Remove KeyboardInterrupt exit behavior from main chat loop

- Change KeyboardInterrupt handler to continue loop instead of exiting
- Let signal handler manage Ctrl+C behavior completely
- Only exit on explicit /exit command or outer KeyboardInterrupt

This ensures that Ctrl+C during agent processing returns to chat loop
instead of exiting the entire application.

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

.devcontainer/README.md

@@ -1 +0,0 @@
-This way of running OpenHands is not officially supported. It is maintained by the community.

.devcontainer/setup.sh

@@ -7,8 +7,5 @@ git config --global --add safe.directory "$(realpath .)"
 # Install `nc`
 sudo apt update && sudo apt install netcat -y
 
-# Install `uv` and `uvx`
-wget -qO- https://astral.sh/uv/install.sh | sh
-
 # Do common setup tasks
 source .openhands/setup.sh

.github/pull_request_template.md

@@ -13,7 +13,6 @@
 - [ ] Other (dependency update, docs, typo fixes, etc.)
 
 ## Checklist
-<!-- AI/LLM AGENTS: This checklist is for a human author to complete. Do NOT check either of the two boxes below. Leave them unchecked until a human has personally reviewed and tested the changes. -->
 
 - [ ] I have read and reviewed the code and I understand what the code is doing.
 - [ ] I have tested the code to the best of my ability and ensured it works as expected.

.github/scripts/check_version_consistency.py

@@ -0,0 +1,73 @@
+#!/usr/bin/env python3
+import os
+import re
+import sys
+
+
+def find_version_references(directory: str) -> tuple[set[str], set[str]]:
+    openhands_versions = set()
+    runtime_versions = set()
+
+    version_pattern_openhands = re.compile(r'openhands:(\d{1})\.(\d{2})')
+    version_pattern_runtime = re.compile(r'runtime:(\d{1})\.(\d{2})')
+
+    for root, _, files in os.walk(directory):
+        # Skip .git directory and docs/build directory
+        if '.git' in root or 'docs/build' in root:
+            continue
+
+        for file in files:
+            if file.endswith(
+                ('.md', '.yml', '.yaml', '.txt', '.html', '.py', '.js', '.ts')
+            ):
+                file_path = os.path.join(root, file)
+                try:
+                    with open(file_path, 'r', encoding='utf-8') as f:
+                        content = f.read()
+
+                        # Find all openhands version references
+                        matches = version_pattern_openhands.findall(content)
+                        if matches:
+                            print(f'Found openhands version {matches} in {file_path}')
+                            openhands_versions.update(matches)
+
+                        # Find all runtime version references
+                        matches = version_pattern_runtime.findall(content)
+                        if matches:
+                            print(f'Found runtime version {matches} in {file_path}')
+                            runtime_versions.update(matches)
+                except Exception as e:
+                    print(f'Error reading {file_path}: {e}', file=sys.stderr)
+
+    return openhands_versions, runtime_versions
+
+
+def main():
+    repo_root = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..'))
+    print(f'Checking version consistency in {repo_root}')
+    openhands_versions, runtime_versions = find_version_references(repo_root)
+
+    print(f'Found openhands versions: {sorted(openhands_versions)}')
+    print(f'Found runtime versions: {sorted(runtime_versions)}')
+
+    exit_code = 0
+
+    if len(openhands_versions) > 1:
+        print('Error: Multiple openhands versions found:', file=sys.stderr)
+        print('Found versions:', sorted(openhands_versions), file=sys.stderr)
+        exit_code = 1
+    elif len(openhands_versions) == 0:
+        print('Warning: No openhands version references found', file=sys.stderr)
+
+    if len(runtime_versions) > 1:
+        print('Error: Multiple runtime versions found:', file=sys.stderr)
+        print('Found versions:', sorted(runtime_versions), file=sys.stderr)
+        exit_code = 1
+    elif len(runtime_versions) == 0:
+        print('Warning: No runtime version references found', file=sys.stderr)
+
+    sys.exit(exit_code)
+
+
+if __name__ == '__main__':
+    main()

.github/workflows/check-package-versions.yml

@@ -1,65 +0,0 @@
-name: Check Package Versions
-
-on:
-  push:
-    branches: [main]
-  pull_request:
-  workflow_dispatch:
-
-jobs:
-  check-package-versions:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-
-      - name: Check for any 'rev' fields in pyproject.toml
-        run: |
-          python - <<'PY'
-          import sys, tomllib, pathlib
-
-          path = pathlib.Path("pyproject.toml")
-          if not path.exists():
-              print("❌ ERROR: pyproject.toml not found")
-              sys.exit(1)
-
-          try:
-              data = tomllib.loads(path.read_text(encoding="utf-8"))
-          except Exception as e:
-              print(f"❌ ERROR: Failed to parse pyproject.toml: {e}")
-              sys.exit(1)
-
-          poetry = data.get("tool", {}).get("poetry", {})
-          sections = {
-              "dependencies": poetry.get("dependencies", {}),
-          }
-
-          errors = []
-
-          print("🔍 Checking for any dependencies with 'rev' fields...\n")
-          for section_name, deps in sections.items():
-              if not isinstance(deps, dict):
-                  continue
-
-              for pkg_name, cfg in deps.items():
-                  if isinstance(cfg, dict) and "rev" in cfg:
-                      msg = f"  ✖ {pkg_name} in [{section_name}] uses rev='{cfg['rev']}' (NOT ALLOWED)"
-                      print(msg)
-                      errors.append(msg)
-                  else:
-                      print(f"  • {pkg_name}: OK")
-
-          if errors:
-              print("\n❌ FAILED: Found dependencies using 'rev' fields:\n" + "\n".join(errors))
-              print("\nPlease use versioned releases instead, e.g.:")
-              print('  my-package = "1.0.0"')
-              sys.exit(1)
-
-          print("\n✅ SUCCESS: No 'rev' fields found. All dependencies are using proper versioned releases.")
-          PY

.github/workflows/cli-build-test.yml

@@ -1,58 +0,0 @@
-# Workflow that builds and tests the CLI binary executable
-name: CLI - Build and Test Binary
-
-# Run on pushes to main branch and all pull requests, but only when CLI files change
-on:
-  push:
-    branches:
-      - main
-    paths:
-      - "openhands-cli/**"
-  pull_request:
-    paths:
-      - "openhands-cli/**"
-
-# Cancel previous runs if a new commit is pushed
-concurrency:
-  group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  build-and-test-binary:
-    name: Build and test binary executable
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: 3.12
-
-      - name: Install uv
-        uses: astral-sh/setup-uv@v3
-        with:
-          version: "latest"
-
-      - name: Install dependencies
-        working-directory: openhands-cli
-        run: |
-          uv sync
-
-      - name: Build binary executable
-        working-directory: openhands-cli
-        run: |
-          ./build.sh --install-pyinstaller | tee output.log
-          echo "Full output:"
-          cat output.log
-
-          if grep -q "❌" output.log; then
-            echo "❌ Found failure marker in output"
-            exit 1
-          fi
-
-          echo "✅ Build & test finished without ❌ markers"

.github/workflows/ghcr-build.yml

@@ -86,7 +86,7 @@ jobs:
 
   # Builds the runtime Docker images
   ghcr_build_runtime:
-    name: Build Runtime Image
+    name: Build Image
     runs-on: blacksmith-8vcpu-ubuntu-2204
     if: "!(github.event_name == 'push' && startsWith(github.ref, 'refs/tags/ext-v'))"
     permissions:
@@ -256,7 +256,7 @@ jobs:
   test_runtime_root:
     name: RT Unit Tests (Root)
     needs: [ghcr_build_runtime, define-matrix]
-    runs-on: blacksmith-4vcpu-ubuntu-2404
+    runs-on: blacksmith-8vcpu-ubuntu-2204
     strategy:
       fail-fast: false
       matrix:
@@ -298,7 +298,7 @@ jobs:
           # We install pytest-xdist in order to run tests across CPUs
           poetry run pip install pytest-xdist
 
-          # Install to be able to retry on failures for flakey tests
+          # Install to be able to retry on failures for flaky tests
           poetry run pip install pytest-rerunfailures
 
           image_name=ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
@@ -311,14 +311,14 @@ jobs:
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=false \
-          poetry run pytest -n 5 -raRs --reruns 2 --reruns-delay 3 -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
+          poetry run pytest -n 0 -raRs --reruns 2 --reruns-delay 5 -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
         env:
           DEBUG: "1"
 
   # Run unit tests with the Docker runtime Docker images as openhands user
   test_runtime_oh:
     name: RT Unit Tests (openhands)
-    runs-on: blacksmith-4vcpu-ubuntu-2404
+    runs-on: blacksmith-8vcpu-ubuntu-2204
     needs: [ghcr_build_runtime, define-matrix]
     strategy:
       matrix:
@@ -370,7 +370,7 @@ jobs:
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=true \
-          poetry run pytest -n 5 -raRs --reruns 2 --reruns-delay 3 -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
+          poetry run pytest -n 0 -raRs --reruns 2 --reruns-delay 5 -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py --durations=10
         env:
           DEBUG: "1"
 

.github/workflows/integration-runner.yml

@@ -0,0 +1,199 @@
+name: Run Integration Tests
+
+on:
+  pull_request:
+    types: [labeled]
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: 'Reason for manual trigger'
+        required: true
+        default: ''
+  schedule:
+    - cron: '30 22 * * *'  # Runs at 10:30pm UTC every day
+
+env:
+  N_PROCESSES: 10 # Global configuration for number of parallel processes for evaluation
+
+jobs:
+  run-integration-tests:
+    if: github.event.label.name == 'integration-test' || github.event_name == 'workflow_dispatch' || github.event_name == 'schedule'
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    permissions:
+      contents: "read"
+      id-token: "write"
+      pull-requests: "write"
+      issues: "write"
+    strategy:
+      matrix:
+        python-version: ["3.12"]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: useblacksmith/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "poetry"
+
+      - name: Setup Node.js
+        uses: useblacksmith/setup-node@v5
+        with:
+          node-version: '22.x'
+
+      - name: Comment on PR if 'integration-test' label is present
+        if: github.event_name == 'pull_request' && github.event.label.name == 'integration-test'
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          unique: false
+          comment: |
+            Hi! I started running the integration tests on your PR. You will receive a comment with the results shortly.
+
+      - name: Install Python dependencies using Poetry
+        run: poetry install --with dev,test,runtime,evaluation
+
+      - name: Configure config.toml for testing with Haiku
+        env:
+          LLM_MODEL: "litellm_proxy/claude-3-5-haiku-20241022"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 10
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+
+      - name: Build environment
+        run: make build
+
+      - name: Run integration test evaluation for Haiku
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' 10 $N_PROCESSES '' 'haiku_run'
+
+          # get integration tests report
+          REPORT_FILE_HAIKU=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/*haiku*_maxiter_10_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE: $REPORT_FILE_HAIKU"
+          echo "INTEGRATION_TEST_REPORT_HAIKU<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_HAIKU >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      - name: Wait a little bit
+        run: sleep 10
+
+      - name: Configure config.toml for testing with DeepSeek
+        env:
+          LLM_MODEL: "litellm_proxy/deepseek-chat"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 10
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+
+      - name: Run integration test evaluation for DeepSeek
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' 10 $N_PROCESSES '' 'deepseek_run'
+
+          # get integration tests report
+          REPORT_FILE_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/deepseek*_maxiter_10_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE: $REPORT_FILE_DEEPSEEK"
+          echo "INTEGRATION_TEST_REPORT_DEEPSEEK<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_DEEPSEEK >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      # -------------------------------------------------------------
+      # Run VisualBrowsingAgent tests for DeepSeek, limited to t05 and t06
+      - name: Wait a little bit (again)
+        run: sleep 5
+
+      - name: Configure config.toml for testing VisualBrowsingAgent (DeepSeek)
+        env:
+          LLM_MODEL: "litellm_proxy/deepseek-chat"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 15
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+      - name: Run integration test evaluation for VisualBrowsingAgent (DeepSeek)
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD VisualBrowsingAgent '' 15 $N_PROCESSES "t05_simple_browsing,t06_github_pr_browsing.py" 'visualbrowsing_deepseek_run'
+
+          # Find and export the visual browsing agent test results
+          REPORT_FILE_VISUALBROWSING_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/VisualBrowsingAgent/deepseek*_maxiter_15_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE_VISUALBROWSING_DEEPSEEK: $REPORT_FILE_VISUALBROWSING_DEEPSEEK"
+          echo "INTEGRATION_TEST_REPORT_VISUALBROWSING_DEEPSEEK<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_VISUALBROWSING_DEEPSEEK >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      - name: Create archive of evaluation outputs
+        run: |
+          TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
+          cd evaluation/evaluation_outputs/outputs  # Change to the outputs directory
+          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/* integration_tests/VisualBrowsingAgent/* # Only include the actual result directories
+
+      - name: Upload evaluation results as artifact
+        uses: actions/upload-artifact@v4
+        id: upload_results_artifact
+        with:
+          name: integration-test-outputs-${{ github.run_id }}-${{ github.run_attempt }}
+          path: integration_tests_*.tar.gz
+
+      - name: Get artifact URLs
+        run: |
+          echo "ARTIFACT_URL=${{ steps.upload_results_artifact.outputs.artifact-url }}" >> $GITHUB_ENV
+
+      - name: Set timestamp and trigger reason
+        run: |
+          echo "TIMESTAMP=$(date +'%Y-%m-%d-%H-%M')" >> $GITHUB_ENV
+          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            echo "TRIGGER_REASON=pr-${{ github.event.pull_request.number }}" >> $GITHUB_ENV
+          elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            echo "TRIGGER_REASON=manual-${{ github.event.inputs.reason }}" >> $GITHUB_ENV
+          else
+            echo "TRIGGER_REASON=nightly-scheduled" >> $GITHUB_ENV
+          fi
+
+      - name: Comment with results and artifact link
+        id: create_comment
+        uses: KeisukeYamashita/create-comment@v1
+        with:
+          # if triggered by PR, use PR number, otherwise use 9745 as fallback issue number for manual triggers
+          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || 9745 }}
+          unique: false
+          comment: |
+              Trigger by: ${{ github.event_name == 'pull_request' && format('Pull Request (integration-test label on PR #{0})', github.event.pull_request.number) || (github.event_name == 'workflow_dispatch' && format('Manual Trigger: {0}', github.event.inputs.reason)) || 'Nightly Scheduled Run' }}
+              Commit: ${{ github.sha }}
+              **Integration Tests Report (Haiku)**
+              Haiku LLM Test Results:
+              ${{ env.INTEGRATION_TEST_REPORT_HAIKU }}
+              ---
+              **Integration Tests Report (DeepSeek)**
+              DeepSeek LLM Test Results:
+              ${{ env.INTEGRATION_TEST_REPORT_DEEPSEEK }}
+              ---
+              **Integration Tests Report VisualBrowsing (DeepSeek)**
+              ${{ env.INTEGRATION_TEST_REPORT_VISUALBROWSING_DEEPSEEK }}
+              ---
+              Download testing outputs (includes both Haiku and DeepSeek results): [Download](${{ steps.upload_results_artifact.outputs.artifact-url }})

.github/workflows/lint.yml

@@ -37,7 +37,7 @@ jobs:
           npm run make-i18n && tsc
           npm run check-translation-completeness
 
-  # Run lint on the python code (excluding CLI and enterprise)
+  # Run lint on the python code
   lint-python:
     name: Lint python
     runs-on: blacksmith-4vcpu-ubuntu-2204
@@ -90,3 +90,16 @@ jobs:
       - name: Run pre-commit hooks
         working-directory: ./openhands-cli
         run: pre-commit run --all-files --config ./dev_config/python/.pre-commit-config.yaml
+
+  # Check version consistency across documentation
+  check-version-consistency:
+    name: Check version consistency
+    runs-on: blacksmith-4vcpu-ubuntu-2204
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up python
+        uses: useblacksmith/setup-python@v6
+        with:
+          python-version: 3.12
+      - name: Run version consistency check
+        run: .github/scripts/check_version_consistency.py

.github/workflows/py-tests.yml

@@ -48,10 +48,7 @@ jobs:
           python-version: ${{ matrix.python-version }}
           cache: "poetry"
       - name: Install Python dependencies using Poetry
-        run: |
-          poetry install --with dev,test,runtime
-          poetry run pip install pytest-xdist
-          poetry run pip install pytest-rerunfailures
+        run: poetry install --with dev,test,runtime
       - name: Build Environment
         run: make build
       - name: Run Unit Tests
@@ -59,7 +56,7 @@ jobs:
         env:
           COVERAGE_FILE: ".coverage.${{ matrix.python_version }}"
       - name: Run Runtime Tests with CLIRuntime
-        run: PYTHONPATH=".:$PYTHONPATH" TEST_RUNTIME=cli poetry run pytest -n 5 --reruns 2 --reruns-delay 3 -s tests/runtime/test_bash.py --cov=openhands --cov-branch
+        run: PYTHONPATH=".:$PYTHONPATH" TEST_RUNTIME=cli poetry run pytest -s tests/runtime/test_bash.py --cov=openhands --cov-branch
         env:
           COVERAGE_FILE: ".coverage.runtime.${{ matrix.python_version }}"
       - name: Store coverage file
@@ -70,7 +67,37 @@ jobs:
             .coverage.${{ matrix.python_version }}
             .coverage.runtime.${{ matrix.python_version }}
           include-hidden-files: true
-
+  # Run specific Windows python tests
+  test-on-windows:
+    name: Python Tests on Windows
+    runs-on: windows-latest
+    strategy:
+      matrix:
+        python-version: ["3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install pipx
+        run: pip install pipx
+      - name: Install poetry via pipx
+        run: pipx install poetry
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "poetry"
+      - name: Install Python dependencies using Poetry
+        run: poetry install --with dev,test,runtime
+      - name: Run Windows unit tests
+        run: poetry run pytest -svv tests/unit/runtime/utils/test_windows_bash.py
+        env:
+          PYTHONPATH: ".;$env:PYTHONPATH"
+          DEBUG: "1"
+      - name: Run Windows runtime tests with LocalRuntime
+        run: $env:TEST_RUNTIME="local"; poetry run pytest -svv tests/runtime/test_bash.py
+        env:
+          PYTHONPATH: ".;$env:PYTHONPATH"
+          TEST_RUNTIME: local
+          DEBUG: "1"
   test-enterprise:
     name: Enterprise Python Unit Tests
     runs-on: blacksmith-4vcpu-ubuntu-2404
@@ -146,6 +173,7 @@ jobs:
           path: ".coverage.openhands-cli.${{ matrix.python-version }}"
           include-hidden-files: true
 
+
   coverage-comment:
     name: Coverage Comment
     if: github.event_name == 'pull_request'

.gitignore

@@ -31,8 +31,7 @@ requirements.txt
 #  Usually these files are written by a python script from a template
 #  before PyInstaller builds the exe, so as to inject date/other infos into it.
 *.manifest
-# Note: openhands-cli.spec is intentionally tracked for CLI builds
-# *.spec
+*.spec
 
 # Installer logs
 pip-log.txt
@@ -186,9 +185,6 @@ cython_debug/
 .repomix
 repomix-output.txt
 
-# Emacs backup
-*~
-
 # evaluation
 evaluation/evaluation_outputs
 evaluation/outputs

CNAME

@@ -1 +0,0 @@
-docs.all-hands.dev

CONTRIBUTING.md

@@ -58,7 +58,7 @@ by implementing the [interface specified here](https://github.com/OpenHands/Open
 
 #### Testing
 When you write code, it is also good to write tests. Please navigate to the [`./tests`](./tests) folder to see existing test suites.
-At the moment, we have these kinds of tests: [`unit`](./tests/unit), [`runtime`](./tests/runtime), and [`end-to-end (e2e)`](./tests/e2e). Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
+At the moment, we have two kinds of tests: [`unit`](./tests/unit) and [`integration`](./evaluation/integration_tests). Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
 
 ## Sending Pull Requests to OpenHands
 

Development.md

@@ -159,7 +159,7 @@ poetry run pytest ./tests/unit/test_*.py
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker
 container image by setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
 
-Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/openhands/runtime:0.62-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/openhands/runtime:0.60-nikolaik`
 
 ## Develop inside Docker container
 

README.md

@@ -51,7 +51,7 @@ Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or [sign up for
 
 ## ☁️ OpenHands Cloud
 The easiest way to get started with OpenHands is on [OpenHands Cloud](https://app.all-hands.dev),
-which comes with $10 in free credits for new users.
+which comes with $20 in free credits for new users.
 
 ## 💻 Running OpenHands Locally
 
@@ -82,17 +82,17 @@ You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)
 You can also run OpenHands directly with Docker:
 
 ```bash
-docker pull docker.openhands.dev/openhands/runtime:0.62-nikolaik
+docker pull docker.openhands.dev/openhands/runtime:0.60-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.openhands.dev/openhands/runtime:0.62-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.openhands.dev/openhands/runtime:0.60-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands:/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.openhands.dev/openhands/openhands:0.62
+    docker.openhands.dev/openhands/openhands:0.60
 ```
 
 </details>

containers/dev/README.md

@@ -1,7 +1,7 @@
 # Develop in Docker
 
 > [!WARNING]
-> This way of running OpenHands is not officially supported. It is maintained by the community and may not work.
+> This is not officially supported and may not work.
 
 Install [Docker](https://docs.docker.com/engine/install/) on your host machine and run:
 

containers/dev/compose.yml

@@ -12,7 +12,7 @@ services:
       - SANDBOX_API_HOSTNAME=host.docker.internal
       - DOCKER_HOST_ADDR=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/openhands/runtime:0.62-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/openhands/runtime:0.60-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docker-compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.openhands.dev/openhands/runtime:0.62-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.openhands.dev/openhands/runtime:0.60-nikolaik}
       #- SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234} # enable this only if you want a specific non-root sandbox user but you will have to manually adjust permissions of ~/.openhands for this user
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docs/usage/environment-variables.mdx

@@ -1,251 +0,0 @@
----
-title: Environment Variables Reference
-description: Complete reference of all environment variables supported by OpenHands
----
-
-This page provides a reference of environment variables that can be used to configure OpenHands. Environment variables provide an alternative to TOML configuration files and are particularly useful for containerized deployments, CI/CD pipelines, and cloud environments.
-
-## Environment Variable Naming Convention
-
-OpenHands follows a consistent naming pattern for environment variables:
-
-- **Core settings**: Direct uppercase mapping (e.g., `debug` → `DEBUG`)
-- **LLM settings**: Prefixed with `LLM_` (e.g., `model` → `LLM_MODEL`)
-- **Agent settings**: Prefixed with `AGENT_` (e.g., `enable_browsing` → `AGENT_ENABLE_BROWSING`)
-- **Sandbox settings**: Prefixed with `SANDBOX_` (e.g., `timeout` → `SANDBOX_TIMEOUT`)
-- **Security settings**: Prefixed with `SECURITY_` (e.g., `confirmation_mode` → `SECURITY_CONFIRMATION_MODE`)
-
-## Core Configuration Variables
-
-These variables correspond to the `[core]` section in `config.toml`:
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `DEBUG` | boolean | `false` | Enable debug logging throughout the application |
-| `DISABLE_COLOR` | boolean | `false` | Disable colored output in terminal |
-| `CACHE_DIR` | string | `"/tmp/cache"` | Directory path for caching |
-| `SAVE_TRAJECTORY_PATH` | string | `"./trajectories"` | Path to store conversation trajectories |
-| `REPLAY_TRAJECTORY_PATH` | string | `""` | Path to load and replay a trajectory file |
-| `FILE_STORE_PATH` | string | `"/tmp/file_store"` | File store directory path |
-| `FILE_STORE` | string | `"memory"` | File store type (`memory`, `local`, etc.) |
-| `FILE_UPLOADS_MAX_FILE_SIZE_MB` | integer | `0` | Maximum file upload size in MB (0 = no limit) |
-| `FILE_UPLOADS_RESTRICT_FILE_TYPES` | boolean | `false` | Whether to restrict file upload types |
-| `FILE_UPLOADS_ALLOWED_EXTENSIONS` | list | `[".*"]` | List of allowed file extensions for uploads |
-| `MAX_BUDGET_PER_TASK` | float | `0.0` | Maximum budget per task (0.0 = no limit) |
-| `MAX_ITERATIONS` | integer | `100` | Maximum number of iterations per task |
-| `RUNTIME` | string | `"docker"` | Runtime environment (`docker`, `local`, `cli`, etc.) |
-| `DEFAULT_AGENT` | string | `"CodeActAgent"` | Default agent class to use |
-| `JWT_SECRET` | string | auto-generated | JWT secret for authentication |
-| `RUN_AS_OPENHANDS` | boolean | `true` | Whether to run as the openhands user |
-| `VOLUMES` | string | `""` | Volume mounts in format `host:container[:mode]` |
-
-## LLM Configuration Variables
-
-These variables correspond to the `[llm]` section in `config.toml`:
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `LLM_MODEL` | string | `"claude-3-5-sonnet-20241022"` | LLM model to use |
-| `LLM_API_KEY` | string | `""` | API key for the LLM provider |
-| `LLM_BASE_URL` | string | `""` | Custom API base URL |
-| `LLM_API_VERSION` | string | `""` | API version to use |
-| `LLM_TEMPERATURE` | float | `0.0` | Sampling temperature |
-| `LLM_TOP_P` | float | `1.0` | Top-p sampling parameter |
-| `LLM_MAX_INPUT_TOKENS` | integer | `0` | Maximum input tokens (0 = no limit) |
-| `LLM_MAX_OUTPUT_TOKENS` | integer | `0` | Maximum output tokens (0 = no limit) |
-| `LLM_MAX_MESSAGE_CHARS` | integer | `30000` | Maximum characters that will be sent to the model in observation content |
-| `LLM_TIMEOUT` | integer | `0` | API timeout in seconds (0 = no timeout) |
-| `LLM_NUM_RETRIES` | integer | `8` | Number of retry attempts |
-| `LLM_RETRY_MIN_WAIT` | integer | `15` | Minimum wait time between retries (seconds) |
-| `LLM_RETRY_MAX_WAIT` | integer | `120` | Maximum wait time between retries (seconds) |
-| `LLM_RETRY_MULTIPLIER` | float | `2.0` | Exponential backoff multiplier |
-| `LLM_DROP_PARAMS` | boolean | `false` | Drop unsupported parameters without error |
-| `LLM_CACHING_PROMPT` | boolean | `true` | Enable prompt caching if supported |
-| `LLM_DISABLE_VISION` | boolean | `false` | Disable vision capabilities for cost reduction |
-| `LLM_CUSTOM_LLM_PROVIDER` | string | `""` | Custom LLM provider name |
-| `LLM_OLLAMA_BASE_URL` | string | `""` | Base URL for Ollama API |
-| `LLM_INPUT_COST_PER_TOKEN` | float | `0.0` | Cost per input token |
-| `LLM_OUTPUT_COST_PER_TOKEN` | float | `0.0` | Cost per output token |
-| `LLM_REASONING_EFFORT` | string | `""` | Reasoning effort for o-series models (`low`, `medium`, `high`) |
-
-### AWS Configuration
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `LLM_AWS_ACCESS_KEY_ID` | string | `""` | AWS access key ID |
-| `LLM_AWS_SECRET_ACCESS_KEY` | string | `""` | AWS secret access key |
-| `LLM_AWS_REGION_NAME` | string | `""` | AWS region name |
-
-## Agent Configuration Variables
-
-These variables correspond to the `[agent]` section in `config.toml`:
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `AGENT_LLM_CONFIG` | string | `""` | Name of LLM config group to use |
-| `AGENT_FUNCTION_CALLING` | boolean | `true` | Enable function calling |
-| `AGENT_ENABLE_BROWSING` | boolean | `false` | Enable browsing delegate |
-| `AGENT_ENABLE_LLM_EDITOR` | boolean | `false` | Enable LLM-based editor |
-| `AGENT_ENABLE_JUPYTER` | boolean | `false` | Enable Jupyter integration |
-| `AGENT_ENABLE_HISTORY_TRUNCATION` | boolean | `true` | Enable history truncation |
-| `AGENT_ENABLE_PROMPT_EXTENSIONS` | boolean | `true` | Enable microagents (prompt extensions) |
-| `AGENT_DISABLED_MICROAGENTS` | list | `[]` | List of microagents to disable |
-
-## Sandbox Configuration Variables
-
-These variables correspond to the `[sandbox]` section in `config.toml`:
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `SANDBOX_TIMEOUT` | integer | `120` | Sandbox timeout in seconds |
-| `SANDBOX_USER_ID` | integer | `1000` | User ID for sandbox processes |
-| `SANDBOX_BASE_CONTAINER_IMAGE` | string | `"nikolaik/python-nodejs:python3.12-nodejs22"` | Base container image |
-| `SANDBOX_USE_HOST_NETWORK` | boolean | `false` | Use host networking |
-| `SANDBOX_RUNTIME_BINDING_ADDRESS` | string | `"0.0.0.0"` | Runtime binding address |
-| `SANDBOX_ENABLE_AUTO_LINT` | boolean | `false` | Enable automatic linting |
-| `SANDBOX_INITIALIZE_PLUGINS` | boolean | `true` | Initialize sandbox plugins |
-| `SANDBOX_RUNTIME_EXTRA_DEPS` | string | `""` | Extra dependencies to install |
-| `SANDBOX_RUNTIME_STARTUP_ENV_VARS` | dict | `{}` | Environment variables for runtime |
-| `SANDBOX_BROWSERGYM_EVAL_ENV` | string | `""` | BrowserGym evaluation environment |
-| `SANDBOX_VOLUMES` | string | `""` | Volume mounts (replaces deprecated workspace settings) |
-| `SANDBOX_RUNTIME_CONTAINER_IMAGE` | string | `""` | Pre-built runtime container image |
-| `SANDBOX_KEEP_RUNTIME_ALIVE` | boolean | `false` | Keep runtime alive after session ends |
-| `SANDBOX_PAUSE_CLOSED_RUNTIMES` | boolean | `false` | Pause instead of stopping closed runtimes |
-| `SANDBOX_CLOSE_DELAY` | integer | `300` | Delay before closing idle runtimes (seconds) |
-| `SANDBOX_RM_ALL_CONTAINERS` | boolean | `false` | Remove all containers when stopping |
-| `SANDBOX_ENABLE_GPU` | boolean | `false` | Enable GPU support |
-| `SANDBOX_CUDA_VISIBLE_DEVICES` | string | `""` | Specify GPU devices by ID |
-| `SANDBOX_VSCODE_PORT` | integer | auto | Specific port for VSCode server |
-
-### Sandbox Environment Variables
-Variables prefixed with `SANDBOX_ENV_` are passed through to the sandbox environment:
-
-| Environment Variable | Description |
-|---------------------|-------------|
-| `SANDBOX_ENV_*` | Any variable with this prefix is passed to the sandbox (e.g., `SANDBOX_ENV_OPENAI_API_KEY`) |
-
-## Security Configuration Variables
-
-These variables correspond to the `[security]` section in `config.toml`:
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `SECURITY_CONFIRMATION_MODE` | boolean | `false` | Enable confirmation mode for actions |
-| `SECURITY_SECURITY_ANALYZER` | string | `"llm"` | Security analyzer to use (`llm`, `invariant`) |
-| `SECURITY_ENABLE_SECURITY_ANALYZER` | boolean | `true` | Enable security analysis |
-
-## Debug and Logging Variables
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `DEBUG` | boolean | `false` | Enable general debug logging |
-| `DEBUG_LLM` | boolean | `false` | Enable LLM-specific debug logging |
-| `DEBUG_RUNTIME` | boolean | `false` | Enable runtime debug logging |
-| `LOG_TO_FILE` | boolean | auto | Log to file (auto-enabled when DEBUG=true) |
-
-## Runtime-Specific Variables
-
-### Docker Runtime
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `SANDBOX_VOLUME_OVERLAYS` | string | `""` | Volume overlay configurations |
-
-### Remote Runtime
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `SANDBOX_API_KEY` | string | `""` | API key for remote runtime |
-| `SANDBOX_REMOTE_RUNTIME_API_URL` | string | `""` | Remote runtime API URL |
-
-### Local Runtime
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `RUNTIME_URL` | string | `""` | Runtime URL for local runtime |
-| `RUNTIME_URL_PATTERN` | string | `""` | Runtime URL pattern |
-| `RUNTIME_ID` | string | `""` | Runtime identifier |
-| `LOCAL_RUNTIME_MODE` | string | `""` | Enable local runtime mode (`1` to enable) |
-
-## Integration Variables
-
-### GitHub Integration
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `GITHUB_TOKEN` | string | `""` | GitHub personal access token |
-
-### Third-Party API Keys
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `OPENAI_API_KEY` | string | `""` | OpenAI API key |
-| `ANTHROPIC_API_KEY` | string | `""` | Anthropic API key |
-| `GOOGLE_API_KEY` | string | `""` | Google API key |
-| `AZURE_API_KEY` | string | `""` | Azure API key |
-| `TAVILY_API_KEY` | string | `""` | Tavily search API key |
-
-## Server Configuration Variables
-
-These are primarily used when running OpenHands as a server:
-
-| Environment Variable | Type | Default | Description |
-|---------------------|------|---------|-------------|
-| `FRONTEND_PORT` | integer | `3000` | Frontend server port |
-| `BACKEND_PORT` | integer | `8000` | Backend server port |
-| `FRONTEND_HOST` | string | `"localhost"` | Frontend host address |
-| `BACKEND_HOST` | string | `"localhost"` | Backend host address |
-| `WEB_HOST` | string | `"localhost"` | Web server host |
-| `SERVE_FRONTEND` | boolean | `true` | Whether to serve frontend |
-
-## Deprecated Variables
-
-These variables are deprecated and should be replaced:
-
-| Environment Variable | Replacement | Description |
-|---------------------|-------------|-------------|
-| `WORKSPACE_BASE` | `SANDBOX_VOLUMES` | Use volume mounting instead |
-| `WORKSPACE_MOUNT_PATH` | `SANDBOX_VOLUMES` | Use volume mounting instead |
-| `WORKSPACE_MOUNT_PATH_IN_SANDBOX` | `SANDBOX_VOLUMES` | Use volume mounting instead |
-| `WORKSPACE_MOUNT_REWRITE` | `SANDBOX_VOLUMES` | Use volume mounting instead |
-
-## Usage Examples
-
-### Basic Setup with OpenAI
-```bash
-export LLM_MODEL="gpt-4o"
-export LLM_API_KEY="your-openai-api-key"
-export DEBUG=true
-```
-
-### Docker Deployment with Custom Volumes
-```bash
-export RUNTIME="docker"
-export SANDBOX_VOLUMES="/host/workspace:/workspace:rw,/host/data:/data:ro"
-export SANDBOX_TIMEOUT=300
-```
-
-### Remote Runtime Configuration
-```bash
-export RUNTIME="remote"
-export SANDBOX_API_KEY="your-remote-api-key"
-export SANDBOX_REMOTE_RUNTIME_API_URL="https://your-runtime-api.com"
-```
-
-### Security-Enhanced Setup
-```bash
-export SECURITY_CONFIRMATION_MODE=true
-export SECURITY_SECURITY_ANALYZER="llm"
-export DEBUG_RUNTIME=true
-```
-
-## Notes
-
-1. **Boolean Values**: Environment variables expecting boolean values accept `true`/`false`, `1`/`0`, or `yes`/`no` (case-insensitive).
-
-2. **List Values**: Lists should be provided as Python literal strings, e.g., `AGENT_DISABLED_MICROAGENTS='["microagent1", "microagent2"]'`.
-
-3. **Dictionary Values**: Dictionaries should be provided as Python literal strings, e.g., `SANDBOX_RUNTIME_STARTUP_ENV_VARS='{"KEY": "value"}'`.
-
-4. **Precedence**: Environment variables take precedence over TOML configuration files.
-
-5. **Docker Usage**: When using Docker, pass environment variables with the `-e` flag:
-   ```bash
-   docker run -e LLM_API_KEY="your-key" -e DEBUG=true openhands/openhands
-   ```
-
-6. **Validation**: Invalid environment variable values will be logged as errors and fall back to defaults.

enterprise/experiments/experiment_manager.py

@@ -5,8 +5,12 @@ from experiments.constants import (
     EXPERIMENT_SYSTEM_PROMPT_EXPERIMENT,
 )
 from experiments.experiment_versions import (
+    handle_condenser_max_step_experiment,
     handle_system_prompt_experiment,
 )
+from experiments.experiment_versions._004_condenser_max_step_experiment import (
+    handle_condenser_max_step_experiment__v1,
+)
 
 from openhands.core.config.openhands_config import OpenHandsConfig
 from openhands.core.logger import openhands_logger as logger
@@ -27,6 +31,10 @@ class SaaSExperimentManager(ExperimentManager):
             )
             return agent
 
+        agent = handle_condenser_max_step_experiment__v1(
+            user_id, conversation_id, agent
+        )
+
         if EXPERIMENT_SYSTEM_PROMPT_EXPERIMENT:
             agent = agent.model_copy(
                 update={'system_prompt_filename': 'system_prompt_long_horizon.j2'}
@@ -52,7 +60,20 @@ class SaaSExperimentManager(ExperimentManager):
         """
         logger.debug(
             'experiment_manager:run_conversation_variant_test:started',
-            extra={'user_id': user_id, 'conversation_id': conversation_id},
+            extra={'user_id': user_id},
+        )
+
+        # Skip all experiment processing if the experiment manager is disabled
+        if not ENABLE_EXPERIMENT_MANAGER:
+            logger.info(
+                'experiment_manager:run_conversation_variant_test:skipped',
+                extra={'reason': 'experiment_manager_disabled'},
+            )
+            return conversation_settings
+
+        # Apply conversation-scoped experiments
+        conversation_settings = handle_condenser_max_step_experiment(
+            user_id, conversation_id, conversation_settings
         )
 
         return conversation_settings

enterprise/migrations/versions/080_add_status_and_updated_at_to_callback.py

@@ -1,71 +0,0 @@
-"""add status and updated_at to callback
-
-Revision ID: 080
-Revises: 079
-Create Date: 2025-11-05 00:00:00.000000
-
-"""
-
-from enum import Enum
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = '080'
-down_revision: Union[str, None] = '079'
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-class EventCallbackStatus(Enum):
-    ACTIVE = 'ACTIVE'
-    DISABLED = 'DISABLED'
-    COMPLETED = 'COMPLETED'
-    ERROR = 'ERROR'
-
-
-def upgrade() -> None:
-    """Upgrade schema."""
-    status = sa.Enum(EventCallbackStatus, name='eventcallbackstatus')
-    status.create(op.get_bind(), checkfirst=True)
-    op.add_column(
-        'event_callback',
-        sa.Column('status', status, nullable=False, server_default='ACTIVE'),
-    )
-    op.add_column(
-        'event_callback',
-        sa.Column(
-            'updated_at', sa.DateTime, nullable=False, server_default=sa.func.now()
-        ),
-    )
-    op.drop_index('ix_event_callback_result_event_id')
-    op.drop_column('event_callback_result', 'event_id')
-    op.add_column(
-        'event_callback_result', sa.Column('event_id', sa.String, nullable=True)
-    )
-    op.create_index(
-        op.f('ix_event_callback_result_event_id'),
-        'event_callback_result',
-        ['event_id'],
-        unique=False,
-    )
-
-
-def downgrade() -> None:
-    """Downgrade schema."""
-    op.drop_column('event_callback', 'status')
-    op.drop_column('event_callback', 'updated_at')
-    op.drop_index('ix_event_callback_result_event_id')
-    op.drop_column('event_callback_result', 'event_id')
-    op.add_column(
-        'event_callback_result', sa.Column('event_id', sa.UUID, nullable=True)
-    )
-    op.create_index(
-        op.f('ix_event_callback_result_event_id'),
-        'event_callback_result',
-        ['event_id'],
-        unique=False,
-    )
-    op.execute('DROP TYPE eventcallbackstatus')

enterprise/migrations/versions/081_add_parent_conversation_id.py

@@ -1,41 +0,0 @@
-"""add parent_conversation_id to conversation_metadata
-
-Revision ID: 081
-Revises: 080
-Create Date: 2025-11-06 00:00:00.000000
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = '081'
-down_revision: Union[str, None] = '080'
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    """Upgrade schema."""
-    op.add_column(
-        'conversation_metadata',
-        sa.Column('parent_conversation_id', sa.String(), nullable=True),
-    )
-    op.create_index(
-        op.f('ix_conversation_metadata_parent_conversation_id'),
-        'conversation_metadata',
-        ['parent_conversation_id'],
-        unique=False,
-    )
-
-
-def downgrade() -> None:
-    """Downgrade schema."""
-    op.drop_index(
-        op.f('ix_conversation_metadata_parent_conversation_id'),
-        table_name='conversation_metadata',
-    )
-    op.drop_column('conversation_metadata', 'parent_conversation_id')

enterprise/poetry.lock

@@ -201,20 +201,19 @@ files = [
 
 [[package]]
 name = "anthropic"
-version = "0.72.0"
+version = "0.65.0"
 description = "The official Python library for the anthropic API"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "anthropic-0.72.0-py3-none-any.whl", hash = "sha256:0e9f5a7582f038cab8efbb4c959e49ef654a56bfc7ba2da51b5a7b8a84de2e4d"},
-    {file = "anthropic-0.72.0.tar.gz", hash = "sha256:8971fe76dcffc644f74ac3883069beb1527641115ae0d6eb8fa21c1ce4082f7a"},
+    {file = "anthropic-0.65.0-py3-none-any.whl", hash = "sha256:ba9d9f82678046c74ddf5698ca06d9f5b0f599cfac922ab0d5921638eb448d98"},
+    {file = "anthropic-0.65.0.tar.gz", hash = "sha256:6b6b6942574e54342050dfd42b8d856a8366b171daec147df3b80be4722733b9"},
 ]
 
 [package.dependencies]
 anyio = ">=3.5.0,<5"
 distro = ">=1.7.0,<2"
-docstring-parser = ">=0.15,<1"
 google-auth = {version = ">=2,<3", extras = ["requests"], optional = true, markers = "extra == \"vertex\""}
 httpx = ">=0.25.0,<1"
 jiter = ">=0.4.0,<1"
@@ -223,7 +222,7 @@ sniffio = "*"
 typing-extensions = ">=4.10,<5"
 
 [package.extras]
-aiohttp = ["aiohttp", "httpx-aiohttp (>=0.1.9)"]
+aiohttp = ["aiohttp", "httpx-aiohttp (>=0.1.8)"]
 bedrock = ["boto3 (>=1.28.57)", "botocore (>=1.31.57)"]
 vertex = ["google-auth[requests] (>=2,<3)"]
 
@@ -682,34 +681,31 @@ crt = ["awscrt (==0.27.6)"]
 
 [[package]]
 name = "browser-use"
-version = "0.9.5"
+version = "0.7.10"
 description = "Make websites accessible for AI agents"
 optional = false
 python-versions = "<4.0,>=3.11"
 groups = ["main"]
 files = [
-    {file = "browser_use-0.9.5-py3-none-any.whl", hash = "sha256:4a2e92847204d1ded269026a99cb0cc0e60e38bd2751fa3f58aedd78f00b4e67"},
-    {file = "browser_use-0.9.5.tar.gz", hash = "sha256:f8285fe253b149d01769a7084883b4cf4db351e2f38e26302c157bcbf14a703f"},
+    {file = "browser_use-0.7.10-py3-none-any.whl", hash = "sha256:669e12571a0c0c4c93e5fd26abf9e2534eb9bacbc510328aedcab795bd8906a9"},
+    {file = "browser_use-0.7.10.tar.gz", hash = "sha256:f93ce59e06906c12d120360dee4aa33d83618ddf7c9a575dd0ac517d2de7ccbc"},
 ]
 
 [package.dependencies]
 aiohttp = "3.12.15"
-anthropic = ">=0.68.1,<1.0.0"
+anthropic = ">=0.58.2,<1.0.0"
 anyio = ">=4.9.0"
 authlib = ">=1.6.0"
 bubus = ">=1.5.6"
 cdp-use = ">=1.4.0"
-click = ">=8.1.8"
-cloudpickle = ">=3.1.1"
 google-api-core = ">=2.25.0"
 google-api-python-client = ">=2.174.0"
 google-auth = ">=2.40.3"
 google-auth-oauthlib = ">=1.2.2"
 google-genai = ">=1.29.0,<2.0.0"
 groq = ">=0.30.0"
+html2text = ">=2025.4.15"
 httpx = ">=0.28.1"
-inquirerpy = ">=0.3.4"
-markdownify = ">=1.2.0"
 mcp = ">=1.10.1"
 ollama = ">=0.5.1"
 openai = ">=1.99.2,<2.0.0"
@@ -724,20 +720,16 @@ pypdf = ">=5.7.0"
 python-dotenv = ">=1.0.1"
 reportlab = ">=4.0.0"
 requests = ">=2.32.3"
-rich = ">=14.0.0"
 screeninfo = {version = ">=0.8.1", markers = "platform_system != \"darwin\""}
 typing-extensions = ">=4.12.2"
 uuid7 = ">=0.1.0"
 
 [package.extras]
-all = ["agentmail (==0.0.59)", "boto3 (>=1.38.45)", "botocore (>=1.37.23)", "imgcat (>=0.6.0)", "langchain-openai (>=0.3.26)", "oci (>=2.126.4)", "textual (>=3.2.0)"]
+all = ["agentmail (>=0.0.53)", "boto3 (>=1.38.45)", "botocore (>=1.37.23)", "click (>=8.1.8)", "imgcat (>=0.6.0)", "langchain-openai (>=0.3.26)", "rich (>=14.0.0)", "textual (>=3.2.0)"]
 aws = ["boto3 (>=1.38.45)"]
-cli = ["textual (>=3.2.0)"]
-cli-oci = ["oci (>=2.126.4)", "textual (>=3.2.0)"]
-code = ["matplotlib (>=3.9.0)", "numpy (>=2.3.2)", "pandas (>=2.2.0)", "tabulate (>=0.9.0)"]
-eval = ["anyio (>=4.9.0)", "datamodel-code-generator (>=0.26.0)", "lmnr[all] (==0.7.17)", "psutil (>=7.0.0)"]
-examples = ["agentmail (==0.0.59)", "botocore (>=1.37.23)", "imgcat (>=0.6.0)", "langchain-openai (>=0.3.26)"]
-oci = ["oci (>=2.126.4)"]
+cli = ["click (>=8.1.8)", "rich (>=14.0.0)", "textual (>=3.2.0)"]
+eval = ["anyio (>=4.9.0)", "browserbase (==1.4.0)", "datamodel-code-generator (>=0.26.0)", "hyperbrowser (==0.47.0)", "lmnr[all] (==0.7.10)", "psutil (>=7.0.0)"]
+examples = ["agentmail (>=0.0.53)", "botocore (>=1.37.23)", "imgcat (>=0.6.0)", "langchain-openai (>=0.3.26)"]
 video = ["imageio[ffmpeg] (>=2.37.0)", "numpy (>=2.3.2)"]
 
 [[package]]
@@ -3533,25 +3525,6 @@ files = [
     {file = "iniconfig-2.1.0.tar.gz", hash = "sha256:3abbd2e30b36733fee78f9c7f7308f2d0050e88f0087fd25c2645f63c773e1c7"},
 ]
 
-[[package]]
-name = "inquirerpy"
-version = "0.3.4"
-description = "Python port of Inquirer.js (A collection of common interactive command-line user interfaces)"
-optional = false
-python-versions = ">=3.7,<4.0"
-groups = ["main"]
-files = [
-    {file = "InquirerPy-0.3.4-py3-none-any.whl", hash = "sha256:c65fdfbac1fa00e3ee4fb10679f4d3ed7a012abf4833910e63c295827fe2a7d4"},
-    {file = "InquirerPy-0.3.4.tar.gz", hash = "sha256:89d2ada0111f337483cb41ae31073108b2ec1e618a49d7110b0d7ade89fc197e"},
-]
-
-[package.dependencies]
-pfzy = ">=0.3.1,<0.4.0"
-prompt-toolkit = ">=3.0.1,<4.0.0"
-
-[package.extras]
-docs = ["Sphinx (>=4.1.2,<5.0.0)", "furo (>=2021.8.17-beta.43,<2022.0.0)", "myst-parser (>=0.15.1,<0.16.0)", "sphinx-autobuild (>=2021.3.14,<2022.0.0)", "sphinx-copybutton (>=0.4.0,<0.5.0)"]
-
 [[package]]
 name = "installer"
 version = "0.7.0"
@@ -4607,62 +4580,6 @@ files = [
     {file = "llvmlite-0.44.0.tar.gz", hash = "sha256:07667d66a5d150abed9157ab6c0b9393c9356f229784a4385c02f99e94fc94d4"},
 ]
 
-[[package]]
-name = "lmnr"
-version = "0.7.20"
-description = "Python SDK for Laminar"
-optional = false
-python-versions = "<4,>=3.10"
-groups = ["main"]
-files = [
-    {file = "lmnr-0.7.20-py3-none-any.whl", hash = "sha256:5f9fa7444e6f96c25e097f66484ff29e632bdd1de0e9346948bf5595f4a8af38"},
-    {file = "lmnr-0.7.20.tar.gz", hash = "sha256:1f484cd618db2d71af65f90a0b8b36d20d80dc91a5138b811575c8677bf7c4fd"},
-]
-
-[package.dependencies]
-grpcio = ">=1"
-httpx = ">=0.24.0"
-opentelemetry-api = ">=1.33.0"
-opentelemetry-exporter-otlp-proto-grpc = ">=1.33.0"
-opentelemetry-exporter-otlp-proto-http = ">=1.33.0"
-opentelemetry-instrumentation = ">=0.54b0"
-opentelemetry-instrumentation-threading = ">=0.57b0"
-opentelemetry-sdk = ">=1.33.0"
-opentelemetry-semantic-conventions = ">=0.54b0"
-opentelemetry-semantic-conventions-ai = ">=0.4.13"
-orjson = ">=3.0.0"
-packaging = ">=22.0"
-pydantic = ">=2.0.3,<3.0.0"
-python-dotenv = ">=1.0"
-tenacity = ">=8.0"
-tqdm = ">=4.0"
-
-[package.extras]
-alephalpha = ["opentelemetry-instrumentation-alephalpha (>=0.47.1)"]
-all = ["opentelemetry-instrumentation-alephalpha (>=0.47.1)", "opentelemetry-instrumentation-bedrock (>=0.47.1)", "opentelemetry-instrumentation-chromadb (>=0.47.1)", "opentelemetry-instrumentation-cohere (>=0.47.1)", "opentelemetry-instrumentation-crewai (>=0.47.1)", "opentelemetry-instrumentation-haystack (>=0.47.1)", "opentelemetry-instrumentation-lancedb (>=0.47.1)", "opentelemetry-instrumentation-langchain (>=0.47.1)", "opentelemetry-instrumentation-llamaindex (>=0.47.1)", "opentelemetry-instrumentation-marqo (>=0.47.1)", "opentelemetry-instrumentation-mcp (>=0.47.1)", "opentelemetry-instrumentation-milvus (>=0.47.1)", "opentelemetry-instrumentation-mistralai (>=0.47.1)", "opentelemetry-instrumentation-ollama (>=0.47.1)", "opentelemetry-instrumentation-pinecone (>=0.47.1)", "opentelemetry-instrumentation-qdrant (>=0.47.1)", "opentelemetry-instrumentation-replicate (>=0.47.1)", "opentelemetry-instrumentation-sagemaker (>=0.47.1)", "opentelemetry-instrumentation-together (>=0.47.1)", "opentelemetry-instrumentation-transformers (>=0.47.1)", "opentelemetry-instrumentation-vertexai (>=0.47.1)", "opentelemetry-instrumentation-watsonx (>=0.47.1)", "opentelemetry-instrumentation-weaviate (>=0.47.1)"]
-bedrock = ["opentelemetry-instrumentation-bedrock (>=0.47.1)"]
-chromadb = ["opentelemetry-instrumentation-chromadb (>=0.47.1)"]
-cohere = ["opentelemetry-instrumentation-cohere (>=0.47.1)"]
-crewai = ["opentelemetry-instrumentation-crewai (>=0.47.1)"]
-haystack = ["opentelemetry-instrumentation-haystack (>=0.47.1)"]
-lancedb = ["opentelemetry-instrumentation-lancedb (>=0.47.1)"]
-langchain = ["opentelemetry-instrumentation-langchain (>=0.47.1)"]
-llamaindex = ["opentelemetry-instrumentation-llamaindex (>=0.47.1)"]
-marqo = ["opentelemetry-instrumentation-marqo (>=0.47.1)"]
-mcp = ["opentelemetry-instrumentation-mcp (>=0.47.1)"]
-milvus = ["opentelemetry-instrumentation-milvus (>=0.47.1)"]
-mistralai = ["opentelemetry-instrumentation-mistralai (>=0.47.1)"]
-ollama = ["opentelemetry-instrumentation-ollama (>=0.47.1)"]
-pinecone = ["opentelemetry-instrumentation-pinecone (>=0.47.1)"]
-qdrant = ["opentelemetry-instrumentation-qdrant (>=0.47.1)"]
-replicate = ["opentelemetry-instrumentation-replicate (>=0.47.1)"]
-sagemaker = ["opentelemetry-instrumentation-sagemaker (>=0.47.1)"]
-together = ["opentelemetry-instrumentation-together (>=0.47.1)"]
-transformers = ["opentelemetry-instrumentation-transformers (>=0.47.1)"]
-vertexai = ["opentelemetry-instrumentation-vertexai (>=0.47.1)"]
-watsonx = ["opentelemetry-instrumentation-watsonx (>=0.47.1)"]
-weaviate = ["opentelemetry-instrumentation-weaviate (>=0.47.1)"]
-
 [[package]]
 name = "lxml"
 version = "6.0.1"
@@ -5820,15 +5737,13 @@ llama = ["llama-index (>=0.12.29,<0.13.0)", "llama-index-core (>=0.12.29,<0.13.0
 
 [[package]]
 name = "openhands-agent-server"
-version = "1.1.0"
+version = "1.0.0a4"
 description = "OpenHands Agent Server - REST/WebSocket interface for OpenHands AI Agent"
 optional = false
 python-versions = ">=3.12"
 groups = ["main"]
-files = [
-    {file = "openhands_agent_server-1.1.0-py3-none-any.whl", hash = "sha256:59a856883df23488c0723e47655ef21649a321fcd4709a25a4690866eff6ac88"},
-    {file = "openhands_agent_server-1.1.0.tar.gz", hash = "sha256:e39bebd39afd45cfcfd765005e7c4e5409e46678bd7612ae20bae79f7057b935"},
-]
+files = []
+develop = false
 
 [package.dependencies]
 aiosqlite = ">=0.19"
@@ -5841,9 +5756,16 @@ uvicorn = ">=0.31.1"
 websockets = ">=12"
 wsproto = ">=1.2.0"
 
+[package.source]
+type = "git"
+url = "https://github.com/OpenHands/agent-sdk.git"
+reference = "3d8af53b2f0259dc98555a4acd4238f90e0afbce"
+resolved_reference = "3d8af53b2f0259dc98555a4acd4238f90e0afbce"
+subdirectory = "openhands-agent-server"
+
 [[package]]
 name = "openhands-ai"
-version = "0.0.0-post.5525+0b6631523"
+version = "0.0.0-post.5456+15c207c40"
 description = "OpenHands: Code Less, Make More"
 optional = false
 python-versions = "^3.12,<3.14"
@@ -5879,14 +5801,13 @@ jupyter_kernel_gateway = "*"
 kubernetes = "^33.1.0"
 libtmux = ">=0.46.2"
 litellm = ">=1.74.3, <1.78.0, !=1.64.4, !=1.67.*"
-lmnr = "^0.7.20"
 memory-profiler = "^0.61.0"
 numpy = "*"
 openai = "1.99.9"
 openhands-aci = "0.3.2"
-openhands-agent-server = "1.1.0"
-openhands-sdk = "1.1.0"
-openhands-tools = "1.1.0"
+openhands-agent-server = {git = "https://github.com/OpenHands/agent-sdk.git", rev = "3d8af53b2f0259dc98555a4acd4238f90e0afbce", subdirectory = "openhands-agent-server"}
+openhands-sdk = {git = "https://github.com/OpenHands/agent-sdk.git", rev = "3d8af53b2f0259dc98555a4acd4238f90e0afbce", subdirectory = "openhands-sdk"}
+openhands-tools = {git = "https://github.com/OpenHands/agent-sdk.git", rev = "3d8af53b2f0259dc98555a4acd4238f90e0afbce", subdirectory = "openhands-tools"}
 opentelemetry-api = "^1.33.1"
 opentelemetry-exporter-otlp-proto-grpc = "^1.33.1"
 pathspec = "^0.12.1"
@@ -5942,21 +5863,18 @@ url = ".."
 
 [[package]]
 name = "openhands-sdk"
-version = "1.1.0"
+version = "1.0.0a4"
 description = "OpenHands SDK - Core functionality for building AI agents"
 optional = false
 python-versions = ">=3.12"
 groups = ["main"]
-files = [
-    {file = "openhands_sdk-1.1.0-py3-none-any.whl", hash = "sha256:4a984ce1687a48cf99a67fdf3d37b116f8b2840743d4807810b5024af6a1d57e"},
-    {file = "openhands_sdk-1.1.0.tar.gz", hash = "sha256:855e0d8f3657205e4119e50520c17e65b3358b1a923f7a051a82512a54bf426c"},
-]
+files = []
+develop = false
 
 [package.dependencies]
 fastmcp = ">=2.11.3"
 httpx = ">=0.27.0"
 litellm = ">=1.77.7.dev9"
-lmnr = ">=0.7.20"
 pydantic = ">=2.11.7"
 python-frontmatter = ">=1.1.0"
 python-json-logger = ">=3.3.0"
@@ -5966,28 +5884,40 @@ websockets = ">=12"
 [package.extras]
 boto3 = ["boto3 (>=1.35.0)"]
 
+[package.source]
+type = "git"
+url = "https://github.com/OpenHands/agent-sdk.git"
+reference = "3d8af53b2f0259dc98555a4acd4238f90e0afbce"
+resolved_reference = "3d8af53b2f0259dc98555a4acd4238f90e0afbce"
+subdirectory = "openhands-sdk"
+
 [[package]]
 name = "openhands-tools"
-version = "1.1.0"
+version = "1.0.0a4"
 description = "OpenHands Tools - Runtime tools for AI agents"
 optional = false
 python-versions = ">=3.12"
 groups = ["main"]
-files = [
-    {file = "openhands_tools-1.1.0-py3-none-any.whl", hash = "sha256:767d6746f05edade49263aa24450a037485a3dc23379f56917ef19aad22033f9"},
-    {file = "openhands_tools-1.1.0.tar.gz", hash = "sha256:c2fadaa4f4e16e9a3df5781ea847565dcae7171584f09ef7c0e1d97c8dfc83f6"},
-]
+files = []
+develop = false
 
 [package.dependencies]
 bashlex = ">=0.18"
 binaryornot = ">=0.4.4"
-browser-use = ">=0.8.0"
+browser-use = ">=0.7.7"
 cachetools = "*"
 func-timeout = ">=4.3.5"
 libtmux = ">=0.46.2"
 openhands-sdk = "*"
 pydantic = ">=2.11.7"
 
+[package.source]
+type = "git"
+url = "https://github.com/OpenHands/agent-sdk.git"
+reference = "3d8af53b2f0259dc98555a4acd4238f90e0afbce"
+resolved_reference = "3d8af53b2f0259dc98555a4acd4238f90e0afbce"
+subdirectory = "openhands-tools"
+
 [[package]]
 name = "openpyxl"
 version = "3.1.5"
@@ -6058,62 +5988,6 @@ opentelemetry-proto = "1.36.0"
 opentelemetry-sdk = ">=1.36.0,<1.37.0"
 typing-extensions = ">=4.6.0"
 
-[[package]]
-name = "opentelemetry-exporter-otlp-proto-http"
-version = "1.36.0"
-description = "OpenTelemetry Collector Protobuf over HTTP Exporter"
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "opentelemetry_exporter_otlp_proto_http-1.36.0-py3-none-any.whl", hash = "sha256:3d769f68e2267e7abe4527f70deb6f598f40be3ea34c6adc35789bea94a32902"},
-    {file = "opentelemetry_exporter_otlp_proto_http-1.36.0.tar.gz", hash = "sha256:dd3637f72f774b9fc9608ab1ac479f8b44d09b6fb5b2f3df68a24ad1da7d356e"},
-]
-
-[package.dependencies]
-googleapis-common-protos = ">=1.52,<2.0"
-opentelemetry-api = ">=1.15,<2.0"
-opentelemetry-exporter-otlp-proto-common = "1.36.0"
-opentelemetry-proto = "1.36.0"
-opentelemetry-sdk = ">=1.36.0,<1.37.0"
-requests = ">=2.7,<3.0"
-typing-extensions = ">=4.5.0"
-
-[[package]]
-name = "opentelemetry-instrumentation"
-version = "0.57b0"
-description = "Instrumentation Tools & Auto Instrumentation for OpenTelemetry Python"
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "opentelemetry_instrumentation-0.57b0-py3-none-any.whl", hash = "sha256:9109280f44882e07cec2850db28210b90600ae9110b42824d196de357cbddf7e"},
-    {file = "opentelemetry_instrumentation-0.57b0.tar.gz", hash = "sha256:f2a30135ba77cdea2b0e1df272f4163c154e978f57214795d72f40befd4fcf05"},
-]
-
-[package.dependencies]
-opentelemetry-api = ">=1.4,<2.0"
-opentelemetry-semantic-conventions = "0.57b0"
-packaging = ">=18.0"
-wrapt = ">=1.0.0,<2.0.0"
-
-[[package]]
-name = "opentelemetry-instrumentation-threading"
-version = "0.57b0"
-description = "Thread context propagation support for OpenTelemetry"
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "opentelemetry_instrumentation_threading-0.57b0-py3-none-any.whl", hash = "sha256:adfd64857c8c78d6111cf80552311e1713bad64272dd81abdd61f07b892a161b"},
-    {file = "opentelemetry_instrumentation_threading-0.57b0.tar.gz", hash = "sha256:06fa4c98d6bfe4670e7532497670ac202db42afa647ff770aedce0e422421c6e"},
-]
-
-[package.dependencies]
-opentelemetry-api = ">=1.12,<2.0"
-opentelemetry-instrumentation = "0.57b0"
-wrapt = ">=1.0.0,<2.0.0"
-
 [[package]]
 name = "opentelemetry-proto"
 version = "1.36.0"
@@ -6162,115 +6036,6 @@ files = [
 opentelemetry-api = "1.36.0"
 typing-extensions = ">=4.5.0"
 
-[[package]]
-name = "opentelemetry-semantic-conventions-ai"
-version = "0.4.13"
-description = "OpenTelemetry Semantic Conventions Extension for Large Language Models"
-optional = false
-python-versions = "<4,>=3.9"
-groups = ["main"]
-files = [
-    {file = "opentelemetry_semantic_conventions_ai-0.4.13-py3-none-any.whl", hash = "sha256:883a30a6bb5deaec0d646912b5f9f6dcbb9f6f72557b73d0f2560bf25d13e2d5"},
-    {file = "opentelemetry_semantic_conventions_ai-0.4.13.tar.gz", hash = "sha256:94efa9fb4ffac18c45f54a3a338ffeb7eedb7e1bb4d147786e77202e159f0036"},
-]
-
-[[package]]
-name = "orjson"
-version = "3.11.4"
-description = "Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy"
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "orjson-3.11.4-cp310-cp310-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:e3aa2118a3ece0d25489cbe48498de8a5d580e42e8d9979f65bf47900a15aba1"},
-    {file = "orjson-3.11.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a69ab657a4e6733133a3dca82768f2f8b884043714e8d2b9ba9f52b6efef5c44"},
-    {file = "orjson-3.11.4-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3740bffd9816fc0326ddc406098a3a8f387e42223f5f455f2a02a9f834ead80c"},
-    {file = "orjson-3.11.4-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:65fd2f5730b1bf7f350c6dc896173d3460d235c4be007af73986d7cd9a2acd23"},
-    {file = "orjson-3.11.4-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9fdc3ae730541086158d549c97852e2eea6820665d4faf0f41bf99df41bc11ea"},
-    {file = "orjson-3.11.4-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e10b4d65901da88845516ce9f7f9736f9638d19a1d483b3883dc0182e6e5edba"},
-    {file = "orjson-3.11.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fb6a03a678085f64b97f9d4a9ae69376ce91a3a9e9b56a82b1580d8e1d501aff"},
-    {file = "orjson-3.11.4-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:2c82e4f0b1c712477317434761fbc28b044c838b6b1240d895607441412371ac"},
-    {file = "orjson-3.11.4-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:d58c166a18f44cc9e2bad03a327dc2d1a3d2e85b847133cfbafd6bfc6719bd79"},
-    {file = "orjson-3.11.4-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:94f206766bf1ea30e1382e4890f763bd1eefddc580e08fec1ccdc20ddd95c827"},
-    {file = "orjson-3.11.4-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:41bf25fb39a34cf8edb4398818523277ee7096689db352036a9e8437f2f3ee6b"},
-    {file = "orjson-3.11.4-cp310-cp310-win32.whl", hash = "sha256:fa9627eba4e82f99ca6d29bc967f09aba446ee2b5a1ea728949ede73d313f5d3"},
-    {file = "orjson-3.11.4-cp310-cp310-win_amd64.whl", hash = "sha256:23ef7abc7fca96632d8174ac115e668c1e931b8fe4dde586e92a500bf1914dcc"},
-    {file = "orjson-3.11.4-cp311-cp311-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:5e59d23cd93ada23ec59a96f215139753fbfe3a4d989549bcb390f8c00370b39"},
-    {file = "orjson-3.11.4-cp311-cp311-macosx_15_0_arm64.whl", hash = "sha256:5c3aedecfc1beb988c27c79d52ebefab93b6c3921dbec361167e6559aba2d36d"},
-    {file = "orjson-3.11.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:da9e5301f1c2caa2a9a4a303480d79c9ad73560b2e7761de742ab39fe59d9175"},
-    {file = "orjson-3.11.4-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8873812c164a90a79f65368f8f96817e59e35d0cc02786a5356f0e2abed78040"},
-    {file = "orjson-3.11.4-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5d7feb0741ebb15204e748f26c9638e6665a5fa93c37a2c73d64f1669b0ddc63"},
-    {file = "orjson-3.11.4-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:01ee5487fefee21e6910da4c2ee9eef005bee568a0879834df86f888d2ffbdd9"},
-    {file = "orjson-3.11.4-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3d40d46f348c0321df01507f92b95a377240c4ec31985225a6668f10e2676f9a"},
-    {file = "orjson-3.11.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95713e5fc8af84d8edc75b785d2386f653b63d62b16d681687746734b4dfc0be"},
-    {file = "orjson-3.11.4-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:ad73ede24f9083614d6c4ca9a85fe70e33be7bf047ec586ee2363bc7418fe4d7"},
-    {file = "orjson-3.11.4-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:842289889de515421f3f224ef9c1f1efb199a32d76d8d2ca2706fa8afe749549"},
-    {file = "orjson-3.11.4-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:3b2427ed5791619851c52a1261b45c233930977e7de8cf36de05636c708fa905"},
-    {file = "orjson-3.11.4-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:3c36e524af1d29982e9b190573677ea02781456b2e537d5840e4538a5ec41907"},
-    {file = "orjson-3.11.4-cp311-cp311-win32.whl", hash = "sha256:87255b88756eab4a68ec61837ca754e5d10fa8bc47dc57f75cedfeaec358d54c"},
-    {file = "orjson-3.11.4-cp311-cp311-win_amd64.whl", hash = "sha256:e2d5d5d798aba9a0e1fede8d853fa899ce2cb930ec0857365f700dffc2c7af6a"},
-    {file = "orjson-3.11.4-cp311-cp311-win_arm64.whl", hash = "sha256:6bb6bb41b14c95d4f2702bce9975fda4516f1db48e500102fc4d8119032ff045"},
-    {file = "orjson-3.11.4-cp312-cp312-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:d4371de39319d05d3f482f372720b841c841b52f5385bd99c61ed69d55d9ab50"},
-    {file = "orjson-3.11.4-cp312-cp312-macosx_15_0_arm64.whl", hash = "sha256:e41fd3b3cac850eaae78232f37325ed7d7436e11c471246b87b2cd294ec94853"},
-    {file = "orjson-3.11.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:600e0e9ca042878c7fdf189cf1b028fe2c1418cc9195f6cb9824eb6ed99cb938"},
-    {file = "orjson-3.11.4-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7bbf9b333f1568ef5da42bc96e18bf30fd7f8d54e9ae066d711056add508e415"},
-    {file = "orjson-3.11.4-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4806363144bb6e7297b8e95870e78d30a649fdc4e23fc84daa80c8ebd366ce44"},
-    {file = "orjson-3.11.4-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ad355e8308493f527d41154e9053b86a5be892b3b359a5c6d5d95cda23601cb2"},
-    {file = "orjson-3.11.4-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c8a7517482667fb9f0ff1b2f16fe5829296ed7a655d04d68cd9711a4d8a4e708"},
-    {file = "orjson-3.11.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:97eb5942c7395a171cbfecc4ef6701fc3c403e762194683772df4c54cfbb2210"},
-    {file = "orjson-3.11.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:149d95d5e018bdd822e3f38c103b1a7c91f88d38a88aada5c4e9b3a73a244241"},
-    {file = "orjson-3.11.4-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:624f3951181eb46fc47dea3d221554e98784c823e7069edb5dbd0dc826ac909b"},
-    {file = "orjson-3.11.4-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:03bfa548cf35e3f8b3a96c4e8e41f753c686ff3d8e182ce275b1751deddab58c"},
-    {file = "orjson-3.11.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:525021896afef44a68148f6ed8a8bf8375553d6066c7f48537657f64823565b9"},
-    {file = "orjson-3.11.4-cp312-cp312-win32.whl", hash = "sha256:b58430396687ce0f7d9eeb3dd47761ca7d8fda8e9eb92b3077a7a353a75efefa"},
-    {file = "orjson-3.11.4-cp312-cp312-win_amd64.whl", hash = "sha256:c6dbf422894e1e3c80a177133c0dda260f81428f9de16d61041949f6a2e5c140"},
-    {file = "orjson-3.11.4-cp312-cp312-win_arm64.whl", hash = "sha256:d38d2bc06d6415852224fcc9c0bfa834c25431e466dc319f0edd56cca81aa96e"},
-    {file = "orjson-3.11.4-cp313-cp313-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:2d6737d0e616a6e053c8b4acc9eccea6b6cce078533666f32d140e4f85002534"},
-    {file = "orjson-3.11.4-cp313-cp313-macosx_15_0_arm64.whl", hash = "sha256:afb14052690aa328cc118a8e09f07c651d301a72e44920b887c519b313d892ff"},
-    {file = "orjson-3.11.4-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:38aa9e65c591febb1b0aed8da4d469eba239d434c218562df179885c94e1a3ad"},
-    {file = "orjson-3.11.4-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f2cf4dfaf9163b0728d061bebc1e08631875c51cd30bf47cb9e3293bfbd7dcd5"},
-    {file = "orjson-3.11.4-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:89216ff3dfdde0e4070932e126320a1752c9d9a758d6a32ec54b3b9334991a6a"},
-    {file = "orjson-3.11.4-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9daa26ca8e97fae0ce8aa5d80606ef8f7914e9b129b6b5df9104266f764ce436"},
-    {file = "orjson-3.11.4-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5c8b2769dc31883c44a9cd126560327767f848eb95f99c36c9932f51090bfce9"},
-    {file = "orjson-3.11.4-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1469d254b9884f984026bd9b0fa5bbab477a4bfe558bba6848086f6d43eb5e73"},
-    {file = "orjson-3.11.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:68e44722541983614e37117209a194e8c3ad07838ccb3127d96863c95ec7f1e0"},
-    {file = "orjson-3.11.4-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:8e7805fda9672c12be2f22ae124dcd7b03928d6c197544fe12174b86553f3196"},
-    {file = "orjson-3.11.4-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:04b69c14615fb4434ab867bf6f38b2d649f6f300af30a6705397e895f7aec67a"},
-    {file = "orjson-3.11.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:639c3735b8ae7f970066930e58cf0ed39a852d417c24acd4a25fc0b3da3c39a6"},
-    {file = "orjson-3.11.4-cp313-cp313-win32.whl", hash = "sha256:6c13879c0d2964335491463302a6ca5ad98105fc5db3565499dcb80b1b4bd839"},
-    {file = "orjson-3.11.4-cp313-cp313-win_amd64.whl", hash = "sha256:09bf242a4af98732db9f9a1ec57ca2604848e16f132e3f72edfd3c5c96de009a"},
-    {file = "orjson-3.11.4-cp313-cp313-win_arm64.whl", hash = "sha256:a85f0adf63319d6c1ba06fb0dbf997fced64a01179cf17939a6caca662bf92de"},
-    {file = "orjson-3.11.4-cp314-cp314-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:42d43a1f552be1a112af0b21c10a5f553983c2a0938d2bbb8ecd8bc9fb572803"},
-    {file = "orjson-3.11.4-cp314-cp314-macosx_15_0_arm64.whl", hash = "sha256:26a20f3fbc6c7ff2cb8e89c4c5897762c9d88cf37330c6a117312365d6781d54"},
-    {file = "orjson-3.11.4-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6e3f20be9048941c7ffa8fc523ccbd17f82e24df1549d1d1fe9317712d19938e"},
-    {file = "orjson-3.11.4-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:aac364c758dc87a52e68e349924d7e4ded348dedff553889e4d9f22f74785316"},
-    {file = "orjson-3.11.4-cp314-cp314-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d5c54a6d76e3d741dcc3f2707f8eeb9ba2a791d3adbf18f900219b62942803b1"},
-    {file = "orjson-3.11.4-cp314-cp314-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f28485bdca8617b79d44627f5fb04336897041dfd9fa66d383a49d09d86798bc"},
-    {file = "orjson-3.11.4-cp314-cp314-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bfc2a484cad3585e4ba61985a6062a4c2ed5c7925db6d39f1fa267c9d166487f"},
-    {file = "orjson-3.11.4-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e34dbd508cb91c54f9c9788923daca129fe5b55c5b4eebe713bf5ed3791280cf"},
-    {file = "orjson-3.11.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:b13c478fa413d4b4ee606ec8e11c3b2e52683a640b006bb586b3041c2ca5f606"},
-    {file = "orjson-3.11.4-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:724ca721ecc8a831b319dcd72cfa370cc380db0bf94537f08f7edd0a7d4e1780"},
-    {file = "orjson-3.11.4-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:977c393f2e44845ce1b540e19a786e9643221b3323dae190668a98672d43fb23"},
-    {file = "orjson-3.11.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:1e539e382cf46edec157ad66b0b0872a90d829a6b71f17cb633d6c160a223155"},
-    {file = "orjson-3.11.4-cp314-cp314-win32.whl", hash = "sha256:d63076d625babab9db5e7836118bdfa086e60f37d8a174194ae720161eb12394"},
-    {file = "orjson-3.11.4-cp314-cp314-win_amd64.whl", hash = "sha256:0a54d6635fa3aaa438ae32e8570b9f0de36f3f6562c308d2a2a452e8b0592db1"},
-    {file = "orjson-3.11.4-cp314-cp314-win_arm64.whl", hash = "sha256:78b999999039db3cf58f6d230f524f04f75f129ba3d1ca2ed121f8657e575d3d"},
-    {file = "orjson-3.11.4-cp39-cp39-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:405261b0a8c62bcbd8e2931c26fdc08714faf7025f45531541e2b29e544b545b"},
-    {file = "orjson-3.11.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:af02ff34059ee9199a3546f123a6ab4c86caf1708c79042caf0820dc290a6d4f"},
-    {file = "orjson-3.11.4-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:0b2eba969ea4203c177c7b38b36c69519e6067ee68c34dc37081fac74c796e10"},
-    {file = "orjson-3.11.4-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0baa0ea43cfa5b008a28d3c07705cf3ada40e5d347f0f44994a64b1b7b4b5350"},
-    {file = "orjson-3.11.4-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:80fd082f5dcc0e94657c144f1b2a3a6479c44ad50be216cf0c244e567f5eae19"},
-    {file = "orjson-3.11.4-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1e3704d35e47d5bee811fb1cbd8599f0b4009b14d451c4c57be5a7e25eb89a13"},
-    {file = "orjson-3.11.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:caa447f2b5356779d914658519c874cf3b7629e99e63391ed519c28c8aea4919"},
-    {file = "orjson-3.11.4-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:bba5118143373a86f91dadb8df41d9457498226698ebdf8e11cbb54d5b0e802d"},
-    {file = "orjson-3.11.4-cp39-cp39-musllinux_1_2_armv7l.whl", hash = "sha256:622463ab81d19ef3e06868b576551587de8e4d518892d1afab71e0fbc1f9cffc"},
-    {file = "orjson-3.11.4-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:3e0a700c4b82144b72946b6629968df9762552ee1344bfdb767fecdd634fbd5a"},
-    {file = "orjson-3.11.4-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:6e18a5c15e764e5f3fc569b47872450b4bcea24f2a6354c0a0e95ad21045d5a9"},
-    {file = "orjson-3.11.4-cp39-cp39-win32.whl", hash = "sha256:fb1c37c71cad991ef4d89c7a634b5ffb4447dbd7ae3ae13e8f5ee7f1775e7ab1"},
-    {file = "orjson-3.11.4-cp39-cp39-win_amd64.whl", hash = "sha256:e2985ce8b8c42d00492d0ed79f2bd2b6460d00f2fa671dfde4bf2e02f49bf5c6"},
-    {file = "orjson-3.11.4.tar.gz", hash = "sha256:39485f4ab4c9b30a3943cfe99e1a213c4776fb69e8abd68f66b83d5a0b0fdc6d"},
-]
-
 [[package]]
 name = "packaging"
 version = "25.0"
@@ -6487,21 +6252,6 @@ files = [
 [package.dependencies]
 ptyprocess = ">=0.5"
 
-[[package]]
-name = "pfzy"
-version = "0.3.4"
-description = "Python port of the fzy fuzzy string matching algorithm"
-optional = false
-python-versions = ">=3.7,<4.0"
-groups = ["main"]
-files = [
-    {file = "pfzy-0.3.4-py3-none-any.whl", hash = "sha256:5f50d5b2b3207fa72e7ec0ef08372ef652685470974a107d0d4999fc5a903a96"},
-    {file = "pfzy-0.3.4.tar.gz", hash = "sha256:717ea765dd10b63618e7298b2d98efd819e0b30cd5905c9707223dceeb94b3f1"},
-]
-
-[package.extras]
-docs = ["Sphinx (>=4.1.2,<5.0.0)", "furo (>=2021.8.17-beta.43,<2022.0.0)", "myst-parser (>=0.15.1,<0.16.0)", "sphinx-autobuild (>=2021.3.14,<2022.0.0)", "sphinx-copybutton (>=0.4.0,<0.5.0)"]
-
 [[package]]
 name = "pg8000"
 version = "1.31.5"

enterprise/server/constants.py

@@ -50,7 +50,7 @@ SUBSCRIPTION_PRICE_DATA = {
     },
 }
 
-DEFAULT_INITIAL_BUDGET = float(os.environ.get('DEFAULT_INITIAL_BUDGET', '10'))
+DEFAULT_INITIAL_BUDGET = float(os.environ.get('DEFAULT_INITIAL_BUDGET', '20'))
 STRIPE_API_KEY = os.environ.get('STRIPE_API_KEY', None)
 STRIPE_WEBHOOK_SECRET = os.environ.get('STRIPE_WEBHOOK_SECRET', None)
 REQUIRE_PAYMENT = os.environ.get('REQUIRE_PAYMENT', '0') in ('1', 'true')

enterprise/server/routes/auth.py

@@ -30,7 +30,6 @@ from openhands.server.services.conversation_service import create_provider_token
 from openhands.server.shared import config
 from openhands.server.user_auth import get_access_token
 from openhands.server.user_auth.user_auth import get_user_auth
-from openhands.utils.posthog_tracker import track_user_signup_completed
 
 with warnings.catch_warnings():
     warnings.simplefilter('ignore')
@@ -363,12 +362,6 @@ async def accept_tos(request: Request):
 
     logger.info(f'User {user_id} accepted TOS')
 
-    # Track user signup completion in PostHog
-    track_user_signup_completed(
-        user_id=user_id,
-        signup_timestamp=user_settings.accepted_tos.isoformat(),
-    )
-
     response = JSONResponse(
         status_code=status.HTTP_200_OK, content={'redirect_url': redirect_url}
     )

enterprise/server/routes/billing.py

@@ -25,11 +25,9 @@ from storage.billing_session import BillingSession
 from storage.database import session_maker
 from storage.saas_settings_store import SaasSettingsStore
 from storage.subscription_access import SubscriptionAccess
-from storage.user_settings import UserSettings
 
 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')
@@ -459,20 +457,6 @@ async def success_callback(session_id: str, request: Request):
             )
             session.commit()
 
-            # Track credits purchased in PostHog
-            try:
-                track_credits_purchased(
-                    user_id=billing_session.user_id,
-                    amount_usd=amount_subtotal / 100,  # Convert cents to dollars
-                    credits_added=add_credits,
-                    stripe_session_id=session_id,
-                )
-            except Exception as e:
-                logger.warning(
-                    f'Failed to track credits purchase: {e}',
-                    extra={'user_id': billing_session.user_id, 'error': str(e)},
-                )
-
     return RedirectResponse(
         f'{request.base_url}settings/billing?checkout=success', status_code=302
     )

enterprise/storage/saas_conversation_store.py

@@ -35,7 +35,6 @@ class SaasConversationStore(ConversationStore):
             session.query(StoredConversationMetadata)
             .filter(StoredConversationMetadata.user_id == self.user_id)
             .filter(StoredConversationMetadata.conversation_id == conversation_id)
-            .filter(StoredConversationMetadata.conversation_version == 'V0')
         )
 
     def _to_external_model(self, conversation_metadata: StoredConversationMetadata):
@@ -60,7 +59,6 @@ class SaasConversationStore(ConversationStore):
         kwargs.pop('reasoning_tokens', None)
         kwargs.pop('context_window', None)
         kwargs.pop('per_turn_token', None)
-        kwargs.pop('parent_conversation_id', None)
 
         return ConversationMetadata(**kwargs)
 
@@ -125,7 +123,6 @@ class SaasConversationStore(ConversationStore):
                 conversations = (
                     session.query(StoredConversationMetadata)
                     .filter(StoredConversationMetadata.user_id == self.user_id)
-                    .filter(StoredConversationMetadata.conversation_version == 'V0')
                     .order_by(StoredConversationMetadata.created_at.desc())
                     .offset(offset)
                     .limit(limit + 1)

enterprise/tests/unit/experiments/test_saas_experiment_manager.py

@@ -92,8 +92,11 @@ def test_unknown_variant_returns_original_agent_without_changes(monkeypatch):
     assert getattr(result, 'condenser', None) is None
 
 
+@patch('experiments.experiment_manager.handle_condenser_max_step_experiment__v1')
 @patch('experiments.experiment_manager.ENABLE_EXPERIMENT_MANAGER', False)
-def test_run_agent_variant_tests_v1_noop_when_manager_disabled():
+def test_run_agent_variant_tests_v1_noop_when_manager_disabled(
+    mock_handle_condenser,
+):
     """If ENABLE_EXPERIMENT_MANAGER is False, the method returns the exact same agent and does not call the handler."""
     agent = make_agent()
     conv_id = uuid4()
@@ -106,6 +109,8 @@ def test_run_agent_variant_tests_v1_noop_when_manager_disabled():
 
     # Same object returned (no copy)
     assert result is agent
+    # Handler should not have been called
+    mock_handle_condenser.assert_not_called()
 
 
 @patch('experiments.experiment_manager.ENABLE_EXPERIMENT_MANAGER', True)
@@ -126,3 +131,7 @@ def test_run_agent_variant_tests_v1_calls_handler_and_sets_system_prompt(monkeyp
     # Should be a different instance than the original (copied after handler runs)
     assert result is not agent
     assert result.system_prompt_filename == 'system_prompt_long_horizon.j2'
+
+    # The condenser returned by the handler must be preserved after the system-prompt override copy
+    assert isinstance(result.condenser, LLMSummarizingCondenser)
+    assert result.condenser.max_size == 80

enterprise/tests/unit/test_saas_settings_store.py

@@ -243,7 +243,7 @@ async def test_update_settings_with_litellm_default(
     # Check that the URL and most of the JSON payload match what we expect
     assert call_args['json']['user_email'] == 'testy@tester.com'
     assert call_args['json']['models'] == []
-    assert call_args['json']['max_budget'] == 10.0
+    assert call_args['json']['max_budget'] == 20.0
     assert call_args['json']['user_id'] == 'user-id'
     assert call_args['json']['teams'] == ['test_team']
     assert call_args['json']['auto_create_key'] is True

evaluation/benchmarks/multi_swe_bench/README.md

@@ -15,7 +15,7 @@ python evaluation/benchmarks/multi_swe_bench/scripts/data/data_change.py
 
 ## Docker image download
 
-Please download the multi-swe-bench docker images from [here](https://github.com/multi-swe-bench/multi-swe-bench?tab=readme-ov-file#run-evaluation).
+Please download the multi-swe-bench dokcer images from [here](https://github.com/multi-swe-bench/multi-swe-bench?tab=readme-ov-file#run-evaluation).
 
 ## Generate patch
 
@@ -47,7 +47,7 @@ For debugging purposes, you can set `export EVAL_SKIP_MAXIMUM_RETRIES_EXCEEDED=t
 
 The results will be generated in evaluation/evaluation_outputs/outputs/XXX/CodeActAgent/YYY/output.jsonl, you can refer to the [example](examples/output.jsonl).
 
-## Running evaluation
+## Runing evaluation
 
 First, install [multi-swe-bench](https://github.com/multi-swe-bench/multi-swe-bench).
 

evaluation/integration_tests/README.md

@@ -0,0 +1,69 @@
+# Integration tests
+
+This directory implements integration tests that [was running in CI](https://github.com/OpenHands/OpenHands/tree/23d3becf1d6f5d07e592f7345750c314a826b4e9/tests/integration).
+
+[PR 3985](https://github.com/OpenHands/OpenHands/pull/3985) introduce LLM-based editing, which requires access to LLM to perform edit. Hence, we remove integration tests from CI and intend to run them as nightly evaluation to ensure the quality of OpenHands softwares.
+
+## To add new tests
+
+Each test is a file named like `tXX_testname.py` where `XX` is a number.
+Make sure to name the file for each test to start with `t` and ends with `.py`.
+
+Each test should be structured as a subclass of [`BaseIntegrationTest`](./tests/base.py), where you need to implement `initialize_runtime` that setup the runtime enviornment before test, and `verify_result` that takes in a `Runtime` and history of `Event` and return a `TestResult`. See [t01_fix_simple_typo.py](./tests/t01_fix_simple_typo.py) and [t05_simple_browsing.py](./tests/t05_simple_browsing.py) for two representative examples.
+
+```python
+class TestResult(BaseModel):
+    success: bool
+    reason: str | None = None
+
+
+class BaseIntegrationTest(ABC):
+    """Base class for integration tests."""
+
+    INSTRUCTION: str
+
+    @classmethod
+    @abstractmethod
+    def initialize_runtime(cls, runtime: Runtime) -> None:
+        """Initialize the runtime for the test to run."""
+        pass
+
+    @classmethod
+    @abstractmethod
+    def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
+        """Verify the result of the test.
+
+        This method will be called after the agent performs the task on the runtime.
+        """
+        pass
+```
+
+
+## Setup Environment and LLM Configuration
+
+Please follow instruction [here](../README.md#setup) to setup your local
+development environment and LLM.
+
+## Start the evaluation
+
+```bash
+./evaluation/integration_tests/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [eval-num-workers] [eval_ids]
+```
+
+- `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 `0.9.0`.
+- `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 Exercism test set
+    (133 issues). Note: in order to use `eval_limit`, you must also set `agent`.
+- `eval-num-workers`: the number of workers to use for evaluation. Default: `1`.
+- `eval_ids`, e.g. `"1,3,10"`, limits the evaluation to instances with the
+    given IDs (comma separated).
+
+Example:
+```bash
+./evaluation/integration_tests/scripts/run_infer.sh llm.claude-35-sonnet-eval HEAD CodeActAgent
+```

evaluation/integration_tests/run_infer.py

@@ -0,0 +1,251 @@
+import asyncio
+import importlib.util
+import os
+
+import pandas as pd
+
+from evaluation.integration_tests.tests.base import BaseIntegrationTest, TestResult
+from evaluation.utils.shared import (
+    EvalMetadata,
+    EvalOutput,
+    get_default_sandbox_config_for_eval,
+    get_metrics,
+    get_openhands_config_for_eval,
+    make_metadata,
+    prepare_dataset,
+    reset_logger_for_multiprocessing,
+    run_evaluation,
+    update_llm_config_for_completions_logging,
+)
+from evaluation.utils.shared import (
+    codeact_user_response as fake_user_response,
+)
+from openhands.controller.state.state import State
+from openhands.core.config import (
+    AgentConfig,
+    OpenHandsConfig,
+    get_evaluation_parser,
+    get_llm_config_arg,
+)
+from openhands.core.logger import openhands_logger as logger
+from openhands.core.main import create_runtime, run_controller
+from openhands.events.action import MessageAction
+from openhands.events.serialization.event import event_to_dict
+from openhands.runtime.base import Runtime
+from openhands.utils.async_utils import call_async_from_sync
+
+FAKE_RESPONSES = {
+    'CodeActAgent': fake_user_response,
+    'VisualBrowsingAgent': fake_user_response,
+}
+
+
+def get_config(
+    metadata: EvalMetadata,
+    instance_id: str,
+) -> OpenHandsConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.platform = 'linux/amd64'
+    config = get_openhands_config_for_eval(
+        metadata=metadata,
+        runtime=os.environ.get('RUNTIME', 'docker'),
+        sandbox_config=sandbox_config,
+    )
+    config.debug = True
+    config.set_llm_config(
+        update_llm_config_for_completions_logging(
+            metadata.llm_config, metadata.eval_output_dir, instance_id
+        )
+    )
+    agent_config = AgentConfig(
+        enable_jupyter=True,
+        enable_browsing=True,
+        enable_llm_editor=False,
+    )
+    config.set_agent_config(agent_config)
+    return config
+
+
+def process_instance(
+    instance: pd.Series,
+    metadata: EvalMetadata,
+    reset_logger: bool = True,
+) -> EvalOutput:
+    config = get_config(metadata, instance.instance_id)
+
+    # 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, str(instance.instance_id), log_dir)
+    else:
+        logger.info(
+            f'\nStarting evaluation for instance {str(instance.instance_id)}.\n'
+        )
+
+    # =============================================
+    # import test instance
+    # =============================================
+    instance_id = instance.instance_id
+    spec = importlib.util.spec_from_file_location(instance_id, instance.file_path)
+    test_module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(test_module)
+    assert hasattr(test_module, 'Test'), (
+        f'Test module {instance_id} does not have a Test class'
+    )
+
+    test_class: type[BaseIntegrationTest] = test_module.Test
+    assert issubclass(test_class, BaseIntegrationTest), (
+        f'Test class {instance_id} does not inherit from BaseIntegrationTest'
+    )
+
+    instruction = test_class.INSTRUCTION
+
+    # =============================================
+    # create sandbox and run the agent
+    # =============================================
+    runtime: Runtime = create_runtime(config)
+    call_async_from_sync(runtime.connect)
+    try:
+        test_class.initialize_runtime(runtime)
+
+        # 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=MessageAction(content=instruction),
+                runtime=runtime,
+                fake_user_response_fn=FAKE_RESPONSES[metadata.agent_class],
+            )
+        )
+        if state is None:
+            raise ValueError('State should not be None.')
+
+        # # =============================================
+        # # result evaluation
+        # # =============================================
+
+        histories = state.history
+
+        # some basic check
+        logger.info(f'Total events in history: {len(histories)}')
+        assert len(histories) > 0, 'History should not be empty'
+
+        test_result: TestResult = test_class.verify_result(runtime, histories)
+        metrics = get_metrics(state)
+    finally:
+        runtime.close()
+
+    # Save the output
+    output = EvalOutput(
+        instance_id=str(instance.instance_id),
+        instance=instance.to_dict(),
+        instruction=instruction,
+        metadata=metadata,
+        history=[event_to_dict(event) for event in histories],
+        metrics=metrics,
+        error=state.last_error if state and state.last_error else None,
+        test_result=test_result.model_dump(),
+    )
+    return output
+
+
+def load_integration_tests() -> pd.DataFrame:
+    """Load tests from python files under ./tests"""
+    cur_dir = os.path.dirname(os.path.abspath(__file__))
+    test_dir = os.path.join(cur_dir, 'tests')
+    test_files = [
+        os.path.join(test_dir, f)
+        for f in os.listdir(test_dir)
+        if f.startswith('t') and f.endswith('.py')
+    ]
+    df = pd.DataFrame(test_files, columns=['file_path'])
+    df['instance_id'] = df['file_path'].apply(
+        lambda x: os.path.basename(x).rstrip('.py')
+    )
+    return df
+
+
+if __name__ == '__main__':
+    parser = get_evaluation_parser()
+    args, _ = parser.parse_known_args()
+    integration_tests = load_integration_tests()
+
+    llm_config = None
+    if args.llm_config:
+        llm_config = get_llm_config_arg(args.llm_config)
+
+    if llm_config is None:
+        raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
+
+    metadata = make_metadata(
+        llm_config,
+        'integration_tests',
+        args.agent_cls,
+        args.max_iterations,
+        args.eval_note,
+        args.eval_output_dir,
+    )
+    output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
+
+    # Parse dataset IDs if provided
+    eval_ids = None
+    if args.eval_ids:
+        eval_ids = str(args.eval_ids).split(',')
+        logger.info(f'\nUsing specific dataset IDs: {eval_ids}\n')
+
+    instances = prepare_dataset(
+        integration_tests,
+        output_file,
+        args.eval_n_limit,
+        eval_ids=eval_ids,
+    )
+
+    run_evaluation(
+        instances,
+        metadata,
+        output_file,
+        args.eval_num_workers,
+        process_instance,
+    )
+
+    df = pd.read_json(output_file, lines=True, orient='records')
+
+    # record success and reason
+    df['success'] = df['test_result'].apply(lambda x: x['success'])
+    df['reason'] = df['test_result'].apply(lambda x: x['reason'])
+    logger.info('-' * 100)
+    logger.info(
+        f'Success rate: {df["success"].mean():.2%} ({df["success"].sum()}/{len(df)})'
+    )
+    logger.info(
+        '\nEvaluation Results:'
+        + '\n'
+        + df[['instance_id', 'success', 'reason']].to_string(index=False)
+    )
+    logger.info('-' * 100)
+
+    # record cost for each instance, with 3 decimal places
+    # we sum up all the "costs" from the metrics array
+    df['cost'] = df['metrics'].apply(
+        lambda m: round(sum(c['cost'] for c in m['costs']), 3)
+        if m and 'costs' in m
+        else 0.0
+    )
+
+    # capture the top-level error if present, per instance
+    df['error_message'] = df.get('error', None)
+
+    logger.info(f'Total cost: USD {df["cost"].sum():.2f}')
+
+    report_file = os.path.join(metadata.eval_output_dir, 'report.md')
+    with open(report_file, 'w') as f:
+        f.write(
+            f'Success rate: {df["success"].mean():.2%}'
+            f' ({df["success"].sum()}/{len(df)})\n'
+        )
+        f.write(f'\nTotal cost: USD {df["cost"].sum():.2f}\n')
+        f.write(
+            df[
+                ['instance_id', 'success', 'reason', 'cost', 'error_message']
+            ].to_markdown(index=False)
+        )

evaluation/integration_tests/scripts/run_infer.sh

@@ -0,0 +1,62 @@
+#!/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_ITERATIONS=$5
+NUM_WORKERS=$6
+EVAL_IDS=$7
+
+if [ -z "$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
+
+get_openhands_version
+
+echo "AGENT: $AGENT"
+echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "MODEL_CONFIG: $MODEL_CONFIG"
+
+EVAL_NOTE=$OPENHANDS_VERSION
+
+# Default to NOT use unit tests.
+if [ -z "$USE_UNIT_TESTS" ]; then
+  export USE_UNIT_TESTS=false
+fi
+echo "USE_UNIT_TESTS: $USE_UNIT_TESTS"
+# If use unit tests, set EVAL_NOTE to the commit hash
+if [ "$USE_UNIT_TESTS" = true ]; then
+  EVAL_NOTE=$EVAL_NOTE-w-test
+fi
+
+# export PYTHONPATH=evaluation/integration_tests:\$PYTHONPATH
+COMMAND="poetry run python evaluation/integration_tests/run_infer.py \
+  --agent-cls $AGENT \
+  --llm-config $MODEL_CONFIG \
+  --max-iterations ${MAX_ITERATIONS:-10} \
+  --eval-num-workers $NUM_WORKERS \
+  --eval-note $EVAL_NOTE"
+
+if [ -n "$EVAL_LIMIT" ]; then
+  echo "EVAL_LIMIT: $EVAL_LIMIT"
+  COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
+fi
+
+if [ -n "$EVAL_IDS" ]; then
+  echo "EVAL_IDS: $EVAL_IDS"
+  COMMAND="$COMMAND --eval-ids $EVAL_IDS"
+fi
+
+# Run the command
+eval $COMMAND

evaluation/integration_tests/tests/base.py

@@ -0,0 +1,32 @@
+from abc import ABC, abstractmethod
+
+from pydantic import BaseModel
+
+from openhands.events.event import Event
+from openhands.runtime.base import Runtime
+
+
+class TestResult(BaseModel):
+    success: bool
+    reason: str | None = None
+
+
+class BaseIntegrationTest(ABC):
+    """Base class for integration tests."""
+
+    INSTRUCTION: str
+
+    @classmethod
+    @abstractmethod
+    def initialize_runtime(cls, runtime: Runtime) -> None:
+        """Initialize the runtime for the test to run."""
+        pass
+
+    @classmethod
+    @abstractmethod
+    def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
+        """Verify the result of the test.
+
+        This method will be called after the agent performs the task on the runtime.
+        """
+        pass

evaluation/integration_tests/tests/t01_fix_simple_typo.py

@@ -0,0 +1,39 @@
+import os
+import tempfile
+
+from evaluation.integration_tests.tests.base import BaseIntegrationTest, TestResult
+from openhands.events.action import CmdRunAction
+from openhands.events.event import Event
+from openhands.runtime.base import Runtime
+
+
+class Test(BaseIntegrationTest):
+    INSTRUCTION = 'Fix typos in bad.txt.'
+
+    @classmethod
+    def initialize_runtime(cls, runtime: Runtime) -> None:
+        # create a file with a typo in /workspace/bad.txt
+        with tempfile.TemporaryDirectory() as temp_dir:
+            temp_file_path = os.path.join(temp_dir, 'bad.txt')
+            with open(temp_file_path, 'w') as f:
+                f.write('This is a stupid typoo.\nReally?\nNo mor typos!\nEnjoy!')
+
+            # Copy the file to the desired location
+            runtime.copy_to(temp_file_path, '/workspace')
+
+    @classmethod
+    def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
+        # check if the file /workspace/bad.txt has been fixed
+        action = CmdRunAction(command='cat /workspace/bad.txt')
+        obs = runtime.run_action(action)
+        if obs.exit_code != 0:
+            return TestResult(
+                success=False, reason=f'Failed to run command: {obs.content}'
+            )
+        # check if the file /workspace/bad.txt has been fixed
+        if (
+            obs.content.strip().replace('\r\n', '\n')
+            == 'This is a stupid typo.\nReally?\nNo more typos!\nEnjoy!'
+        ):
+            return TestResult(success=True)
+        return TestResult(success=False, reason=f'File not fixed: {obs.content}')

evaluation/integration_tests/tests/t02_add_bash_hello.py

@@ -0,0 +1,40 @@
+from evaluation.integration_tests.tests.base import BaseIntegrationTest, TestResult
+from evaluation.utils.shared import assert_and_raise
+from openhands.events.action import CmdRunAction
+from openhands.events.event import Event
+from openhands.runtime.base import Runtime
+
+
+class Test(BaseIntegrationTest):
+    INSTRUCTION = "Write a shell script '/workspace/hello.sh' that prints 'hello'."
+
+    @classmethod
+    def initialize_runtime(cls, runtime: Runtime) -> None:
+        action = CmdRunAction(command='mkdir -p /workspace')
+        obs = runtime.run_action(action)
+        assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
+
+    @classmethod
+    def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
+        # check if the file /workspace/hello.sh exists
+        action = CmdRunAction(command='cat /workspace/hello.sh')
+        obs = runtime.run_action(action)
+        if obs.exit_code != 0:
+            return TestResult(
+                success=False,
+                reason=f'Failed to cat /workspace/hello.sh: {obs.content}.',
+            )
+
+        # execute the script
+        action = CmdRunAction(command='bash /workspace/hello.sh')
+        obs = runtime.run_action(action)
+        if obs.exit_code != 0:
+            return TestResult(
+                success=False,
+                reason=f'Failed to execute /workspace/hello.sh: {obs.content}.',
+            )
+        if obs.content.strip() != 'hello':
+            return TestResult(
+                success=False, reason=f'Script did not print "hello": {obs.content}.'
+            )
+        return TestResult(success=True)

evaluation/integration_tests/tests/t03_jupyter_write_file.py

@@ -0,0 +1,43 @@
+from evaluation.integration_tests.tests.base import BaseIntegrationTest, TestResult
+from evaluation.utils.shared import assert_and_raise
+from openhands.events.action import CmdRunAction
+from openhands.events.event import Event
+from openhands.runtime.base import Runtime
+
+
+class Test(BaseIntegrationTest):
+    INSTRUCTION = "Use Jupyter IPython to write a text file containing 'hello world' to '/workspace/test.txt'."
+
+    @classmethod
+    def initialize_runtime(cls, runtime: Runtime) -> None:
+        action = CmdRunAction(command='mkdir -p /workspace')
+        obs = runtime.run_action(action)
+        assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
+
+    @classmethod
+    def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
+        # check if the file /workspace/hello.sh exists
+        action = CmdRunAction(command='cat /workspace/test.txt')
+        obs = runtime.run_action(action)
+        if obs.exit_code != 0:
+            return TestResult(
+                success=False,
+                reason=f'Failed to cat /workspace/test.txt: {obs.content}.',
+            )
+
+        # execute the script
+        action = CmdRunAction(command='cat /workspace/test.txt')
+        obs = runtime.run_action(action)
+
+        if obs.exit_code != 0:
+            return TestResult(
+                success=False,
+                reason=f'Failed to cat /workspace/test.txt: {obs.content}.',
+            )
+
+        if 'hello world' not in obs.content.strip():
+            return TestResult(
+                success=False,
+                reason=f'File did not contain "hello world": {obs.content}.',
+            )
+        return TestResult(success=True)

evaluation/integration_tests/tests/t04_git_staging.py

@@ -0,0 +1,57 @@
+from evaluation.integration_tests.tests.base import BaseIntegrationTest, TestResult
+from evaluation.utils.shared import assert_and_raise
+from openhands.events.action import CmdRunAction
+from openhands.events.event import Event
+from openhands.runtime.base import Runtime
+
+
+class Test(BaseIntegrationTest):
+    INSTRUCTION = 'Write a git commit message for the current staging area and commit the changes.'
+
+    @classmethod
+    def initialize_runtime(cls, runtime: Runtime) -> None:
+        action = CmdRunAction(command='mkdir -p /workspace')
+        obs = runtime.run_action(action)
+        assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
+
+        # git init
+        action = CmdRunAction(command='git init')
+        obs = runtime.run_action(action)
+        assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
+
+        # create file
+        action = CmdRunAction(command='echo \'print("hello world")\' > hello.py')
+        obs = runtime.run_action(action)
+        assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
+
+        # git add
+        cmd_str = 'git add hello.py'
+        action = CmdRunAction(command=cmd_str)
+        obs = runtime.run_action(action)
+        assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
+
+    @classmethod
+    def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
+        # check if the file /workspace/hello.py exists
+        action = CmdRunAction(command='cat /workspace/hello.py')
+        obs = runtime.run_action(action)
+        if obs.exit_code != 0:
+            return TestResult(
+                success=False,
+                reason=f'Failed to cat /workspace/hello.py: {obs.content}.',
+            )
+
+        # check if the staging area is empty
+        action = CmdRunAction(command='git status')
+        obs = runtime.run_action(action)
+        if obs.exit_code != 0:
+            return TestResult(
+                success=False, reason=f'Failed to git status: {obs.content}.'
+            )
+        if 'nothing to commit, working tree clean' in obs.content.strip():
+            return TestResult(success=True)
+
+        return TestResult(
+            success=False,
+            reason=f'Failed to check for "nothing to commit, working tree clean": {obs.content}.',
+        )

evaluation/integration_tests/tests/t05_simple_browsing.py

@@ -0,0 +1,145 @@
+import os
+import tempfile
+
+from evaluation.integration_tests.tests.base import BaseIntegrationTest, TestResult
+from evaluation.utils.shared import assert_and_raise
+from openhands.events.action import AgentFinishAction, CmdRunAction, MessageAction
+from openhands.events.event import Event
+from openhands.events.observation import AgentDelegateObservation
+from openhands.runtime.base import Runtime
+
+HTML_FILE = """
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>The Ultimate Answer</title>
+    <style>
+        body {
+            display: flex;
+            justify-content: center;
+            align-items: center;
+            height: 100vh;
+            margin: 0;
+            background: linear-gradient(to right, #1e3c72, #2a5298);
+            color: #fff;
+            font-family: 'Arial', sans-serif;
+            text-align: center;
+        }
+        .container {
+            text-align: center;
+            padding: 20px;
+            background: rgba(255, 255, 255, 0.1);
+            border-radius: 10px;
+            box-shadow: 0 0 10px rgba(0, 0, 0, 0.2);
+        }
+        h1 {
+            font-size: 36px;
+            margin-bottom: 20px;
+        }
+        p {
+            font-size: 18px;
+            margin-bottom: 30px;
+        }
+        #showButton {
+            padding: 10px 20px;
+            font-size: 16px;
+            color: #1e3c72;
+            background: #fff;
+            border: none;
+            border-radius: 5px;
+            cursor: pointer;
+            transition: background 0.3s ease;
+        }
+        #showButton:hover {
+            background: #f0f0f0;
+        }
+        #result {
+            margin-top: 20px;
+            font-size: 24px;
+        }
+    </style>
+</head>
+<body>
+    <div class="container">
+        <h1>The Ultimate Answer</h1>
+        <p>Click the button to reveal the answer to life, the universe, and everything.</p>
+        <button id="showButton">Click me</button>
+        <div id="result"></div>
+    </div>
+    <script>
+        document.getElementById('showButton').addEventListener('click', function() {
+            document.getElementById('result').innerText = 'The answer is OpenHands is all you need!';
+        });
+    </script>
+</body>
+</html>
+"""
+
+
+class Test(BaseIntegrationTest):
+    INSTRUCTION = 'Browse localhost:8000, and tell me the ultimate answer to life.'
+
+    @classmethod
+    def initialize_runtime(cls, runtime: Runtime) -> None:
+        action = CmdRunAction(command='mkdir -p /workspace')
+        obs = runtime.run_action(action)
+        assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
+
+        action = CmdRunAction(command='mkdir -p /tmp/server')
+        obs = runtime.run_action(action)
+        assert_and_raise(obs.exit_code == 0, f'Failed to run command: {obs.content}')
+
+        # create a file with a typo in /workspace/bad.txt
+        with tempfile.TemporaryDirectory() as temp_dir:
+            temp_file_path = os.path.join(temp_dir, 'index.html')
+            with open(temp_file_path, 'w') as f:
+                f.write(HTML_FILE)
+            # Copy the file to the desired location
+            runtime.copy_to(temp_file_path, '/tmp/server')
+
+        # create README.md
+        action = CmdRunAction(
+            command='cd /tmp/server && nohup python3 -m http.server 8000 &'
+        )
+        obs = runtime.run_action(action)
+
+    @classmethod
+    def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
+        from openhands.core.logger import openhands_logger as logger
+
+        # check if the "The answer is OpenHands is all you need!" is in any message
+        message_actions = [
+            event
+            for event in histories
+            if isinstance(
+                event, (MessageAction, AgentFinishAction, AgentDelegateObservation)
+            )
+        ]
+        logger.debug(f'Total message-like events: {len(message_actions)}')
+
+        for event in message_actions:
+            try:
+                if isinstance(event, AgentDelegateObservation):
+                    content = event.content
+                elif isinstance(event, AgentFinishAction):
+                    content = event.outputs.get('content', '')
+                elif isinstance(event, MessageAction):
+                    content = event.content
+                else:
+                    logger.warning(f'Unexpected event type: {type(event)}')
+                    continue
+
+                if 'OpenHands is all you need!' in content:
+                    return TestResult(success=True)
+            except Exception as e:
+                logger.error(f'Error processing event: {e}')
+
+        logger.debug(
+            f'Total messages: {len(message_actions)}. Messages: {message_actions}'
+        )
+        return TestResult(
+            success=False,
+            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}.',
+        )

evaluation/integration_tests/tests/t06_github_pr_browsing.py

@@ -0,0 +1,58 @@
+from evaluation.integration_tests.tests.base import BaseIntegrationTest, TestResult
+from openhands.events.action import AgentFinishAction, MessageAction
+from openhands.events.event import Event
+from openhands.events.observation import AgentDelegateObservation
+from openhands.runtime.base import Runtime
+
+
+class Test(BaseIntegrationTest):
+    INSTRUCTION = 'Look at https://github.com/OpenHands/OpenHands/pull/8, and tell me what is happening there and what did @asadm suggest.'
+
+    @classmethod
+    def initialize_runtime(cls, runtime: Runtime) -> None:
+        pass
+
+    @classmethod
+    def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
+        from openhands.core.logger import openhands_logger as logger
+
+        # check if the license information is in any message
+        message_actions = [
+            event
+            for event in histories
+            if isinstance(
+                event, (MessageAction, AgentFinishAction, AgentDelegateObservation)
+            )
+        ]
+        logger.info(f'Total message-like events: {len(message_actions)}')
+
+        for event in message_actions:
+            try:
+                if isinstance(event, AgentDelegateObservation):
+                    content = event.content
+                elif isinstance(event, AgentFinishAction):
+                    content = event.outputs.get('content', '')
+                    if event.thought:
+                        content += f'\n\n{event.thought}'
+                elif isinstance(event, MessageAction):
+                    content = event.content
+                else:
+                    logger.warning(f'Unexpected event type: {type(event)}')
+                    continue
+
+                if (
+                    'non-commercial' in content
+                    or 'MIT' in content
+                    or 'Apache 2.0' in content
+                ):
+                    return TestResult(success=True)
+            except Exception as e:
+                logger.error(f'Error processing event: {e}')
+
+        logger.debug(
+            f'Total messages: {len(message_actions)}. Messages: {message_actions}'
+        )
+        return TestResult(
+            success=False,
+            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}.',
+        )

evaluation/integration_tests/tests/t07_interactive_commands.py

@@ -0,0 +1,73 @@
+import hashlib
+
+from evaluation.integration_tests.tests.base import BaseIntegrationTest, TestResult
+from openhands.events.action import (
+    AgentFinishAction,
+    FileWriteAction,
+    MessageAction,
+)
+from openhands.events.event import Event
+from openhands.events.observation import AgentDelegateObservation
+from openhands.runtime.base import Runtime
+
+
+class Test(BaseIntegrationTest):
+    INSTRUCTION = 'Execute the python script /workspace/python_script.py with input "John" and "25" and tell me the secret number.'
+    SECRET_NUMBER = int(hashlib.sha256(str(25).encode()).hexdigest()[:8], 16) % 1000
+
+    @classmethod
+    def initialize_runtime(cls, runtime: Runtime) -> None:
+        from openhands.core.logger import openhands_logger as logger
+
+        action = FileWriteAction(
+            path='/workspace/python_script.py',
+            content=(
+                'name = input("Enter your name: "); age = input("Enter your age: "); '
+                'import hashlib; secret = int(hashlib.sha256(str(age).encode()).hexdigest()[:8], 16) % 1000; '
+                'print(f"Hello {name}, you are {age} years old. Tell you a secret number: {secret}")'
+            ),
+        )
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        observation = runtime.run_action(action)
+        logger.info(observation, extra={'msg_type': 'OBSERVATION'})
+
+    @classmethod
+    def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
+        from openhands.core.logger import openhands_logger as logger
+
+        # check if the license information is in any message
+        message_actions = [
+            event
+            for event in histories
+            if isinstance(
+                event, (MessageAction, AgentFinishAction, AgentDelegateObservation)
+            )
+        ]
+        logger.info(f'Total message-like events: {len(message_actions)}')
+
+        for event in message_actions:
+            try:
+                if isinstance(event, AgentDelegateObservation):
+                    content = event.content
+                elif isinstance(event, AgentFinishAction):
+                    content = event.outputs.get('content', '')
+                    if event.thought:
+                        content += f'\n\n{event.thought}'
+                elif isinstance(event, MessageAction):
+                    content = event.content
+                else:
+                    logger.warning(f'Unexpected event type: {type(event)}')
+                    continue
+
+                if str(cls.SECRET_NUMBER) in content:
+                    return TestResult(success=True)
+            except Exception as e:
+                logger.error(f'Error processing event: {e}')
+
+        logger.debug(
+            f'Total messages: {len(message_actions)}. Messages: {message_actions}'
+        )
+        return TestResult(
+            success=False,
+            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}.',
+        )

frontend/__tests__/components/context-menu/account-settings-context-menu.test.tsx

@@ -33,24 +33,9 @@ describe("AccountSettingsContextMenu", () => {
     expect(
       screen.getByTestId("account-settings-context-menu"),
     ).toBeInTheDocument();
-    expect(screen.getByText("SIDEBAR$DOCS")).toBeInTheDocument();
     expect(screen.getByText("ACCOUNT_SETTINGS$LOGOUT")).toBeInTheDocument();
   });
 
-  it("should render Documentation link with correct attributes", () => {
-    renderWithRouter(
-      <AccountSettingsContextMenu
-        onLogout={onLogoutMock}
-        onClose={onCloseMock}
-      />,
-    );
-
-    const documentationLink = screen.getByText("SIDEBAR$DOCS").closest("a");
-    expect(documentationLink).toHaveAttribute("href", "https://docs.openhands.dev");
-    expect(documentationLink).toHaveAttribute("target", "_blank");
-    expect(documentationLink).toHaveAttribute("rel", "noopener noreferrer");
-  });
-
   it("should call onLogout when the logout option is clicked", async () => {
     renderWithRouter(
       <AccountSettingsContextMenu

frontend/__tests__/components/features/auth-modal.test.tsx

@@ -8,13 +8,6 @@ vi.mock("#/hooks/use-auth-url", () => ({
   useAuthUrl: () => "https://gitlab.com/oauth/authorize",
 }));
 
-// Mock the useTracking hook
-vi.mock("#/hooks/use-tracking", () => ({
-  useTracking: () => ({
-    trackLoginButtonClick: vi.fn(),
-  }),
-}));
-
 describe("AuthModal", () => {
   beforeEach(() => {
     vi.stubGlobal("location", { href: "" });

frontend/__tests__/components/features/chat/task-tracking-observation-content.test.tsx

@@ -8,11 +8,10 @@ vi.mock("react-i18next", () => ({
   useTranslation: () => ({
     t: (key: string) => {
       const translations: Record<string, string> = {
-        TASK_TRACKING_OBSERVATION$TASK_LIST: "Task List",
-        TASK_TRACKING_OBSERVATION$TASK_ID: "ID",
-        TASK_TRACKING_OBSERVATION$TASK_NOTES: "Notes",
-        TASK_TRACKING_OBSERVATION$RESULT: "Result",
-        COMMON$TASKS: "Tasks",
+        "TASK_TRACKING_OBSERVATION$TASK_LIST": "Task List",
+        "TASK_TRACKING_OBSERVATION$TASK_ID": "ID",
+        "TASK_TRACKING_OBSERVATION$TASK_NOTES": "Notes",
+        "TASK_TRACKING_OBSERVATION$RESULT": "Result",
       };
       return translations[key] || key;
     },
@@ -62,26 +61,19 @@ describe("TaskTrackingObservationContent", () => {
   it("renders task list when command is 'plan' and tasks exist", () => {
     render(<TaskTrackingObservationContent event={mockEvent} />);
 
-    expect(screen.getByText("Tasks")).toBeInTheDocument();
+    expect(screen.getByText("Task List (3 items)")).toBeInTheDocument();
     expect(screen.getByText("Implement feature A")).toBeInTheDocument();
     expect(screen.getByText("Fix bug B")).toBeInTheDocument();
     expect(screen.getByText("Deploy to production")).toBeInTheDocument();
   });
 
   it("displays correct status icons and badges", () => {
-    const { container } = render(
-      <TaskTrackingObservationContent event={mockEvent} />,
-    );
+    render(<TaskTrackingObservationContent event={mockEvent} />);
 
-    // Status is represented by icons, not text. Verify task items are rendered with their titles
-    // which indicates the status icons are present (status affects icon rendering)
-    expect(screen.getByText("Implement feature A")).toBeInTheDocument();
-    expect(screen.getByText("Fix bug B")).toBeInTheDocument();
-    expect(screen.getByText("Deploy to production")).toBeInTheDocument();
-
-    // Verify task items are present (they contain the status icons)
-    const taskItems = container.querySelectorAll('[data-name="item"]');
-    expect(taskItems).toHaveLength(3);
+    // Check for status text (the icons are emojis)
+    expect(screen.getByText("todo")).toBeInTheDocument();
+    expect(screen.getByText("in progress")).toBeInTheDocument();
+    expect(screen.getByText("done")).toBeInTheDocument();
   });
 
   it("displays task IDs and notes", () => {
@@ -92,9 +84,14 @@ describe("TaskTrackingObservationContent", () => {
     expect(screen.getByText("ID: task-3")).toBeInTheDocument();
 
     expect(screen.getByText("Notes: This is a test task")).toBeInTheDocument();
-    expect(
-      screen.getByText("Notes: Completed successfully"),
-    ).toBeInTheDocument();
+    expect(screen.getByText("Notes: Completed successfully")).toBeInTheDocument();
+  });
+
+  it("renders result section when content exists", () => {
+    render(<TaskTrackingObservationContent event={mockEvent} />);
+
+    expect(screen.getByText("Result")).toBeInTheDocument();
+    expect(screen.getByText("Task tracking operation completed successfully")).toBeInTheDocument();
   });
 
   it("does not render task list when command is not 'plan'", () => {
@@ -108,7 +105,7 @@ describe("TaskTrackingObservationContent", () => {
 
     render(<TaskTrackingObservationContent event={eventWithoutPlan} />);
 
-    expect(screen.queryByText("Tasks")).not.toBeInTheDocument();
+    expect(screen.queryByText("Task List")).not.toBeInTheDocument();
   });
 
   it("does not render task list when task list is empty", () => {
@@ -122,6 +119,17 @@ describe("TaskTrackingObservationContent", () => {
 
     render(<TaskTrackingObservationContent event={eventWithEmptyTasks} />);
 
-    expect(screen.queryByText("Tasks")).not.toBeInTheDocument();
+    expect(screen.queryByText("Task List")).not.toBeInTheDocument();
+  });
+
+  it("does not render result section when content is empty", () => {
+    const eventWithoutContent = {
+      ...mockEvent,
+      content: "",
+    };
+
+    render(<TaskTrackingObservationContent event={eventWithoutContent} />);
+
+    expect(screen.queryByText("Result")).not.toBeInTheDocument();
   });
 });

frontend/__tests__/components/features/conversation-panel/conversation-panel.test.tsx

@@ -3,7 +3,7 @@ import { beforeAll, beforeEach, describe, expect, it, vi } from "vitest";
 import userEvent from "@testing-library/user-event";
 import { createRoutesStub } from "react-router";
 import React from "react";
-import { renderWithQueryAndI18n } from "test-utils";
+import { renderWithProviders } from "test-utils";
 import { ConversationPanel } from "#/components/features/conversation-panel/conversation-panel";
 import ConversationService from "#/api/conversation-service/conversation-service.api";
 import { Conversation } from "#/api/open-hands.types";

frontend/__tests__/components/features/conversation/server-status.test.tsx

@@ -13,6 +13,34 @@ vi.mock("#/hooks/use-agent-state", () => ({
   useAgentState: vi.fn(),
 }));
 
+// Mock the custom hooks
+const mockStartConversationMutate = vi.fn();
+const mockStopConversationMutate = vi.fn();
+
+vi.mock("#/hooks/mutation/use-unified-start-conversation", () => ({
+  useUnifiedStartConversation: () => ({
+    mutate: mockStartConversationMutate,
+  }),
+}));
+
+vi.mock("#/hooks/mutation/use-unified-stop-conversation", () => ({
+  useUnifiedStopConversation: () => ({
+    mutate: mockStopConversationMutate,
+  }),
+}));
+
+vi.mock("#/hooks/use-conversation-id", () => ({
+  useConversationId: () => ({
+    conversationId: "test-conversation-id",
+  }),
+}));
+
+vi.mock("#/hooks/use-user-providers", () => ({
+  useUserProviders: () => ({
+    providers: [],
+  }),
+}));
+
 vi.mock("#/hooks/query/use-task-polling", () => ({
   useTaskPolling: () => ({
     isTask: false,
@@ -38,12 +66,8 @@ vi.mock("react-i18next", async () => {
           COMMON$SERVER_STOPPED: "Server Stopped",
           COMMON$ERROR: "Error",
           COMMON$STARTING: "Starting",
-          COMMON$STOPPING: "Stopping...",
           COMMON$STOP_RUNTIME: "Stop Runtime",
           COMMON$START_RUNTIME: "Start Runtime",
-          CONVERSATION$ERROR_STARTING_CONVERSATION:
-            "Error starting conversation",
-          CONVERSATION$READY: "Ready",
         };
         return translations[key] || key;
       },
@@ -55,6 +79,10 @@ vi.mock("react-i18next", async () => {
 });
 
 describe("ServerStatus", () => {
+  // Mock functions for handlers
+  const mockHandleStop = vi.fn();
+  const mockHandleResumeAgent = vi.fn();
+
   // Helper function to mock agent state with specific state
   const mockAgentStore = (agentState: AgentState) => {
     vi.mocked(useAgentState).mockReturnValue({
@@ -66,91 +94,248 @@ describe("ServerStatus", () => {
     vi.clearAllMocks();
   });
 
-  it("should render server status with RUNNING conversation status", () => {
+  it("should render server status with different conversation statuses", () => {
+    // Mock agent store to return RUNNING state
     mockAgentStore(AgentState.RUNNING);
 
-    renderWithProviders(<ServerStatus conversationStatus="RUNNING" />);
+    // Test RUNNING status
+    const { rerender } = renderWithProviders(
+      <ServerStatus
+        conversationStatus="RUNNING"
+        handleStop={mockHandleStop}
+        handleResumeAgent={mockHandleResumeAgent}
+      />,
+    );
+    expect(screen.getByText("Running")).toBeInTheDocument();
 
-    expect(screen.getByTestId("server-status")).toBeInTheDocument();
+    // Test STOPPED status
+    rerender(
+      <ServerStatus
+        conversationStatus="STOPPED"
+        handleStop={mockHandleStop}
+        handleResumeAgent={mockHandleResumeAgent}
+      />,
+    );
+    expect(screen.getByText("Server Stopped")).toBeInTheDocument();
+
+    // Test STARTING status (shows "Running" due to agent state being RUNNING)
+    rerender(
+      <ServerStatus
+        conversationStatus="STARTING"
+        handleStop={mockHandleStop}
+        handleResumeAgent={mockHandleResumeAgent}
+      />,
+    );
+    expect(screen.getByText("Running")).toBeInTheDocument();
+
+    // Test null status (shows "Running" due to agent state being RUNNING)
+    rerender(
+      <ServerStatus
+        conversationStatus={null}
+        handleStop={mockHandleStop}
+        handleResumeAgent={mockHandleResumeAgent}
+      />,
+    );
     expect(screen.getByText("Running")).toBeInTheDocument();
   });
 
-  it("should render server status with STOPPED conversation status", () => {
-    mockAgentStore(AgentState.RUNNING);
+  it("should show context menu when clicked with RUNNING status", async () => {
+    const user = userEvent.setup();
 
-    renderWithProviders(<ServerStatus conversationStatus="STOPPED" />);
-
-    expect(screen.getByTestId("server-status")).toBeInTheDocument();
-    expect(screen.getByText("Server Stopped")).toBeInTheDocument();
-  });
-
-  it("should render STARTING status when agent state is LOADING", () => {
-    mockAgentStore(AgentState.LOADING);
-
-    renderWithProviders(<ServerStatus conversationStatus="STARTING" />);
-
-    expect(screen.getByTestId("server-status")).toBeInTheDocument();
-    expect(screen.getByText("Starting")).toBeInTheDocument();
-  });
-
-  it("should render STARTING status when agent state is INIT", () => {
-    mockAgentStore(AgentState.INIT);
-
-    renderWithProviders(<ServerStatus conversationStatus="STARTING" />);
-
-    expect(screen.getByTestId("server-status")).toBeInTheDocument();
-    expect(screen.getByText("Starting")).toBeInTheDocument();
-  });
-
-  it("should render ERROR status when agent state is ERROR", () => {
-    mockAgentStore(AgentState.ERROR);
-
-    renderWithProviders(<ServerStatus conversationStatus="RUNNING" />);
-
-    expect(screen.getByTestId("server-status")).toBeInTheDocument();
-    expect(screen.getByText("Error")).toBeInTheDocument();
-  });
-
-  it("should render STOPPING status when isPausing is true", () => {
+    // Mock agent store to return RUNNING state
     mockAgentStore(AgentState.RUNNING);
 
     renderWithProviders(
-      <ServerStatus conversationStatus="RUNNING" isPausing={true} />,
+      <ServerStatus
+        conversationStatus="RUNNING"
+        handleStop={mockHandleStop}
+        handleResumeAgent={mockHandleResumeAgent}
+      />,
     );
 
-    expect(screen.getByTestId("server-status")).toBeInTheDocument();
-    expect(screen.getByText("Stopping...")).toBeInTheDocument();
+    const statusContainer = screen.getByText("Running").closest("div");
+    expect(statusContainer).toBeInTheDocument();
+
+    await user.click(statusContainer!);
+
+    // Context menu should appear
+    expect(
+      screen.getByTestId("server-status-context-menu"),
+    ).toBeInTheDocument();
+    expect(screen.getByTestId("stop-server-button")).toBeInTheDocument();
+  });
+
+  it("should show context menu when clicked with STOPPED status", async () => {
+    const user = userEvent.setup();
+
+    // Mock agent store to return STOPPED state
+    mockAgentStore(AgentState.STOPPED);
+
+    renderWithProviders(
+      <ServerStatus
+        conversationStatus="STOPPED"
+        handleStop={mockHandleStop}
+        handleResumeAgent={mockHandleResumeAgent}
+      />,
+    );
+
+    const statusContainer = screen.getByText("Server Stopped").closest("div");
+    expect(statusContainer).toBeInTheDocument();
+
+    await user.click(statusContainer!);
+
+    // Context menu should appear
+    expect(
+      screen.getByTestId("server-status-context-menu"),
+    ).toBeInTheDocument();
+    expect(screen.getByTestId("start-server-button")).toBeInTheDocument();
+  });
+
+  it("should not show context menu when clicked with other statuses", async () => {
+    const user = userEvent.setup();
+
+    // Mock agent store to return RUNNING state
+    mockAgentStore(AgentState.RUNNING);
+
+    renderWithProviders(
+      <ServerStatus
+        conversationStatus="STARTING"
+        handleStop={mockHandleStop}
+        handleResumeAgent={mockHandleResumeAgent}
+      />,
+    );
+
+    const statusContainer = screen.getByText("Running").closest("div");
+    expect(statusContainer).toBeInTheDocument();
+
+    await user.click(statusContainer!);
+
+    // Context menu should not appear
+    expect(
+      screen.queryByTestId("server-status-context-menu"),
+    ).not.toBeInTheDocument();
+  });
+
+  it("should call stop conversation mutation when stop server is clicked", async () => {
+    const user = userEvent.setup();
+
+    // Clear previous calls
+    mockHandleStop.mockClear();
+
+    // Mock agent store to return RUNNING state
+    mockAgentStore(AgentState.RUNNING);
+
+    renderWithProviders(
+      <ServerStatus
+        conversationStatus="RUNNING"
+        handleStop={mockHandleStop}
+        handleResumeAgent={mockHandleResumeAgent}
+      />,
+    );
+
+    const statusContainer = screen.getByText("Running").closest("div");
+    await user.click(statusContainer!);
+
+    const stopButton = screen.getByTestId("stop-server-button");
+    await user.click(stopButton);
+
+    expect(mockHandleStop).toHaveBeenCalledTimes(1);
+  });
+
+  it("should call start conversation mutation when start server is clicked", async () => {
+    const user = userEvent.setup();
+
+    // Clear previous calls
+    mockHandleResumeAgent.mockClear();
+
+    // Mock agent store to return STOPPED state
+    mockAgentStore(AgentState.STOPPED);
+
+    renderWithProviders(
+      <ServerStatus
+        conversationStatus="STOPPED"
+        handleStop={mockHandleStop}
+        handleResumeAgent={mockHandleResumeAgent}
+      />,
+    );
+
+    const statusContainer = screen.getByText("Server Stopped").closest("div");
+    await user.click(statusContainer!);
+
+    const startButton = screen.getByTestId("start-server-button");
+    await user.click(startButton);
+
+    expect(mockHandleResumeAgent).toHaveBeenCalledTimes(1);
+  });
+
+  it("should close context menu after stop server action", async () => {
+    const user = userEvent.setup();
+
+    // Mock agent store to return RUNNING state
+    mockAgentStore(AgentState.RUNNING);
+
+    renderWithProviders(
+      <ServerStatus
+        conversationStatus="RUNNING"
+        handleStop={mockHandleStop}
+        handleResumeAgent={mockHandleResumeAgent}
+      />,
+    );
+
+    const statusContainer = screen.getByText("Running").closest("div");
+    await user.click(statusContainer!);
+
+    const stopButton = screen.getByTestId("stop-server-button");
+    await user.click(stopButton);
+
+    // Context menu should be closed (handled by the component)
+    expect(mockHandleStop).toHaveBeenCalledTimes(1);
+  });
+
+  it("should close context menu after start server action", async () => {
+    const user = userEvent.setup();
+
+    // Mock agent store to return STOPPED state
+    mockAgentStore(AgentState.STOPPED);
+
+    renderWithProviders(
+      <ServerStatus
+        conversationStatus="STOPPED"
+        handleStop={mockHandleStop}
+        handleResumeAgent={mockHandleResumeAgent}
+      />,
+    );
+
+    const statusContainer = screen.getByText("Server Stopped").closest("div");
+    await user.click(statusContainer!);
+
+    const startButton = screen.getByTestId("start-server-button");
+    await user.click(startButton);
+
+    // Context menu should be closed
+    expect(
+      screen.queryByTestId("server-status-context-menu"),
+    ).not.toBeInTheDocument();
   });
 
   it("should handle null conversation status", () => {
-    mockAgentStore(AgentState.RUNNING);
-
-    renderWithProviders(<ServerStatus conversationStatus={null} />);
-
-    expect(screen.getByTestId("server-status")).toBeInTheDocument();
-    expect(screen.getByText("Running")).toBeInTheDocument();
-  });
-
-  it("should apply custom className", () => {
+    // Mock agent store to return RUNNING state
     mockAgentStore(AgentState.RUNNING);
 
     renderWithProviders(
-      <ServerStatus conversationStatus="RUNNING" className="custom-class" />,
+      <ServerStatus
+        conversationStatus={null}
+        handleStop={mockHandleStop}
+        handleResumeAgent={mockHandleResumeAgent}
+      />,
     );
 
-    const container = screen.getByTestId("server-status");
-    expect(container).toHaveClass("custom-class");
+    const statusText = screen.getByText("Running");
+    expect(statusText).toBeInTheDocument();
   });
 });
 
 describe("ServerStatusContextMenu", () => {
-  // Helper function to mock agent state with specific state
-  const mockAgentStore = (agentState: AgentState) => {
-    vi.mocked(useAgentState).mockReturnValue({
-      curAgentState: agentState,
-    });
-  };
-
   const defaultProps = {
     onClose: vi.fn(),
     conversationStatus: "RUNNING" as ConversationStatus,
@@ -161,8 +346,6 @@ describe("ServerStatusContextMenu", () => {
   });
 
   it("should render stop server button when status is RUNNING", () => {
-    mockAgentStore(AgentState.RUNNING);
-
     renderWithProviders(
       <ServerStatusContextMenu
         {...defaultProps}
@@ -171,14 +354,11 @@ describe("ServerStatusContextMenu", () => {
       />,
     );
 
-    expect(screen.getByTestId("server-status")).toBeInTheDocument();
     expect(screen.getByTestId("stop-server-button")).toBeInTheDocument();
     expect(screen.getByText("Stop Runtime")).toBeInTheDocument();
   });
 
   it("should render start server button when status is STOPPED", () => {
-    mockAgentStore(AgentState.RUNNING);
-
     renderWithProviders(
       <ServerStatusContextMenu
         {...defaultProps}
@@ -187,14 +367,11 @@ describe("ServerStatusContextMenu", () => {
       />,
     );
 
-    expect(screen.getByTestId("server-status")).toBeInTheDocument();
     expect(screen.getByTestId("start-server-button")).toBeInTheDocument();
     expect(screen.getByText("Start Runtime")).toBeInTheDocument();
   });
 
   it("should not render stop server button when onStopServer is not provided", () => {
-    mockAgentStore(AgentState.RUNNING);
-
     renderWithProviders(
       <ServerStatusContextMenu
         {...defaultProps}
@@ -202,13 +379,10 @@ describe("ServerStatusContextMenu", () => {
       />,
     );
 
-    expect(screen.getByTestId("server-status")).toBeInTheDocument();
     expect(screen.queryByTestId("stop-server-button")).not.toBeInTheDocument();
   });
 
   it("should not render start server button when onStartServer is not provided", () => {
-    mockAgentStore(AgentState.RUNNING);
-
     renderWithProviders(
       <ServerStatusContextMenu
         {...defaultProps}
@@ -216,14 +390,12 @@ describe("ServerStatusContextMenu", () => {
       />,
     );
 
-    expect(screen.getByTestId("server-status")).toBeInTheDocument();
     expect(screen.queryByTestId("start-server-button")).not.toBeInTheDocument();
   });
 
   it("should call onStopServer when stop button is clicked", async () => {
     const user = userEvent.setup();
     const onStopServer = vi.fn();
-    mockAgentStore(AgentState.RUNNING);
 
     renderWithProviders(
       <ServerStatusContextMenu
@@ -242,7 +414,6 @@ describe("ServerStatusContextMenu", () => {
   it("should call onStartServer when start button is clicked", async () => {
     const user = userEvent.setup();
     const onStartServer = vi.fn();
-    mockAgentStore(AgentState.RUNNING);
 
     renderWithProviders(
       <ServerStatusContextMenu
@@ -259,8 +430,6 @@ describe("ServerStatusContextMenu", () => {
   });
 
   it("should render correct text content for stop server button", () => {
-    mockAgentStore(AgentState.RUNNING);
-
     renderWithProviders(
       <ServerStatusContextMenu
         {...defaultProps}
@@ -275,8 +444,6 @@ describe("ServerStatusContextMenu", () => {
   });
 
   it("should render correct text content for start server button", () => {
-    mockAgentStore(AgentState.RUNNING);
-
     renderWithProviders(
       <ServerStatusContextMenu
         {...defaultProps}
@@ -292,7 +459,6 @@ describe("ServerStatusContextMenu", () => {
 
   it("should call onClose when context menu is closed", () => {
     const onClose = vi.fn();
-    mockAgentStore(AgentState.RUNNING);
 
     renderWithProviders(
       <ServerStatusContextMenu
@@ -309,8 +475,6 @@ describe("ServerStatusContextMenu", () => {
   });
 
   it("should not render any buttons for other conversation statuses", () => {
-    mockAgentStore(AgentState.RUNNING);
-
     renderWithProviders(
       <ServerStatusContextMenu
         {...defaultProps}
@@ -318,7 +482,6 @@ describe("ServerStatusContextMenu", () => {
       />,
     );
 
-    expect(screen.getByTestId("server-status")).toBeInTheDocument();
     expect(screen.queryByTestId("stop-server-button")).not.toBeInTheDocument();
     expect(screen.queryByTestId("start-server-button")).not.toBeInTheDocument();
   });

frontend/__tests__/components/features/microagent-management/microagent-management.test.tsx

@@ -21,7 +21,6 @@ const mockUseConfig = vi.fn();
 const mockUseRepositoryMicroagents = vi.fn();
 const mockUseMicroagentManagementConversations = vi.fn();
 const mockUseSearchRepositories = vi.fn();
-const mockUseCreateConversationAndSubscribeMultiple = vi.fn();
 
 vi.mock("#/hooks/use-user-providers", () => ({
   useUserProviders: () => mockUseUserProviders(),
@@ -48,17 +47,6 @@ vi.mock("#/hooks/query/use-search-repositories", () => ({
   useSearchRepositories: () => mockUseSearchRepositories(),
 }));
 
-vi.mock("#/hooks/use-tracking", () => ({
-  useTracking: () => ({
-    trackEvent: vi.fn(),
-  }),
-}));
-
-vi.mock("#/hooks/use-create-conversation-and-subscribe-multiple", () => ({
-  useCreateConversationAndSubscribeMultiple: () =>
-    mockUseCreateConversationAndSubscribeMultiple(),
-}));
-
 describe("MicroagentManagement", () => {
   const RouterStub = createRoutesStub([
     {
@@ -321,16 +309,6 @@ describe("MicroagentManagement", () => {
       isError: false,
     });
 
-    mockUseCreateConversationAndSubscribeMultiple.mockReturnValue({
-      createConversationAndSubscribe: vi.fn(({ onSuccessCallback }) => {
-        // Immediately call the success callback to close the modal
-        if (onSuccessCallback) {
-          onSuccessCallback();
-        }
-      }),
-      isPending: false,
-    });
-
     // Mock the search repositories hook to return repositories with OpenHands suffixes
     const mockSearchResults =
       getRepositoriesWithOpenHandsSuffix(mockRepositories);

frontend/__tests__/components/image-preview.test.tsx

@@ -30,7 +30,7 @@ describe("ImagePreview", () => {
     expect(onRemoveMock).toHaveBeenCalledOnce();
   });
 
-  it("should not display the close button when onRemove is not provided", () => {
+  it("shoud not display the close button when onRemove is not provided", () => {
     render(<ImagePreview src="https://example.com/image.jpg" />);
     expect(screen.queryByRole("button")).not.toBeInTheDocument();
   });

frontend/__tests__/components/interactive-chat-box.test.tsx

@@ -108,16 +108,6 @@ describe("InteractiveChatBox", () => {
       options,
     );
 
-  // Helper function to render with Router context
-  const renderInteractiveChatBox = (props: any, options: any = {}) => {
-    return renderWithProviders(
-      <MemoryRouter>
-        <InteractiveChatBox {...props} />
-      </MemoryRouter>,
-      options,
-    );
-  };
-
   beforeAll(() => {
     global.URL.createObjectURL = vi
       .fn()

frontend/__tests__/hooks/use-websocket.test.ts

@@ -268,7 +268,7 @@ describe("useWebSocket", () => {
     });
 
     // onError handler should have been called
-    expect(onErrorSpy).toHaveBeenCalled();
+    expect(onErrorSpy).toHaveBeenCalledOnce();
   });
 
   it("should provide sendMessage function to send messages to WebSocket", async () => {

frontend/__tests__/routes/accept-tos.test.tsx

@@ -1,9 +1,10 @@
 import { render, screen } from "@testing-library/react";
 import { it, describe, expect, vi, beforeEach, afterEach } from "vitest";
 import userEvent from "@testing-library/user-event";
-import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
 import AcceptTOS from "#/routes/accept-tos";
 import * as CaptureConsent from "#/utils/handle-capture-consent";
+import * as ToastHandlers from "#/utils/custom-toast-handlers";
+import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
 import { openHands } from "#/api/open-hands-axios";
 
 // Mock the react-router hooks
@@ -43,13 +44,9 @@ const createWrapper = () => {
     },
   });
 
-  function Wrapper({ children }: { children: React.ReactNode }) {
-    return (
-      <QueryClientProvider client={queryClient}>{children}</QueryClientProvider>
-    );
-  }
-
-  return Wrapper;
+  return ({ children }: { children: React.ReactNode }) => (
+    <QueryClientProvider client={queryClient}>{children}</QueryClientProvider>
+  );
 };
 
 describe("AcceptTOS", () => {
@@ -109,10 +106,7 @@ describe("AcceptTOS", () => {
     // Wait for the mutation to complete
     await new Promise(process.nextTick);
 
-    expect(handleCaptureConsentSpy).toHaveBeenCalledWith(
-      expect.anything(),
-      true,
-    );
+    expect(handleCaptureConsentSpy).toHaveBeenCalledWith(true);
     expect(openHands.post).toHaveBeenCalledWith("/api/accept_tos", {
       redirect_url: "/dashboard",
     });

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

@@ -46,21 +46,6 @@ describe("Content", () => {
     });
   });
 
-  it("should render analytics toggle as enabled when server returns null (opt-in by default)", async () => {
-    const getSettingsSpy = vi.spyOn(SettingsService, "getSettings");
-    getSettingsSpy.mockResolvedValue({
-      ...MOCK_DEFAULT_USER_SETTINGS,
-      user_consents_to_analytics: null,
-    });
-
-    renderAppSettingsScreen();
-
-    await waitFor(() => {
-      const analytics = screen.getByTestId("enable-analytics-switch");
-      expect(analytics).toBeChecked();
-    });
-  });
-
   it("should render the language options", async () => {
     renderAppSettingsScreen();
 
@@ -178,10 +163,7 @@ describe("Form submission", () => {
     await userEvent.click(submit);
 
     await waitFor(() =>
-      expect(handleCaptureConsentsSpy).toHaveBeenCalledWith(
-        expect.anything(),
-        true,
-      ),
+      expect(handleCaptureConsentsSpy).toHaveBeenCalledWith(true),
     );
   });
 
@@ -206,10 +188,7 @@ describe("Form submission", () => {
     await userEvent.click(submit);
 
     await waitFor(() =>
-      expect(handleCaptureConsentsSpy).toHaveBeenCalledWith(
-        expect.anything(),
-        false,
-      ),
+      expect(handleCaptureConsentsSpy).toHaveBeenCalledWith(false),
     );
   });
 

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

@@ -10,19 +10,6 @@ import {
 } from "#/mocks/handlers";
 import * as AdvancedSettingsUtlls from "#/utils/has-advanced-settings-set";
 import * as ToastHandlers from "#/utils/custom-toast-handlers";
-import BillingService from "#/api/billing-service/billing-service.api";
-
-// Mock react-router hooks
-const mockUseSearchParams = vi.fn();
-vi.mock("react-router", () => ({
-  useSearchParams: () => mockUseSearchParams(),
-}));
-
-// Mock useIsAuthed hook
-const mockUseIsAuthed = vi.fn();
-vi.mock("#/hooks/query/use-is-authed", () => ({
-  useIsAuthed: () => mockUseIsAuthed(),
-}));
 
 // Mock react-router hooks
 const mockUseSearchParams = vi.fn();

frontend/__tests__/services/actions.test.tsx

@@ -28,14 +28,6 @@ vi.mock("#/state/security-analyzer-slice", () => ({
   appendSecurityAnalyzerInput: vi.fn(),
 }));
 
-vi.mock("#/state/metrics-slice", () => ({
-  setMetrics: vi.fn(),
-}));
-
-vi.mock("#/state/security-analyzer-slice", () => ({
-  appendSecurityAnalyzerInput: vi.fn(),
-}));
-
 describe("handleActionMessage", () => {
   beforeEach(() => {
     // Clear all mocks before each test

frontend/__tests__/utils/error-handler.test.ts

@@ -32,7 +32,6 @@ describe("Error Handler", () => {
       const error = {
         message: "Test error",
         source: "test",
-        posthog,
       };
 
       trackError(error);
@@ -53,7 +52,6 @@ describe("Error Handler", () => {
           extra: "info",
           details: { foo: "bar" },
         },
-        posthog,
       };
 
       trackError(error);
@@ -75,7 +73,6 @@ describe("Error Handler", () => {
       const error = {
         message: "Toast error",
         source: "toast-test",
-        posthog,
       };
 
       showErrorToast(error);
@@ -97,7 +94,6 @@ describe("Error Handler", () => {
         message: "Toast error",
         source: "toast-test",
         metadata: { context: "testing" },
-        posthog,
       };
 
       showErrorToast(error);
@@ -117,7 +113,6 @@ describe("Error Handler", () => {
         message: "Agent error",
         source: "agent-status",
         metadata: { id: "error.agent" },
-        posthog,
       });
 
       expect(posthog.captureException).toHaveBeenCalledWith(
@@ -132,7 +127,6 @@ describe("Error Handler", () => {
         message: "Server error",
         source: "server",
         metadata: { error_code: 500, details: "Internal error" },
-        posthog,
       });
 
       expect(posthog.captureException).toHaveBeenCalledWith(
@@ -151,7 +145,6 @@ describe("Error Handler", () => {
         message: error.message,
         source: "feedback",
         metadata: { conversationId: "123", error },
-        posthog,
       });
 
       expect(posthog.captureException).toHaveBeenCalledWith(
@@ -171,7 +164,6 @@ describe("Error Handler", () => {
         message: "Chat error",
         source: "chat-test",
         msgId: "123",
-        posthog,
       };
 
       showChatError(error);

frontend/__tests__/utils/handle-capture-consent.test.ts

@@ -13,14 +13,14 @@ describe("handleCaptureConsent", () => {
   });
 
   it("should opt out of of capturing", () => {
-    handleCaptureConsent(posthog, false);
+    handleCaptureConsent(false);
 
     expect(optOutSpy).toHaveBeenCalled();
     expect(optInSpy).not.toHaveBeenCalled();
   });
 
   it("should opt in to capturing if the user consents", () => {
-    handleCaptureConsent(posthog, true);
+    handleCaptureConsent(true);
 
     expect(optInSpy).toHaveBeenCalled();
     expect(optOutSpy).not.toHaveBeenCalled();
@@ -28,7 +28,7 @@ describe("handleCaptureConsent", () => {
 
   it("should not opt in to capturing if the user is already opted in", () => {
     hasOptedInSpy.mockReturnValueOnce(true);
-    handleCaptureConsent(posthog, true);
+    handleCaptureConsent(true);
 
     expect(optInSpy).not.toHaveBeenCalled();
     expect(optOutSpy).not.toHaveBeenCalled();
@@ -36,7 +36,7 @@ describe("handleCaptureConsent", () => {
 
   it("should not opt out of capturing if the user is already opted out", () => {
     hasOptedOutSpy.mockReturnValueOnce(true);
-    handleCaptureConsent(posthog, false);
+    handleCaptureConsent(false);
 
     expect(optOutSpy).not.toHaveBeenCalled();
     expect(optInSpy).not.toHaveBeenCalled();

frontend/__tests__/utils/status.test.ts

@@ -1,239 +0,0 @@
-import { describe, it, expect } from "vitest";
-import { getStatusCode, getIndicatorColor, IndicatorColor } from "#/utils/status";
-import { AgentState } from "#/types/agent-state";
-import { I18nKey } from "#/i18n/declaration";
-
-describe("getStatusCode", () => {
-  it("should prioritize agent readiness over stale runtime status", () => {
-    // Test case: Agent is ready (AWAITING_USER_INPUT) but runtime status is still starting
-    const result = getStatusCode(
-      { id: "", message: "", type: "info", status_update: true }, // statusMessage
-      "CONNECTED", // webSocketStatus
-      "RUNNING", // conversationStatus
-      "STATUS$STARTING_RUNTIME", // runtimeStatus (stale)
-      AgentState.AWAITING_USER_INPUT, // agentState (ready)
-    );
-
-    // Should return agent state message, not runtime status
-    expect(result).toBe(I18nKey.AGENT_STATUS$WAITING_FOR_TASK);
-  });
-
-  it("should show runtime status when agent is not ready", () => {
-    // Test case: Agent is loading and runtime is starting
-    const result = getStatusCode(
-      { id: "", message: "", type: "info", status_update: true }, // statusMessage
-      "CONNECTED", // webSocketStatus
-      "STARTING", // conversationStatus
-      "STATUS$STARTING_RUNTIME", // runtimeStatus
-      AgentState.LOADING, // agentState (not ready)
-    );
-
-    // Should return runtime status since agent is not ready
-    expect(result).toBe("STATUS$STARTING_RUNTIME");
-  });
-
-  it("should handle agent running state with stale runtime status", () => {
-    // Test case: Agent is running but runtime status is stale
-    const result = getStatusCode(
-      { id: "", message: "", type: "info", status_update: true }, // statusMessage
-      "CONNECTED", // webSocketStatus
-      "RUNNING", // conversationStatus
-      "STATUS$BUILDING_RUNTIME", // runtimeStatus (stale)
-      AgentState.RUNNING, // agentState (ready)
-    );
-
-    // Should return agent state message, not runtime status
-    expect(result).toBe(I18nKey.AGENT_STATUS$RUNNING_TASK);
-  });
-
-  it("should handle agent finished state with stale runtime status", () => {
-    // Test case: Agent is finished but runtime status is stale
-    const result = getStatusCode(
-      { id: "", message: "", type: "info", status_update: true }, // statusMessage
-      "CONNECTED", // webSocketStatus
-      "RUNNING", // conversationStatus
-      "STATUS$SETTING_UP_WORKSPACE", // runtimeStatus (stale)
-      AgentState.FINISHED, // agentState (ready)
-    );
-
-    // Should return agent state message, not runtime status
-    expect(result).toBe(I18nKey.AGENT_STATUS$WAITING_FOR_TASK);
-  });
-
-  it("should still respect stopped states", () => {
-    // Test case: Runtime is stopped - should always show stopped
-    const result = getStatusCode(
-      { id: "", message: "", type: "info", status_update: true }, // statusMessage
-      "CONNECTED", // webSocketStatus
-      "STOPPED", // conversationStatus
-      "STATUS$STOPPED", // runtimeStatus
-      AgentState.RUNNING, // agentState
-    );
-
-    // Should return stopped status regardless of agent state
-    expect(result).toBe(I18nKey.CHAT_INTERFACE$STOPPED);
-  });
-
-  it("should handle null agent state with runtime status", () => {
-    // Test case: No agent state, runtime is starting
-    const result = getStatusCode(
-      { id: "", message: "", type: "info", status_update: true }, // statusMessage
-      "CONNECTED", // webSocketStatus
-      "STARTING", // conversationStatus
-      "STATUS$STARTING_RUNTIME", // runtimeStatus
-      null, // agentState
-    );
-
-    // Should return runtime status since no agent state
-    expect(result).toBe("STATUS$STARTING_RUNTIME");
-  });
-
-  it("should prioritize task ERROR status over websocket CONNECTING state", () => {
-    // Test case: Task has errored but websocket is still trying to connect
-    const result = getStatusCode(
-      { id: "", message: "", type: "info", status_update: true }, // statusMessage
-      "CONNECTING", // webSocketStatus (stuck connecting)
-      null, // conversationStatus
-      null, // runtimeStatus
-      AgentState.LOADING, // agentState
-      "ERROR", // taskStatus (ERROR)
-    );
-
-    // Should return error message, not "Connecting..."
-    expect(result).toBe(I18nKey.AGENT_STATUS$ERROR_OCCURRED);
-  });
-
-  it("should show Connecting when task is working and websocket is connecting", () => {
-    // Test case: Task is in progress and websocket is connecting normally
-    const result = getStatusCode(
-      { id: "", message: "", type: "info", status_update: true }, // statusMessage
-      "CONNECTING", // webSocketStatus
-      null, // conversationStatus
-      null, // runtimeStatus
-      AgentState.LOADING, // agentState
-      "WORKING", // taskStatus (in progress)
-    );
-
-    // Should show connecting message since task hasn't errored
-    expect(result).toBe(I18nKey.CHAT_INTERFACE$CONNECTING);
-  });
-});
-
-describe("getIndicatorColor", () => {
-  it("should prioritize agent readiness over stale runtime status for AWAITING_USER_INPUT", () => {
-    // Test case: Agent is ready (AWAITING_USER_INPUT) but runtime status is still starting
-    const result = getIndicatorColor(
-      "CONNECTED", // webSocketStatus
-      "RUNNING", // conversationStatus
-      "STATUS$STARTING_RUNTIME", // runtimeStatus (stale)
-      AgentState.AWAITING_USER_INPUT, // agentState (ready)
-    );
-
-    // Should return blue for AWAITING_USER_INPUT, not yellow for stale runtime
-    expect(result).toBe(IndicatorColor.BLUE);
-  });
-
-  it("should prioritize agent readiness over stale runtime status for RUNNING", () => {
-    // Test case: Agent is running but runtime status is stale
-    const result = getIndicatorColor(
-      "CONNECTED", // webSocketStatus
-      "RUNNING", // conversationStatus
-      "STATUS$BUILDING_RUNTIME", // runtimeStatus (stale)
-      AgentState.RUNNING, // agentState (ready)
-    );
-
-    // Should return green for RUNNING, not yellow for stale runtime
-    expect(result).toBe(IndicatorColor.GREEN);
-  });
-
-  it("should prioritize agent readiness over stale runtime status for FINISHED", () => {
-    // Test case: Agent is finished but runtime status is stale
-    const result = getIndicatorColor(
-      "CONNECTED", // webSocketStatus
-      "RUNNING", // conversationStatus
-      "STATUS$SETTING_UP_WORKSPACE", // runtimeStatus (stale)
-      AgentState.FINISHED, // agentState (ready)
-    );
-
-    // Should return green for FINISHED, not yellow for stale runtime
-    expect(result).toBe(IndicatorColor.GREEN);
-  });
-
-  it("should show yellow when agent is not ready and runtime is starting", () => {
-    // Test case: Agent is loading and runtime is starting
-    const result = getIndicatorColor(
-      "CONNECTED", // webSocketStatus
-      "STARTING", // conversationStatus
-      "STATUS$STARTING_RUNTIME", // runtimeStatus
-      AgentState.LOADING, // agentState (not ready)
-    );
-
-    // Should return yellow since agent is not ready
-    expect(result).toBe(IndicatorColor.YELLOW);
-  });
-
-  it("should show orange for AWAITING_USER_CONFIRMATION even with stale runtime", () => {
-    // Test case: Agent is awaiting confirmation but runtime status is stale
-    const result = getIndicatorColor(
-      "CONNECTED", // webSocketStatus
-      "RUNNING", // conversationStatus
-      "STATUS$STARTING_RUNTIME", // runtimeStatus (stale)
-      AgentState.AWAITING_USER_CONFIRMATION, // agentState (ready)
-    );
-
-    // Should return orange for AWAITING_USER_CONFIRMATION, not yellow for stale runtime
-    expect(result).toBe(IndicatorColor.ORANGE);
-  });
-
-  it("should still respect stopped states", () => {
-    // Test case: Runtime is stopped - should always show red
-    const result = getIndicatorColor(
-      "CONNECTED", // webSocketStatus
-      "STOPPED", // conversationStatus
-      "STATUS$STOPPED", // runtimeStatus
-      AgentState.RUNNING, // agentState
-    );
-
-    // Should return red for stopped status regardless of agent state
-    expect(result).toBe(IndicatorColor.RED);
-  });
-
-  it("should handle null agent state with runtime status", () => {
-    // Test case: No agent state, runtime is starting
-    const result = getIndicatorColor(
-      "CONNECTED", // webSocketStatus
-      "STARTING", // conversationStatus
-      "STATUS$STARTING_RUNTIME", // runtimeStatus
-      null, // agentState
-    );
-
-    // Should return yellow since no agent state and runtime is starting
-    expect(result).toBe(IndicatorColor.YELLOW);
-  });
-
-  it("should handle USER_CONFIRMED state with stale runtime status", () => {
-    // Test case: Agent is in USER_CONFIRMED state but runtime status is stale
-    const result = getIndicatorColor(
-      "CONNECTED", // webSocketStatus
-      "RUNNING", // conversationStatus
-      "STATUS$BUILDING_RUNTIME", // runtimeStatus (stale)
-      AgentState.USER_CONFIRMED, // agentState (ready)
-    );
-
-    // Should return green for USER_CONFIRMED, not yellow for stale runtime
-    expect(result).toBe(IndicatorColor.GREEN);
-  });
-
-  it("should handle USER_REJECTED state with stale runtime status", () => {
-    // Test case: Agent is in USER_REJECTED state but runtime status is stale
-    const result = getIndicatorColor(
-      "CONNECTED", // webSocketStatus
-      "RUNNING", // conversationStatus
-      "STATUS$BUILDING_RUNTIME", // runtimeStatus (stale)
-      AgentState.USER_REJECTED, // agentState (ready)
-    );
-
-    // Should return green for USER_REJECTED, not yellow for stale runtime
-    expect(result).toBe(IndicatorColor.GREEN);
-  });
-});

frontend/package-lock.json

@@ -1,18 +1,17 @@
 {
   "name": "openhands-frontend",
-  "version": "0.62.0",
+  "version": "0.60.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "openhands-frontend",
-      "version": "0.62.0",
+      "version": "0.60.0",
       "dependencies": {
         "@heroui/react": "^2.8.4",
         "@heroui/use-infinite-scroll": "^2.2.11",
         "@microlink/react-json-view": "^1.26.2",
         "@monaco-editor/react": "^4.7.0-rc.0",
-        "@posthog/react": "^1.4.0",
         "@react-router/node": "^7.9.3",
         "@react-router/serve": "^7.9.3",
         "@react-types/shared": "^3.32.0",
@@ -39,7 +38,7 @@
         "jose": "^6.1.0",
         "lucide-react": "^0.544.0",
         "monaco-editor": "^0.53.0",
-        "posthog-js": "^1.290.0",
+        "posthog-js": "^1.268.8",
         "react": "^19.1.1",
         "react-dom": "^19.1.1",
         "react-highlight": "^0.15.0",
@@ -3512,29 +3511,9 @@
       "license": "MIT"
     },
     "node_modules/@posthog/core": {
-      "version": "1.5.2",
-      "resolved": "https://registry.npmjs.org/@posthog/core/-/core-1.5.2.tgz",
-      "integrity": "sha512-iedUP3EnOPPxTA2VaIrsrd29lSZnUV+ZrMnvY56timRVeZAXoYCkmjfIs3KBAsF8OUT5h1GXLSkoQdrV0r31OQ==",
-      "license": "MIT",
-      "dependencies": {
-        "cross-spawn": "^7.0.6"
-      }
-    },
-    "node_modules/@posthog/react": {
-      "version": "1.4.0",
-      "resolved": "https://registry.npmjs.org/@posthog/react/-/react-1.4.0.tgz",
-      "integrity": "sha512-xzPeZ753fQ0deZzdgY/0YavZvNpmdaxUzLYJYu5XjONNcZ8PwJnNLEK+7D/Cj8UM4Q8nWI7QC5mjum0uLWa4FA==",
-      "license": "MIT",
-      "peerDependencies": {
-        "@types/react": ">=16.8.0",
-        "posthog-js": ">=1.257.2",
-        "react": ">=16.8.0"
-      },
-      "peerDependenciesMeta": {
-        "@types/react": {
-          "optional": true
-        }
-      }
+      "version": "1.2.2",
+      "resolved": "https://registry.npmjs.org/@posthog/core/-/core-1.2.2.tgz",
+      "integrity": "sha512-f16Ozx6LIigRG+HsJdt+7kgSxZTHeX5f1JlCGKI1lXcvlZgfsCR338FuMI2QRYXGl+jg/vYFzGOTQBxl90lnBg=="
     },
     "node_modules/@react-aria/breadcrumbs": {
       "version": "3.5.28",
@@ -8204,6 +8183,7 @@
       "version": "7.0.6",
       "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.6.tgz",
       "integrity": "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA==",
+      "dev": true,
       "license": "MIT",
       "dependencies": {
         "path-key": "^3.1.0",
@@ -8218,6 +8198,7 @@
       "version": "2.0.2",
       "resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz",
       "integrity": "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA==",
+      "dev": true,
       "license": "ISC",
       "dependencies": {
         "isexe": "^2.0.0"
@@ -11422,6 +11403,7 @@
       "version": "2.0.0",
       "resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz",
       "integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==",
+      "dev": true,
       "license": "ISC"
     },
     "node_modules/istanbul-lib-coverage": {
@@ -14091,6 +14073,7 @@
       "version": "3.1.1",
       "resolved": "https://registry.npmjs.org/path-key/-/path-key-3.1.1.tgz",
       "integrity": "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q==",
+      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8"
@@ -14281,16 +14264,27 @@
       "license": "MIT"
     },
     "node_modules/posthog-js": {
-      "version": "1.290.0",
-      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.290.0.tgz",
-      "integrity": "sha512-zavBwZkf+3JeiSDVE7ZDXBfzva/iOljicdhdJH+cZoqp0LsxjKxjnNhGOd3KpAhw0wqdwjhd7Lp1aJuI7DXyaw==",
-      "license": "SEE LICENSE IN LICENSE",
+      "version": "1.268.8",
+      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.268.8.tgz",
+      "integrity": "sha512-BJiKK4MlUvs7ybnQcy1KkwAz+SZkE/wRLotetIoank5kbqZs8FLbeyozFvmmgx4aoMmaVymYBSmYphYjYQeidw==",
       "dependencies": {
-        "@posthog/core": "1.5.2",
+        "@posthog/core": "1.2.2",
         "core-js": "^3.38.1",
         "fflate": "^0.4.8",
         "preact": "^10.19.3",
         "web-vitals": "^4.2.4"
+      },
+      "peerDependencies": {
+        "@rrweb/types": "2.0.0-alpha.17",
+        "rrweb-snapshot": "2.0.0-alpha.17"
+      },
+      "peerDependenciesMeta": {
+        "@rrweb/types": {
+          "optional": true
+        },
+        "rrweb-snapshot": {
+          "optional": true
+        }
       }
     },
     "node_modules/posthog-js/node_modules/web-vitals": {
@@ -15553,6 +15547,7 @@
       "version": "2.0.0",
       "resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz",
       "integrity": "sha512-kHxr2zZpYtdmrN1qDjrrX/Z1rR1kG8Dx+gkpK1G4eXmvXswmcE1hTWBWYUzlraYw1/yZp6YuDY77YtvbN0dmDA==",
+      "dev": true,
       "license": "MIT",
       "dependencies": {
         "shebang-regex": "^3.0.0"
@@ -15565,6 +15560,7 @@
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/shebang-regex/-/shebang-regex-3.0.0.tgz",
       "integrity": "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==",
+      "dev": true,
       "license": "MIT",
       "engines": {
         "node": ">=8"

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.62.0",
+  "version": "0.60.0",
   "private": true,
   "type": "module",
   "engines": {
@@ -11,7 +11,6 @@
     "@heroui/use-infinite-scroll": "^2.2.11",
     "@microlink/react-json-view": "^1.26.2",
     "@monaco-editor/react": "^4.7.0-rc.0",
-    "@posthog/react": "^1.4.0",
     "@react-router/node": "^7.9.3",
     "@react-router/serve": "^7.9.3",
     "@react-types/shared": "^3.32.0",
@@ -38,7 +37,7 @@
     "jose": "^6.1.0",
     "lucide-react": "^0.544.0",
     "monaco-editor": "^0.53.0",
-    "posthog-js": "^1.290.0",
+    "posthog-js": "^1.268.8",
     "react": "^19.1.1",
     "react-dom": "^19.1.1",
     "react-highlight": "^0.15.0",

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

@@ -11,6 +11,7 @@ import type {
   V1AppConversationStartTask,
   V1AppConversationStartTaskPage,
   V1AppConversation,
+  V1SandboxInfo,
 } from "./v1-conversation-service.types";
 
 class V1ConversationService {
@@ -212,6 +213,36 @@ class V1ConversationService {
     return data;
   }
 
+  /**
+   * Pause a V1 sandbox
+   * Calls the /api/v1/sandboxes/{id}/pause endpoint
+   *
+   * @param sandboxId The sandbox ID to pause
+   * @returns Success response
+   */
+  static async pauseSandbox(sandboxId: string): Promise<{ success: boolean }> {
+    const { data } = await openHands.post<{ success: boolean }>(
+      `/api/v1/sandboxes/${sandboxId}/pause`,
+      {},
+    );
+    return data;
+  }
+
+  /**
+   * Resume a V1 sandbox
+   * Calls the /api/v1/sandboxes/{id}/resume endpoint
+   *
+   * @param sandboxId The sandbox ID to resume
+   * @returns Success response
+   */
+  static async resumeSandbox(sandboxId: string): Promise<{ success: boolean }> {
+    const { data } = await openHands.post<{ success: boolean }>(
+      `/api/v1/sandboxes/${sandboxId}/resume`,
+      {},
+    );
+    return data;
+  }
+
   /**
    * Batch get V1 app conversations by their IDs
    * Returns null for any missing conversations
@@ -238,6 +269,32 @@ class V1ConversationService {
     return data;
   }
 
+  /**
+   * Batch get V1 sandboxes by their IDs
+   * Returns null for any missing sandboxes
+   *
+   * @param ids Array of sandbox IDs (max 100)
+   * @returns Array of sandboxes or null for missing ones
+   */
+  static async batchGetSandboxes(
+    ids: string[],
+  ): Promise<(V1SandboxInfo | null)[]> {
+    if (ids.length === 0) {
+      return [];
+    }
+    if (ids.length > 100) {
+      throw new Error("Cannot request more than 100 sandboxes at once");
+    }
+
+    const params = new URLSearchParams();
+    ids.forEach((id) => params.append("id", id));
+
+    const { data } = await openHands.get<(V1SandboxInfo | null)[]>(
+      `/api/v1/sandboxes?${params.toString()}`,
+    );
+    return data;
+  }
+
   /**
    * Upload a single file to the V1 conversation workspace
    * V1 API endpoint: POST /api/file/upload/{path}
@@ -288,6 +345,24 @@ class V1ConversationService {
     const { data } = await openHands.get<{ runtime_id: string }>(url);
     return data;
   }
+
+  /**
+   * Get the count of events for a conversation
+   * Uses the V1 API endpoint: GET /api/v1/events/count
+   *
+   * @param conversationId The conversation ID to get event count for
+   * @returns The number of events in the conversation
+   */
+  static async getEventCount(conversationId: string): Promise<number> {
+    const params = new URLSearchParams();
+    params.append("conversation_id__eq", conversationId);
+
+    const { data } = await openHands.get<number>(
+      `/api/v1/events/count?${params.toString()}`,
+    );
+
+    return data;
+  }
 }
 
 export default V1ConversationService;

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

@@ -1,6 +1,5 @@
 import { ConversationTrigger } from "../open-hands.types";
 import { Provider } from "#/types/settings";
-import { V1SandboxStatus } from "../sandbox-service/sandbox-service.types";
 
 // V1 API Types for requests
 // Note: This represents the serialized API format, not the internal TextContent/ImageContent types
@@ -65,7 +64,14 @@ export interface V1AppConversationStartTaskPage {
   next_page_id: string | null;
 }
 
-export type V1ConversationExecutionStatus =
+export type V1SandboxStatus =
+  | "MISSING"
+  | "STARTING"
+  | "RUNNING"
+  | "STOPPED"
+  | "PAUSED";
+
+export type V1AgentExecutionStatus =
   | "RUNNING"
   | "AWAITING_USER_INPUT"
   | "AWAITING_USER_CONFIRMATION"
@@ -88,7 +94,22 @@ export interface V1AppConversation {
   created_at: string;
   updated_at: string;
   sandbox_status: V1SandboxStatus;
-  execution_status: V1ConversationExecutionStatus | null;
+  agent_status: V1AgentExecutionStatus | null;
   conversation_url: string | null;
   session_api_key: string | null;
 }
+
+export interface V1ExposedUrl {
+  name: string;
+  url: string;
+}
+
+export interface V1SandboxInfo {
+  id: string;
+  created_by_user_id: string | null;
+  sandbox_spec_id: string;
+  status: V1SandboxStatus;
+  session_api_key: string | null;
+  exposed_urls: V1ExposedUrl[] | null;
+  created_at: string;
+}

frontend/src/api/event-service/event-service.api.ts

@@ -5,7 +5,6 @@ import type {
   ConfirmationResponseRequest,
   ConfirmationResponseResponse,
 } from "./event-service.types";
-import { openHands } from "../open-hands-axios";
 
 class EventService {
   /**
@@ -37,14 +36,6 @@ class EventService {
 
     return data;
   }
-
-  static async getEventCount(conversationId: string): Promise<number> {
-    const params = new URLSearchParams();
-    params.append("conversation_id__eq", conversationId);
-    const { data } = await openHands.get<number>(
-      `/api/v1/events/count?${params.toString()}`,
-    );
-    return data;
-  }
 }
+
 export default EventService;

frontend/src/api/sandbox-service/sandbox-service.api.ts

@@ -1,52 +0,0 @@
-// sandbox-service.api.ts
-// This file contains API methods for /api/v1/sandboxes endpoints.
-
-import { openHands } from "../open-hands-axios";
-import type { V1SandboxInfo } from "./sandbox-service.types";
-
-export class SandboxService {
-  /**
-   * Pause a V1 sandbox
-   * Calls the /api/v1/sandboxes/{id}/pause endpoint
-   */
-  static async pauseSandbox(sandboxId: string): Promise<{ success: boolean }> {
-    const { data } = await openHands.post<{ success: boolean }>(
-      `/api/v1/sandboxes/${sandboxId}/pause`,
-      {},
-    );
-    return data;
-  }
-
-  /**
-   * Resume a V1 sandbox
-   * Calls the /api/v1/sandboxes/{id}/resume endpoint
-   */
-  static async resumeSandbox(sandboxId: string): Promise<{ success: boolean }> {
-    const { data } = await openHands.post<{ success: boolean }>(
-      `/api/v1/sandboxes/${sandboxId}/resume`,
-      {},
-    );
-    return data;
-  }
-
-  /**
-   * Batch get V1 sandboxes by their IDs
-   * Returns null for any missing sandboxes
-   */
-  static async batchGetSandboxes(
-    ids: string[],
-  ): Promise<(V1SandboxInfo | null)[]> {
-    if (ids.length === 0) {
-      return [];
-    }
-    if (ids.length > 100) {
-      throw new Error("Cannot request more than 100 sandboxes at once");
-    }
-    const params = new URLSearchParams();
-    ids.forEach((id) => params.append("id", id));
-    const { data } = await openHands.get<(V1SandboxInfo | null)[]>(
-      `/api/v1/sandboxes?${params.toString()}`,
-    );
-    return data;
-  }
-}

frontend/src/api/sandbox-service/sandbox-service.types.ts

@@ -1,24 +0,0 @@
-// sandbox-service.types.ts
-// This file contains types for Sandbox API.
-
-export type V1SandboxStatus =
-  | "MISSING"
-  | "STARTING"
-  | "RUNNING"
-  | "STOPPED"
-  | "PAUSED";
-
-export interface V1ExposedUrl {
-  name: string;
-  url: string;
-}
-
-export interface V1SandboxInfo {
-  id: string;
-  created_by_user_id: string | null;
-  sandbox_spec_id: string;
-  status: V1SandboxStatus;
-  session_api_key: string | null;
-  exposed_urls: V1ExposedUrl[] | null;
-  created_at: string;
-}

frontend/src/components/features/analytics/analytics-consent-form-modal.tsx

@@ -1,5 +1,4 @@
 import { useTranslation } from "react-i18next";
-import { usePostHog } from "posthog-js/react";
 import {
   BaseModalTitle,
   BaseModalDescription,
@@ -18,7 +17,6 @@ interface AnalyticsConsentFormModalProps {
 export function AnalyticsConsentFormModal({
   onClose,
 }: AnalyticsConsentFormModalProps) {
-  const posthog = usePostHog();
   const { t } = useTranslation();
   const { mutate: saveUserSettings } = useSaveSettings();
 
@@ -31,7 +29,7 @@ export function AnalyticsConsentFormModal({
       { user_consents_to_analytics: analytics },
       {
         onSuccess: () => {
-          handleCaptureConsent(posthog, analytics);
+          handleCaptureConsent(analytics);
           onClose();
         },
       },

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

@@ -1,109 +0,0 @@
-import React, { useMemo, useEffect } from "react";
-import { useTranslation } from "react-i18next";
-import { Typography } from "#/ui/typography";
-import { I18nKey } from "#/i18n/declaration";
-import CodeTagIcon from "#/icons/code-tag.svg?react";
-import ChevronDownSmallIcon from "#/icons/chevron-down-small.svg?react";
-import LessonPlanIcon from "#/icons/lesson-plan.svg?react";
-import { useConversationStore } from "#/state/conversation-store";
-import { ChangeAgentContextMenu } from "./change-agent-context-menu";
-import { cn } from "#/utils/utils";
-import { USE_PLANNING_AGENT } from "#/utils/feature-flags";
-import { useAgentState } from "#/hooks/use-agent-state";
-import { AgentState } from "#/types/agent-state";
-
-export function ChangeAgentButton() {
-  const { t } = useTranslation();
-  const [contextMenuOpen, setContextMenuOpen] = React.useState(false);
-
-  const conversationMode = useConversationStore(
-    (state) => state.conversationMode,
-  );
-
-  const setConversationMode = useConversationStore(
-    (state) => state.setConversationMode,
-  );
-
-  const shouldUsePlanningAgent = USE_PLANNING_AGENT();
-
-  const { curAgentState } = useAgentState();
-
-  const isAgentRunning = curAgentState === AgentState.RUNNING;
-
-  // Close context menu when agent starts running
-  useEffect(() => {
-    if (isAgentRunning && contextMenuOpen) {
-      setContextMenuOpen(false);
-    }
-  }, [isAgentRunning, contextMenuOpen]);
-
-  const handleButtonClick = (event: React.MouseEvent<HTMLButtonElement>) => {
-    event.preventDefault();
-    event.stopPropagation();
-    setContextMenuOpen(!contextMenuOpen);
-  };
-
-  const handleCodeClick = (event: React.MouseEvent<HTMLButtonElement>) => {
-    event.preventDefault();
-    event.stopPropagation();
-    setConversationMode("code");
-  };
-
-  const handlePlanClick = (event: React.MouseEvent<HTMLButtonElement>) => {
-    event.preventDefault();
-    event.stopPropagation();
-    setConversationMode("plan");
-  };
-
-  const isExecutionAgent = conversationMode === "code";
-
-  const buttonLabel = useMemo(() => {
-    if (isExecutionAgent) {
-      return t(I18nKey.COMMON$CODE);
-    }
-    return t(I18nKey.COMMON$PLAN);
-  }, [isExecutionAgent, t]);
-
-  const buttonIcon = useMemo(() => {
-    if (isExecutionAgent) {
-      return <CodeTagIcon width={18} height={18} color="#737373" />;
-    }
-    return <LessonPlanIcon width={18} height={18} color="#ffffff" />;
-  }, [isExecutionAgent]);
-
-  if (!shouldUsePlanningAgent) {
-    return null;
-  }
-
-  return (
-    <div className="relative">
-      <button
-        type="button"
-        onClick={handleButtonClick}
-        disabled={isAgentRunning}
-        className={cn(
-          "flex items-center border border-[#4B505F] rounded-[100px] transition-opacity",
-          !isExecutionAgent && "border-[#597FF4] bg-[#4A67BD]",
-          isAgentRunning
-            ? "opacity-50 cursor-not-allowed"
-            : "cursor-pointer hover:opacity-80",
-        )}
-      >
-        <div className="flex items-center gap-1 pl-1.5">
-          {buttonIcon}
-          <Typography.Text className="text-white text-2.75 not-italic font-normal leading-5">
-            {buttonLabel}
-          </Typography.Text>
-        </div>
-        <ChevronDownSmallIcon width={24} height={24} color="#ffffff" />
-      </button>
-      {contextMenuOpen && (
-        <ChangeAgentContextMenu
-          onClose={() => setContextMenuOpen(false)}
-          onCodeClick={handleCodeClick}
-          onPlanClick={handlePlanClick}
-        />
-      )}
-    </div>
-  );
-}

frontend/src/components/features/chat/change-agent-context-menu.tsx

@@ -1,81 +0,0 @@
-import React from "react";
-import { useTranslation } from "react-i18next";
-import { I18nKey } from "#/i18n/declaration";
-import CodeTagIcon from "#/icons/code-tag.svg?react";
-import LessonPlanIcon from "#/icons/lesson-plan.svg?react";
-import { ContextMenu } from "#/ui/context-menu";
-import { ContextMenuListItem } from "../context-menu/context-menu-list-item";
-import { ContextMenuIconText } from "../context-menu/context-menu-icon-text";
-import { useClickOutsideElement } from "#/hooks/use-click-outside-element";
-import { cn } from "#/utils/utils";
-import { CONTEXT_MENU_ICON_TEXT_CLASSNAME } from "#/utils/constants";
-
-const contextMenuListItemClassName = cn(
-  "cursor-pointer p-0 h-auto hover:bg-transparent",
-  CONTEXT_MENU_ICON_TEXT_CLASSNAME,
-);
-
-const contextMenuIconTextClassName =
-  "gap-2 p-2 hover:bg-[#5C5D62] rounded h-[30px]";
-
-interface ChangeAgentContextMenuProps {
-  onClose: () => void;
-  onCodeClick?: (event: React.MouseEvent<HTMLButtonElement>) => void;
-  onPlanClick?: (event: React.MouseEvent<HTMLButtonElement>) => void;
-}
-
-export function ChangeAgentContextMenu({
-  onClose,
-  onCodeClick,
-  onPlanClick,
-}: ChangeAgentContextMenuProps) {
-  const { t } = useTranslation();
-  const menuRef = useClickOutsideElement<HTMLUListElement>(onClose);
-
-  const handleCodeClick = (event: React.MouseEvent<HTMLButtonElement>) => {
-    event.preventDefault();
-    event.stopPropagation();
-    onCodeClick?.(event);
-    onClose();
-  };
-
-  const handlePlanClick = (event: React.MouseEvent<HTMLButtonElement>) => {
-    event.preventDefault();
-    event.stopPropagation();
-    onPlanClick?.(event);
-    onClose();
-  };
-
-  return (
-    <ContextMenu
-      ref={menuRef}
-      testId="change-agent-context-menu"
-      position="top"
-      alignment="left"
-      className="min-h-fit min-w-[195px] mb-2"
-    >
-      <ContextMenuListItem
-        testId="code-option"
-        onClick={handleCodeClick}
-        className={contextMenuListItemClassName}
-      >
-        <ContextMenuIconText
-          icon={CodeTagIcon}
-          text={t(I18nKey.COMMON$CODE)}
-          className={contextMenuIconTextClassName}
-        />
-      </ContextMenuListItem>
-      <ContextMenuListItem
-        testId="plan-option"
-        onClick={handlePlanClick}
-        className={contextMenuListItemClassName}
-      >
-        <ContextMenuIconText
-          icon={LessonPlanIcon}
-          text={t(I18nKey.COMMON$PLAN)}
-          className={contextMenuIconTextClassName}
-        />
-      </ContextMenuListItem>
-    </ContextMenu>
-  );
-}

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

@@ -1,5 +1,5 @@
 import React from "react";
-import { usePostHog } from "posthog-js/react";
+import posthog from "posthog-js";
 import { useParams } from "react-router";
 import { useTranslation } from "react-i18next";
 import { convertImageToBase64 } from "#/utils/convert-image-to-base-64";
@@ -60,7 +60,6 @@ function getEntryPoint(
 }
 
 export function ChatInterface() {
-  const posthog = usePostHog();
   const { setMessageToSend } = useConversationStore();
   const { data: conversation } = useActiveConversation();
   const { errorMessage } = useErrorMessageStore();
@@ -98,29 +97,24 @@ export function ChatInterface() {
 
   const isV1Conversation = conversation?.conversation_version === "V1";
 
-  // Track when we should show V1 messages (after DOM has rendered)
-  const [showV1Messages, setShowV1Messages] = React.useState(false);
-  const prevV1LoadingRef = React.useRef(
+  // Instantly scroll to bottom when history loading completes
+  const prevLoadingHistoryRef = React.useRef(
     conversationWebSocket?.isLoadingHistory,
   );
-
-  // Wait for DOM to render before showing V1 messages
   React.useEffect(() => {
-    const wasLoading = prevV1LoadingRef.current;
+    const wasLoading = prevLoadingHistoryRef.current;
     const isLoading = conversationWebSocket?.isLoadingHistory;
 
-    if (wasLoading && !isLoading) {
-      // Loading just finished - wait for next frame to ensure DOM is ready
-      requestAnimationFrame(() => {
-        setShowV1Messages(true);
+    // When history loading transitions from true to false, instantly scroll to bottom
+    if (wasLoading && !isLoading && scrollRef.current) {
+      scrollRef.current.scrollTo({
+        top: scrollRef.current.scrollHeight,
+        behavior: "instant",
       });
-    } else if (isLoading) {
-      // Reset when loading starts
-      setShowV1Messages(false);
     }
 
-    prevV1LoadingRef.current = isLoading;
-  }, [conversationWebSocket?.isLoadingHistory]);
+    prevLoadingHistoryRef.current = isLoading;
+  }, [conversationWebSocket?.isLoadingHistory, scrollRef]);
 
   // Filter V0 events
   const v0Events = storeEvents
@@ -258,7 +252,7 @@ export function ChatInterface() {
             </div>
           )}
 
-          {(conversationWebSocket?.isLoadingHistory || !showV1Messages) &&
+          {conversationWebSocket?.isLoadingHistory &&
             isV1Conversation &&
             !isTask && (
               <div className="flex justify-center">
@@ -275,7 +269,7 @@ export function ChatInterface() {
             />
           )}
 
-          {showV1Messages && v1UserEventsExist && (
+          {!conversationWebSocket?.isLoadingHistory && v1UserEventsExist && (
             <V1Messages messages={v1UiEvents} allEvents={v1FullEvents} />
           )}
         </div>

frontend/src/components/features/chat/components/chat-input-actions.tsx

@@ -1,33 +1,45 @@
+import { ConversationStatus } from "#/types/conversation-status";
+import { ServerStatus } from "#/components/features/controls/server-status";
 import { AgentStatus } from "#/components/features/controls/agent-status";
 import { Tools } from "../../controls/tools";
 import { useUnifiedPauseConversationSandbox } from "#/hooks/mutation/use-unified-stop-conversation";
 import { useConversationId } from "#/hooks/use-conversation-id";
+import { useUnifiedResumeConversationSandbox } from "#/hooks/mutation/use-unified-start-conversation";
+import { useUserProviders } from "#/hooks/use-user-providers";
 import { useActiveConversation } from "#/hooks/query/use-active-conversation";
 import { useSendMessage } from "#/hooks/use-send-message";
 import { generateAgentStateChangeEvent } from "#/services/agent-state-service";
 import { AgentState } from "#/types/agent-state";
 import { useV1PauseConversation } from "#/hooks/mutation/use-v1-pause-conversation";
 import { useV1ResumeConversation } from "#/hooks/mutation/use-v1-resume-conversation";
-import { ChangeAgentButton } from "../change-agent-button";
 
 interface ChatInputActionsProps {
+  conversationStatus: ConversationStatus | null;
   disabled: boolean;
   handleResumeAgent: () => void;
 }
 
 export function ChatInputActions({
+  conversationStatus,
   disabled,
   handleResumeAgent,
 }: ChatInputActionsProps) {
   const { data: conversation } = useActiveConversation();
   const pauseConversationSandboxMutation = useUnifiedPauseConversationSandbox();
+  const resumeConversationSandboxMutation =
+    useUnifiedResumeConversationSandbox();
   const v1PauseConversationMutation = useV1PauseConversation();
   const v1ResumeConversationMutation = useV1ResumeConversation();
   const { conversationId } = useConversationId();
+  const { providers } = useUserProviders();
   const { send } = useSendMessage();
 
   const isV1Conversation = conversation?.conversation_version === "V1";
 
+  const handleStopClick = () => {
+    pauseConversationSandboxMutation.mutate({ conversationId });
+  };
+
   const handlePauseAgent = () => {
     if (isV1Conversation) {
       // V1: Pause the conversation (agent execution)
@@ -50,6 +62,10 @@ export function ChatInputActions({
     handleResumeAgent();
   };
 
+  const handleStartClick = () => {
+    resumeConversationSandboxMutation.mutate({ conversationId, providers });
+  };
+
   const isPausing =
     pauseConversationSandboxMutation.isPending ||
     v1PauseConversationMutation.isPending;
@@ -57,10 +73,13 @@ export function ChatInputActions({
   return (
     <div className="w-full flex items-center justify-between">
       <div className="flex items-center gap-1">
-        <div className="flex items-center gap-4">
-          <Tools />
-          <ChangeAgentButton />
-        </div>
+        <Tools />
+        <ServerStatus
+          conversationStatus={conversationStatus}
+          isPausing={isPausing}
+          handleStop={handleStopClick}
+          handleResumeAgent={handleStartClick}
+        />
       </div>
       <AgentStatus
         className="ml-2 md:ml-3"

frontend/src/components/features/chat/components/chat-input-container.tsx

@@ -1,10 +1,9 @@
 import React from "react";
+import { ConversationStatus } from "#/types/conversation-status";
 import { DragOver } from "../drag-over";
 import { UploadedFiles } from "../uploaded-files";
 import { ChatInputRow } from "./chat-input-row";
 import { ChatInputActions } from "./chat-input-actions";
-import { useConversationStore } from "#/state/conversation-store";
-import { cn } from "#/utils/utils";
 
 interface ChatInputContainerProps {
   chatContainerRef: React.RefObject<HTMLDivElement | null>;
@@ -12,6 +11,7 @@ interface ChatInputContainerProps {
   disabled: boolean;
   showButton: boolean;
   buttonClassName: string;
+  conversationStatus: ConversationStatus | null;
   chatInputRef: React.RefObject<HTMLDivElement | null>;
   handleFileIconClick: (isDisabled: boolean) => void;
   handleSubmit: () => void;
@@ -32,6 +32,7 @@ export function ChatInputContainer({
   disabled,
   showButton,
   buttonClassName,
+  conversationStatus,
   chatInputRef,
   handleFileIconClick,
   handleSubmit,
@@ -45,17 +46,10 @@ export function ChatInputContainer({
   onFocus,
   onBlur,
 }: ChatInputContainerProps) {
-  const conversationMode = useConversationStore(
-    (state) => state.conversationMode,
-  );
-
   return (
     <div
       ref={chatContainerRef}
-      className={cn(
-        "bg-[#25272D] box-border content-stretch flex flex-col items-start justify-center p-4 pt-3 relative rounded-[15px] w-full",
-        conversationMode === "plan" && "border border-[#597FF4]",
-      )}
+      className="bg-[#25272D] box-border content-stretch flex flex-col items-start justify-center p-4 pt-3 relative rounded-[15px] w-full"
       onDragOver={(e) => onDragOver(e, disabled)}
       onDragLeave={(e) => onDragLeave(e, disabled)}
       onDrop={(e) => onDrop(e, disabled)}
@@ -80,6 +74,7 @@ export function ChatInputContainer({
       />
 
       <ChatInputActions
+        conversationStatus={conversationStatus}
         disabled={disabled}
         handleResumeAgent={handleResumeAgent}
       />

frontend/src/components/features/chat/components/chat-input-field.tsx

@@ -1,7 +1,5 @@
 import React from "react";
 import { useTranslation } from "react-i18next";
-import { I18nKey } from "#/i18n/declaration";
-import { useConversationStore } from "#/state/conversation-store";
 
 interface ChatInputFieldProps {
   chatInputRef: React.RefObject<HTMLDivElement | null>;
@@ -22,12 +20,6 @@ export function ChatInputField({
 }: ChatInputFieldProps) {
   const { t } = useTranslation();
 
-  const conversationMode = useConversationStore(
-    (state) => state.conversationMode,
-  );
-
-  const isPlanMode = conversationMode === "plan";
-
   return (
     <div
       className="box-border content-stretch flex flex-row items-center justify-start min-h-6 p-0 relative shrink-0 flex-1"
@@ -38,11 +30,7 @@ export function ChatInputField({
           ref={chatInputRef}
           className="chat-input bg-transparent text-white text-[16px] font-normal leading-[20px] outline-none resize-none custom-scrollbar min-h-[20px] max-h-[400px] [text-overflow:inherit] [text-wrap-mode:inherit] [white-space-collapse:inherit] block whitespace-pre-wrap"
           contentEditable
-          data-placeholder={
-            isPlanMode
-              ? t(I18nKey.COMMON$LET_S_WORK_ON_A_PLAN)
-              : t(I18nKey.SUGGESTIONS$WHAT_TO_BUILD)
-          }
+          data-placeholder={t("SUGGESTIONS$WHAT_TO_BUILD")}
           data-testid="chat-input"
           onInput={onInput}
           onPaste={onPaste}

frontend/src/components/features/chat/custom-chat-input.tsx

@@ -137,6 +137,7 @@ export function CustomChatInput({
           disabled={isDisabled}
           showButton={showButton}
           buttonClassName={buttonClassName}
+          conversationStatus={conversationStatus}
           chatInputRef={chatInputRef}
           handleFileIconClick={handleFileIconClick}
           handleSubmit={handleSubmit}

frontend/src/components/features/chat/event-message-components/task-tracking-event-message.tsx

@@ -1,7 +1,11 @@
+import React from "react";
+import { useTranslation } from "react-i18next";
 import { OpenHandsObservation } from "#/types/core/observations";
 import { isTaskTrackingObservation } from "#/types/core/guards";
+import { GenericEventMessage } from "../generic-event-message";
 import { TaskTrackingObservationContent } from "../task-tracking-observation-content";
 import { ConfirmationButtons } from "#/components/shared/buttons/confirmation-buttons";
+import { getObservationResult } from "../event-content-helpers/get-observation-result";
 
 interface TaskTrackingEventMessageProps {
   event: OpenHandsObservation;
@@ -12,13 +16,34 @@ export function TaskTrackingEventMessage({
   event,
   shouldShowConfirmationButtons,
 }: TaskTrackingEventMessageProps) {
+  const { t } = useTranslation();
+
   if (!isTaskTrackingObservation(event)) {
     return null;
   }
 
+  const { command } = event.extras;
+  let title: React.ReactNode;
+  let initiallyExpanded = false;
+
+  // Determine title and expansion state based on command
+  if (command === "plan") {
+    title = t("OBSERVATION_MESSAGE$TASK_TRACKING_PLAN");
+    initiallyExpanded = true;
+  } else {
+    // command === "view"
+    title = t("OBSERVATION_MESSAGE$TASK_TRACKING_VIEW");
+    initiallyExpanded = false;
+  }
+
   return (
     <div>
-      <TaskTrackingObservationContent event={event} />
+      <GenericEventMessage
+        title={title}
+        details={<TaskTrackingObservationContent event={event} />}
+        success={getObservationResult(event)}
+        initiallyExpanded={initiallyExpanded}
+      />
       {shouldShowConfirmationButtons && <ConfirmationButtons />}
     </div>
   );

frontend/src/components/features/chat/git-control-bar-pr-button.tsx

@@ -1,10 +1,10 @@
 import { useTranslation } from "react-i18next";
+import posthog from "posthog-js";
 import PRIcon from "#/icons/u-pr.svg?react";
 import { cn, getCreatePRPrompt } from "#/utils/utils";
 import { useUserProviders } from "#/hooks/use-user-providers";
 import { I18nKey } from "#/i18n/declaration";
 import { Provider } from "#/types/settings";
-import { useTracking } from "#/hooks/use-tracking";
 
 interface GitControlBarPrButtonProps {
   onSuggestionsClick: (value: string) => void;
@@ -20,7 +20,6 @@ export function GitControlBarPrButton({
   isConversationReady = true,
 }: GitControlBarPrButtonProps) {
   const { t } = useTranslation();
-  const { trackCreatePrButtonClick } = useTracking();
 
   const { providers } = useUserProviders();
 
@@ -29,7 +28,7 @@ export function GitControlBarPrButton({
     providersAreSet && hasRepository && isConversationReady;
 
   const handlePrClick = () => {
-    trackCreatePrButtonClick();
+    posthog.capture("create_pr_button_clicked");
     onSuggestionsClick(getCreatePRPrompt(currentGitProvider));
   };
 

frontend/src/components/features/chat/git-control-bar-pull-button.tsx

@@ -1,10 +1,10 @@
 import { useTranslation } from "react-i18next";
+import posthog from "posthog-js";
 import ArrowDownIcon from "#/icons/u-arrow-down.svg?react";
 import { cn, getGitPullPrompt } from "#/utils/utils";
 import { useActiveConversation } from "#/hooks/query/use-active-conversation";
 import { useUserProviders } from "#/hooks/use-user-providers";
 import { I18nKey } from "#/i18n/declaration";
-import { useTracking } from "#/hooks/use-tracking";
 
 interface GitControlBarPullButtonProps {
   onSuggestionsClick: (value: string) => void;
@@ -16,7 +16,6 @@ export function GitControlBarPullButton({
   isConversationReady = true,
 }: GitControlBarPullButtonProps) {
   const { t } = useTranslation();
-  const { trackPullButtonClick } = useTracking();
 
   const { data: conversation } = useActiveConversation();
   const { providers } = useUserProviders();
@@ -27,7 +26,7 @@ export function GitControlBarPullButton({
     providersAreSet && hasRepository && isConversationReady;
 
   const handlePullClick = () => {
-    trackPullButtonClick();
+    posthog.capture("pull_button_clicked");
     onSuggestionsClick(getGitPullPrompt());
   };
 

frontend/src/components/features/chat/git-control-bar-push-button.tsx

@@ -1,10 +1,10 @@
 import { useTranslation } from "react-i18next";
+import posthog from "posthog-js";
 import ArrowUpIcon from "#/icons/u-arrow-up.svg?react";
 import { cn, getGitPushPrompt } from "#/utils/utils";
 import { useUserProviders } from "#/hooks/use-user-providers";
 import { I18nKey } from "#/i18n/declaration";
 import { Provider } from "#/types/settings";
-import { useTracking } from "#/hooks/use-tracking";
 
 interface GitControlBarPushButtonProps {
   onSuggestionsClick: (value: string) => void;
@@ -20,7 +20,6 @@ export function GitControlBarPushButton({
   isConversationReady = true,
 }: GitControlBarPushButtonProps) {
   const { t } = useTranslation();
-  const { trackPushButtonClick } = useTracking();
 
   const { providers } = useUserProviders();
 
@@ -29,7 +28,7 @@ export function GitControlBarPushButton({
     providersAreSet && hasRepository && isConversationReady;
 
   const handlePushClick = () => {
-    trackPushButtonClick();
+    posthog.capture("push_button_clicked");
     onSuggestionsClick(getGitPushPrompt(currentGitProvider));
   };
 

frontend/src/components/features/chat/plan-preview.tsx

@@ -1,82 +0,0 @@
-import { useTranslation } from "react-i18next";
-import { ArrowUpRight } from "lucide-react";
-import LessonPlanIcon from "#/icons/lesson-plan.svg?react";
-import { USE_PLANNING_AGENT } from "#/utils/feature-flags";
-import { Typography } from "#/ui/typography";
-import { I18nKey } from "#/i18n/declaration";
-
-interface PlanPreviewProps {
-  title?: string;
-  description?: string;
-  onViewClick?: () => void;
-  onBuildClick?: () => void;
-}
-
-// TODO: Remove the hardcoded values and use the plan content from the conversation store
-/* eslint-disable i18next/no-literal-string */
-export function PlanPreview({
-  title = "Improve Developer Onboarding and Examples",
-  description = "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...",
-  onViewClick,
-  onBuildClick,
-}: PlanPreviewProps) {
-  const { t } = useTranslation();
-
-  const shouldUsePlanningAgent = USE_PLANNING_AGENT();
-
-  if (!shouldUsePlanningAgent) {
-    return null;
-  }
-
-  return (
-    <div className="bg-[#25272d] border border-[#597FF4] rounded-[12px] w-full mb-4 mt-2">
-      {/* Header */}
-      <div className="border-b border-[#525252] flex h-[41px] items-center px-2 gap-1">
-        <LessonPlanIcon width={18} height={18} color="#9299aa" />
-        <Typography.Text className="font-medium text-[11px] text-white tracking-[0.11px] leading-4">
-          {t(I18nKey.COMMON$PLAN_MD)}
-        </Typography.Text>
-        <div className="flex-1" />
-        <button
-          type="button"
-          onClick={onViewClick}
-          className="flex items-center gap-1 hover:opacity-80 transition-opacity"
-        >
-          <Typography.Text className="font-medium text-[11px] text-white tracking-[0.11px] leading-4">
-            {t(I18nKey.COMMON$VIEW)}
-          </Typography.Text>
-          <ArrowUpRight className="text-white" size={18} />
-        </button>
-      </div>
-
-      {/* Content */}
-      <div className="flex flex-col gap-[10px] p-4">
-        <h3 className="font-bold text-[19px] text-white leading-[29px]">
-          {title}
-        </h3>
-        <p className="text-[15px] text-white leading-[29px]">
-          {description}
-          <Typography.Text className="text-[#4a67bd] cursor-pointer hover:underline ml-1">
-            {t(I18nKey.COMMON$READ_MORE)}
-          </Typography.Text>
-        </p>
-      </div>
-
-      {/* Footer */}
-      <div className="border-t border-[#525252] flex h-[54px] items-center justify-start px-4">
-        <button
-          type="button"
-          onClick={onBuildClick}
-          className="bg-white flex items-center justify-center h-[26px] px-2 rounded-[4px] w-[93px] hover:opacity-90 transition-opacity cursor-pointer"
-        >
-          <Typography.Text className="font-medium text-[14px] text-black leading-5">
-            {t(I18nKey.COMMON$BUILD)}{" "}
-            <Typography.Text className="font-medium text-black">
-              ⌘↩
-            </Typography.Text>
-          </Typography.Text>
-        </button>
-      </div>
-    </div>
-  );
-}

frontend/src/components/features/chat/task-tracking-observation-content.tsx

@@ -1,5 +1,6 @@
 import { TaskTrackingObservation } from "#/types/core/observations";
 import { TaskListSection } from "./task-tracking/task-list-section";
+import { ResultSection } from "./task-tracking/result-section";
 
 interface TaskTrackingObservationContentProps {
   event: TaskTrackingObservation;
@@ -15,6 +16,11 @@ export function TaskTrackingObservationContent({
     <div className="flex flex-col gap-4">
       {/* Task List section - only show for 'plan' command */}
       {shouldShowTaskList && <TaskListSection taskList={taskList} />}
+
+      {/* Result message - only show if there's meaningful content */}
+      {event.content && event.content.trim() && (
+        <ResultSection content={event.content} />
+      )}
     </div>
   );
 }

frontend/src/components/features/chat/task-tracking/task-item.tsx

@@ -1,11 +1,7 @@
-import { useMemo } from "react";
 import { useTranslation } from "react-i18next";
-import CircleIcon from "#/icons/u-circle.svg?react";
-import CheckCircleIcon from "#/icons/u-check-circle.svg?react";
-import LoadingIcon from "#/icons/loading.svg?react";
-import { I18nKey } from "#/i18n/declaration";
-import { cn } from "#/utils/utils";
 import { Typography } from "#/ui/typography";
+import { StatusIcon } from "./status-icon";
+import { StatusBadge } from "./status-badge";
 
 interface TaskItemProps {
   task: {
@@ -14,47 +10,33 @@ interface TaskItemProps {
     status: "todo" | "in_progress" | "done";
     notes?: string;
   };
+  index: number;
 }
 
-export function TaskItem({ task }: TaskItemProps) {
+export function TaskItem({ task, index }: TaskItemProps) {
   const { t } = useTranslation();
 
-  const icon = useMemo(() => {
-    switch (task.status) {
-      case "todo":
-        return <CircleIcon className="w-4 h-4 text-[#ffffff]" />;
-      case "in_progress":
-        return <LoadingIcon className="w-4 h-4 text-[#ffffff]" />;
-      case "done":
-        return <CheckCircleIcon className="w-4 h-4 text-[#A3A3A3]" />;
-      default:
-        return <CircleIcon className="w-4 h-4 text-[#ffffff]" />;
-    }
-  }, [task.status]);
-
-  const isDoneStatus = task.status === "done";
-
   return (
-    <div
-      className="flex gap-[14px] items-center px-4 py-2 w-full"
-      data-name="item"
-    >
-      <div className="shrink-0">{icon}</div>
-      <div className="flex flex-col items-start justify-center leading-[20px] text-nowrap whitespace-pre font-normal">
-        <Typography.Text
-          className={cn(
-            "text-[12px] text-white",
-            isDoneStatus && "text-[#A3A3A3]",
+    <div className="border-l-2 border-gray-600 pl-3">
+      <div className="flex items-start gap-2">
+        <StatusIcon status={task.status} />
+        <div className="flex-1">
+          <div className="flex items-center gap-2 mb-1">
+            <Typography.Text className="text-sm text-gray-400">
+              {index + 1}.
+            </Typography.Text>
+            <StatusBadge status={task.status} />
+          </div>
+          <h4 className="font-medium text-white mb-1">{task.title}</h4>
+          <Typography.Text className="text-xs text-gray-400 mb-1">
+            {t("TASK_TRACKING_OBSERVATION$TASK_ID")}: {task.id}
+          </Typography.Text>
+          {task.notes && (
+            <Typography.Text className="text-sm text-gray-300 italic">
+              {t("TASK_TRACKING_OBSERVATION$TASK_NOTES")}: {task.notes}
+            </Typography.Text>
           )}
-        >
-          {task.title}
-        </Typography.Text>
-        <Typography.Text className="text-[10px] text-[#A3A3A3] font-normal">
-          {t(I18nKey.TASK_TRACKING_OBSERVATION$TASK_ID)}: {task.id}
-        </Typography.Text>
-        <Typography.Text className="text-[10px] text-[#A3A3A3]">
-          {t(I18nKey.TASK_TRACKING_OBSERVATION$TASK_NOTES)}: {task.notes}
-        </Typography.Text>
+        </div>
       </div>
     </div>
   );

frontend/src/components/features/chat/task-tracking/task-list-section.tsx

@@ -1,7 +1,5 @@
 import { useTranslation } from "react-i18next";
 import { TaskItem } from "./task-item";
-import LessonPlanIcon from "#/icons/lesson-plan.svg?react";
-import { I18nKey } from "#/i18n/declaration";
 import { Typography } from "#/ui/typography";
 
 interface TaskListSectionProps {
@@ -17,20 +15,19 @@ export function TaskListSection({ taskList }: TaskListSectionProps) {
   const { t } = useTranslation();
 
   return (
-    <div className="flex flex-col overflow-clip bg-[#25272d] border border-[#525252] rounded-[12px] w-full">
-      {/* Header Tabs */}
-      <div className="flex gap-1 items-center border-b border-[#525252] h-[41px] px-2 shrink-0">
-        <LessonPlanIcon className="shrink-0 w-4.5 h-4.5 text-[#9299aa]" />
-        <Typography.Text className="text-[11px] text-nowrap text-white tracking-[0.11px] font-medium leading-[16px] whitespace-pre">
-          {t(I18nKey.COMMON$TASKS)}
-        </Typography.Text>
+    <div className="flex flex-col gap-2">
+      <div className="flex items-center justify-between">
+        <Typography.H3>
+          {t("TASK_TRACKING_OBSERVATION$TASK_LIST")} ({taskList.length}{" "}
+          {taskList.length === 1 ? "item" : "items"})
+        </Typography.H3>
       </div>
-
-      {/* Task Items */}
-      <div>
-        {taskList.map((task) => (
-          <TaskItem key={task.id} task={task} />
-        ))}
+      <div className="p-3 bg-gray-900 rounded-md overflow-auto text-gray-300 max-h-[400px] shadow-inner">
+        <div className="space-y-3">
+          {taskList.map((task, index) => (
+            <TaskItem key={task.id} task={task} index={index} />
+          ))}
+        </div>
       </div>
     </div>
   );

frontend/src/components/features/context-menu/account-settings-context-menu.tsx

@@ -8,7 +8,6 @@ import { useClickOutsideElement } from "#/hooks/use-click-outside-element";
 import { useConfig } from "#/hooks/query/use-config";
 import { I18nKey } from "#/i18n/declaration";
 import LogOutIcon from "#/icons/log-out.svg?react";
-import DocumentIcon from "#/icons/document.svg?react";
 import { SAAS_NAV_ITEMS, OSS_NAV_ITEMS } from "#/constants/settings-nav";
 
 interface AccountSettingsContextMenuProps {
@@ -16,77 +15,6 @@ interface AccountSettingsContextMenuProps {
   onClose: () => void;
 }
 
-const SAAS_NAV_ITEMS = [
-  {
-    icon: <UserIcon width={16} height={16} />,
-    to: "/settings/user",
-    text: "COMMON$USER_SETTINGS",
-  },
-  {
-    icon: <PuzzlePieceIcon width={16} height={16} />,
-    to: "/settings/integrations",
-    text: "SETTINGS$NAV_INTEGRATIONS",
-  },
-  {
-    icon: <SettingsGearIcon width={16} height={16} />,
-    to: "/settings/app",
-    text: "COMMON$APPLICATION_SETTINGS",
-  },
-  {
-    icon: <CircuitIcon width={16} height={16} />,
-    to: "/settings",
-    text: "COMMON$LANGUAGE_MODEL_LLM",
-  },
-  {
-    icon: <CreditCardIcon width={16} height={16} />,
-    to: "/settings/billing",
-    text: "SETTINGS$NAV_BILLING",
-  },
-  {
-    icon: <KeyIcon width={16} height={16} />,
-    to: "/settings/secrets",
-    text: "SETTINGS$NAV_SECRETS",
-  },
-  {
-    icon: <KeyIcon width={16} height={16} />,
-    to: "/settings/api-keys",
-    text: "SETTINGS$NAV_API_KEYS",
-  },
-  {
-    icon: <ServerProcessIcon width={16} height={16} />,
-    to: "/settings/mcp",
-    text: "SETTINGS$NAV_MCP",
-  },
-];
-
-const OSS_NAV_ITEMS = [
-  {
-    icon: <CircuitIcon width={16} height={16} />,
-    to: "/settings",
-    text: "COMMON$LANGUAGE_MODEL_LLM",
-  },
-  {
-    icon: <ServerProcessIcon width={16} height={16} />,
-    to: "/settings/mcp",
-    text: "COMMON$MODEL_CONTEXT_PROTOCOL_MCP",
-  },
-  {
-    icon: <PuzzlePieceIcon width={16} height={16} />,
-    to: "/settings/integrations",
-    text: "SETTINGS$NAV_INTEGRATIONS",
-  },
-  {
-    icon: <SettingsGearIcon width={16} height={16} />,
-    to: "/settings/app",
-    text: "COMMON$APPLICATION_SETTINGS",
-  },
-  {
-    icon: <KeyIcon width={16} height={16} />,
-    to: "/settings/secrets",
-    text: "SETTINGS$NAV_SECRETS",
-  },
-];
-
 export function AccountSettingsContextMenu({
   onLogout,
   onClose,
@@ -130,21 +58,6 @@ export function AccountSettingsContextMenu({
 
       <Divider />
 
-      <a
-        href="https://docs.openhands.dev"
-        target="_blank"
-        rel="noopener noreferrer"
-        className="text-decoration-none"
-      >
-        <ContextMenuListItem
-          onClick={onClose}
-          className="flex items-center gap-2 p-2 hover:bg-[#5C5D62] rounded h-[30px]"
-        >
-          <DocumentIcon width={16} height={16} />
-          <span className="text-white text-sm">{t(I18nKey.SIDEBAR$DOCS)}</span>
-        </ContextMenuListItem>
-      </a>
-
       <ContextMenuListItem
         onClick={onLogout}
         className="flex items-center gap-2 p-2 hover:bg-[#5C5D62] rounded h-[30px]"

frontend/src/components/features/controls/agent-status.tsx

@@ -13,7 +13,6 @@ import { useConversationStore } from "#/state/conversation-store";
 import CircleErrorIcon from "#/icons/circle-error.svg?react";
 import { useAgentState } from "#/hooks/use-agent-state";
 import { useUnifiedWebSocketStatus } from "#/hooks/use-unified-websocket-status";
-import { useTaskPolling } from "#/hooks/query/use-task-polling";
 
 export interface AgentStatusProps {
   className?: string;
@@ -36,7 +35,6 @@ export function AgentStatus({
   const { curStatusMessage } = useStatusStore();
   const webSocketStatus = useUnifiedWebSocketStatus();
   const { data: conversation } = useActiveConversation();
-  const { taskStatus } = useTaskPolling();
 
   const statusCode = getStatusCode(
     curStatusMessage,
@@ -44,33 +42,25 @@ export function AgentStatus({
     conversation?.status || null,
     conversation?.runtime_status || null,
     curAgentState,
-    taskStatus,
   );
 
-  const isTaskLoading =
-    taskStatus && taskStatus !== "ERROR" && taskStatus !== "READY";
-
   const shouldShownAgentLoading =
     isPausing ||
     curAgentState === AgentState.INIT ||
     curAgentState === AgentState.LOADING ||
-    (webSocketStatus === "CONNECTING" && taskStatus !== "ERROR") ||
-    isTaskLoading;
+    webSocketStatus === "CONNECTING";
 
   const shouldShownAgentError =
     curAgentState === AgentState.ERROR ||
-    curAgentState === AgentState.RATE_LIMITED ||
-    webSocketStatus === "DISCONNECTED" ||
-    taskStatus === "ERROR";
+    curAgentState === AgentState.RATE_LIMITED;
 
   const shouldShownAgentStop = curAgentState === AgentState.RUNNING;
 
-  const shouldShownAgentResume =
-    curAgentState === AgentState.STOPPED || curAgentState === AgentState.PAUSED;
+  const shouldShownAgentResume = curAgentState === AgentState.STOPPED;
 
   // Update global state when agent loading condition changes
   useEffect(() => {
-    setShouldShownAgentLoading(!!shouldShownAgentLoading);
+    setShouldShownAgentLoading(shouldShownAgentLoading);
   }, [shouldShownAgentLoading, setShouldShownAgentLoading]);
 
   return (

frontend/src/components/features/controls/server-status-context-menu-icon-text.tsx

@@ -13,7 +13,7 @@ export function ServerStatusContextMenuIconText({
 }: ServerStatusContextMenuIconTextProps) {
   return (
     <button
-      className="flex items-center justify-between p-2 hover:bg-[#5C5D62] rounded text-sm text-white font-normal leading-5 cursor-pointer w-full"
+      className="flex items-center gap-2 p-2 hover:bg-[#5C5D62] rounded text-sm text-white font-normal leading-5 cursor-pointer w-full"
       onClick={onClick}
       data-testid={testId}
       type="button"

frontend/src/components/features/controls/server-status-context-menu.tsx

@@ -6,9 +6,6 @@ import { ConversationStatus } from "#/types/conversation-status";
 import StopCircleIcon from "#/icons/stop-circle.svg?react";
 import PlayCircleIcon from "#/icons/play-circle.svg?react";
 import { ServerStatusContextMenuIconText } from "./server-status-context-menu-icon-text";
-import { ServerStatus } from "./server-status";
-import { Divider } from "#/ui/divider";
-import { cn } from "#/utils/utils";
 
 interface ServerStatusContextMenuProps {
   onClose: () => void;
@@ -16,8 +13,6 @@ interface ServerStatusContextMenuProps {
   onStartServer?: (event: React.MouseEvent<HTMLButtonElement>) => void;
   conversationStatus: ConversationStatus | null;
   position?: "top" | "bottom";
-  className?: string;
-  isPausing?: boolean;
 }
 
 export function ServerStatusContextMenu({
@@ -26,15 +21,10 @@ export function ServerStatusContextMenu({
   onStartServer,
   conversationStatus,
   position = "top",
-  className = "",
-  isPausing = false,
 }: ServerStatusContextMenuProps) {
   const { t } = useTranslation();
   const ref = useClickOutsideElement<HTMLUListElement>(onClose);
 
-  const shouldActionShown =
-    conversationStatus === "RUNNING" || conversationStatus === "STOPPED";
-
   return (
     <ContextMenu
       ref={ref}
@@ -42,36 +32,24 @@ export function ServerStatusContextMenu({
       position={position}
       alignment="left"
       size="default"
-      className={cn("left-2 w-fit min-w-42", className)}
+      className="left-2 w-fit min-w-max"
     >
-      <ServerStatus
-        conversationStatus={conversationStatus}
-        isPausing={isPausing}
-        className="py-1"
-      />
+      {conversationStatus === "RUNNING" && onStopServer && (
+        <ServerStatusContextMenuIconText
+          icon={<StopCircleIcon width={18} height={18} />}
+          text={t(I18nKey.COMMON$STOP_RUNTIME)}
+          onClick={onStopServer}
+          testId="stop-server-button"
+        />
+      )}
 
-      {shouldActionShown && (
-        <>
-          <Divider />
-
-          {conversationStatus === "RUNNING" && onStopServer && (
-            <ServerStatusContextMenuIconText
-              icon={<StopCircleIcon width={18} height={18} />}
-              text={t(I18nKey.COMMON$STOP_RUNTIME)}
-              onClick={onStopServer}
-              testId="stop-server-button"
-            />
-          )}
-
-          {conversationStatus === "STOPPED" && onStartServer && (
-            <ServerStatusContextMenuIconText
-              icon={<PlayCircleIcon width={18} height={18} />}
-              text={t(I18nKey.COMMON$START_RUNTIME)}
-              onClick={onStartServer}
-              testId="start-server-button"
-            />
-          )}
-        </>
+      {conversationStatus === "STOPPED" && onStartServer && (
+        <ServerStatusContextMenuIconText
+          icon={<PlayCircleIcon width={18} height={18} />}
+          text={t(I18nKey.COMMON$START_RUNTIME)}
+          onClick={onStartServer}
+          testId="start-server-button"
+        />
       )}
     </ContextMenu>
   );

frontend/src/components/features/controls/server-status.tsx

@@ -1,23 +1,30 @@
 import { useTranslation } from "react-i18next";
+import { useState } from "react";
 import DebugStackframeDot from "#/icons/debug-stackframe-dot.svg?react";
 import { I18nKey } from "#/i18n/declaration";
 import { ConversationStatus } from "#/types/conversation-status";
 import { AgentState } from "#/types/agent-state";
+import { ServerStatusContextMenu } from "./server-status-context-menu";
 import { useAgentState } from "#/hooks/use-agent-state";
 import { useTaskPolling } from "#/hooks/query/use-task-polling";
-import { getStatusColor } from "#/utils/utils";
 
 export interface ServerStatusProps {
   className?: string;
   conversationStatus: ConversationStatus | null;
   isPausing?: boolean;
+  handleStop: () => void;
+  handleResumeAgent: () => void;
 }
 
 export function ServerStatus({
   className = "",
   conversationStatus,
   isPausing = false,
+  handleStop,
+  handleResumeAgent,
 }: ServerStatusProps) {
+  const [showContextMenu, setShowContextMenu] = useState(false);
+
   const { curAgentState } = useAgentState();
   const { t } = useTranslation();
   const { isTask, taskStatus, taskDetail } = useTaskPolling();
@@ -27,15 +34,34 @@ export function ServerStatus({
 
   const isStopStatus = conversationStatus === "STOPPED";
 
-  const statusColor = getStatusColor({
-    isPausing,
-    isTask,
-    taskStatus,
-    isStartingStatus,
-    isStopStatus,
-    curAgentState,
-  });
+  // Get the appropriate color based on agent status
+  const getStatusColor = (): string => {
+    // Show pausing status
+    if (isPausing) {
+      return "#FFD600";
+    }
 
+    // Show task status if we're polling a task
+    if (isTask && taskStatus) {
+      if (taskStatus === "ERROR") {
+        return "#FF684E";
+      }
+      return "#FFD600";
+    }
+
+    if (isStartingStatus) {
+      return "#FFD600";
+    }
+    if (isStopStatus) {
+      return "#ffffff";
+    }
+    if (curAgentState === AgentState.ERROR) {
+      return "#FF684E";
+    }
+    return "#BCFF8C";
+  };
+
+  // Get the appropriate status text based on agent status
   const getStatusText = (): string => {
     // Show pausing status
     if (isPausing) {
@@ -74,14 +100,49 @@ export function ServerStatus({
     return t(I18nKey.COMMON$RUNNING);
   };
 
+  const handleClick = () => {
+    if (conversationStatus === "RUNNING" || conversationStatus === "STOPPED") {
+      setShowContextMenu(true);
+    }
+  };
+
+  const handleCloseContextMenu = () => {
+    setShowContextMenu(false);
+  };
+
+  const handleStopServer = (event: React.MouseEvent<HTMLButtonElement>) => {
+    event.preventDefault();
+    handleStop();
+    setShowContextMenu(false);
+  };
+
+  const handleStartServer = (event: React.MouseEvent<HTMLButtonElement>) => {
+    event.preventDefault();
+    handleResumeAgent();
+    setShowContextMenu(false);
+  };
+
+  const statusColor = getStatusColor();
   const statusText = getStatusText();
 
   return (
-    <div className={className} data-testid="server-status">
-      <div className="flex items-center">
+    <div className={`relative ${className}`}>
+      <div className="flex items-center cursor-pointer" onClick={handleClick}>
         <DebugStackframeDot className="w-6 h-6" color={statusColor} />
-        <span className="text-[13px] text-white font-normal">{statusText}</span>
+        <span className="text-[11px] text-white font-normal leading-5">
+          {statusText}
+        </span>
       </div>
+
+      {showContextMenu && (
+        <ServerStatusContextMenu
+          onClose={handleCloseContextMenu}
+          onStopServer={handleStopServer}
+          onStartServer={handleStartServer}
+          conversationStatus={conversationStatus}
+          position="top"
+        />
+      )}
     </div>
   );
 }

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

@@ -1,5 +1,5 @@
 import React from "react";
-import { usePostHog } from "posthog-js/react";
+import posthog from "posthog-js";
 import { cn } from "#/utils/utils";
 import { transformVSCodeUrl } from "#/utils/vscode-url-helper";
 import ConversationService from "#/api/conversation-service/conversation-service.api";
@@ -44,7 +44,6 @@ export function ConversationCard({
   contextMenuOpen = false,
   onContextMenuToggle,
 }: ConversationCardProps) {
-  const posthog = usePostHog();
   const [titleMode, setTitleMode] = React.useState<"view" | "edit">("view");
 
   const onTitleSave = (newTitle: string) => {

frontend/src/components/features/conversation/conversation-name-with-status.tsx

@@ -1,79 +0,0 @@
-import React from "react";
-import { useParams } from "react-router";
-import { useAgentState } from "#/hooks/use-agent-state";
-import { useTaskPolling } from "#/hooks/query/use-task-polling";
-import { useActiveConversation } from "#/hooks/query/use-active-conversation";
-import { useUnifiedPauseConversationSandbox } from "#/hooks/mutation/use-unified-stop-conversation";
-import { useUnifiedResumeConversationSandbox } from "#/hooks/mutation/use-unified-start-conversation";
-import { useUserProviders } from "#/hooks/use-user-providers";
-import { getStatusColor } from "#/utils/utils";
-import { AgentState } from "#/types/agent-state";
-import DebugStackframeDot from "#/icons/debug-stackframe-dot.svg?react";
-import { ServerStatusContextMenu } from "../controls/server-status-context-menu";
-import { ConversationName } from "./conversation-name";
-
-export function ConversationNameWithStatus() {
-  const { conversationId } = useParams<{ conversationId: string }>();
-  const { data: conversation } = useActiveConversation();
-  const { curAgentState } = useAgentState();
-  const { isTask, taskStatus } = useTaskPolling();
-  const { mutate: pauseConversationSandbox } =
-    useUnifiedPauseConversationSandbox();
-  const { mutate: resumeConversationSandbox } =
-    useUnifiedResumeConversationSandbox();
-  const { providers } = useUserProviders();
-
-  const isStartingStatus =
-    curAgentState === AgentState.LOADING || curAgentState === AgentState.INIT;
-  const isStopStatus = conversation?.status === "STOPPED";
-
-  const statusColor = getStatusColor({
-    isPausing: false,
-    isTask,
-    taskStatus,
-    isStartingStatus,
-    isStopStatus,
-    curAgentState,
-  });
-
-  const handleStopServer = (event: React.MouseEvent<HTMLButtonElement>) => {
-    event.preventDefault();
-    event.stopPropagation();
-    if (conversationId) {
-      pauseConversationSandbox({ conversationId });
-    }
-  };
-
-  const handleStartServer = (event: React.MouseEvent<HTMLButtonElement>) => {
-    event.preventDefault();
-    event.stopPropagation();
-    if (conversationId) {
-      resumeConversationSandbox({ conversationId, providers });
-    }
-  };
-
-  return (
-    <div className="flex items-center">
-      <div className="group relative">
-        <DebugStackframeDot
-          className="ml-[3.5px] w-6 h-6 cursor-pointer"
-          color={statusColor}
-        />
-        <ServerStatusContextMenu
-          onClose={() => {}}
-          onStopServer={
-            conversation?.status === "RUNNING" ? handleStopServer : undefined
-          }
-          onStartServer={
-            conversation?.status === "STOPPED" ? handleStartServer : undefined
-          }
-          conversationStatus={conversation?.status ?? null}
-          position="bottom"
-          className="opacity-0 invisible pointer-events-none group-hover:opacity-100 group-hover:visible group-hover:pointer-events-auto bottom-full left-0 mt-0 min-h-fit"
-          isPausing={false}
-        />
-      </div>
-      <ConversationName />
-    </div>
-  );
-}

frontend/src/components/features/conversation/conversation-name.tsx

@@ -124,7 +124,7 @@ export function ConversationName() {
   return (
     <>
       <div
-        className="flex items-center gap-2 h-[22px] text-base font-normal text-left pl-0 lg:pl-1"
+        className="flex items-center gap-2 h-[22px] text-base font-normal text-left pl-0 lg:pl-3.5"
         data-testid="conversation-name"
       >
         {titleMode === "edit" ? (

frontend/src/components/features/conversation/conversation-tabs/conversation-tab-content/conversation-tab-content.tsx

@@ -15,7 +15,6 @@ const EditorTab = lazy(() => import("#/routes/changes-tab"));
 const BrowserTab = lazy(() => import("#/routes/browser-tab"));
 const ServedTab = lazy(() => import("#/routes/served-tab"));
 const VSCodeTab = lazy(() => import("#/routes/vscode-tab"));
-const PlannerTab = lazy(() => import("#/routes/planner-tab"));
 
 export function ConversationTabContent() {
   const { selectedTab, shouldShownAgentLoading } = useConversationStore();
@@ -29,7 +28,6 @@ export function ConversationTabContent() {
   const isServedActive = selectedTab === "served";
   const isVSCodeActive = selectedTab === "vscode";
   const isTerminalActive = selectedTab === "terminal";
-  const isPlannerActive = selectedTab === "planner";
 
   // Define tab configurations
   const tabs = [
@@ -46,11 +44,6 @@ export function ConversationTabContent() {
       component: Terminal,
       isActive: isTerminalActive,
     },
-    {
-      key: "planner",
-      component: PlannerTab,
-      isActive: isPlannerActive,
-    },
   ];
 
   const conversationTabTitle = useMemo(() => {
@@ -69,9 +62,6 @@ export function ConversationTabContent() {
     if (isTerminalActive) {
       return t(I18nKey.COMMON$TERMINAL);
     }
-    if (isPlannerActive) {
-      return t(I18nKey.COMMON$PLANNER);
-    }
     return "";
   }, [
     isEditorActive,
@@ -79,7 +69,6 @@ export function ConversationTabContent() {
     isServedActive,
     isVSCodeActive,
     isTerminalActive,
-    isPlannerActive,
   ]);
 
   if (shouldShownAgentLoading) {

frontend/src/components/features/conversation/conversation-tabs/conversation-tab-nav.tsx

@@ -5,16 +5,12 @@ type ConversationTabNavProps = {
   icon: ComponentType<{ className: string }>;
   onClick(): void;
   isActive?: boolean;
-  label?: string;
-  className?: string;
 };
 
 export function ConversationTabNav({
   icon: Icon,
   onClick,
   isActive,
-  label,
-  className,
 }: ConversationTabNavProps) {
   return (
     <button
@@ -23,21 +19,18 @@ export function ConversationTabNav({
         onClick();
       }}
       className={cn(
-        "flex items-center gap-2 rounded-md cursor-pointer",
-        "pl-1.5 pr-2 py-1",
+        "p-1 rounded-md cursor-pointer",
         "text-[#9299AA] bg-[#0D0F11]",
         isActive && "bg-[#25272D] text-white",
         isActive
           ? "hover:text-white hover:bg-tertiary"
           : "hover:text-white hover:bg-[#0D0F11]",
-        isActive ? "focus-within:text-white" : "focus-within:text-[#9299AA]",
-        className,
+        isActive
+          ? "focus-within:text-white focus-within:bg-tertiary"
+          : "focus-within:text-[#9299AA] focus-within:bg-[#0D0F11]",
       )}
     >
-      <Icon className={cn("w-5 h-5 text-inherit flex-shrink-0")} />
-      {isActive && label && (
-        <span className="text-sm font-medium whitespace-nowrap">{label}</span>
-      )}
+      <Icon className={cn("w-5 h-5 text-inherit")} />
     </button>
   );
 }

frontend/src/components/features/conversation/conversation-tabs/conversation-tabs-context-menu.tsx

@@ -1,116 +0,0 @@
-import { useTranslation } from "react-i18next";
-import { useLocalStorage } from "@uidotdev/usehooks";
-import { ContextMenu } from "#/ui/context-menu";
-import { ContextMenuListItem } from "../../context-menu/context-menu-list-item";
-import { useClickOutsideElement } from "#/hooks/use-click-outside-element";
-import { I18nKey } from "#/i18n/declaration";
-import TerminalIcon from "#/icons/terminal.svg?react";
-import GlobeIcon from "#/icons/globe.svg?react";
-import ServerIcon from "#/icons/server.svg?react";
-import GitChanges from "#/icons/git_changes.svg?react";
-import VSCodeIcon from "#/icons/vscode.svg?react";
-import PillIcon from "#/icons/pill.svg?react";
-import PillFillIcon from "#/icons/pill-fill.svg?react";
-import { USE_PLANNING_AGENT } from "#/utils/feature-flags";
-import LessonPlanIcon from "#/icons/lesson-plan.svg?react";
-
-interface ConversationTabsContextMenuProps {
-  isOpen: boolean;
-  onClose: () => void;
-}
-
-export function ConversationTabsContextMenu({
-  isOpen,
-  onClose,
-}: ConversationTabsContextMenuProps) {
-  const ref = useClickOutsideElement<HTMLUListElement>(onClose);
-  const { t } = useTranslation();
-  const [unpinnedTabs, setUnpinnedTabs] = useLocalStorage<string[]>(
-    "conversation-unpinned-tabs",
-    [],
-  );
-
-  const shouldUsePlanningAgent = USE_PLANNING_AGENT();
-
-  const tabConfig = [
-    {
-      tab: "editor",
-      icon: GitChanges,
-      i18nKey: I18nKey.COMMON$CHANGES,
-    },
-    {
-      tab: "vscode",
-      icon: VSCodeIcon,
-      i18nKey: I18nKey.COMMON$CODE,
-    },
-    {
-      tab: "terminal",
-      icon: TerminalIcon,
-      i18nKey: I18nKey.COMMON$TERMINAL,
-    },
-    {
-      tab: "served",
-      icon: ServerIcon,
-      i18nKey: I18nKey.COMMON$APP,
-    },
-    {
-      tab: "browser",
-      icon: GlobeIcon,
-      i18nKey: I18nKey.COMMON$BROWSER,
-    },
-  ];
-
-  if (shouldUsePlanningAgent) {
-    tabConfig.unshift({
-      tab: "planner",
-      icon: LessonPlanIcon,
-      i18nKey: I18nKey.COMMON$PLANNER,
-    });
-  }
-
-  if (!isOpen) return null;
-
-  const handleTabClick = (tab: string) => {
-    const tabString = tab;
-    if (unpinnedTabs.includes(tabString)) {
-      // Tab is unpinned, pin it (remove from unpinned list)
-      setUnpinnedTabs(
-        unpinnedTabs.filter((unpinnedTab) => unpinnedTab !== tabString),
-      );
-    } else {
-      // Tab is pinned, unpin it (add to unpinned list)
-      setUnpinnedTabs([...unpinnedTabs, tabString]);
-    }
-  };
-
-  const isTabPinned = (tab: string) => !unpinnedTabs.includes(tab as string);
-
-  return (
-    <ContextMenu
-      testId="conversation-tabs-context-menu"
-      ref={ref}
-      alignment="right"
-      position="bottom"
-      className="mt-2 w-fit z-[9999]"
-    >
-      {tabConfig.map(({ tab, icon: Icon, i18nKey }) => {
-        const pinned = isTabPinned(tab);
-        return (
-          <ContextMenuListItem
-            key={tab}
-            onClick={() => handleTabClick(tab)}
-            className="flex items-center gap-2 p-2 hover:bg-[#5C5D62] rounded h-[30px]"
-          >
-            <Icon className="w-4 h-4" />
-            <span className="text-white text-sm">{t(i18nKey)}</span>
-            {pinned ? (
-              <PillFillIcon className="w-7 h-7 ml-auto flex-shrink-0 text-white -mr-[5px]" />
-            ) : (
-              <PillIcon className="w-4.5 h-4.5 ml-auto flex-shrink-0 text-white" />
-            )}
-          </ContextMenuListItem>
-        );
-      })}
-    </ContextMenu>
-  );
-}

frontend/src/components/features/conversation/conversation-tabs/conversation-tabs.tsx

@@ -1,4 +1,4 @@
-import { useEffect, useState } from "react";
+import { useEffect } from "react";
 import { useTranslation } from "react-i18next";
 import { useLocalStorage } from "@uidotdev/usehooks";
 import TerminalIcon from "#/icons/terminal.svg?react";
@@ -6,8 +6,6 @@ import GlobeIcon from "#/icons/globe.svg?react";
 import ServerIcon from "#/icons/server.svg?react";
 import GitChanges from "#/icons/git_changes.svg?react";
 import VSCodeIcon from "#/icons/vscode.svg?react";
-import ThreeDotsVerticalIcon from "#/icons/three-dots-vertical.svg?react";
-import LessonPlanIcon from "#/icons/lesson-plan.svg?react";
 import { cn } from "#/utils/utils";
 import { ConversationTabNav } from "./conversation-tab-nav";
 import { ChatActionTooltip } from "../../chat/chat-action-tooltip";
@@ -17,8 +15,6 @@ import {
   useConversationStore,
   type ConversationTab,
 } from "#/state/conversation-store";
-import { ConversationTabsContextMenu } from "./conversation-tabs-context-menu";
-import { USE_PLANNING_AGENT } from "#/utils/feature-flags";
 
 export function ConversationTabs() {
   const {
@@ -28,8 +24,6 @@ export function ConversationTabs() {
     setSelectedTab,
   } = useConversationStore();
 
-  const [isMenuOpen, setIsMenuOpen] = useState(false);
-
   // Persist selectedTab and isRightPanelShown in localStorage
   const [persistedSelectedTab, setPersistedSelectedTab] =
     useLocalStorage<ConversationTab | null>(
@@ -40,13 +34,6 @@ export function ConversationTabs() {
   const [persistedIsRightPanelShown, setPersistedIsRightPanelShown] =
     useLocalStorage<boolean>("conversation-right-panel-shown", true);
 
-  const [persistedUnpinnedTabs] = useLocalStorage<string[]>(
-    "conversation-unpinned-tabs",
-    [],
-  );
-
-  const shouldUsePlanningAgent = USE_PLANNING_AGENT();
-
   const onTabChange = (value: ConversationTab | null) => {
     setSelectedTab(value);
     // Persist the selected tab to localStorage
@@ -100,70 +87,42 @@ export function ConversationTabs() {
 
   const tabs = [
     {
-      tabValue: "editor",
       isActive: isTabActive("editor"),
       icon: GitChanges,
       onClick: () => onTabSelected("editor"),
       tooltipContent: t(I18nKey.COMMON$CHANGES),
       tooltipAriaLabel: t(I18nKey.COMMON$CHANGES),
-      label: t(I18nKey.COMMON$CHANGES),
     },
     {
-      tabValue: "vscode",
       isActive: isTabActive("vscode"),
       icon: VSCodeIcon,
       onClick: () => onTabSelected("vscode"),
       tooltipContent: <VSCodeTooltipContent />,
       tooltipAriaLabel: t(I18nKey.COMMON$CODE),
-      label: t(I18nKey.COMMON$CODE),
     },
     {
-      tabValue: "terminal",
       isActive: isTabActive("terminal"),
       icon: TerminalIcon,
       onClick: () => onTabSelected("terminal"),
       tooltipContent: t(I18nKey.COMMON$TERMINAL),
       tooltipAriaLabel: t(I18nKey.COMMON$TERMINAL),
-      label: t(I18nKey.COMMON$TERMINAL),
-      className: "pl-2",
     },
     {
-      tabValue: "served",
       isActive: isTabActive("served"),
       icon: ServerIcon,
       onClick: () => onTabSelected("served"),
       tooltipContent: t(I18nKey.COMMON$APP),
       tooltipAriaLabel: t(I18nKey.COMMON$APP),
-      label: t(I18nKey.COMMON$APP),
     },
     {
-      tabValue: "browser",
       isActive: isTabActive("browser"),
       icon: GlobeIcon,
       onClick: () => onTabSelected("browser"),
       tooltipContent: t(I18nKey.COMMON$BROWSER),
       tooltipAriaLabel: t(I18nKey.COMMON$BROWSER),
-      label: t(I18nKey.COMMON$BROWSER),
     },
   ];
 
-  if (shouldUsePlanningAgent) {
-    tabs.unshift({
-      tabValue: "planner",
-      isActive: isTabActive("planner"),
-      icon: LessonPlanIcon,
-      onClick: () => onTabSelected("planner"),
-      tooltipContent: t(I18nKey.COMMON$PLANNER),
-      tooltipAriaLabel: t(I18nKey.COMMON$PLANNER),
-      label: t(I18nKey.COMMON$PLANNER),
-    });
-  }
-
-  // Filter out unpinned tabs
-  const visibleTabs = tabs.filter(
-    (tab) => !persistedUnpinnedTabs.includes(tab.tabValue),
-  );
-
   return (
     <div
       className={cn(
@@ -171,17 +130,9 @@ export function ConversationTabs() {
         "flex flex-row justify-start lg:justify-end items-center gap-4.5",
       )}
     >
-      {visibleTabs.map(
+      {tabs.map(
         (
-          {
-            icon,
-            onClick,
-            isActive,
-            tooltipContent,
-            tooltipAriaLabel,
-            label,
-            className,
-          },
+          { icon, onClick, isActive, tooltipContent, tooltipAriaLabel },
           index,
         ) => (
           <ChatActionTooltip
@@ -193,29 +144,10 @@ export function ConversationTabs() {
               icon={icon}
               onClick={onClick}
               isActive={isActive}
-              label={label}
-              className={className}
             />
           </ChatActionTooltip>
         ),
       )}
-      <div className="relative">
-        <button
-          type="button"
-          onClick={() => setIsMenuOpen(!isMenuOpen)}
-          className={cn(
-            "p-1 pl-0 rounded-md cursor-pointer",
-            "text-[#9299AA] bg-[#0D0F11]",
-          )}
-          aria-label={t(I18nKey.COMMON$MORE_OPTIONS)}
-        >
-          <ThreeDotsVerticalIcon className={cn("w-5 h-5 text-inherit")} />
-        </button>
-        <ConversationTabsContextMenu
-          isOpen={isMenuOpen}
-          onClose={() => setIsMenuOpen(false)}
-        />
-      </div>
     </div>
   );
 }

frontend/src/components/features/home/repo-selection-form.tsx

@@ -131,7 +131,7 @@ export function RepositorySelectionForm({
         onBranchSelect={handleBranchSelection}
         defaultBranch={defaultBranch}
         placeholder="Select branch..."
-        className="max-w-full"
+        className="max-w-[500px]"
         disabled={!selectedRepository || isLoadingSettings}
       />
     );

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

@@ -1,80 +0,0 @@
-import React from "react";
-import { ExtraProps } from "react-markdown";
-
-// Custom component to render <h1> in markdown
-export function h1({
-  children,
-}: React.ClassAttributes<HTMLHeadingElement> &
-  React.HTMLAttributes<HTMLHeadingElement> &
-  ExtraProps) {
-  return (
-    <h1 className="text-[32px] text-white font-bold leading-8 mb-4 mt-6 first:mt-0">
-      {children}
-    </h1>
-  );
-}
-
-// Custom component to render <h2> in markdown
-export function h2({
-  children,
-}: React.ClassAttributes<HTMLHeadingElement> &
-  React.HTMLAttributes<HTMLHeadingElement> &
-  ExtraProps) {
-  return (
-    <h2 className="text-xl font-semibold leading-6 -tracking-[0.02em] text-white mb-3 mt-5 first:mt-0">
-      {children}
-    </h2>
-  );
-}
-
-// Custom component to render <h3> in markdown
-export function h3({
-  children,
-}: React.ClassAttributes<HTMLHeadingElement> &
-  React.HTMLAttributes<HTMLHeadingElement> &
-  ExtraProps) {
-  return (
-    <h3 className="text-lg font-semibold text-white mb-2 mt-4 first:mt-0">
-      {children}
-    </h3>
-  );
-}
-
-// Custom component to render <h4> in markdown
-export function h4({
-  children,
-}: React.ClassAttributes<HTMLHeadingElement> &
-  React.HTMLAttributes<HTMLHeadingElement> &
-  ExtraProps) {
-  return (
-    <h4 className="text-base font-semibold text-white mb-2 mt-4 first:mt-0">
-      {children}
-    </h4>
-  );
-}
-
-// Custom component to render <h5> in markdown
-export function h5({
-  children,
-}: React.ClassAttributes<HTMLHeadingElement> &
-  React.HTMLAttributes<HTMLHeadingElement> &
-  ExtraProps) {
-  return (
-    <h5 className="text-sm font-semibold text-white mb-2 mt-3 first:mt-0">
-      {children}
-    </h5>
-  );
-}
-
-// Custom component to render <h6> in markdown
-export function h6({
-  children,
-}: React.ClassAttributes<HTMLHeadingElement> &
-  React.HTMLAttributes<HTMLHeadingElement> &
-  ExtraProps) {
-  return (
-    <h6 className="text-sm font-medium text-gray-300 mb-2 mt-3 first:mt-0">
-      {children}
-    </h6>
-  );
-}

frontend/src/components/features/payment/payment-form.tsx

@@ -1,8 +1,7 @@
 import React from "react";
-import { useTranslation, Trans } from "react-i18next";
+import { useTranslation } from "react-i18next";
 import { useCreateStripeCheckoutSession } from "#/hooks/mutation/stripe/use-create-stripe-checkout-session";
 import { useBalance } from "#/hooks/query/use-balance";
-import { useSubscriptionAccess } from "#/hooks/query/use-subscription-access";
 import { cn } from "#/utils/utils";
 import MoneyIcon from "#/icons/money.svg?react";
 import { SettingsInput } from "../settings/settings-input";
@@ -11,24 +10,13 @@ import { LoadingSpinner } from "#/components/shared/loading-spinner";
 import { amountIsValid } from "#/utils/amount-is-valid";
 import { I18nKey } from "#/i18n/declaration";
 import { PoweredByStripeTag } from "./powered-by-stripe-tag";
-import { CancelSubscriptionModal } from "./cancel-subscription-modal";
 
 export function PaymentForm() {
   const { t } = useTranslation();
   const { data: balance, isLoading } = useBalance();
-  const { data: subscriptionAccess } = useSubscriptionAccess();
   const { mutate: addBalance, isPending } = useCreateStripeCheckoutSession();
 
   const [buttonIsDisabled, setButtonIsDisabled] = React.useState(true);
-  const [showCancelModal, setShowCancelModal] = React.useState(false);
-
-  const subscriptionExpiredDate =
-    subscriptionAccess?.end_at &&
-    new Date(subscriptionAccess.end_at).toLocaleDateString("en-US", {
-      year: "numeric",
-      month: "long",
-      day: "numeric",
-    });
 
   const billingFormAction = async (formData: FormData) => {
     const amount = formData.get("top-up-input")?.toString();
@@ -94,50 +82,7 @@ export function PaymentForm() {
           {isPending && <LoadingSpinner size="small" />}
           <PoweredByStripeTag />
         </div>
-
-        {/* Cancel Subscription Button or Cancellation Message */}
-        {subscriptionAccess && (
-          <div className="flex flex-col w-[680px] gap-2 mt-4">
-            {subscriptionAccess.cancelled_at ? (
-              <div className="text-red-500 text-sm">
-                <Trans
-                  i18nKey={I18nKey.PAYMENT$SUBSCRIPTION_CANCELLED_EXPIRES}
-                  values={{ date: subscriptionExpiredDate }}
-                  components={{ date: <span className="underline" /> }}
-                />
-              </div>
-            ) : (
-              <div className="flex items-center gap-4">
-                <BrandButton
-                  testId="cancel-subscription-button"
-                  variant="ghost-danger"
-                  type="button"
-                  onClick={() => setShowCancelModal(true)}
-                >
-                  {t(I18nKey.PAYMENT$CANCEL_SUBSCRIPTION)}
-                </BrandButton>
-                <div
-                  className="text-sm text-gray-300"
-                  data-testid="next-billing-date"
-                >
-                  <Trans
-                    i18nKey={I18nKey.PAYMENT$NEXT_BILLING_DATE}
-                    values={{ date: subscriptionExpiredDate }}
-                    components={{ date: <span className="underline" /> }}
-                  />
-                </div>
-              </div>
-            )}
-          </div>
-        )}
       </div>
-
-      {/* Cancel Subscription Modal */}
-      <CancelSubscriptionModal
-        isOpen={showCancelModal}
-        onClose={() => setShowCancelModal(false)}
-        endDate={subscriptionExpiredDate}
-      />
     </form>
   );
 }

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

@@ -11,7 +11,6 @@ import BitbucketLogo from "#/assets/branding/bitbucket-logo.svg?react";
 import { useAuthUrl } from "#/hooks/use-auth-url";
 import { GetConfigResponse } from "#/api/option-service/option.types";
 import { Provider } from "#/types/settings";
-import { useTracking } from "#/hooks/use-tracking";
 
 interface AuthModalProps {
   githubAuthUrl: string | null;
@@ -27,7 +26,6 @@ export function AuthModal({
   providersConfigured,
 }: AuthModalProps) {
   const { t } = useTranslation();
-  const { trackLoginButtonClick } = useTracking();
 
   const gitlabAuthUrl = useAuthUrl({
     appMode: appMode || null,
@@ -49,7 +47,6 @@ export function AuthModal({
 
   const handleGitHubAuth = () => {
     if (githubAuthUrl) {
-      trackLoginButtonClick({ provider: "github" });
       // Always start the OIDC flow, let the backend handle TOS check
       window.location.href = githubAuthUrl;
     }
@@ -57,7 +54,6 @@ export function AuthModal({
 
   const handleGitLabAuth = () => {
     if (gitlabAuthUrl) {
-      trackLoginButtonClick({ provider: "gitlab" });
       // Always start the OIDC flow, let the backend handle TOS check
       window.location.href = gitlabAuthUrl;
     }
@@ -65,7 +61,6 @@ export function AuthModal({
 
   const handleBitbucketAuth = () => {
     if (bitbucketAuthUrl) {
-      trackLoginButtonClick({ provider: "bitbucket" });
       // Always start the OIDC flow, let the backend handle TOS check
       window.location.href = bitbucketAuthUrl;
     }
@@ -73,7 +68,6 @@ export function AuthModal({
 
   const handleEnterpriseSsoAuth = () => {
     if (enterpriseSsoUrl) {
-      trackLoginButtonClick({ provider: "enterprise_sso" });
       // Always start the OIDC flow, let the backend handle TOS check
       window.location.href = enterpriseSsoUrl;
     }

frontend/src/components/shared/modals/settings/settings-form.tsx

@@ -1,7 +1,7 @@
 import { useLocation } from "react-router";
 import { useTranslation } from "react-i18next";
 import React from "react";
-import { usePostHog } from "posthog-js/react";
+import posthog from "posthog-js";
 import { I18nKey } from "#/i18n/declaration";
 import { organizeModelsAndProviders } from "#/utils/organize-models-and-providers";
 import { DangerModal } from "../confirmation-modals/danger-modal";
@@ -22,7 +22,6 @@ interface SettingsFormProps {
 }
 
 export function SettingsForm({ settings, models, onClose }: SettingsFormProps) {
-  const posthog = usePostHog();
   const { mutate: saveUserSettings } = useSaveSettings();
 
   const location = useLocation();

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

@@ -1,13 +1,10 @@
 import { Trans } from "react-i18next";
-import React from "react";
-import { OpenHandsEvent, ObservationEvent } from "#/types/v1/core";
+import { OpenHandsEvent } from "#/types/v1/core";
 import { isActionEvent, isObservationEvent } from "#/types/v1/type-guards";
 import { MonoComponent } from "../../../features/chat/mono-component";
 import { PathComponent } from "../../../features/chat/path-component";
 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 i18n from "#/i18n";
 
 const trimText = (text: string, maxLength: number): string => {
@@ -161,24 +158,14 @@ const getObservationEventTitle = (event: OpenHandsEvent): React.ReactNode => {
 
 export const getEventContent = (event: OpenHandsEvent) => {
   let title: React.ReactNode = "";
-  let details: string | React.ReactNode = "";
+  let details: string = "";
 
   if (isActionEvent(event)) {
     title = getActionEventTitle(event);
     details = getActionContent(event);
   } else if (isObservationEvent(event)) {
     title = getObservationEventTitle(event);
-
-    // For TaskTrackerObservation, use React component instead of markdown
-    if (event.observation.kind === "TaskTrackerObservation") {
-      details = (
-        <TaskTrackingObservationContent
-          event={event as ObservationEvent<TaskTrackerObservation>}
-        />
-      );
-    } else {
-      details = getObservationContent(event);
-    }
+    details = getObservationContent(event);
   }
 
   return {