ * parseDateAsUTC("2025-12-01T11:53:37.273886"); // Parsed as UTC
+ * parseDateAsUTC("2025-12-01T11:53:37.273886Z"); // Already has timezone, parsed correctly
+ * parseDateAsUTC("2025-12-01T11:53:37+00:00"); // Already has timezone, parsed correctly
+ */
+const parseDateAsUTC = (dateString: string): Date => {
+  // Check if the string already has a timezone indicator
+  // Look for 'Z' (UTC), '+' (positive offset), or '-' after the time part (negative offset)
+  const hasTimezone =
+    dateString.includes("Z") || dateString.match(/[+-]\d{2}:\d{2}$/) !== null;
+
+  if (hasTimezone) {
+    // Already has timezone info, parse normally
+    return new Date(dateString);
+  }
+
+  // No timezone indicator - append 'Z' to force UTC parsing
+  return new Date(`${dateString}Z`);
+};
+
 /**
  * Formats a date into a compact string representing the time delta between the given date and the current date.
- * @param date The date to format
+ * @param date The date to format (Date object or ISO 8601 string)
  * @returns A compact string representing the time delta between the given date and the current date
  *
  * @example
  * // now is 2024-01-01T00:00:00Z
  * formatTimeDelta(new Date("2023-12-31T23:59:59Z")); // "1s"
- * formatTimeDelta(new Date("2022-01-01T00:00:00Z")); // "2y"
+ * formatTimeDelta("2023-12-31T23:59:59Z"); // "1s"
+ * formatTimeDelta("2025-12-01T11:53:37.273886"); // Parsed as UTC automatically
  */
-export const formatTimeDelta = (date: Date) => {
+export const formatTimeDelta = (date: Date | string) => {
+  // Parse string dates as UTC if needed, or use Date object directly
+  const dateObj = typeof date === "string" ? parseDateAsUTC(date) : date;
   const now = new Date();
-  const delta = now.getTime() - date.getTime();
+  const delta = now.getTime() - dateObj.getTime();
 
   const seconds = Math.floor(delta / 1000);
   const minutes = Math.floor(seconds / 60);

frontend/src/utils/verified-models.ts

@@ -59,6 +59,7 @@ export const VERIFIED_ANTHROPIC_MODELS = [
   "claude-haiku-4-5-20251001",
   "claude-opus-4-20250514",
   "claude-opus-4-1-20250805",
+  "claude-opus-4-5-20251101",
 ];
 
 // LiteLLM does not return the compatible Mistral models with the provider, so we list them here to set them ourselves

openhands/app_server/app_conversation/app_conversation_info_service.py

@@ -9,6 +9,7 @@ from openhands.app_server.app_conversation.app_conversation_models import (
     AppConversationSortOrder,
 )
 from openhands.app_server.services.injector import Injector
+from openhands.sdk.event import ConversationStateUpdateEvent
 from openhands.sdk.utils.models import DiscriminatedUnionMixin
 
 
@@ -92,6 +93,19 @@ class AppConversationInfoService(ABC):
         Return the stored info
         """
 
+    @abstractmethod
+    async def process_stats_event(
+        self,
+        event: ConversationStateUpdateEvent,
+        conversation_id: UUID,
+    ) -> None:
+        """Process a stats event and update conversation statistics.
+
+        Args:
+            event: The ConversationStateUpdateEvent with key='stats'
+            conversation_id: The ID of the conversation to update
+        """
+
 
 class AppConversationInfoServiceInjector(
     DiscriminatedUnionMixin, Injector[AppConversationInfoService], ABC

openhands/app_server/app_conversation/app_conversation_service_base.py

@@ -9,6 +9,7 @@ from typing import AsyncGenerator
 import base62
 
 from openhands.app_server.app_conversation.app_conversation_models import (
+    AgentType,
     AppConversationStartTask,
     AppConversationStartTaskStatus,
 )
@@ -25,7 +26,9 @@ from openhands.app_server.sandbox.sandbox_models import SandboxInfo
 from openhands.app_server.user.user_context import UserContext
 from openhands.sdk import Agent
 from openhands.sdk.context.agent_context import AgentContext
+from openhands.sdk.context.condenser import LLMSummarizingCondenser
 from openhands.sdk.context.skills import load_user_skills
+from openhands.sdk.llm import LLM
 from openhands.sdk.workspace.remote.async_remote_workspace import AsyncRemoteWorkspace
 
 _logger = logging.getLogger(__name__)
@@ -182,6 +185,43 @@ class AppConversationServiceBase(AppConversationService, ABC):
             workspace.working_dir,
         )
 
+    async def _configure_git_user_settings(
+        self,
+        workspace: AsyncRemoteWorkspace,
+    ) -> None:
+        """Configure git global user settings from user preferences.
+
+        Reads git_user_name and git_user_email from user settings and
+        configures them as git global settings in the workspace.
+
+        Args:
+            workspace: The remote workspace to configure git settings in.
+        """
+        try:
+            user_info = await self.user_context.get_user_info()
+
+            if user_info.git_user_name:
+                cmd = f'git config --global user.name "{user_info.git_user_name}"'
+                result = await workspace.execute_command(cmd, workspace.working_dir)
+                if result.exit_code:
+                    _logger.warning(f'Git config user.name failed: {result.stderr}')
+                else:
+                    _logger.info(
+                        f'Git configured with user.name={user_info.git_user_name}'
+                    )
+
+            if user_info.git_user_email:
+                cmd = f'git config --global user.email "{user_info.git_user_email}"'
+                result = await workspace.execute_command(cmd, workspace.working_dir)
+                if result.exit_code:
+                    _logger.warning(f'Git config user.email failed: {result.stderr}')
+                else:
+                    _logger.info(
+                        f'Git configured with user.email={user_info.git_user_email}'
+                    )
+        except Exception as e:
+            _logger.warning(f'Failed to configure git user settings: {e}')
+
     async def clone_or_init_git_repo(
         self,
         task: AppConversationStartTask,
@@ -197,6 +237,9 @@ class AppConversationServiceBase(AppConversationService, ABC):
         if result.exit_code:
             _logger.warning(f'mkdir failed: {result.stderr}')
 
+        # Configure git user settings from user preferences
+        await self._configure_git_user_settings(workspace)
+
         if not request.selected_repository:
             if self.init_git_in_empty_workspace:
                 _logger.debug('Initializing a new git repository in the workspace.')
@@ -221,7 +264,9 @@ class AppConversationServiceBase(AppConversationService, ABC):
 
         # Clone the repo - this is the slow part!
         clone_command = f'git clone {remote_repo_url} {dir_name}'
-        result = await workspace.execute_command(clone_command, workspace.working_dir)
+        result = await workspace.execute_command(
+            clone_command, workspace.working_dir, 120
+        )
         if result.exit_code:
             _logger.warning(f'Git clone failed: {result.stderr}')
 
@@ -233,7 +278,10 @@ class AppConversationServiceBase(AppConversationService, ABC):
             random_str = base62.encodebytes(os.urandom(16))
             openhands_workspace_branch = f'openhands-workspace-{random_str}'
             checkout_command = f'git checkout -b {openhands_workspace_branch}'
-        await workspace.execute_command(checkout_command, workspace.working_dir)
+        git_dir = Path(workspace.working_dir) / dir_name
+        result = await workspace.execute_command(checkout_command, git_dir)
+        if result.exit_code:
+            _logger.warning(f'Git checkout failed: {result.stderr}')
 
     async def maybe_run_setup_script(
         self,
@@ -295,3 +343,39 @@ class AppConversationServiceBase(AppConversationService, ABC):
             return
 
         _logger.info('Git pre-commit hook installed successfully')
+
+    def _create_condenser(
+        self,
+        llm: LLM,
+        agent_type: AgentType,
+        condenser_max_size: int | None,
+    ) -> LLMSummarizingCondenser:
+        """Create a condenser based on user settings and agent type.
+
+        Args:
+            llm: The LLM instance to use for condensation
+            agent_type: Type of agent (PLAN or DEFAULT)
+            condenser_max_size: condenser_max_size setting
+
+        Returns:
+            Configured LLMSummarizingCondenser instance
+        """
+        # LLMSummarizingCondenser has defaults: max_size=120, keep_first=4
+        condenser_kwargs = {
+            'llm': llm.model_copy(
+                update={
+                    'usage_id': (
+                        'condenser'
+                        if agent_type == AgentType.DEFAULT
+                        else 'planning_condenser'
+                    )
+                }
+            ),
+        }
+        # Only override max_size if user has a custom value
+        if condenser_max_size is not None:
+            condenser_kwargs['max_size'] = condenser_max_size
+
+        condenser = LLMSummarizingCondenser(**condenser_kwargs)
+
+        return condenser

openhands/app_server/app_conversation/live_status_app_conversation_service.py

@@ -4,12 +4,12 @@ from collections import defaultdict
 from dataclasses import dataclass
 from datetime import datetime, timedelta
 from time import time
-from typing import AsyncGenerator, Sequence
+from typing import Any, AsyncGenerator, Sequence
 from uuid import UUID, uuid4
 
 import httpx
 from fastapi import Request
-from pydantic import Field, TypeAdapter
+from pydantic import Field, SecretStr, TypeAdapter
 
 from openhands.agent_server.models import (
     ConversationInfo,
@@ -63,19 +63,25 @@ from openhands.app_server.sandbox.sandbox_spec_service import SandboxSpecService
 from openhands.app_server.services.injector import InjectorState
 from openhands.app_server.services.jwt_service import JwtService
 from openhands.app_server.user.user_context import UserContext
+from openhands.app_server.user.user_models import UserInfo
 from openhands.app_server.utils.docker_utils import (
     replace_localhost_hostname_for_docker,
 )
 from openhands.experiments.experiment_manager import ExperimentManagerImpl
 from openhands.integrations.provider import ProviderType
-from openhands.sdk import AgentContext, LocalWorkspace
+from openhands.sdk import Agent, AgentContext, LocalWorkspace
 from openhands.sdk.conversation.secret_source import LookupSecret, StaticSecret
 from openhands.sdk.llm import LLM
 from openhands.sdk.security.confirmation_policy import AlwaysConfirm
 from openhands.sdk.workspace.remote.async_remote_workspace import AsyncRemoteWorkspace
 from openhands.server.types import AppMode
-from openhands.tools.preset.default import get_default_agent
-from openhands.tools.preset.planning import get_planning_agent
+from openhands.tools.preset.default import (
+    get_default_tools,
+)
+from openhands.tools.preset.planning import (
+    format_plan_structure,
+    get_planning_tools,
+)
 
 _conversation_info_type_adapter = TypeAdapter(list[ConversationInfo | None])
 _logger = logging.getLogger(__name__)
@@ -99,6 +105,7 @@ class LiveStatusAppConversationService(AppConversationServiceBase):
     access_token_hard_timeout: timedelta | None
     app_mode: str | None = None
     keycloak_auth_cookie: str | None = None
+    tavily_api_key: str | None = None
 
     async def search_app_conversations(
         self,
@@ -519,6 +526,224 @@ class LiveStatusAppConversationService(AppConversationServiceBase):
         if not request.llm_model and parent_info.llm_model:
             request.llm_model = parent_info.llm_model
 
+    async def _setup_secrets_for_git_provider(
+        self, git_provider: ProviderType | None, user: UserInfo
+    ) -> dict:
+        """Set up secrets for git provider authentication.
+
+        Args:
+            git_provider: The git provider type (GitHub, GitLab, etc.)
+            user: User information containing authentication details
+
+        Returns:
+            Dictionary of secrets for the conversation
+        """
+        secrets = await self.user_context.get_secrets()
+
+        if not git_provider:
+            return secrets
+
+        secret_name = f'{git_provider.name}_TOKEN'
+
+        if self.web_url:
+            # Create an access token for web-based authentication
+            access_token = self.jwt_service.create_jws_token(
+                payload={
+                    'user_id': user.id,
+                    'provider_type': git_provider.value,
+                },
+                expires_in=self.access_token_hard_timeout,
+            )
+            headers = {'X-Access-Token': access_token}
+
+            # Include keycloak_auth cookie in headers if app_mode is SaaS
+            if self.app_mode == 'saas' and self.keycloak_auth_cookie:
+                headers['Cookie'] = f'keycloak_auth={self.keycloak_auth_cookie}'
+
+            secrets[secret_name] = LookupSecret(
+                url=self.web_url + '/api/v1/webhooks/secrets',
+                headers=headers,
+            )
+        else:
+            # Use static token for environments without web URL access
+            static_token = await self.user_context.get_latest_token(git_provider)
+            if static_token:
+                secrets[secret_name] = StaticSecret(value=static_token)
+
+        return secrets
+
+    async def _configure_llm_and_mcp(
+        self, user: UserInfo, llm_model: str | None
+    ) -> tuple[LLM, dict]:
+        """Configure LLM and MCP (Model Context Protocol) settings.
+
+        Args:
+            user: User information containing LLM preferences
+            llm_model: Optional specific model to use, falls back to user default
+
+        Returns:
+            Tuple of (configured LLM instance, MCP config dictionary)
+        """
+        # Configure LLM
+        model = llm_model or user.llm_model
+        llm = LLM(
+            model=model,
+            base_url=user.llm_base_url,
+            api_key=user.llm_api_key,
+            usage_id='agent',
+        )
+
+        # Configure MCP
+        mcp_config: dict[str, Any] = {}
+        if self.web_url:
+            mcp_url = f'{self.web_url}/mcp/mcp'
+            mcp_config = {
+                'default': {
+                    'url': mcp_url,
+                }
+            }
+
+            # Add API key if available
+            mcp_api_key = await self.user_context.get_mcp_api_key()
+            if mcp_api_key:
+                mcp_config['default']['headers'] = {
+                    'X-Session-API-Key': mcp_api_key,
+                }
+
+            # Get the actual API key values, prioritizing user's key over service key
+            user_search_key = None
+            if user.search_api_key:
+                key_value = user.search_api_key.get_secret_value()
+                if key_value and key_value.strip():
+                    user_search_key = key_value
+
+            service_tavily_key = None
+            if self.tavily_api_key:
+                # tavily_api_key is already a string (extracted in the factory method)
+                if self.tavily_api_key.strip():
+                    service_tavily_key = self.tavily_api_key
+
+            tavily_api_key = user_search_key or service_tavily_key
+
+            if tavily_api_key:
+                _logger.info('Adding search engine to MCP config')
+                mcp_config['tavily'] = {
+                    'url': f'https://mcp.tavily.com/mcp/?tavilyApiKey={tavily_api_key}'
+                }
+            else:
+                _logger.info('No search engine API key found, skipping search engine')
+
+        return llm, mcp_config
+
+    def _create_agent_with_context(
+        self,
+        llm: LLM,
+        agent_type: AgentType,
+        system_message_suffix: str | None,
+        mcp_config: dict,
+        condenser_max_size: int | None,
+    ) -> Agent:
+        """Create an agent with appropriate tools and context based on agent type.
+
+        Args:
+            llm: Configured LLM instance
+            agent_type: Type of agent to create (PLAN or DEFAULT)
+            system_message_suffix: Optional suffix for system messages
+            mcp_config: MCP configuration dictionary
+            condenser_max_size: condenser_max_size setting
+
+        Returns:
+            Configured Agent instance with context
+        """
+        # Create condenser with user's settings
+        condenser = self._create_condenser(llm, agent_type, condenser_max_size)
+
+        # Create agent based on type
+        if agent_type == AgentType.PLAN:
+            agent = Agent(
+                llm=llm,
+                tools=get_planning_tools(),
+                system_prompt_filename='system_prompt_planning.j2',
+                system_prompt_kwargs={'plan_structure': format_plan_structure()},
+                condenser=condenser,
+                security_analyzer=None,
+                mcp_config=mcp_config,
+            )
+        else:
+            agent = Agent(
+                llm=llm,
+                tools=get_default_tools(enable_browser=True),
+                system_prompt_kwargs={'cli_mode': False},
+                condenser=condenser,
+                mcp_config=mcp_config,
+            )
+
+        # Add agent context
+        agent_context = AgentContext(system_message_suffix=system_message_suffix)
+        agent = agent.model_copy(update={'agent_context': agent_context})
+
+        return agent
+
+    async def _finalize_conversation_request(
+        self,
+        agent: Agent,
+        conversation_id: UUID | None,
+        user: UserInfo,
+        workspace: LocalWorkspace,
+        initial_message: SendMessageRequest | None,
+        secrets: dict,
+        sandbox: SandboxInfo,
+        remote_workspace: AsyncRemoteWorkspace | None,
+        selected_repository: str | None,
+        working_dir: str,
+    ) -> StartConversationRequest:
+        """Finalize the conversation request with experiment variants and skills.
+
+        Args:
+            agent: The configured agent
+            conversation_id: Optional conversation ID, generates new one if None
+            user: User information
+            workspace: Local workspace instance
+            initial_message: Optional initial message for the conversation
+            secrets: Dictionary of secrets for authentication
+            sandbox: Sandbox information
+            remote_workspace: Optional remote workspace for skills loading
+            selected_repository: Optional repository name
+            working_dir: Working directory path
+
+        Returns:
+            Complete StartConversationRequest ready for use
+        """
+        # Generate conversation ID if not provided
+        conversation_id = conversation_id or uuid4()
+
+        # Apply experiment variants
+        agent = ExperimentManagerImpl.run_agent_variant_tests__v1(
+            user.id, conversation_id, agent
+        )
+
+        # Load and merge skills if remote workspace is available
+        if remote_workspace:
+            try:
+                agent = await self._load_skills_and_update_agent(
+                    sandbox, agent, remote_workspace, selected_repository, working_dir
+                )
+            except Exception as e:
+                _logger.warning(f'Failed to load skills: {e}', exc_info=True)
+                # Continue without skills - don't fail conversation startup
+
+        # Create and return the final request
+        return StartConversationRequest(
+            conversation_id=conversation_id,
+            agent=agent,
+            workspace=workspace,
+            confirmation_policy=(
+                AlwaysConfirm() if user.confirmation_mode else NeverConfirm()
+            ),
+            initial_message=initial_message,
+            secrets=secrets,
+        )
+
     async def _build_start_conversation_request_for_user(
         self,
         sandbox: SandboxInfo,
@@ -532,87 +757,41 @@ class LiveStatusAppConversationService(AppConversationServiceBase):
         remote_workspace: AsyncRemoteWorkspace | None = None,
         selected_repository: str | None = None,
     ) -> StartConversationRequest:
+        """Build a complete conversation request for a user.
+
+        This method orchestrates the creation of a conversation request by:
+        1. Setting up git provider secrets
+        2. Configuring LLM and MCP settings
+        3. Creating an agent with appropriate context
+        4. Finalizing the request with skills and experiment variants
+        """
         user = await self.user_context.get_user_info()
-
-        # Set up a secret for the git token
-        secrets = await self.user_context.get_secrets()
-        if git_provider:
-            secret_name = f'{git_provider.name}_TOKEN'
-            if self.web_url:
-                # If there is a web url, then we create an access token to access it.
-                # For security reasons, we are explicit here - only this user, and
-                # only this provider, with a timeout
-                access_token = self.jwt_service.create_jws_token(
-                    payload={
-                        'user_id': user.id,
-                        'provider_type': git_provider.value,
-                    },
-                    expires_in=self.access_token_hard_timeout,
-                )
-                headers = {'X-Access-Token': access_token}
-
-                # Include keycloak_auth cookie in headers if app_mode is SaaS
-                if self.app_mode == 'saas' and self.keycloak_auth_cookie:
-                    headers['Cookie'] = f'keycloak_auth={self.keycloak_auth_cookie}'
-
-                secrets[secret_name] = LookupSecret(
-                    url=self.web_url + '/api/v1/webhooks/secrets',
-                    headers=headers,
-                )
-            else:
-                # If there is no URL specified where the sandbox can access the app server
-                # then we supply a static secret with the most recent value. Depending
-                # on the type, this may eventually expire.
-                static_token = await self.user_context.get_latest_token(git_provider)
-                if static_token:
-                    secrets[secret_name] = StaticSecret(value=static_token)
-
         workspace = LocalWorkspace(working_dir=working_dir)
 
-        # Use provided llm_model if available, otherwise fall back to user's default
-        model = llm_model or user.llm_model
-        llm = LLM(
-            model=model,
-            base_url=user.llm_base_url,
-            api_key=user.llm_api_key,
-            usage_id='agent',
-        )
-        # The agent gets passed initial instructions
-        # Select agent based on agent_type
-        if agent_type == AgentType.PLAN:
-            agent = get_planning_agent(llm=llm)
-        else:
-            agent = get_default_agent(llm=llm)
+        # Set up secrets for git provider
+        secrets = await self._setup_secrets_for_git_provider(git_provider, user)
 
-        agent_context = AgentContext(system_message_suffix=system_message_suffix)
-        agent = agent.model_copy(update={'agent_context': agent_context})
+        # Configure LLM and MCP
+        llm, mcp_config = await self._configure_llm_and_mcp(user, llm_model)
 
-        conversation_id = conversation_id or uuid4()
-        agent = ExperimentManagerImpl.run_agent_variant_tests__v1(
-            user.id, conversation_id, agent
+        # Create agent with context
+        agent = self._create_agent_with_context(
+            llm, agent_type, system_message_suffix, mcp_config, user.condenser_max_size
         )
 
-        # Load and merge all skills if remote_workspace is available
-        if remote_workspace:
-            try:
-                agent = await self._load_skills_and_update_agent(
-                    sandbox, agent, remote_workspace, selected_repository, working_dir
-                )
-            except Exception as e:
-                _logger.warning(f'Failed to load skills: {e}', exc_info=True)
-                # Continue without skills - don't fail conversation startup
-
-        start_conversation_request = StartConversationRequest(
-            conversation_id=conversation_id,
-            agent=agent,
-            workspace=workspace,
-            confirmation_policy=(
-                AlwaysConfirm() if user.confirmation_mode else NeverConfirm()
-            ),
-            initial_message=initial_message,
-            secrets=secrets,
+        # Finalize and return the conversation request
+        return await self._finalize_conversation_request(
+            agent,
+            conversation_id,
+            user,
+            workspace,
+            initial_message,
+            secrets,
+            sandbox,
+            remote_workspace,
+            selected_repository,
+            working_dir,
         )
-        return start_conversation_request
 
     async def update_agent_server_conversation_title(
         self,
@@ -817,6 +996,10 @@ class LiveStatusAppConversationServiceInjector(AppConversationServiceInjector):
             'be retrieved by a sandboxed conversation.'
         ),
     )
+    tavily_api_key: SecretStr | None = Field(
+        default=None,
+        description='The Tavily Search API key to add to MCP integration',
+    )
 
     async def inject(
         self, state: InjectorState, request: Request | None = None
@@ -874,6 +1057,14 @@ class LiveStatusAppConversationServiceInjector(AppConversationServiceInjector):
                 # If server_config is not available (e.g., in tests), continue without it
                 pass
 
+            # We supply the global tavily key only if the app mode is not SAAS, where
+            # currently the search endpoints are patched into the app server instead
+            # so the tavily key does not need to be shared
+            if self.tavily_api_key and app_mode != AppMode.SAAS:
+                tavily_api_key = self.tavily_api_key.get_secret_value()
+            else:
+                tavily_api_key = None
+
             yield LiveStatusAppConversationService(
                 init_git_in_empty_workspace=self.init_git_in_empty_workspace,
                 user_context=user_context,
@@ -890,4 +1081,5 @@ class LiveStatusAppConversationServiceInjector(AppConversationServiceInjector):
                 access_token_hard_timeout=access_token_hard_timeout,
                 app_mode=app_mode,
                 keycloak_auth_cookie=keycloak_auth_cookie,
+                tavily_api_key=tavily_api_key,
             )

openhands/app_server/app_conversation/sql_app_conversation_info_service.py

@@ -45,6 +45,8 @@ from openhands.app_server.utils.sql_utils import (
     create_json_type_decorator,
 )
 from openhands.integrations.provider import ProviderType
+from openhands.sdk.conversation.conversation_stats import ConversationStats
+from openhands.sdk.event import ConversationStateUpdateEvent
 from openhands.sdk.llm import MetricsSnapshot
 from openhands.sdk.llm.utils.metrics import TokenUsage
 from openhands.storage.data_models.conversation_metadata import ConversationTrigger
@@ -354,6 +356,130 @@ class SQLAppConversationInfoService(AppConversationInfoService):
         await self.db_session.commit()
         return info
 
+    async def update_conversation_statistics(
+        self, conversation_id: UUID, stats: ConversationStats
+    ) -> None:
+        """Update conversation statistics from stats event data.
+
+        Args:
+            conversation_id: The ID of the conversation to update
+            stats: ConversationStats object containing usage_to_metrics data from stats event
+        """
+        # Extract agent metrics from usage_to_metrics
+        usage_to_metrics = stats.usage_to_metrics
+        agent_metrics = usage_to_metrics.get('agent')
+
+        if not agent_metrics:
+            logger.debug(
+                'No agent metrics found in stats for conversation %s', conversation_id
+            )
+            return
+
+        # Query existing record using secure select (filters for V1 and user if available)
+        query = await self._secure_select()
+        query = query.where(
+            StoredConversationMetadata.conversation_id == str(conversation_id)
+        )
+        result = await self.db_session.execute(query)
+        stored = result.scalar_one_or_none()
+
+        if not stored:
+            logger.debug(
+                'Conversation %s not found or not accessible, skipping statistics update',
+                conversation_id,
+            )
+            return
+
+        # Extract accumulated_cost and max_budget_per_task from Metrics object
+        accumulated_cost = agent_metrics.accumulated_cost
+        max_budget_per_task = agent_metrics.max_budget_per_task
+
+        # Extract accumulated_token_usage from Metrics object
+        accumulated_token_usage = agent_metrics.accumulated_token_usage
+        if accumulated_token_usage:
+            prompt_tokens = accumulated_token_usage.prompt_tokens
+            completion_tokens = accumulated_token_usage.completion_tokens
+            cache_read_tokens = accumulated_token_usage.cache_read_tokens
+            cache_write_tokens = accumulated_token_usage.cache_write_tokens
+            reasoning_tokens = accumulated_token_usage.reasoning_tokens
+            context_window = accumulated_token_usage.context_window
+            per_turn_token = accumulated_token_usage.per_turn_token
+        else:
+            prompt_tokens = None
+            completion_tokens = None
+            cache_read_tokens = None
+            cache_write_tokens = None
+            reasoning_tokens = None
+            context_window = None
+            per_turn_token = None
+
+        # Update fields only if values are provided (not None)
+        if accumulated_cost is not None:
+            stored.accumulated_cost = accumulated_cost
+        if max_budget_per_task is not None:
+            stored.max_budget_per_task = max_budget_per_task
+        if prompt_tokens is not None:
+            stored.prompt_tokens = prompt_tokens
+        if completion_tokens is not None:
+            stored.completion_tokens = completion_tokens
+        if cache_read_tokens is not None:
+            stored.cache_read_tokens = cache_read_tokens
+        if cache_write_tokens is not None:
+            stored.cache_write_tokens = cache_write_tokens
+        if reasoning_tokens is not None:
+            stored.reasoning_tokens = reasoning_tokens
+        if context_window is not None:
+            stored.context_window = context_window
+        if per_turn_token is not None:
+            stored.per_turn_token = per_turn_token
+
+        # Update last_updated_at timestamp
+        stored.last_updated_at = utc_now()
+
+        await self.db_session.commit()
+
+    async def process_stats_event(
+        self,
+        event: ConversationStateUpdateEvent,
+        conversation_id: UUID,
+    ) -> None:
+        """Process a stats event and update conversation statistics.
+
+        Args:
+            event: The ConversationStateUpdateEvent with key='stats'
+            conversation_id: The ID of the conversation to update
+        """
+        try:
+            # Parse event value into ConversationStats model for type safety
+            # event.value can be a dict (from JSON deserialization) or a ConversationStats object
+            event_value = event.value
+            conversation_stats: ConversationStats | None = None
+
+            if isinstance(event_value, ConversationStats):
+                # Already a ConversationStats object
+                conversation_stats = event_value
+            elif isinstance(event_value, dict):
+                # Parse dict into ConversationStats model
+                # This validates the structure and ensures type safety
+                conversation_stats = ConversationStats.model_validate(event_value)
+            elif hasattr(event_value, 'usage_to_metrics'):
+                # Handle objects with usage_to_metrics attribute (e.g., from tests)
+                # Convert to dict first, then validate
+                stats_dict = {'usage_to_metrics': event_value.usage_to_metrics}
+                conversation_stats = ConversationStats.model_validate(stats_dict)
+
+            if conversation_stats and conversation_stats.usage_to_metrics:
+                # Pass ConversationStats object directly for type safety
+                await self.update_conversation_statistics(
+                    conversation_id, conversation_stats
+                )
+        except Exception:
+            logger.exception(
+                'Error updating conversation statistics for conversation %s',
+                conversation_id,
+                stack_info=True,
+            )
+
     async def _secure_select(self):
         query = select(StoredConversationMetadata).where(
             StoredConversationMetadata.conversation_version == 'V1'

openhands/app_server/config.py

@@ -6,7 +6,7 @@ from typing import AsyncContextManager
 
 import httpx
 from fastapi import Depends, Request
-from pydantic import Field
+from pydantic import Field, SecretStr
 from sqlalchemy.ext.asyncio import AsyncSession
 
 # Import the event_callback module to ensure all processors are registered
@@ -185,7 +185,13 @@ def config_from_env() -> AppServerConfig:
         )
 
     if config.app_conversation is None:
-        config.app_conversation = LiveStatusAppConversationServiceInjector()
+        tavily_api_key = None
+        tavily_api_key_str = os.getenv('TAVILY_API_KEY') or os.getenv('SEARCH_API_KEY')
+        if tavily_api_key_str:
+            tavily_api_key = SecretStr(tavily_api_key_str)
+        config.app_conversation = LiveStatusAppConversationServiceInjector(
+            tavily_api_key=tavily_api_key
+        )
 
     if config.user is None:
         config.user = AuthUserContextInjector()

openhands/app_server/event_callback/sql_event_callback_service.py

@@ -6,7 +6,6 @@ from __future__ import annotations
 import asyncio
 import logging
 from dataclasses import dataclass
-from datetime import datetime
 from typing import AsyncGenerator
 from uuid import UUID
 
@@ -15,6 +14,7 @@ from sqlalchemy import UUID as SQLUUID
 from sqlalchemy import Column, Enum, String, and_, func, or_, select
 from sqlalchemy.ext.asyncio import AsyncSession
 
+from openhands.agent_server.utils import utc_now
 from openhands.app_server.event_callback.event_callback_models import (
     CreateEventCallbackRequest,
     EventCallback,
@@ -177,7 +177,7 @@ class SQLEventCallbackService(EventCallbackService):
         return EventCallbackPage(items=callbacks, next_page_id=next_page_id)
 
     async def save_event_callback(self, event_callback: EventCallback) -> EventCallback:
-        event_callback.updated_at = datetime.now()
+        event_callback.updated_at = utc_now()
         stored_callback = StoredEventCallback(**event_callback.model_dump())
         await self.db_session.merge(stored_callback)
         return event_callback

openhands/app_server/event_callback/webhook_router.py

@@ -43,6 +43,7 @@ from openhands.app_server.user.specifiy_user_context import (
 from openhands.app_server.user.user_context import UserContext
 from openhands.integrations.provider import ProviderType
 from openhands.sdk import Event
+from openhands.sdk.event import ConversationStateUpdateEvent
 from openhands.server.user_auth.default_user_auth import DefaultUserAuth
 from openhands.server.user_auth.user_auth import (
     get_for_user as get_user_auth_for_user,
@@ -144,6 +145,13 @@ async def on_event(
             *[event_service.save_event(conversation_id, event) for event in events]
         )
 
+        # Process stats events for V1 conversations
+        for event in events:
+            if isinstance(event, ConversationStateUpdateEvent) and event.key == 'stats':
+                await app_conversation_info_service.process_stats_event(
+                    event, conversation_id
+                )
+
         asyncio.create_task(
             _run_callbacks_in_bg_and_close(
                 conversation_id, app_conversation_info.created_by_user_id, events

openhands/app_server/user/auth_user_context.py

@@ -78,6 +78,10 @@ class AuthUserContext(UserContext):
 
         return results
 
+    async def get_mcp_api_key(self) -> str | None:
+        mcp_api_key = await self.user_auth.get_mcp_api_key()
+        return mcp_api_key
+
 
 USER_ID_ATTR = 'user_id'
 

openhands/app_server/user/specifiy_user_context.py

@@ -30,6 +30,9 @@ class SpecifyUserContext(UserContext):
     async def get_secrets(self) -> dict[str, SecretSource]:
         raise NotImplementedError()
 
+    async def get_mcp_api_key(self) -> str | None:
+        raise NotImplementedError()
+
 
 USER_CONTEXT_ATTR = 'user_context'
 ADMIN = SpecifyUserContext(user_id=None)

openhands/app_server/user/user_context.py

@@ -34,6 +34,10 @@ class UserContext(ABC):
     async def get_secrets(self) -> dict[str, SecretSource]:
         """Get custom secrets and github provider secrets for the conversation."""
 
+    @abstractmethod
+    async def get_mcp_api_key(self) -> str | None:
+        """Get an MCP API Key."""
+
 
 class UserContextInjector(DiscriminatedUnionMixin, Injector[UserContext], ABC):
     """Injector for user contexts."""

openhands/controller/agent_controller.py

@@ -42,10 +42,6 @@ from openhands.core.exceptions import (
 from openhands.core.logger import LOG_ALL_EVENTS
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.schema import AgentState
-from openhands.utils.posthog_tracker import (
-    track_agent_task_completed,
-    track_credit_limit_reached,
-)
 from openhands.events import (
     EventSource,
     EventStream,
@@ -713,20 +709,6 @@ class AgentController:
             EventSource.ENVIRONMENT,
         )
 
-        # Track agent task completion in PostHog
-        if new_state == AgentState.FINISHED:
-            try:
-                # Get app_mode from environment, default to 'oss'
-                app_mode = os.environ.get('APP_MODE', 'oss')
-                track_agent_task_completed(
-                    conversation_id=self.id,
-                    user_id=self.user_id,
-                    app_mode=app_mode,
-                )
-            except Exception as e:
-                # Don't let tracking errors interrupt the agent
-                self.log('warning', f'Failed to track agent completion: {e}')
-
         # Save state whenever agent state changes to ensure we don't lose state
         # in case of crashes or unexpected circumstances
         self.save_state()
@@ -905,18 +887,6 @@ class AgentController:
             self.state_tracker.run_control_flags()
         except Exception as e:
             logger.warning('Control flag limits hit')
-            # Track credit limit reached if it's a budget exception
-            if 'budget' in str(e).lower() and self.state.budget_flag:
-                try:
-                    track_credit_limit_reached(
-                        conversation_id=self.id,
-                        user_id=self.user_id,
-                        current_budget=self.state.budget_flag.current_value,
-                        max_budget=self.state.budget_flag.max_value,
-                    )
-                except Exception as track_error:
-                    # Don't let tracking errors interrupt the agent
-                    self.log('warning', f'Failed to track credit limit: {track_error}')
             await self._react_to_exception(e)
             return
 

openhands/llm/llm.py

@@ -188,12 +188,14 @@ class LLM(RetryMixin, DebugMixin):
         if 'claude-opus-4-1' in self.config.model.lower():
             kwargs['thinking'] = {'type': 'disabled'}
 
-        # Anthropic constraint: Opus 4.1 and Sonnet 4 models cannot accept both temperature and top_p
+        # Anthropic constraint: Opus 4.1, Opus 4.5, and Sonnet 4 models cannot accept both temperature and top_p
         # Prefer temperature (drop top_p) if both are specified.
         _model_lower = self.config.model.lower()
-        # Apply to Opus 4.1 and Sonnet 4 models to avoid API errors
+        # Apply to Opus 4.1, Opus 4.5, and Sonnet 4 models to avoid API errors
         if (
-            ('claude-opus-4-1' in _model_lower) or ('claude-sonnet-4' in _model_lower)
+            ('claude-opus-4-1' in _model_lower)
+            or ('claude-opus-4-5' in _model_lower)
+            or ('claude-sonnet-4' in _model_lower)
         ) and ('temperature' in kwargs and 'top_p' in kwargs):
             kwargs.pop('top_p', None)
 

openhands/llm/model_features.py

@@ -132,6 +132,8 @@ SUPPORTS_STOP_WORDS_FALSE_PATTERNS: list[str] = [
     'grok-code-fast-1',
     # DeepSeek R1 family
     'deepseek-r1-0528*',
+    # Azure GPT-5 family
+    'azure/gpt-5*',
 ]
 
 

openhands/server/routes/git.py

@@ -26,13 +26,11 @@ from openhands.microagent.types import (
 )
 from openhands.server.dependencies import get_dependencies
 from openhands.server.shared import server_config
-from openhands.server.types import AppMode
 from openhands.server.user_auth import (
     get_access_token,
     get_provider_tokens,
     get_user_id,
 )
-from openhands.utils.posthog_tracker import alias_user_identities
 
 app = APIRouter(prefix='/api/user', dependencies=get_dependencies())
 
@@ -119,14 +117,6 @@ async def get_user(
 
         try:
             user: User = await client.get_user()
-
-            # Alias git provider login with Keycloak user ID in PostHog (SaaS mode only)
-            if user_id and user.login and server_config.app_mode == AppMode.SAAS:
-                alias_user_identities(
-                    keycloak_user_id=user_id,
-                    git_login=user.login,
-                )
-
             return user
 
         except UnknownException as e:

openhands/server/user_auth/default_user_auth.py

@@ -88,6 +88,9 @@ class DefaultUserAuth(UserAuth):
             return None
         return user_secrets.provider_tokens
 
+    async def get_mcp_api_key(self) -> str | None:
+        return None
+
     @classmethod
     async def get_instance(cls, request: Request) -> UserAuth:
         user_auth = DefaultUserAuth()

openhands/server/user_auth/user_auth.py

@@ -75,6 +75,10 @@ class UserAuth(ABC):
     def get_auth_type(self) -> AuthType | None:
         return None
 
+    @abstractmethod
+    async def get_mcp_api_key(self) -> str | None:
+        """Get an mcp api key for the user"""
+
     @classmethod
     @abstractmethod
     async def get_instance(cls, request: Request) -> UserAuth:

openhands/utils/posthog_tracker.py

@@ -1,270 +0,0 @@
-"""PostHog tracking utilities for OpenHands events."""
-
-import os
-
-from openhands.core.logger import openhands_logger as logger
-
-# Lazy import posthog to avoid import errors in environments where it's not installed
-posthog = None
-
-
-def _init_posthog():
-    """Initialize PostHog client lazily."""
-    global posthog
-    if posthog is None:
-        try:
-            import posthog as ph
-
-            posthog = ph
-            posthog.api_key = os.environ.get(
-                'POSTHOG_CLIENT_KEY', 'phc_3ESMmY9SgqEAGBB6sMGK5ayYHkeUuknH2vP6FmWH9RA'
-            )
-            posthog.host = os.environ.get('POSTHOG_HOST', 'https://us.i.posthog.com')
-        except ImportError:
-            logger.warning(
-                'PostHog not installed. Analytics tracking will be disabled.'
-            )
-            posthog = None
-
-
-def track_agent_task_completed(
-    conversation_id: str,
-    user_id: str | None = None,
-    app_mode: str | None = None,
-) -> None:
-    """Track when an agent completes a task.
-
-    Args:
-        conversation_id: The ID of the conversation/session
-        user_id: The ID of the user (optional, may be None for unauthenticated users)
-        app_mode: The application mode (saas/oss), optional
-    """
-    _init_posthog()
-
-    if posthog is None:
-        return
-
-    # Use conversation_id as distinct_id if user_id is not available
-    # This ensures we can track completions even for anonymous users
-    distinct_id = user_id if user_id else f'conversation_{conversation_id}'
-
-    try:
-        posthog.capture(
-            distinct_id=distinct_id,
-            event='agent_task_completed',
-            properties={
-                'conversation_id': conversation_id,
-                'user_id': user_id,
-                'app_mode': app_mode or 'unknown',
-            },
-        )
-        logger.debug(
-            'posthog_track',
-            extra={
-                'event': 'agent_task_completed',
-                'conversation_id': conversation_id,
-                'user_id': user_id,
-            },
-        )
-    except Exception as e:
-        logger.warning(
-            f'Failed to track agent_task_completed to PostHog: {e}',
-            extra={
-                'conversation_id': conversation_id,
-                'error': str(e),
-            },
-        )
-
-
-def track_user_signup_completed(
-    user_id: str,
-    signup_timestamp: str,
-) -> None:
-    """Track when a user completes signup by accepting TOS.
-
-    Args:
-        user_id: The ID of the user (Keycloak user ID)
-        signup_timestamp: ISO format timestamp of when TOS was accepted
-    """
-    _init_posthog()
-
-    if posthog is None:
-        return
-
-    try:
-        posthog.capture(
-            distinct_id=user_id,
-            event='user_signup_completed',
-            properties={
-                'user_id': user_id,
-                'signup_timestamp': signup_timestamp,
-            },
-        )
-        logger.debug(
-            'posthog_track',
-            extra={
-                'event': 'user_signup_completed',
-                'user_id': user_id,
-            },
-        )
-    except Exception as e:
-        logger.warning(
-            f'Failed to track user_signup_completed to PostHog: {e}',
-            extra={
-                'user_id': user_id,
-                'error': str(e),
-            },
-        )
-
-
-def track_credit_limit_reached(
-    conversation_id: str,
-    user_id: str | None = None,
-    current_budget: float = 0.0,
-    max_budget: float = 0.0,
-) -> None:
-    """Track when a user reaches their credit limit during a conversation.
-
-    Args:
-        conversation_id: The ID of the conversation/session
-        user_id: The ID of the user (optional, may be None for unauthenticated users)
-        current_budget: The current budget spent
-        max_budget: The maximum budget allowed
-    """
-    _init_posthog()
-
-    if posthog is None:
-        return
-
-    distinct_id = user_id if user_id else f'conversation_{conversation_id}'
-
-    try:
-        posthog.capture(
-            distinct_id=distinct_id,
-            event='credit_limit_reached',
-            properties={
-                'conversation_id': conversation_id,
-                'user_id': user_id,
-                'current_budget': current_budget,
-                'max_budget': max_budget,
-            },
-        )
-        logger.debug(
-            'posthog_track',
-            extra={
-                'event': 'credit_limit_reached',
-                'conversation_id': conversation_id,
-                'user_id': user_id,
-                'current_budget': current_budget,
-                'max_budget': max_budget,
-            },
-        )
-    except Exception as e:
-        logger.warning(
-            f'Failed to track credit_limit_reached to PostHog: {e}',
-            extra={
-                'conversation_id': conversation_id,
-                'error': str(e),
-            },
-        )
-
-
-def track_credits_purchased(
-    user_id: str,
-    amount_usd: float,
-    credits_added: float,
-    stripe_session_id: str,
-) -> None:
-    """Track when a user successfully purchases credits.
-
-    Args:
-        user_id: The ID of the user (Keycloak user ID)
-        amount_usd: The amount paid in USD (cents converted to dollars)
-        credits_added: The number of credits added to the user's account
-        stripe_session_id: The Stripe checkout session ID
-    """
-    _init_posthog()
-
-    if posthog is None:
-        return
-
-    try:
-        posthog.capture(
-            distinct_id=user_id,
-            event='credits_purchased',
-            properties={
-                'user_id': user_id,
-                'amount_usd': amount_usd,
-                'credits_added': credits_added,
-                'stripe_session_id': stripe_session_id,
-            },
-        )
-        logger.debug(
-            'posthog_track',
-            extra={
-                'event': 'credits_purchased',
-                'user_id': user_id,
-                'amount_usd': amount_usd,
-                'credits_added': credits_added,
-            },
-        )
-    except Exception as e:
-        logger.warning(
-            f'Failed to track credits_purchased to PostHog: {e}',
-            extra={
-                'user_id': user_id,
-                'error': str(e),
-            },
-        )
-
-
-def alias_user_identities(
-    keycloak_user_id: str,
-    git_login: str,
-) -> None:
-    """Alias a user's Keycloak ID with their git provider login for unified tracking.
-
-    This allows PostHog to link events tracked from the frontend (using git provider login)
-    with events tracked from the backend (using Keycloak user ID).
-
-    PostHog Python alias syntax: alias(previous_id, distinct_id)
-    - previous_id: The old/previous distinct ID that will be merged
-    - distinct_id: The new/canonical distinct ID to merge into
-
-    For our use case:
-    - Git provider login is the previous_id (first used in frontend, before backend auth)
-    - Keycloak user ID is the distinct_id (canonical backend ID)
-    - Result: All events with git login will be merged into Keycloak user ID
-
-    Args:
-        keycloak_user_id: The Keycloak user ID (canonical distinct_id)
-        git_login: The git provider username (GitHub/GitLab/Bitbucket) to merge
-
-    Reference:
-        https://github.com/PostHog/posthog-python/blob/master/posthog/client.py
-    """
-    _init_posthog()
-
-    if posthog is None:
-        return
-
-    try:
-        # Merge git provider login into Keycloak user ID
-        # posthog.alias(previous_id, distinct_id) - official Python SDK signature
-        posthog.alias(git_login, keycloak_user_id)
-        logger.debug(
-            'posthog_alias',
-            extra={
-                'previous_id': git_login,
-                'distinct_id': keycloak_user_id,
-            },
-        )
-    except Exception as e:
-        logger.warning(
-            f'Failed to alias user identities in PostHog: {e}',
-            extra={
-                'keycloak_user_id': keycloak_user_id,
-                'git_login': git_login,
-                'error': str(e),
-            },
-        )

tests/unit/app_server/test_app_conversation_service_base.py

@@ -0,0 +1,628 @@
+"""Unit tests for git functionality in AppConversationServiceBase.
+
+This module tests the git-related functionality, specifically the clone_or_init_git_repo method
+and the recent bug fixes for git checkout operations.
+"""
+
+import subprocess
+from unittest.mock import AsyncMock, MagicMock, Mock, patch
+
+import pytest
+
+from openhands.app_server.app_conversation.app_conversation_models import AgentType
+from openhands.app_server.app_conversation.app_conversation_service_base import (
+    AppConversationServiceBase,
+)
+from openhands.app_server.user.user_context import UserContext
+
+
+class MockUserInfo:
+    """Mock class for UserInfo to simulate user settings."""
+
+    def __init__(
+        self, git_user_name: str | None = None, git_user_email: str | None = None
+    ):
+        self.git_user_name = git_user_name
+        self.git_user_email = git_user_email
+
+
+class MockCommandResult:
+    """Mock class for command execution result."""
+
+    def __init__(self, exit_code: int = 0, stderr: str = ''):
+        self.exit_code = exit_code
+        self.stderr = stderr
+
+
+class MockWorkspace:
+    """Mock class for AsyncRemoteWorkspace."""
+
+    def __init__(self, working_dir: str = '/workspace'):
+        self.working_dir = working_dir
+        self.execute_command = AsyncMock(return_value=MockCommandResult())
+
+
+class MockAppConversationServiceBase:
+    """Mock class to test git functionality without complex dependencies."""
+
+    def __init__(self):
+        self.logger = MagicMock()
+
+    async def clone_or_init_git_repo(
+        self,
+        workspace_path: str,
+        repo_url: str,
+        branch: str = 'main',
+        timeout: int = 300,
+    ) -> bool:
+        """Clone or initialize a git repository.
+
+        This is a simplified version of the actual method for testing purposes.
+        """
+        try:
+            # Try to clone the repository
+            clone_result = subprocess.run(
+                ['git', 'clone', '--branch', branch, repo_url, workspace_path],
+                capture_output=True,
+                text=True,
+                timeout=timeout,
+            )
+
+            if clone_result.returncode == 0:
+                self.logger.info(
+                    f'Successfully cloned repository {repo_url} to {workspace_path}'
+                )
+                return True
+
+            # If clone fails, try to checkout the branch
+            checkout_result = subprocess.run(
+                ['git', 'checkout', branch],
+                cwd=workspace_path,
+                capture_output=True,
+                text=True,
+                timeout=timeout,
+            )
+
+            if checkout_result.returncode == 0:
+                self.logger.info(f'Successfully checked out branch {branch}')
+                return True
+            else:
+                self.logger.error(
+                    f'Failed to checkout branch {branch}: {checkout_result.stderr}'
+                )
+                return False
+
+        except subprocess.TimeoutExpired:
+            self.logger.error(f'Git operation timed out after {timeout} seconds')
+            return False
+        except Exception as e:
+            self.logger.error(f'Git operation failed: {str(e)}')
+            return False
+
+
+@pytest.fixture
+def service():
+    """Create a mock service instance for testing."""
+    return MockAppConversationServiceBase()
+
+
+@pytest.mark.asyncio
+async def test_clone_or_init_git_repo_successful_clone(service):
+    """Test successful git clone operation."""
+    with patch('subprocess.run') as mock_run:
+        # Mock successful clone
+        mock_run.return_value = MagicMock(returncode=0, stderr='', stdout='Cloning...')
+
+        result = await service.clone_or_init_git_repo(
+            workspace_path='/tmp/test_repo',
+            repo_url='https://github.com/test/repo.git',
+            branch='main',
+            timeout=300,
+        )
+
+        assert result is True
+        mock_run.assert_called_once_with(
+            [
+                'git',
+                'clone',
+                '--branch',
+                'main',
+                'https://github.com/test/repo.git',
+                '/tmp/test_repo',
+            ],
+            capture_output=True,
+            text=True,
+            timeout=300,
+        )
+        service.logger.info.assert_called_with(
+            'Successfully cloned repository https://github.com/test/repo.git to /tmp/test_repo'
+        )
+
+
+@pytest.mark.asyncio
+async def test_clone_or_init_git_repo_clone_fails_checkout_succeeds(service):
+    """Test git clone fails but checkout succeeds."""
+    with patch('subprocess.run') as mock_run:
+        # Mock clone failure, then checkout success
+        mock_run.side_effect = [
+            MagicMock(returncode=1, stderr='Clone failed', stdout=''),  # Clone fails
+            MagicMock(
+                returncode=0, stderr='', stdout='Switched to branch'
+            ),  # Checkout succeeds
+        ]
+
+        result = await service.clone_or_init_git_repo(
+            workspace_path='/tmp/test_repo',
+            repo_url='https://github.com/test/repo.git',
+            branch='feature-branch',
+            timeout=300,
+        )
+
+        assert result is True
+        assert mock_run.call_count == 2
+
+        # Check clone call
+        mock_run.assert_any_call(
+            [
+                'git',
+                'clone',
+                '--branch',
+                'feature-branch',
+                'https://github.com/test/repo.git',
+                '/tmp/test_repo',
+            ],
+            capture_output=True,
+            text=True,
+            timeout=300,
+        )
+
+        # Check checkout call
+        mock_run.assert_any_call(
+            ['git', 'checkout', 'feature-branch'],
+            cwd='/tmp/test_repo',
+            capture_output=True,
+            text=True,
+            timeout=300,
+        )
+
+        service.logger.info.assert_called_with(
+            'Successfully checked out branch feature-branch'
+        )
+
+
+@pytest.mark.asyncio
+async def test_clone_or_init_git_repo_both_operations_fail(service):
+    """Test both git clone and checkout operations fail."""
+    with patch('subprocess.run') as mock_run:
+        # Mock both operations failing
+        mock_run.side_effect = [
+            MagicMock(returncode=1, stderr='Clone failed', stdout=''),  # Clone fails
+            MagicMock(
+                returncode=1, stderr='Checkout failed', stdout=''
+            ),  # Checkout fails
+        ]
+
+        result = await service.clone_or_init_git_repo(
+            workspace_path='/tmp/test_repo',
+            repo_url='https://github.com/test/repo.git',
+            branch='nonexistent-branch',
+            timeout=300,
+        )
+
+        assert result is False
+        assert mock_run.call_count == 2
+        service.logger.error.assert_called_with(
+            'Failed to checkout branch nonexistent-branch: Checkout failed'
+        )
+
+
+@pytest.mark.asyncio
+async def test_clone_or_init_git_repo_timeout(service):
+    """Test git operation timeout."""
+    with patch('subprocess.run') as mock_run:
+        # Mock timeout exception
+        mock_run.side_effect = subprocess.TimeoutExpired(
+            cmd=['git', 'clone'], timeout=300
+        )
+
+        result = await service.clone_or_init_git_repo(
+            workspace_path='/tmp/test_repo',
+            repo_url='https://github.com/test/repo.git',
+            branch='main',
+            timeout=300,
+        )
+
+        assert result is False
+        service.logger.error.assert_called_with(
+            'Git operation timed out after 300 seconds'
+        )
+
+
+@pytest.mark.asyncio
+async def test_clone_or_init_git_repo_exception(service):
+    """Test git operation with unexpected exception."""
+    with patch('subprocess.run') as mock_run:
+        # Mock unexpected exception
+        mock_run.side_effect = Exception('Unexpected error')
+
+        result = await service.clone_or_init_git_repo(
+            workspace_path='/tmp/test_repo',
+            repo_url='https://github.com/test/repo.git',
+            branch='main',
+            timeout=300,
+        )
+
+        assert result is False
+        service.logger.error.assert_called_with(
+            'Git operation failed: Unexpected error'
+        )
+
+
+@pytest.mark.asyncio
+async def test_clone_or_init_git_repo_custom_timeout(service):
+    """Test git operation with custom timeout."""
+    with patch('subprocess.run') as mock_run:
+        # Mock successful clone with custom timeout
+        mock_run.return_value = MagicMock(returncode=0, stderr='', stdout='Cloning...')
+
+        result = await service.clone_or_init_git_repo(
+            workspace_path='/tmp/test_repo',
+            repo_url='https://github.com/test/repo.git',
+            branch='main',
+            timeout=600,  # Custom timeout
+        )
+
+        assert result is True
+        mock_run.assert_called_once_with(
+            [
+                'git',
+                'clone',
+                '--branch',
+                'main',
+                'https://github.com/test/repo.git',
+                '/tmp/test_repo',
+            ],
+            capture_output=True,
+            text=True,
+            timeout=600,  # Verify custom timeout is used
+        )
+
+
+@patch(
+    'openhands.app_server.app_conversation.app_conversation_service_base.LLMSummarizingCondenser'
+)
+def test_create_condenser_default_agent_with_none_max_size(mock_condenser_class):
+    """Test _create_condenser for DEFAULT agent with condenser_max_size = None uses default."""
+    # Arrange
+    mock_user_context = Mock(spec=UserContext)
+    with patch.object(
+        AppConversationServiceBase,
+        '__abstractmethods__',
+        set(),
+    ):
+        service = AppConversationServiceBase(
+            init_git_in_empty_workspace=True,
+            user_context=mock_user_context,
+        )
+        mock_llm = MagicMock()
+        mock_llm_copy = MagicMock()
+        mock_llm_copy.usage_id = 'condenser'
+        mock_llm.model_copy.return_value = mock_llm_copy
+        mock_condenser_instance = MagicMock()
+        mock_condenser_class.return_value = mock_condenser_instance
+
+        # Act
+        service._create_condenser(mock_llm, AgentType.DEFAULT, None)
+
+        # Assert
+        mock_condenser_class.assert_called_once()
+        call_kwargs = mock_condenser_class.call_args[1]
+        # When condenser_max_size is None, max_size should not be passed (uses SDK default of 120)
+        assert 'max_size' not in call_kwargs
+        # keep_first is never passed (uses SDK default of 4)
+        assert 'keep_first' not in call_kwargs
+        assert call_kwargs['llm'].usage_id == 'condenser'
+        mock_llm.model_copy.assert_called_once()
+
+
+@patch(
+    'openhands.app_server.app_conversation.app_conversation_service_base.LLMSummarizingCondenser'
+)
+def test_create_condenser_default_agent_with_custom_max_size(mock_condenser_class):
+    """Test _create_condenser for DEFAULT agent with custom condenser_max_size."""
+    # Arrange
+    mock_user_context = Mock(spec=UserContext)
+    with patch.object(
+        AppConversationServiceBase,
+        '__abstractmethods__',
+        set(),
+    ):
+        service = AppConversationServiceBase(
+            init_git_in_empty_workspace=True,
+            user_context=mock_user_context,
+        )
+        mock_llm = MagicMock()
+        mock_llm_copy = MagicMock()
+        mock_llm_copy.usage_id = 'condenser'
+        mock_llm.model_copy.return_value = mock_llm_copy
+        mock_condenser_instance = MagicMock()
+        mock_condenser_class.return_value = mock_condenser_instance
+
+        # Act
+        service._create_condenser(mock_llm, AgentType.DEFAULT, 150)
+
+        # Assert
+        mock_condenser_class.assert_called_once()
+        call_kwargs = mock_condenser_class.call_args[1]
+        assert call_kwargs['max_size'] == 150  # Custom value should be used
+        # keep_first is never passed (uses SDK default of 4)
+        assert 'keep_first' not in call_kwargs
+        assert call_kwargs['llm'].usage_id == 'condenser'
+        mock_llm.model_copy.assert_called_once()
+
+
+@patch(
+    'openhands.app_server.app_conversation.app_conversation_service_base.LLMSummarizingCondenser'
+)
+def test_create_condenser_plan_agent_with_none_max_size(mock_condenser_class):
+    """Test _create_condenser for PLAN agent with condenser_max_size = None uses default."""
+    # Arrange
+    mock_user_context = Mock(spec=UserContext)
+    with patch.object(
+        AppConversationServiceBase,
+        '__abstractmethods__',
+        set(),
+    ):
+        service = AppConversationServiceBase(
+            init_git_in_empty_workspace=True,
+            user_context=mock_user_context,
+        )
+        mock_llm = MagicMock()
+        mock_llm_copy = MagicMock()
+        mock_llm_copy.usage_id = 'planning_condenser'
+        mock_llm.model_copy.return_value = mock_llm_copy
+        mock_condenser_instance = MagicMock()
+        mock_condenser_class.return_value = mock_condenser_instance
+
+        # Act
+        service._create_condenser(mock_llm, AgentType.PLAN, None)
+
+        # Assert
+        mock_condenser_class.assert_called_once()
+        call_kwargs = mock_condenser_class.call_args[1]
+        # When condenser_max_size is None, max_size should not be passed (uses SDK default of 120)
+        assert 'max_size' not in call_kwargs
+        # keep_first is never passed (uses SDK default of 4)
+        assert 'keep_first' not in call_kwargs
+        assert call_kwargs['llm'].usage_id == 'planning_condenser'
+        mock_llm.model_copy.assert_called_once()
+
+
+@patch(
+    'openhands.app_server.app_conversation.app_conversation_service_base.LLMSummarizingCondenser'
+)
+def test_create_condenser_plan_agent_with_custom_max_size(mock_condenser_class):
+    """Test _create_condenser for PLAN agent with custom condenser_max_size."""
+    # Arrange
+    mock_user_context = Mock(spec=UserContext)
+    with patch.object(
+        AppConversationServiceBase,
+        '__abstractmethods__',
+        set(),
+    ):
+        service = AppConversationServiceBase(
+            init_git_in_empty_workspace=True,
+            user_context=mock_user_context,
+        )
+        mock_llm = MagicMock()
+        mock_llm_copy = MagicMock()
+        mock_llm_copy.usage_id = 'planning_condenser'
+        mock_llm.model_copy.return_value = mock_llm_copy
+        mock_condenser_instance = MagicMock()
+        mock_condenser_class.return_value = mock_condenser_instance
+
+        # Act
+        service._create_condenser(mock_llm, AgentType.PLAN, 200)
+
+        # Assert
+        mock_condenser_class.assert_called_once()
+        call_kwargs = mock_condenser_class.call_args[1]
+        assert call_kwargs['max_size'] == 200  # Custom value should be used
+        # keep_first is never passed (uses SDK default of 4)
+        assert 'keep_first' not in call_kwargs
+        assert call_kwargs['llm'].usage_id == 'planning_condenser'
+        mock_llm.model_copy.assert_called_once()
+
+
+# =============================================================================
+# Tests for _configure_git_user_settings
+# =============================================================================
+
+
+def _create_service_with_mock_user_context(user_info: MockUserInfo) -> tuple:
+    """Create a mock service with the actual _configure_git_user_settings method.
+
+    Uses MagicMock for the service but binds the real method for testing.
+
+    Returns a tuple of (service, mock_user_context) for testing.
+    """
+    mock_user_context = MagicMock()
+    mock_user_context.get_user_info = AsyncMock(return_value=user_info)
+
+    # Create a simple mock service and set required attribute
+    service = MagicMock()
+    service.user_context = mock_user_context
+
+    # Bind the actual method from the real class to test real implementation
+    service._configure_git_user_settings = (
+        lambda workspace: AppConversationServiceBase._configure_git_user_settings(
+            service, workspace
+        )
+    )
+
+    return service, mock_user_context
+
+
+@pytest.fixture
+def mock_workspace():
+    """Create a mock workspace instance for testing."""
+    return MockWorkspace(working_dir='/workspace/project')
+
+
+@pytest.mark.asyncio
+async def test_configure_git_user_settings_both_name_and_email(mock_workspace):
+    """Test configuring both git user name and email."""
+    user_info = MockUserInfo(
+        git_user_name='Test User', git_user_email='test@example.com'
+    )
+    service, mock_user_context = _create_service_with_mock_user_context(user_info)
+
+    await service._configure_git_user_settings(mock_workspace)
+
+    # Verify get_user_info was called
+    mock_user_context.get_user_info.assert_called_once()
+
+    # Verify both git config commands were executed
+    assert mock_workspace.execute_command.call_count == 2
+
+    # Check git config user.name call
+    mock_workspace.execute_command.assert_any_call(
+        'git config --global user.name "Test User"', '/workspace/project'
+    )
+
+    # Check git config user.email call
+    mock_workspace.execute_command.assert_any_call(
+        'git config --global user.email "test@example.com"', '/workspace/project'
+    )
+
+
+@pytest.mark.asyncio
+async def test_configure_git_user_settings_only_name(mock_workspace):
+    """Test configuring only git user name."""
+    user_info = MockUserInfo(git_user_name='Test User', git_user_email=None)
+    service, _ = _create_service_with_mock_user_context(user_info)
+
+    await service._configure_git_user_settings(mock_workspace)
+
+    # Verify only user.name was configured
+    assert mock_workspace.execute_command.call_count == 1
+    mock_workspace.execute_command.assert_called_once_with(
+        'git config --global user.name "Test User"', '/workspace/project'
+    )
+
+
+@pytest.mark.asyncio
+async def test_configure_git_user_settings_only_email(mock_workspace):
+    """Test configuring only git user email."""
+    user_info = MockUserInfo(git_user_name=None, git_user_email='test@example.com')
+    service, _ = _create_service_with_mock_user_context(user_info)
+
+    await service._configure_git_user_settings(mock_workspace)
+
+    # Verify only user.email was configured
+    assert mock_workspace.execute_command.call_count == 1
+    mock_workspace.execute_command.assert_called_once_with(
+        'git config --global user.email "test@example.com"', '/workspace/project'
+    )
+
+
+@pytest.mark.asyncio
+async def test_configure_git_user_settings_neither_set(mock_workspace):
+    """Test when neither git user name nor email is set."""
+    user_info = MockUserInfo(git_user_name=None, git_user_email=None)
+    service, _ = _create_service_with_mock_user_context(user_info)
+
+    await service._configure_git_user_settings(mock_workspace)
+
+    # Verify no git config commands were executed
+    mock_workspace.execute_command.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_configure_git_user_settings_empty_strings(mock_workspace):
+    """Test when git user name and email are empty strings."""
+    user_info = MockUserInfo(git_user_name='', git_user_email='')
+    service, _ = _create_service_with_mock_user_context(user_info)
+
+    await service._configure_git_user_settings(mock_workspace)
+
+    # Empty strings are falsy, so no commands should be executed
+    mock_workspace.execute_command.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_configure_git_user_settings_get_user_info_fails(mock_workspace):
+    """Test handling of exception when get_user_info fails."""
+    user_info = MockUserInfo()
+    service, mock_user_context = _create_service_with_mock_user_context(user_info)
+    mock_user_context.get_user_info = AsyncMock(
+        side_effect=Exception('User info error')
+    )
+
+    # Should not raise exception, just log warning
+    await service._configure_git_user_settings(mock_workspace)
+
+    # Verify no git config commands were executed
+    mock_workspace.execute_command.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_configure_git_user_settings_name_command_fails(mock_workspace):
+    """Test handling when git config user.name command fails."""
+    user_info = MockUserInfo(
+        git_user_name='Test User', git_user_email='test@example.com'
+    )
+    service, _ = _create_service_with_mock_user_context(user_info)
+
+    # Make the first command fail (user.name), second succeed (user.email)
+    mock_workspace.execute_command = AsyncMock(
+        side_effect=[
+            MockCommandResult(exit_code=1, stderr='Permission denied'),
+            MockCommandResult(exit_code=0),
+        ]
+    )
+
+    # Should not raise exception
+    await service._configure_git_user_settings(mock_workspace)
+
+    # Verify both commands were still attempted
+    assert mock_workspace.execute_command.call_count == 2
+
+
+@pytest.mark.asyncio
+async def test_configure_git_user_settings_email_command_fails(mock_workspace):
+    """Test handling when git config user.email command fails."""
+    user_info = MockUserInfo(
+        git_user_name='Test User', git_user_email='test@example.com'
+    )
+    service, _ = _create_service_with_mock_user_context(user_info)
+
+    # Make the first command succeed (user.name), second fail (user.email)
+    mock_workspace.execute_command = AsyncMock(
+        side_effect=[
+            MockCommandResult(exit_code=0),
+            MockCommandResult(exit_code=1, stderr='Permission denied'),
+        ]
+    )
+
+    # Should not raise exception
+    await service._configure_git_user_settings(mock_workspace)
+
+    # Verify both commands were still attempted
+    assert mock_workspace.execute_command.call_count == 2
+
+
+@pytest.mark.asyncio
+async def test_configure_git_user_settings_special_characters_in_name(mock_workspace):
+    """Test git user name with special characters."""
+    user_info = MockUserInfo(
+        git_user_name="Test O'Brien", git_user_email='test@example.com'
+    )
+    service, _ = _create_service_with_mock_user_context(user_info)
+
+    await service._configure_git_user_settings(mock_workspace)
+
+    # Verify the name is passed with special characters
+    mock_workspace.execute_command.assert_any_call(
+        'git config --global user.name "Test O\'Brien"', '/workspace/project'
+    )

tests/unit/app_server/test_live_status_app_conversation_service.py

@@ -0,0 +1,721 @@
+"""Unit tests for the methods in LiveStatusAppConversationService."""
+
+from unittest.mock import AsyncMock, Mock, patch
+from uuid import UUID, uuid4
+
+import pytest
+
+from openhands.agent_server.models import SendMessageRequest, StartConversationRequest
+from openhands.app_server.app_conversation.app_conversation_models import AgentType
+from openhands.app_server.app_conversation.live_status_app_conversation_service import (
+    LiveStatusAppConversationService,
+)
+from openhands.app_server.sandbox.sandbox_models import SandboxInfo, SandboxStatus
+from openhands.app_server.user.user_context import UserContext
+from openhands.integrations.provider import ProviderType
+from openhands.sdk import Agent
+from openhands.sdk.conversation.secret_source import LookupSecret, StaticSecret
+from openhands.sdk.llm import LLM
+from openhands.sdk.workspace import LocalWorkspace
+from openhands.sdk.workspace.remote.async_remote_workspace import AsyncRemoteWorkspace
+from openhands.server.types import AppMode
+
+
+class TestLiveStatusAppConversationService:
+    """Test cases for the methods in LiveStatusAppConversationService."""
+
+    def setup_method(self):
+        """Set up test fixtures."""
+        # Create mock dependencies
+        self.mock_user_context = Mock(spec=UserContext)
+        self.mock_jwt_service = Mock()
+        self.mock_sandbox_service = Mock()
+        self.mock_sandbox_spec_service = Mock()
+        self.mock_app_conversation_info_service = Mock()
+        self.mock_app_conversation_start_task_service = Mock()
+        self.mock_event_callback_service = Mock()
+        self.mock_httpx_client = Mock()
+
+        # Create service instance
+        self.service = LiveStatusAppConversationService(
+            init_git_in_empty_workspace=True,
+            user_context=self.mock_user_context,
+            app_conversation_info_service=self.mock_app_conversation_info_service,
+            app_conversation_start_task_service=self.mock_app_conversation_start_task_service,
+            event_callback_service=self.mock_event_callback_service,
+            sandbox_service=self.mock_sandbox_service,
+            sandbox_spec_service=self.mock_sandbox_spec_service,
+            jwt_service=self.mock_jwt_service,
+            sandbox_startup_timeout=30,
+            sandbox_startup_poll_frequency=1,
+            httpx_client=self.mock_httpx_client,
+            web_url='https://test.example.com',
+            access_token_hard_timeout=None,
+            app_mode='test',
+            keycloak_auth_cookie=None,
+        )
+
+        # Mock user info
+        self.mock_user = Mock()
+        self.mock_user.id = 'test_user_123'
+        self.mock_user.llm_model = 'gpt-4'
+        self.mock_user.llm_base_url = 'https://api.openai.com/v1'
+        self.mock_user.llm_api_key = 'test_api_key'
+        self.mock_user.confirmation_mode = False
+        self.mock_user.search_api_key = None  # Default to None
+        self.mock_user.condenser_max_size = None  # Default to None
+
+        # Mock sandbox
+        self.mock_sandbox = Mock(spec=SandboxInfo)
+        self.mock_sandbox.id = uuid4()
+        self.mock_sandbox.status = SandboxStatus.RUNNING
+
+    @pytest.mark.asyncio
+    async def test_setup_secrets_for_git_provider_no_provider(self):
+        """Test _setup_secrets_for_git_provider with no git provider."""
+        # Arrange
+        base_secrets = {'existing': 'secret'}
+        self.mock_user_context.get_secrets.return_value = base_secrets
+
+        # Act
+        result = await self.service._setup_secrets_for_git_provider(
+            None, self.mock_user
+        )
+
+        # Assert
+        assert result == base_secrets
+        self.mock_user_context.get_secrets.assert_called_once()
+
+    @pytest.mark.asyncio
+    async def test_setup_secrets_for_git_provider_with_web_url(self):
+        """Test _setup_secrets_for_git_provider with web URL (creates access token)."""
+        # Arrange
+        base_secrets = {}
+        self.mock_user_context.get_secrets.return_value = base_secrets
+        self.mock_jwt_service.create_jws_token.return_value = 'test_access_token'
+        git_provider = ProviderType.GITHUB
+
+        # Act
+        result = await self.service._setup_secrets_for_git_provider(
+            git_provider, self.mock_user
+        )
+
+        # Assert
+        assert 'GITHUB_TOKEN' in result
+        assert isinstance(result['GITHUB_TOKEN'], LookupSecret)
+        assert (
+            result['GITHUB_TOKEN'].url
+            == 'https://test.example.com/api/v1/webhooks/secrets'
+        )
+        assert result['GITHUB_TOKEN'].headers['X-Access-Token'] == 'test_access_token'
+
+        self.mock_jwt_service.create_jws_token.assert_called_once_with(
+            payload={
+                'user_id': self.mock_user.id,
+                'provider_type': git_provider.value,
+            },
+            expires_in=None,
+        )
+
+    @pytest.mark.asyncio
+    async def test_setup_secrets_for_git_provider_with_saas_mode(self):
+        """Test _setup_secrets_for_git_provider with SaaS mode (includes keycloak cookie)."""
+        # Arrange
+        self.service.app_mode = 'saas'
+        self.service.keycloak_auth_cookie = 'test_cookie'
+        base_secrets = {}
+        self.mock_user_context.get_secrets.return_value = base_secrets
+        self.mock_jwt_service.create_jws_token.return_value = 'test_access_token'
+        git_provider = ProviderType.GITLAB
+
+        # Act
+        result = await self.service._setup_secrets_for_git_provider(
+            git_provider, self.mock_user
+        )
+
+        # Assert
+        assert 'GITLAB_TOKEN' in result
+        lookup_secret = result['GITLAB_TOKEN']
+        assert isinstance(lookup_secret, LookupSecret)
+        assert 'Cookie' in lookup_secret.headers
+        assert lookup_secret.headers['Cookie'] == 'keycloak_auth=test_cookie'
+
+    @pytest.mark.asyncio
+    async def test_setup_secrets_for_git_provider_without_web_url(self):
+        """Test _setup_secrets_for_git_provider without web URL (uses static token)."""
+        # Arrange
+        self.service.web_url = None
+        base_secrets = {}
+        self.mock_user_context.get_secrets.return_value = base_secrets
+        self.mock_user_context.get_latest_token.return_value = 'static_token_value'
+        git_provider = ProviderType.GITHUB
+
+        # Act
+        result = await self.service._setup_secrets_for_git_provider(
+            git_provider, self.mock_user
+        )
+
+        # Assert
+        assert 'GITHUB_TOKEN' in result
+        assert isinstance(result['GITHUB_TOKEN'], StaticSecret)
+        assert result['GITHUB_TOKEN'].value.get_secret_value() == 'static_token_value'
+        self.mock_user_context.get_latest_token.assert_called_once_with(git_provider)
+
+    @pytest.mark.asyncio
+    async def test_setup_secrets_for_git_provider_no_static_token(self):
+        """Test _setup_secrets_for_git_provider when no static token is available."""
+        # Arrange
+        self.service.web_url = None
+        base_secrets = {}
+        self.mock_user_context.get_secrets.return_value = base_secrets
+        self.mock_user_context.get_latest_token.return_value = None
+        git_provider = ProviderType.GITHUB
+
+        # Act
+        result = await self.service._setup_secrets_for_git_provider(
+            git_provider, self.mock_user
+        )
+
+        # Assert
+        assert 'GITHUB_TOKEN' not in result
+        assert result == base_secrets
+
+    @pytest.mark.asyncio
+    async def test_configure_llm_and_mcp_with_custom_model(self):
+        """Test _configure_llm_and_mcp with custom LLM model."""
+        # Arrange
+        custom_model = 'gpt-3.5-turbo'
+        self.mock_user_context.get_mcp_api_key.return_value = 'mcp_api_key'
+
+        # Act
+        llm, mcp_config = await self.service._configure_llm_and_mcp(
+            self.mock_user, custom_model
+        )
+
+        # Assert
+        assert isinstance(llm, LLM)
+        assert llm.model == custom_model
+        assert llm.base_url == self.mock_user.llm_base_url
+        assert llm.api_key.get_secret_value() == self.mock_user.llm_api_key
+        assert llm.usage_id == 'agent'
+
+        assert 'default' in mcp_config
+        assert mcp_config['default']['url'] == 'https://test.example.com/mcp/mcp'
+        assert mcp_config['default']['headers']['X-Session-API-Key'] == 'mcp_api_key'
+
+    @pytest.mark.asyncio
+    async def test_configure_llm_and_mcp_with_user_default_model(self):
+        """Test _configure_llm_and_mcp using user's default model."""
+        # Arrange
+        self.mock_user_context.get_mcp_api_key.return_value = None
+
+        # Act
+        llm, mcp_config = await self.service._configure_llm_and_mcp(
+            self.mock_user, None
+        )
+
+        # Assert
+        assert llm.model == self.mock_user.llm_model
+        assert 'default' in mcp_config
+        assert 'headers' not in mcp_config['default']
+
+    @pytest.mark.asyncio
+    async def test_configure_llm_and_mcp_without_web_url(self):
+        """Test _configure_llm_and_mcp without web URL (no MCP config)."""
+        # Arrange
+        self.service.web_url = None
+
+        # Act
+        llm, mcp_config = await self.service._configure_llm_and_mcp(
+            self.mock_user, None
+        )
+
+        # Assert
+        assert isinstance(llm, LLM)
+        assert mcp_config == {}
+
+    @pytest.mark.asyncio
+    async def test_configure_llm_and_mcp_tavily_with_user_search_api_key(self):
+        """Test _configure_llm_and_mcp adds tavily when user has search_api_key."""
+        # Arrange
+        from pydantic import SecretStr
+
+        self.mock_user.search_api_key = SecretStr('user_search_key')
+        self.mock_user_context.get_mcp_api_key.return_value = 'mcp_api_key'
+
+        # Act
+        llm, mcp_config = await self.service._configure_llm_and_mcp(
+            self.mock_user, None
+        )
+
+        # Assert
+        assert isinstance(llm, LLM)
+        assert 'default' in mcp_config
+        assert 'tavily' in mcp_config
+        assert (
+            mcp_config['tavily']['url']
+            == 'https://mcp.tavily.com/mcp/?tavilyApiKey=user_search_key'
+        )
+
+    @pytest.mark.asyncio
+    async def test_configure_llm_and_mcp_tavily_with_env_tavily_key(self):
+        """Test _configure_llm_and_mcp adds tavily when service has tavily_api_key."""
+        # Arrange
+        self.service.tavily_api_key = 'env_tavily_key'
+        self.mock_user_context.get_mcp_api_key.return_value = None
+
+        # Act
+        llm, mcp_config = await self.service._configure_llm_and_mcp(
+            self.mock_user, None
+        )
+
+        # Assert
+        assert isinstance(llm, LLM)
+        assert 'default' in mcp_config
+        assert 'tavily' in mcp_config
+        assert (
+            mcp_config['tavily']['url']
+            == 'https://mcp.tavily.com/mcp/?tavilyApiKey=env_tavily_key'
+        )
+
+    @pytest.mark.asyncio
+    async def test_configure_llm_and_mcp_tavily_user_key_takes_precedence(self):
+        """Test _configure_llm_and_mcp user search_api_key takes precedence over env key."""
+        # Arrange
+        from pydantic import SecretStr
+
+        self.mock_user.search_api_key = SecretStr('user_search_key')
+        self.service.tavily_api_key = 'env_tavily_key'
+        self.mock_user_context.get_mcp_api_key.return_value = None
+
+        # Act
+        llm, mcp_config = await self.service._configure_llm_and_mcp(
+            self.mock_user, None
+        )
+
+        # Assert
+        assert isinstance(llm, LLM)
+        assert 'tavily' in mcp_config
+        assert (
+            mcp_config['tavily']['url']
+            == 'https://mcp.tavily.com/mcp/?tavilyApiKey=user_search_key'
+        )
+
+    @pytest.mark.asyncio
+    async def test_configure_llm_and_mcp_no_tavily_without_keys(self):
+        """Test _configure_llm_and_mcp does not add tavily when no keys are available."""
+        # Arrange
+        self.mock_user.search_api_key = None
+        self.service.tavily_api_key = None
+        self.mock_user_context.get_mcp_api_key.return_value = None
+
+        # Act
+        llm, mcp_config = await self.service._configure_llm_and_mcp(
+            self.mock_user, None
+        )
+
+        # Assert
+        assert isinstance(llm, LLM)
+        assert 'default' in mcp_config
+        assert 'tavily' not in mcp_config
+
+    @pytest.mark.asyncio
+    async def test_configure_llm_and_mcp_saas_mode_no_tavily_without_user_key(self):
+        """Test _configure_llm_and_mcp does not add tavily in SAAS mode without user search_api_key.
+
+        In SAAS mode, the global tavily_api_key should not be passed to the service instance,
+        so tavily should only be added if the user has their own search_api_key.
+        """
+        # Arrange - simulate SAAS mode where no global tavily key is available
+        self.service.app_mode = AppMode.SAAS.value
+        self.service.tavily_api_key = None  # In SAAS mode, this should be None
+        self.mock_user.search_api_key = None
+        self.mock_user_context.get_mcp_api_key.return_value = None
+
+        # Act
+        llm, mcp_config = await self.service._configure_llm_and_mcp(
+            self.mock_user, None
+        )
+
+        # Assert
+        assert isinstance(llm, LLM)
+        assert 'default' in mcp_config
+        assert 'tavily' not in mcp_config
+
+    @pytest.mark.asyncio
+    async def test_configure_llm_and_mcp_saas_mode_with_user_search_key(self):
+        """Test _configure_llm_and_mcp adds tavily in SAAS mode when user has search_api_key.
+
+        Even in SAAS mode, if the user has their own search_api_key, tavily should be added.
+        """
+        # Arrange - simulate SAAS mode with user having their own search key
+        from pydantic import SecretStr
+
+        self.service.app_mode = AppMode.SAAS.value
+        self.service.tavily_api_key = None  # In SAAS mode, this should be None
+        self.mock_user.search_api_key = SecretStr('user_search_key')
+        self.mock_user_context.get_mcp_api_key.return_value = None
+
+        # Act
+        llm, mcp_config = await self.service._configure_llm_and_mcp(
+            self.mock_user, None
+        )
+
+        # Assert
+        assert isinstance(llm, LLM)
+        assert 'default' in mcp_config
+        assert 'tavily' in mcp_config
+        assert (
+            mcp_config['tavily']['url']
+            == 'https://mcp.tavily.com/mcp/?tavilyApiKey=user_search_key'
+        )
+
+    @pytest.mark.asyncio
+    async def test_configure_llm_and_mcp_tavily_with_empty_user_search_key(self):
+        """Test _configure_llm_and_mcp handles empty user search_api_key correctly."""
+        # Arrange
+        from pydantic import SecretStr
+
+        self.mock_user.search_api_key = SecretStr('')  # Empty string
+        self.service.tavily_api_key = 'env_tavily_key'
+        self.mock_user_context.get_mcp_api_key.return_value = None
+
+        # Act
+        llm, mcp_config = await self.service._configure_llm_and_mcp(
+            self.mock_user, None
+        )
+
+        # Assert
+        assert isinstance(llm, LLM)
+        assert 'tavily' in mcp_config
+        # Should fall back to env key since user key is empty
+        assert (
+            mcp_config['tavily']['url']
+            == 'https://mcp.tavily.com/mcp/?tavilyApiKey=env_tavily_key'
+        )
+
+    @pytest.mark.asyncio
+    async def test_configure_llm_and_mcp_tavily_with_whitespace_user_search_key(self):
+        """Test _configure_llm_and_mcp handles whitespace-only user search_api_key correctly."""
+        # Arrange
+        from pydantic import SecretStr
+
+        self.mock_user.search_api_key = SecretStr('   ')  # Whitespace only
+        self.service.tavily_api_key = 'env_tavily_key'
+        self.mock_user_context.get_mcp_api_key.return_value = None
+
+        # Act
+        llm, mcp_config = await self.service._configure_llm_and_mcp(
+            self.mock_user, None
+        )
+
+        # Assert
+        assert isinstance(llm, LLM)
+        assert 'tavily' in mcp_config
+        # Should fall back to env key since user key is whitespace only
+        assert (
+            mcp_config['tavily']['url']
+            == 'https://mcp.tavily.com/mcp/?tavilyApiKey=env_tavily_key'
+        )
+
+    @patch(
+        'openhands.app_server.app_conversation.live_status_app_conversation_service.get_planning_tools'
+    )
+    @patch(
+        'openhands.app_server.app_conversation.app_conversation_service_base.AppConversationServiceBase._create_condenser'
+    )
+    @patch(
+        'openhands.app_server.app_conversation.live_status_app_conversation_service.format_plan_structure'
+    )
+    def test_create_agent_with_context_planning_agent(
+        self, mock_format_plan, mock_create_condenser, mock_get_tools
+    ):
+        """Test _create_agent_with_context for planning agent type."""
+        # Arrange
+        mock_llm = Mock(spec=LLM)
+        mock_llm.model_copy.return_value = mock_llm
+        mock_get_tools.return_value = []
+        mock_condenser = Mock()
+        mock_create_condenser.return_value = mock_condenser
+        mock_format_plan.return_value = 'test_plan_structure'
+        mcp_config = {'default': {'url': 'test'}}
+        system_message_suffix = 'Test suffix'
+
+        # Act
+        with patch(
+            'openhands.app_server.app_conversation.live_status_app_conversation_service.Agent'
+        ) as mock_agent_class:
+            mock_agent_instance = Mock()
+            mock_agent_instance.model_copy.return_value = mock_agent_instance
+            mock_agent_class.return_value = mock_agent_instance
+
+            self.service._create_agent_with_context(
+                mock_llm,
+                AgentType.PLAN,
+                system_message_suffix,
+                mcp_config,
+                self.mock_user.condenser_max_size,
+            )
+
+            # Assert
+            mock_agent_class.assert_called_once()
+            call_kwargs = mock_agent_class.call_args[1]
+            assert call_kwargs['llm'] == mock_llm
+            assert call_kwargs['system_prompt_filename'] == 'system_prompt_planning.j2'
+            assert (
+                call_kwargs['system_prompt_kwargs']['plan_structure']
+                == 'test_plan_structure'
+            )
+            assert call_kwargs['mcp_config'] == mcp_config
+            assert call_kwargs['security_analyzer'] is None
+            assert call_kwargs['condenser'] == mock_condenser
+            mock_create_condenser.assert_called_once_with(
+                mock_llm, AgentType.PLAN, self.mock_user.condenser_max_size
+            )
+
+    @patch(
+        'openhands.app_server.app_conversation.live_status_app_conversation_service.get_default_tools'
+    )
+    @patch(
+        'openhands.app_server.app_conversation.app_conversation_service_base.AppConversationServiceBase._create_condenser'
+    )
+    def test_create_agent_with_context_default_agent(
+        self, mock_create_condenser, mock_get_tools
+    ):
+        """Test _create_agent_with_context for default agent type."""
+        # Arrange
+        mock_llm = Mock(spec=LLM)
+        mock_llm.model_copy.return_value = mock_llm
+        mock_get_tools.return_value = []
+        mock_condenser = Mock()
+        mock_create_condenser.return_value = mock_condenser
+        mcp_config = {'default': {'url': 'test'}}
+
+        # Act
+        with patch(
+            'openhands.app_server.app_conversation.live_status_app_conversation_service.Agent'
+        ) as mock_agent_class:
+            mock_agent_instance = Mock()
+            mock_agent_instance.model_copy.return_value = mock_agent_instance
+            mock_agent_class.return_value = mock_agent_instance
+
+            self.service._create_agent_with_context(
+                mock_llm,
+                AgentType.DEFAULT,
+                None,
+                mcp_config,
+                self.mock_user.condenser_max_size,
+            )
+
+            # Assert
+            mock_agent_class.assert_called_once()
+            call_kwargs = mock_agent_class.call_args[1]
+            assert call_kwargs['llm'] == mock_llm
+            assert call_kwargs['system_prompt_kwargs']['cli_mode'] is False
+            assert call_kwargs['mcp_config'] == mcp_config
+            assert call_kwargs['condenser'] == mock_condenser
+            mock_get_tools.assert_called_once_with(enable_browser=True)
+            mock_create_condenser.assert_called_once_with(
+                mock_llm, AgentType.DEFAULT, self.mock_user.condenser_max_size
+            )
+
+    @pytest.mark.asyncio
+    @patch(
+        'openhands.app_server.app_conversation.live_status_app_conversation_service.ExperimentManagerImpl'
+    )
+    async def test_finalize_conversation_request_with_skills(
+        self, mock_experiment_manager
+    ):
+        """Test _finalize_conversation_request with skills loading."""
+        # Arrange
+        mock_agent = Mock(spec=Agent)
+        mock_updated_agent = Mock(spec=Agent)
+        mock_experiment_manager.run_agent_variant_tests__v1.return_value = (
+            mock_updated_agent
+        )
+
+        conversation_id = uuid4()
+        workspace = LocalWorkspace(working_dir='/test')
+        initial_message = Mock(spec=SendMessageRequest)
+        secrets = {'test': StaticSecret(value='secret')}
+        remote_workspace = Mock(spec=AsyncRemoteWorkspace)
+
+        # Mock the skills loading method
+        self.service._load_skills_and_update_agent = AsyncMock(
+            return_value=mock_updated_agent
+        )
+
+        # Act
+        result = await self.service._finalize_conversation_request(
+            mock_agent,
+            conversation_id,
+            self.mock_user,
+            workspace,
+            initial_message,
+            secrets,
+            self.mock_sandbox,
+            remote_workspace,
+            'test_repo',
+            '/test/dir',
+        )
+
+        # Assert
+        assert isinstance(result, StartConversationRequest)
+        assert result.conversation_id == conversation_id
+        assert result.agent == mock_updated_agent
+        assert result.workspace == workspace
+        assert result.initial_message == initial_message
+        assert result.secrets == secrets
+
+        mock_experiment_manager.run_agent_variant_tests__v1.assert_called_once_with(
+            self.mock_user.id, conversation_id, mock_agent
+        )
+        self.service._load_skills_and_update_agent.assert_called_once_with(
+            self.mock_sandbox,
+            mock_updated_agent,
+            remote_workspace,
+            'test_repo',
+            '/test/dir',
+        )
+
+    @pytest.mark.asyncio
+    @patch(
+        'openhands.app_server.app_conversation.live_status_app_conversation_service.ExperimentManagerImpl'
+    )
+    async def test_finalize_conversation_request_without_skills(
+        self, mock_experiment_manager
+    ):
+        """Test _finalize_conversation_request without remote workspace (no skills)."""
+        # Arrange
+        mock_agent = Mock(spec=Agent)
+        mock_updated_agent = Mock(spec=Agent)
+        mock_experiment_manager.run_agent_variant_tests__v1.return_value = (
+            mock_updated_agent
+        )
+
+        workspace = LocalWorkspace(working_dir='/test')
+        secrets = {'test': StaticSecret(value='secret')}
+
+        # Act
+        result = await self.service._finalize_conversation_request(
+            mock_agent,
+            None,
+            self.mock_user,
+            workspace,
+            None,
+            secrets,
+            self.mock_sandbox,
+            None,
+            None,
+            '/test/dir',
+        )
+
+        # Assert
+        assert isinstance(result, StartConversationRequest)
+        assert isinstance(result.conversation_id, UUID)
+        assert result.agent == mock_updated_agent
+        mock_experiment_manager.run_agent_variant_tests__v1.assert_called_once()
+
+    @pytest.mark.asyncio
+    @patch(
+        'openhands.app_server.app_conversation.live_status_app_conversation_service.ExperimentManagerImpl'
+    )
+    async def test_finalize_conversation_request_skills_loading_fails(
+        self, mock_experiment_manager
+    ):
+        """Test _finalize_conversation_request when skills loading fails."""
+        # Arrange
+        mock_agent = Mock(spec=Agent)
+        mock_updated_agent = Mock(spec=Agent)
+        mock_experiment_manager.run_agent_variant_tests__v1.return_value = (
+            mock_updated_agent
+        )
+
+        workspace = LocalWorkspace(working_dir='/test')
+        secrets = {'test': StaticSecret(value='secret')}
+        remote_workspace = Mock(spec=AsyncRemoteWorkspace)
+
+        # Mock skills loading to raise an exception
+        self.service._load_skills_and_update_agent = AsyncMock(
+            side_effect=Exception('Skills loading failed')
+        )
+
+        # Act
+        with patch(
+            'openhands.app_server.app_conversation.live_status_app_conversation_service._logger'
+        ) as mock_logger:
+            result = await self.service._finalize_conversation_request(
+                mock_agent,
+                None,
+                self.mock_user,
+                workspace,
+                None,
+                secrets,
+                self.mock_sandbox,
+                remote_workspace,
+                'test_repo',
+                '/test/dir',
+            )
+
+            # Assert
+            assert isinstance(result, StartConversationRequest)
+            assert (
+                result.agent == mock_updated_agent
+            )  # Should still use the experiment-modified agent
+            mock_logger.warning.assert_called_once()
+
+    @pytest.mark.asyncio
+    async def test_build_start_conversation_request_for_user_integration(self):
+        """Test the main _build_start_conversation_request_for_user method integration."""
+        # Arrange
+        self.mock_user_context.get_user_info.return_value = self.mock_user
+
+        # Mock all the helper methods
+        mock_secrets = {'GITHUB_TOKEN': Mock()}
+        mock_llm = Mock(spec=LLM)
+        mock_mcp_config = {'default': {'url': 'test'}}
+        mock_agent = Mock(spec=Agent)
+        mock_final_request = Mock(spec=StartConversationRequest)
+
+        self.service._setup_secrets_for_git_provider = AsyncMock(
+            return_value=mock_secrets
+        )
+        self.service._configure_llm_and_mcp = AsyncMock(
+            return_value=(mock_llm, mock_mcp_config)
+        )
+        self.service._create_agent_with_context = Mock(return_value=mock_agent)
+        self.service._finalize_conversation_request = AsyncMock(
+            return_value=mock_final_request
+        )
+
+        # Act
+        result = await self.service._build_start_conversation_request_for_user(
+            sandbox=self.mock_sandbox,
+            initial_message=None,
+            system_message_suffix='Test suffix',
+            git_provider=ProviderType.GITHUB,
+            working_dir='/test/dir',
+            agent_type=AgentType.DEFAULT,
+            llm_model='gpt-4',
+            conversation_id=None,
+            remote_workspace=None,
+            selected_repository='test/repo',
+        )
+
+        # Assert
+        assert result == mock_final_request
+
+        self.service._setup_secrets_for_git_provider.assert_called_once_with(
+            ProviderType.GITHUB, self.mock_user
+        )
+        self.service._configure_llm_and_mcp.assert_called_once_with(
+            self.mock_user, 'gpt-4'
+        )
+        self.service._create_agent_with_context.assert_called_once_with(
+            mock_llm,
+            AgentType.DEFAULT,
+            'Test suffix',
+            mock_mcp_config,
+            self.mock_user.condenser_max_size,
+        )
+        self.service._finalize_conversation_request.assert_called_once()

tests/unit/app_server/test_webhook_router_stats.py

@@ -0,0 +1,615 @@
+"""Tests for stats event processing in webhook_router.
+
+This module tests the stats event processing functionality introduced for
+updating conversation statistics from ConversationStateUpdateEvent events.
+"""
+
+from datetime import datetime, timezone
+from typing import AsyncGenerator
+from unittest.mock import AsyncMock, MagicMock, patch
+from uuid import uuid4
+
+import pytest
+from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
+from sqlalchemy.pool import StaticPool
+
+from openhands.app_server.app_conversation.app_conversation_models import (
+    AppConversationInfo,
+)
+from openhands.app_server.app_conversation.sql_app_conversation_info_service import (
+    SQLAppConversationInfoService,
+    StoredConversationMetadata,
+)
+from openhands.app_server.user.specifiy_user_context import SpecifyUserContext
+from openhands.app_server.utils.sql_utils import Base
+from openhands.sdk.conversation.conversation_stats import ConversationStats
+from openhands.sdk.event import ConversationStateUpdateEvent
+from openhands.sdk.llm.utils.metrics import Metrics, TokenUsage
+
+# ---------------------------------------------------------------------------
+# Fixtures
+# ---------------------------------------------------------------------------
+
+
+@pytest.fixture
+async def async_engine():
+    """Create an async SQLite engine for testing."""
+    engine = create_async_engine(
+        'sqlite+aiosqlite:///:memory:',
+        poolclass=StaticPool,
+        connect_args={'check_same_thread': False},
+        echo=False,
+    )
+
+    # Create all tables
+    async with engine.begin() as conn:
+        await conn.run_sync(Base.metadata.create_all)
+
+    yield engine
+
+    await engine.dispose()
+
+
+@pytest.fixture
+async def async_session(async_engine) -> AsyncGenerator[AsyncSession, None]:
+    """Create an async session for testing."""
+    async_session_maker = async_sessionmaker(
+        async_engine, class_=AsyncSession, expire_on_commit=False
+    )
+
+    async with async_session_maker() as db_session:
+        yield db_session
+
+
+@pytest.fixture
+def service(async_session) -> SQLAppConversationInfoService:
+    """Create a SQLAppConversationInfoService instance for testing."""
+    return SQLAppConversationInfoService(
+        db_session=async_session, user_context=SpecifyUserContext(user_id=None)
+    )
+
+
+@pytest.fixture
+async def v1_conversation_metadata(async_session, service):
+    """Create a V1 conversation metadata record for testing."""
+    conversation_id = uuid4()
+    stored = StoredConversationMetadata(
+        conversation_id=str(conversation_id),
+        user_id='test_user_123',
+        sandbox_id='sandbox_123',
+        conversation_version='V1',
+        title='Test Conversation',
+        accumulated_cost=0.0,
+        prompt_tokens=0,
+        completion_tokens=0,
+        cache_read_tokens=0,
+        cache_write_tokens=0,
+        reasoning_tokens=0,
+        context_window=0,
+        per_turn_token=0,
+        created_at=datetime.now(timezone.utc),
+        last_updated_at=datetime.now(timezone.utc),
+    )
+    async_session.add(stored)
+    await async_session.commit()
+    return conversation_id, stored
+
+
+@pytest.fixture
+def stats_event_with_dict_value():
+    """Create a ConversationStateUpdateEvent with dict value."""
+    event_value = {
+        'usage_to_metrics': {
+            'agent': {
+                'accumulated_cost': 0.03411525,
+                'max_budget_per_task': None,
+                'accumulated_token_usage': {
+                    'prompt_tokens': 8770,
+                    'completion_tokens': 82,
+                    'cache_read_tokens': 0,
+                    'cache_write_tokens': 8767,
+                    'reasoning_tokens': 0,
+                    'context_window': 0,
+                    'per_turn_token': 8852,
+                },
+            },
+            'condenser': {
+                'accumulated_cost': 0.0,
+                'accumulated_token_usage': {
+                    'prompt_tokens': 0,
+                    'completion_tokens': 0,
+                },
+            },
+        }
+    }
+    return ConversationStateUpdateEvent(key='stats', value=event_value)
+
+
+@pytest.fixture
+def stats_event_with_object_value():
+    """Create a ConversationStateUpdateEvent with object value."""
+    event_value = MagicMock()
+    event_value.usage_to_metrics = {
+        'agent': {
+            'accumulated_cost': 0.05,
+            'accumulated_token_usage': {
+                'prompt_tokens': 1000,
+                'completion_tokens': 100,
+            },
+        }
+    }
+    return ConversationStateUpdateEvent(key='stats', value=event_value)
+
+
+@pytest.fixture
+def stats_event_no_usage_to_metrics():
+    """Create a ConversationStateUpdateEvent without usage_to_metrics."""
+    event_value = {'some_other_key': 'value'}
+    return ConversationStateUpdateEvent(key='stats', value=event_value)
+
+
+# ---------------------------------------------------------------------------
+# Tests for update_conversation_statistics
+# ---------------------------------------------------------------------------
+
+
+class TestUpdateConversationStatistics:
+    """Test the update_conversation_statistics method."""
+
+    @pytest.mark.asyncio
+    async def test_update_statistics_success(
+        self, service, async_session, v1_conversation_metadata
+    ):
+        """Test successfully updating conversation statistics."""
+        conversation_id, stored = v1_conversation_metadata
+
+        agent_metrics = Metrics(
+            model_name='test-model',
+            accumulated_cost=0.03411525,
+            max_budget_per_task=10.0,
+            accumulated_token_usage=TokenUsage(
+                model='test-model',
+                prompt_tokens=8770,
+                completion_tokens=82,
+                cache_read_tokens=0,
+                cache_write_tokens=8767,
+                reasoning_tokens=0,
+                context_window=0,
+                per_turn_token=8852,
+            ),
+        )
+        stats = ConversationStats(usage_to_metrics={'agent': agent_metrics})
+
+        await service.update_conversation_statistics(conversation_id, stats)
+
+        # Verify the update
+        await async_session.refresh(stored)
+        assert stored.accumulated_cost == 0.03411525
+        assert stored.max_budget_per_task == 10.0
+        assert stored.prompt_tokens == 8770
+        assert stored.completion_tokens == 82
+        assert stored.cache_read_tokens == 0
+        assert stored.cache_write_tokens == 8767
+        assert stored.reasoning_tokens == 0
+        assert stored.context_window == 0
+        assert stored.per_turn_token == 8852
+        assert stored.last_updated_at is not None
+
+    @pytest.mark.asyncio
+    async def test_update_statistics_partial_update(
+        self, service, async_session, v1_conversation_metadata
+    ):
+        """Test updating only some statistics fields."""
+        conversation_id, stored = v1_conversation_metadata
+
+        # Set initial values
+        stored.accumulated_cost = 0.01
+        stored.prompt_tokens = 100
+        await async_session.commit()
+
+        agent_metrics = Metrics(
+            model_name='test-model',
+            accumulated_cost=0.05,
+            accumulated_token_usage=TokenUsage(
+                model='test-model',
+                prompt_tokens=200,
+                completion_tokens=0,  # Default value
+            ),
+        )
+        stats = ConversationStats(usage_to_metrics={'agent': agent_metrics})
+
+        await service.update_conversation_statistics(conversation_id, stats)
+
+        # Verify updated fields
+        await async_session.refresh(stored)
+        assert stored.accumulated_cost == 0.05
+        assert stored.prompt_tokens == 200
+        # completion_tokens should remain unchanged (not None in stats)
+        assert stored.completion_tokens == 0
+
+    @pytest.mark.asyncio
+    async def test_update_statistics_no_agent_metrics(
+        self, service, v1_conversation_metadata
+    ):
+        """Test that update is skipped when no agent metrics are present."""
+        conversation_id, stored = v1_conversation_metadata
+        original_cost = stored.accumulated_cost
+
+        condenser_metrics = Metrics(
+            model_name='test-model',
+            accumulated_cost=0.1,
+        )
+        stats = ConversationStats(usage_to_metrics={'condenser': condenser_metrics})
+
+        await service.update_conversation_statistics(conversation_id, stats)
+
+        # Verify no update occurred
+        assert stored.accumulated_cost == original_cost
+
+    @pytest.mark.asyncio
+    async def test_update_statistics_conversation_not_found(self, service):
+        """Test that update is skipped when conversation doesn't exist."""
+        nonexistent_id = uuid4()
+        agent_metrics = Metrics(
+            model_name='test-model',
+            accumulated_cost=0.1,
+        )
+        stats = ConversationStats(usage_to_metrics={'agent': agent_metrics})
+
+        # Should not raise an exception
+        await service.update_conversation_statistics(nonexistent_id, stats)
+
+    @pytest.mark.asyncio
+    async def test_update_statistics_v0_conversation_skipped(
+        self, service, async_session
+    ):
+        """Test that V0 conversations are skipped."""
+        conversation_id = uuid4()
+        stored = StoredConversationMetadata(
+            conversation_id=str(conversation_id),
+            user_id='test_user_123',
+            sandbox_id='sandbox_123',
+            conversation_version='V0',  # V0 conversation
+            title='V0 Conversation',
+            accumulated_cost=0.0,
+            created_at=datetime.now(timezone.utc),
+            last_updated_at=datetime.now(timezone.utc),
+        )
+        async_session.add(stored)
+        await async_session.commit()
+
+        original_cost = stored.accumulated_cost
+
+        agent_metrics = Metrics(
+            model_name='test-model',
+            accumulated_cost=0.1,
+        )
+        stats = ConversationStats(usage_to_metrics={'agent': agent_metrics})
+
+        await service.update_conversation_statistics(conversation_id, stats)
+
+        # Verify no update occurred
+        await async_session.refresh(stored)
+        assert stored.accumulated_cost == original_cost
+
+    @pytest.mark.asyncio
+    async def test_update_statistics_with_none_values(
+        self, service, async_session, v1_conversation_metadata
+    ):
+        """Test that None values in stats don't overwrite existing values."""
+        conversation_id, stored = v1_conversation_metadata
+
+        # Set initial values
+        stored.accumulated_cost = 0.01
+        stored.max_budget_per_task = 5.0
+        stored.prompt_tokens = 100
+        await async_session.commit()
+
+        agent_metrics = Metrics(
+            model_name='test-model',
+            accumulated_cost=0.05,
+            max_budget_per_task=None,  # None value
+            accumulated_token_usage=TokenUsage(
+                model='test-model',
+                prompt_tokens=200,
+                completion_tokens=0,  # Default value (None is not valid for int)
+            ),
+        )
+        stats = ConversationStats(usage_to_metrics={'agent': agent_metrics})
+
+        await service.update_conversation_statistics(conversation_id, stats)
+
+        # Verify updated fields and that None values didn't overwrite
+        await async_session.refresh(stored)
+        assert stored.accumulated_cost == 0.05
+        assert stored.max_budget_per_task == 5.0  # Should remain unchanged
+        assert stored.prompt_tokens == 200
+        assert (
+            stored.completion_tokens == 0
+        )  # Should remain unchanged (was 0, None doesn't update)
+
+
+# ---------------------------------------------------------------------------
+# Tests for process_stats_event
+# ---------------------------------------------------------------------------
+
+
+class TestProcessStatsEvent:
+    """Test the process_stats_event method."""
+
+    @pytest.mark.asyncio
+    async def test_process_stats_event_with_dict_value(
+        self,
+        service,
+        async_session,
+        stats_event_with_dict_value,
+        v1_conversation_metadata,
+    ):
+        """Test processing stats event with dict value."""
+        conversation_id, stored = v1_conversation_metadata
+
+        await service.process_stats_event(stats_event_with_dict_value, conversation_id)
+
+        # Verify the update occurred
+        await async_session.refresh(stored)
+        assert stored.accumulated_cost == 0.03411525
+        assert stored.prompt_tokens == 8770
+        assert stored.completion_tokens == 82
+
+    @pytest.mark.asyncio
+    async def test_process_stats_event_with_object_value(
+        self,
+        service,
+        async_session,
+        stats_event_with_object_value,
+        v1_conversation_metadata,
+    ):
+        """Test processing stats event with object value."""
+        conversation_id, stored = v1_conversation_metadata
+
+        await service.process_stats_event(
+            stats_event_with_object_value, conversation_id
+        )
+
+        # Verify the update occurred
+        await async_session.refresh(stored)
+        assert stored.accumulated_cost == 0.05
+        assert stored.prompt_tokens == 1000
+        assert stored.completion_tokens == 100
+
+    @pytest.mark.asyncio
+    async def test_process_stats_event_no_usage_to_metrics(
+        self,
+        service,
+        async_session,
+        stats_event_no_usage_to_metrics,
+        v1_conversation_metadata,
+    ):
+        """Test processing stats event without usage_to_metrics."""
+        conversation_id, stored = v1_conversation_metadata
+        original_cost = stored.accumulated_cost
+
+        await service.process_stats_event(
+            stats_event_no_usage_to_metrics, conversation_id
+        )
+
+        # Verify update_conversation_statistics was NOT called
+        await async_session.refresh(stored)
+        assert stored.accumulated_cost == original_cost
+
+    @pytest.mark.asyncio
+    async def test_process_stats_event_service_error_handled(
+        self, service, stats_event_with_dict_value
+    ):
+        """Test that errors from service are caught and logged."""
+        conversation_id = uuid4()
+
+        # Should not raise an exception
+        with (
+            patch.object(
+                service,
+                'update_conversation_statistics',
+                side_effect=Exception('Database error'),
+            ),
+            patch(
+                'openhands.app_server.app_conversation.sql_app_conversation_info_service.logger'
+            ) as mock_logger,
+        ):
+            await service.process_stats_event(
+                stats_event_with_dict_value, conversation_id
+            )
+
+            # Verify error was logged
+            mock_logger.exception.assert_called_once()
+
+    @pytest.mark.asyncio
+    async def test_process_stats_event_empty_usage_to_metrics(
+        self, service, async_session, v1_conversation_metadata
+    ):
+        """Test processing stats event with empty usage_to_metrics."""
+        conversation_id, stored = v1_conversation_metadata
+        original_cost = stored.accumulated_cost
+
+        # Create event with empty usage_to_metrics
+        event = ConversationStateUpdateEvent(
+            key='stats', value={'usage_to_metrics': {}}
+        )
+
+        await service.process_stats_event(event, conversation_id)
+
+        # Empty dict is falsy, so update_conversation_statistics should NOT be called
+        await async_session.refresh(stored)
+        assert stored.accumulated_cost == original_cost
+
+
+# ---------------------------------------------------------------------------
+# Integration tests for on_event endpoint
+# ---------------------------------------------------------------------------
+
+
+class TestOnEventStatsProcessing:
+    """Test stats event processing in the on_event endpoint."""
+
+    @pytest.mark.asyncio
+    async def test_on_event_processes_stats_events(self):
+        """Test that on_event processes stats events."""
+        from openhands.app_server.event_callback.webhook_router import on_event
+        from openhands.app_server.sandbox.sandbox_models import (
+            SandboxInfo,
+            SandboxStatus,
+        )
+
+        conversation_id = uuid4()
+        sandbox_id = 'sandbox_123'
+
+        # Create stats event
+        stats_event = ConversationStateUpdateEvent(
+            key='stats',
+            value={
+                'usage_to_metrics': {
+                    'agent': {
+                        'accumulated_cost': 0.1,
+                        'accumulated_token_usage': {
+                            'prompt_tokens': 1000,
+                        },
+                    }
+                }
+            },
+        )
+
+        # Create non-stats event
+        other_event = ConversationStateUpdateEvent(
+            key='execution_status', value='running'
+        )
+
+        events = [stats_event, other_event]
+
+        # Mock dependencies
+        mock_sandbox = SandboxInfo(
+            id=sandbox_id,
+            status=SandboxStatus.RUNNING,
+            session_api_key='test_key',
+            created_by_user_id='user_123',
+            sandbox_spec_id='spec_123',
+        )
+
+        mock_app_conversation_info = AppConversationInfo(
+            id=conversation_id,
+            sandbox_id=sandbox_id,
+            created_by_user_id='user_123',
+        )
+
+        mock_event_service = AsyncMock()
+        mock_app_conversation_info_service = AsyncMock()
+        mock_app_conversation_info_service.get_app_conversation_info.return_value = (
+            mock_app_conversation_info
+        )
+
+        # Set up process_stats_event to call update_conversation_statistics
+        async def process_stats_event_side_effect(event, conversation_id):
+            # Simulate what process_stats_event does - call update_conversation_statistics
+            from openhands.sdk.conversation.conversation_stats import ConversationStats
+
+            if isinstance(event.value, dict):
+                stats = ConversationStats.model_validate(event.value)
+                if stats and stats.usage_to_metrics:
+                    await mock_app_conversation_info_service.update_conversation_statistics(
+                        conversation_id, stats
+                    )
+
+        mock_app_conversation_info_service.process_stats_event.side_effect = (
+            process_stats_event_side_effect
+        )
+
+        with (
+            patch(
+                'openhands.app_server.event_callback.webhook_router.valid_sandbox',
+                return_value=mock_sandbox,
+            ),
+            patch(
+                'openhands.app_server.event_callback.webhook_router.valid_conversation',
+                return_value=mock_app_conversation_info,
+            ),
+            patch(
+                'openhands.app_server.event_callback.webhook_router._run_callbacks_in_bg_and_close'
+            ) as mock_callbacks,
+        ):
+            await on_event(
+                events=events,
+                conversation_id=conversation_id,
+                sandbox_info=mock_sandbox,
+                app_conversation_info_service=mock_app_conversation_info_service,
+                event_service=mock_event_service,
+            )
+
+            # Verify events were saved
+            assert mock_event_service.save_event.call_count == 2
+
+            # Verify stats event was processed
+            mock_app_conversation_info_service.update_conversation_statistics.assert_called_once()
+
+            # Verify callbacks were scheduled
+            mock_callbacks.assert_called_once()
+
+    @pytest.mark.asyncio
+    async def test_on_event_skips_non_stats_events(self):
+        """Test that on_event skips non-stats events."""
+        from openhands.app_server.event_callback.webhook_router import on_event
+        from openhands.app_server.sandbox.sandbox_models import (
+            SandboxInfo,
+            SandboxStatus,
+        )
+        from openhands.events.action.message import MessageAction
+
+        conversation_id = uuid4()
+        sandbox_id = 'sandbox_123'
+
+        # Create non-stats events
+        events = [
+            ConversationStateUpdateEvent(key='execution_status', value='running'),
+            MessageAction(content='test'),
+        ]
+
+        mock_sandbox = SandboxInfo(
+            id=sandbox_id,
+            status=SandboxStatus.RUNNING,
+            session_api_key='test_key',
+            created_by_user_id='user_123',
+            sandbox_spec_id='spec_123',
+        )
+
+        mock_app_conversation_info = AppConversationInfo(
+            id=conversation_id,
+            sandbox_id=sandbox_id,
+            created_by_user_id='user_123',
+        )
+
+        mock_event_service = AsyncMock()
+        mock_app_conversation_info_service = AsyncMock()
+        mock_app_conversation_info_service.get_app_conversation_info.return_value = (
+            mock_app_conversation_info
+        )
+
+        with (
+            patch(
+                'openhands.app_server.event_callback.webhook_router.valid_sandbox',
+                return_value=mock_sandbox,
+            ),
+            patch(
+                'openhands.app_server.event_callback.webhook_router.valid_conversation',
+                return_value=mock_app_conversation_info,
+            ),
+            patch(
+                'openhands.app_server.event_callback.webhook_router._run_callbacks_in_bg_and_close'
+            ),
+        ):
+            await on_event(
+                events=events,
+                conversation_id=conversation_id,
+                sandbox_info=mock_sandbox,
+                app_conversation_info_service=mock_app_conversation_info_service,
+                event_service=mock_event_service,
+            )
+
+            # Verify stats update was NOT called
+            mock_app_conversation_info_service.update_conversation_statistics.assert_not_called()

tests/unit/controller/test_agent_controller_posthog.py

@@ -1,243 +0,0 @@
-"""Integration tests for PostHog tracking in AgentController."""
-
-import asyncio
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from openhands.controller.agent import Agent
-from openhands.controller.agent_controller import AgentController
-from openhands.core.config import OpenHandsConfig
-from openhands.core.config.agent_config import AgentConfig
-from openhands.core.config.llm_config import LLMConfig
-from openhands.core.schema import AgentState
-from openhands.events import EventSource, EventStream
-from openhands.events.action.message import SystemMessageAction
-from openhands.llm.llm_registry import LLMRegistry
-from openhands.server.services.conversation_stats import ConversationStats
-from openhands.storage.memory import InMemoryFileStore
-
-
-@pytest.fixture(scope='function')
-def event_loop():
-    """Create event loop for async tests."""
-    loop = asyncio.get_event_loop_policy().new_event_loop()
-    yield loop
-    loop.close()
-
-
-@pytest.fixture
-def mock_agent_with_stats():
-    """Create a mock agent with properly connected LLM registry and conversation stats."""
-    import uuid
-
-    # Create LLM registry
-    config = OpenHandsConfig()
-    llm_registry = LLMRegistry(config=config)
-
-    # Create conversation stats
-    file_store = InMemoryFileStore({})
-    conversation_id = f'test-conversation-{uuid.uuid4()}'
-    conversation_stats = ConversationStats(
-        file_store=file_store, conversation_id=conversation_id, user_id='test-user'
-    )
-
-    # Connect registry to stats
-    llm_registry.subscribe(conversation_stats.register_llm)
-
-    # Create mock agent
-    agent = MagicMock(spec=Agent)
-    agent_config = MagicMock(spec=AgentConfig)
-    llm_config = LLMConfig(
-        model='gpt-4o',
-        api_key='test_key',
-        num_retries=2,
-        retry_min_wait=1,
-        retry_max_wait=2,
-    )
-    agent_config.disabled_microagents = []
-    agent_config.enable_mcp = True
-    agent_config.enable_stuck_detection = True
-    llm_registry.service_to_llm.clear()
-    mock_llm = llm_registry.get_llm('agent_llm', llm_config)
-    agent.llm = mock_llm
-    agent.name = 'test-agent'
-    agent.sandbox_plugins = []
-    agent.config = agent_config
-    agent.llm_registry = llm_registry
-    agent.prompt_manager = MagicMock()
-
-    # Add a proper system message mock
-    system_message = SystemMessageAction(
-        content='Test system message', tools=['test_tool']
-    )
-    system_message._source = EventSource.AGENT
-    system_message._id = -1  # Set invalid ID to avoid the ID check
-    agent.get_system_message.return_value = system_message
-
-    return agent, conversation_stats, llm_registry
-
-
-@pytest.fixture
-def mock_event_stream():
-    """Create a mock event stream."""
-    mock = MagicMock(
-        spec=EventStream,
-        event_stream=EventStream(sid='test', file_store=InMemoryFileStore({})),
-    )
-    mock.get_latest_event_id.return_value = 0
-    return mock
-
-
-@pytest.mark.asyncio
-async def test_agent_finish_triggers_posthog_tracking(
-    mock_agent_with_stats, mock_event_stream
-):
-    """Test that setting agent state to FINISHED triggers PostHog tracking."""
-    mock_agent, conversation_stats, llm_registry = mock_agent_with_stats
-
-    controller = AgentController(
-        agent=mock_agent,
-        event_stream=mock_event_stream,
-        conversation_stats=conversation_stats,
-        iteration_delta=10,
-        sid='test-conversation-123',
-        user_id='test-user-456',
-        confirmation_mode=False,
-        headless_mode=True,
-    )
-
-    with (
-        patch('openhands.utils.posthog_tracker.posthog') as mock_posthog,
-        patch('os.environ.get') as mock_env_get,
-    ):
-        # Setup mocks
-        mock_posthog.capture = MagicMock()
-        mock_env_get.return_value = 'saas'
-
-        # Initialize posthog in the tracker module
-        import openhands.utils.posthog_tracker as tracker
-
-        tracker.posthog = mock_posthog
-
-        # Set agent state to FINISHED
-        await controller.set_agent_state_to(AgentState.FINISHED)
-
-        # Verify PostHog tracking was called
-        mock_posthog.capture.assert_called_once()
-        call_args = mock_posthog.capture.call_args
-
-        assert call_args[1]['distinct_id'] == 'test-user-456'
-        assert call_args[1]['event'] == 'agent_task_completed'
-        assert 'conversation_id' in call_args[1]['properties']
-        assert call_args[1]['properties']['user_id'] == 'test-user-456'
-        assert call_args[1]['properties']['app_mode'] == 'saas'
-
-    await controller.close()
-
-
-@pytest.mark.asyncio
-async def test_agent_finish_without_user_id(mock_agent_with_stats, mock_event_stream):
-    """Test tracking when user_id is None."""
-    mock_agent, conversation_stats, llm_registry = mock_agent_with_stats
-
-    controller = AgentController(
-        agent=mock_agent,
-        event_stream=mock_event_stream,
-        conversation_stats=conversation_stats,
-        iteration_delta=10,
-        sid='test-conversation-789',
-        user_id=None,
-        confirmation_mode=False,
-        headless_mode=True,
-    )
-
-    with (
-        patch('openhands.utils.posthog_tracker.posthog') as mock_posthog,
-        patch('os.environ.get') as mock_env_get,
-    ):
-        mock_posthog.capture = MagicMock()
-        mock_env_get.return_value = 'oss'
-
-        import openhands.utils.posthog_tracker as tracker
-
-        tracker.posthog = mock_posthog
-
-        await controller.set_agent_state_to(AgentState.FINISHED)
-
-        mock_posthog.capture.assert_called_once()
-        call_args = mock_posthog.capture.call_args
-
-        # When user_id is None, distinct_id should be conversation_id
-        assert call_args[1]['distinct_id'].startswith('conversation_')
-        assert call_args[1]['properties']['user_id'] is None
-
-    await controller.close()
-
-
-@pytest.mark.asyncio
-async def test_other_states_dont_trigger_tracking(
-    mock_agent_with_stats, mock_event_stream
-):
-    """Test that non-FINISHED states don't trigger tracking."""
-    mock_agent, conversation_stats, llm_registry = mock_agent_with_stats
-
-    controller = AgentController(
-        agent=mock_agent,
-        event_stream=mock_event_stream,
-        conversation_stats=conversation_stats,
-        iteration_delta=10,
-        sid='test-conversation-999',
-        confirmation_mode=False,
-        headless_mode=True,
-    )
-
-    with patch('openhands.utils.posthog_tracker.posthog') as mock_posthog:
-        mock_posthog.capture = MagicMock()
-
-        import openhands.utils.posthog_tracker as tracker
-
-        tracker.posthog = mock_posthog
-
-        # Try different states
-        await controller.set_agent_state_to(AgentState.RUNNING)
-        await controller.set_agent_state_to(AgentState.PAUSED)
-        await controller.set_agent_state_to(AgentState.STOPPED)
-
-        # PostHog should not be called for non-FINISHED states
-        mock_posthog.capture.assert_not_called()
-
-    await controller.close()
-
-
-@pytest.mark.asyncio
-async def test_tracking_error_doesnt_break_agent(
-    mock_agent_with_stats, mock_event_stream
-):
-    """Test that tracking errors don't interrupt agent operation."""
-    mock_agent, conversation_stats, llm_registry = mock_agent_with_stats
-
-    controller = AgentController(
-        agent=mock_agent,
-        event_stream=mock_event_stream,
-        conversation_stats=conversation_stats,
-        iteration_delta=10,
-        sid='test-conversation-error',
-        confirmation_mode=False,
-        headless_mode=True,
-    )
-
-    with patch('openhands.utils.posthog_tracker.posthog') as mock_posthog:
-        mock_posthog.capture = MagicMock(side_effect=Exception('PostHog error'))
-
-        import openhands.utils.posthog_tracker as tracker
-
-        tracker.posthog = mock_posthog
-
-        # Should not raise an exception
-        await controller.set_agent_state_to(AgentState.FINISHED)
-
-        # Agent state should still be FINISHED despite tracking error
-        assert controller.state.agent_state == AgentState.FINISHED
-
-    await controller.close()

tests/unit/experiments/test_experiment_manager.py

@@ -152,6 +152,7 @@ class TestExperimentManagerIntegration:
                     llm_base_url=None,
                     llm_api_key=None,
                     confirmation_mode=False,
+                    condenser_max_size=None,
                 )
 
             async def get_secrets(self):
@@ -200,8 +201,24 @@ class TestExperimentManagerIntegration:
 
         # Patch the pieces invoked by the service
         with (
-            patch(
-                'openhands.app_server.app_conversation.live_status_app_conversation_service.get_default_agent',
+            patch.object(
+                service,
+                '_setup_secrets_for_git_provider',
+                return_value={},
+            ),
+            patch.object(
+                service,
+                '_configure_llm_and_mcp',
+                return_value=(mock_llm, {}),
+            ),
+            patch.object(
+                service,
+                '_create_agent_with_context',
+                return_value=mock_agent,
+            ),
+            patch.object(
+                service,
+                '_load_skills_and_update_agent',
                 return_value=mock_agent,
             ),
             patch(

tests/unit/llm/test_llm.py

@@ -1255,6 +1255,25 @@ def test_opus_41_keeps_temperature_top_p(mock_completion):
     assert 'top_p' not in call_kwargs
 
 
+@patch('openhands.llm.llm.litellm_completion')
+def test_opus_45_keeps_temperature_drops_top_p(mock_completion):
+    mock_completion.return_value = {
+        'choices': [{'message': {'content': 'ok'}}],
+    }
+    config = LLMConfig(
+        model='anthropic/claude-opus-4-5-20251101',
+        api_key='k',
+        temperature=0.7,
+        top_p=0.9,
+    )
+    llm = LLM(config, service_id='svc')
+    llm.completion(messages=[{'role': 'user', 'content': 'hi'}])
+    call_kwargs = mock_completion.call_args[1]
+    assert call_kwargs.get('temperature') == 0.7
+    # Anthropic rejects both temperature and top_p together on Opus 4.5; we keep temperature and drop top_p
+    assert 'top_p' not in call_kwargs
+
+
 @patch('openhands.llm.llm.litellm_completion')
 def test_sonnet_4_keeps_temperature_drops_top_p(mock_completion):
     mock_completion.return_value = {

tests/unit/server/routes/test_settings_api.py

@@ -46,6 +46,9 @@ class MockUserAuth(UserAuth):
     async def get_secrets(self) -> Secrets | None:
         return None
 
+    async def get_mcp_api_key(self) -> str | None:
+        return None
+
     @classmethod
     async def get_instance(cls, request: Request) -> UserAuth:
         return MockUserAuth()

tests/unit/server/test_openapi_schema_generation.py

@@ -46,6 +46,9 @@ class MockUserAuth(UserAuth):
     async def get_secrets(self) -> Secrets | None:
         return None
 
+    async def get_mcp_api_key(self) -> str | None:
+        return None
+
     @classmethod
     async def get_instance(cls, request: Request) -> UserAuth:
         return MockUserAuth()

tests/unit/utils/test_posthog_tracker.py

@@ -1,356 +0,0 @@
-"""Unit tests for PostHog tracking utilities."""
-
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from openhands.utils.posthog_tracker import (
-    alias_user_identities,
-    track_agent_task_completed,
-    track_credit_limit_reached,
-    track_credits_purchased,
-    track_user_signup_completed,
-)
-
-
-@pytest.fixture
-def mock_posthog():
-    """Mock the posthog module."""
-    with patch('openhands.utils.posthog_tracker.posthog') as mock_ph:
-        mock_ph.capture = MagicMock()
-        yield mock_ph
-
-
-def test_track_agent_task_completed_with_user_id(mock_posthog):
-    """Test tracking agent task completion with user ID."""
-    # Initialize posthog manually in the test
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-
-    track_agent_task_completed(
-        conversation_id='test-conversation-123',
-        user_id='user-456',
-        app_mode='saas',
-    )
-
-    mock_posthog.capture.assert_called_once_with(
-        distinct_id='user-456',
-        event='agent_task_completed',
-        properties={
-            'conversation_id': 'test-conversation-123',
-            'user_id': 'user-456',
-            'app_mode': 'saas',
-        },
-    )
-
-
-def test_track_agent_task_completed_without_user_id(mock_posthog):
-    """Test tracking agent task completion without user ID (anonymous)."""
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-
-    track_agent_task_completed(
-        conversation_id='test-conversation-789',
-        user_id=None,
-        app_mode='oss',
-    )
-
-    mock_posthog.capture.assert_called_once_with(
-        distinct_id='conversation_test-conversation-789',
-        event='agent_task_completed',
-        properties={
-            'conversation_id': 'test-conversation-789',
-            'user_id': None,
-            'app_mode': 'oss',
-        },
-    )
-
-
-def test_track_agent_task_completed_default_app_mode(mock_posthog):
-    """Test tracking with default app_mode."""
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-
-    track_agent_task_completed(
-        conversation_id='test-conversation-999',
-        user_id='user-111',
-    )
-
-    mock_posthog.capture.assert_called_once_with(
-        distinct_id='user-111',
-        event='agent_task_completed',
-        properties={
-            'conversation_id': 'test-conversation-999',
-            'user_id': 'user-111',
-            'app_mode': 'unknown',
-        },
-    )
-
-
-def test_track_agent_task_completed_handles_errors(mock_posthog):
-    """Test that tracking errors are handled gracefully."""
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-    mock_posthog.capture.side_effect = Exception('PostHog API error')
-
-    # Should not raise an exception
-    track_agent_task_completed(
-        conversation_id='test-conversation-error',
-        user_id='user-error',
-        app_mode='saas',
-    )
-
-
-def test_track_agent_task_completed_when_posthog_not_installed():
-    """Test tracking when posthog is not installed."""
-    import openhands.utils.posthog_tracker as tracker
-
-    # Simulate posthog not being installed
-    tracker.posthog = None
-
-    # Should not raise an exception
-    track_agent_task_completed(
-        conversation_id='test-conversation-no-ph',
-        user_id='user-no-ph',
-        app_mode='oss',
-    )
-
-
-def test_track_user_signup_completed(mock_posthog):
-    """Test tracking user signup completion."""
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-
-    track_user_signup_completed(
-        user_id='test-user-123',
-        signup_timestamp='2025-01-15T10:30:00Z',
-    )
-
-    mock_posthog.capture.assert_called_once_with(
-        distinct_id='test-user-123',
-        event='user_signup_completed',
-        properties={
-            'user_id': 'test-user-123',
-            'signup_timestamp': '2025-01-15T10:30:00Z',
-        },
-    )
-
-
-def test_track_user_signup_completed_handles_errors(mock_posthog):
-    """Test that user signup tracking errors are handled gracefully."""
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-    mock_posthog.capture.side_effect = Exception('PostHog API error')
-
-    # Should not raise an exception
-    track_user_signup_completed(
-        user_id='test-user-error',
-        signup_timestamp='2025-01-15T12:00:00Z',
-    )
-
-
-def test_track_user_signup_completed_when_posthog_not_installed():
-    """Test user signup tracking when posthog is not installed."""
-    import openhands.utils.posthog_tracker as tracker
-
-    # Simulate posthog not being installed
-    tracker.posthog = None
-
-    # Should not raise an exception
-    track_user_signup_completed(
-        user_id='test-user-no-ph',
-        signup_timestamp='2025-01-15T13:00:00Z',
-    )
-
-
-def test_track_credit_limit_reached_with_user_id(mock_posthog):
-    """Test tracking credit limit reached with user ID."""
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-
-    track_credit_limit_reached(
-        conversation_id='test-conversation-456',
-        user_id='user-789',
-        current_budget=10.50,
-        max_budget=10.00,
-    )
-
-    mock_posthog.capture.assert_called_once_with(
-        distinct_id='user-789',
-        event='credit_limit_reached',
-        properties={
-            'conversation_id': 'test-conversation-456',
-            'user_id': 'user-789',
-            'current_budget': 10.50,
-            'max_budget': 10.00,
-        },
-    )
-
-
-def test_track_credit_limit_reached_without_user_id(mock_posthog):
-    """Test tracking credit limit reached without user ID (anonymous)."""
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-
-    track_credit_limit_reached(
-        conversation_id='test-conversation-999',
-        user_id=None,
-        current_budget=5.25,
-        max_budget=5.00,
-    )
-
-    mock_posthog.capture.assert_called_once_with(
-        distinct_id='conversation_test-conversation-999',
-        event='credit_limit_reached',
-        properties={
-            'conversation_id': 'test-conversation-999',
-            'user_id': None,
-            'current_budget': 5.25,
-            'max_budget': 5.00,
-        },
-    )
-
-
-def test_track_credit_limit_reached_handles_errors(mock_posthog):
-    """Test that credit limit tracking errors are handled gracefully."""
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-    mock_posthog.capture.side_effect = Exception('PostHog API error')
-
-    # Should not raise an exception
-    track_credit_limit_reached(
-        conversation_id='test-conversation-error',
-        user_id='user-error',
-        current_budget=15.00,
-        max_budget=10.00,
-    )
-
-
-def test_track_credit_limit_reached_when_posthog_not_installed():
-    """Test credit limit tracking when posthog is not installed."""
-    import openhands.utils.posthog_tracker as tracker
-
-    # Simulate posthog not being installed
-    tracker.posthog = None
-
-    # Should not raise an exception
-    track_credit_limit_reached(
-        conversation_id='test-conversation-no-ph',
-        user_id='user-no-ph',
-        current_budget=8.00,
-        max_budget=5.00,
-    )
-
-
-def test_track_credits_purchased(mock_posthog):
-    """Test tracking credits purchased."""
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-
-    track_credits_purchased(
-        user_id='test-user-999',
-        amount_usd=50.00,
-        credits_added=50.00,
-        stripe_session_id='cs_test_abc123',
-    )
-
-    mock_posthog.capture.assert_called_once_with(
-        distinct_id='test-user-999',
-        event='credits_purchased',
-        properties={
-            'user_id': 'test-user-999',
-            'amount_usd': 50.00,
-            'credits_added': 50.00,
-            'stripe_session_id': 'cs_test_abc123',
-        },
-    )
-
-
-def test_track_credits_purchased_handles_errors(mock_posthog):
-    """Test that credits purchased tracking errors are handled gracefully."""
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-    mock_posthog.capture.side_effect = Exception('PostHog API error')
-
-    # Should not raise an exception
-    track_credits_purchased(
-        user_id='test-user-error',
-        amount_usd=100.00,
-        credits_added=100.00,
-        stripe_session_id='cs_test_error',
-    )
-
-
-def test_track_credits_purchased_when_posthog_not_installed():
-    """Test credits purchased tracking when posthog is not installed."""
-    import openhands.utils.posthog_tracker as tracker
-
-    # Simulate posthog not being installed
-    tracker.posthog = None
-
-    # Should not raise an exception
-    track_credits_purchased(
-        user_id='test-user-no-ph',
-        amount_usd=25.00,
-        credits_added=25.00,
-        stripe_session_id='cs_test_no_ph',
-    )
-
-
-def test_alias_user_identities(mock_posthog):
-    """Test aliasing user identities.
-
-    Verifies that posthog.alias(previous_id, distinct_id) is called correctly
-    where git_login is the previous_id and keycloak_user_id is the distinct_id.
-    """
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-    mock_posthog.alias = MagicMock()
-
-    alias_user_identities(
-        keycloak_user_id='keycloak-123',
-        git_login='git-user',
-    )
-
-    # Verify: posthog.alias(previous_id='git-user', distinct_id='keycloak-123')
-    mock_posthog.alias.assert_called_once_with('git-user', 'keycloak-123')
-
-
-def test_alias_user_identities_handles_errors(mock_posthog):
-    """Test that aliasing errors are handled gracefully."""
-    import openhands.utils.posthog_tracker as tracker
-
-    tracker.posthog = mock_posthog
-    mock_posthog.alias = MagicMock(side_effect=Exception('PostHog API error'))
-
-    # Should not raise an exception
-    alias_user_identities(
-        keycloak_user_id='keycloak-error',
-        git_login='git-error',
-    )
-
-
-def test_alias_user_identities_when_posthog_not_installed():
-    """Test aliasing when posthog is not installed."""
-    import openhands.utils.posthog_tracker as tracker
-
-    # Simulate posthog not being installed
-    tracker.posthog = None
-
-    # Should not raise an exception
-    alias_user_identities(
-        keycloak_user_id='keycloak-no-ph',
-        git_login='git-no-ph',
-    )