Improve SQLAlchemy concurrency test to use real database operations

- Replace mocked error test with comprehensive real database tests
- Use in-memory SQLite database with proper fixtures
- Test both sequential (fixed) and concurrent (problematic) patterns
- Demonstrate that sequential approach works reliably
- Show that concurrent approach can fail silently (data not saved)
- Add multiple test scenarios covering various concurrency patterns
- Tests now actually verify database operations instead of just mocking errors

The improved tests provide better coverage of the actual fix and demonstrate
why the sequential approach is more reliable than asyncio.gather() with
shared database sessions.

Co-authored-by: openhands <openhands@all-hands.dev>

.github/workflows/clean-up.yml

@@ -0,0 +1,69 @@
+# Workflow that cleans up outdated and old workflows to prevent out of disk issues
+name: Delete old workflow runs
+
+# This workflow is currently only triggered manually
+on:
+  workflow_dispatch:
+    inputs:
+      days:
+        description: 'Days-worth of runs to keep for each workflow'
+        required: true
+        default: '30'
+      minimum_runs:
+        description: 'Minimum runs to keep for each workflow'
+        required: true
+        default: '10'
+      delete_workflow_pattern:
+        description: 'Name or filename of the workflow (if not set, all workflows are targeted)'
+        required: false
+      delete_workflow_by_state_pattern:
+        description: 'Filter workflows by state: active, deleted, disabled_fork, disabled_inactivity, disabled_manually'
+        required: true
+        default: "ALL"
+        type: choice
+        options:
+          - "ALL"
+          - active
+          - deleted
+          - disabled_inactivity
+          - disabled_manually
+      delete_run_by_conclusion_pattern:
+        description: 'Remove runs based on conclusion: action_required, cancelled, failure, skipped, success'
+        required: true
+        default: 'ALL'
+        type: choice
+        options:
+          - 'ALL'
+          - 'Unsuccessful: action_required,cancelled,failure,skipped'
+          - action_required
+          - cancelled
+          - failure
+          - skipped
+          - success
+      dry_run:
+        description: 'Logs simulated changes, no deletions are performed'
+        required: false
+
+jobs:
+  del_runs:
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    permissions:
+      actions: write
+      contents: read
+    steps:
+      - name: Delete workflow runs
+        uses: Mattraks/delete-workflow-runs@v2
+        with:
+          token: ${{ github.token }}
+          repository: ${{ github.repository }}
+          retain_days: ${{ github.event.inputs.days }}
+          keep_minimum_runs: ${{ github.event.inputs.minimum_runs }}
+          delete_workflow_pattern: ${{ github.event.inputs.delete_workflow_pattern }}
+          delete_workflow_by_state_pattern: ${{ github.event.inputs.delete_workflow_by_state_pattern }}
+          delete_run_by_conclusion_pattern: >-
+            ${{
+              startsWith(github.event.inputs.delete_run_by_conclusion_pattern, 'Unsuccessful:')
+              && 'action_required,cancelled,failure,skipped'
+              || github.event.inputs.delete_run_by_conclusion_pattern
+            }}
+          dry_run: ${{ github.event.inputs.dry_run }}

.github/workflows/dispatch-to-docs.yml

@@ -0,0 +1,23 @@
+name: Dispatch to docs repo
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - 'docs/**'
+  workflow_dispatch:
+
+jobs:
+  dispatch:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        repo: ["OpenHands/docs"]
+    steps:
+      - name: Push to docs repo
+        uses: peter-evans/repository-dispatch@v3
+        with:
+          token: ${{ secrets.ALLHANDS_BOT_GITHUB_PAT }}
+          repository: ${{ matrix.repo }}
+          event-type: update
+          client-payload: '{"ref": "${{ github.ref }}", "sha": "${{ github.sha }}", "module": "openhands", "branch": "main"}'

.github/workflows/mdx-lint.yml

@@ -0,0 +1,70 @@
+# Workflow that checks MDX format in docs/ folder
+name: MDX Lint
+
+# Run on pushes to main and on pull requests that modify docs/ files
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'docs/**/*.mdx'
+  pull_request:
+    paths:
+      - 'docs/**/*.mdx'
+
+# If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
+concurrency:
+  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  mdx-lint:
+    name: Lint MDX files
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Node.js 22
+        uses: useblacksmith/setup-node@v5
+        with:
+          node-version: 22
+
+      - name: Install MDX dependencies
+        run: |
+          npm install @mdx-js/mdx@3 glob@10
+
+      - name: Validate MDX files
+        run: |
+          node -e "
+          const {compile} = require('@mdx-js/mdx');
+          const fs = require('fs');
+          const path = require('path');
+          const glob = require('glob');
+
+          async function validateMDXFiles() {
+            const files = glob.sync('docs/**/*.mdx');
+            console.log('Found', files.length, 'MDX files to validate');
+
+            let hasErrors = false;
+
+            for (const file of files) {
+              try {
+                const content = fs.readFileSync(file, 'utf8');
+                await compile(content);
+                console.log('✅ MDX parsing successful for', file);
+              } catch (err) {
+                console.error('❌ MDX parsing failed for', file, ':', err.message);
+                hasErrors = true;
+              }
+            }
+
+            if (hasErrors) {
+              console.error('\\n❌ Some MDX files have parsing errors. Please fix them before merging.');
+              process.exit(1);
+            } else {
+              console.log('\\n✅ All MDX files are valid!');
+            }
+          }
+
+          validateMDXFiles();
+          "

.github/workflows/run-eval.yml

@@ -0,0 +1,135 @@
+# Run evaluation on a PR, after releases, or manually
+name: Run Eval
+
+# Runs when a PR is labeled with one of the "run-eval-" labels, after releases, or manually triggered
+on:
+  pull_request:
+    types: [labeled]
+  release:
+    types: [published]
+  workflow_dispatch:
+    inputs:
+      branch:
+        description: 'Branch to evaluate'
+        required: true
+        default: 'main'
+      eval_instances:
+        description: 'Number of evaluation instances'
+        required: true
+        default: '50'
+        type: choice
+        options:
+          - '1'
+          - '2'
+          - '50'
+          - '100'
+      reason:
+        description: 'Reason for manual trigger'
+        required: false
+        default: ''
+
+env:
+  # Environment variable for the master GitHub issue number where all evaluation results will be commented
+  # This should be set to the issue number where you want all evaluation results to be posted
+  MASTER_EVAL_ISSUE_NUMBER: ${{ vars.MASTER_EVAL_ISSUE_NUMBER || '0' }}
+
+jobs:
+  trigger-job:
+    name: Trigger remote eval job
+    if: ${{ (github.event_name == 'pull_request' && (github.event.label.name == 'run-eval-1' || github.event.label.name == 'run-eval-2' || github.event.label.name == 'run-eval-50' || github.event.label.name == 'run-eval-100')) || github.event_name == 'release' || github.event_name == 'workflow_dispatch' }}
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+
+    steps:
+      - name: Checkout branch
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event_name == 'pull_request' && github.head_ref || (github.event_name == 'workflow_dispatch' && github.event.inputs.branch) || github.ref }}
+
+      - name: Set evaluation parameters
+        id: eval_params
+        run: |
+          REPO_URL="https://github.com/${{ github.repository }}"
+          echo "Repository URL: $REPO_URL"
+
+          # Determine branch based on trigger type
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            EVAL_BRANCH="${{ github.head_ref }}"
+            echo "PR Branch: $EVAL_BRANCH"
+          elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            EVAL_BRANCH="${{ github.event.inputs.branch }}"
+            echo "Manual Branch: $EVAL_BRANCH"
+          else
+            # For release events, use the tag name or main branch
+            EVAL_BRANCH="${{ github.ref_name }}"
+            echo "Release Branch/Tag: $EVAL_BRANCH"
+          fi
+
+          # Determine evaluation instances based on trigger type
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            if [[ "${{ github.event.label.name }}" == "run-eval-1" ]]; then
+              EVAL_INSTANCES="1"
+            elif [[ "${{ github.event.label.name }}" == "run-eval-2" ]]; then
+              EVAL_INSTANCES="2"
+            elif [[ "${{ github.event.label.name }}" == "run-eval-50" ]]; then
+              EVAL_INSTANCES="50"
+            elif [[ "${{ github.event.label.name }}" == "run-eval-100" ]]; then
+              EVAL_INSTANCES="100"
+            fi
+          elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            EVAL_INSTANCES="${{ github.event.inputs.eval_instances }}"
+          else
+            # For release events, default to 50 instances
+            EVAL_INSTANCES="50"
+          fi
+
+          echo "Evaluation instances: $EVAL_INSTANCES"
+          echo "repo_url=$REPO_URL" >> $GITHUB_OUTPUT
+          echo "eval_branch=$EVAL_BRANCH" >> $GITHUB_OUTPUT
+          echo "eval_instances=$EVAL_INSTANCES" >> $GITHUB_OUTPUT
+
+      - name: Trigger remote job
+        run: |
+          # Determine PR number for the remote evaluation system
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            PR_NUMBER="${{ github.event.pull_request.number }}"
+          else
+            # For non-PR triggers, use the master issue number as PR number
+            PR_NUMBER="${{ env.MASTER_EVAL_ISSUE_NUMBER }}"
+          fi
+
+          curl -X POST \
+            -H "Authorization: Bearer ${{ secrets.PAT_TOKEN }}" \
+            -H "Accept: application/vnd.github+json" \
+            -d "{\"ref\": \"main\", \"inputs\": {\"github-repo\": \"${{ steps.eval_params.outputs.repo_url }}\", \"github-branch\": \"${{ steps.eval_params.outputs.eval_branch }}\", \"pr-number\": \"${PR_NUMBER}\", \"eval-instances\": \"${{ steps.eval_params.outputs.eval_instances }}\"}}" \
+            https://api.github.com/repos/OpenHands/evaluation/actions/workflows/create-branch.yml/dispatches
+
+          # Send Slack message
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            TRIGGER_URL="https://github.com/${{ github.repository }}/pull/${{ github.event.pull_request.number }}"
+            slack_text="PR $TRIGGER_URL has triggered evaluation on ${{ steps.eval_params.outputs.eval_instances }} instances..."
+          elif [[ "${{ github.event_name }}" == "release" ]]; then
+            TRIGGER_URL="https://github.com/${{ github.repository }}/releases/tag/${{ github.ref_name }}"
+            slack_text="Release $TRIGGER_URL has triggered evaluation on ${{ steps.eval_params.outputs.eval_instances }} instances..."
+          else
+            TRIGGER_URL="https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"
+            slack_text="Manual trigger (${{ github.event.inputs.reason || 'No reason provided' }}) has triggered evaluation on ${{ steps.eval_params.outputs.eval_instances }} instances for branch ${{ steps.eval_params.outputs.eval_branch }}..."
+          fi
+
+          curl -X POST -H 'Content-type: application/json' --data '{"text":"'"$slack_text"'"}' \
+            https://hooks.slack.com/services/${{ secrets.SLACK_TOKEN }}
+
+      - name: Comment on issue/PR
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          # For PR triggers, comment on the PR. For other triggers, comment on the master issue
+          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || env.MASTER_EVAL_ISSUE_NUMBER }}
+          unique: false
+          comment: |
+            **Evaluation Triggered**
+
+            **Trigger:** ${{ github.event_name == 'pull_request' && format('Pull Request #{0}', github.event.pull_request.number) || (github.event_name == 'release' && 'Release') || format('Manual Trigger: {0}', github.event.inputs.reason || 'No reason provided') }}
+            **Branch:** ${{ steps.eval_params.outputs.eval_branch }}
+            **Instances:** ${{ steps.eval_params.outputs.eval_instances }}
+            **Commit:** ${{ github.sha }}
+
+            Running evaluation on the specified branch. Once eval is done, the results will be posted here.

README.md

@@ -1,7 +1,7 @@
 <a name="readme-top"></a>
 
 <div align="center">
-  <img src="https://raw.githubusercontent.com/OpenHands/docs/main/openhands/static/img/logo.png" alt="Logo" width="200">
+  <img src="https://raw.githubusercontent.com/All-Hands-AI/docs/main/openhands/static/img/logo.png" alt="Logo" width="200">
   <h1 align="center" style="border-bottom: none">OpenHands: AI-Driven Development</h1>
 </div>
 
@@ -35,9 +35,9 @@ There are a few ways to work with OpenHands:
 ### OpenHands Software Agent SDK
 The SDK is a composable Python library that contains all of our agentic tech. It's the engine that powers everything else below.
 
-Define agents in code, then run them locally, or scale to 1000s of agents in the cloud.
+Define agents in code, then run them locally, or scale to 1000s of agents in the cloud
 
-[Check out the docs](https://docs.openhands.dev/sdk) or [view the source](https://github.com/OpenHands/software-agent-sdk/)
+[Check out the docs](https://docs.openhands.dev/sdk) or [view the source](https://github.com/All-Hands-AI/agent-sdk/)
 
 ### OpenHands CLI
 The CLI is the easiest way to start using OpenHands. The experience will be familiar to anyone who has worked
@@ -52,15 +52,18 @@ The experience will be familiar to anyone who has used Devin or Jules.
 [Check out the docs](https://docs.openhands.dev/openhands/usage/run-openhands/local-setup) or view the source in this repo.
 
 ### OpenHands Cloud
-This is a deployment of OpenHands GUI, running on hosted infrastructure.
+This is a commercial deployment of OpenHands GUI, running on hosted infrastructure.
 
 You can try it with a free $10 credit by [signing in with your GitHub account](https://app.all-hands.dev).
 
 OpenHands Cloud comes with source-available features and integrations:
+- Deeper integrations with GitHub, GitLab, and Bitbucket
 - Integrations with Slack, Jira, and Linear
 - Multi-user support
 - RBAC and permissions
 - Collaboration features (e.g., conversation sharing)
+- Usage reporting
+- Budgeting enforcement
 
 ### OpenHands Enterprise
 Large enterprises can work with us to self-host OpenHands Cloud in their own VPC, via Kubernetes.

enterprise/integrations/github/github_manager.py

@@ -292,26 +292,18 @@ class GithubManager(Manager):
                     f'[GitHub] Created conversation {conversation_id} for user {user_info.username}'
                 )
 
-                from openhands.server.shared import ConversationStoreImpl, config
-
-                conversation_store = await ConversationStoreImpl.get_instance(
-                    config, github_view.user_info.keycloak_user_id
+                # Create a GithubCallbackProcessor
+                processor = GithubCallbackProcessor(
+                    github_view=github_view,
+                    send_summary_instruction=True,
                 )
-                metadata = await conversation_store.get_metadata(conversation_id)
 
-                if metadata.conversation_version != 'v1':
-                    # Create a GithubCallbackProcessor
-                    processor = GithubCallbackProcessor(
-                        github_view=github_view,
-                        send_summary_instruction=True,
-                    )
+                # Register the callback processor
+                register_callback_processor(conversation_id, processor)
 
-                    # Register the callback processor
-                    register_callback_processor(conversation_id, processor)
-
-                    logger.info(
-                        f'[Github] Registered callback processor for conversation {conversation_id}'
-                    )
+                logger.info(
+                    f'[Github] Registered callback processor for conversation {conversation_id}'
+                )
 
                 # Send message with conversation link
                 conversation_link = CONVERSATION_URL.format(conversation_id)

enterprise/integrations/github/github_view.py

@@ -1,4 +1,4 @@
-from uuid import UUID, uuid4
+from uuid import uuid4
 
 from github import Github, GithubIntegration
 from github.Issue import Issue
@@ -26,22 +26,10 @@ from storage.proactive_conversation_store import ProactiveConversationStore
 from storage.saas_secrets_store import SaasSecretsStore
 from storage.saas_settings_store import SaasSettingsStore
 
-from openhands.agent_server.models import SendMessageRequest
-from openhands.app_server.app_conversation.app_conversation_models import (
-    AppConversationStartRequest,
-    AppConversationStartTaskStatus,
-)
-from openhands.app_server.config import get_app_conversation_service
-from openhands.app_server.services.injector import InjectorState
-from openhands.app_server.user.specifiy_user_context import USER_CONTEXT_ATTR
-from openhands.app_server.user.user_context import UserContext
-from openhands.app_server.user.user_models import UserInfo
 from openhands.core.logger import openhands_logger as logger
 from openhands.integrations.github.github_service import GithubServiceImpl
 from openhands.integrations.provider import PROVIDER_TOKEN_TYPE, ProviderType
 from openhands.integrations.service_types import Comment
-from openhands.sdk import TextContent
-from openhands.sdk.conversation.secret_source import SecretSource
 from openhands.server.services.conversation_service import (
     initialize_conversation,
     start_conversation,
@@ -55,52 +43,6 @@ from openhands.utils.async_utils import call_sync_from_async
 OH_LABEL, INLINE_OH_LABEL = get_oh_labels(HOST)
 
 
-class GithubUserContext(UserContext):
-    """User context for GitHub integration that provides user info without web request."""
-
-    def __init__(self, keycloak_user_id: str, git_provider_tokens: PROVIDER_TOKEN_TYPE):
-        self.keycloak_user_id = keycloak_user_id
-        self.git_provider_tokens = git_provider_tokens
-        self.settings_store = SaasSettingsStore(
-            user_id=self.keycloak_user_id,
-            session_maker=session_maker,
-            config=get_config(),
-        )
-
-        self.secrets_store = SaasSecretsStore(
-            self.keycloak_user_id, session_maker, get_config()
-        )
-
-    async def get_user_id(self) -> str | None:
-        return self.keycloak_user_id
-
-    async def get_user_info(self) -> UserInfo:
-        user_settings = await self.settings_store.load()
-        return UserInfo(
-            id=self.keycloak_user_id,
-            **user_settings.model_dump(context={'expose_secrets': True}),
-        )
-
-    async def get_authenticated_git_url(self, repository: str) -> str:
-        # This would need to be implemented based on the git provider tokens
-        # For now, return a basic HTTPS URL
-        return f'https://github.com/{repository}.git'
-
-    async def get_latest_token(self, provider_type: ProviderType) -> str | None:
-        # Return the appropriate token from git_provider_tokens
-        if provider_type == ProviderType.GITHUB and self.git_provider_tokens:
-            return self.git_provider_tokens.get(ProviderType.GITHUB)
-        return None
-
-    async def get_secrets(self) -> dict[str, SecretSource]:
-        # Return empty dict for now - GitHub integration handles secrets separately
-        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.
 
@@ -134,35 +76,6 @@ async def get_user_proactive_conversation_setting(user_id: str | None) -> bool:
     return settings.enable_proactive_conversation_starters
 
 
-async def get_user_v1_enabled_setting(user_id: str | None) -> bool:
-    """Get the user's V1 conversation API setting.
-
-    Args:
-        user_id: The keycloak user ID
-
-    Returns:
-        True if V1 conversations are enabled for this user, False otherwise
-    """
-
-    # If no user ID is provided, we can't check user settings
-    if not user_id:
-        return False
-
-    config = get_config()
-    settings_store = SaasSettingsStore(
-        user_id=user_id, session_maker=session_maker, config=config
-    )
-
-    settings = await call_sync_from_async(
-        settings_store.get_user_settings_by_keycloak_id, user_id
-    )
-
-    if not settings or settings.v1_enabled is None:
-        return False
-
-    return settings.v1_enabled
-
-
 # =================================================
 # SECTION: Github view types
 # =================================================
@@ -246,31 +159,6 @@ class GithubIssue(ResolverViewInterface):
         git_provider_tokens: PROVIDER_TOKEN_TYPE,
         conversation_metadata: ConversationMetadata,
     ):
-        v1_enabled = await get_user_v1_enabled_setting(self.user_info.keycloak_user_id)
-
-        if v1_enabled:
-            try:
-                # Use V1 app conversation service
-                await self._create_v1_conversation(
-                    jinja_env, git_provider_tokens, conversation_metadata
-                )
-                return
-
-            except Exception as e:
-                logger.warning(f'Error checking V1 settings, falling back to V0: {e}')
-
-        # Use existing V0 conversation service
-        await self._create_v0_conversation(
-            jinja_env, git_provider_tokens, conversation_metadata
-        )
-
-    async def _create_v0_conversation(
-        self,
-        jinja_env: Environment,
-        git_provider_tokens: PROVIDER_TOKEN_TYPE,
-        conversation_metadata: ConversationMetadata,
-    ):
-        """Create conversation using the legacy V0 system."""
         custom_secrets = await self._get_user_secrets()
 
         user_instructions, conversation_instructions = await self._get_instructions(
@@ -289,77 +177,6 @@ class GithubIssue(ResolverViewInterface):
             conversation_instructions=conversation_instructions,
         )
 
-    async def _create_v1_conversation(
-        self,
-        jinja_env: Environment,
-        git_provider_tokens: PROVIDER_TOKEN_TYPE,
-        conversation_metadata: ConversationMetadata,
-    ):
-        """Create conversation using the new V1 app conversation system."""
-        user_instructions, conversation_instructions = await self._get_instructions(
-            jinja_env
-        )
-
-        # Create the initial message request
-        initial_message = SendMessageRequest(
-            role='user', content=[TextContent(text=user_instructions)]
-        )
-
-        # Create the GitHub V1 callback processor
-        github_callback_processor = self._create_github_v1_callback_processor()
-
-        # Get the app conversation service and start the conversation
-        injector_state = InjectorState()
-
-        # Create the V1 conversation start request with the callback processor
-        start_request = AppConversationStartRequest(
-            conversation_id=UUID(conversation_metadata.conversation_id),
-            system_message_suffix=conversation_instructions,
-            initial_message=initial_message,
-            selected_repository=self.full_repo_name,
-            git_provider=ProviderType.GITHUB,
-            title=f'GitHub Issue #{self.issue_number}: {self.title}',
-            trigger=ConversationTrigger.RESOLVER,
-            processors=[
-                github_callback_processor
-            ],  # Pass the callback processor directly
-        )
-
-        # Set up the GitHub user context for the V1 system
-        github_user_context = GithubUserContext(
-            keycloak_user_id=self.user_info.keycloak_user_id,
-            git_provider_tokens=git_provider_tokens,
-        )
-        setattr(injector_state, USER_CONTEXT_ATTR, github_user_context)
-
-        async with get_app_conversation_service(
-            injector_state
-        ) as app_conversation_service:
-            async for task in app_conversation_service.start_app_conversation(
-                start_request
-            ):
-                if task.status == AppConversationStartTaskStatus.ERROR:
-                    logger.error(f'Failed to start V1 conversation: {task.detail}')
-                    raise RuntimeError(
-                        f'Failed to start V1 conversation: {task.detail}'
-                    )
-
-    def _create_github_v1_callback_processor(self):
-        """Create a V1 callback processor for GitHub integration."""
-        from openhands.app_server.event_callback.github_v1_callback_processor import (
-            GithubV1CallbackProcessor,
-        )
-
-        # Create and return the GitHub V1 callback processor
-        return GithubV1CallbackProcessor(
-            github_view_data={
-                'issue_number': self.issue_number,
-                'full_repo_name': self.full_repo_name,
-                'installation_id': self.installation_id,
-            },
-            send_summary_instruction=self.send_summary_instruction,
-        )
-
 
 @dataclass
 class GithubIssueComment(GithubIssue):
@@ -475,24 +292,6 @@ class GithubInlinePRComment(GithubPRComment):
 
         return user_instructions, conversation_instructions
 
-    def _create_github_v1_callback_processor(self):
-        """Create a V1 callback processor for GitHub integration."""
-        from openhands.app_server.event_callback.github_v1_callback_processor import (
-            GithubV1CallbackProcessor,
-        )
-
-        # Create and return the GitHub V1 callback processor
-        return GithubV1CallbackProcessor(
-            github_view_data={
-                'issue_number': self.issue_number,
-                'full_repo_name': self.full_repo_name,
-                'installation_id': self.installation_id,
-                'comment_id': self.comment_id,
-            },
-            inline_pr_comment=True,
-            send_summary_instruction=self.send_summary_instruction,
-        )
-
 
 @dataclass
 class GithubFailingAction:

enterprise/migrations/versions/083_add_v1_enabled_to_user_settings.py

@@ -1,35 +0,0 @@
-"""Add v1_enabled column to user_settings
-
-Revision ID: 083
-Revises: 082
-Create Date: 2025-11-18 00:00:00.000000
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = '083'
-down_revision: Union[str, None] = '082'
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    """Add v1_enabled column to user_settings table."""
-    op.add_column(
-        'user_settings',
-        sa.Column(
-            'v1_enabled',
-            sa.Boolean(),
-            nullable=True,
-        ),
-    )
-
-
-def downgrade() -> None:
-    """Remove v1_enabled column from user_settings table."""
-    op.drop_column('user_settings', 'v1_enabled')

enterprise/poetry.lock

@@ -5820,15 +5820,16 @@ llama = ["llama-index (>=0.12.29,<0.13.0)", "llama-index-core (>=0.12.29,<0.13.0
 
 [[package]]
 name = "openhands-agent-server"
-version = "1.3.0"
+version = "1.1.0"
 description = "OpenHands Agent Server - REST/WebSocket interface for OpenHands AI Agent"
 optional = false
 python-versions = ">=3.12"
 groups = ["main"]
 files = [
-    {file = "openhands_agent_server-1.3.0-py3-none-any.whl", hash = "sha256:2f87f790c740dc3fb81821c5f9fa375af875fbb937ebca3baa6dc5c035035b3c"},
-    {file = "openhands_agent_server-1.3.0.tar.gz", hash = "sha256:0a83ae77373f5c41d0ba0e22d8f0f6144d54d55784183a50b7c098c96cd5135c"},
+    {file = "openhands_agent_server-1.1.0-py3-none-any.whl", hash = "sha256:59a856883df23488c0723e47655ef21649a321fcd4709a25a4690866eff6ac88"},
+    {file = "openhands_agent_server-1.1.0.tar.gz", hash = "sha256:e39bebd39afd45cfcfd765005e7c4e5409e46678bd7612ae20bae79f7057b935"},
 ]
+develop = false
 
 [package.dependencies]
 aiosqlite = ">=0.19"
@@ -5841,9 +5842,16 @@ uvicorn = ">=0.31.1"
 websockets = ">=12"
 wsproto = ">=1.2.0"
 
+[package.source]
+type = "git"
+url = "https://github.com/OpenHands/agent-sdk.git"
+reference = "15f565b8ac38876e40dc05c08e2b04ccaae4a66d"
+resolved_reference = "15f565b8ac38876e40dc05c08e2b04ccaae4a66d"
+subdirectory = "openhands-agent-server"
+
 [[package]]
 name = "openhands-ai"
-version = "0.62.0"
+version = "0.0.0-post.5576+ed2ac6040"
 description = "OpenHands: Code Less, Make More"
 optional = false
 python-versions = "^3.12,<3.14"
@@ -5885,9 +5893,9 @@ memory-profiler = "^0.61.0"
 numpy = "*"
 openai = "1.99.9"
 openhands-aci = "0.3.2"
-openhands-agent-server = "1.3.0"
-openhands-sdk = "1.3.0"
-openhands-tools = "1.3.0"
+openhands-agent-server = "1.1.0"
+openhands-sdk = "1.1.0"
+openhands-tools = "1.1.0"
 opentelemetry-api = "^1.33.1"
 opentelemetry-exporter-otlp-proto-grpc = "^1.33.1"
 pathspec = "^0.12.1"
@@ -5943,15 +5951,16 @@ url = ".."
 
 [[package]]
 name = "openhands-sdk"
-version = "1.3.0"
+version = "1.1.0"
 description = "OpenHands SDK - Core functionality for building AI agents"
 optional = false
 python-versions = ">=3.12"
 groups = ["main"]
 files = [
-    {file = "openhands_sdk-1.3.0-py3-none-any.whl", hash = "sha256:feee838346f8e60ea3e4d3391de7cb854314eb8b3c9e3dbbb56f98a784aadc56"},
-    {file = "openhands_sdk-1.3.0.tar.gz", hash = "sha256:2d060803a78de462121b56dea717a66356922deb02276f37b29fae8af66343fb"},
+    {file = "openhands_sdk-1.1.0-py3-none-any.whl", hash = "sha256:4a984ce1687a48cf99a67fdf3d37b116f8b2840743d4807810b5024af6a1d57e"},
+    {file = "openhands_sdk-1.1.0.tar.gz", hash = "sha256:855e0d8f3657205e4119e50520c17e65b3358b1a923f7a051a82512a54bf426c"},
 ]
+develop = false
 
 [package.dependencies]
 deprecation = ">=2.1.0"
@@ -5968,17 +5977,25 @@ websockets = ">=12"
 [package.extras]
 boto3 = ["boto3 (>=1.35.0)"]
 
+[package.source]
+type = "git"
+url = "https://github.com/OpenHands/agent-sdk.git"
+reference = "15f565b8ac38876e40dc05c08e2b04ccaae4a66d"
+resolved_reference = "15f565b8ac38876e40dc05c08e2b04ccaae4a66d"
+subdirectory = "openhands-sdk"
+
 [[package]]
 name = "openhands-tools"
-version = "1.3.0"
+version = "1.1.0"
 description = "OpenHands Tools - Runtime tools for AI agents"
 optional = false
 python-versions = ">=3.12"
 groups = ["main"]
 files = [
-    {file = "openhands_tools-1.3.0-py3-none-any.whl", hash = "sha256:f31056d87c3058ac92709f9161c7c602daeee3ed0cb4439097b43cda105ed03e"},
-    {file = "openhands_tools-1.3.0.tar.gz", hash = "sha256:3da46f09e28593677d3e17252ce18584fcc13caab1a73213e66bd7edca2cebe0"},
+    {file = "openhands_tools-1.1.0-py3-none-any.whl", hash = "sha256:767d6746f05edade49263aa24450a037485a3dc23379f56917ef19aad22033f9"},
+    {file = "openhands_tools-1.1.0.tar.gz", hash = "sha256:c2fadaa4f4e16e9a3df5781ea847565dcae7171584f09ef7c0e1d97c8dfc83f6"},
 ]
+develop = false
 
 [package.dependencies]
 bashlex = ">=0.18"
@@ -5990,6 +6007,13 @@ libtmux = ">=0.46.2"
 openhands-sdk = "*"
 pydantic = ">=2.11.7"
 
+[package.source]
+type = "git"
+url = "https://github.com/OpenHands/agent-sdk.git"
+reference = "15f565b8ac38876e40dc05c08e2b04ccaae4a66d"
+resolved_reference = "15f565b8ac38876e40dc05c08e2b04ccaae4a66d"
+subdirectory = "openhands-tools"
+
 [[package]]
 name = "openpyxl"
 version = "3.1.5"

enterprise/server/auth/constants.py

@@ -30,11 +30,3 @@ JIRA_DC_CLIENT_SECRET = os.getenv('JIRA_DC_CLIENT_SECRET', '').strip()
 JIRA_DC_BASE_URL = os.getenv('JIRA_DC_BASE_URL', '').strip()
 JIRA_DC_ENABLE_OAUTH = os.getenv('JIRA_DC_ENABLE_OAUTH', '1') in ('1', 'true')
 AUTH_URL = os.getenv('AUTH_URL', '').rstrip('/')
-ROLE_CHECK_ENABLED = os.getenv('ROLE_CHECK_ENABLED', 'false').lower() in (
-    '1',
-    'true',
-    't',
-    'yes',
-    'y',
-    'on',
-)

enterprise/server/auth/saas_user_auth.py

@@ -203,15 +203,6 @@ 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')
@@ -252,12 +243,7 @@ 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
-    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')
+    return request.headers.get('X-Session-API-Key')
 
 
 async def saas_user_auth_from_bearer(request: Request) -> SaasUserAuth | None:

enterprise/server/routes/auth.py

@@ -12,7 +12,6 @@ from server.auth.constants import (
     KEYCLOAK_CLIENT_ID,
     KEYCLOAK_REALM_NAME,
     KEYCLOAK_SERVER_URL_EXT,
-    ROLE_CHECK_ENABLED,
 )
 from server.auth.gitlab_sync import schedule_gitlab_repo_sync
 from server.auth.saas_user_auth import SaasUserAuth
@@ -31,6 +30,7 @@ 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')
@@ -133,12 +133,6 @@ async def keycloak_callback(
 
     user_info = await token_manager.get_user_info(keycloak_access_token)
     logger.debug(f'user_info: {user_info}')
-    if ROLE_CHECK_ENABLED and 'roles' not in user_info:
-        return JSONResponse(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            content={'error': 'Missing required role'},
-        )
-
     if 'sub' not in user_info or 'preferred_username' not in user_info:
         return JSONResponse(
             status_code=status.HTTP_400_BAD_REQUEST,
@@ -369,6 +363,12 @@ 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

@@ -28,6 +28,7 @@ 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')
@@ -457,6 +458,20 @@ 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/storage/saas_settings_store.py

@@ -97,10 +97,6 @@ class SaasSettingsStore(SettingsStore):
             return settings
 
     async def store(self, item: Settings):
-        # Check if provider is OpenHands and generate API key if needed
-        if item and self._is_openhands_provider(item):
-            await self._ensure_openhands_api_key(item)
-
         with self.session_maker() as session:
             existing = None
             kwargs = {}
@@ -372,30 +368,6 @@ class SaasSettingsStore(SettingsStore):
     def _should_encrypt(self, key: str) -> bool:
         return key in ('llm_api_key', 'llm_api_key_for_byor', 'search_api_key')
 
-    def _is_openhands_provider(self, item: Settings) -> bool:
-        """Check if the settings use the OpenHands provider."""
-        return bool(item.llm_model and item.llm_model.startswith('openhands/'))
-
-    async def _ensure_openhands_api_key(self, item: Settings) -> None:
-        """Generate and set the OpenHands API key for the given settings.
-
-        First checks if an existing key with the OpenHands alias exists,
-        and reuses it if found. Otherwise, generates a new key.
-        """
-        # Generate new key if none exists
-        generated_key = await self._generate_openhands_key()
-        if generated_key:
-            item.llm_api_key = SecretStr(generated_key)
-            logger.info(
-                'saas_settings_store:store:generated_openhands_key',
-                extra={'user_id': self.user_id},
-            )
-        else:
-            logger.warning(
-                'saas_settings_store:store:failed_to_generate_openhands_key',
-                extra={'user_id': self.user_id},
-            )
-
     async def _create_user_in_lite_llm(
         self, client: httpx.AsyncClient, email: str | None, max_budget: int, spend: int
     ):
@@ -418,55 +390,3 @@ class SaasSettingsStore(SettingsStore):
             },
         )
         return response
-
-    async def _generate_openhands_key(self) -> str | None:
-        """Generate a new OpenHands provider key for a user."""
-        if not (LITE_LLM_API_KEY and LITE_LLM_API_URL):
-            logger.warning(
-                'saas_settings_store:_generate_openhands_key:litellm_config_not_found',
-                extra={'user_id': self.user_id},
-            )
-            return None
-
-        try:
-            async with httpx.AsyncClient(
-                verify=httpx_verify_option(),
-                headers={
-                    'x-goog-api-key': LITE_LLM_API_KEY,
-                },
-            ) as client:
-                response = await client.post(
-                    f'{LITE_LLM_API_URL}/key/generate',
-                    json={
-                        'user_id': self.user_id,
-                        'metadata': {'type': 'openhands'},
-                    },
-                )
-                response.raise_for_status()
-                response_json = response.json()
-                key = response_json.get('key')
-
-                if key:
-                    logger.info(
-                        'saas_settings_store:_generate_openhands_key:success',
-                        extra={
-                            'user_id': self.user_id,
-                            'key_length': len(key) if key else 0,
-                            'key_prefix': (
-                                key[:10] + '...' if key and len(key) > 10 else key
-                            ),
-                        },
-                    )
-                    return key
-                else:
-                    logger.error(
-                        'saas_settings_store:_generate_openhands_key:no_key_in_response',
-                        extra={'user_id': self.user_id, 'response_json': response_json},
-                    )
-                    return None
-        except Exception as e:
-            logger.exception(
-                'saas_settings_store:_generate_openhands_key:error',
-                extra={'user_id': self.user_id, 'error': str(e)},
-            )
-            return None

enterprise/storage/user_settings.py

@@ -38,4 +38,3 @@ class UserSettings(Base):  # type: ignore
     email_verified = Column(Boolean, nullable=True)
     git_user_name = Column(String, nullable=True)
     git_user_email = Column(String, nullable=True)
-    v1_enabled = Column(Boolean, nullable=True)

enterprise/tests/unit/test_github_view.py

@@ -1,9 +1,7 @@
 from unittest import TestCase, mock
-from unittest.mock import MagicMock, patch
 
-from integrations.github.github_view import GithubFactory, GithubIssue, get_oh_labels
+from integrations.github.github_view import GithubFactory, get_oh_labels
 from integrations.models import Message, SourceType
-from integrations.types import UserData
 
 
 class TestGithubLabels(TestCase):
@@ -77,128 +75,3 @@ class TestGithubCommentCaseInsensitivity(TestCase):
         self.assertTrue(GithubFactory.is_issue_comment(message_lower))
         self.assertTrue(GithubFactory.is_issue_comment(message_upper))
         self.assertTrue(GithubFactory.is_issue_comment(message_mixed))
-
-
-class TestGithubV1ConversationRouting(TestCase):
-    """Test V1 conversation routing logic in GitHub integration."""
-
-    def setUp(self):
-        """Set up test fixtures."""
-        # Create a proper UserData instance instead of MagicMock
-        user_data = UserData(
-            user_id=123, username='testuser', keycloak_user_id='test-keycloak-id'
-        )
-
-        # Create a mock raw_payload
-        raw_payload = Message(
-            source=SourceType.GITHUB,
-            message={
-                'payload': {
-                    'action': 'opened',
-                    'issue': {'number': 123},
-                }
-            },
-        )
-
-        self.github_issue = GithubIssue(
-            user_info=user_data,
-            full_repo_name='test/repo',
-            issue_number=123,
-            installation_id=456,
-            conversation_id='test-conversation-id',
-            should_extract=True,
-            send_summary_instruction=False,
-            is_public_repo=True,
-            raw_payload=raw_payload,
-            uuid='test-uuid',
-            title='Test Issue',
-            description='Test issue description',
-            previous_comments=[],
-        )
-
-    @patch('integrations.github.github_view.get_user_v1_enabled_setting')
-    @patch.object(GithubIssue, '_create_v0_conversation')
-    @patch.object(GithubIssue, '_create_v1_conversation')
-    async def test_create_new_conversation_routes_to_v0_when_disabled(
-        self, mock_create_v1, mock_create_v0, mock_get_v1_setting
-    ):
-        """Test that conversation creation routes to V0 when v1_enabled is False."""
-        # Mock v1_enabled as False
-        mock_get_v1_setting.return_value = False
-        mock_create_v0.return_value = None
-        mock_create_v1.return_value = None
-
-        # Mock parameters
-        jinja_env = MagicMock()
-        git_provider_tokens = MagicMock()
-        conversation_metadata = MagicMock()
-
-        # Call the method
-        await self.github_issue.create_new_conversation(
-            jinja_env, git_provider_tokens, conversation_metadata
-        )
-
-        # Verify V0 was called and V1 was not
-        mock_create_v0.assert_called_once_with(
-            jinja_env, git_provider_tokens, conversation_metadata
-        )
-        mock_create_v1.assert_not_called()
-
-    @patch('integrations.github.github_view.get_user_v1_enabled_setting')
-    @patch.object(GithubIssue, '_create_v0_conversation')
-    @patch.object(GithubIssue, '_create_v1_conversation')
-    async def test_create_new_conversation_routes_to_v1_when_enabled(
-        self, mock_create_v1, mock_create_v0, mock_get_v1_setting
-    ):
-        """Test that conversation creation routes to V1 when v1_enabled is True."""
-        # Mock v1_enabled as True
-        mock_get_v1_setting.return_value = True
-        mock_create_v0.return_value = None
-        mock_create_v1.return_value = None
-
-        # Mock parameters
-        jinja_env = MagicMock()
-        git_provider_tokens = MagicMock()
-        conversation_metadata = MagicMock()
-
-        # Call the method
-        await self.github_issue.create_new_conversation(
-            jinja_env, git_provider_tokens, conversation_metadata
-        )
-
-        # Verify V1 was called and V0 was not
-        mock_create_v1.assert_called_once_with(
-            jinja_env, git_provider_tokens, conversation_metadata
-        )
-        mock_create_v0.assert_not_called()
-
-    @patch('integrations.github.github_view.get_user_v1_enabled_setting')
-    @patch.object(GithubIssue, '_create_v0_conversation')
-    @patch.object(GithubIssue, '_create_v1_conversation')
-    async def test_create_new_conversation_fallback_on_v1_setting_error(
-        self, mock_create_v1, mock_create_v0, mock_get_v1_setting
-    ):
-        """Test that conversation creation falls back to V0 when _create_v1_conversation fails."""
-        # Mock v1_enabled as True so V1 is attempted
-        mock_get_v1_setting.return_value = True
-        # Mock _create_v1_conversation to raise an exception
-        mock_create_v1.side_effect = Exception('V1 conversation creation failed')
-        mock_create_v0.return_value = None
-
-        # Mock parameters
-        jinja_env = MagicMock()
-        git_provider_tokens = MagicMock()
-        conversation_metadata = MagicMock()
-
-        # Call the method
-        await self.github_issue.create_new_conversation(
-            jinja_env, git_provider_tokens, conversation_metadata
-        )
-
-        # Verify V1 was attempted first, then V0 was called as fallback
-        mock_create_v1.assert_called_once_with(
-            jinja_env, git_provider_tokens, conversation_metadata
-        )
-        mock_create_v0.assert_called_once_with(
-            jinja_env, git_provider_tokens, conversation_metadata
-        )

enterprise/tests/unit/test_saas_user_auth.py

@@ -535,115 +535,3 @@ 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 == ''

evaluation/benchmarks/swefficiency/README.md

@@ -1,65 +0,0 @@
-# SWE-fficiency Evaluation
-
-This folder contains the OpenHands inference generation of the [SWE-fficiency benchmark](https://swefficiency.com/) ([paper](https://arxiv.org/pdf/2507.12415v1)).
-
-The evaluation consists of three steps:
-
-1. Environment setup: [install python environment](../../README.md#development-environment) and [configure LLM config](../../README.md#configure-openhands-and-your-llm).
-2. [Run inference](#running-inference-locally-with-docker): Generate a edit patch for each Github issue
-3. [Evaluate patches](#evaluate-generated-patches)
-
-## Setup Environment and LLM Configuration
-
-Please follow instruction [here](../../README.md#setup) to setup your local development environment and LLM.
-
-## Running inference Locally with Docker
-
-Make sure your Docker daemon is running, and you have ample disk space (at least 200-500GB, depends on the SWE-PErf set you are running on) for the instance-level docker image.
-
-When the `run_infer.sh` script is started, it will automatically pull the relevant SWE-Perf images.
-For example, for instance ID `scikit-learn_scikit-learn-11674`, it will try to pull our pre-build docker image `betty1202/sweb.eval.x86_64.scikit-learn_s_scikit-learn-11674` from DockerHub.
-This image will be used create an OpenHands runtime image where the agent will operate on.
-
-```bash
-./evaluation/benchmarks/swefficiency/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split] [n_runs] [mode]
-
-# Example
-./evaluation/benchmarks/swefficiency/scripts/run_infer.sh llm.eval_gpt4_1106_preview HEAD CodeActAgent 500 100 1 swefficiency/swefficiency test
-```
-
-where `model_config` is mandatory, and the rest are optional.
-
-- `model_config`, e.g. `eval_gpt4_1106_preview`, is the config group name for your
-LLM settings, as defined in your `config.toml`.
-- `git-version`, e.g. `HEAD`, is the git commit hash of the OpenHands version you would
-like to evaluate. It could also be a release tag like `0.6.2`.
-- `agent`, e.g. `CodeActAgent`, is the name of the agent for benchmarks, defaulting
-to `CodeActAgent`.
-- `eval_limit`, e.g. `10`, limits the evaluation to the first `eval_limit` instances. By
-default, the script evaluates the entire SWE-Perf test set (140 issues). Note:
-in order to use `eval_limit`, you must also set `agent`.
-- `max_iter`, e.g. `20`, is the maximum number of iterations for the agent to run. By
-default, it is set to 100.
-- `num_workers`, e.g. `3`, is the number of parallel workers to run the evaluation. By
-default, it is set to 1.
-- `dataset`, a huggingface dataset name. e.g. `SWE-Perf/SWE-Perf`, specifies which dataset to evaluate on.
-- `dataset_split`, split for the huggingface dataset. e.g., `test`, `dev`. Default to `test`.
-
-- `n_runs`, e.g. `3`, is the number of times to run the evaluation. Default is 1.
-- `mode`, e.g. `swt`, `swt-ci`, or `swe`, specifies the evaluation mode. Default is `swe`.
-
-> [!CAUTION]
-> Setting `num_workers` larger than 1 is not officially tested, YMMV.
-
-
-Let's say you'd like to run 10 instances using `llm.eval_gpt4_1106_preview` and CodeActAgent,
-
-then your command would be:
-
-```bash
-./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval_gpt4_1106_preview HEAD CodeActAgent 10
-```
-
-### 2. Run the SWE-fficiency benchmark official evaluation
-
-Once the output is converted, use the [official SWE-fficiency benchmark evaluation](https://github.com/swefficiency/swefficiency) to evaluate it.

evaluation/benchmarks/swefficiency/binary_patch_utils.py

@@ -1,52 +0,0 @@
-"""
-Utilities for handling binary files and patch generation in SWE-bench evaluation.
-"""
-
-
-def remove_binary_diffs(patch_text):
-    """
-    Remove binary file diffs from a git patch.
-
-    Args:
-        patch_text (str): The git patch text
-
-    Returns:
-        str: The cleaned patch text with binary diffs removed
-    """
-    lines = patch_text.splitlines()
-    cleaned_lines = []
-    block = []
-    is_binary_block = False
-
-    for line in lines:
-        if line.startswith('diff --git '):
-            if block and not is_binary_block:
-                cleaned_lines.extend(block)
-            block = [line]
-            is_binary_block = False
-        elif 'Binary files' in line:
-            is_binary_block = True
-            block.append(line)
-        else:
-            block.append(line)
-
-    if block and not is_binary_block:
-        cleaned_lines.extend(block)
-    return '\n'.join(cleaned_lines)
-
-
-def remove_binary_files_from_git():
-    """
-    Generate a bash command to remove binary files from git staging.
-
-    Returns:
-        str: A bash command that removes binary files from git staging
-    """
-    return """
-    for file in $(git status --porcelain | grep -E "^(M| M|\\?\\?|A| A)" | cut -c4-); do
-        if [ -f "$file" ] && (file "$file" | grep -q "executable" || git check-attr binary "$file" | grep -q "binary: set"); then
-            git rm -f "$file" 2>/dev/null || rm -f "$file"
-            echo "Removed: $file"
-        fi
-    done
-    """.strip()

evaluation/benchmarks/swefficiency/run_infer.py

@@ -1,960 +0,0 @@
-import asyncio
-import copy
-import functools
-import json
-import multiprocessing
-import os
-import tempfile
-from typing import Any, Literal
-
-import pandas as pd
-import toml
-from datasets import load_dataset
-
-import openhands.agenthub
-from evaluation.benchmarks.swe_bench.binary_patch_utils import (
-    remove_binary_diffs,
-    remove_binary_files_from_git,
-)
-from evaluation.utils.shared import (
-    EvalException,
-    EvalMetadata,
-    EvalOutput,
-    assert_and_raise,
-    codeact_user_response,
-    get_default_sandbox_config_for_eval,
-    get_metrics,
-    is_fatal_evaluation_error,
-    make_metadata,
-    prepare_dataset,
-    reset_logger_for_multiprocessing,
-    run_evaluation,
-    update_llm_config_for_completions_logging,
-)
-from openhands.controller.state.state import State
-from openhands.core.config import (
-    AgentConfig,
-    OpenHandsConfig,
-    get_evaluation_parser,
-    get_llm_config_arg,
-)
-from openhands.core.config.condenser_config import NoOpCondenserConfig
-from openhands.core.config.utils import get_condenser_config_arg
-from openhands.core.logger import openhands_logger as logger
-from openhands.core.main import create_runtime, run_controller
-from openhands.critic import AgentFinishedCritic
-from openhands.events.action import CmdRunAction, FileReadAction, MessageAction
-from openhands.events.observation import (
-    CmdOutputObservation,
-    ErrorObservation,
-    FileReadObservation,
-)
-from openhands.events.serialization.event import event_from_dict, event_to_dict
-from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync
-from openhands.utils.shutdown_listener import sleep_if_should_continue
-
-USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
-RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'true'
-BenchMode = Literal['swe', 'swt', 'swt-ci']
-
-
-AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
-    'CodeActAgent': codeact_user_response,
-}
-
-
-def _get_swebench_workspace_dir_name(instance: pd.Series) -> str:
-    return f'{instance.repo}__{instance.version}'.replace('/', '__')
-
-
-def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageAction:
-    workspace_dir_name = _get_swebench_workspace_dir_name(instance)
-
-    # TODO: Change to testbed?
-    instruction = f"""
-<uploaded_files>
-/workspace/{workspace_dir_name}
-</uploaded_files>
-
-I’ve uploaded a python code repository in the directory workspace_dir_name. Consider the following performance workload and `workload()` function showing an specific usage of the repository:
-<performance_workload>
-{instance.workload}
-</performance_workload>
-
-Can you help me implement the necessary changes to the repository so that the runtime of the `workload()` function is faster? Basic guidelines:
-1. Your task is to make changes to non-test files in the /workspace directory to improve the performance of the code running in `workload()`. Please do not directly change the implementation of the `workload()` function to optimize things: I want you to focus on making the workload AS IS run faster by only editing the repository containing code that the `workload()` function calls.
-2. Make changes while ensuring the repository is functionally equivalent to the original: your changes should not introduce new bugs or cause already-passing tests to begin failing after your changes. However, you do not need to worry about tests that already fail without any changes made. For relevant test files you find in the repository, you can run them via the bash command `{instance.test_cmd} <test_file>` to check for correctness. Note that running all the tests may take a long time, so you need to determine which tests are relevant to your changes.
-3. Make sure the `workload()` function improves in performance after you make changes to the repository. The workload can potentially take some time to run, so please allow it to finish and be generous with setting your timeout parameter (a timeout value of 3600 or larger here is encouraged): for faster iteration, you should adjust the workload script to use fewer iterations. Before you complete your task, please make sure to check that the **original performance workload** and `workload()` function runs successfully and the performance is improved.
-4. You may need to reinstall/rebuild the repo for your changes to take effect before testing if you made non-Python changes. Reinstalling may take a long time to run (a timeout value of 3600 or larger here is encouraged), so please be patient with running it and allow it to complete if possible. You can reinstall the repository by running the bash command `{instance.rebuild_cmd}` in the workspace directory.
-5. All the dependencies required to run the `workload()` function are already installed in the environment. You should not install or upgrade any dependencies.
-
-Follow these steps to improve performance:
-1. As a first step, explore the repository structure.
-2. Create a Python script to reproduce the performance workload, execute it with python <workload_file>, and examine the printed output metrics.
-3. Edit the source code of the repository to improve performance. Please do not change the contents of the `workload()` function itself, but focus on optimizing the code in the repository that the original `workload()` function uses.
-4. If non-Python changes were made, rebuild the repo to make sure the changes take effect.
-5. Rerun your script to confirm that performance has improved.
-6. If necessary, identify any relevant test files in the repository related to your changes and verify that test statuses did not change after your modifications.
-7. After each attempted change, please reflect on the changes attempted and the performance impact observed. If the performance did not improve, consider alternative approaches or optimizations.
-8. Once you are satisfied, please use the finish command to complete your task.
-
-Please remember that you should not change the implementation of the `workload()` function. The performance improvement should solely come from editing the source files in the code repository.
-"""
-
-    if RUN_WITH_BROWSING:
-        instruction += (
-            '<IMPORTANT!>\nYou SHOULD NEVER attempt to browse the web. </IMPORTANT!>\n'
-        )
-
-    return MessageAction(content=instruction)
-
-
-def get_instance_docker_image(
-    instance_id: str,
-) -> str:
-    return f'ghcr.io/swefficiency/swefficiency-images:{instance_id}'
-
-
-def get_config(
-    instance: pd.Series,
-    metadata: EvalMetadata,
-    cpu_group: list[int] | None = None,
-) -> OpenHandsConfig:
-    # We use a different instance image for the each instance of swe-bench eval
-    base_container_image = get_instance_docker_image(
-        instance['instance_id'],
-    )
-    logger.info(
-        f'Using instance container image: {base_container_image}. '
-        f'Please make sure this image exists. '
-        f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
-    )
-
-    sandbox_config = get_default_sandbox_config_for_eval()
-    sandbox_config.base_container_image = base_container_image
-    sandbox_config.enable_auto_lint = True
-    sandbox_config.use_host_network = False
-    sandbox_config.timeout = 3600
-
-    # Control container cleanup behavior via environment variable
-    # Default to False for multiprocessing stability to prevent cascade failures
-    sandbox_config.rm_all_containers = True
-
-    sandbox_config.platform = 'linux/amd64'
-    sandbox_config.remote_runtime_resource_factor = 4.0
-    sandbox_config.runtime_startup_env_vars.update(
-        {
-            'NO_CHANGE_TIMEOUT_SECONDS': '900',  # 15 minutes
-        }
-    )
-
-    if cpu_group is not None:
-        print(f'Configuring Docker runtime with CPU group: {cpu_group}')
-        sandbox_config.docker_runtime_kwargs = {
-            # HACK: Use the cpu_group if provided, otherwise use all available CPUs
-            'cpuset_cpus': ','.join(map(str, cpu_group)),
-            'nano_cpus': int(1e9 * len(cpu_group)),  # optional: hard cap to vCPU count
-            'mem_limit': '16g',
-        }
-
-    # Note: We keep rm_all_containers = False for worker process safety
-
-    config = OpenHandsConfig(
-        default_agent=metadata.agent_class,
-        run_as_openhands=False,
-        max_iterations=metadata.max_iterations,
-        runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox=sandbox_config,
-        # do not mount workspace
-        workspace_base=None,
-        workspace_mount_path=None,
-    )
-    config.set_llm_config(
-        update_llm_config_for_completions_logging(
-            metadata.llm_config, metadata.eval_output_dir, instance['instance_id']
-        )
-    )
-    agent_config = AgentConfig(
-        enable_jupyter=False,
-        enable_browsing=RUN_WITH_BROWSING,
-        enable_llm_editor=False,
-        enable_mcp=False,
-        condenser=metadata.condenser_config,
-        enable_prompt_extensions=False,
-    )
-    config.set_agent_config(agent_config)
-    return config
-
-
-def initialize_runtime(
-    runtime: Runtime,
-    instance: pd.Series,  # this argument is not required
-    metadata: EvalMetadata,
-):
-    """Initialize the runtime for the agent.
-
-    This function is called before the runtime is used to run the agent.
-    """
-    logger.info('-' * 30)
-    logger.info('BEGIN Runtime Initialization Fn')
-    logger.info('-' * 30)
-    workspace_dir_name = _get_swebench_workspace_dir_name(instance)
-    obs: CmdOutputObservation
-
-    # Set instance id and git configuration
-    action = CmdRunAction(
-        command=f"""echo 'export SWE_INSTANCE_ID={instance['instance_id']}' >> ~/.bashrc && echo 'export PIP_CACHE_DIR=~/.cache/pip' >> ~/.bashrc && echo "alias git='git --no-pager'" >> ~/.bashrc && git config --global core.pager "" && git config --global diff.binary false"""
-    )
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        obs.exit_code == 0,
-        f'Failed to export SWE_INSTANCE_ID and configure git: {str(obs)}',
-    )
-
-    action = CmdRunAction(command="""export USER=$(whoami); echo USER=${USER} """)
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(obs.exit_code == 0, f'Failed to export USER: {str(obs)}')
-
-    # inject the init script
-    script_dir = os.path.dirname(__file__)
-
-    # inject the instance info
-    action = CmdRunAction(command='mkdir -p /swe_util/eval_data/instances')
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        obs.exit_code == 0,
-        f'Failed to create /swe_util/eval_data/instances: {str(obs)}',
-    )
-
-    swe_instance_json_name = 'swe-bench-instance.json'
-    with tempfile.TemporaryDirectory() as temp_dir:
-        # Construct the full path for the desired file name within the temporary directory
-        temp_file_path = os.path.join(temp_dir, swe_instance_json_name)
-        # Write to the file with the desired name within the temporary directory
-        with open(temp_file_path, 'w') as f:
-            if not isinstance(instance, dict):
-                json.dump([instance.to_dict()], f)
-            else:
-                json.dump([instance], f)
-
-        # Copy the file to the desired location
-        runtime.copy_to(temp_file_path, '/swe_util/eval_data/instances/')
-
-        # inject the instance swe entry
-        runtime.copy_to(
-            str(os.path.join(script_dir, 'scripts/setup/instance_swe_entry.sh')),
-            '/swe_util/',
-        )
-
-    action = CmdRunAction(command='cat ~/.bashrc')
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(obs.exit_code == 0, f'Failed to cat ~/.bashrc: {str(obs)}')
-
-    action = CmdRunAction(command='source ~/.bashrc')
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    if isinstance(obs, ErrorObservation):
-        logger.error(f'Failed to source ~/.bashrc: {str(obs)}')
-    assert_and_raise(obs.exit_code == 0, f'Failed to source ~/.bashrc: {str(obs)}')
-
-    action = CmdRunAction(command='source /swe_util/instance_swe_entry.sh')
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        obs.exit_code == 0,
-        f'Failed to source /swe_util/instance_swe_entry.sh: {str(obs)}',
-    )
-
-    action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        obs.exit_code == 0,
-        f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
-    )
-
-    action = CmdRunAction(command='git reset --hard')
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(obs.exit_code == 0, f'Failed to git reset --hard: {str(obs)}')
-
-    action = CmdRunAction(
-        command='for remote_name in $(git remote); do git remote remove "${remote_name}"; done'
-    )
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(obs.exit_code == 0, f'Failed to remove git remotes: {str(obs)}')
-
-    action = CmdRunAction(command='which python')
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        obs.exit_code == 0 and 'testbed' in obs.content,
-        f'Expected to find python interpreter from testbed, but got: {str(obs)}',
-    )
-
-    logger.info('-' * 30)
-    logger.info('END Runtime Initialization Fn')
-    logger.info('-' * 30)
-
-
-def complete_runtime(
-    runtime: Runtime,
-    instance: pd.Series,  # this argument is not required, but it is used to get the workspace_dir_name
-) -> dict[str, Any]:
-    """Complete the runtime for the agent.
-
-    This function is called before the runtime is used to run the agent.
-    If you need to do something in the sandbox to get the correctness metric after
-    the agent has run, modify this function.
-    """
-    logger.info('-' * 30)
-    logger.info('BEGIN Runtime Completion Fn')
-    logger.info('-' * 30)
-    obs: CmdOutputObservation
-    workspace_dir_name = _get_swebench_workspace_dir_name(instance)
-
-    action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-
-    if obs.exit_code == -1:
-        # The previous command is still running
-        # We need to kill previous command
-        logger.info('The previous command is still running, trying to kill it...')
-        action = CmdRunAction(command='C-c')
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-
-        # Then run the command again
-        action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
-        action.set_hard_timeout(600)
-        logger.info(action, extra={'msg_type': 'ACTION'})
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-
-    if obs.exit_code == -1:
-        # The previous command is still running
-        # We need to kill previous command
-        logger.info('The previous command is still running, trying to ctrl+z it...')
-        action = CmdRunAction(command='C-z')
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-
-        # Then run the command again
-        action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
-        action.set_hard_timeout(600)
-        logger.info(action, extra={'msg_type': 'ACTION'})
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
-        f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
-    )
-
-    action = CmdRunAction(command='git config --global core.pager ""')
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
-        f'Failed to git config --global core.pager "": {str(obs)}',
-    )
-
-    # First check for any git repositories in subdirectories
-    action = CmdRunAction(command='find . -type d -name .git -not -path "./.git"')
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
-        f'Failed to find git repositories: {str(obs)}',
-    )
-
-    git_dirs = [p for p in obs.content.strip().split('\n') if p]
-    if git_dirs:
-        # Remove all .git directories in subdirectories
-        for git_dir in git_dirs:
-            action = CmdRunAction(command=f'rm -rf "{git_dir}"')
-            action.set_hard_timeout(600)
-            logger.info(action, extra={'msg_type': 'ACTION'})
-            obs = runtime.run_action(action)
-            logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-            assert_and_raise(
-                isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
-                f'Failed to remove git directory {git_dir}: {str(obs)}',
-            )
-
-    # add all files
-    action = CmdRunAction(command='git add -A')
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
-        f'Failed to git add -A: {str(obs)}',
-    )
-
-    # Remove binary files from git staging
-    action = CmdRunAction(command=remove_binary_files_from_git())
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
-        f'Failed to remove binary files: {str(obs)}',
-    )
-
-    n_retries = 0
-    git_patch = None
-    while n_retries < 5:
-        action = CmdRunAction(
-            command=f'git diff --no-color --cached {instance["base_commit"]} > patch.diff'
-        )
-        action.set_hard_timeout(max(300 + 100 * n_retries, 600))
-        logger.info(action, extra={'msg_type': 'ACTION'})
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-        n_retries += 1
-        if isinstance(obs, CmdOutputObservation):
-            if obs.exit_code == 0:
-                # Read the patch file
-                action = FileReadAction(path='patch.diff')
-                action.set_hard_timeout(max(300 + 100 * n_retries, 600))
-                logger.info(action, extra={'msg_type': 'ACTION'})
-                obs = runtime.run_action(action)
-                logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-                if isinstance(obs, FileReadObservation):
-                    git_patch = obs.content
-                    break
-                elif isinstance(obs, ErrorObservation):
-                    # Fall back to cat "patch.diff" to get the patch
-                    assert 'File could not be decoded as utf-8' in obs.content
-                    action = CmdRunAction(command='cat patch.diff')
-                    action.set_hard_timeout(max(300 + 100 * n_retries, 600))
-                    logger.info(action, extra={'msg_type': 'ACTION'})
-                    obs = runtime.run_action(action)
-                    assert isinstance(obs, CmdOutputObservation) and obs.exit_code == 0
-                    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-                    git_patch = obs.content
-                    break
-                else:
-                    assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
-            else:
-                logger.info('Failed to get git diff, retrying...')
-                sleep_if_should_continue(10)
-        elif isinstance(obs, ErrorObservation):
-            logger.error(f'Error occurred: {obs.content}. Retrying...')
-            sleep_if_should_continue(10)
-        else:
-            assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
-
-    assert_and_raise(git_patch is not None, 'Failed to get git diff (None)')
-
-    # Remove binary diffs from the patch
-    git_patch = remove_binary_diffs(git_patch)
-
-    logger.info('-' * 30)
-    logger.info('END Runtime Completion Fn')
-    logger.info('-' * 30)
-    return {'git_patch': git_patch}
-
-
-class CPUGroupManager:
-    def __init__(self, cpu_groups_queue: multiprocessing.Queue):
-        self.cpu_groups_queue = cpu_groups_queue
-
-    def __enter__(self):
-        # Get the current CPU group for this worker]
-        if self.cpu_groups_queue is not None:
-            self.cpu_group = self.cpu_groups_queue.get()
-            logger.info(f'Worker started with CPU group: {self.cpu_group}')
-            return self.cpu_group
-        return None
-
-    def __exit__(self, exc_type, exc_value, traceback):
-        # Put the CPU group back into the queue for other workers to use
-        if self.cpu_groups_queue is not None:
-            self.cpu_groups_queue.put(self.cpu_group)
-            logger.info(f'Worker finished with CPU group: {self.cpu_group}')
-
-
-def cleanup_docker_resources_for_worker():
-    """Clean up Docker resources specific to this worker process.
-
-    This prevents cascade failures when one worker's container crashes.
-    Note: This only cleans up stale locks, not containers, to avoid
-    interfering with other workers. Container cleanup is handled
-    by the DockerRuntime.close() method based on configuration.
-    """
-
-    # Clean up any stale port locks from crashed processes
-    try:
-        from openhands.runtime.utils.port_lock import cleanup_stale_locks
-
-        cleanup_stale_locks(max_age_seconds=300)  # Clean up locks older than 5 minutes
-    except Exception as e:
-        logger.debug(f'Error cleaning up stale port locks: {e}')
-
-
-def process_instance(
-    instance: pd.Series,
-    metadata: EvalMetadata,
-    reset_logger: bool = True,
-    runtime_failure_count: int = 0,
-    cpu_groups_queue: multiprocessing.Queue = None,
-) -> EvalOutput:
-    # Clean up any Docker resources from previous failed runs
-    cleanup_docker_resources_for_worker()
-
-    # HACK: Use the global and get the cpu group for this worker.
-    with CPUGroupManager(cpu_groups_queue) as cpu_group:
-        config = get_config(instance, metadata, cpu_group=cpu_group)
-
-        # Setup the logger properly, so you can run multi-processing to parallelize the evaluation
-        if reset_logger:
-            log_dir = os.path.join(metadata.eval_output_dir, 'infer_logs')
-            reset_logger_for_multiprocessing(logger, instance.instance_id, log_dir)
-        else:
-            logger.info(f'Starting evaluation for instance {instance.instance_id}.')
-
-        metadata = copy.deepcopy(metadata)
-        metadata.details['runtime_failure_count'] = runtime_failure_count
-        metadata.details['remote_runtime_resource_factor'] = (
-            config.sandbox.remote_runtime_resource_factor
-        )
-
-        runtime = create_runtime(config, sid=None)
-        call_async_from_sync(runtime.connect)
-
-        try:
-            initialize_runtime(runtime, instance, metadata)
-
-            message_action = get_instruction(instance, metadata)
-
-            # Here's how you can run the agent (similar to the `main` function) and get the final task state
-            state: State | None = asyncio.run(
-                run_controller(
-                    config=config,
-                    initial_user_action=message_action,
-                    runtime=runtime,
-                    fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
-                        metadata.agent_class
-                    ],
-                )
-            )
-
-            # if fatal error, throw EvalError to trigger re-run
-            if is_fatal_evaluation_error(state.last_error):
-                raise EvalException('Fatal error detected: ' + state.last_error)
-
-            # ======= THIS IS SWE-Bench specific =======
-            # Get git patch
-            return_val = complete_runtime(runtime, instance)
-            git_patch = return_val['git_patch']
-            logger.info(
-                f'Got git diff for instance {instance.instance_id}:\n--------\n{git_patch}\n--------'
-            )
-        except Exception as e:
-            # Log the error but don't let it crash other workers
-            logger.error(
-                f'Error in worker processing instance {instance.instance_id}: {str(e)}'
-            )
-            raise
-        finally:
-            # Ensure runtime is properly closed to prevent cascade failures
-            try:
-                runtime.close()
-            except Exception as e:
-                logger.warning(
-                    f'Error closing runtime for {instance.instance_id}: {str(e)}'
-                )
-                # Don't re-raise - we want to continue cleanup
-
-        # ==========================================
-
-        # ======= Attempt to evaluate the agent's edits =======
-        # we use eval_infer.sh to evaluate the agent's edits, not here
-        # because the agent may alter the environment / testcases
-        test_result = {
-            'git_patch': git_patch,
-        }
-
-        # If you are working on some simpler benchmark that only evaluates the final model output (e.g., in a MessageAction)
-        # You can simply get the LAST `MessageAction` from the returned `state.history` and parse it for evaluation.
-        if state is None:
-            raise ValueError('State should not be None.')
-
-        # NOTE: this is NO LONGER the event stream, but an agent history that includes delegate agent's events
-        histories = [event_to_dict(event) for event in state.history]
-        metrics = get_metrics(state)
-
-        # Save the output
-        instruction = message_action.content
-        if message_action.image_urls:
-            instruction += (
-                '\n\n<image_urls>'
-                + '\n'.join(message_action.image_urls)
-                + '</image_urls>'
-            )
-        output = EvalOutput(
-            instance_id=instance.instance_id,
-            instruction=instruction,
-            instance=instance.to_dict(),  # SWE Bench specific
-            test_result=test_result,
-            metadata=metadata,
-            history=histories,
-            metrics=metrics,
-            error=state.last_error if state and state.last_error else None,
-        )
-        return output
-
-
-def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
-    file_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'config.toml')
-    if os.path.exists(file_path):
-        with open(file_path, 'r') as file:
-            data = toml.load(file)
-            if 'selected_ids' in data:
-                selected_ids = data['selected_ids']
-                logger.info(
-                    f'Filtering {len(selected_ids)} tasks from "selected_ids"...'
-                )
-                subset = dataset[dataset[filter_column].isin(selected_ids)]
-                logger.info(f'Retained {subset.shape[0]} tasks after filtering')
-                return subset
-            if 'selected_repos' in data:
-                # repos for the swe-bench instances:
-                # ['astropy/astropy', 'django/django', 'matplotlib/matplotlib', 'mwaskom/seaborn', 'pallets/flask', 'psf/requests', 'pydata/xarray', 'pylint-dev/pylint', 'pytest-dev/pytest', 'scikit-learn/scikit-learn', 'sphinx-doc/sphinx', 'sympy/sympy']
-                selected_repos = data['selected_repos']
-                if isinstance(selected_repos, str):
-                    selected_repos = [selected_repos]
-                assert isinstance(selected_repos, list)
-                logger.info(
-                    f'Filtering {selected_repos} tasks from "selected_repos"...'
-                )
-                subset = dataset[dataset['repo'].isin(selected_repos)]
-                logger.info(f'Retained {subset.shape[0]} tasks after filtering')
-                return subset
-
-    skip_ids = os.environ.get('SKIP_IDS', '').split(',')
-    if len(skip_ids) > 0:
-        logger.info(f'Filtering {len(skip_ids)} tasks from "SKIP_IDS"...')
-        return dataset[~dataset[filter_column].isin(skip_ids)]
-    return dataset
-
-
-def divide_cpus_among_workers(num_workers, num_cpus_per_worker=4, num_to_skip=0):
-    """Divide CPUs among workers, with better error handling for multiprocessing."""
-    try:
-        current_cpus = list(os.sched_getaffinity(0))
-    except AttributeError:
-        # os.sched_getaffinity not available on all platforms
-        import multiprocessing
-
-        current_cpus = list(range(multiprocessing.cpu_count()))
-
-    num_cpus = len(current_cpus)
-    if num_workers <= 0:
-        raise ValueError('Number of workers must be greater than 0')
-
-    # Chec that num worers and num_cpus_per_worker fit into available CPUs
-    total_cpus_needed = num_workers * num_cpus_per_worker + num_to_skip
-    if total_cpus_needed > num_cpus:
-        raise ValueError(
-            f'Not enough CPUs available. Requested {total_cpus_needed} '
-            f'CPUs (num_workers={num_workers}, num_cpus_per_worker={num_cpus_per_worker}, '
-            f'num_to_skip={num_to_skip}), but only {num_cpus} CPUs are available.'
-        )
-
-    # Divide this into groups, skipping the first `num_to_skip` CPUs.
-    available_cpus = current_cpus[num_to_skip:]
-    cpu_groups = [
-        available_cpus[i * num_cpus_per_worker : (i + 1) * num_cpus_per_worker]
-        for i in range(num_workers)
-    ]
-    print(
-        f'Divided {num_cpus} CPUs into {num_workers} groups, each with {num_cpus_per_worker} CPUs.'
-    )
-    print(f'CPU groups: {cpu_groups}')
-
-    return cpu_groups
-
-
-if __name__ == '__main__':
-    parser = get_evaluation_parser()
-    parser.add_argument(
-        '--dataset',
-        type=str,
-        default=None,
-        help='data set to evaluate on, for now use local.',
-    )
-    parser.add_argument(
-        '--split',
-        type=str,
-        default='test',
-        help='split to evaluate on',
-    )
-    parser.add_argument(
-        '--mode',
-        type=str,
-        default='swe',
-        help='mode to evaluate on',
-    )
-
-    args, _ = parser.parse_known_args()
-
-    # NOTE: It is preferable to load datasets from huggingface datasets and perform post-processing
-    # so we don't need to manage file uploading to OpenHands's repo
-
-    # dataset = load_dataset(args.dataset, split=args.split)
-    # swe_bench_tests = filter_dataset(dataset.to_pandas(), 'instance_id')
-    dataset = load_dataset(args.dataset, split=args.split)
-
-    # Convert dataset to pandas DataFrame if it is not already.
-    if not isinstance(dataset, pd.DataFrame):
-        dataset = dataset.to_pandas()
-
-    dataset['version'] = dataset['version'].astype(str)
-
-    # Convert created_at column to string.
-    dataset['created_at'] = dataset['created_at'].astype(str)
-
-    swe_bench_tests = filter_dataset(dataset, 'instance_id')
-
-    logger.info(
-        f'Loaded dataset {args.dataset} with split {args.split}: {len(swe_bench_tests)} tasks'
-    )
-
-    llm_config = None
-    if args.llm_config:
-        llm_config = get_llm_config_arg(args.llm_config)
-        llm_config.log_completions = True
-        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
-        llm_config.modify_params = False
-
-    if llm_config is None:
-        raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
-
-    # Get condenser config from environment variable
-    condenser_name = os.environ.get('EVAL_CONDENSER')
-    if condenser_name:
-        condenser_config = get_condenser_config_arg(condenser_name)
-        if condenser_config is None:
-            raise ValueError(
-                f'Could not find Condenser config: EVAL_CONDENSER={condenser_name}'
-            )
-    else:
-        # If no specific condenser config is provided via env var, default to NoOpCondenser
-        condenser_config = NoOpCondenserConfig()
-        logger.debug(
-            'No Condenser config provided via EVAL_CONDENSER, using NoOpCondenser.'
-        )
-
-    details = {'mode': args.mode}
-    _agent_cls = openhands.agenthub.Agent.get_cls(args.agent_cls)
-
-    dataset_descrption = (
-        args.dataset.replace('/', '__') + '-' + args.split.replace('/', '__')
-    )
-    metadata = make_metadata(
-        llm_config,
-        dataset_descrption,
-        args.agent_cls,
-        args.max_iterations,
-        args.eval_note,
-        args.eval_output_dir,
-        details=details,
-        condenser_config=condenser_config,
-    )
-
-    output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
-    print(f'### OUTPUT FILE: {output_file} ###')
-
-    # Run evaluation in iterative mode:
-    # If a rollout fails to output AgentFinishAction, we will try again until it succeeds OR total 3 attempts have been made.
-    ITERATIVE_EVAL_MODE = (
-        os.environ.get('ITERATIVE_EVAL_MODE', 'false').lower() == 'true'
-    )
-    ITERATIVE_EVAL_MODE_MAX_ATTEMPTS = int(
-        os.environ.get('ITERATIVE_EVAL_MODE_MAX_ATTEMPTS', '3')
-    )
-
-    # Get all CPUs and divide into groups of num_workers and put them into a multiprocessing.Queue.
-    cpu_groups_queue = None
-    cpu_groups_list = divide_cpus_among_workers(args.eval_num_workers, num_to_skip=8)
-    cpu_groups_queue = multiprocessing.Manager().Queue()
-    for cpu_group in cpu_groups_list:
-        cpu_groups_queue.put(cpu_group)
-
-    if not ITERATIVE_EVAL_MODE:
-        # load the dataset
-        instances = prepare_dataset(swe_bench_tests, output_file, args.eval_n_limit)
-
-        process_instance_with_cpu_groups = functools.partial(
-            process_instance,
-            cpu_groups_queue=cpu_groups_queue,
-        )
-
-        config = get_config(
-            instances.iloc[0],  # Use the first instance to get the config
-            metadata,
-            cpu_group=None,  # We will use the cpu_groups_queue to get the cpu group later
-        )
-
-        run_evaluation(
-            instances,
-            metadata,
-            output_file,
-            args.eval_num_workers,
-            process_instance_with_cpu_groups,
-            timeout_seconds=8
-            * 60
-            * 60,  # 8 hour PER instance should be more than enough
-            max_retries=3,
-        )
-    else:
-        critic = AgentFinishedCritic()
-
-        def get_cur_output_file_path(attempt: int) -> str:
-            return (
-                f'{output_file.removesuffix(".jsonl")}.critic_attempt_{attempt}.jsonl'
-            )
-
-        eval_ids = None
-        for attempt in range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1):
-            cur_output_file = get_cur_output_file_path(attempt)
-            logger.info(
-                f'Running evaluation with critic {critic.__class__.__name__} for attempt {attempt} of {ITERATIVE_EVAL_MODE_MAX_ATTEMPTS}.'
-            )
-
-            # For deterministic eval, we set temperature to 0.1 for (>1) attempt
-            # so hopefully we get slightly different results
-            if attempt > 1 and metadata.llm_config.temperature == 0:
-                logger.info(
-                    f'Detected temperature is 0 for (>1) attempt {attempt}. Setting temperature to 0.1...'
-                )
-                metadata.llm_config.temperature = 0.1
-
-            # Load instances - at first attempt, we evaluate all instances
-            # On subsequent attempts, we only evaluate the instances that failed the previous attempt determined by critic
-            instances = prepare_dataset(
-                swe_bench_tests, cur_output_file, args.eval_n_limit, eval_ids=eval_ids
-            )
-            if len(instances) > 0 and not isinstance(
-                instances['PASS_TO_PASS'][instances['PASS_TO_PASS'].index[0]], str
-            ):
-                for col in ['PASS_TO_PASS', 'FAIL_TO_PASS']:
-                    instances[col] = instances[col].apply(lambda x: str(x))
-
-            # Run evaluation - but save them to cur_output_file
-            logger.info(
-                f'Evaluating {len(instances)} instances for attempt {attempt}...'
-            )
-            run_evaluation(
-                instances,
-                metadata,
-                cur_output_file,
-                args.eval_num_workers,
-                process_instance,
-                timeout_seconds=8
-                * 60
-                * 60,  # 8 hour PER instance should be more than enough
-                max_retries=1,
-            )
-
-            # When eval is done, we update eval_ids to the instances that failed the current attempt
-            instances_failed = []
-            logger.info(
-                f'Use critic {critic.__class__.__name__} to check {len(instances)} instances for attempt {attempt}...'
-            )
-            with open(cur_output_file, 'r') as f:
-                for line in f:
-                    instance = json.loads(line)
-                    try:
-                        history = [
-                            event_from_dict(event) for event in instance['history']
-                        ]
-                        critic_result = critic.evaluate(
-                            history, instance['test_result'].get('git_patch', '')
-                        )
-                        if not critic_result.success:
-                            instances_failed.append(instance['instance_id'])
-                    except Exception as e:
-                        logger.error(
-                            f'Error loading history for instance {instance["instance_id"]}: {e}'
-                        )
-                        instances_failed.append(instance['instance_id'])
-            logger.info(
-                f'{len(instances_failed)} instances failed the current attempt {attempt}: {instances_failed}'
-            )
-            eval_ids = instances_failed
-
-            # If no instances failed, we break
-            if len(instances_failed) == 0:
-                break
-
-        # Then we should aggregate the results from all attempts into the original output file
-        # and remove the intermediate files
-        logger.info(
-            'Aggregating results from all attempts into the original output file...'
-        )
-        fout = open(output_file, 'w')
-        added_instance_ids = set()
-        for attempt in reversed(range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1)):
-            cur_output_file = get_cur_output_file_path(attempt)
-            if not os.path.exists(cur_output_file):
-                logger.warning(
-                    f'Intermediate output file {cur_output_file} does not exist. Skipping...'
-                )
-                continue
-
-            with open(cur_output_file, 'r') as f:
-                for line in f:
-                    instance = json.loads(line)
-                    # Also make sure git_patch is not empty - otherwise we fall back to previous attempt (empty patch is worse than anything else)
-                    if (
-                        instance['instance_id'] not in added_instance_ids
-                        and instance['test_result'].get('git_patch', '').strip()
-                    ):
-                        fout.write(line)
-                        added_instance_ids.add(instance['instance_id'])
-            logger.info(
-                f'Aggregated instances from {cur_output_file}. Total instances added so far: {len(added_instance_ids)}'
-            )
-        fout.close()
-        logger.info(
-            f'Done! Total {len(added_instance_ids)} instances added to {output_file}'
-        )

evaluation/benchmarks/swefficiency/scripts/run_infer.sh

@@ -1,148 +0,0 @@
-#!/usr/bin/env bash
-set -eo pipefail
-
-source "evaluation/utils/version_control.sh"
-
-MODEL_CONFIG=$1
-COMMIT_HASH=$2
-AGENT=$3
-EVAL_LIMIT=$4
-MAX_ITER=$5
-NUM_WORKERS=$6
-DATASET=$7
-SPLIT=$8
-N_RUNS=$9
-MODE=${10}
-
-
-if [ -z "$NUM_WORKERS" ]; then
-  NUM_WORKERS=1
-  echo "Number of workers not specified, use default $NUM_WORKERS"
-fi
-checkout_eval_branch
-
-if [ -z "$AGENT" ]; then
-  echo "Agent not specified, use default CodeActAgent"
-  AGENT="CodeActAgent"
-fi
-
-if [ -z "$MAX_ITER" ]; then
-  echo "MAX_ITER not specified, use default 100"
-  MAX_ITER=100
-fi
-
-if [ -z "$RUN_WITH_BROWSING" ]; then
-  echo "RUN_WITH_BROWSING not specified, use default false"
-  RUN_WITH_BROWSING=false
-fi
-
-
-if [ -z "$DATASET" ]; then
-  echo "DATASET not specified, use default princeton-nlp/SWE-bench_Lite"
-  DATASET="swefficiency/swefficiency"
-fi
-
-if [ -z "$SPLIT" ]; then
-  echo "SPLIT not specified, use default test"
-  SPLIT="test"
-fi
-
-if [ -z "$MODE" ]; then
-  MODE="swe"
-  echo "MODE not specified, use default $MODE"
-fi
-
-if [ -n "$EVAL_CONDENSER" ]; then
-  echo "Using Condenser Config: $EVAL_CONDENSER"
-else
-  echo "No Condenser Config provided via EVAL_CONDENSER, use default (NoOpCondenser)."
-fi
-
-export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
-echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
-
-get_openhands_version
-
-echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
-echo "MODEL_CONFIG: $MODEL_CONFIG"
-echo "DATASET: $DATASET"
-echo "SPLIT: $SPLIT"
-echo "MAX_ITER: $MAX_ITER"
-echo "NUM_WORKERS: $NUM_WORKERS"
-echo "COMMIT_HASH: $COMMIT_HASH"
-echo "MODE: $MODE"
-echo "EVAL_CONDENSER: $EVAL_CONDENSER"
-
-# Default to NOT use Hint
-if [ -z "$USE_HINT_TEXT" ]; then
-  export USE_HINT_TEXT=false
-fi
-echo "USE_HINT_TEXT: $USE_HINT_TEXT"
-EVAL_NOTE="$OPENHANDS_VERSION"
-# if not using Hint, add -no-hint to the eval note
-if [ "$USE_HINT_TEXT" = false ]; then
-  EVAL_NOTE="$EVAL_NOTE-no-hint"
-fi
-
-if [ "$RUN_WITH_BROWSING" = true ]; then
-  EVAL_NOTE="$EVAL_NOTE-with-browsing"
-fi
-
-if [ -n "$EXP_NAME" ]; then
-  EVAL_NOTE="$EVAL_NOTE-$EXP_NAME"
-fi
-# if mode != swe, add mode to the eval note
-if [ "$MODE" != "swe" ]; then
-  EVAL_NOTE="${EVAL_NOTE}-${MODE}"
-fi
-# Add condenser config to eval note if provided
-if [ -n "$EVAL_CONDENSER" ]; then
-  EVAL_NOTE="${EVAL_NOTE}-${EVAL_CONDENSER}"
-fi
-
-# export RUNTIME="remote"
-# export SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev"
-export NO_CHANGE_TIMEOUT_SECONDS=900 # 15 minutes
-
-function run_eval() {
-  local eval_note="${1}"
-  COMMAND="poetry run python evaluation/benchmarks/swefficiency/run_infer.py \
-    --agent-cls $AGENT \
-    --llm-config $MODEL_CONFIG \
-    --max-iterations $MAX_ITER \
-    --eval-num-workers $NUM_WORKERS \
-    --eval-note $eval_note \
-    --dataset $DATASET \
-    --split $SPLIT \
-    --mode $MODE"
-
-  if [ -n "$EVAL_LIMIT" ]; then
-    echo "EVAL_LIMIT: $EVAL_LIMIT"
-    COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
-  fi
-
-  # Run the command
-  eval $COMMAND
-}
-
-unset SANDBOX_ENV_GITHUB_TOKEN # prevent the agent from using the github token to push
-if [ -z "$N_RUNS" ]; then
-  N_RUNS=1
-  echo "N_RUNS not specified, use default $N_RUNS"
-fi
-
-# Skip runs if the run number is in the SKIP_RUNS list
-# read from env variable SKIP_RUNS as a comma separated list of run numbers
-SKIP_RUNS=(${SKIP_RUNS//,/ })
-for i in $(seq 1 $N_RUNS); do
-  if [[ " ${SKIP_RUNS[@]} " =~ " $i " ]]; then
-    echo "Skipping run $i"
-    continue
-  fi
-  current_eval_note="$EVAL_NOTE-run_$i"
-  echo "EVAL_NOTE: $current_eval_note"
-  run_eval $current_eval_note
-done
-
-checkout_original_branch

evaluation/benchmarks/swefficiency/scripts/setup/instance_swe_entry.sh

@@ -1,43 +0,0 @@
-#!/usr/bin/env bash
-
-source ~/.bashrc
-SWEUTIL_DIR=/swe_util
-
-# FIXME: Cannot read SWE_INSTANCE_ID from the environment variable
-# SWE_INSTANCE_ID=django__django-11099
-if [ -z "$SWE_INSTANCE_ID" ]; then
-    echo "Error: SWE_INSTANCE_ID is not set." >&2
-    exit 1
-fi
-
-# Read the swe-bench-test-lite.json file and extract the required item based on instance_id
-item=$(jq --arg INSTANCE_ID "$SWE_INSTANCE_ID" '.[] | select(.instance_id == $INSTANCE_ID)' $SWEUTIL_DIR/eval_data/instances/swe-bench-instance.json)
-
-if [[ -z "$item" ]]; then
-  echo "No item found for the provided instance ID."
-  exit 1
-fi
-
-
-WORKSPACE_NAME=$(echo "$item" | jq -r '(.repo | tostring) + "__" + (.version | tostring) | gsub("/"; "__")')
-
-echo "WORKSPACE_NAME: $WORKSPACE_NAME"
-
-# Clear the workspace
-if [ -d /workspace ]; then
-    rm -rf /workspace/*
-else
-    mkdir /workspace
-fi
-# Copy repo to workspace
-if [ -d /workspace/$WORKSPACE_NAME ]; then
-    rm -rf /workspace/$WORKSPACE_NAME
-fi
-mkdir -p /workspace
-cp -r /testbed /workspace/$WORKSPACE_NAME
-
-# Activate instance-specific environment
-if [ -d /opt/miniconda3 ]; then
-    . /opt/miniconda3/etc/profile.d/conda.sh
-    conda activate testbed
-fi

evaluation/benchmarks/swefficiency/scripts/setup/prepare_swe_utils.sh

@@ -1,27 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-EVAL_WORKSPACE="evaluation/benchmarks/swe_bench/eval_workspace"
-mkdir -p $EVAL_WORKSPACE
-
-# 1. Prepare REPO
-echo "==== Prepare SWE-bench repo ===="
-OH_SWE_BENCH_REPO_PATH="https://github.com/All-Hands-AI/SWE-bench.git"
-OH_SWE_BENCH_REPO_BRANCH="eval"
-git clone -b $OH_SWE_BENCH_REPO_BRANCH $OH_SWE_BENCH_REPO_PATH $EVAL_WORKSPACE/OH-SWE-bench
-
-# 2. Prepare DATA
-echo "==== Prepare SWE-bench data ===="
-EVAL_IMAGE=ghcr.io/all-hands-ai/eval-swe-bench:builder_with_conda
-EVAL_WORKSPACE=$(realpath $EVAL_WORKSPACE)
-chmod +x $EVAL_WORKSPACE/OH-SWE-bench/swebench/harness/prepare_data.sh
-if [ -d $EVAL_WORKSPACE/eval_data ]; then
-    rm -r $EVAL_WORKSPACE/eval_data
-fi
-docker run \
-    -v $EVAL_WORKSPACE:/workspace \
-    -w /workspace \
-    -u $(id -u):$(id -g) \
-    -e HF_DATASETS_CACHE="/tmp" \
-    --rm -it $EVAL_IMAGE \
-    bash -c "cd OH-SWE-bench/swebench/harness && /swe_util/miniforge3/bin/conda run -n swe-bench-eval ./prepare_data.sh && mv eval_data /workspace/"

evaluation/benchmarks/swefficiency/scripts/setup/swe_entry.sh

@@ -1,96 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-
-# assert user name is `root`
-if [ "$USER" != "root" ]; then
-    echo "Error: This script is intended to be run by the 'root' user only." >&2
-    exit 1
-fi
-
-source ~/.bashrc
-
-SWEUTIL_DIR=/swe_util
-
-# Create logs directory
-LOG_DIR=/openhands/logs
-mkdir -p $LOG_DIR && chmod 777 $LOG_DIR
-
-# FIXME: Cannot read SWE_INSTANCE_ID from the environment variable
-# SWE_INSTANCE_ID=django__django-11099
-if [ -z "$SWE_INSTANCE_ID" ]; then
-    echo "Error: SWE_INSTANCE_ID is not set." >&2
-    exit 1
-fi
-
-# Read the swe-bench-test-lite.json file and extract the required item based on instance_id
-item=$(jq --arg INSTANCE_ID "$SWE_INSTANCE_ID" '.[] | select(.instance_id == $INSTANCE_ID)' $SWEUTIL_DIR/eval_data/instances/swe-bench-test-lite.json)
-
-if [[ -z "$item" ]]; then
-  echo "No item found for the provided instance ID."
-  exit 1
-fi
-
-CONDA_ENV_NAME=$(echo "$item" | jq -r '.repo + "__" + .version | gsub("/"; "__")')
-
-echo "CONDA_ENV_NAME: $CONDA_ENV_NAME"
-
-SWE_TASK_DIR=/openhands/swe_tasks
-mkdir -p $SWE_TASK_DIR
-# Dump test_patch to /workspace/test.patch
-echo "$item" | jq -r '.test_patch' > $SWE_TASK_DIR/test.patch
-# Dump patch to /workspace/gold.patch
-echo "$item" | jq -r '.patch' > $SWE_TASK_DIR/gold.patch
-# Dump the item to /workspace/instance.json except for the "test_patch" and "patch" fields
-echo "$item" | jq 'del(.test_patch, .patch)' > $SWE_TASK_DIR/instance.json
-
-# Clear the workspace
-rm -rf /workspace/*
-# Copy repo to workspace
-if [ -d /workspace/$CONDA_ENV_NAME ]; then
-    rm -rf /workspace/$CONDA_ENV_NAME
-fi
-cp -r $SWEUTIL_DIR/eval_data/testbeds/$CONDA_ENV_NAME /workspace
-
-# Reset swe-bench testbed and install the repo
-. $SWEUTIL_DIR/miniforge3/etc/profile.d/conda.sh
-conda config --set changeps1 False
-conda config --append channels conda-forge
-conda activate swe-bench-eval
-
-mkdir -p $SWE_TASK_DIR/reset_testbed_temp
-mkdir -p $SWE_TASK_DIR/reset_testbed_log_dir
-SWE_BENCH_DIR=/swe_util/OH-SWE-bench
-output=$(
-    export PYTHONPATH=$SWE_BENCH_DIR && \
-    cd $SWE_BENCH_DIR && \
-    python swebench/harness/reset_swe_env.py \
-    --swe_bench_tasks $SWEUTIL_DIR/eval_data/instances/swe-bench-test.json \
-    --temp_dir $SWE_TASK_DIR/reset_testbed_temp \
-    --testbed /workspace \
-    --conda_path $SWEUTIL_DIR/miniforge3 \
-    --instance_id $SWE_INSTANCE_ID \
-    --log_dir $SWE_TASK_DIR/reset_testbed_log_dir \
-    --timeout 900 \
-    --verbose
-)
-
-REPO_PATH=$(echo "$output" | awk -F': ' '/repo_path:/ {print $2}')
-TEST_CMD=$(echo "$output" | awk -F': ' '/test_cmd:/ {print $2}')
-echo "Repo Path: $REPO_PATH"
-echo "Test Command: $TEST_CMD"
-
-echo "export SWE_BENCH_DIR=\"$SWE_BENCH_DIR\"" >> ~/.bashrc
-echo "export REPO_PATH=\"$REPO_PATH\"" >> ~/.bashrc
-echo "export TEST_CMD=\"$TEST_CMD\"" >> ~/.bashrc
-
-if [[ "$REPO_PATH" == "None" ]]; then
-    echo "Error: Failed to retrieve repository path. Tests may not have passed or output was not as expected." >&2
-    exit 1
-fi
-
-# Activate instance-specific environment
-. $SWEUTIL_DIR/miniforge3/etc/profile.d/conda.sh
-conda activate $CONDA_ENV_NAME
-
-set +e

frontend/__tests__/components/features/home/repo-connector.test.tsx

@@ -71,7 +71,6 @@ beforeEach(() => {
     provider_tokens_set: {
       github: "some-token",
       gitlab: null,
-      azure_devops: null,
     },
   });
 });

frontend/__tests__/components/features/home/task-card.test.tsx

@@ -23,7 +23,6 @@ const MOCK_RESPOSITORIES: GitRepository[] = [
   { id: "2", full_name: "repo2", git_provider: "github", is_public: true },
   { id: "3", full_name: "repo3", git_provider: "gitlab", is_public: true },
   { id: "4", full_name: "repo4", git_provider: "gitlab", is_public: true },
-  { id: "5", full_name: "repo5", git_provider: "azure_devops", is_public: true },
 ];
 
 const renderTaskCard = (task = MOCK_TASK_1) => {

frontend/__tests__/routes/git-settings.test.tsx

@@ -124,9 +124,6 @@ describe("Content", () => {
     await screen.findByTestId("bitbucket-token-input");
     await screen.findByTestId("bitbucket-token-help-anchor");
 
-    await screen.findByTestId("azure-devops-token-input");
-    await screen.findByTestId("azure-devops-token-help-anchor");
-
     getConfigSpy.mockResolvedValue(VALID_SAAS_CONFIG);
     queryClient.invalidateQueries();
     rerender();
@@ -152,13 +149,6 @@ describe("Content", () => {
       expect(
         screen.queryByTestId("bitbucket-token-help-anchor"),
       ).not.toBeInTheDocument();
-
-      expect(
-        screen.queryByTestId("azure-devops-token-input"),
-      ).not.toBeInTheDocument();
-      expect(
-        screen.queryByTestId("azure-devops-token-help-anchor"),
-      ).not.toBeInTheDocument();
     });
   });
 
@@ -297,7 +287,6 @@ describe("Form submission", () => {
       github: { token: "test-token", host: "" },
       gitlab: { token: "", host: "" },
       bitbucket: { token: "", host: "" },
-      azure_devops: { token: "", host: "" },
     });
   });
 
@@ -319,7 +308,6 @@ describe("Form submission", () => {
       github: { token: "", host: "" },
       gitlab: { token: "test-token", host: "" },
       bitbucket: { token: "", host: "" },
-      azure_devops: { token: "", host: "" },
     });
   });
 
@@ -341,29 +329,6 @@ describe("Form submission", () => {
       github: { token: "", host: "" },
       gitlab: { token: "", host: "" },
       bitbucket: { token: "test-token", host: "" },
-      azure_devops: { token: "", host: "" },
-    });
-  });
-
-  it("should save the Azure DevOps token", async () => {
-    const saveProvidersSpy = vi.spyOn(SecretsService, "addGitProvider");
-    saveProvidersSpy.mockImplementation(() => Promise.resolve(true));
-    const getConfigSpy = vi.spyOn(OptionService, "getConfig");
-    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
-
-    renderGitSettingsScreen();
-
-    const azureDevOpsInput = await screen.findByTestId("azure-devops-token-input");
-    const submit = await screen.findByTestId("submit-button");
-
-    await userEvent.type(azureDevOpsInput, "test-token");
-    await userEvent.click(submit);
-
-    expect(saveProvidersSpy).toHaveBeenCalledWith({
-      github: { token: "", host: "" },
-      gitlab: { token: "", host: "" },
-      bitbucket: { token: "", host: "" },
-      azure_devops: { token: "test-token", host: "" },
     });
   });
 

frontend/__tests__/utils/convert-raw-providers-to-list.test.ts

@@ -7,7 +7,6 @@ describe("convertRawProvidersToList", () => {
     const example1: Partial<Record<Provider, string | null>> | undefined = {
       github: "test-token",
       gitlab: "test-token",
-      azure_devops: "test-token",
     };
     const example2: Partial<Record<Provider, string | null>> | undefined = {
       github: "",
@@ -15,13 +14,9 @@ describe("convertRawProvidersToList", () => {
     const example3: Partial<Record<Provider, string | null>> | undefined = {
       gitlab: null,
     };
-    const example4: Partial<Record<Provider, string | null>> | undefined = {
-      azure_devops: "test-token",
-    };
 
-    expect(convertRawProvidersToList(example1)).toEqual(["github", "gitlab", "azure_devops"]);
+    expect(convertRawProvidersToList(example1)).toEqual(["github", "gitlab"]);
     expect(convertRawProvidersToList(example2)).toEqual(["github"]);
     expect(convertRawProvidersToList(example3)).toEqual(["gitlab"]);
-    expect(convertRawProvidersToList(example4)).toEqual(["azure_devops"]);
   });
 });

frontend/package-lock.json

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

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

@@ -296,25 +296,6 @@ class V1ConversationService {
     const { data } = await openHands.get<{ runtime_id: string }>(url);
     return data;
   }
-
-  /**
-   * Read a file from a specific conversation's sandbox workspace
-   * @param conversationId The conversation ID
-   * @param filePath Path to the file to read within the sandbox workspace (defaults to /workspace/project/PLAN.md)
-   * @returns The content of the file or an empty string if the file doesn't exist
-   */
-  static async readConversationFile(
-    conversationId: string,
-    filePath: string = "/workspace/project/PLAN.md",
-  ): Promise<string> {
-    const params = new URLSearchParams();
-    params.append("file_path", filePath);
-
-    const { data } = await openHands.get<string>(
-      `/api/v1/app-conversations/${conversationId}/file?${params.toString()}`,
-    );
-    return data;
-  }
 }
 
 export default V1ConversationService;

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

@@ -3,19 +3,15 @@ import { Provider } from "#/types/settings";
 import { V1SandboxStatus } from "../sandbox-service/sandbox-service.types";
 
 // V1 API Types for requests
-// These types match the SDK's TextContent and ImageContent formats
-export interface V1TextContent {
-  type: "text";
-  text: string;
+// 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;
+  };
 }
 
-export interface V1ImageContent {
-  type: "image";
-  image_urls: string[];
-}
-
-export type V1MessageContent = V1TextContent | V1ImageContent;
-
 type V1Role = "user" | "system" | "assistant" | "tool";
 
 export interface V1SendMessageRequest {

frontend/src/assets/branding/azure-devops-logo.svg

@@ -1 +0,0 @@
-<svg height="24" viewBox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg"><path fill="currentColor" d="m22 18-5 4-8-3v3l-4.19-5.75 12.91 1.05v-10.96l4.28-.69zm-17.19-1.75v-7.29l12.91-2.62-7.12-4.34v2.84l-6.63 1.92-1.97 2.62v5.69z"/></svg>

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

@@ -12,15 +12,20 @@ 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, subConversationTaskId } =
-    useConversationStore();
+  const {
+    conversationMode,
+    setConversationMode,
+    setSubConversationTaskId,
+    subConversationTaskId,
+  } = useConversationStore();
 
   const webSocketStatus = useUnifiedWebSocketStatus();
 
@@ -35,6 +40,8 @@ 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(
@@ -42,9 +49,6 @@ 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) {
@@ -52,6 +56,45 @@ 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

@@ -1,9 +1,15 @@
 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;
@@ -13,7 +19,6 @@ interface ChatMessageProps {
     onClick: () => void;
     tooltip?: string;
   }>;
-  isFromPlanningAgent?: boolean;
 }
 
 export function ChatMessage({
@@ -21,7 +26,6 @@ export function ChatMessage({
   message,
   children,
   actions,
-  isFromPlanningAgent = false,
 }: React.PropsWithChildren<ChatMessageProps>) {
   const [isHovering, setIsHovering] = React.useState(false);
   const [isCopy, setIsCopy] = React.useState(false);
@@ -55,7 +59,6 @@ export function ChatMessage({
         "flex flex-col gap-2",
         type === "user" && " p-4 bg-tertiary self-end",
         type === "agent" && "mt-6 w-full max-w-full bg-transparent",
-        isFromPlanningAgent && "border border-[#597ff4] bg-tertiary p-4",
       )}
     >
       <div
@@ -110,7 +113,18 @@ export function ChatMessage({
           wordBreak: "break-word",
         }}
       >
-        <MarkdownRenderer includeStandard>{message}</MarkdownRenderer>
+        <Markdown
+          components={{
+            code,
+            ul,
+            ol,
+            a: anchor,
+            p: paragraph,
+          }}
+          remarkPlugins={[remarkGfm, remarkBreaks]}
+        >
+          {message}
+        </Markdown>
       </div>
       {children}
     </article>

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

@@ -1,9 +1,13 @@
 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;
@@ -36,7 +40,18 @@ export function ErrorMessage({ errorId, defaultMessage }: ErrorMessageProps) {
         </button>
       </div>
 
-      {showDetails && <MarkdownRenderer>{defaultMessage}</MarkdownRenderer>}
+      {showDetails && (
+        <Markdown
+          components={{
+            code,
+            ul,
+            ol,
+          }}
+          remarkPlugins={[remarkGfm, remarkBreaks]}
+        >
+          {defaultMessage}
+        </Markdown>
+      )}
     </div>
   );
 }

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

@@ -1,6 +1,9 @@
 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";
@@ -10,7 +13,9 @@ 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 { MarkdownRenderer } from "../markdown/markdown-renderer";
+import { code } from "../markdown/code";
+import { ol, ul } from "../markdown/list";
+import { paragraph } from "../markdown/paragraph";
 import { MonoComponent } from "./mono-component";
 import { PathComponent } from "./path-component";
 
@@ -187,7 +192,17 @@ export function ExpandableMessage({
         </div>
         {showDetails && (
           <div className="text-sm">
-            <MarkdownRenderer includeStandard>{details}</MarkdownRenderer>
+            <Markdown
+              components={{
+                code,
+                ul,
+                ol,
+                p: paragraph,
+              }}
+              remarkPlugins={[remarkGfm, remarkBreaks]}
+            >
+              {details}
+            </Markdown>
           </div>
         )}
       </div>

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

@@ -1,9 +1,13 @@
 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;
@@ -45,7 +49,16 @@ export function GenericEventMessage({
 
       {showDetails &&
         (typeof details === "string" ? (
-          <MarkdownRenderer>{details}</MarkdownRenderer>
+          <Markdown
+            components={{
+              code,
+              ul,
+              ol,
+            }}
+            remarkPlugins={[remarkGfm, remarkBreaks]}
+          >
+            {details}
+          </Markdown>
         ) : (
           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(lastUpdatedAt ?? createdAt)} ${t(I18nKey.CONVERSATION$AGO)}`}
+            {`${formatTimeDelta(new Date(lastUpdatedAt ?? createdAt))} ${t(I18nKey.CONVERSATION$AGO)}`}
           </time>
         </p>
       )}

frontend/src/components/features/conversation-panel/conversation-card/conversation-repo-link.tsx

@@ -3,13 +3,12 @@ import { FaCodeBranch } from "react-icons/fa";
 import { IconType } from "react-icons/lib";
 import { RepositorySelection } from "#/api/open-hands.types";
 import { Provider } from "#/types/settings";
-import AzureDevOpsLogo from "#/assets/branding/azure-devops-logo.svg?react";
 
 interface ConversationRepoLinkProps {
   selectedRepository: RepositorySelection;
 }
 
-const providerIcon: Partial<Record<Provider, IconType>> = {
+const providerIcon: Record<Provider, IconType> = {
   bitbucket: FaBitbucket,
   github: FaGithub,
   gitlab: FaGitlab,
@@ -27,9 +26,6 @@ export function ConversationRepoLink({
     <div className="flex items-center gap-3 flex-1">
       <div className="flex items-center gap-1">
         {Icon && <Icon size={14} className="text-[#A3A3A3]" />}
-        {selectedRepository.git_provider === "azure_devops" && (
-          <AzureDevOpsLogo className="text-[#A3A3A3] w-[14px] h-[14px]" />
-        )}
         <span
           data-testid="conversation-card-selected-repository"
           className="text-xs text-[#A3A3A3] whitespace-nowrap overflow-hidden text-ellipsis max-w-44"

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(createdAt)} ${t(I18nKey.CONVERSATION$AGO)}`}
+              {`${formatTimeDelta(new Date(createdAt))} ${t(I18nKey.CONVERSATION$AGO)}`}
             </time>
           </p>
         )}

frontend/src/components/features/conversation/metrics-modal/context-window-section.tsx

@@ -12,8 +12,7 @@ export function ContextWindowSection({
 }: ContextWindowSectionProps) {
   const { t } = useTranslation();
 
-  const usagePercentage =
-    contextWindow > 0 ? (perTurnToken / contextWindow) * 100 : 0;
+  const usagePercentage = (perTurnToken / contextWindow) * 100;
   const progressWidth = Math.min(100, usagePercentage);
 
   return (

frontend/src/components/features/home/git-provider-dropdown/git-provider-dropdown.tsx

@@ -51,8 +51,6 @@ export function GitProviderDropdown({
         return "GitLab";
       case "bitbucket":
         return "Bitbucket";
-      case "azure_devops":
-        return "Azure DevOps";
       case "enterprise_sso":
         return "Enterprise SSO";
       default:

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

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

frontend/src/components/features/home/tasks/task-card.tsx

@@ -56,15 +56,6 @@ export function TaskCard({ task }: TaskCardProps) {
     const issueType =
       task.task_type === "OPEN_ISSUE" ? "issues" : "pull-requests";
     href = `https://bitbucket.org/${task.repo}/${issueType}/${task.issue_number}`;
-  } else if (task.git_provider === "azure_devops") {
-    // Azure DevOps URL format: https://dev.azure.com/{organization}/{project}/_workitems/edit/{id}
-    // or https://dev.azure.com/{organization}/{project}/_git/{repo}/pullrequest/{id}
-    const azureDevOpsBaseUrl = "https://dev.azure.com";
-    if (task.task_type === "OPEN_ISSUE") {
-      href = `${azureDevOpsBaseUrl}/${task.repo}/_workitems/edit/${task.issue_number}`;
-    } else {
-      href = `${azureDevOpsBaseUrl}/${task.repo}/_git/${task.repo.split("/")[1]}/pullrequest/${task.issue_number}`;
-    }
   } else {
     const hrefType = task.task_type === "OPEN_ISSUE" ? "issues" : "pull";
     href = `https://github.com/${task.repo}/${hrefType}/${task.issue_number}`;

frontend/src/components/features/markdown/headings.tsx

@@ -8,7 +8,7 @@ export function h1({
   React.HTMLAttributes<HTMLHeadingElement> &
   ExtraProps) {
   return (
-    <h1 className="text-2xl text-white font-bold leading-8 mb-4 mt-6 first:mt-0">
+    <h1 className="text-[32px] text-white font-bold leading-8 mb-4 mt-6 first:mt-0">
       {children}
     </h1>
   );

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

@@ -1,80 +0,0 @@
-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

@@ -1,10 +1,16 @@
 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();
@@ -43,9 +49,18 @@ export function MicroagentManagementViewMicroagentContent() {
         </div>
       )}
       {microagentData && !isLoading && !error && (
-        <MarkdownRenderer includeStandard>
+        <Markdown
+          components={{
+            code,
+            ul,
+            ol,
+            a: anchor,
+            p: paragraph,
+          }}
+          remarkPlugins={[remarkGfm, remarkBreaks]}
+        >
           {microagentData.content}
-        </MarkdownRenderer>
+        </Markdown>
       )}
     </div>
   );

frontend/src/components/features/settings/git-settings/azure-devops-token-help-anchor.tsx

@@ -1,20 +0,0 @@
-import { useTranslation } from "react-i18next";
-import { I18nKey } from "#/i18n/declaration";
-
-export function AzureDevOpsTokenHelpAnchor() {
-  const { t } = useTranslation();
-
-  return (
-    <p data-testid="azure-devops-token-help-anchor" className="text-xs">
-      <a
-        href="https://learn.microsoft.com/en-us/azure/devops/organizations/accounts/use-personal-access-tokens-to-authenticate"
-        target="_blank"
-        className="underline underline-offset-2"
-        rel="noopener noreferrer"
-        aria-label={t(I18nKey.GIT$AZURE_DEVOPS_TOKEN_HELP)}
-      >
-        {t(I18nKey.GIT$AZURE_DEVOPS_TOKEN_HELP)}
-      </a>
-    </p>
-  );
-}

frontend/src/components/features/settings/git-settings/azure-devops-token-input.tsx

@@ -1,64 +0,0 @@
-import { useTranslation } from "react-i18next";
-import { I18nKey } from "#/i18n/declaration";
-import { SettingsInput } from "../settings-input";
-import { AzureDevOpsTokenHelpAnchor } from "./azure-devops-token-help-anchor";
-import { KeyStatusIcon } from "../key-status-icon";
-
-interface AzureDevOpsTokenInputProps {
-  onChange: (value: string) => void;
-  onAzureDevOpsHostChange: (value: string) => void;
-  isAzureDevOpsTokenSet: boolean;
-  name: string;
-  azureDevOpsHostSet: string | null | undefined;
-}
-
-export function AzureDevOpsTokenInput({
-  onChange,
-  onAzureDevOpsHostChange,
-  isAzureDevOpsTokenSet,
-  name,
-  azureDevOpsHostSet,
-}: AzureDevOpsTokenInputProps) {
-  const { t } = useTranslation();
-
-  return (
-    <div className="flex flex-col gap-6">
-      <SettingsInput
-        testId={name}
-        name={name}
-        onChange={onChange}
-        label={t(I18nKey.GIT$AZURE_DEVOPS_TOKEN)}
-        type="password"
-        className="w-full max-w-[680px]"
-        placeholder={isAzureDevOpsTokenSet ? "<hidden>" : ""}
-        startContent={
-          isAzureDevOpsTokenSet && (
-            <KeyStatusIcon
-              testId="azure-devops-set-token-indicator"
-              isSet={isAzureDevOpsTokenSet}
-            />
-          )
-        }
-      />
-
-      <SettingsInput
-        onChange={onAzureDevOpsHostChange || (() => {})}
-        name="azure-devops-host-input"
-        testId="azure-devops-host-input"
-        label={t(I18nKey.GIT$AZURE_DEVOPS_HOST)}
-        type="text"
-        className="w-full max-w-[680px]"
-        placeholder={t(I18nKey.GIT$AZURE_DEVOPS_HOST_PLACEHOLDER)}
-        defaultValue={azureDevOpsHostSet || undefined}
-        startContent={
-          azureDevOpsHostSet &&
-          azureDevOpsHostSet.trim() !== "" && (
-            <KeyStatusIcon testId="azure-devops-set-host-indicator" isSet />
-          )
-        }
-      />
-
-      <AzureDevOpsTokenHelpAnchor />
-    </div>
-  );
-}

frontend/src/components/features/settings/git-settings/configure-azure-devops-anchor.tsx

@@ -1,37 +0,0 @@
-import { useTranslation } from "react-i18next";
-import { I18nKey } from "#/i18n/declaration";
-import { useConfig } from "#/hooks/query/use-config";
-import { useAuthUrl } from "#/hooks/use-auth-url";
-import { BrandButton } from "../brand-button";
-
-export function ConfigureAzureDevOpsAnchor() {
-  const { t } = useTranslation();
-  const { data: config } = useConfig();
-
-  const authUrl = useAuthUrl({
-    appMode: config?.APP_MODE ?? null,
-    identityProvider: "azure_devops",
-    authUrl: config?.AUTH_URL,
-  });
-
-  const handleOAuthFlow = () => {
-    if (!authUrl) {
-      return;
-    }
-
-    window.location.href = authUrl;
-  };
-
-  return (
-    <div data-testid="configure-azure-devops-button" className="py-9">
-      <BrandButton
-        type="button"
-        variant="primary"
-        className="w-55"
-        onClick={handleOAuthFlow}
-      >
-        {t(I18nKey.AZURE_DEVOPS$CONNECT_ACCOUNT)}
-      </BrandButton>
-    </div>
-  );
-}

frontend/src/components/features/waitlist/auth-modal.tsx

@@ -8,7 +8,6 @@ import { BrandButton } from "../settings/brand-button";
 import GitHubLogo from "#/assets/branding/github-logo.svg?react";
 import GitLabLogo from "#/assets/branding/gitlab-logo.svg?react";
 import BitbucketLogo from "#/assets/branding/bitbucket-logo.svg?react";
-import AzureDevOpsLogo from "#/assets/branding/azure-devops-logo.svg?react";
 import { useAuthUrl } from "#/hooks/use-auth-url";
 import { GetConfigResponse } from "#/api/option-service/option.types";
 import { Provider } from "#/types/settings";
@@ -42,12 +41,6 @@ export function AuthModal({
     authUrl,
   });
 
-  const azureDevOpsAuthUrl = useAuthUrl({
-    appMode: appMode || null,
-    identityProvider: "azure_devops",
-    authUrl,
-  });
-
   const enterpriseSsoUrl = useAuthUrl({
     appMode: appMode || null,
     identityProvider: "enterprise_sso",
@@ -78,13 +71,6 @@ export function AuthModal({
     }
   };
 
-  const handleAzureDevOpsAuth = () => {
-    if (azureDevOpsAuthUrl) {
-      // Always start the OIDC flow, let the backend handle TOS check
-      window.location.href = azureDevOpsAuthUrl;
-    }
-  };
-
   const handleEnterpriseSsoAuth = () => {
     if (enterpriseSsoUrl) {
       trackLoginButtonClick({ provider: "enterprise_sso" });
@@ -106,10 +92,6 @@ export function AuthModal({
     providersConfigured &&
     providersConfigured.length > 0 &&
     providersConfigured.includes("bitbucket");
-  const showAzureDevOps =
-    providersConfigured &&
-    providersConfigured.length > 0 &&
-    providersConfigured.includes("azure_devops");
   const showEnterpriseSso =
     providersConfigured &&
     providersConfigured.length > 0 &&
@@ -172,18 +154,6 @@ export function AuthModal({
                 </BrandButton>
               )}
 
-              {showAzureDevOps && (
-                <BrandButton
-                  type="button"
-                  variant="primary"
-                  onClick={handleAzureDevOpsAuth}
-                  className="w-full font-semibold"
-                  startContent={<AzureDevOpsLogo width={20} height={20} />}
-                >
-                  {t(I18nKey.AZURE_DEVOPS$CONNECT_ACCOUNT)}
-                </BrandButton>
-              )}
-
               {showEnterpriseSso && (
                 <BrandButton
                   type="button"

frontend/src/components/shared/git-provider-icon.tsx

@@ -1,6 +1,5 @@
 import { FaBitbucket, FaGithub, FaGitlab } from "react-icons/fa6";
 import { Provider } from "#/types/settings";
-import AzureDevOpsLogo from "#/assets/branding/azure-devops-logo.svg?react";
 
 interface GitProviderIconProps {
   gitProvider: Provider;
@@ -14,13 +13,8 @@ export function GitProviderIcon({
   return (
     <>
       {gitProvider === "github" && <FaGithub size={14} className={className} />}
-      {gitProvider === "gitlab" && <FaGitlab size={14} className={className} />}
-      {gitProvider === "bitbucket" && (
-        <FaBitbucket size={14} className={className} />
-      )}
-      {gitProvider === "azure_devops" && (
-        <AzureDevOpsLogo className={`${className} w-[14px] h-[14px]`} />
-      )}
+      {gitProvider === "gitlab" && <FaGitlab className={className} />}
+      {gitProvider === "bitbucket" && <FaBitbucket className={className} />}
     </>
   );
 }

frontend/src/components/shared/modals/settings/model-selector.tsx

@@ -21,11 +21,7 @@ interface ModelSelectorProps {
   isDisabled?: boolean;
   models: Record<string, { separator: string; models: string[] }>;
   currentModel?: string;
-  onChange?: (provider: string | null, model: string | null) => void;
-  onDefaultValuesChanged?: (
-    provider: string | null,
-    model: string | null,
-  ) => void;
+  onChange?: (model: string | null) => void;
   wrapperClassName?: string;
   labelClassName?: string;
 }
@@ -35,7 +31,6 @@ export function ModelSelector({
   models,
   currentModel,
   onChange,
-  onDefaultValuesChanged,
   wrapperClassName,
   labelClassName,
 }: ModelSelectorProps) {
@@ -61,7 +56,6 @@ export function ModelSelector({
       setLitellmId(currentModel);
       setSelectedProvider(provider);
       setSelectedModel(model);
-      onDefaultValuesChanged?.(provider, model);
     }
   }, [currentModel]);
 
@@ -71,7 +65,6 @@ export function ModelSelector({
 
     const separator = models[provider]?.separator || "";
     setLitellmId(provider + separator);
-    onChange?.(provider, null);
   };
 
   const handleChangeModel = (model: string) => {
@@ -83,7 +76,7 @@ export function ModelSelector({
     }
     setLitellmId(fullModel);
     setSelectedModel(model);
-    onChange?.(selectedProvider, model);
+    onChange?.(fullModel);
   };
 
   const clear = () => {

frontend/src/components/v1/chat/event-content-helpers/create-skill-ready-event.ts

@@ -1,56 +0,0 @@
-import { MessageEvent } from "#/types/v1/core";
-import { BaseEvent } from "#/types/v1/core/base/event";
-import { getSkillReadyContent } from "./get-skill-ready-content";
-
-/**
- * Synthetic event type for Skill Ready events.
- * This extends BaseEvent and includes a marker to identify it as a skill ready event.
- */
-export interface SkillReadyEvent extends BaseEvent {
-  _isSkillReadyEvent: true;
-  _skillReadyContent: string;
-}
-
-/**
- * Type guard for Skill Ready events.
- */
-export const isSkillReadyEvent = (event: unknown): event is SkillReadyEvent =>
-  typeof event === "object" &&
-  event !== null &&
-  "_isSkillReadyEvent" in event &&
-  event._isSkillReadyEvent === true;
-
-/**
- * Creates a synthetic "Skill Ready" event from a user MessageEvent.
- * This event appears as originating from the agent and contains formatted
- * information about activated skills and extended content.
- */
-export const createSkillReadyEvent = (
-  userEvent: MessageEvent,
-): SkillReadyEvent => {
-  // Support both activated_skills and activated_microagents field names
-  const activatedSkills =
-    (userEvent as unknown as { activated_skills?: string[] })
-      .activated_skills ||
-    userEvent.activated_microagents ||
-    [];
-
-  const extendedContent = userEvent.extended_content || [];
-
-  // Only create event if we have skills or extended content
-  if (activatedSkills.length === 0 && extendedContent.length === 0) {
-    throw new Error(
-      "Cannot create skill ready event without activated skills or extended content",
-    );
-  }
-
-  const content = getSkillReadyContent(activatedSkills, extendedContent);
-
-  return {
-    id: `${userEvent.id}-skill-ready`,
-    timestamp: userEvent.timestamp,
-    source: "agent",
-    _isSkillReadyEvent: true,
-    _skillReadyContent: content,
-  };
-};

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

@@ -4,7 +4,6 @@ import i18n from "#/i18n";
 import { SecurityRisk } from "#/types/v1/core/base/common";
 import {
   ExecuteBashAction,
-  TerminalAction,
   FileEditorAction,
   StrReplaceEditorAction,
   MCPToolAction,
@@ -59,7 +58,7 @@ const getFileEditorActionContent = (
 
 // Command Actions
 const getExecuteBashActionContent = (
-  event: ActionEvent<ExecuteBashAction | TerminalAction>,
+  event: ActionEvent<ExecuteBashAction>,
 ): string => {
   let content = `Command:\n\`${event.action.command}\``;
 
@@ -132,61 +131,27 @@ type BrowserAction =
 
 const getBrowserActionContent = (action: BrowserAction): string => {
   switch (action.kind) {
-    case "BrowserNavigateAction": {
-      let content = `Browsing ${action.url}`;
-      if (action.new_tab) {
-        content += `\n**New Tab:** Yes`;
-      }
-      return content;
-    }
-    case "BrowserClickAction": {
-      let content = `**Element Index:** ${action.index}`;
-      if (action.new_tab) {
-        content += `\n**New Tab:** Yes`;
-      }
-      return content;
-    }
-    case "BrowserTypeAction": {
-      const textPreview =
-        action.text.length > 50
-          ? `${action.text.slice(0, 50)}...`
-          : action.text;
-      return `**Element Index:** ${action.index}\n**Text:** ${textPreview}`;
-    }
-    case "BrowserGetStateAction": {
-      if (action.include_screenshot) {
-        return `**Include Screenshot:** Yes`;
+    case "BrowserNavigateAction":
+      if ("url" in action) {
+        return `Browsing ${action.url}`;
       }
+      break;
+    case "BrowserClickAction":
+    case "BrowserTypeAction":
+    case "BrowserGetStateAction":
+    case "BrowserGetContentAction":
+    case "BrowserScrollAction":
+    case "BrowserGoBackAction":
+    case "BrowserListTabsAction":
+    case "BrowserSwitchTabAction":
+    case "BrowserCloseTabAction":
+      // These browser actions typically don't need detailed content display
       return getNoContentActionContent();
-    }
-    case "BrowserGetContentAction": {
-      const parts: string[] = [];
-      if (action.extract_links) {
-        parts.push(`**Extract Links:** Yes`);
-      }
-      if (action.start_from_char > 0) {
-        parts.push(`**Start From Character:** ${action.start_from_char}`);
-      }
-      return parts.length > 0 ? parts.join("\n") : getNoContentActionContent();
-    }
-    case "BrowserScrollAction": {
-      return `**Direction:** ${action.direction}`;
-    }
-    case "BrowserGoBackAction": {
-      return getNoContentActionContent();
-    }
-    case "BrowserListTabsAction": {
-      return getNoContentActionContent();
-    }
-    case "BrowserSwitchTabAction": {
-      return `**Tab ID:** ${action.tab_id}`;
-    }
-    case "BrowserCloseTabAction": {
-      return `**Tab ID:** ${action.tab_id}`;
-    }
     default:
       return getNoContentActionContent();
   }
+
+  return getNoContentActionContent();
 };
 
 export const getActionContent = (event: ActionEvent): string => {
@@ -199,9 +164,8 @@ export const getActionContent = (event: ActionEvent): string => {
       return getFileEditorActionContent(action);
 
     case "ExecuteBashAction":
-    case "TerminalAction":
       return getExecuteBashActionContent(
-        event as ActionEvent<ExecuteBashAction | TerminalAction>,
+        event as ActionEvent<ExecuteBashAction>,
       );
 
     case "MCPToolAction":

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

@@ -8,7 +8,6 @@ import { getActionContent } from "./get-action-content";
 import { getObservationContent } from "./get-observation-content";
 import { TaskTrackingObservationContent } from "../task-tracking/task-tracking-observation-content";
 import { TaskTrackerObservation } from "#/types/v1/core/base/observation";
-import { SkillReadyEvent, isSkillReadyEvent } from "./create-skill-ready-event";
 import i18n from "#/i18n";
 
 const trimText = (text: string, maxLength: number): string => {
@@ -50,7 +49,6 @@ const getActionEventTitle = (event: OpenHandsEvent): React.ReactNode => {
 
   switch (actionType) {
     case "ExecuteBashAction":
-    case "TerminalAction":
       actionKey = "ACTION_MESSAGE$RUN";
       actionValues = {
         command: trimText(event.action.command, 80),
@@ -85,20 +83,11 @@ const getActionEventTitle = (event: OpenHandsEvent): React.ReactNode => {
       actionKey = "ACTION_MESSAGE$TASK_TRACKING";
       break;
     case "BrowserNavigateAction":
-    case "BrowserClickAction":
-    case "BrowserTypeAction":
-    case "BrowserGetStateAction":
-    case "BrowserGetContentAction":
-    case "BrowserScrollAction":
-    case "BrowserGoBackAction":
-    case "BrowserListTabsAction":
-    case "BrowserSwitchTabAction":
-    case "BrowserCloseTabAction":
       actionKey = "ACTION_MESSAGE$BROWSE";
       break;
     default:
       // For unknown actions, use the type name
-      return String(actionType).replace("Action", "").toUpperCase();
+      return actionType.replace("Action", "").toUpperCase();
   }
 
   if (actionKey) {
@@ -121,7 +110,6 @@ const getObservationEventTitle = (event: OpenHandsEvent): React.ReactNode => {
 
   switch (observationType) {
     case "ExecuteBashObservation":
-    case "TerminalObservation":
       observationKey = "OBSERVATION_MESSAGE$RUN";
       observationValues = {
         command: event.observation.command
@@ -171,21 +159,11 @@ const getObservationEventTitle = (event: OpenHandsEvent): React.ReactNode => {
   return observationType;
 };
 
-export const getEventContent = (event: OpenHandsEvent | SkillReadyEvent) => {
+export const getEventContent = (event: OpenHandsEvent) => {
   let title: React.ReactNode = "";
   let details: string | React.ReactNode = "";
 
-  // Handle Skill Ready events first
-  if (isSkillReadyEvent(event)) {
-    // Use translation key if available, otherwise use "SKILL READY"
-    const skillReadyKey = "OBSERVATION_MESSAGE$SKILL_READY";
-    if (i18n.exists(skillReadyKey)) {
-      title = createTitleFromKey(skillReadyKey, {});
-    } else {
-      title = "Skill Ready";
-    }
-    details = event._skillReadyContent;
-  } else if (isActionEvent(event)) {
+  if (isActionEvent(event)) {
     title = getActionEventTitle(event);
     details = getActionContent(event);
   } else if (isObservationEvent(event)) {

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

@@ -8,7 +8,6 @@ import {
   ThinkObservation,
   BrowserObservation,
   ExecuteBashObservation,
-  TerminalObservation,
   FileEditorObservation,
   StrReplaceEditorObservation,
   TaskTrackerObservation,
@@ -24,15 +23,6 @@ const getFileEditorObservationContent = (
     return `**Error:**\n${observation.error}`;
   }
 
-  // Extract text content from the observation if it exists
-  const textContent =
-    "content" in observation && Array.isArray(observation.content)
-      ? observation.content
-          .filter((c) => c.type === "text")
-          .map((c) => c.text)
-          .join("\n")
-      : null;
-
   const successMessage = getObservationResult(event) === "success";
 
   // For view commands or successful edits with content changes, format as code block
@@ -44,18 +34,16 @@ const getFileEditorObservationContent = (
       observation.new_content) ||
     observation.command === "view"
   ) {
-    // Prefer content over output for view commands, fallback to output if content is not available
-    const displayContent = textContent || observation.output;
-    return `\`\`\`\n${displayContent}\n\`\`\``;
+    return `\`\`\`\n${observation.output}\n\`\`\``;
   }
 
-  // For other commands, prefer content if available, otherwise use output
-  return textContent || observation.output;
+  // For other commands, return the output as-is
+  return observation.output;
 };
 
 // Command Observations
-const getTerminalObservationContent = (
-  event: ObservationEvent<ExecuteBashObservation | TerminalObservation>,
+const getExecuteBashObservationContent = (
+  event: ObservationEvent<ExecuteBashObservation>,
 ): string => {
   const { observation } = event;
 
@@ -80,23 +68,14 @@ const getBrowserObservationContent = (
 ): string => {
   const { observation } = event;
 
-  // Extract text content from the observation
-  const textContent =
-    "content" in observation && Array.isArray(observation.content)
-      ? observation.content
-          .filter((c) => c.type === "text")
-          .map((c) => c.text)
-          .join("\n")
-      : "";
-
   let contentDetails = "";
 
-  if ("is_error" in observation && observation.is_error) {
-    contentDetails += `**Error:**\n${textContent}`;
-  } else {
-    contentDetails += `**Output:**\n${textContent}`;
+  if ("error" in observation && observation.error) {
+    contentDetails += `**Error:**\n${observation.error}\n\n`;
   }
 
+  contentDetails += `**Output:**\n${observation.output}`;
+
   if (contentDetails.length > MAX_CONTENT_LENGTH) {
     contentDetails = `${contentDetails.slice(0, MAX_CONTENT_LENGTH)}...(truncated)`;
   }
@@ -184,22 +163,7 @@ const getFinishObservationContent = (
   event: ObservationEvent<FinishObservation>,
 ): string => {
   const { observation } = event;
-
-  // 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;
+  return observation.message || "";
 };
 
 export const getObservationContent = (event: ObservationEvent): string => {
@@ -215,9 +179,8 @@ export const getObservationContent = (event: ObservationEvent): string => {
       );
 
     case "ExecuteBashObservation":
-    case "TerminalObservation":
-      return getTerminalObservationContent(
-        event as ObservationEvent<ExecuteBashObservation | TerminalObservation>,
+      return getExecuteBashObservationContent(
+        event as ObservationEvent<ExecuteBashObservation>,
       );
 
     case "BrowserObservation":

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

@@ -17,15 +17,6 @@ export const getObservationResult = (
       if (exitCode === 0 || metadata.exit_code === 0) return "success"; // Command executed successfully
       return "error"; // Command failed
     }
-    case "TerminalObservation": {
-      const exitCode =
-        observation.exit_code ?? observation.metadata.exit_code ?? null;
-
-      if (observation.timeout || exitCode === -1) return "timeout";
-      if (exitCode === 0) return "success";
-      if (observation.is_error) return "error";
-      return "success";
-    }
     case "FileEditorObservation":
     case "StrReplaceEditorObservation":
       // Check if there's an error

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

@@ -1,108 +0,0 @@
-import { TextContent } from "#/types/v1/core/base/common";
-
-/**
- * Extracts all text content from an array of TextContent items.
- */
-const extractAllText = (extendedContent: TextContent[]): string =>
-  extendedContent
-    .filter((c) => c.type === "text")
-    .map((c) => c.text)
-    .join("");
-
-/**
- * Extracts all <EXTRA_INFO> blocks from the given text.
- * Returns an array of content strings (without the wrapper tags).
- */
-const extractExtraInfoBlocks = (text: string): string[] => {
-  const blocks: string[] = [];
-  const blockRegex = /<EXTRA_INFO>([\s\S]*?)<\/EXTRA_INFO>/gi;
-  let match = blockRegex.exec(text);
-
-  while (match !== null) {
-    const blockContent = match[1].trim();
-    if (blockContent.length > 0) {
-      blocks.push(blockContent);
-    }
-    match = blockRegex.exec(text);
-  }
-
-  return blocks;
-};
-
-/**
- * Formats a single skill with its corresponding content block.
- */
-const formatSkillWithContent = (
-  skill: string,
-  contentBlock: string | undefined,
-): string => {
-  let formatted = `\n\n- **${skill}**`;
-
-  if (contentBlock && contentBlock.trim().length > 0) {
-    formatted += `\n\n${contentBlock}`;
-  }
-
-  return formatted;
-};
-
-/**
- * Formats skills paired with their corresponding extended content blocks.
- */
-const formatSkillKnowledge = (
-  activatedSkills: string[],
-  extraInfoBlocks: string[],
-): string => {
-  let content = `\n\n**Triggered Skill Knowledge:**`;
-
-  activatedSkills.forEach((skill, index) => {
-    const contentBlock =
-      index < extraInfoBlocks.length ? extraInfoBlocks[index] : undefined;
-    content += formatSkillWithContent(skill, contentBlock);
-  });
-
-  return content;
-};
-
-/**
- * Formats extended content blocks when no skills are present.
- */
-const formatExtendedContentOnly = (extraInfoBlocks: string[]): string => {
-  let content = `\n\n**Extended Content:**`;
-
-  extraInfoBlocks.forEach((block) => {
-    if (block.trim().length > 0) {
-      content += `\n\n${block}`;
-    }
-  });
-
-  return content;
-};
-
-/**
- * Formats activated skills and extended content into markdown for display.
- * Similar to how v0 formats microagent knowledge in recall observations.
- *
- * Each skill is paired with its corresponding <EXTRA_INFO> block by index.
- */
-export const getSkillReadyContent = (
-  activatedSkills: string[],
-  extendedContent: TextContent[],
-): string => {
-  // Extract all <EXTRA_INFO> blocks from extended_content
-  const extraInfoBlocks: string[] = [];
-  if (extendedContent && extendedContent.length > 0) {
-    const allText = extractAllText(extendedContent);
-    extraInfoBlocks.push(...extractExtraInfoBlocks(allText));
-  }
-
-  // Format output based on what we have
-  if (activatedSkills && activatedSkills.length > 0) {
-    return formatSkillKnowledge(activatedSkills, extraInfoBlocks);
-  }
-
-  if (extraInfoBlocks.length > 0) {
-    return formatExtendedContentOnly(extraInfoBlocks);
-  }
-
-  return "";
-};

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

@@ -3,16 +3,10 @@ import { GenericEventMessage } from "../../../features/chat/generic-event-messag
 import { getEventContent } from "../event-content-helpers/get-event-content";
 import { getObservationResult } from "../event-content-helpers/get-observation-result";
 import { isObservationEvent } from "#/types/v1/type-guards";
-import {
-  SkillReadyEvent,
-  isSkillReadyEvent,
-} 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;
+  event: OpenHandsEvent;
   isLastMessage: boolean;
 }
 
@@ -22,29 +16,11 @@ export function GenericEventMessageWrapper({
 }: GenericEventMessageWrapperProps) {
   const { title, details } = getEventContent(event);
 
-  // SkillReadyEvent is not an observation event, so skip the observation checks
-  if (!isSkillReadyEvent(event)) {
-    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>
-        );
-      }
-    }
-  }
-
-  // Determine success status
-  let success: ObservationResultStatus | undefined;
-  if (isSkillReadyEvent(event)) {
-    // Skill Ready events should show success indicator, same as v0 recall observations
-    success = "success";
-  } else if (isObservationEvent(event)) {
-    success = getObservationResult(event);
+  if (
+    isObservationEvent(event) &&
+    event.observation.kind === "TaskTrackerObservation"
+  ) {
+    return <div>{details}</div>;
   }
 
   return (
@@ -52,7 +28,9 @@ export function GenericEventMessageWrapper({
       <GenericEventMessage
         title={title}
         details={details}
-        success={success}
+        success={
+          isObservationEvent(event) ? getObservationResult(event) : undefined
+        }
         initiallyExpanded={false}
       />
       {isLastMessage && <V1ConfirmationButtons />}

frontend/src/components/v1/chat/event-message-components/user-assistant-event-message.tsx

@@ -22,7 +22,6 @@ interface UserAssistantEventMessageProps {
     tooltip?: string;
   }>;
   isLastMessage: boolean;
-  isFromPlanningAgent: boolean;
 }
 
 export function UserAssistantEventMessage({
@@ -32,7 +31,6 @@ export function UserAssistantEventMessage({
   microagentPRUrl,
   actions,
   isLastMessage,
-  isFromPlanningAgent,
 }: UserAssistantEventMessageProps) {
   const message = parseMessageFromEvent(event);
 
@@ -48,12 +46,7 @@ export function UserAssistantEventMessage({
 
   return (
     <>
-      <ChatMessage
-        type={event.source}
-        message={message}
-        actions={actions}
-        isFromPlanningAgent={isFromPlanningAgent}
-      >
+      <ChatMessage type={event.source} message={message} actions={actions}>
         {imageUrls.length > 0 && (
           <ImageCarousel size="small" images={imageUrls} />
         )}

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

@@ -5,7 +5,6 @@ import {
   isActionEvent,
   isObservationEvent,
   isAgentErrorEvent,
-  isUserMessageEvent,
 } from "#/types/v1/type-guards";
 import { MicroagentStatus } from "#/types/microagent-status";
 import { useConfig } from "#/hooks/query/use-config";
@@ -18,10 +17,9 @@ import {
   GenericEventMessageWrapper,
   ThoughtEventMessage,
 } from "./event-message-components";
-import { createSkillReadyEvent } from "./event-content-helpers/create-skill-ready-event";
 
 interface EventMessageProps {
-  event: OpenHandsEvent & { isFromPlanningAgent?: boolean };
+  event: OpenHandsEvent;
   messages: OpenHandsEvent[];
   isLastMessage: boolean;
   microagentStatus?: MicroagentStatus | null;
@@ -35,104 +33,6 @@ interface EventMessageProps {
   isInLast10Actions: boolean;
 }
 
-/**
- * Extracts activated skills from a MessageEvent, supporting both
- * activated_skills and activated_microagents field names.
- */
-const getActivatedSkills = (event: MessageEvent): string[] =>
-  (event as unknown as { activated_skills?: string[] }).activated_skills ||
-  event.activated_microagents ||
-  [];
-
-/**
- * Checks if extended content contains valid text content.
- */
-const hasValidExtendedContent = (
-  extendedContent: MessageEvent["extended_content"],
-): boolean => {
-  if (!extendedContent || extendedContent.length === 0) {
-    return false;
-  }
-
-  return extendedContent.some(
-    (content) => content.type === "text" && content.text.trim().length > 0,
-  );
-};
-
-/**
- * Determines if a Skill Ready event should be displayed for the given message event.
- */
-const shouldShowSkillReadyEvent = (messageEvent: MessageEvent): boolean => {
-  const activatedSkills = getActivatedSkills(messageEvent);
-  const hasActivatedSkills = activatedSkills.length > 0;
-  const hasExtendedContent = hasValidExtendedContent(
-    messageEvent.extended_content,
-  );
-
-  return hasActivatedSkills && hasExtendedContent;
-};
-
-interface CommonProps {
-  microagentStatus?: MicroagentStatus | null;
-  microagentConversationId?: string;
-  microagentPRUrl?: string;
-  actions?: Array<{
-    icon: React.ReactNode;
-    onClick: () => void;
-    tooltip?: string;
-  }>;
-  isLastMessage: boolean;
-  isInLast10Actions: boolean;
-  config: unknown;
-  isCheckingFeedback: boolean;
-  feedbackData: { exists: boolean };
-  isFromPlanningAgent: boolean;
-}
-
-/**
- * Renders a user message with its corresponding Skill Ready event.
- */
-const renderUserMessageWithSkillReady = (
-  messageEvent: MessageEvent,
-  commonProps: CommonProps,
-  isLastMessage: boolean,
-): React.ReactElement => {
-  try {
-    const skillReadyEvent = createSkillReadyEvent(messageEvent);
-    return (
-      <>
-        <UserAssistantEventMessage
-          event={messageEvent}
-          microagentStatus={commonProps.microagentStatus}
-          microagentConversationId={commonProps.microagentConversationId}
-          microagentPRUrl={commonProps.microagentPRUrl}
-          actions={commonProps.actions}
-          isLastMessage={false}
-          isFromPlanningAgent={commonProps.isFromPlanningAgent}
-        />
-        <GenericEventMessageWrapper
-          event={skillReadyEvent}
-          isLastMessage={isLastMessage}
-        />
-      </>
-    );
-  } catch (error) {
-    // If skill ready event creation fails, just render the user message
-    console.error("Failed to create skill ready event:", error);
-    return (
-      <UserAssistantEventMessage
-        event={messageEvent}
-        microagentStatus={commonProps.microagentStatus}
-        microagentConversationId={commonProps.microagentConversationId}
-        microagentPRUrl={commonProps.microagentPRUrl}
-        actions={commonProps.actions}
-        isLastMessage={isLastMessage}
-        isFromPlanningAgent={commonProps.isFromPlanningAgent}
-      />
-    );
-  }
-};
-
 /* eslint-disable react/jsx-props-no-spreading */
 export function EventMessage({
   event,
@@ -151,9 +51,6 @@ export function EventMessage({
   const feedbackData = { exists: false };
   const isCheckingFeedback = false;
 
-  // Read isFromPlanningAgent directly from the event object
-  const isFromPlanningAgent = event.isFromPlanningAgent || false;
-
   // Common props for components that need them
   const commonProps = {
     microagentStatus,
@@ -165,7 +62,6 @@ export function EventMessage({
     config,
     isCheckingFeedback,
     feedbackData,
-    isFromPlanningAgent,
   };
 
   // Agent error events
@@ -218,21 +114,10 @@ export function EventMessage({
 
   // Message events (user and assistant messages)
   if (!isActionEvent(event) && !isObservationEvent(event)) {
-    const messageEvent = event as MessageEvent;
-
-    // Check if this is a user message that should display a Skill Ready event
-    if (isUserMessageEvent(event) && shouldShowSkillReadyEvent(messageEvent)) {
-      return renderUserMessageWithSkillReady(
-        messageEvent,
-        commonProps,
-        isLastMessage,
-      );
-    }
-
-    // Render normal message event (user or assistant)
+    // This is a MessageEvent
     return (
       <UserAssistantEventMessage
-        event={messageEvent}
+        event={event as MessageEvent}
         {...commonProps}
         isLastMessage={isLastMessage}
       />

frontend/src/context/conversation-subscriptions-provider.tsx

@@ -31,13 +31,7 @@ interface ConversationSubscriptionsContextType {
   subscribeToConversation: (options: {
     conversationId: string;
     sessionApiKey: string | null;
-    providersSet: (
-      | "github"
-      | "gitlab"
-      | "bitbucket"
-      | "azure_devops"
-      | "enterprise_sso"
-    )[];
+    providersSet: ("github" | "gitlab" | "bitbucket" | "enterprise_sso")[];
     baseUrl: string;
     socketPath?: string;
     onEvent?: (event: unknown, conversationId: string) => void;
@@ -141,13 +135,7 @@ export function ConversationSubscriptionsProvider({
     (options: {
       conversationId: string;
       sessionApiKey: string | null;
-      providersSet: (
-        | "github"
-        | "gitlab"
-        | "bitbucket"
-        | "azure_devops"
-        | "enterprise_sso"
-      )[];
+      providersSet: ("github" | "gitlab" | "bitbucket" | "enterprise_sso")[];
       baseUrl: string;
       socketPath?: string;
       onEvent?: (event: unknown, conversationId: string) => void;

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

@@ -22,13 +22,10 @@ import {
   isConversationStateUpdateEvent,
   isFullStateConversationStateUpdateEvent,
   isAgentStatusConversationStateUpdateEvent,
-  isStatsConversationStateUpdateEvent,
   isExecuteBashActionEvent,
   isExecuteBashObservationEvent,
   isConversationErrorEvent,
-  isPlanningFileEditorObservationEvent,
 } from "#/types/v1/type-guards";
-import { ConversationStateUpdateEventStats } from "#/types/v1/core/events/conversation-state-event";
 import { handleActionEventCacheInvalidation } from "#/utils/cache-utils";
 import { buildWebSocketUrl } from "#/utils/websocket-url";
 import type {
@@ -39,8 +36,6 @@ import EventService from "#/api/event-service/event-service.api";
 import { useConversationStore } from "#/state/conversation-store";
 import { isBudgetOrCreditError } from "#/utils/error-handler";
 import { useTracking } from "#/hooks/use-tracking";
-import { useReadConversationFile } from "#/hooks/mutation/use-read-conversation-file";
-import useMetricsStore from "#/stores/metrics-store";
 
 // eslint-disable-next-line @typescript-eslint/naming-convention
 export type V1_WebSocketConnectionState =
@@ -104,53 +99,12 @@ export function ConversationWebSocketProvider({
     number | null
   >(null);
 
-  const { conversationMode, setPlanContent } = useConversationStore();
-
-  // Hook for reading conversation file
-  const { mutate: readConversationFile } = useReadConversationFile();
+  const { conversationMode } = useConversationStore();
 
   // Separate received event count tracking per connection
   const receivedEventCountRefMain = useRef(0);
   const receivedEventCountRefPlanning = useRef(0);
 
-  // Track the latest PlanningFileEditorObservation event during history replay
-  // We'll only call the API once after history loading completes
-  const latestPlanningFileEventRef = useRef<{
-    path: string;
-    conversationId: string;
-  } | null>(null);
-
-  // Helper function to update metrics from stats event
-  const updateMetricsFromStats = useCallback(
-    (event: ConversationStateUpdateEventStats) => {
-      if (event.value.usage_to_metrics?.agent) {
-        const agentMetrics = event.value.usage_to_metrics.agent;
-        const metrics = {
-          cost: agentMetrics.accumulated_cost,
-          max_budget_per_task: agentMetrics.max_budget_per_task ?? null,
-          usage: agentMetrics.accumulated_token_usage
-            ? {
-                prompt_tokens:
-                  agentMetrics.accumulated_token_usage.prompt_tokens,
-                completion_tokens:
-                  agentMetrics.accumulated_token_usage.completion_tokens,
-                cache_read_tokens:
-                  agentMetrics.accumulated_token_usage.cache_read_tokens,
-                cache_write_tokens:
-                  agentMetrics.accumulated_token_usage.cache_write_tokens,
-                context_window:
-                  agentMetrics.accumulated_token_usage.context_window,
-                per_turn_token:
-                  agentMetrics.accumulated_token_usage.per_turn_token,
-              }
-            : null,
-        };
-        useMetricsStore.getState().setMetrics(metrics);
-      }
-    },
-    [],
-  );
-
   // Build WebSocket URL from props
   // Only build URL if we have both conversationId and conversationUrl
   // This prevents connection attempts during task polling phase
@@ -247,40 +201,11 @@ export function ConversationWebSocketProvider({
     receivedEventCountRefPlanning,
   ]);
 
-  // Call API once after history loading completes if we tracked any PlanningFileEditorObservation events
-  useEffect(() => {
-    if (!isLoadingHistoryPlanning && latestPlanningFileEventRef.current) {
-      const { path, conversationId: currentPlanningConversationId } =
-        latestPlanningFileEventRef.current;
-
-      readConversationFile(
-        {
-          conversationId: currentPlanningConversationId,
-          filePath: path,
-        },
-        {
-          onSuccess: (fileContent) => {
-            setPlanContent(fileContent);
-          },
-          onError: (error) => {
-            // eslint-disable-next-line no-console
-            console.warn("Failed to read conversation file:", error);
-          },
-        },
-      );
-
-      // Clear the ref after calling the API
-      latestPlanningFileEventRef.current = null;
-    }
-  }, [isLoadingHistoryPlanning, readConversationFile, setPlanContent]);
-
   useEffect(() => {
     hasConnectedRefMain.current = false;
     setIsLoadingHistoryPlanning(!!subConversationIds?.length);
     setExpectedEventCountPlanning(null);
     receivedEventCountRefPlanning.current = 0;
-    // Reset the tracked event ref when sub-conversations change
-    latestPlanningFileEventRef.current = null;
   }, [subConversationIds]);
 
   // Merged loading history state - true if either connection is still loading
@@ -295,8 +220,6 @@ export function ConversationWebSocketProvider({
     setIsLoadingHistoryMain(true);
     setExpectedEventCountMain(null);
     receivedEventCountRefMain.current = 0;
-    // Reset the tracked event ref when conversation changes
-    latestPlanningFileEventRef.current = null;
   }, [conversationId]);
 
   // Separate message handlers for each connection
@@ -364,9 +287,6 @@ export function ConversationWebSocketProvider({
             if (isAgentStatusConversationStateUpdateEvent(event)) {
               setExecutionStatus(event.value);
             }
-            if (isStatsConversationStateUpdateEvent(event)) {
-              updateMetricsFromStats(event);
-            }
           }
 
           // Handle ExecuteBashAction events - add command as input to terminal
@@ -400,7 +320,6 @@ export function ConversationWebSocketProvider({
       setExecutionStatus,
       appendInput,
       appendOutput,
-      updateMetricsFromStats,
     ],
   );
 
@@ -424,12 +343,7 @@ export function ConversationWebSocketProvider({
 
         // Use type guard to validate v1 event structure
         if (isV1Event(event)) {
-          // Mark this event as coming from the planning agent
-          const eventWithPlanningFlag = {
-            ...event,
-            isFromPlanningAgent: true,
-          };
-          addEvent(eventWithPlanningFlag);
+          addEvent(event);
 
           // Handle AgentErrorEvent specifically
           if (isAgentErrorEvent(event)) {
@@ -462,9 +376,6 @@ export function ConversationWebSocketProvider({
             if (isAgentStatusConversationStateUpdateEvent(event)) {
               setExecutionStatus(event.value);
             }
-            if (isStatsConversationStateUpdateEvent(event)) {
-              updateMetricsFromStats(event);
-            }
           }
 
           // Handle ExecuteBashAction events - add command as input to terminal
@@ -481,41 +392,6 @@ export function ConversationWebSocketProvider({
               .join("\n");
             appendOutput(textContent);
           }
-
-          // Handle PlanningFileEditorObservation events - read and update plan content
-          if (isPlanningFileEditorObservationEvent(event)) {
-            const planningAgentConversation = subConversations?.[0];
-            const planningConversationId = planningAgentConversation?.id;
-
-            if (planningConversationId && event.observation.path) {
-              // During history replay, track the latest event but don't call API
-              // After history loading completes, we'll call the API once with the latest event
-              if (isLoadingHistoryPlanning) {
-                latestPlanningFileEventRef.current = {
-                  path: event.observation.path,
-                  conversationId: planningConversationId,
-                };
-              } else {
-                // History loading is complete - this is a new real-time event
-                // Call the API immediately for real-time updates
-                readConversationFile(
-                  {
-                    conversationId: planningConversationId,
-                    filePath: event.observation.path,
-                  },
-                  {
-                    onSuccess: (fileContent) => {
-                      setPlanContent(fileContent);
-                    },
-                    onError: (error) => {
-                      // eslint-disable-next-line no-console
-                      console.warn("Failed to read conversation file:", error);
-                    },
-                  },
-                );
-              }
-            }
-          }
         }
       } catch (error) {
         // eslint-disable-next-line no-console
@@ -533,9 +409,6 @@ export function ConversationWebSocketProvider({
       setExecutionStatus,
       appendInput,
       appendOutput,
-      readConversationFile,
-      setPlanContent,
-      updateMetricsFromStats,
     ],
   );
 

frontend/src/hooks/mutation/use-read-conversation-file.ts

@@ -1,17 +0,0 @@
-import { useMutation } from "@tanstack/react-query";
-import V1ConversationService from "#/api/conversation-service/v1-conversation-service.api";
-
-interface UseReadConversationFileVariables {
-  conversationId: string;
-  filePath?: string;
-}
-
-export const useReadConversationFile = () =>
-  useMutation({
-    mutationKey: ["read-conversation-file"],
-    mutationFn: async ({
-      conversationId,
-      filePath,
-    }: UseReadConversationFileVariables): Promise<string> =>
-      V1ConversationService.readConversationFile(conversationId, filePath),
-  });

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

@@ -1,71 +0,0 @@
-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

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

frontend/src/i18n/declaration.ts

@@ -1,11 +1,6 @@
 // this file generate by script, don't modify it manually!!!
 export enum I18nKey {
   MAINTENANCE$SCHEDULED_MESSAGE = "MAINTENANCE$SCHEDULED_MESSAGE",
-  AZURE_DEVOPS$CONNECT_ACCOUNT = "AZURE_DEVOPS$CONNECT_ACCOUNT",
-  GIT$AZURE_DEVOPS_TOKEN = "GIT$AZURE_DEVOPS_TOKEN",
-  GIT$AZURE_DEVOPS_HOST = "GIT$AZURE_DEVOPS_HOST",
-  GIT$AZURE_DEVOPS_HOST_PLACEHOLDER = "GIT$AZURE_DEVOPS_HOST_PLACEHOLDER",
-  GIT$AZURE_DEVOPS_TOKEN_HELP = "GIT$AZURE_DEVOPS_TOKEN_HELP",
   MICROAGENT$NO_REPOSITORY_FOUND = "MICROAGENT$NO_REPOSITORY_FOUND",
   MICROAGENT$ADD_TO_MICROAGENT = "MICROAGENT$ADD_TO_MICROAGENT",
   MICROAGENT$WHAT_TO_ADD = "MICROAGENT$WHAT_TO_ADD",
@@ -122,7 +117,6 @@ export enum I18nKey {
   SETTINGS$NAV_SECRETS = "SETTINGS$NAV_SECRETS",
   SETTINGS$NAV_API_KEYS = "SETTINGS$NAV_API_KEYS",
   SETTINGS$GITHUB = "SETTINGS$GITHUB",
-  SETTINGS$AZURE_DEVOPS = "SETTINGS$AZURE_DEVOPS",
   SETTINGS$SLACK = "SETTINGS$SLACK",
   SETTINGS$NAV_LLM = "SETTINGS$NAV_LLM",
   GIT$MERGE_REQUEST = "GIT$MERGE_REQUEST",
@@ -954,5 +948,4 @@ export enum I18nKey {
   COMMON$CODE_AGENT_DESCRIPTION = "COMMON$CODE_AGENT_DESCRIPTION",
   COMMON$PLAN_AGENT_DESCRIPTION = "COMMON$PLAN_AGENT_DESCRIPTION",
   PLANNING_AGENTT$PLANNING_AGENT_INITIALIZED = "PLANNING_AGENTT$PLANNING_AGENT_INITIALIZED",
-  OBSERVATION_MESSAGE$SKILL_READY = "OBSERVATION_MESSAGE$SKILL_READY",
 }

frontend/src/i18n/translation.json

@@ -15,86 +15,6 @@
     "de": "Die geplante Wartung beginnt um {{time}}",
     "uk": "Планове технічне обслуговування розпочнеться о {{time}}"
   },
-  "AZURE_DEVOPS$CONNECT_ACCOUNT": {
-    "en": "Connect Azure DevOps Account",
-    "ja": "Azure DevOps アカウントを接続",
-    "zh-CN": "连接 Azure DevOps 账户",
-    "zh-TW": "連接 Azure DevOps 帳戶",
-    "ko-KR": "Azure DevOps 계정 연결",
-    "no": "Koble til Azure DevOps-konto",
-    "it": "Connetti account Azure DevOps",
-    "pt": "Conectar conta do Azure DevOps",
-    "es": "Conectar cuenta de Azure DevOps",
-    "ar": "ربط حساب Azure DevOps",
-    "fr": "Connecter le compte Azure DevOps",
-    "tr": "Azure DevOps hesabını bağla",
-    "de": "Azure DevOps-Konto verbinden",
-    "uk": "Підключити обліковий запис Azure DevOps"
-  },
-  "GIT$AZURE_DEVOPS_TOKEN": {
-    "en": "Azure DevOps Personal Access Token",
-    "ja": "Azure DevOps 個人用アクセス トークン",
-    "zh-CN": "Azure DevOps 个人访问令牌",
-    "zh-TW": "Azure DevOps 個人存取權杖",
-    "ko-KR": "Azure DevOps 개인 액세스 토큰",
-    "no": "Azure DevOps personlig tilgangstoken",
-    "it": "Token di accesso personale Azure DevOps",
-    "pt": "Token de acesso pessoal do Azure DevOps",
-    "es": "Token de acceso personal de Azure DevOps",
-    "ar": "رمز الوصول الشخصي لـ Azure DevOps",
-    "fr": "Jeton d'accès personnel Azure DevOps",
-    "tr": "Azure DevOps kişisel erişim belirteci",
-    "de": "Azure DevOps persönliches Zugriffstoken",
-    "uk": "Персональний токен доступу Azure DevOps"
-  },
-  "GIT$AZURE_DEVOPS_HOST": {
-    "en": "Azure DevOps Organization",
-    "ja": "Azure DevOps 組織",
-    "zh-CN": "Azure DevOps 组织",
-    "zh-TW": "Azure DevOps 組織",
-    "ko-KR": "Azure DevOps 조직",
-    "no": "Azure DevOps organisasjon",
-    "it": "Organizzazione Azure DevOps",
-    "pt": "Organização do Azure DevOps",
-    "es": "Organización de Azure DevOps",
-    "ar": "مؤسسة Azure DevOps",
-    "fr": "Organisation Azure DevOps",
-    "tr": "Azure DevOps kuruluş",
-    "de": "Azure DevOps Organisation",
-    "uk": "Організація Azure DevOps"
-  },
-  "GIT$AZURE_DEVOPS_HOST_PLACEHOLDER": {
-    "en": "organization",
-    "ja": "組織",
-    "zh-CN": "组织",
-    "zh-TW": "組織",
-    "ko-KR": "조직",
-    "no": "organisasjon",
-    "it": "organizzazione",
-    "pt": "organização",
-    "es": "organización",
-    "ar": "مؤسسة",
-    "fr": "organisation",
-    "tr": "kuruluş/proje",
-    "de": "organisation/projekt",
-    "uk": "організація/проект"
-  },
-  "GIT$AZURE_DEVOPS_TOKEN_HELP": {
-    "en": "How to create an Azure DevOps token",
-    "ja": "Azure DevOps トークンの作成方法",
-    "zh-CN": "如何创建 Azure DevOps 令牌",
-    "zh-TW": "如何創建 Azure DevOps 權杖",
-    "ko-KR": "Azure DevOps 토큰 생성 방법",
-    "no": "Hvordan lage et Azure DevOps-token",
-    "it": "Come creare un token Azure DevOps",
-    "pt": "Como criar um token do Azure DevOps",
-    "es": "Cómo crear un token de Azure DevOps",
-    "ar": "كيفية إنشاء رمز Azure DevOps",
-    "fr": "Comment créer un jeton Azure DevOps",
-    "tr": "Azure DevOps belirteci nasıl oluşturulur",
-    "de": "Wie man ein Azure DevOps-Token erstellt",
-    "uk": "Як створити токен Azure DevOps"
-  },
   "MICROAGENT$NO_REPOSITORY_FOUND": {
     "en": "No repository found to launch microagent",
     "ja": "マイクロエージェントを起動するためのリポジトリが見つかりません",
@@ -1312,20 +1232,20 @@
     "uk": "Невірний JSON"
   },
   "HOME$CONNECT_PROVIDER_MESSAGE": {
-    "en": "To get started with suggested tasks, please connect your GitHub, GitLab, Bitbucket, or Azure DevOps account.",
-    "ja": "提案されたタスクを始めるには、GitHub、GitLab、Bitbucket、またはAzure DevOpsアカウントを接続してください。",
-    "zh-CN": "要开始使用建议的任务，请连接您的GitHub、GitLab、Bitbucket或Azure DevOps账户。",
-    "zh-TW": "要開始使用建議的任務，請連接您的GitHub、GitLab、Bitbucket或Azure DevOps帳戶。",
-    "ko-KR": "제안된 작업을 시작하려면 GitHub, GitLab, Bitbucket 또는 Azure DevOps 계정을 연결하세요.",
-    "no": "For å komme i gang med foreslåtte oppgaver, vennligst koble til GitHub, GitLab, Bitbucket eller Azure DevOps-kontoen din.",
-    "it": "Per iniziare con le attività suggerite, collega il tuo account GitHub, GitLab, Bitbucket o Azure DevOps.",
-    "pt": "Para começar com tarefas sugeridas, conecte sua conta GitHub, GitLab, Bitbucket ou Azure DevOps.",
-    "es": "Para comenzar con las tareas sugeridas, conecte su cuenta de GitHub, GitLab, Bitbucket o Azure DevOps.",
-    "ar": "للبدء بالمهام المقترحة، يرجى ربط حساب GitHub أو GitLab أو Bitbucket أو Azure DevOps الخاص بك.",
-    "fr": "Pour commencer avec les tâches suggérées, veuillez connecter votre compte GitHub, GitLab, Bitbucket ou Azure DevOps.",
-    "tr": "Önerilen görevlerle başlamak için lütfen GitHub, GitLab, Bitbucket veya Azure DevOps hesabınızı bağlayın.",
-    "de": "Um mit vorgeschlagenen Aufgaben zu beginnen, verbinden Sie bitte Ihr GitHub-, GitLab-, Bitbucket- oder Azure DevOps-Konto.",
-    "uk": "Щоб розпочати роботу з запропонованими завданнями, підключіть свій обліковий запис GitHub, GitLab, Bitbucket або Azure DevOps."
+    "en": "To get started with suggested tasks, please connect your GitHub, GitLab, or Bitbucket account.",
+    "ja": "提案されたタスクを始めるには、GitHub、GitLab、またはBitbucketアカウントを接続してください。",
+    "zh-CN": "要开始使用建议的任务，请连接您的GitHub、GitLab或Bitbucket账户。",
+    "zh-TW": "要開始使用建議的任務，請連接您的GitHub、GitLab或Bitbucket帳戶。",
+    "ko-KR": "제안된 작업을 시작하려면 GitHub, GitLab 또는 Bitbucket 계정을 연결하세요.",
+    "no": "For å komme i gang med foreslåtte oppgaver, vennligst koble til GitHub, GitLab eller Bitbucket-kontoen din.",
+    "it": "Per iniziare con le attività suggerite, collega il tuo account GitHub, GitLab o Bitbucket.",
+    "pt": "Para começar com tarefas sugeridas, conecte sua conta GitHub, GitLab ou Bitbucket.",
+    "es": "Para comenzar con las tareas sugeridas, conecte su cuenta de GitHub, GitLab o Bitbucket.",
+    "ar": "للبدء بالمهام المقترحة، يرجى ربط حساب GitHub أو GitLab أو Bitbucket الخاص بك.",
+    "fr": "Pour commencer avec les tâches suggérées, veuillez connecter votre compte GitHub, GitLab ou Bitbucket.",
+    "tr": "Önerilen görevlerle başlamak için lütfen GitHub, GitLab veya Bitbucket hesabınızı bağlayın.",
+    "de": "Um mit vorgeschlagenen Aufgaben zu beginnen, verbinden Sie bitte Ihr GitHub-, GitLab- oder Bitbucket-Konto.",
+    "uk": "Щоб розпочати роботу з запропонованими завданнями, підключіть свій обліковий запис GitHub, GitLab або Bitbucket."
   },
   "HOME$LETS_START_BUILDING": {
     "en": "Let's Start Building!",
@@ -1951,22 +1871,6 @@
     "de": "GitHub",
     "uk": "GitHub"
   },
-  "SETTINGS$AZURE_DEVOPS": {
-    "en": "Azure DevOps",
-    "ja": "Azure DevOps",
-    "zh-CN": "Azure DevOps",
-    "zh-TW": "Azure DevOps",
-    "ko-KR": "Azure DevOps",
-    "no": "Azure DevOps",
-    "it": "Azure DevOps",
-    "pt": "Azure DevOps",
-    "es": "Azure DevOps",
-    "ar": "Azure DevOps",
-    "fr": "Azure DevOps",
-    "tr": "Azure DevOps",
-    "de": "Azure DevOps",
-    "uk": "Azure DevOps"
-  },
   "SETTINGS$SLACK": {
     "en": "Slack",
     "ja": "Slack",
@@ -15262,21 +15166,5 @@
     "tr": "Planlama ajanı başlatıldı",
     "de": "Planungsagent wurde initialisiert",
     "uk": "Агент планування ініціалізовано"
-  },
-  "OBSERVATION_MESSAGE$SKILL_READY": {
-    "en": "Skill Ready",
-    "ja": "スキル準備完了",
-    "zh-CN": "技能已就绪",
-    "zh-TW": "技能已就緒",
-    "ko-KR": "스킬 준비 완료",
-    "no": "Ferdighet klar",
-    "it": "Abilità pronta",
-    "pt": "Habilidade pronta",
-    "es": "Habilidad lista",
-    "ar": "المهارة جاهزة",
-    "fr": "Compétence prête",
-    "tr": "Yetenek hazır",
-    "de": "Fähigkeit bereit",
-    "uk": "Навичка готова"
   }
 }

frontend/src/routes/billing.tsx

@@ -30,12 +30,11 @@ 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/git-settings.tsx

@@ -7,7 +7,6 @@ import { useLogout } from "#/hooks/mutation/use-logout";
 import { GitHubTokenInput } from "#/components/features/settings/git-settings/github-token-input";
 import { GitLabTokenInput } from "#/components/features/settings/git-settings/gitlab-token-input";
 import { BitbucketTokenInput } from "#/components/features/settings/git-settings/bitbucket-token-input";
-import { AzureDevOpsTokenInput } from "#/components/features/settings/git-settings/azure-devops-token-input";
 import { ConfigureGitHubRepositoriesAnchor } from "#/components/features/settings/git-settings/configure-github-repositories-anchor";
 import { InstallSlackAppAnchor } from "#/components/features/settings/git-settings/install-slack-app-anchor";
 import { I18nKey } from "#/i18n/declaration";
@@ -38,8 +37,6 @@ function GitSettingsScreen() {
     React.useState(false);
   const [bitbucketTokenInputHasValue, setBitbucketTokenInputHasValue] =
     React.useState(false);
-  const [azureDevOpsTokenInputHasValue, setAzureDevOpsTokenInputHasValue] =
-    React.useState(false);
 
   const [githubHostInputHasValue, setGithubHostInputHasValue] =
     React.useState(false);
@@ -47,19 +44,15 @@ function GitSettingsScreen() {
     React.useState(false);
   const [bitbucketHostInputHasValue, setBitbucketHostInputHasValue] =
     React.useState(false);
-  const [azureDevOpsHostInputHasValue, setAzureDevOpsHostInputHasValue] =
-    React.useState(false);
 
   const existingGithubHost = settings?.PROVIDER_TOKENS_SET.github;
   const existingGitlabHost = settings?.PROVIDER_TOKENS_SET.gitlab;
   const existingBitbucketHost = settings?.PROVIDER_TOKENS_SET.bitbucket;
-  const existingAzureDevOpsHost = settings?.PROVIDER_TOKENS_SET.azure_devops;
 
   const isSaas = config?.APP_MODE === "saas";
   const isGitHubTokenSet = providers.includes("github");
   const isGitLabTokenSet = providers.includes("gitlab");
   const isBitbucketTokenSet = providers.includes("bitbucket");
-  const isAzureDevOpsTokenSet = providers.includes("azure_devops");
 
   const formAction = async (formData: FormData) => {
     const disconnectButtonClicked =
@@ -74,21 +67,16 @@ function GitSettingsScreen() {
     const gitlabToken = formData.get("gitlab-token-input")?.toString() || "";
     const bitbucketToken =
       formData.get("bitbucket-token-input")?.toString() || "";
-    const azureDevOpsToken =
-      formData.get("azure-devops-token-input")?.toString() || "";
     const githubHost = formData.get("github-host-input")?.toString() || "";
     const gitlabHost = formData.get("gitlab-host-input")?.toString() || "";
     const bitbucketHost =
       formData.get("bitbucket-host-input")?.toString() || "";
-    const azureDevOpsHost =
-      formData.get("azure-devops-host-input")?.toString() || "";
 
     // Create providers object with all tokens
     const providerTokens: Record<string, { token: string; host: string }> = {
       github: { token: githubToken, host: githubHost },
       gitlab: { token: gitlabToken, host: gitlabHost },
       bitbucket: { token: bitbucketToken, host: bitbucketHost },
-      azure_devops: { token: azureDevOpsToken, host: azureDevOpsHost },
     };
 
     saveGitProviders(
@@ -107,11 +95,9 @@ function GitSettingsScreen() {
           setGithubTokenInputHasValue(false);
           setGitlabTokenInputHasValue(false);
           setBitbucketTokenInputHasValue(false);
-          setAzureDevOpsTokenInputHasValue(false);
           setGithubHostInputHasValue(false);
           setGitlabHostInputHasValue(false);
           setBitbucketHostInputHasValue(false);
-          setAzureDevOpsHostInputHasValue(false);
         },
       },
     );
@@ -121,11 +107,9 @@ function GitSettingsScreen() {
     !githubTokenInputHasValue &&
     !gitlabTokenInputHasValue &&
     !bitbucketTokenInputHasValue &&
-    !azureDevOpsTokenInputHasValue &&
     !githubHostInputHasValue &&
     !gitlabHostInputHasValue &&
-    !bitbucketHostInputHasValue &&
-    !azureDevOpsHostInputHasValue;
+    !bitbucketHostInputHasValue;
   const shouldRenderExternalConfigureButtons = isSaas && config.APP_SLUG;
   const shouldRenderProjectManagementIntegrations =
     config?.FEATURE_FLAGS?.ENABLE_JIRA ||
@@ -212,20 +196,6 @@ function GitSettingsScreen() {
                 bitbucketHostSet={existingBitbucketHost}
               />
             )}
-
-            {!isSaas && (
-              <AzureDevOpsTokenInput
-                name="azure-devops-token-input"
-                isAzureDevOpsTokenSet={isAzureDevOpsTokenSet}
-                onChange={(value) => {
-                  setAzureDevOpsTokenInputHasValue(!!value);
-                }}
-                onAzureDevOpsHostChange={(value) => {
-                  setAzureDevOpsHostInputHasValue(!!value);
-                }}
-                azureDevOpsHostSet={existingAzureDevOpsHost}
-              />
-            )}
           </div>
         </div>
       )}
@@ -241,10 +211,7 @@ function GitSettingsScreen() {
               type="submit"
               variant="secondary"
               isDisabled={
-                !isGitHubTokenSet &&
-                !isGitLabTokenSet &&
-                !isBitbucketTokenSet &&
-                !isAzureDevOpsTokenSet
+                !isGitHubTokenSet && !isGitLabTokenSet && !isBitbucketTokenSet
               }
             >
               {t(I18nKey.GIT$DISCONNECT_TOKENS)}

frontend/src/routes/llm-settings.tsx

@@ -28,7 +28,6 @@ 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;
@@ -103,25 +102,10 @@ function LlmSettingsScreen() {
         : (settings?.SECURITY_ANALYZER ?? DEFAULT_SETTINGS.SECURITY_ANALYZER),
     );
 
-  const [selectedProvider, setSelectedProvider] = React.useState<string | null>(
-    null,
-  );
-
   const modelsAndProviders = organizeModelsAndProviders(
     resources?.models || [],
   );
 
-  // Determine if we should hide the API key input and use OpenHands-managed key (when using OpenHands provider in SaaS mode)
-  const currentModel = currentSelectedModel || settings?.LLM_MODEL;
-  const isOpenHandsProvider =
-    (view === "basic" && selectedProvider === "openhands") ||
-    (view === "advanced" && currentModel?.startsWith("openhands/"));
-  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) {
@@ -212,13 +196,10 @@ function LlmSettingsScreen() {
 
     const fullLlmModel = provider && model && `${provider}/${model}`;
 
-    // Use OpenHands-managed key for OpenHands provider in SaaS mode
-    const finalApiKey = shouldUseOpenHandsKey ? null : apiKey;
-
     saveSettings(
       {
         LLM_MODEL: fullLlmModel,
-        llm_api_key: finalApiKey || null,
+        llm_api_key: apiKey || null,
         SEARCH_API_KEY: searchApiKey || "",
         CONFIRMATION_MODE: confirmationMode,
         SECURITY_ANALYZER:
@@ -263,14 +244,11 @@ function LlmSettingsScreen() {
       .get("security-analyzer-input")
       ?.toString();
 
-    // Use OpenHands-managed key for OpenHands provider in SaaS mode
-    const finalApiKey = shouldUseOpenHandsKey ? null : apiKey;
-
     saveSettings(
       {
         LLM_MODEL: model,
         LLM_BASE_URL: baseUrl,
-        llm_api_key: finalApiKey || null,
+        llm_api_key: apiKey || null,
         SEARCH_API_KEY: searchApiKey || "",
         AGENT: agent,
         CONFIRMATION_MODE: confirmationMode,
@@ -304,10 +282,7 @@ function LlmSettingsScreen() {
     });
   };
 
-  const handleModelIsDirty = (
-    provider: string | null,
-    model: string | null,
-  ) => {
+  const handleModelIsDirty = (model: string | null) => {
     // openai providers are special case; see ModelSelector
     // component for details
     const modelIsDirty = model !== settings?.LLM_MODEL.replace("openai/", "");
@@ -318,15 +293,6 @@ function LlmSettingsScreen() {
 
     // Track the currently selected model for help text display
     setCurrentSelectedModel(model);
-    setSelectedProvider(provider);
-  };
-
-  const onDefaultValuesChanged = (
-    provider: string | null,
-    model: string | null,
-  ) => {
-    setSelectedProvider(provider);
-    setCurrentSelectedModel(model);
   };
 
   const handleApiKeyIsDirty = (apiKey: string) => {
@@ -497,7 +463,6 @@ function LlmSettingsScreen() {
                     models={modelsAndProviders}
                     currentModel={settings.LLM_MODEL || DEFAULT_OPENHANDS_MODEL}
                     onChange={handleModelIsDirty}
-                    onDefaultValuesChanged={onDefaultValuesChanged}
                     wrapperClassName="!flex-col !gap-6"
                   />
                   {(settings.LLM_MODEL?.startsWith("openhands/") ||
@@ -507,31 +472,27 @@ function LlmSettingsScreen() {
                 </>
               )}
 
-              {!shouldUseOpenHandsKey && (
-                <>
-                  <SettingsInput
-                    testId="llm-api-key-input"
-                    name="llm-api-key-input"
-                    label={t(I18nKey.SETTINGS_FORM$API_KEY)}
-                    type="password"
-                    className="w-full max-w-[680px]"
-                    placeholder={settings.LLM_API_KEY_SET ? "<hidden>" : ""}
-                    onChange={handleApiKeyIsDirty}
-                    startContent={
-                      settings.LLM_API_KEY_SET && (
-                        <KeyStatusIcon isSet={settings.LLM_API_KEY_SET} />
-                      )
-                    }
-                  />
+              <SettingsInput
+                testId="llm-api-key-input"
+                name="llm-api-key-input"
+                label={t(I18nKey.SETTINGS_FORM$API_KEY)}
+                type="password"
+                className="w-full max-w-[680px]"
+                placeholder={settings.LLM_API_KEY_SET ? "<hidden>" : ""}
+                onChange={handleApiKeyIsDirty}
+                startContent={
+                  settings.LLM_API_KEY_SET && (
+                    <KeyStatusIcon isSet={settings.LLM_API_KEY_SET} />
+                  )
+                }
+              />
 
-                  <HelpLink
-                    testId="llm-api-key-help-anchor"
-                    text={t(I18nKey.SETTINGS$DONT_KNOW_API_KEY)}
-                    linkText={t(I18nKey.SETTINGS$CLICK_FOR_INSTRUCTIONS)}
-                    href="https://docs.all-hands.dev/usage/local-setup#getting-an-api-key"
-                  />
-                </>
-              )}
+              <HelpLink
+                testId="llm-api-key-help-anchor"
+                text={t(I18nKey.SETTINGS$DONT_KNOW_API_KEY)}
+                linkText={t(I18nKey.SETTINGS$CLICK_FOR_INSTRUCTIONS)}
+                href="https://docs.all-hands.dev/usage/local-setup#getting-an-api-key"
+              />
             </div>
           )}
 
@@ -566,30 +527,26 @@ function LlmSettingsScreen() {
                 onChange={handleBaseUrlIsDirty}
               />
 
-              {!shouldUseOpenHandsKey && (
-                <>
-                  <SettingsInput
-                    testId="llm-api-key-input"
-                    name="llm-api-key-input"
-                    label={t(I18nKey.SETTINGS_FORM$API_KEY)}
-                    type="password"
-                    className="w-full max-w-[680px]"
-                    placeholder={settings.LLM_API_KEY_SET ? "<hidden>" : ""}
-                    onChange={handleApiKeyIsDirty}
-                    startContent={
-                      settings.LLM_API_KEY_SET && (
-                        <KeyStatusIcon isSet={settings.LLM_API_KEY_SET} />
-                      )
-                    }
-                  />
-                  <HelpLink
-                    testId="llm-api-key-help-anchor-advanced"
-                    text={t(I18nKey.SETTINGS$DONT_KNOW_API_KEY)}
-                    linkText={t(I18nKey.SETTINGS$CLICK_FOR_INSTRUCTIONS)}
-                    href="https://docs.all-hands.dev/usage/local-setup#getting-an-api-key"
-                  />
-                </>
-              )}
+              <SettingsInput
+                testId="llm-api-key-input"
+                name="llm-api-key-input"
+                label={t(I18nKey.SETTINGS_FORM$API_KEY)}
+                type="password"
+                className="w-full max-w-[680px]"
+                placeholder={settings.LLM_API_KEY_SET ? "<hidden>" : ""}
+                onChange={handleApiKeyIsDirty}
+                startContent={
+                  settings.LLM_API_KEY_SET && (
+                    <KeyStatusIcon isSet={settings.LLM_API_KEY_SET} />
+                  )
+                }
+              />
+              <HelpLink
+                testId="llm-api-key-help-anchor-advanced"
+                text={t(I18nKey.SETTINGS$DONT_KNOW_API_KEY)}
+                linkText={t(I18nKey.SETTINGS$CLICK_FOR_INSTRUCTIONS)}
+                href="https://docs.all-hands.dev/usage/local-setup#getting-an-api-key"
+              />
 
               {config?.APP_MODE !== "saas" && (
                 <>
@@ -616,23 +573,21 @@ function LlmSettingsScreen() {
                     href="https://tavily.com/"
                   />
 
-                  {!isV1Enabled && (
-                    <SettingsDropdownInput
-                      testId="agent-input"
-                      name="agent-input"
-                      label={t(I18nKey.SETTINGS$AGENT)}
-                      items={
-                        resources?.agents.map((agent) => ({
-                          key: agent,
-                          label: agent, // TODO: Add i18n support for agent names
-                        })) || []
-                      }
-                      defaultSelectedKey={settings.AGENT}
-                      isClearable={false}
-                      onInputChange={handleAgentIsDirty}
-                      wrapperClassName="w-full max-w-[680px]"
-                    />
-                  )}
+                  <SettingsDropdownInput
+                    testId="agent-input"
+                    name="agent-input"
+                    label={t(I18nKey.SETTINGS$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

@@ -1,31 +1,49 @@
-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 { useScrollToBottom } from "#/hooks/use-scroll-to-bottom";
-import { MarkdownRenderer } from "#/components/features/markdown/markdown-renderer";
-import { useHandlePlanClick } from "#/hooks/use-handle-plan-click";
+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";
 
 function PlannerTab() {
   const { t } = useTranslation();
-  const { scrollRef: scrollContainerRef, onChatBodyScroll } = useScrollToBottom(
-    React.useRef<HTMLDivElement>(null),
-  );
 
-  const { planContent } = useConversationStore();
-  const { handlePlanClick } = useHandlePlanClick();
+  const { planContent, setConversationMode } = useConversationStore();
 
-  if (planContent !== null && planContent !== undefined) {
+  if (planContent) {
     return (
-      <div
-        ref={scrollContainerRef}
-        onScroll={(e) => onChatBodyScroll(e.currentTarget)}
-        className="flex flex-col w-full h-full p-4 overflow-auto"
-      >
-        <MarkdownRenderer includeStandard includeHeadings>
+      <div 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]}
+        >
           {planContent}
-        </MarkdownRenderer>
+        </Markdown>
       </div>
     );
   }
@@ -38,7 +56,7 @@ function PlannerTab() {
       </span>
       <button
         type="button"
-        onClick={handlePlanClick}
+        onClick={() => setConversationMode("plan")}
         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/state/conversation-store.ts

@@ -56,7 +56,6 @@ interface ConversationActions {
   setHasRightPanelToggled: (hasRightPanelToggled: boolean) => void;
   setConversationMode: (conversationMode: ConversationMode) => void;
   setSubConversationTaskId: (taskId: string | null) => void;
-  setPlanContent: (planContent: string | null) => void;
 }
 
 type ConversationStore = ConversationState & ConversationActions;
@@ -82,7 +81,91 @@ export const useConversationStore = create<ConversationStore>()(
       submittedMessage: null,
       shouldHideSuggestions: false,
       hasRightPanelToggled: true,
-      planContent: null,
+      planContent: `
+# Improve Developer Onboarding and Examples
+
+## Overview
+
+Based on the analysis of Browser-Use's current documentation and examples, this plan addresses gaps in developer onboarding by creating a progressive learning path, troubleshooting resources, and practical examples that address real-world scenarios (like the LM Studio/local LLM integration issues encountered).
+
+## Current State Analysis
+
+**Strengths:**
+
+- Good quickstart documentation in \`docs/quickstart.mdx\`
+- Extensive examples across multiple categories (60+ example files)
+- Well-structured docs with multiple LLM provider examples
+- Active community support via Discord
+
+**Gaps Identified:**
+
+- No progressive tutorial series that builds complexity gradually
+- Limited troubleshooting documentation for common issues
+- Sparse comments in example files explaining what's happening
+- Local LLM setup (Ollama/LM Studio) not prominently featured
+- No "first 10 minutes" success path
+- Missing visual/conceptual architecture guides for beginners
+- Error messages don't always point to solutions
+
+## Proposed Improvements
+
+### 1. Create Interactive Tutorial Series (\`examples/tutorials/\`)
+
+**New folder structure:**
+
+\`\`\`
+examples/tutorials/
+├── README.md              # Tutorial overview and prerequisites
+├── 00_hello_world.py      # Absolute minimal example
+├── 01_your_first_search.py # Basic search with detailed comments
+├── 02_understanding_actions.py # How actions work
+├── 03_data_extraction_basics.py # Extract data step-by-step
+├── 04_error_handling.py   # Common errors and solutions
+├── 05_custom_tools_intro.py # First custom tool
+├── 06_local_llm_setup.py  # Ollama/LM Studio complete guide
+└── 07_debugging_tips.py   # Debugging strategies
+\`\`\`
+
+**Key Features:**
+
+- Each file 50–80 lines max
+- Extensive inline comments explaining every concept
+- Clear learning objectives at the top of each file
+- "What you'll learn" and "Prerequisites" sections
+- Common pitfalls highlighted
+- Expected output shown in comments
+
+### 2. Troubleshooting Guide (\`docs/troubleshooting.mdx\`)
+
+**Sections:**
+
+- Installation issues (Chromium, dependencies, virtual environments)
+- LLM provider connection errors (API keys, timeouts, rate limits)
+- Local LLM setup (Ollama vs LM Studio, model compatibility)
+- Browser automation issues (element not found, timeout errors)
+- Common error messages with solutions
+- Performance optimization tips
+- When to ask for help (Discord/GitHub)
+
+**Format:**
+
+**Error: "LLM call timed out after 60 seconds"**
+
+**What it means:**
+The model took too long to respond
+
+**Common causes:**
+
+1. Model is too slow for the task
+2. LM Studio/Ollama not responding properly
+3. Complex page overwhelming the model
+
+**Solutions:**
+
+- Use flash_mode for faster execution
+- Try a faster model (Gemini Flash, GPT-4 Turbo Mini)
+- Simplify the task
+- Check model server logs`,
       conversationMode: "code",
       subConversationTaskId: null,
 
@@ -221,7 +304,6 @@ export const useConversationStore = create<ConversationStore>()(
             shouldHideSuggestions: false,
             conversationMode: "code",
             subConversationTaskId: null,
-            planContent: null,
           },
           false,
           "resetConversationState",
@@ -235,9 +317,6 @@ export const useConversationStore = create<ConversationStore>()(
 
       setSubConversationTaskId: (subConversationTaskId) =>
         set({ subConversationTaskId }, false, "setSubConversationTaskId"),
-
-      setPlanContent: (planContent) =>
-        set({ planContent }, false, "setPlanContent"),
     }),
     {
       name: "conversation-store",

frontend/src/stores/use-event-store.ts

@@ -5,9 +5,7 @@ import { OpenHandsParsedEvent } from "#/types/core";
 import { isV1Event } from "#/types/v1/type-guards";
 
 // While we transition to v1 events, our store can handle both v0 and v1 events
-type OHEvent = (OpenHandsEvent | OpenHandsParsedEvent) & {
-  isFromPlanningAgent?: boolean;
-};
+type OHEvent = OpenHandsEvent | OpenHandsParsedEvent;
 
 interface EventState {
   events: OHEvent[];

frontend/src/types/settings.ts

@@ -2,7 +2,6 @@ export const ProviderOptions = {
   github: "github",
   gitlab: "gitlab",
   bitbucket: "bitbucket",
-  azure_devops: "azure_devops",
   enterprise_sso: "enterprise_sso",
 } as const;
 

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

@@ -41,25 +41,6 @@ export interface ExecuteBashAction extends ActionBase<"ExecuteBashAction"> {
   reset: boolean;
 }
 
-export interface TerminalAction extends ActionBase<"TerminalAction"> {
-  /**
-   * The terminal command to execute.
-   */
-  command: string;
-  /**
-   * If True, the command is an input to the running process. If False, the command is executed directly.
-   */
-  is_input: boolean;
-  /**
-   * Optional max time limit (seconds) for the command.
-   */
-  timeout: number | null;
-  /**
-   * If True, reset the terminal session before running the command.
-   */
-  reset: boolean;
-}
-
 export interface FileEditorAction extends ActionBase<"FileEditorAction"> {
   /**
    * The commands to run. Allowed options are: `view`, `create`, `str_replace`, `insert`, `undo_edit`.
@@ -225,7 +206,6 @@ export type Action =
   | FinishAction
   | ThinkAction
   | ExecuteBashAction
-  | TerminalAction
   | FileEditorAction
   | StrReplaceEditorAction
   | TaskTrackerAction

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

@@ -3,11 +3,9 @@ type EventType =
   | "Finish"
   | "Think"
   | "ExecuteBash"
-  | "Terminal"
   | "FileEditor"
   | "StrReplaceEditor"
-  | "TaskTracker"
-  | "PlanningFileEditor";
+  | "TaskTracker";
 
 type ActionOnlyType =
   | "BrowserNavigate"
@@ -26,8 +24,7 @@ type ObservationOnlyType = "Browser";
 type ActionEventType = `${ActionOnlyType}Action` | `${EventType}Action`;
 type ObservationEventType =
   | `${ObservationOnlyType}Observation`
-  | `${EventType}Observation`
-  | "TerminalObservation";
+  | `${EventType}Observation`;
 
 export interface ActionBase<T extends ActionEventType = ActionEventType> {
   kind: T;

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

@@ -25,13 +25,9 @@ export interface MCPToolObservation
 export interface FinishObservation
   extends ObservationBase<"FinishObservation"> {
   /**
-   * Content returned from the finish action as a list of TextContent/ImageContent objects.
+   * Final message sent to the user
    */
-  content: Array<TextContent | ImageContent>;
-  /**
-   * Whether the finish action resulted in an error
-   */
-  is_error: boolean;
+  message: string;
 }
 
 export interface ThinkObservation extends ObservationBase<"ThinkObservation"> {
@@ -85,34 +81,6 @@ export interface ExecuteBashObservation
   metadata: CmdOutputMetadata;
 }
 
-export interface TerminalObservation
-  extends ObservationBase<"TerminalObservation"> {
-  /**
-   * Content returned from the terminal as a list of TextContent/ImageContent objects.
-   */
-  content: Array<TextContent | ImageContent>;
-  /**
-   * The bash command that was executed.
-   */
-  command: string | null;
-  /**
-   * The exit code of the command if it has finished.
-   */
-  exit_code: number | null;
-  /**
-   * Whether the command execution produced an error.
-   */
-  is_error: boolean;
-  /**
-   * Whether the command execution timed out.
-   */
-  timeout: boolean;
-  /**
-   * Additional metadata captured from the shell after command execution.
-   */
-  metadata: CmdOutputMetadata;
-}
-
 export interface FileEditorObservation
   extends ObservationBase<"FileEditorObservation"> {
   /**
@@ -194,46 +162,12 @@ export interface TaskTrackerObservation
   task_list: TaskItem[];
 }
 
-export interface PlanningFileEditorObservation
-  extends ObservationBase<"PlanningFileEditorObservation"> {
-  /**
-   * Content returned from the tool as a list of TextContent/ImageContent objects.
-   */
-  content: Array<TextContent | ImageContent>;
-  /**
-   * Whether the call resulted in an error.
-   */
-  is_error: boolean;
-  /**
-   * The commands to run. Allowed options are: `view`, `create`, `str_replace`, `insert`, `undo_edit`.
-   */
-  command: "view" | "create" | "str_replace" | "insert" | "undo_edit";
-  /**
-   * The file path that was edited.
-   */
-  path: string | null;
-  /**
-   * Indicates if the file previously existed. If not, it was created.
-   */
-  prev_exist: boolean;
-  /**
-   * The content of the file before the edit.
-   */
-  old_content: string | null;
-  /**
-   * The content of the file after the edit.
-   */
-  new_content: string | null;
-}
-
 export type Observation =
   | MCPToolObservation
   | FinishObservation
   | ThinkObservation
   | BrowserObservation
   | ExecuteBashObservation
-  | TerminalObservation
   | FileEditorObservation
   | StrReplaceEditorObservation
-  | TaskTrackerObservation
-  | PlanningFileEditorObservation;
+  | TaskTrackerObservation;

frontend/src/types/v1/core/events/conversation-state-event.ts

@@ -1,63 +1,11 @@
 import { BaseEvent } from "../base/event";
 import { V1ExecutionStatus } from "../base/common";
 
-/**
- * Token usage metrics for LLM calls
- */
-export interface TokenUsage {
-  model: string;
-  prompt_tokens: number;
-  completion_tokens: number;
-  cache_read_tokens: number;
-  cache_write_tokens: number;
-  reasoning_tokens: number;
-  context_window: number;
-  per_turn_token: number;
-  response_id: string;
-}
-
-/**
- * LLM metrics for a specific component (agent or condenser)
- */
-export interface LLMMetrics {
-  model_name: string;
-  accumulated_cost: number;
-  max_budget_per_task: number | null;
-  accumulated_token_usage: TokenUsage;
-  costs: Array<{
-    model: string;
-    cost: number;
-    timestamp: number;
-  }>;
-  response_latencies: Array<{
-    model: string;
-    latency: number;
-    response_id: string;
-  }>;
-  token_usages: TokenUsage[];
-}
-
-/**
- * Usage metrics mapping for different components
- */
-export interface UsageToMetrics {
-  agent: LLMMetrics;
-  condenser: LLMMetrics;
-}
-
-/**
- * Stats containing usage metrics
- */
-export interface ConversationStats {
-  usage_to_metrics: UsageToMetrics;
-}
-
 /**
  * Conversation state value types
  */
 export interface ConversationState {
   execution_status: V1ExecutionStatus;
-  stats?: ConversationStats;
   // Add other conversation state fields here as needed
 }
 
@@ -71,12 +19,12 @@ interface ConversationStateUpdateEventBase extends BaseEvent {
    * Unique key for this state update event.
    * Can be "full_state" for full state snapshots or field names for partial updates.
    */
-  key: "full_state" | "execution_status" | "stats"; // Extend with other keys as needed
+  key: "full_state" | "execution_status"; // Extend with other keys as needed
 
   /**
    * Conversation state updates
    */
-  value: ConversationState | V1ExecutionStatus | ConversationStats;
+  value: ConversationState | V1ExecutionStatus;
 }
 
 // Narrowed interfaces for full state update event
@@ -93,18 +41,10 @@ export interface ConversationStateUpdateEventAgentStatus
   value: V1ExecutionStatus;
 }
 
-// Narrowed interface for stats update event
-export interface ConversationStateUpdateEventStats
-  extends ConversationStateUpdateEventBase {
-  key: "stats";
-  value: ConversationStats;
-}
-
 // Conversation state update event - contains conversation state updates
 export type ConversationStateUpdateEvent =
   | ConversationStateUpdateEventFullState
-  | ConversationStateUpdateEventAgentStatus
-  | ConversationStateUpdateEventStats;
+  | ConversationStateUpdateEventAgentStatus;
 
 // Conversation error event - contains error information
 export interface ConversationErrorEvent extends BaseEvent {

frontend/src/types/v1/type-guards.ts

@@ -3,10 +3,7 @@ import {
   ObservationEvent,
   BaseEvent,
   ExecuteBashAction,
-  TerminalAction,
   ExecuteBashObservation,
-  PlanningFileEditorObservation,
-  TerminalObservation,
 } from "./core";
 import { AgentErrorEvent } from "./core/events/observation-event";
 import { MessageEvent } from "./core/events/message-event";
@@ -15,7 +12,6 @@ import {
   ConversationStateUpdateEvent,
   ConversationStateUpdateEventAgentStatus,
   ConversationStateUpdateEventFullState,
-  ConversationStateUpdateEventStats,
   ConversationErrorEvent,
 } from "./core/events/conversation-state-event";
 import { SystemPromptEvent } from "./core/events/system-event";
@@ -102,29 +98,17 @@ export const isActionEvent = (event: OpenHandsEvent): event is ActionEvent =>
  */
 export const isExecuteBashActionEvent = (
   event: OpenHandsEvent,
-): event is ActionEvent<ExecuteBashAction | TerminalAction> =>
-  isActionEvent(event) &&
-  (event.action.kind === "ExecuteBashAction" ||
-    event.action.kind === "TerminalAction");
+): event is ActionEvent<ExecuteBashAction> =>
+  isActionEvent(event) && event.action.kind === "ExecuteBashAction";
 
 /**
- * Type guard function to check if an observation event contains terminal output
+ * Type guard function to check if an observation event is an ExecuteBashObservation
  */
 export const isExecuteBashObservationEvent = (
   event: OpenHandsEvent,
-): event is ObservationEvent<ExecuteBashObservation | TerminalObservation> =>
+): event is ObservationEvent<ExecuteBashObservation> =>
   isObservationEvent(event) &&
-  (event.observation.kind === "ExecuteBashObservation" ||
-    event.observation.kind === "TerminalObservation");
-
-/**
- * Type guard function to check if an observation event is a PlanningFileEditorObservation
- */
-export const isPlanningFileEditorObservationEvent = (
-  event: OpenHandsEvent,
-): event is ObservationEvent<PlanningFileEditorObservation> =>
-  isObservationEvent(event) &&
-  event.observation.kind === "PlanningFileEditorObservation";
+  event.observation.kind === "ExecuteBashObservation";
 
 /**
  * Type guard function to check if an event is a system prompt event
@@ -155,10 +139,6 @@ export const isAgentStatusConversationStateUpdateEvent = (
 ): event is ConversationStateUpdateEventAgentStatus =>
   event.key === "execution_status";
 
-export const isStatsConversationStateUpdateEvent = (
-  event: ConversationStateUpdateEvent,
-): event is ConversationStateUpdateEventStats => event.key === "stats";
-
 /**
  * Type guard function to check if an event is a conversation error event
  */

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

@@ -1,45 +1,16 @@
-/**
- * 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 (Date object or ISO 8601 string)
+ * @param date The date to format
  * @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("2023-12-31T23:59:59Z"); // "1s"
- * formatTimeDelta("2025-12-01T11:53:37.273886"); // Parsed as UTC automatically
+ * formatTimeDelta(new Date("2022-01-01T00:00:00Z")); // "2y"
  */
-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;
+export const formatTimeDelta = (date: Date) => {
   const now = new Date();
-  const delta = now.getTime() - dateObj.getTime();
+  const delta = now.getTime() - date.getTime();
 
   const seconds = Math.floor(delta / 1000);
   const minutes = Math.floor(seconds / 60);

frontend/src/utils/generate-auth-url.ts

@@ -1,6 +1,6 @@
 /**
  * Generates a URL to redirect to for OAuth authentication
- * @param identityProvider The identity provider to use (e.g., "github", "gitlab", "bitbucket", "azure_devops")
+ * @param identityProvider The identity provider to use (e.g., "github", "gitlab", "bitbucket")
  * @param requestUrl The URL of the request
  * @returns The URL to redirect to for OAuth
  */

frontend/src/utils/local-storage.ts

@@ -8,13 +8,12 @@ export enum LoginMethod {
   GITHUB = "github",
   GITLAB = "gitlab",
   BITBUCKET = "bitbucket",
-  AZURE_DEVOPS = "azure_devops",
   ENTERPRISE_SSO = "enterprise_sso",
 }
 
 /**
  * Set the login method in local storage
- * @param method The login method (github, gitlab, bitbucket, or azure_devops)
+ * @param method The login method (github, gitlab, or bitbucket)
  */
 export const setLoginMethod = (method: LoginMethod): void => {
   localStorage.setItem(LOCAL_STORAGE_KEYS.LOGIN_METHOD, method);

frontend/src/utils/reo.ts

@@ -4,8 +4,6 @@
  * Using CDN approach for better TypeScript compatibility
  */
 
-import EventLogger from "./event-logger";
-
 export interface ReoIdentity {
   username: string;
   type: "github" | "email";
@@ -43,7 +41,7 @@ class ReoService {
         this.initialized = true;
       }
     } catch (error) {
-      EventLogger.error(`Failed to initialize Reo.dev tracking: ${error}`);
+      console.error("Failed to initialize Reo.dev tracking:", error);
     }
   }
 
@@ -80,7 +78,7 @@ class ReoService {
    */
   identify(identity: ReoIdentity): void {
     if (!this.initialized) {
-      EventLogger.warning("Reo.dev not initialized. Call init() first.");
+      console.warn("Reo.dev not initialized. Call init() first.");
       return;
     }
 
@@ -89,7 +87,7 @@ class ReoService {
         window.Reo.identify(identity);
       }
     } catch (error) {
-      EventLogger.error(`Failed to identify user in Reo.dev: ${error}`);
+      console.error("Failed to identify user in Reo.dev:", error);
     }
   }
 

frontend/src/utils/utils.ts

@@ -182,8 +182,6 @@ export const shouldUseInstallationRepos = (
       return true;
     case "gitlab":
       return false;
-    case "azure_devops":
-      return false;
     case "github":
       return app_mode === "saas";
     default:
@@ -199,8 +197,6 @@ export const getGitProviderBaseUrl = (gitProvider: Provider): string => {
       return "https://gitlab.com";
     case "bitbucket":
       return "https://bitbucket.org";
-    case "azure_devops":
-      return "https://dev.azure.com";
     default:
       return "";
   }
@@ -214,7 +210,6 @@ export const getGitProviderBaseUrl = (gitProvider: Provider): string => {
 export const getProviderName = (gitProvider: Provider) => {
   if (gitProvider === "gitlab") return "GitLab";
   if (gitProvider === "bitbucket") return "Bitbucket";
-  if (gitProvider === "azure_devops") return "Azure DevOps";
   return "GitHub";
 };
 
@@ -259,15 +254,6 @@ export const constructPullRequestUrl = (
       return `${baseUrl}/${repositoryName}/-/merge_requests/${prNumber}`;
     case "bitbucket":
       return `${baseUrl}/${repositoryName}/pull-requests/${prNumber}`;
-    case "azure_devops": {
-      // Azure DevOps format: org/project/repo
-      const parts = repositoryName.split("/");
-      if (parts.length === 3) {
-        const [org, project, repo] = parts;
-        return `${baseUrl}/${org}/${project}/_git/${repo}/pullrequest/${prNumber}`;
-      }
-      return "";
-    }
     default:
       return "";
   }
@@ -302,15 +288,6 @@ export const constructMicroagentUrl = (
       return `${baseUrl}/${repositoryName}/-/blob/main/${microagentPath}`;
     case "bitbucket":
       return `${baseUrl}/${repositoryName}/src/main/${microagentPath}`;
-    case "azure_devops": {
-      // Azure DevOps format: org/project/repo
-      const parts = repositoryName.split("/");
-      if (parts.length === 3) {
-        const [org, project, repo] = parts;
-        return `${baseUrl}/${org}/${project}/_git/${repo}?path=/${microagentPath}&version=GBmain`;
-      }
-      return "";
-    }
     default:
       return "";
   }
@@ -380,15 +357,6 @@ export const constructBranchUrl = (
       return `${baseUrl}/${repositoryName}/-/tree/${branchName}`;
     case "bitbucket":
       return `${baseUrl}/${repositoryName}/src/${branchName}`;
-    case "azure_devops": {
-      // Azure DevOps format: org/project/repo
-      const parts = repositoryName.split("/");
-      if (parts.length === 3) {
-        const [org, project, repo] = parts;
-        return `${baseUrl}/${org}/${project}/_git/${repo}?version=GB${branchName}`;
-      }
-      return "";
-    }
     default:
       return "";
   }

frontend/src/utils/verified-models.ts

@@ -59,7 +59,6 @@ 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/agenthub/codeact_agent/prompts/system_prompt.j2

@@ -72,7 +72,7 @@ Your primary role is to assist users by executing commands, modifying code, and
 </SECURITY_RISK_ASSESSMENT>
 
 <EXTERNAL_SERVICES>
-* When interacting with external services like GitHub, GitLab, Bitbucket, or Azure DevOps, use their respective APIs instead of browser-based interactions whenever possible.
+* When interacting with external services like GitHub, GitLab, or Bitbucket, use their respective APIs instead of browser-based interactions whenever possible.
 * Only resort to browser-based interactions with these services if specifically requested by the user or if the required operation cannot be performed via API.
 </EXTERNAL_SERVICES>
 

openhands/app_server/app_conversation/app_conversation_info_service.py

@@ -9,7 +9,6 @@ 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
 
 
@@ -93,19 +92,6 @@ 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_models.py

@@ -1,6 +1,6 @@
 from datetime import datetime
 from enum import Enum
-from uuid import UUID, uuid4
+from uuid import uuid4
 
 from pydantic import BaseModel, Field
 
@@ -97,9 +97,7 @@ class AppConversationStartRequest(BaseModel):
     """
 
     sandbox_id: str | None = Field(default=None)
-    conversation_id: UUID | None = Field(default=None)
     initial_message: SendMessageRequest | None = None
-    system_message_suffix: str | None = None
     processors: list[EventCallbackProcessor] | None = Field(default=None)
     llm_model: str | None = None
 

openhands/app_server/app_conversation/app_conversation_router.py

@@ -1,9 +1,7 @@
 """Sandboxed Conversation router for OpenHands Server."""
 
 import asyncio
-import os
 import sys
-import tempfile
 from datetime import datetime
 from typing import Annotated, AsyncGenerator
 from uuid import UUID
@@ -51,21 +49,9 @@ from openhands.app_server.config import (
     depends_app_conversation_start_task_service,
     depends_db_session,
     depends_httpx_client,
-    depends_sandbox_service,
-    depends_sandbox_spec_service,
     depends_user_context,
     get_app_conversation_service,
 )
-from openhands.app_server.sandbox.sandbox_models import (
-    AGENT_SERVER,
-    SandboxStatus,
-)
-from openhands.app_server.sandbox.sandbox_service import SandboxService
-from openhands.app_server.sandbox.sandbox_spec_service import SandboxSpecService
-from openhands.app_server.utils.docker_utils import (
-    replace_localhost_hostname_for_docker,
-)
-from openhands.sdk.workspace.remote.async_remote_workspace import AsyncRemoteWorkspace
 
 router = APIRouter(prefix='/app-conversations', tags=['Conversations'])
 app_conversation_service_dependency = depends_app_conversation_service()
@@ -75,8 +61,6 @@ app_conversation_start_task_service_dependency = (
 user_context_dependency = depends_user_context()
 db_session_dependency = depends_db_session()
 httpx_client_dependency = depends_httpx_client()
-sandbox_service_dependency = depends_sandbox_service()
-sandbox_spec_service_dependency = depends_sandbox_spec_service()
 
 # Read methods
 
@@ -305,101 +289,6 @@ async def batch_get_app_conversation_start_tasks(
     return start_tasks
 
 
-@router.get('/{conversation_id}/file')
-async def read_conversation_file(
-    conversation_id: UUID,
-    file_path: Annotated[
-        str,
-        Query(title='Path to the file to read within the sandbox workspace'),
-    ] = '/workspace/project/PLAN.md',
-    app_conversation_service: AppConversationService = (
-        app_conversation_service_dependency
-    ),
-    sandbox_service: SandboxService = sandbox_service_dependency,
-    sandbox_spec_service: SandboxSpecService = sandbox_spec_service_dependency,
-) -> str:
-    """Read a file from a specific conversation's sandbox workspace.
-
-    Returns the content of the file at the specified path if it exists, otherwise returns an empty string.
-
-    Args:
-        conversation_id: The UUID of the conversation
-        file_path: Path to the file to read within the sandbox workspace
-
-    Returns:
-        The content of the file or an empty string if the file doesn't exist
-    """
-    # Get the conversation info
-    conversation = await app_conversation_service.get_app_conversation(conversation_id)
-    if not conversation:
-        return ''
-
-    # Get the sandbox info
-    sandbox = await sandbox_service.get_sandbox(conversation.sandbox_id)
-    if not sandbox or sandbox.status != SandboxStatus.RUNNING:
-        return ''
-
-    # Get the sandbox spec to find the working directory
-    sandbox_spec = await sandbox_spec_service.get_sandbox_spec(sandbox.sandbox_spec_id)
-    if not sandbox_spec:
-        return ''
-
-    # Get the agent server URL
-    if not sandbox.exposed_urls:
-        return ''
-
-    agent_server_url = None
-    for exposed_url in sandbox.exposed_urls:
-        if exposed_url.name == AGENT_SERVER:
-            agent_server_url = exposed_url.url
-            break
-
-    if not agent_server_url:
-        return ''
-
-    agent_server_url = replace_localhost_hostname_for_docker(agent_server_url)
-
-    # Create remote workspace
-    remote_workspace = AsyncRemoteWorkspace(
-        host=agent_server_url,
-        api_key=sandbox.session_api_key,
-        working_dir=sandbox_spec.working_dir,
-    )
-
-    # Read the file at the specified path
-    temp_file_path = None
-    try:
-        # Create a temporary file path to download the remote file
-        with tempfile.NamedTemporaryFile(mode='w+b', delete=False) as temp_file:
-            temp_file_path = temp_file.name
-
-        # Download the file from remote system
-        result = await remote_workspace.file_download(
-            source_path=file_path,
-            destination_path=temp_file_path,
-        )
-
-        if result.success:
-            # Read the content from the temporary file
-            with open(temp_file_path, 'rb') as f:
-                content = f.read()
-            # Decode bytes to string
-            return content.decode('utf-8')
-    except Exception:
-        # If there's any error reading the file, return empty string
-        pass
-    finally:
-        # Clean up the temporary file
-        if temp_file_path:
-            try:
-                os.unlink(temp_file_path)
-            except Exception:
-                # Ignore errors during cleanup
-                pass
-
-    return ''
-
-
 async def _consume_remaining(
     async_iter, db_session: AsyncSession, httpx_client: httpx.AsyncClient
 ):

openhands/app_server/app_conversation/app_conversation_service_base.py

@@ -9,7 +9,6 @@ from typing import AsyncGenerator
 import base62
 
 from openhands.app_server.app_conversation.app_conversation_models import (
-    AgentType,
     AppConversationStartTask,
     AppConversationStartTaskStatus,
 )
@@ -26,9 +25,7 @@ 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__)
@@ -185,43 +182,6 @@ 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,
@@ -237,9 +197,6 @@ 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.')
@@ -264,9 +221,7 @@ 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, 120
-        )
+        result = await workspace.execute_command(clone_command, workspace.working_dir)
         if result.exit_code:
             _logger.warning(f'Git clone failed: {result.stderr}')
 
@@ -278,10 +233,7 @@ 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}'
-        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}')
+        await workspace.execute_command(checkout_command, workspace.working_dir)
 
     async def maybe_run_setup_script(
         self,
@@ -343,39 +295,3 @@ 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 Any, AsyncGenerator, Sequence
+from typing import AsyncGenerator, Sequence
 from uuid import UUID, uuid4
 
 import httpx
 from fastapi import Request
-from pydantic import Field, SecretStr, TypeAdapter
+from pydantic import Field, TypeAdapter
 
 from openhands.agent_server.models import (
     ConversationInfo,
@@ -63,28 +63,22 @@ 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 Agent, AgentContext, LocalWorkspace
+from openhands.sdk import 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_tools,
-)
-from openhands.tools.preset.planning import (
-    format_plan_structure,
-    get_planning_tools,
-)
+from openhands.tools.preset.default import get_default_agent
+from openhands.tools.preset.planning import get_planning_agent
 
 _conversation_info_type_adapter = TypeAdapter(list[ConversationInfo | None])
 _logger = logging.getLogger(__name__)
+GIT_TOKEN = 'GIT_TOKEN'
 
 
 @dataclass
@@ -103,9 +97,6 @@ class LiveStatusAppConversationService(AppConversationServiceBase):
     httpx_client: httpx.AsyncClient
     web_url: str | None
     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,
@@ -237,12 +228,10 @@ class LiveStatusAppConversationService(AppConversationServiceBase):
                 await self._build_start_conversation_request_for_user(
                     sandbox,
                     request.initial_message,
-                    request.system_message_suffix,
                     request.git_provider,
                     sandbox_spec.working_dir,
                     request.agent_type,
                     request.llm_model,
-                    request.conversation_id,
                     remote_workspace=remote_workspace,
                     selected_repository=request.selected_repository,
                 )
@@ -288,17 +277,14 @@ class LiveStatusAppConversationService(AppConversationServiceBase):
             )
 
             # Setup default processors
-            processors = request.processors or []
-
-            # Always ensure SetTitleCallbackProcessor is included
-            has_set_title_processor = any(
-                isinstance(processor, SetTitleCallbackProcessor)
-                for processor in processors
-            )
-            if not has_set_title_processor:
-                processors.append(SetTitleCallbackProcessor())
+            processors = request.processors
+            if processors is None:
+                processors = [SetTitleCallbackProcessor()]
 
             # Save processors
+            # Save processors sequentially to avoid concurrent database session usage
+            # This is a simple database operation (upsert) that's very fast, so the
+            # performance impact of sequential vs parallel is negligible
             for processor in processors:
                 await self.event_callback_service.save_event_callback(
                     EventCallback(
@@ -526,65 +512,48 @@ 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.
+    async def _build_start_conversation_request_for_user(
+        self,
+        sandbox: SandboxInfo,
+        initial_message: SendMessageRequest | None,
+        git_provider: ProviderType | None,
+        working_dir: str,
+        agent_type: AgentType = AgentType.DEFAULT,
+        llm_model: str | None = None,
+        remote_workspace: AsyncRemoteWorkspace | None = None,
+        selected_repository: str | None = None,
+    ) -> StartConversationRequest:
+        user = await self.user_context.get_user_info()
 
-        Args:
-            git_provider: The git provider type (GitHub, GitLab, etc.)
-            user: User information containing authentication details
-
-        Returns:
-            Dictionary of secrets for the conversation
-        """
+        # Set up a secret for the git token
         secrets = await self.user_context.get_secrets()
+        if git_provider:
+            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,
+                )
+                secrets[GIT_TOKEN] = LookupSecret(
+                    url=self.web_url + '/api/v1/webhooks/secrets',
+                    headers={'X-Access-Token': access_token},
+                )
+            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[GIT_TOKEN] = StaticSecret(value=static_token)
 
-        if not git_provider:
-            return secrets
+        workspace = LocalWorkspace(working_dir=working_dir)
 
-        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
+        # Use provided llm_model if available, otherwise fall back to user's default
         model = llm_model or user.llm_model
         llm = LLM(
             model=model,
@@ -592,137 +561,19 @@ class LiveStatusAppConversationService(AppConversationServiceBase):
             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
+        # The agent gets passed initial instructions
+        # Select agent based on agent_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,
-            )
+            agent = get_planning_agent(llm=llm)
         else:
-            agent = Agent(
-                llm=llm,
-                tools=get_default_tools(enable_browser=True),
-                system_prompt_kwargs={'cli_mode': False},
-                condenser=condenser,
-                mcp_config=mcp_config,
-            )
+            agent = get_default_agent(llm=llm)
 
-        # 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
+        conversation_id = uuid4()
         agent = ExperimentManagerImpl.run_agent_variant_tests__v1(
             user.id, conversation_id, agent
         )
 
-        # Load and merge skills if remote workspace is available
+        # Load and merge all skills if remote_workspace is available
         if remote_workspace:
             try:
                 agent = await self._load_skills_and_update_agent(
@@ -732,8 +583,7 @@ class LiveStatusAppConversationService(AppConversationServiceBase):
                 _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(
+        start_conversation_request = StartConversationRequest(
             conversation_id=conversation_id,
             agent=agent,
             workspace=workspace,
@@ -743,55 +593,7 @@ class LiveStatusAppConversationService(AppConversationServiceBase):
             initial_message=initial_message,
             secrets=secrets,
         )
-
-    async def _build_start_conversation_request_for_user(
-        self,
-        sandbox: SandboxInfo,
-        initial_message: SendMessageRequest | None,
-        system_message_suffix: str | None,
-        git_provider: ProviderType | None,
-        working_dir: str,
-        agent_type: AgentType = AgentType.DEFAULT,
-        llm_model: str | None = None,
-        conversation_id: UUID | None = None,
-        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()
-        workspace = LocalWorkspace(working_dir=working_dir)
-
-        # Set up secrets for git provider
-        secrets = await self._setup_secrets_for_git_provider(git_provider, user)
-
-        # Configure LLM and MCP
-        llm, mcp_config = await self._configure_llm_and_mcp(user, llm_model)
-
-        # Create agent with context
-        agent = self._create_agent_with_context(
-            llm, agent_type, system_message_suffix, mcp_config, user.condenser_max_size
-        )
-
-        # 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,
@@ -996,10 +798,6 @@ 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
@@ -1042,29 +840,6 @@ class LiveStatusAppConversationServiceInjector(AppConversationServiceInjector):
                 if isinstance(sandbox_service, DockerSandboxService):
                     web_url = f'http://host.docker.internal:{sandbox_service.host_port}'
 
-            # Get app_mode and keycloak_auth cookie for SaaS mode
-            app_mode = None
-            keycloak_auth_cookie = None
-            try:
-                from openhands.server.shared import server_config
-
-                app_mode = (
-                    server_config.app_mode.value if server_config.app_mode else None
-                )
-                if request and server_config.app_mode == AppMode.SAAS:
-                    keycloak_auth_cookie = request.cookies.get('keycloak_auth')
-            except (ImportError, AttributeError):
-                # 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,
@@ -1079,7 +854,4 @@ class LiveStatusAppConversationServiceInjector(AppConversationServiceInjector):
                 httpx_client=httpx_client,
                 web_url=web_url,
                 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

@@ -45,8 +45,6 @@ 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
@@ -356,130 +354,6 @@ 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

@@ -6,11 +6,9 @@ from typing import AsyncContextManager
 
 import httpx
 from fastapi import Depends, Request
-from pydantic import Field, SecretStr
+from pydantic import Field
 from sqlalchemy.ext.asyncio import AsyncSession
 
-# Import the event_callback module to ensure all processors are registered
-import openhands.app_server.event_callback  # noqa: F401
 from openhands.agent_server.env_parser import from_env
 from openhands.app_server.app_conversation.app_conversation_info_service import (
     AppConversationInfoService,
@@ -185,13 +183,7 @@ def config_from_env() -> AppServerConfig:
         )
 
     if config.app_conversation is None:
-        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
-        )
+        config.app_conversation = LiveStatusAppConversationServiceInjector()
 
     if config.user is None:
         config.user = AuthUserContextInjector()

openhands/app_server/event_callback/__init__.py

@@ -1,21 +0,0 @@
-"""Event callback system for OpenHands.
-
-This module provides the event callback system that allows processors to be
-registered and executed when specific events occur during conversations.
-
-All callback processors must be imported here to ensure they are registered
-with the discriminated union system used by Pydantic for validation.
-"""
-
-# Import base classes and processors without circular dependencies
-from .event_callback_models import EventCallbackProcessor, LoggingCallbackProcessor
-from .github_v1_callback_processor import GithubV1CallbackProcessor
-
-# Note: SetTitleCallbackProcessor is not imported here to avoid circular imports
-# It will be registered when imported elsewhere in the application
-
-__all__ = [
-    'EventCallbackProcessor',
-    'LoggingCallbackProcessor',
-    'GithubV1CallbackProcessor',
-]

openhands/app_server/event_callback/github_v1_callback_processor.py

@@ -1,296 +0,0 @@
-import logging
-import os
-from typing import Any
-from uuid import UUID
-
-import httpx
-from github import Github, GithubIntegration
-from pydantic import Field
-
-from openhands.agent_server.models import AskAgentRequest, AskAgentResponse
-from openhands.app_server.event_callback.event_callback_models import (
-    EventCallback,
-    EventCallbackProcessor,
-)
-from openhands.app_server.event_callback.event_callback_result_models import (
-    EventCallbackResult,
-    EventCallbackResultStatus,
-)
-from openhands.app_server.event_callback.util import (
-    ensure_conversation_found,
-    ensure_running_sandbox,
-    get_agent_server_url_from_sandbox,
-    get_conversation_url,
-    get_prompt_template,
-)
-from openhands.sdk import Event
-from openhands.sdk.event import ConversationStateUpdateEvent
-
-_logger = logging.getLogger(__name__)
-
-
-class GithubV1CallbackProcessor(EventCallbackProcessor):
-    """Callback processor for GitHub V1 integrations."""
-
-    github_view_data: dict[str, Any] = Field(default_factory=dict)
-    should_request_summary: bool = Field(default=True)
-    should_extract: bool = Field(default=True)
-    inline_pr_comment: bool = Field(default=False)
-
-    async def __call__(
-        self,
-        conversation_id: UUID,
-        callback: EventCallback,
-        event: Event,
-    ) -> EventCallbackResult | None:
-        """Process events for GitHub V1 integration."""
-
-        # Only handle ConversationStateUpdateEvent
-        if not isinstance(event, ConversationStateUpdateEvent):
-            return None
-
-        # Only act when execution has finished
-        if not (event.key == 'execution_status' and event.value == 'finished'):
-            return None
-
-        _logger.info('[GitHub V1] Callback agent state was %s', event)
-        _logger.info(
-            '[GitHub V1] Should request summary: %s', self.should_request_summary
-        )
-
-        if not self.should_request_summary:
-            return None
-
-        self.should_request_summary = False
-
-        try:
-            summary = await self._request_summary(conversation_id)
-            await self._post_summary_to_github(summary)
-
-            return EventCallbackResult(
-                status=EventCallbackResultStatus.SUCCESS,
-                event_callback_id=callback.id,
-                event_id=event.id,
-                conversation_id=conversation_id,
-                detail=summary,
-            )
-        except Exception as e:
-            _logger.exception('[GitHub V1] Error processing callback: %s', e)
-
-            # Only try to post error to GitHub if we have basic requirements
-            try:
-                # Check if we have installation ID and credentials before posting
-                if (
-                    self.github_view_data.get('installation_id')
-                    and os.getenv('GITHUB_APP_CLIENT_ID')
-                    and os.getenv('GITHUB_APP_PRIVATE_KEY')
-                ):
-                    await self._post_summary_to_github(
-                        f'OpenHands encountered an error: **{str(e)}**.\n\n'
-                        f'[See the conversation]({get_conversation_url().format(conversation_id)})'
-                        'for more information.'
-                    )
-            except Exception as post_error:
-                _logger.warning(
-                    '[GitHub V1] Failed to post error message to GitHub: %s', post_error
-                )
-
-            return EventCallbackResult(
-                status=EventCallbackResultStatus.ERROR,
-                event_callback_id=callback.id,
-                event_id=event.id,
-                conversation_id=conversation_id,
-                detail=str(e),
-            )
-
-    # -------------------------------------------------------------------------
-    # GitHub helpers
-    # -------------------------------------------------------------------------
-
-    def _get_installation_access_token(self) -> str:
-        installation_id = self.github_view_data.get('installation_id')
-
-        if not installation_id:
-            raise ValueError(
-                f'Missing installation ID for GitHub payload: {self.github_view_data}'
-            )
-
-        github_app_client_id = os.getenv('GITHUB_APP_CLIENT_ID', '').strip()
-        github_app_private_key = os.getenv('GITHUB_APP_PRIVATE_KEY', '').replace(
-            '\\n', '\n'
-        )
-
-        if not github_app_client_id or not github_app_private_key:
-            raise ValueError('GitHub App credentials are not configured')
-
-        github_integration = GithubIntegration(
-            github_app_client_id,
-            github_app_private_key,
-        )
-        token_data = github_integration.get_access_token(installation_id)
-        return token_data.token
-
-    async def _post_summary_to_github(self, summary: str) -> None:
-        """Post a summary comment to the configured GitHub issue."""
-        installation_token = self._get_installation_access_token()
-
-        if not installation_token:
-            raise RuntimeError('Missing GitHub credentials')
-
-        full_repo_name = self.github_view_data['full_repo_name']
-        issue_number = self.github_view_data['issue_number']
-
-        if self.inline_pr_comment:
-            with Github(installation_token) as github_client:
-                repo = github_client.get_repo(full_repo_name)
-                pr = repo.get_pull(issue_number)
-                pr.create_review_comment_reply(
-                    comment_id=self.github_view_data.get('comment_id', ''), body=summary
-                )
-            return
-
-        with Github(installation_token) as github_client:
-            repo = github_client.get_repo(full_repo_name)
-            issue = repo.get_issue(number=issue_number)
-            issue.create_comment(summary)
-
-    # -------------------------------------------------------------------------
-    # Agent / sandbox helpers
-    # -------------------------------------------------------------------------
-
-    async def _ask_question(
-        self,
-        httpx_client: httpx.AsyncClient,
-        agent_server_url: str,
-        conversation_id: UUID,
-        session_api_key: str,
-        message_content: str,
-    ) -> str:
-        """Send a message to the agent server via the V1 API and return response text."""
-        send_message_request = AskAgentRequest(question=message_content)
-
-        url = (
-            f'{agent_server_url.rstrip("/")}'
-            f'/api/conversations/{conversation_id}/ask_agent'
-        )
-        headers = {'X-Session-API-Key': session_api_key}
-        payload = send_message_request.model_dump()
-
-        try:
-            response = await httpx_client.post(
-                url,
-                json=payload,
-                headers=headers,
-                timeout=30.0,
-            )
-            response.raise_for_status()
-
-            agent_response = AskAgentResponse.model_validate(response.json())
-            return agent_response.response
-
-        except httpx.HTTPStatusError as e:
-            error_detail = f'HTTP {e.response.status_code} error'
-            try:
-                error_body = e.response.text
-                if error_body:
-                    error_detail += f': {error_body}'
-            except Exception:  # noqa: BLE001
-                pass
-
-            _logger.error(
-                '[GitHub V1] HTTP error sending message to %s: %s. '
-                'Request payload: %s. Response headers: %s',
-                url,
-                error_detail,
-                payload,
-                dict(e.response.headers),
-                exc_info=True,
-            )
-            raise Exception(f'Failed to send message to agent server: {error_detail}')
-
-        except httpx.TimeoutException:
-            error_detail = f'Request timeout after 30 seconds to {url}'
-            _logger.error(
-                '[GitHub V1] %s. Request payload: %s',
-                error_detail,
-                payload,
-                exc_info=True,
-            )
-            raise Exception(error_detail)
-
-        except httpx.RequestError as e:
-            error_detail = f'Request error to {url}: {str(e)}'
-            _logger.error(
-                '[GitHub V1] %s. Request payload: %s',
-                error_detail,
-                payload,
-                exc_info=True,
-            )
-            raise Exception(error_detail)
-
-    # -------------------------------------------------------------------------
-    # Summary orchestration
-    # -------------------------------------------------------------------------
-
-    async def _request_summary(self, conversation_id: UUID) -> str:
-        """
-        Ask the agent to produce a summary of its work and return the agent response.
-
-        NOTE: This method now returns a string (the agent server's response text)
-        and raises exceptions on errors. The wrapping into EventCallbackResult
-        is handled by __call__.
-        """
-        # Import services within the method to avoid circular imports
-        from openhands.app_server.config import (
-            get_app_conversation_info_service,
-            get_httpx_client,
-            get_sandbox_service,
-        )
-        from openhands.app_server.services.injector import InjectorState
-        from openhands.app_server.user.specifiy_user_context import (
-            ADMIN,
-            USER_CONTEXT_ATTR,
-        )
-
-        # Create injector state for dependency injection
-        state = InjectorState()
-        setattr(state, USER_CONTEXT_ATTR, ADMIN)
-
-        async with (
-            get_app_conversation_info_service(state) as app_conversation_info_service,
-            get_sandbox_service(state) as sandbox_service,
-            get_httpx_client(state) as httpx_client,
-        ):
-            # 1. Conversation lookup
-            app_conversation_info = ensure_conversation_found(
-                await app_conversation_info_service.get_app_conversation_info(
-                    conversation_id
-                ),
-                conversation_id,
-            )
-
-            # 2. Sandbox lookup + validation
-            sandbox = ensure_running_sandbox(
-                await sandbox_service.get_sandbox(app_conversation_info.sandbox_id),
-                app_conversation_info.sandbox_id,
-            )
-
-            assert sandbox.session_api_key is not None, (
-                f'No session API key for sandbox: {sandbox.id}'
-            )
-
-            # 3. URL + instruction
-            agent_server_url = get_agent_server_url_from_sandbox(sandbox)
-            agent_server_url = get_agent_server_url_from_sandbox(sandbox)
-
-            # Prepare message based on agent state
-            message_content = get_prompt_template('summary_prompt.j2')
-
-            # Ask the agent and return the response text
-            return await self._ask_question(
-                httpx_client=httpx_client,
-                agent_server_url=agent_server_url,
-                conversation_id=conversation_id,
-                session_api_key=sandbox.session_api_key,
-                message_content=message_content,
-            )

openhands/app_server/event_callback/sql_event_callback_service.py

@@ -6,6 +6,7 @@ from __future__ import annotations
 import asyncio
 import logging
 from dataclasses import dataclass
+from datetime import datetime
 from typing import AsyncGenerator
 from uuid import UUID
 
@@ -14,7 +15,6 @@ 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 = utc_now()
+        event_callback.updated_at = datetime.now()
         stored_callback = StoredEventCallback(**event_callback.model_dump())
         await self.db_session.merge(stored_callback)
         return event_callback
@@ -209,10 +209,6 @@ class SQLEventCallbackService(EventCallbackService):
                     for callback in callbacks
                 ]
             )
-
-            # Persist any new changes callbacks may have made to itself
-            for callback in callbacks:
-                await self.save_event_callback(callback)
             await self.db_session.commit()
 
     async def execute_callback(