Merge branch 'main' into kevin

.github/dependabot.yml

@@ -18,7 +18,7 @@ updates:
           - "chromadb"
       browsergym:
         patterns:
-          - "browsergym"
+          - "browsergym*"
       security-all:
         applies-to: "security-updates"
         patterns:

.github/workflows/openhands-resolver.yml

@@ -239,7 +239,8 @@ jobs:
           if [ "${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}" == "true" ]; then
             cd /tmp && python -m openhands.resolver.send_pull_request \
               --issue-number ${{ env.ISSUE_NUMBER }} \
-              --pr-type draft | tee pr_result.txt && \
+              --pr-type draft \
+              --reviewer ${{ github.actor }} | tee pr_result.txt && \
               grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
           else
             cd /tmp && python -m openhands.resolver.send_pull_request \

docs/modules/usage/how-to/gui-mode.md

@@ -23,10 +23,75 @@ OpenHands provides a user-friendly Graphical User Interface (GUI) mode for inter
 
 OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if it is available. This can happen in two ways:
 
-1. Locally (OSS): The user directly inputs their GitHub token.
-2. Online (SaaS): The token is obtained through GitHub OAuth authentication.
-
-When you reach the `/app` route, the app checks if a token is present. If it finds one, it sets it in the environment for the agent to use.
+1. **Locally (OSS)**: The user directly inputs their GitHub token
+2. **Online (SaaS)**: The token is obtained through GitHub OAuth authentication
+
+#### Setting Up a Local GitHub Token
+
+1. **Generate a Personal Access Token (PAT)**:
+   - Go to GitHub Settings > Developer Settings > Personal Access Tokens > Tokens (classic)
+   - Click "Generate new token (classic)"
+   - Required scopes:
+     - `repo` (Full control of private repositories)
+     - `workflow` (Update GitHub Action workflows)
+     - `read:org` (Read organization data)
+
+2. **Enter Token in OpenHands**:
+   - Click the Settings button (gear icon) in the top right
+   - Navigate to the "GitHub" section
+   - Paste your token in the "GitHub Token" field
+   - Click "Save" to apply the changes
+
+#### Organizational Token Policies
+
+If you're working with organizational repositories, additional setup may be required:
+
+1. **Check Organization Requirements**:
+   - Organization admins may enforce specific token policies
+   - Some organizations require tokens to be created with SSO enabled
+   - Review your organization's [token policy settings](https://docs.github.com/en/organizations/managing-programmatic-access-to-your-organization/setting-a-personal-access-token-policy-for-your-organization)
+
+2. **Verify Organization Access**:
+   - Go to your token settings on GitHub
+   - Look for the organization under "Organization access"
+   - If required, click "Enable SSO" next to your organization
+   - Complete the SSO authorization process
+
+#### OAuth Authentication (Online Mode)
+
+When using OpenHands in online mode, the GitHub OAuth flow:
+
+1. Requests the following permissions:
+   - Repository access (read/write)
+   - Workflow management
+   - Organization read access
+
+2. Authentication steps:
+   - Click "Sign in with GitHub" when prompted
+   - Review the requested permissions
+   - Authorize OpenHands to access your GitHub account
+   - If using an organization, authorize organization access if prompted
+
+#### Troubleshooting
+
+Common issues and solutions:
+
+1. **Token Not Recognized**:
+   - Ensure the token is properly saved in settings
+   - Check that the token hasn't expired
+   - Verify the token has the required scopes
+   - Try regenerating the token
+
+2. **Organization Access Denied**:
+   - Check if SSO is required but not enabled
+   - Verify organization membership
+   - Contact organization admin if token policies are blocking access
+
+3. **Verifying Token Works**:
+   - The app will show a green checkmark if the token is valid
+   - Try accessing a repository to confirm permissions
+   - Check the browser console for any error messages
+   - Use the "Test Connection" button in settings if available
 
 ### Advanced Settings
 

docs/package.json

@@ -25,7 +25,7 @@
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
     "react-icons": "^5.4.0",
-    "react-use": "^17.5.1"
+    "react-use": "^17.6.0"
   },
   "devDependencies": {
     "@docusaurus/module-type-aliases": "^3.5.1",

evaluation/benchmarks/swe_bench/scripts/eval/verify_costs.py

@@ -0,0 +1,104 @@
+import argparse
+
+import pandas as pd
+
+from openhands.core.logger import openhands_logger as logger
+
+
+def verify_instance_costs(row: pd.Series) -> float:
+    """
+    Verifies that the accumulated_cost matches the sum of individual costs in metrics.
+    Also checks for duplicate consecutive costs which might indicate buggy counting.
+    If the consecutive costs are identical, the file is affected by this bug:
+    https://github.com/All-Hands-AI/OpenHands/issues/5383
+
+    Args:
+        row: DataFrame row containing instance data with metrics
+    Returns:
+        float: The verified total cost for this instance (corrected if needed)
+    """
+    try:
+        metrics = row.get('metrics')
+        if not metrics:
+            logger.warning(f"Instance {row['instance_id']}: No metrics found")
+            return 0.0
+
+        accumulated = metrics.get('accumulated_cost')
+        costs = metrics.get('costs', [])
+
+        if accumulated is None:
+            logger.warning(
+                f"Instance {row['instance_id']}: No accumulated_cost in metrics"
+            )
+            return 0.0
+
+        # Check for duplicate consecutive costs and systematic even-odd pairs
+        has_duplicate = False
+        all_pairs_match = True
+
+        # Check each even-odd pair (0-1, 2-3, etc.)
+        for i in range(0, len(costs) - 1, 2):
+            if abs(costs[i]['cost'] - costs[i + 1]['cost']) < 1e-6:
+                has_duplicate = True
+                logger.debug(
+                    f"Instance {row['instance_id']}: Possible buggy double-counting detected! "
+                    f"Steps {i} and {i+1} have identical costs: {costs[i]['cost']:.2f}"
+                )
+            else:
+                all_pairs_match = False
+                break
+
+        # Calculate total cost, accounting for buggy double counting if detected
+        if len(costs) >= 2 and has_duplicate and all_pairs_match:
+            paired_steps_cost = sum(
+                cost_entry['cost']
+                for cost_entry in costs[: -1 if len(costs) % 2 else None]
+            )
+            real_paired_cost = paired_steps_cost / 2
+
+            unpaired_cost = costs[-1]['cost'] if len(costs) % 2 else 0
+            total_cost = real_paired_cost + unpaired_cost
+
+        else:
+            total_cost = sum(cost_entry['cost'] for cost_entry in costs)
+
+        if not abs(total_cost - accumulated) < 1e-6:
+            logger.warning(
+                f"Instance {row['instance_id']}: Cost mismatch: "
+                f"accumulated: {accumulated:.2f}, sum of costs: {total_cost:.2f}, "
+            )
+
+        return total_cost
+
+    except Exception as e:
+        logger.error(
+            f"Error verifying costs for instance {row.get('instance_id', 'UNKNOWN')}: {e}"
+        )
+        return 0.0
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description='Verify costs in SWE-bench output file'
+    )
+    parser.add_argument(
+        'input_filepath', type=str, help='Path to the output.jsonl file'
+    )
+    args = parser.parse_args()
+
+    try:
+        # Load and verify the JSONL file
+        df = pd.read_json(args.input_filepath, lines=True)
+        logger.info(f'Loaded {len(df)} instances from {args.input_filepath}')
+
+        # Verify costs for each instance and sum up total
+        total_cost = df.apply(verify_instance_costs, axis=1).sum()
+        logger.info(f'Total verified cost across all instances: ${total_cost:.2f}')
+
+    except Exception as e:
+        logger.error(f'Failed to process file: {e}')
+        raise
+
+
+if __name__ == '__main__':
+    main()

frontend/__tests__/components/browser.test.tsx

@@ -11,6 +11,7 @@ describe("Browser", () => {
         browser: {
           url: "https://example.com",
           screenshotSrc: "",
+          updateCount: 0,
         },
       },
     });
@@ -26,6 +27,7 @@ describe("Browser", () => {
           url: "https://example.com",
           screenshotSrc:
             "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mN0uGvyHwAFCAJS091fQwAAAABJRU5ErkJggg==",
+          updateCount: 0,
         },
       },
     });

frontend/src/components/features/file-explorer/tree-node.tsx

@@ -1,10 +1,12 @@
 import React from "react";
+import { useSelector } from "react-redux";
 
 import { useFiles } from "#/context/files";
 import { cn } from "#/utils/utils";
 import { useListFiles } from "#/hooks/query/use-list-files";
 import { useListFile } from "#/hooks/query/use-list-file";
 import { Filename } from "./filename";
+import { RootState } from "#/store";
 
 interface TreeNodeProps {
   path: string;
@@ -20,6 +22,7 @@ function TreeNode({ path, defaultOpen = false }: TreeNodeProps) {
     selectedPath,
   } = useFiles();
   const [isOpen, setIsOpen] = React.useState(defaultOpen);
+  const { curAgentState } = useSelector((state: RootState) => state.agent);
 
   const isDirectory = path.endsWith("/");
 
@@ -39,6 +42,12 @@ function TreeNode({ path, defaultOpen = false }: TreeNodeProps) {
     }
   }, [fileContent, path]);
 
+  React.useEffect(() => {
+    if (selectedPath === path && !isDirectory) {
+      refetch();
+    }
+  }, [curAgentState, selectedPath, path, isDirectory]);
+
   const fileParts = path.split("/");
   const filename =
     fileParts[fileParts.length - 1] || fileParts[fileParts.length - 2];

frontend/src/components/features/sidebar/sidebar.tsx

@@ -54,13 +54,13 @@ export function Sidebar() {
 
   return (
     <>
-      <aside className="px-1 flex flex-col gap-1">
+      <aside className="h-[40px] md:h-auto px-1 flex flex-row md:flex-col gap-1">
         <div className="w-[34px] h-[34px] flex items-center justify-center">
           {user.isLoading && <LoadingSpinner size="small" />}
           {!user.isLoading && <AllHandsLogoButton onClick={handleClickLogo} />}
         </div>
 
-        <nav className="py-[18px] flex flex-col items-center gap-[18px]">
+        <nav className="md:py-[18px] flex flex-row md:flex-col items-center gap-[18px]">
           <UserActions
             user={user.data ? { avatar_url: user.data.avatar_url } : undefined}
             onLogout={logout}

frontend/src/components/layout/container.tsx

@@ -8,7 +8,7 @@ import { NavTab } from "./nav-tab";
 interface ContainerProps {
   label?: string;
   labels?: {
-    label: string;
+    label: string | React.ReactNode;
     to: string;
     icon?: React.ReactNode;
     isBeta?: boolean;
@@ -65,7 +65,7 @@ export function Container({
           )}
         </div>
       )}
-      <div className="overflow-auto h-full rounded-b-xl">{children}</div>
+      <div className="overflow-hidden h-full rounded-b-xl">{children}</div>
     </div>
   );
 }

frontend/src/components/layout/count-badge.tsx

@@ -0,0 +1,7 @@
+export function CountBadge({ count }: { count: number }) {
+  return (
+    <span className="text-[11px] leading-5 text-root-primary bg-neutral-400 px-1 rounded-xl">
+      {count}
+    </span>
+  );
+}

frontend/src/components/layout/nav-tab.tsx

@@ -4,7 +4,7 @@ import { BetaBadge } from "./beta-badge";
 
 interface NavTabProps {
   to: string;
-  label: string;
+  label: string | React.ReactNode;
   icon: React.ReactNode;
   isBeta?: boolean;
 }

frontend/src/i18n/translation.json

@@ -2023,6 +2023,9 @@
   "ACTION_MESSAGE$WRITE": {
     "en": "Writing to a file"
   },
+  "ACTION_MESSAGE$BROWSE": {
+    "en": "Browsing the web"
+  },
   "OBSERVATION_MESSAGE$RUN": {
     "en": "Ran a bash command"
   },
@@ -2035,6 +2038,9 @@
   "OBSERVATION_MESSAGE$WRITE": {
     "en": "Wrote to a file"
   },
+  "OBSERVATION_MESSAGE$BROWSE": {
+    "en": "Browsing completed"
+  },
   "EXPANDABLE_MESSAGE$SHOW_DETAILS": {
     "en": "Show details"
   },