feat: sample agent folder, remove docker file in Readme

Handle malformed JSON tool arguments in LiteLLMProvider

.github/workflows/ci.yml

@@ -65,10 +65,31 @@ jobs:
           cd core
           pytest tests/ -v
 
+  test-tools:
+    name: Test Tools
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Install dependencies and run tests
+        run: |
+          cd tools
+          uv sync --extra dev
+          uv pip install --python .venv/bin/python -e ../core
+          uv run --extra dev pytest tests/ -v
+
   validate:
     name: Validate Agent Exports
     runs-on: ubuntu-latest
-    needs: [lint, test]
+    needs: [lint, test, test-tools]
     steps:
       - uses: actions/checkout@v4
 

DEVELOPER.md

@@ -44,7 +44,7 @@ Aden Agent Framework is a Python-based system for building goal-driven, self-imp
 Ensure you have installed:
 
 - **Python 3.11+** - [Download](https://www.python.org/downloads/) (3.12 or 3.13 recommended)
-- **pip** - Package installer for Python (comes with Python)
+- **uv** - Python package manager ([Install](https://docs.astral.sh/uv/getting-started/installation/))
 - **git** - Version control
 - **Claude Code** - [Install](https://docs.anthropic.com/claude/docs/claude-code) (optional, for using building skills)
 
@@ -52,7 +52,7 @@ Verify installation:
 
 ```bash
 python --version    # Should be 3.11+
-pip --version       # Should be latest
+uv --version        # Should be latest
 git --version       # Any recent version
 ```
 
@@ -128,8 +128,12 @@ hive/                                    # Repository root
 │
 ├── .github/                             # GitHub configuration
 │   ├── workflows/
-│   │   ├── ci.yml                       # Runs on every PR
-│   │   └── release.yml                  # Runs on tags
+│   │   ├── ci.yml                       # Lint, test, validate on every PR
+│   │   ├── release.yml                  # Runs on tags
+│   │   ├── pr-requirements.yml          # PR requirement checks
+│   │   ├── pr-check-command.yml         # PR check commands
+│   │   ├── claude-issue-triage.yml      # Automated issue triage
+│   │   └── auto-close-duplicates.yml    # Close duplicate issues
 │   ├── ISSUE_TEMPLATE/                  # Bug report & feature request templates
 │   ├── PULL_REQUEST_TEMPLATE.md         # PR description template
 │   └── CODEOWNERS                       # Auto-assign reviewers
@@ -166,7 +170,6 @@ hive/                                    # Repository root
 │   │   ├── testing/                     # Testing utilities
 │   │   └── __init__.py
 │   ├── pyproject.toml                   # Package metadata and dependencies
-│   ├── requirements.txt                 # Python dependencies
 │   ├── README.md                        # Framework documentation
 │   ├── MCP_INTEGRATION_GUIDE.md         # MCP server integration guide
 │   └── docs/                            # Protocol documentation
@@ -182,7 +185,6 @@ hive/                                    # Repository root
 │   │       ├── mcp_server.py            # HTTP MCP server
 │   │       └── __init__.py
 │   ├── pyproject.toml                   # Package metadata
-│   ├── requirements.txt                 # Python dependencies
 │   └── README.md                        # Tools documentation
 │
 ├── exports/                             # AGENT PACKAGES (user-created, gitignored)
@@ -191,14 +193,16 @@ hive/                                    # Repository root
 ├── docs/                                # Documentation
 │   ├── getting-started.md               # Quick start guide
 │   ├── configuration.md                 # Configuration reference
-│   ├── architecture.md                  # System architecture
-│   └── articles/                        # Technical articles
+│   ├── architecture/                    # System architecture
+│   ├── articles/                        # Technical articles
+│   ├── quizzes/                         # Developer quizzes
+│   └── i18n/                            # Translations
 │
 ├── scripts/                             # Build & utility scripts
 │   ├── setup-python.sh                  # Python environment setup
 │   └── setup.sh                         # Legacy setup script
 │
-├── quickstart.sh                        # Install Claude Code skills
+├── quickstart.sh                        # Interactive setup wizard
 ├── ENVIRONMENT_SETUP.md                 # Complete Python setup guide
 ├── README.md                            # Project overview
 ├── DEVELOPER.md                         # This file
@@ -375,7 +379,7 @@ def test_ticket_categorization():
 - **PEP 8** - Follow Python style guide
 - **Type hints** - Use for function signatures and class attributes
 - **Docstrings** - Document classes and public functions
-- **Black** - Code formatter (run with `black .`)
+- **Ruff** - Linter and formatter (run with `make check`)
 
 ```python
 # Good
@@ -509,8 +513,8 @@ chore(deps): update React to 18.2.0
 
 1. Create a feature branch from `main`
 2. Make your changes with clear commits
-3. Run tests locally: `PYTHONPATH=core:exports python -m pytest`
-4. Run linting: `black --check .`
+3. Run tests locally: `make test`
+4. Run linting: `make check`
 5. Push and create a PR
 6. Fill out the PR template
 7. Request review from CODEOWNERS
@@ -528,16 +532,11 @@ chore(deps): update React to 18.2.0
 ```bash
 # Add to core framework
 cd core
-pip install <package>
-# Then add to requirements.txt or pyproject.toml
+uv add <package>
 
 # Add to tools package
 cd tools
-pip install <package>
-# Then add to requirements.txt or pyproject.toml
-
-# Reinstall in editable mode
-pip install -e .
+uv add <package>
 ```
 
 ### Creating a New Agent
@@ -670,9 +669,8 @@ cat .env
 # Or check shell environment
 echo $ANTHROPIC_API_KEY
 
-# Copy from .env.example if needed
-cp .env.example .env
-# Then edit .env with your API keys
+# Create .env if needed
+# Then add your API keys
 ```
 
 

ENVIRONMENT_SETUP.md

@@ -21,6 +21,43 @@ This will:
 - Fix package compatibility issues (openai + litellm)
 - Verify all installations
 
+## Quick Setup (Windows – PowerShell)
+
+Windows users can use the native PowerShell setup script.
+
+Before running the script, allow script execution for the current session:
+
+```powershell
+Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass
+```
+
+Run setup from the project root:
+
+```powershell
+./scripts/setup-python.ps1
+```
+
+This will:
+
+- Check Python version (requires 3.11+)
+- Create a local `.venv` virtual environment
+- Install the core framework package (`framework`)
+- Install the tools package (`aden_tools`)
+- Fix package compatibility issues (openai + litellm)
+- Verify all installations
+
+After setup, activate the virtual environment:
+
+```powershell
+.\.venv\Scripts\Activate.ps1
+```
+
+Set `PYTHONPATH` (required in every new PowerShell session):
+
+```powershell
+$env:PYTHONPATH="core;exports"
+```
+
 ## Alpine Linux Setup
 
 If you are using Alpine Linux (e.g., inside a Docker container), you must install system dependencies and use a virtual environment before running the setup script:
@@ -100,6 +137,12 @@ For running agents with real LLMs:
 export ANTHROPIC_API_KEY="your-key-here"
 ```
 
+Windows (PowerShell):
+
+```powershell
+$env:ANTHROPIC_API_KEY="your-key-here"
+```
+
 ## Running Agents
 
 All agent commands must be run from the project root with `PYTHONPATH` set:
@@ -109,9 +152,14 @@ All agent commands must be run from the project root with `PYTHONPATH` set:
 PYTHONPATH=core:exports python -m agent_name COMMAND
 ```
 
-### Example Commands
+Windows (PowerShell):
 
-After building an agent via `/building-agents-construction`, use these commands:
+```powershell
+$env:PYTHONPATH="core;exports"
+python -m agent_name COMMAND
+```
+
+### Example: Support Ticket Agent
 
 ```bash
 # Validate agent structure
@@ -248,6 +296,14 @@ source .venv/bin/activate
 PYTHONPATH=core:exports python -m your_agent_name demo
 ```
 
+### PowerShell: “running scripts is disabled on this system”
+
+Run once per session:
+
+```powershell
+Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass
+```
+
 ### "ModuleNotFoundError: No module named 'framework'"
 
 **Solution:** Install the core package:
@@ -270,6 +326,12 @@ Or run the setup script:
 ./quickstart.sh
 ```
 
+Windows:
+
+```powershell
+./scripts/setup-python.ps1
+```
+
 ### "ModuleNotFoundError: No module named 'openai.\_models'"
 
 **Cause:** Outdated `openai` package (0.27.x) incompatible with `litellm`
@@ -284,12 +346,21 @@ pip install --upgrade "openai>=1.0.0"
 
 **Cause:** Not running from project root, missing PYTHONPATH, or agent not yet created
 
-**Solution:** Ensure you're in the project root directory, have built an agent, and use:
+**Solution:** Ensure you're in `/hive/` and use:
+
+Linux/macOS:
 
 ```bash
 PYTHONPATH=core:exports python -m your_agent_name validate
 ```
 
+Windows:
+
+```powershell
+$env:PYTHONPATH="core;exports"
+python -m support_ticket_agent validate
+```
+
 ### Agent imports fail with "broken installation"
 
 **Symptom:** `pip list` shows packages pointing to non-existent directories
@@ -304,6 +375,12 @@ pip uninstall -y framework tools
 ./quickstart.sh
 ```
 
+Windows:
+
+```powershell
+./scripts/setup-python.ps1
+```
+
 ## Package Structure
 
 The Hive framework consists of three Python packages:
@@ -402,6 +479,12 @@ This design allows agents in `exports/` to be:
 ./quickstart.sh
 ```
 
+Windows:
+
+```powershell
+./scripts/setup-python.ps1
+```
+
 ### 2. Build Agent (Claude Code)
 
 ```

README.md

@@ -15,7 +15,6 @@
 
 [![Apache 2.0 License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/adenhq/hive/blob/main/LICENSE)
 [![Y Combinator](https://img.shields.io/badge/Y%20Combinator-Aden-orange)](https://www.ycombinator.com/companies/aden)
-[![Docker Pulls](https://img.shields.io/docker/pulls/adenhq/hive?logo=Docker&labelColor=%23528bff)](https://hub.docker.com/u/adenhq)
 [![Discord](https://img.shields.io/discord/1172610340073242735?logo=discord&labelColor=%235462eb&logoColor=%23f5f5f5&color=%235462eb)](https://discord.com/invite/MXE49hrKDk)
 [![Twitter Follow](https://img.shields.io/twitter/follow/teamaden?logo=X&color=%23f5f5f5)](https://x.com/aden_hq)
 [![LinkedIn](https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff)](https://www.linkedin.com/company/teamaden/)
@@ -40,6 +39,31 @@ Build reliable, self-improving AI agents without hardcoding workflows. Define yo
 
 Visit [adenhq.com](https://adenhq.com) for complete documentation, examples, and guides.
 
+## Who Is Hive For?
+
+Hive is designed for developers and teams who want to build **production-grade AI agents** without manually wiring complex workflows.
+
+Hive is a good fit if you:
+
+- Want AI agents that **execute real business processes**, not demos
+- Prefer **goal-driven development** over hardcoded workflows
+- Need **self-healing and adaptive agents** that improve over time
+- Require **human-in-the-loop control**, observability, and cost limits
+- Plan to run agents in **production environments**
+
+Hive may not be the best fit if you’re only experimenting with simple agent chains or one-off scripts.
+
+## When Should You Use Hive?
+
+Use Hive when you need:
+
+- Long-running, autonomous agents
+- Multi-agent coordination
+- Continuous improvement based on failures
+- Strong monitoring, safety, and budget controls
+- A framework that evolves with your goals
+
+
 ## What is Aden
 
 <p align="center">

ROADMAP.md

@@ -268,7 +268,7 @@ classDef done fill:#9e9e9e,color:#fff,stroke:#757575
     - [ ] Wake-up Tool (resume agent tasks)
 
 ### Deployment (Self-Hosted)
-- [ ] Docker container standardization
+- [ ] Workder agent docker container standardization
 - [ ] Headless backend execution
 - [ ] Exposed API for frontend attachment
 - [ ] Local monitoring & observability

core/framework/graph/safe_eval.py

@@ -75,16 +75,6 @@ class SafeEvalVisitor(ast.NodeVisitor):
     def visit_Constant(self, node: ast.Constant) -> Any:
         return node.value
 
-    # --- Number/String/Bytes/NameConstant (Python < 3.8 compat if needed) ---
-    def visit_Num(self, node: ast.Num) -> Any:
-        return node.n
-
-    def visit_Str(self, node: ast.Str) -> Any:
-        return node.s
-
-    def visit_NameConstant(self, node: ast.NameConstant) -> Any:
-        return node.value
-
     # --- Data Structures ---
     def visit_List(self, node: ast.List) -> list:
         return [self.visit(elt) for elt in node.elts]

core/framework/llm/litellm.py

@@ -378,11 +378,18 @@ class LiteLLMProvider(LLMProvider):
 
             # Execute tools and add results.
             for tool_call in message.tool_calls:
-                # Parse arguments
                 try:
                     args = json.loads(tool_call.function.arguments)
                 except json.JSONDecodeError:
-                    args = {}
+                    # Surface error to LLM and skip tool execution
+                    current_messages.append(
+                        {
+                            "role": "tool",
+                            "tool_call_id": tool_call.id,
+                            "content": "Invalid JSON arguments provided to tool.",
+                        }
+                    )
+                    continue
 
                 tool_use = ToolUse(
                     id=tool_call.id,

core/framework/storage/concurrent.py

@@ -167,14 +167,18 @@ class ConcurrentStorage:
             run: Run to save
             immediate: If True, save immediately (bypasses batching)
         """
+        # Invalidate summary cache since the run data is changing
+        # This ensures load_summary() fetches fresh data after the save
+        self._cache.pop(f"summary:{run.id}", None)
+
         if immediate or not self._running:
             await self._save_run_locked(run)
+            # Update cache only after successful immediate write
+            self._cache[f"run:{run.id}"] = CacheEntry(run, time.time())
         else:
+            # For batched writes, cache will be updated in _flush_batch after successful write
             await self._write_queue.put(("run", run))
 
-        # Update cache
-        self._cache[f"run:{run.id}"] = CacheEntry(run, time.time())
-
     async def _save_run_locked(self, run: Run) -> None:
         """Save a run with file locking, including index locks."""
         lock_key = f"run:{run.id}"
@@ -363,8 +367,12 @@ class ConcurrentStorage:
             try:
                 if item_type == "run":
                     await self._save_run_locked(item)
+                    # Update cache only after successful batched write
+                    # This fixes the race condition where cache was updated before write completed
+                    self._cache[f"run:{item.id}"] = CacheEntry(item, time.time())
             except Exception as e:
                 logger.error(f"Failed to save {item_type}: {e}")
+                # Cache is NOT updated on failure - prevents stale/inconsistent cache state
 
     async def _flush_pending(self) -> None:
         """Flush all pending writes."""

core/tests/test_concurrent_storage.py

@@ -0,0 +1,162 @@
+"""Tests for ConcurrentStorage race condition and cache invalidation fixes."""
+
+import asyncio
+from pathlib import Path
+
+import pytest
+
+from framework.schemas.run import Run, RunMetrics, RunStatus
+from framework.storage.concurrent import ConcurrentStorage
+
+
+def create_test_run(
+    run_id: str, goal_id: str = "test-goal", status: RunStatus = RunStatus.RUNNING
+) -> Run:
+    """Create a minimal test Run object."""
+    return Run(
+        id=run_id,
+        goal_id=goal_id,
+        status=status,
+        narrative="Test run",
+        metrics=RunMetrics(
+            nodes_executed=[],
+        ),
+        decisions=[],
+        problems=[],
+    )
+
+
+@pytest.mark.asyncio
+async def test_cache_invalidation_on_save(tmp_path: Path):
+    """Test that summary cache is invalidated when a run is saved.
+
+    This tests the fix for the cache invalidation bug where load_summary()
+    would return stale data after a run was updated.
+    """
+    storage = ConcurrentStorage(tmp_path)
+    await storage.start()
+
+    try:
+        run_id = "test-run-1"
+
+        # Create and save initial run
+        run = create_test_run(run_id, status=RunStatus.RUNNING)
+        await storage.save_run(run, immediate=True)
+
+        # Load summary to populate the cache
+        summary = await storage.load_summary(run_id)
+        assert summary is not None
+        assert summary.status == RunStatus.RUNNING
+
+        # Update run with new status
+        run.status = RunStatus.COMPLETED
+        await storage.save_run(run, immediate=True)
+
+        # Load summary again - should get fresh data, not cached stale data
+        summary = await storage.load_summary(run_id)
+        assert summary is not None
+        assert summary.status == RunStatus.COMPLETED, (
+            "Summary cache should be invalidated on save - got stale data"
+        )
+    finally:
+        await storage.stop()
+
+
+@pytest.mark.asyncio
+async def test_batched_write_cache_consistency(tmp_path: Path):
+    """Test that cache is only updated after successful batched write.
+
+    This tests the fix for the race condition where cache was updated
+    before the batched write completed.
+    """
+    storage = ConcurrentStorage(tmp_path, batch_interval=0.05)
+    await storage.start()
+
+    try:
+        run_id = "test-run-2"
+
+        # Save via batching (immediate=False)
+        run = create_test_run(run_id, status=RunStatus.RUNNING)
+        await storage.save_run(run, immediate=False)
+
+        # Before batch flush, cache should NOT contain the run
+        # (This is the fix - previously cache was updated immediately)
+        cache_key = f"run:{run_id}"
+        assert cache_key not in storage._cache, (
+            "Cache should not be updated before batch is flushed"
+        )
+
+        # Wait for batch to flush
+        await asyncio.sleep(0.1)
+
+        # After batch flush, cache should contain the run
+        assert cache_key in storage._cache, "Cache should be updated after batch flush"
+
+        # Verify data on disk matches cache
+        loaded_run = await storage.load_run(run_id, use_cache=False)
+        assert loaded_run is not None
+        assert loaded_run.id == run_id
+        assert loaded_run.status == RunStatus.RUNNING
+    finally:
+        await storage.stop()
+
+
+@pytest.mark.asyncio
+async def test_immediate_write_updates_cache(tmp_path: Path):
+    """Test that immediate writes still update cache correctly."""
+    storage = ConcurrentStorage(tmp_path)
+    await storage.start()
+
+    try:
+        run_id = "test-run-3"
+
+        # Save with immediate=True
+        run = create_test_run(run_id, status=RunStatus.COMPLETED)
+        await storage.save_run(run, immediate=True)
+
+        # Cache should be updated immediately for immediate writes
+        cache_key = f"run:{run_id}"
+        assert cache_key in storage._cache, "Cache should be updated after immediate write"
+
+        # Verify cached value is correct
+        cached_run = storage._cache[cache_key].value
+        assert cached_run.id == run_id
+        assert cached_run.status == RunStatus.COMPLETED
+    finally:
+        await storage.stop()
+
+
+@pytest.mark.asyncio
+async def test_summary_cache_invalidated_on_multiple_saves(tmp_path: Path):
+    """Test that summary cache is invalidated on each save, not just the first."""
+    storage = ConcurrentStorage(tmp_path)
+    await storage.start()
+
+    try:
+        run_id = "test-run-4"
+
+        # First save
+        run = create_test_run(run_id, status=RunStatus.RUNNING)
+        await storage.save_run(run, immediate=True)
+
+        # Load summary to cache it
+        summary1 = await storage.load_summary(run_id)
+        assert summary1.status == RunStatus.RUNNING
+
+        # Second save with new status
+        run.status = RunStatus.RUNNING
+        await storage.save_run(run, immediate=True)
+
+        # Load summary - should be fresh
+        summary2 = await storage.load_summary(run_id)
+        assert summary2.status == RunStatus.RUNNING
+
+        # Third save with final status
+        run.status = RunStatus.COMPLETED
+        await storage.save_run(run, immediate=True)
+
+        # Load summary - should be fresh again
+        summary3 = await storage.load_summary(run_id)
+        assert summary3.status == RunStatus.COMPLETED
+    finally:
+        await storage.stop()

core/tests/test_litellm_provider.py

@@ -209,6 +209,62 @@ class TestLiteLLMProviderToolUse:
         assert result.output_tokens == 25  # 15 + 10
         assert mock_completion.call_count == 2
 
+    @patch("litellm.completion")
+    def test_complete_with_tools_invalid_json_arguments_are_handled(self, mock_completion):
+        """Test that invalid JSON tool arguments do not execute the tool."""
+        # Mock response with invalid JSON arguments
+        tool_call_response = MagicMock()
+        tool_call_response.choices = [MagicMock()]
+        tool_call_response.choices[0].message.content = None
+        tool_call_response.choices[0].message.tool_calls = [MagicMock()]
+        tool_call_response.choices[0].message.tool_calls[0].id = "call_123"
+        tool_call_response.choices[0].message.tool_calls[0].function.name = "test_tool"
+        tool_call_response.choices[0].message.tool_calls[0].function.arguments = "{invalid json"
+        tool_call_response.choices[0].finish_reason = "tool_calls"
+        tool_call_response.model = "gpt-4o-mini"
+        tool_call_response.usage.prompt_tokens = 10
+        tool_call_response.usage.completion_tokens = 5
+
+        # Final response (LLM continues after tool error)
+        final_response = MagicMock()
+        final_response.choices = [MagicMock()]
+        final_response.choices[0].message.content = "Handled error"
+        final_response.choices[0].message.tool_calls = None
+        final_response.choices[0].finish_reason = "stop"
+        final_response.model = "gpt-4o-mini"
+        final_response.usage.prompt_tokens = 5
+        final_response.usage.completion_tokens = 5
+
+        mock_completion.side_effect = [tool_call_response, final_response]
+
+        provider = LiteLLMProvider(model="gpt-4o-mini", api_key="test-key")
+
+        tools = [
+            Tool(
+                name="test_tool",
+                description="Test tool",
+                parameters={"properties": {}, "required": []},
+            )
+        ]
+
+        called = {"value": False}
+
+        def tool_executor(tool_use: ToolUse) -> ToolResult:
+            called["value"] = True
+            return ToolResult(
+                tool_use_id=tool_use.id, content="should not be called", is_error=False
+            )
+
+        result = provider.complete_with_tools(
+            messages=[{"role": "user", "content": "Run tool"}],
+            system="You are a test assistant.",
+            tools=tools,
+            tool_executor=tool_executor,
+        )
+
+        assert called["value"] is False
+        assert result.content == "Handled error"
+
 
 class TestToolConversion:
     """Test tool format conversion."""

docs/articles/building-production-ai-agents.md

@@ -362,7 +362,6 @@ class AgentRequest(BaseModel):
             raise ValueError('max_tokens too high')
         return v
 ```
-
 ### Output Sanitization
 > **Note:** The following snippet is illustrative and shows a simplified example
 > of output sanitization logic. Actual implementations may differ.

docs/i18n/es.md

@@ -14,7 +14,6 @@
 
 [![Apache 2.0 License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/adenhq/hive/blob/main/LICENSE)
 [![Y Combinator](https://img.shields.io/badge/Y%20Combinator-Aden-orange)](https://www.ycombinator.com/companies/aden)
-[![Docker Pulls](https://img.shields.io/docker/pulls/adenhq/hive?logo=Docker&labelColor=%23528bff)](https://hub.docker.com/u/adenhq)
 [![Discord](https://img.shields.io/discord/1172610340073242735?logo=discord&labelColor=%235462eb&logoColor=%23f5f5f5&color=%235462eb)](https://discord.com/invite/MXE49hrKDk)
 [![Twitter Follow](https://img.shields.io/twitter/follow/teamaden?logo=X&color=%23f5f5f5)](https://x.com/aden_hq)
 [![LinkedIn](https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff)](https://www.linkedin.com/company/teamaden/)
@@ -66,7 +65,6 @@ Aden es una plataforma para construir, desplegar, operar y adaptar agentes de IA
 ### Prerrequisitos
 
 - [Python 3.11+](https://www.python.org/downloads/) - Para desarrollo de agentes
-- [Docker](https://docs.docker.com/get-docker/) (v20.10+) - Opcional, para herramientas en contenedores
 
 ### Instalación
 

examples/README.md

@@ -0,0 +1,41 @@
+# Examples
+
+This directory contains two types of examples to help you build agents with the Hive framework.
+
+## Recipes vs Templates
+
+### [recipes/](recipes/) — "How to make it"
+
+A recipe is a **prompt-only** description of an agent. It tells you the goal, the nodes, the prompts, the edge routing logic, and what tools to wire in — but it's not runnable code. You read the recipe, then build the agent yourself.
+
+Use recipes when you want to:
+- Understand a pattern before committing to an implementation
+- Adapt an idea to your own codebase or tooling
+- Learn how to think about agent design (goals, nodes, edges, prompts)
+
+### [templates/](templates/) — "Ready to eat"
+
+A template is a **working agent scaffold** that follows the standard Hive export structure. Copy the folder, rename it, swap in your own prompts and tools, and run it.
+
+Use templates when you want to:
+- Get a new agent running quickly
+- Start from a known-good structure instead of from scratch
+- See how all the pieces (goal, nodes, edges, config, CLI) fit together in real code
+
+## How to use a template
+
+```bash
+# 1. Copy the template
+cp -r examples/templates/marketing_agent exports/my_agent
+
+# 2. Edit the goal, nodes, and edges in agent.py and nodes/__init__.py
+
+# 3. Run it
+PYTHONPATH=core python -m exports.my_agent --help
+```
+
+## How to use a recipe
+
+1. Read the recipe markdown file
+2. Use the patterns described to build your own agent — either manually or with the builder agent (`/agent-workflow`)
+3. Refer to the [core README](../core/README.md) for framework API details

examples/recipes/README.md

@@ -0,0 +1,27 @@
+# Recipes
+
+A recipe describes an agent's design — the goal, nodes, prompts, edge logic, and tools — without providing runnable code. Think of it as a blueprint: it tells you *how* to build the agent, but you do the building.
+
+## What's in a recipe
+
+Each recipe is a markdown file (or folder with a markdown file) containing:
+
+- **Goal**: What the agent accomplishes, including success criteria and constraints
+- **Nodes**: Each step in the workflow, with the system prompt, node type, and input/output keys
+- **Edges**: How nodes connect, including conditions and routing logic
+- **Tools**: What external tools or MCP servers the agent needs
+- **Usage notes**: Tips, gotchas, and suggested variations
+
+## How to use a recipe
+
+1. Read through the recipe to understand the design
+2. Create a new agent using the standard export structure (see [templates/](../templates/) for a scaffold)
+3. Translate the recipe's goal, nodes, and edges into code
+4. Wire in the tools described
+5. Test and iterate
+
+## Available recipes
+
+| Recipe | Description |
+|--------|-------------|
+| [marketing_agent](marketing_agent/) | Multi-channel marketing content generator with audience analysis and A/B copy variants |

examples/recipes/marketing_agent/README.md

@@ -0,0 +1,156 @@
+# Recipe: Marketing Content Agent
+
+A multi-channel marketing content generator. Given a product description and target audience, this agent analyzes the audience, generates tailored copy for multiple channels, and produces A/B variants.
+
+## Goal
+
+```
+Name:        Marketing Content Generator
+Description: Generate targeted marketing content across multiple channels
+             for a given product and audience.
+
+Success criteria:
+  - Audience analysis is produced with demographics and pain points
+  - At least 2 channel-specific content pieces are generated
+  - A/B variants are provided for each piece
+  - All content aligns with the specified brand voice
+
+Constraints:
+  - (hard) No competitor brand names in generated content
+  - (soft) Content should be under 280 characters for social media channels
+```
+
+## Input / Output
+
+**Input:**
+- `product_description` (str) — What the product is and does
+- `target_audience` (str) — Who the content is for
+- `brand_voice` (str) — Tone and style guidelines (e.g., "professional but approachable")
+- `channels` (list[str]) — Target channels, e.g. `["email", "twitter", "linkedin"]`
+
+**Output:**
+- `audience_analysis` (dict) — Demographics, pain points, motivations
+- `content` (list[dict]) — Per-channel content with A/B variants
+
+## Workflow
+
+```
+[analyze_audience] → [generate_content] → [review_and_refine]
+                                               |
+                                          (conditional)
+                                               |
+                              needs_revision == True → [generate_content]
+                              needs_revision == False → (done)
+```
+
+## Nodes
+
+### 1. analyze_audience
+
+| Field | Value |
+|-------|-------|
+| Type | `llm_generate` |
+| Input keys | `product_description`, `target_audience` |
+| Output keys | `audience_analysis` |
+| Tools | None |
+
+**System prompt:**
+```
+You are a marketing strategist. Analyze the target audience for a product.
+
+Product: {product_description}
+Target audience: {target_audience}
+
+Produce a structured analysis in JSON:
+{{
+  "audience_analysis": {{
+    "demographics": "...",
+    "pain_points": ["..."],
+    "motivations": ["..."],
+    "preferred_channels": ["..."],
+    "messaging_angle": "..."
+  }}
+}}
+```
+
+### 2. generate_content
+
+| Field | Value |
+|-------|-------|
+| Type | `llm_generate` |
+| Input keys | `product_description`, `audience_analysis`, `brand_voice`, `channels` |
+| Output keys | `content` |
+| Tools | None |
+
+**System prompt:**
+```
+You are a marketing copywriter. Generate content for each channel.
+
+Product: {product_description}
+Audience analysis: {audience_analysis}
+Brand voice: {brand_voice}
+Channels: {channels}
+
+For each channel, produce two variants (A and B).
+
+Output as JSON:
+{{
+  "content": [
+    {{
+      "channel": "twitter",
+      "variant_a": "...",
+      "variant_b": "..."
+    }}
+  ]
+}}
+```
+
+### 3. review_and_refine
+
+| Field | Value |
+|-------|-------|
+| Type | `llm_generate` |
+| Input keys | `content`, `brand_voice` |
+| Output keys | `content`, `needs_revision` |
+| Tools | None |
+
+**System prompt:**
+```
+You are a senior marketing editor. Review the following content for brand
+voice alignment, clarity, and channel appropriateness.
+
+Content: {content}
+Brand voice: {brand_voice}
+
+If any piece needs revision, fix it and set needs_revision to true.
+If everything looks good, return the content unchanged with needs_revision false.
+
+Output as JSON:
+{{
+  "content": [...],
+  "needs_revision": false
+}}
+```
+
+## Edges
+
+| Source | Target | Condition | Priority |
+|--------|--------|-----------|----------|
+| analyze_audience | generate_content | `on_success` | 0 |
+| generate_content | review_and_refine | `on_success` | 0 |
+| review_and_refine | generate_content | `conditional: needs_revision == True` | 10 |
+
+The `review_and_refine → generate_content` loop has higher priority so it's checked first. If `needs_revision` is false, execution ends at `review_and_refine` (terminal node).
+
+## Tools
+
+This recipe uses no external tools — all nodes are `llm_generate`. To extend it, consider adding:
+- A web search tool for competitive analysis in the `analyze_audience` node
+- A URL shortener tool for social media content
+- An image generation tool for visual content variants
+
+## Variations
+
+- **Single-channel mode**: Remove the `channels` input and hardcode to one channel for simpler output
+- **With approval gate**: Add a `human_input` node between `review_and_refine` and the terminal to require human sign-off
+- **With analytics**: Add a `function` node that logs generated content to a tracking system

examples/templates/README.md

@@ -0,0 +1,38 @@
+# Templates
+
+A template is a working agent scaffold that follows the standard Hive export structure. Copy it, rename it, customize the goal/nodes/edges, and run it.
+
+## What's in a template
+
+Each template is a complete agent package:
+
+```
+template_name/
+├── __init__.py       # Package exports
+├── __main__.py       # CLI entry point
+├── agent.py          # Goal, edges, graph spec, agent class
+├── config.py         # Runtime configuration
+├── nodes/
+│   └── __init__.py   # Node definitions (NodeSpec instances)
+└── README.md         # What this template demonstrates
+```
+
+## How to use a template
+
+```bash
+# 1. Copy to your exports directory
+cp -r examples/templates/marketing_agent exports/my_marketing_agent
+
+# 2. Update the module references in __main__.py and __init__.py
+
+# 3. Customize goal, nodes, edges, and prompts
+
+# 4. Run it
+PYTHONPATH=core python -m exports.my_marketing_agent --input '{"product_description": "..."}'
+```
+
+## Available templates
+
+| Template | Description |
+|----------|-------------|
+| [marketing_agent](marketing_agent/) | Multi-channel marketing content generator with audience analysis, content generation, and editorial review nodes |

examples/templates/marketing_agent/README.md

@@ -0,0 +1,57 @@
+# Template: Marketing Content Agent
+
+A multi-channel marketing content generator. Given a product and audience, this agent analyzes the audience, generates tailored copy for multiple channels with A/B variants, and reviews the output for quality.
+
+## Workflow
+
+```
+[analyze-audience] → [generate-content] → [review-and-refine]
+                                                |
+                                           (conditional)
+                                                |
+                               needs_revision == True → [generate-content]
+                               needs_revision == False → (done)
+```
+
+## Nodes
+
+| Node | Type | Description |
+|------|------|-------------|
+| `analyze-audience` | `llm_generate` | Produces structured audience analysis |
+| `generate-content` | `llm_generate` | Creates per-channel copy with A/B variants |
+| `review-and-refine` | `llm_generate` | Reviews and optionally revises content |
+
+## Usage
+
+```bash
+# From the repo root
+PYTHONPATH=core python -m examples.templates.marketing_agent
+
+# With custom input
+PYTHONPATH=core python -m examples.templates.marketing_agent --input '{
+  "product_description": "A fitness tracking app",
+  "target_audience": "Health-conscious millennials",
+  "brand_voice": "Energetic and motivational",
+  "channels": ["instagram", "email"]
+}'
+```
+
+## Customization ideas
+
+- Add a `function` node to call an analytics API and inform audience analysis with real data
+- Add a `human_input` pause node before final output for editorial approval
+- Swap `llm_generate` nodes to `llm_tool_use` and add web search tools for competitive research
+- Add an image generation tool to produce visual assets alongside copy
+
+## File structure
+
+```
+marketing_agent/
+├── __init__.py       # Package exports
+├── __main__.py       # CLI entry point
+├── agent.py          # Goal, edges, graph spec, MarketingAgent class
+├── config.py         # RuntimeConfig and AgentMetadata
+├── nodes/
+│   └── __init__.py   # NodeSpec definitions
+└── README.md         # This file
+```

examples/templates/marketing_agent/__init__.py

@@ -0,0 +1,6 @@
+"""Marketing Content Agent — template example."""
+
+from .agent import MarketingAgent, goal, edges, nodes
+from .config import default_config
+
+__all__ = ["MarketingAgent", "goal", "edges", "nodes", "default_config"]

examples/templates/marketing_agent/__main__.py

@@ -0,0 +1,31 @@
+"""CLI entry point for Marketing Content Agent."""
+
+import asyncio
+import json
+import sys
+
+
+def main():
+    from .agent import MarketingAgent
+    from .config import default_config
+
+    # Simple CLI — replace with Click for production use
+    input_data = {
+        "product_description": "An AI-powered project management tool for remote teams",
+        "target_audience": "Engineering managers at mid-size tech companies",
+        "brand_voice": "Professional but approachable, concise, data-driven",
+        "channels": ["email", "twitter", "linkedin"],
+    }
+
+    # Accept JSON input from command line
+    if len(sys.argv) > 1 and sys.argv[1] == "--input":
+        input_data = json.loads(sys.argv[2])
+
+    agent = MarketingAgent(config=default_config)
+    result = asyncio.run(agent.run(input_data))
+
+    print(json.dumps(result, indent=2))
+
+
+if __name__ == "__main__":
+    main()

examples/templates/marketing_agent/agent.py

@@ -0,0 +1,161 @@
+"""Marketing Content Agent — goal, edges, graph spec, and agent class."""
+
+from pathlib import Path
+
+from framework.graph import EdgeCondition, EdgeSpec, Goal, SuccessCriterion, Constraint
+from framework.graph.edge import GraphSpec
+from framework.graph.executor import GraphExecutor
+from framework.runtime.core import Runtime
+from framework.llm.anthropic import AnthropicProvider
+
+from .config import default_config, RuntimeConfig
+from .nodes import all_nodes
+
+# ---------------------------------------------------------------------------
+# Goal
+# ---------------------------------------------------------------------------
+goal = Goal(
+    id="marketing-content",
+    name="Marketing Content Generator",
+    description=(
+        "Generate targeted marketing content across multiple channels "
+        "for a given product and audience."
+    ),
+    success_criteria=[
+        SuccessCriterion(
+            id="audience-analyzed",
+            description="Audience analysis is produced with demographics and pain points",
+            metric="output_contains",
+            target="audience_analysis",
+        ),
+        SuccessCriterion(
+            id="content-generated",
+            description="At least 2 channel-specific content pieces are generated",
+            metric="custom",
+            target="len(content) >= 2",
+        ),
+        SuccessCriterion(
+            id="variants-provided",
+            description="A/B variants are provided for each content piece",
+            metric="custom",
+            target="all variants present",
+        ),
+    ],
+    constraints=[
+        Constraint(
+            id="no-competitor-names",
+            description="No competitor brand names in generated content",
+            constraint_type="hard",
+            category="safety",
+        ),
+        Constraint(
+            id="social-length",
+            description="Social media content should be under 280 characters",
+            constraint_type="soft",
+            category="quality",
+        ),
+    ],
+    input_schema={
+        "product_description": {"type": "string"},
+        "target_audience": {"type": "string"},
+        "brand_voice": {"type": "string"},
+        "channels": {"type": "array", "items": {"type": "string"}},
+    },
+    output_schema={
+        "audience_analysis": {"type": "object"},
+        "content": {"type": "array"},
+    },
+)
+
+# ---------------------------------------------------------------------------
+# Edges
+# ---------------------------------------------------------------------------
+edges = [
+    EdgeSpec(
+        id="analyze-to-generate",
+        source="analyze-audience",
+        target="generate-content",
+        condition=EdgeCondition.ON_SUCCESS,
+        description="After audience analysis, generate content",
+    ),
+    EdgeSpec(
+        id="generate-to-review",
+        source="generate-content",
+        target="review-and-refine",
+        condition=EdgeCondition.ON_SUCCESS,
+        description="After content generation, review and refine",
+    ),
+    EdgeSpec(
+        id="review-to-regenerate",
+        source="review-and-refine",
+        target="generate-content",
+        condition=EdgeCondition.CONDITIONAL,
+        condition_expr="needs_revision == True",
+        priority=10,
+        description="If revision needed, loop back to content generation",
+    ),
+]
+
+# ---------------------------------------------------------------------------
+# Graph structure
+# ---------------------------------------------------------------------------
+entry_node = "analyze-audience"
+entry_points = {"start": "analyze-audience"}
+terminal_nodes = ["review-and-refine"]
+pause_nodes = []
+nodes = all_nodes
+
+
+# ---------------------------------------------------------------------------
+# Agent class
+# ---------------------------------------------------------------------------
+class MarketingAgent:
+    """Multi-channel marketing content generator agent."""
+
+    def __init__(self, config: RuntimeConfig | None = None):
+        self.config = config or default_config
+        self.goal = goal
+        self.nodes = nodes
+        self.edges = edges
+        self.entry_node = entry_node
+        self.terminal_nodes = terminal_nodes
+        self.executor = None
+
+    def _build_graph(self) -> GraphSpec:
+        return GraphSpec(
+            id="marketing-content-graph",
+            goal_id=self.goal.id,
+            entry_node=self.entry_node,
+            entry_points=entry_points,
+            terminal_nodes=self.terminal_nodes,
+            pause_nodes=pause_nodes,
+            nodes=self.nodes,
+            edges=self.edges,
+            default_model=self.config.model,
+            max_tokens=self.config.max_tokens,
+            description="Marketing content generation workflow",
+        )
+
+    def _create_executor(self):
+        runtime = Runtime(storage_path=Path(self.config.storage_path).expanduser())
+        llm = AnthropicProvider(model=self.config.model)
+        self.executor = GraphExecutor(runtime=runtime, llm=llm)
+        return self.executor
+
+    async def run(self, context: dict, mock_mode: bool = False) -> dict:
+        graph = self._build_graph()
+        executor = self._create_executor()
+        result = await executor.execute(
+            graph=graph,
+            goal=self.goal,
+            input_data=context,
+        )
+        return {
+            "success": result.success,
+            "output": result.output,
+            "steps": result.steps_executed,
+            "path": result.path,
+        }
+
+
+default_agent = MarketingAgent()

examples/templates/marketing_agent/config.py

@@ -0,0 +1,24 @@
+"""Runtime configuration for Marketing Content Agent."""
+
+from dataclasses import dataclass, field
+
+
+@dataclass
+class RuntimeConfig:
+    model: str = "claude-haiku-4-5-20251001"
+    max_tokens: int = 2048
+    storage_path: str = "~/.hive/storage"
+    mock_mode: bool = False
+
+
+@dataclass
+class AgentMetadata:
+    name: str = "marketing_agent"
+    version: str = "0.1.0"
+    description: str = "Multi-channel marketing content generator"
+    author: str = ""
+    tags: list[str] = field(default_factory=lambda: ["marketing", "content", "template"])
+
+
+default_config = RuntimeConfig()
+metadata = AgentMetadata()

examples/templates/marketing_agent/nodes/__init__.py

@@ -0,0 +1,106 @@
+"""Node definitions for Marketing Content Agent."""
+
+from framework.graph import NodeSpec
+
+# ---------------------------------------------------------------------------
+# Node 1: Analyze the target audience
+# ---------------------------------------------------------------------------
+analyze_audience_node = NodeSpec(
+    id="analyze-audience",
+    name="Analyze Audience",
+    description="Produce a structured audience analysis from the product and target audience description.",
+    node_type="llm_generate",
+    input_keys=["product_description", "target_audience"],
+    output_keys=["audience_analysis"],
+    system_prompt="""\
+You are a marketing strategist. Analyze the target audience for a product.
+
+Product: {product_description}
+Target audience: {target_audience}
+
+Produce a structured analysis as raw JSON (no markdown):
+{{
+  "audience_analysis": {{
+    "demographics": "...",
+    "pain_points": ["..."],
+    "motivations": ["..."],
+    "preferred_channels": ["..."],
+    "messaging_angle": "..."
+  }}
+}}
+""",
+    tools=[],
+    max_retries=2,
+)
+
+# ---------------------------------------------------------------------------
+# Node 2: Generate channel-specific content with A/B variants
+# ---------------------------------------------------------------------------
+generate_content_node = NodeSpec(
+    id="generate-content",
+    name="Generate Content",
+    description="Create marketing copy for each requested channel with two variants per channel.",
+    node_type="llm_generate",
+    input_keys=["product_description", "audience_analysis", "brand_voice", "channels"],
+    output_keys=["content"],
+    system_prompt="""\
+You are a marketing copywriter. Generate content for each channel.
+
+Product: {product_description}
+Audience analysis: {audience_analysis}
+Brand voice: {brand_voice}
+Channels: {channels}
+
+For each channel, produce two variants (A and B).
+
+Output as raw JSON (no markdown):
+{{
+  "content": [
+    {{
+      "channel": "twitter",
+      "variant_a": "...",
+      "variant_b": "..."
+    }}
+  ]
+}}
+""",
+    tools=[],
+    max_retries=2,
+)
+
+# ---------------------------------------------------------------------------
+# Node 3: Review and refine content
+# ---------------------------------------------------------------------------
+review_and_refine_node = NodeSpec(
+    id="review-and-refine",
+    name="Review and Refine",
+    description="Review generated content for brand voice alignment and channel fit. Revise if needed.",
+    node_type="llm_generate",
+    input_keys=["content", "brand_voice"],
+    output_keys=["content", "needs_revision"],
+    system_prompt="""\
+You are a senior marketing editor. Review the following content for brand
+voice alignment, clarity, and channel appropriateness.
+
+Content: {content}
+Brand voice: {brand_voice}
+
+If any piece needs revision, fix it and set needs_revision to true.
+If everything looks good, return the content unchanged with needs_revision false.
+
+Output as raw JSON (no markdown):
+{{
+  "content": [...],
+  "needs_revision": false
+}}
+""",
+    tools=[],
+    max_retries=2,
+)
+
+# All nodes for easy import
+all_nodes = [
+    analyze_audience_node,
+    generate_content_node,
+    review_and_refine_node,
+]

scripts/setup-python.ps1

@@ -0,0 +1,251 @@
+<#
+
+setup-python.ps1 - Python Environment Setup for Aden Agent Framework
+
+This script sets up the Python environment with all required packages
+for building and running goal-driven agents.
+#>
+
+$ErrorActionPreference = "Stop"
+
+# Colors for output
+$RED    = "Red"
+$GREEN  = "Green"
+$YELLOW = "Yellow"
+$BLUE   = "Cyan"
+
+# Get the directory where this script is located
+$SCRIPT_DIR = Split-Path -Parent $MyInvocation.MyCommand.Path
+$PROJECT_ROOT = Split-Path -Parent $SCRIPT_DIR
+
+Write-Host ""
+Write-Host "=================================================="
+Write-Host "  Aden Agent Framework - Python Setup"
+Write-Host "=================================================="
+Write-Host ""
+
+# Check for Python
+$pythonCmd = $null
+if (Get-Command python -ErrorAction SilentlyContinue) {
+    $pythonCmd = "python"
+}
+
+if (-not $pythonCmd) {
+    Write-Host "Error: Python is not installed." -ForegroundColor $RED
+    Write-Host "Please install Python 3.11+ from https://python.org"
+    exit 1
+}
+
+# Check Python version
+$versionInfo = & $pythonCmd -c "import sys; print(f'{sys.version_info.major}.{sys.version_info.minor}')"
+$major = & $pythonCmd -c "import sys; print(sys.version_info.major)"
+$minor = & $pythonCmd -c "import sys; print(sys.version_info.minor)"
+
+Write-Host "Detected Python: $versionInfo" -ForegroundColor $BLUE
+
+if ($major -lt 3 -or ($major -eq 3 -and $minor -lt 11)) {
+    Write-Host "Error: Python 3.11+ is required (found $versionInfo)" -ForegroundColor $RED
+    Write-Host "Please upgrade your Python installation"
+    exit 1
+}
+
+if ($minor -lt 11) {
+    Write-Host "Warning: Python 3.11+ is recommended for best compatibility" -ForegroundColor $YELLOW
+    Write-Host "You have Python $versionInfo which may work but is not officially supported" -ForegroundColor $YELLOW
+    Write-Host ""
+}
+
+Write-Host "[OK] Python version check passed" -ForegroundColor $GREEN
+Write-Host ""
+
+# Create and activate virtual environment
+Write-Host "=================================================="
+Write-Host "Setting up Python Virtual Environment"
+Write-Host "=================================================="
+Write-Host ""
+
+$VENV_PATH = Join-Path $PROJECT_ROOT ".venv"
+$VENV_PYTHON = Join-Path $VENV_PATH "Scripts\python.exe"
+$VENV_ACTIVATE = Join-Path $VENV_PATH "Scripts\Activate.ps1"
+
+if (-not (Test-Path $VENV_PYTHON)) {
+    Write-Host "Creating virtual environment at .venv..."
+    & $pythonCmd -m venv $VENV_PATH
+    Write-Host "[OK] Virtual environment created" -ForegroundColor $GREEN
+}
+else {
+    Write-Host "[OK] Virtual environment already exists" -ForegroundColor $GREEN
+}
+
+# Activate venv
+Write-Host "Activating virtual environment..."
+& $VENV_ACTIVATE
+Write-Host "[OK] Virtual environment activated" -ForegroundColor $GREEN
+
+# From here on, always use venv python
+$pythonCmd = $VENV_PYTHON
+
+Write-Host ""
+
+# Check for pip
+try {
+    & $pythonCmd -m pip --version | Out-Null
+}
+catch {
+    Write-Host "Error: pip is not installed" -ForegroundColor $RED
+    Write-Host "Please install pip for Python $versionInfo"
+    exit 1
+}
+
+Write-Host "[OK] pip detected" -ForegroundColor $GREEN
+Write-Host ""
+
+# Upgrade pip, setuptools, and wheel
+Write-Host "Upgrading pip, setuptools, and wheel..."
+& $pythonCmd -m pip install --upgrade pip setuptools wheel 
+Write-Host "[OK] Core packages upgraded" -ForegroundColor $GREEN
+Write-Host ""
+
+# Install core framework package
+Write-Host "=================================================="
+Write-Host "Installing Core Framework Package"
+Write-Host "=================================================="
+Write-Host ""
+
+Set-Location "$PROJECT_ROOT\core"
+
+if (Test-Path "pyproject.toml") {
+    Write-Host "Installing framework from core/ (editable mode)..."
+    & $pythonCmd -m pip install -e . | Out-Null
+    Write-Host "[OK] Framework package installed" -ForegroundColor $GREEN
+}
+else {
+    Write-Host "[WARN] No pyproject.toml found in core/, skipping framework installation" -ForegroundColor $YELLOW
+}
+
+Write-Host ""
+
+# Install tools package
+Write-Host "=================================================="
+Write-Host "Installing Tools Package (aden_tools)"
+Write-Host "=================================================="
+Write-Host ""
+
+Set-Location "$PROJECT_ROOT\tools"
+
+if (Test-Path "pyproject.toml") {
+    Write-Host "Installing aden_tools from tools/ (editable mode)..."
+    & $pythonCmd -m pip install -e . | Out-Null
+    Write-Host "[OK] Tools package installed" -ForegroundColor $GREEN
+}
+else {
+    Write-Host "Error: No pyproject.toml found in tools/" -ForegroundColor $RED
+    exit 1
+}
+
+Write-Host ""
+
+# Fix openai version compatibility with litellm
+Write-Host "=================================================="
+Write-Host "Fixing Package Compatibility"
+Write-Host "=================================================="
+Write-Host ""
+
+try {
+    $openaiVersion = & $pythonCmd -c "import openai; print(openai.__version__)"
+}
+catch {
+    $openaiVersion = "not_installed"
+}
+
+if ($openaiVersion -eq "not_installed") {
+    Write-Host "Installing openai package..."
+    & $pythonCmd -m pip install "openai>=1.0.0" | Out-Null
+    Write-Host "[OK] openai package installed" -ForegroundColor $GREEN
+}
+elseif ($openaiVersion.StartsWith("0.")) {
+    Write-Host "Found old openai version: $openaiVersion" -ForegroundColor $YELLOW
+    Write-Host "Upgrading to openai 1.x+ for litellm compatibility..."
+    & $pythonCmd -m pip install --upgrade "openai>=1.0.0" | Out-Null
+    $openaiVersion = & $pythonCmd -c "import openai; print(openai.__version__)"
+    Write-Host "[OK] openai upgraded to $openaiVersion" -ForegroundColor $GREEN
+}
+else {
+    Write-Host "[OK] openai $openaiVersion is compatible" -ForegroundColor $GREEN
+}
+
+Write-Host ""
+
+# Verify installations
+Write-Host "=================================================="
+Write-Host "Verifying Installation"
+Write-Host "=================================================="
+Write-Host ""
+
+Set-Location $PROJECT_ROOT
+
+# Test framework import
+& $pythonCmd -c "import framework" 2>$null
+if ($LASTEXITCODE -eq 0) {
+    Write-Host "[OK] framework package imports successfully" -ForegroundColor Green
+}
+else {
+    Write-Host "[FAIL] framework package import failed" -ForegroundColor Red
+}
+
+# Test aden_tools import
+& $pythonCmd -c "import aden_tools" 2>$null
+if ($LASTEXITCODE -eq 0) {
+    Write-Host "[OK] aden_tools package imports successfully" -ForegroundColor Green
+}
+else {
+    Write-Host "[FAIL] aden_tools package import failed" -ForegroundColor Red
+    exit 1
+}
+
+# Test litellm
+& $pythonCmd -c "import litellm" 2>$null
+if ($LASTEXITCODE -eq 0) {
+    Write-Host "[OK] litellm package imports successfully" -ForegroundColor $GREEN
+}
+else {
+    Write-Host "[WARN] litellm import had issues (may be OK if not using LLM features)" -ForegroundColor $YELLOW
+}
+
+Write-Host ""
+
+# Print agent commands
+Write-Host "=================================================="
+Write-Host "  Setup Complete!"
+Write-Host "=================================================="
+Write-Host ""
+Write-Host "Python packages installed:"
+Write-Host "  - framework (core agent runtime)"
+Write-Host "  - aden_tools (tools and MCP servers)"
+Write-Host "  - All dependencies and compatibility fixes applied"
+Write-Host ""
+Write-Host "To run agents on Windows (PowerShell):"
+Write-Host ""
+Write-Host "1. From the project root, set PYTHONPATH:"
+Write-Host "   `$env:PYTHONPATH=`"core;exports`""
+Write-Host ""
+Write-Host "2. Run an agent command:"
+Write-Host "   python -m agent_name validate"
+Write-Host "   python -m agent_name info"
+Write-Host "   python -m agent_name run --input '{...}'"
+Write-Host ""
+Write-Host "Example (support_ticket_agent):"
+Write-Host "   python -m support_ticket_agent validate"
+Write-Host "   python -m support_ticket_agent info"
+Write-Host "   python -m support_ticket_agent run --input '{""ticket_content"":""..."",""customer_id"":""..."",""ticket_id"":""...""}'"
+Write-Host ""
+Write-Host "Notes:"
+Write-Host "  - Ensure the virtual environment is activated (.venv)"
+Write-Host "  - PYTHONPATH must be set in each new PowerShell session"
+Write-Host ""
+Write-Host "Documentation:"
+Write-Host "  $PROJECT_ROOT\README.md"
+Write-Host ""
+Write-Host "Agent Examples:"
+Write-Host "  $PROJECT_ROOT\exports\"
+Write-Host ""

tools/requirements.txt

@@ -1,13 +0,0 @@
-# MCP Server
-fastmcp
-
-# Tool dependencies
-diff-match-patch
-pypdf
-beautifulsoup4
-lxml
-playwright
-playwright-stealth
-requests
-
-# Note: After installing, run `playwright install` to download browser binaries

tools/src/aden_tools/credentials/__init__.py

@@ -9,7 +9,7 @@ Philosophy: Google Strictness + Apple UX
 
 Usage:
     from aden_tools.credentials import CredentialStoreAdapter
-    from core.framework.credentials import CredentialStore
+    from framework.credentials import CredentialStore
 
     # With encrypted storage (production)
     store = CredentialStore.with_encrypted_storage()  # defaults to ~/.hive/credentials

tools/src/aden_tools/credentials/store_adapter.py

@@ -5,7 +5,7 @@ This provides backward compatibility, allowing existing tools to work unchanged
 while enabling new features (template resolution, multi-key credentials, etc.).
 
 Usage:
-    from core.framework.credentials import CredentialStore
+    from framework.credentials import CredentialStore
     from aden_tools.credentials.store_adapter import CredentialStoreAdapter
 
     # Create new credential store
@@ -31,7 +31,7 @@ from typing import TYPE_CHECKING
 from .base import CredentialError, CredentialSpec
 
 if TYPE_CHECKING:
-    from core.framework.credentials import CredentialStore
+    from framework.credentials import CredentialStore
 
 
 class CredentialStoreAdapter:
@@ -368,7 +368,7 @@ class CredentialStoreAdapter:
             credentials = CredentialStoreAdapter.for_testing({"brave_search": "test-key"})
             assert credentials.get("brave_search") == "test-key"
         """
-        from core.framework.credentials import CredentialStore
+        from framework.credentials import CredentialStore
 
         # Convert to CredentialStore.for_testing format
         # Simple credentials get a single "api_key" key
@@ -395,13 +395,14 @@ class CredentialStoreAdapter:
         Returns:
             CredentialStoreAdapter using env vars for storage
         """
-        from core.framework.credentials import CredentialStore
+        from framework.credentials import CredentialStore
 
         # Build env mapping from specs if not provided
-        if env_mapping is None and specs is None:
-            from . import CREDENTIAL_SPECS
+        if env_mapping is None:
+            if specs is None:
+                from . import CREDENTIAL_SPECS
 
-            specs = CREDENTIAL_SPECS
+                specs = CREDENTIAL_SPECS
             env_mapping = {name: spec.env_var for name, spec in specs.items()}
 
         store = CredentialStore.with_env_storage(env_mapping)

tools/src/aden_tools/tools/hubspot_tool/tests/test_hubspot_tool.py

@@ -415,13 +415,13 @@ class TestDealTools:
 
 class TestHubSpotOAuth2Provider:
     def test_provider_id(self):
-        from core.framework.credentials.oauth2.hubspot_provider import HubSpotOAuth2Provider
+        from framework.credentials.oauth2.hubspot_provider import HubSpotOAuth2Provider
 
         provider = HubSpotOAuth2Provider(client_id="cid", client_secret="csecret")
         assert provider.provider_id == "hubspot_oauth2"
 
     def test_default_scopes(self):
-        from core.framework.credentials.oauth2.hubspot_provider import (
+        from framework.credentials.oauth2.hubspot_provider import (
             HUBSPOT_DEFAULT_SCOPES,
             HubSpotOAuth2Provider,
         )
@@ -430,7 +430,7 @@ class TestHubSpotOAuth2Provider:
         assert provider.config.default_scopes == HUBSPOT_DEFAULT_SCOPES
 
     def test_custom_scopes(self):
-        from core.framework.credentials.oauth2.hubspot_provider import HubSpotOAuth2Provider
+        from framework.credentials.oauth2.hubspot_provider import HubSpotOAuth2Provider
 
         provider = HubSpotOAuth2Provider(
             client_id="cid",
@@ -440,7 +440,7 @@ class TestHubSpotOAuth2Provider:
         assert provider.config.default_scopes == ["crm.objects.contacts.read"]
 
     def test_endpoints(self):
-        from core.framework.credentials.oauth2.hubspot_provider import (
+        from framework.credentials.oauth2.hubspot_provider import (
             HUBSPOT_AUTHORIZATION_URL,
             HUBSPOT_TOKEN_URL,
             HubSpotOAuth2Provider,
@@ -451,15 +451,15 @@ class TestHubSpotOAuth2Provider:
         assert provider.config.authorization_url == HUBSPOT_AUTHORIZATION_URL
 
     def test_supported_types(self):
-        from core.framework.credentials.models import CredentialType
-        from core.framework.credentials.oauth2.hubspot_provider import HubSpotOAuth2Provider
+        from framework.credentials.models import CredentialType
+        from framework.credentials.oauth2.hubspot_provider import HubSpotOAuth2Provider
 
         provider = HubSpotOAuth2Provider(client_id="cid", client_secret="csecret")
         assert CredentialType.OAUTH2 in provider.supported_types
 
     def test_validate_no_access_token(self):
-        from core.framework.credentials.models import CredentialObject
-        from core.framework.credentials.oauth2.hubspot_provider import HubSpotOAuth2Provider
+        from framework.credentials.models import CredentialObject
+        from framework.credentials.oauth2.hubspot_provider import HubSpotOAuth2Provider
 
         provider = HubSpotOAuth2Provider(client_id="cid", client_secret="csecret")
         cred = CredentialObject(id="test")

tools/src/aden_tools/tools/web_scrape_tool/README.md

@@ -25,8 +25,6 @@ pip install playwright playwright-stealth
 playwright install chromium
 ```
 
-In Docker, add `RUN playwright install chromium --with-deps` to the Dockerfile.
-
 ## Environment Variables
 
 This tool does not require any environment variables.

tools/tests/tools/test_pdf_read_tool.py

@@ -95,6 +95,7 @@ class TestPdfReadTool:
             def __init__(self, path: Path) -> None:  # noqa: ARG002
                 self.pages = [FakePage(f"Page {i + 1}") for i in range(50)]
                 self.is_encrypted = False
+                self.metadata = None
 
         # Patch PdfReader used inside the tool so we don't need a real PDF
         from aden_tools.tools.pdf_read_tool import pdf_read_tool

tools/tests/tools/test_web_scrape_tool.py

@@ -1,6 +1,6 @@
 """Tests for web_scrape tool (FastMCP)."""
 
-from unittest.mock import MagicMock, patch
+from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 from fastmcp import FastMCP
@@ -15,60 +15,135 @@ def web_scrape_fn(mcp: FastMCP):
     return mcp._tool_manager._tools["web_scrape"].fn
 
 
+def _make_playwright_mocks(html, status=200, final_url="https://example.com/page"):
+    """Build a full playwright mock chain and return (context_manager, response, page)."""
+    mock_response = MagicMock(
+        status=status,
+        url=final_url,
+        headers={"content-type": "text/html; charset=utf-8"},
+    )
+
+    mock_page = AsyncMock()
+    mock_page.goto.return_value = mock_response
+    mock_page.content.return_value = html
+    mock_page.wait_for_timeout.return_value = None
+
+    mock_context = AsyncMock()
+    mock_context.new_page.return_value = mock_page
+
+    mock_browser = AsyncMock()
+    mock_browser.new_context.return_value = mock_context
+
+    mock_pw = MagicMock()
+    mock_pw.chromium.launch = AsyncMock(return_value=mock_browser)
+
+    # async context manager for async_playwright()
+    mock_cm = MagicMock()
+    mock_cm.__aenter__ = AsyncMock(return_value=mock_pw)
+    mock_cm.__aexit__ = AsyncMock(return_value=False)
+
+    return mock_cm, mock_response, mock_page
+
+
+_PW_PATH = "aden_tools.tools.web_scrape_tool.web_scrape_tool.async_playwright"
+_STEALTH_PATH = "aden_tools.tools.web_scrape_tool.web_scrape_tool.Stealth"
+
+
 class TestWebScrapeTool:
     """Tests for web_scrape tool."""
 
-    def test_url_auto_prefixed_with_https(self, web_scrape_fn):
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_url_auto_prefixed_with_https(self, mock_pw, mock_stealth, web_scrape_fn):
         """URLs without scheme get https:// prefix."""
-        # This will fail to connect, but we can verify the behavior
-        result = web_scrape_fn(url="example.com")
-        # Should either succeed or have a network error (not a validation error)
-        assert isinstance(result, dict)
+        html = "<html><body>Hello</body></html>"
+        mock_cm, _, _ = _make_playwright_mocks(html, final_url="https://example.com")
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
 
-    def test_max_length_clamped_low(self, web_scrape_fn):
+        result = await web_scrape_fn(url="example.com")
+        assert isinstance(result, dict)
+        assert "error" not in result
+
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_max_length_clamped_low(self, mock_pw, mock_stealth, web_scrape_fn):
         """max_length below 1000 is clamped to 1000."""
-        # Test with a very low max_length - implementation clamps to 1000
-        result = web_scrape_fn(url="https://example.com", max_length=500)
-        # Should not error due to invalid max_length
-        assert isinstance(result, dict)
+        html = "<html><body>Hello</body></html>"
+        mock_cm, _, _ = _make_playwright_mocks(html, final_url="https://example.com")
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
 
-    def test_max_length_clamped_high(self, web_scrape_fn):
+        result = await web_scrape_fn(url="https://example.com", max_length=500)
+        assert isinstance(result, dict)
+        assert "error" not in result
+
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_max_length_clamped_high(self, mock_pw, mock_stealth, web_scrape_fn):
         """max_length above 500000 is clamped to 500000."""
-        # Test with a very high max_length - implementation clamps to 500000
-        result = web_scrape_fn(url="https://example.com", max_length=600000)
-        # Should not error due to invalid max_length
-        assert isinstance(result, dict)
+        html = "<html><body>Hello</body></html>"
+        mock_cm, _, _ = _make_playwright_mocks(html, final_url="https://example.com")
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
 
-    def test_valid_max_length_accepted(self, web_scrape_fn):
+        result = await web_scrape_fn(url="https://example.com", max_length=600000)
+        assert isinstance(result, dict)
+        assert "error" not in result
+
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_valid_max_length_accepted(self, mock_pw, mock_stealth, web_scrape_fn):
         """Valid max_length values are accepted."""
-        result = web_scrape_fn(url="https://example.com", max_length=10000)
-        assert isinstance(result, dict)
+        html = "<html><body>Hello</body></html>"
+        mock_cm, _, _ = _make_playwright_mocks(html, final_url="https://example.com")
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
 
-    def test_include_links_option(self, web_scrape_fn):
+        result = await web_scrape_fn(url="https://example.com", max_length=10000)
+        assert isinstance(result, dict)
+        assert "error" not in result
+
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_include_links_option(self, mock_pw, mock_stealth, web_scrape_fn):
         """include_links parameter is accepted."""
-        result = web_scrape_fn(url="https://example.com", include_links=True)
-        assert isinstance(result, dict)
+        html = '<html><body><a href="/link">Link</a></body></html>'
+        mock_cm, _, _ = _make_playwright_mocks(html, final_url="https://example.com")
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
 
-    def test_selector_option(self, web_scrape_fn):
-        """selector parameter is accepted."""
-        result = web_scrape_fn(url="https://example.com", selector=".content")
+        result = await web_scrape_fn(url="https://example.com", include_links=True)
         assert isinstance(result, dict)
+        assert "error" not in result
+
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_selector_option(self, mock_pw, mock_stealth, web_scrape_fn):
+        """selector parameter is accepted."""
+        html = '<html><body><div class="content">Content here</div></body></html>'
+        mock_cm, _, _ = _make_playwright_mocks(html, final_url="https://example.com")
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
+
+        result = await web_scrape_fn(url="https://example.com", selector=".content")
+        assert isinstance(result, dict)
+        assert "error" not in result
 
 
 class TestWebScrapeToolLinkConversion:
     """Tests for link URL conversion (relative to absolute)."""
 
-    def _mock_response(self, html_content, final_url="https://example.com/page"):
-        """Create a mock httpx response object."""
-        mock_response = MagicMock()
-        mock_response.status_code = 200
-        mock_response.text = html_content
-        mock_response.url = final_url
-        mock_response.headers = {"content-type": "text/html; charset=utf-8"}
-        return mock_response
-
-    @patch("aden_tools.tools.web_scrape_tool.web_scrape_tool.httpx.get")
-    def test_relative_links_converted_to_absolute(self, mock_get, web_scrape_fn):
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_relative_links_converted_to_absolute(self, mock_pw, mock_stealth, web_scrape_fn):
         """Relative URLs like ../page are converted to absolute URLs."""
         html = """
         <html>
@@ -78,9 +153,11 @@ class TestWebScrapeToolLinkConversion:
             </body>
         </html>
         """
-        mock_get.return_value = self._mock_response(html, "https://example.com/blog/post")
+        mock_cm, _, _ = _make_playwright_mocks(html, final_url="https://example.com/blog/post")
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
 
-        result = web_scrape_fn(url="https://example.com/blog/post", include_links=True)
+        result = await web_scrape_fn(url="https://example.com/blog/post", include_links=True)
 
         assert "error" not in result
         assert "links" in result
@@ -95,8 +172,10 @@ class TestWebScrapeToolLinkConversion:
         expected = "https://example.com/blog/page.html"
         assert hrefs["Next Page"] == expected, f"Got {hrefs['Next Page']}"
 
-    @patch("aden_tools.tools.web_scrape_tool.web_scrape_tool.httpx.get")
-    def test_root_relative_links_converted(self, mock_get, web_scrape_fn):
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_root_relative_links_converted(self, mock_pw, mock_stealth, web_scrape_fn):
         """Root-relative URLs like /about are converted to absolute URLs."""
         html = """
         <html>
@@ -106,9 +185,11 @@ class TestWebScrapeToolLinkConversion:
             </body>
         </html>
         """
-        mock_get.return_value = self._mock_response(html, "https://example.com/blog/post")
+        mock_cm, _, _ = _make_playwright_mocks(html, final_url="https://example.com/blog/post")
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
 
-        result = web_scrape_fn(url="https://example.com/blog/post", include_links=True)
+        result = await web_scrape_fn(url="https://example.com/blog/post", include_links=True)
 
         assert "error" not in result
         assert "links" in result
@@ -119,8 +200,10 @@ class TestWebScrapeToolLinkConversion:
         assert hrefs["About"] == "https://example.com/about"
         assert hrefs["Contact"] == "https://example.com/contact"
 
-    @patch("aden_tools.tools.web_scrape_tool.web_scrape_tool.httpx.get")
-    def test_absolute_links_unchanged(self, mock_get, web_scrape_fn):
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_absolute_links_unchanged(self, mock_pw, mock_stealth, web_scrape_fn):
         """Absolute URLs remain unchanged."""
         html = """
         <html>
@@ -130,9 +213,11 @@ class TestWebScrapeToolLinkConversion:
             </body>
         </html>
         """
-        mock_get.return_value = self._mock_response(html)
+        mock_cm, _, _ = _make_playwright_mocks(html)
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
 
-        result = web_scrape_fn(url="https://example.com", include_links=True)
+        result = await web_scrape_fn(url="https://example.com", include_links=True)
 
         assert "error" not in result
         assert "links" in result
@@ -143,8 +228,10 @@ class TestWebScrapeToolLinkConversion:
         assert hrefs["Other Site"] == "https://other.com"
         assert hrefs["Internal"] == "https://example.com/page"
 
-    @patch("aden_tools.tools.web_scrape_tool.web_scrape_tool.httpx.get")
-    def test_links_after_redirects(self, mock_get, web_scrape_fn):
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_links_after_redirects(self, mock_pw, mock_stealth, web_scrape_fn):
         """Links are resolved relative to final URL after redirects."""
         html = """
         <html>
@@ -155,12 +242,14 @@ class TestWebScrapeToolLinkConversion:
         </html>
         """
         # Mock redirect: request to /old/url redirects to /new/location
-        mock_get.return_value = self._mock_response(
+        mock_cm, _, _ = _make_playwright_mocks(
             html,
             final_url="https://example.com/new/location",  # Final URL after redirect
         )
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
 
-        result = web_scrape_fn(url="https://example.com/old/url", include_links=True)
+        result = await web_scrape_fn(url="https://example.com/old/url", include_links=True)
 
         assert "error" not in result
         assert "links" in result
@@ -173,8 +262,10 @@ class TestWebScrapeToolLinkConversion:
         )
         assert hrefs["Next"] == "https://example.com/new/next"
 
-    @patch("aden_tools.tools.web_scrape_tool.web_scrape_tool.httpx.get")
-    def test_fragment_links_preserved(self, mock_get, web_scrape_fn):
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_fragment_links_preserved(self, mock_pw, mock_stealth, web_scrape_fn):
         """Fragment links (anchors) are preserved."""
         html = """
         <html>
@@ -184,9 +275,11 @@ class TestWebScrapeToolLinkConversion:
             </body>
         </html>
         """
-        mock_get.return_value = self._mock_response(html, "https://example.com/page")
+        mock_cm, _, _ = _make_playwright_mocks(html, final_url="https://example.com/page")
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
 
-        result = web_scrape_fn(url="https://example.com/page", include_links=True)
+        result = await web_scrape_fn(url="https://example.com/page", include_links=True)
 
         assert "error" not in result
         assert "links" in result
@@ -197,8 +290,10 @@ class TestWebScrapeToolLinkConversion:
         assert hrefs["Section 1"] == "https://example.com/page#section1"
         assert hrefs["Page Section 2"] == "https://example.com/page#section2"
 
-    @patch("aden_tools.tools.web_scrape_tool.web_scrape_tool.httpx.get")
-    def test_query_parameters_preserved(self, mock_get, web_scrape_fn):
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_query_parameters_preserved(self, mock_pw, mock_stealth, web_scrape_fn):
         """Query parameters in URLs are preserved."""
         html = """
         <html>
@@ -208,9 +303,11 @@ class TestWebScrapeToolLinkConversion:
             </body>
         </html>
         """
-        mock_get.return_value = self._mock_response(html, "https://example.com/blog/post")
+        mock_cm, _, _ = _make_playwright_mocks(html, final_url="https://example.com/blog/post")
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
 
-        result = web_scrape_fn(url="https://example.com/blog/post", include_links=True)
+        result = await web_scrape_fn(url="https://example.com/blog/post", include_links=True)
 
         assert "error" not in result
         assert "links" in result
@@ -222,8 +319,10 @@ class TestWebScrapeToolLinkConversion:
         assert "q=test" in hrefs["Search"]
         assert "sort=date" in hrefs["Search"]
 
-    @patch("aden_tools.tools.web_scrape_tool.web_scrape_tool.httpx.get")
-    def test_empty_href_skipped(self, mock_get, web_scrape_fn):
+    @pytest.mark.asyncio
+    @patch(_STEALTH_PATH)
+    @patch(_PW_PATH)
+    async def test_empty_href_skipped(self, mock_pw, mock_stealth, web_scrape_fn):
         """Links with empty or whitespace text are skipped."""
         html = """
         <html>
@@ -234,9 +333,11 @@ class TestWebScrapeToolLinkConversion:
             </body>
         </html>
         """
-        mock_get.return_value = self._mock_response(html)
+        mock_cm, _, _ = _make_playwright_mocks(html)
+        mock_pw.return_value = mock_cm
+        mock_stealth.return_value.apply_stealth_async = AsyncMock()
 
-        result = web_scrape_fn(url="https://example.com", include_links=True)
+        result = await web_scrape_fn(url="https://example.com", include_links=True)
 
         assert "error" not in result
         assert "links" in result