fix: isolate session loading

* Enhance ToolRegistry type inference for function parameters

- Add _infer_schema() helper to handle Union types (Union[T, U] and T | U)
- Support Optional[T] and Union[T, None] with correct optional flag
- Infer generic types: list[T] -> array with items schema, dict[K, V] -> object with additionalProperties
- Detect Pydantic BaseModel parameters and use model_json_schema()
- Correctly mark parameters as required/optional based on type annotations
- Add comprehensive test suite covering all type inference scenarios
- Maintain backward compatibility for unannotated parameters

* Fix asyncio.run crash in GraphBuilder.run_test

* Revert "Enhance ToolRegistry type inference for function parameters"

This reverts commit dacd0fa8b926e01d3f29e7c9b2ff5101b4a52c3b.

.agent/mcp_config.json

@@ -0,0 +1,9 @@
+{
+  "mcpServers": {
+    "agent-builder": {
+      "command": "uv",
+      "args": ["run", "--directory", "core", "-m", "framework.mcp.agent_builder_server"],
+      "disabled": false
+    }
+  }
+}

.agent/skills/hive

@@ -0,0 +1 @@
+../../.claude/skills/hive

.agent/skills/hive-concepts

@@ -0,0 +1 @@
+../../.claude/skills/hive-concepts

.agent/skills/hive-create

@@ -0,0 +1 @@
+../../.claude/skills/hive-create

.agent/skills/hive-credentials

@@ -0,0 +1 @@
+../../.claude/skills/hive-credentials

.agent/skills/hive-patterns

@@ -0,0 +1 @@
+../../.claude/skills/hive-patterns

.agent/skills/hive-test

@@ -0,0 +1 @@
+../../.claude/skills/hive-test

.agent/workflows/hive-concepts.md

@@ -0,0 +1,5 @@
+---
+description: hive-concepts
+---
+
+use hive-concepts skill

.agent/workflows/hive-create.md

@@ -0,0 +1,5 @@
+---
+description: hive-create
+---
+
+use hive-create skill

.agent/workflows/hive-credentials.md

@@ -0,0 +1,5 @@
+---
+description: hive-credentials
+---
+
+use hive-credentials skill

.agent/workflows/hive-patterns.md

@@ -0,0 +1,5 @@
+---
+description: hive-patterns
+---
+
+use hive-patterns skill

.agent/workflows/hive-test.md

@@ -0,0 +1,5 @@
+---
+description: hive-test
+---
+
+use hive-test skill

.agent/workflows/hive.md

@@ -0,0 +1,5 @@
+---
+description: hive
+---
+
+use hive skill

.agents/skills/hive

@@ -0,0 +1 @@
+../../.claude/skills/hive

.agents/skills/hive-concepts

@@ -0,0 +1 @@
+../../.claude/skills/hive-concepts

.agents/skills/hive-create

@@ -0,0 +1 @@
+../../.claude/skills/hive-create

.agents/skills/hive-credentials

@@ -0,0 +1 @@
+../../.claude/skills/hive-credentials

.agents/skills/hive-patterns

@@ -0,0 +1 @@
+../../.claude/skills/hive-patterns

.agents/skills/hive-test

@@ -0,0 +1 @@
+../../.claude/skills/hive-test

.claude/settings.json

@@ -0,0 +1,15 @@
+{
+  "hooks": {
+    "PostToolUse": [
+      {
+        "matcher": "Edit|Write|NotebookEdit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "ruff check --fix \"$CLAUDE_FILE_PATH\" 2>/dev/null; ruff format \"$CLAUDE_FILE_PATH\" 2>/dev/null; true"
+          }
+        ]
+      }
+    ]
+  }
+}

.claude/settings.local.json

@@ -1,23 +0,0 @@
-{
-  "permissions": {
-    "allow": [
-      "Bash(npm install:*)",
-      "Bash(npm test:*)",
-      "Skill(building-agents-construction)",
-      "Skill(building-agents-construction:*)",
-      "Bash(PYTHONPATH=core:exports pytest:*)",
-      "mcp__agent-builder__create_session",
-      "mcp__agent-builder__get_session_status",
-      "mcp__agent-builder__set_goal",
-      "mcp__agent-builder__list_mcp_servers",
-      "mcp__agent-builder__test_node",
-      "mcp__agent-builder__add_node",
-      "mcp__agent-builder__add_edge",
-      "mcp__agent-builder__validate_graph",
-      "Bash(ruff check:*)",
-      "Bash(PYTHONPATH=core:exports python:*)",
-      "mcp__agent-builder__list_tests",
-      "mcp__agent-builder__generate_constraint_tests"
-    ]
-  }
-}

.claude/settings.local.json.example

@@ -0,0 +1,34 @@
+{
+  "permissions": {
+    "allow": [
+      "mcp__agent-builder__create_session",
+      "mcp__agent-builder__set_goal",
+      "mcp__agent-builder__add_node",
+      "mcp__agent-builder__add_edge",
+      "mcp__agent-builder__configure_loop",
+      "mcp__agent-builder__add_mcp_server",
+      "mcp__agent-builder__validate_graph",
+      "mcp__agent-builder__export_graph",
+      "mcp__agent-builder__load_session_by_id",
+      "Bash(git status:*)",
+      "Bash(gh run view:*)",
+      "Bash(uv run:*)",
+      "Bash(env:*)",
+      "mcp__agent-builder__test_node",
+      "mcp__agent-builder__list_mcp_tools",
+      "Bash(python -m py_compile:*)",
+      "Bash(python -m pytest:*)",
+      "Bash(source:*)",
+      "mcp__agent-builder__update_node",
+      "mcp__agent-builder__check_missing_credentials",
+      "mcp__agent-builder__list_stored_credentials",
+      "Bash(find:*)",
+      "mcp__agent-builder__run_tests",
+      "Bash(PYTHONPATH=core:exports:tools/src uv run pytest:*)",
+      "mcp__agent-builder__list_agent_sessions",
+      "mcp__agent-builder__generate_constraint_tests",
+      "mcp__agent-builder__generate_success_tests"
+    ]
+  },
+  "enabledMcpjsonServers": ["agent-builder", "tools"]
+}

.claude/skills/building-agents-construction/SKILL.md

@@ -1,953 +0,0 @@
----
-name: building-agents-construction
-description: Step-by-step guide for building goal-driven agents. Creates package structure, defines goals, adds nodes, connects edges, and finalizes agent class. Use when actively building an agent.
-license: Apache-2.0
-metadata:
-  author: hive
-  version: "1.0"
-  type: procedural
-  part_of: building-agents
-  requires: building-agents-core
----
-
-# Building Agents - Construction Process
-
-Step-by-step guide for building goal-driven agent packages.
-
-**Prerequisites:** Read `building-agents-core` for fundamental concepts.
-
-## CRITICAL: entry_points Format Reference
-
-**⚠️ Common Mistake Prevention:**
-
-The `entry_points` parameter in GraphSpec has a specific format that is easy to get wrong. This section exists because this mistake has caused production bugs.
-
-### Correct Format
-
-```python
-entry_points = {"start": "first-node-id"}
-```
-
-**Examples from working agents:**
-
-```python
-# From exports/outbound_sales_agent/agent.py
-entry_node = "lead-qualification"
-entry_points = {"start": "lead-qualification"}
-
-# From exports/support_ticket_agent/agent.py (FIXED)
-entry_node = "parse-ticket"
-entry_points = {"start": "parse-ticket"}
-```
-
-### WRONG Formats (DO NOT USE)
-
-```python
-# ❌ WRONG: Using node ID as key with input keys as value
-entry_points = {
-    "parse-ticket": ["ticket_content", "customer_id", "ticket_id"]
-}
-# Error: ValidationError: Input should be a valid string, got list
-
-# ❌ WRONG: Using set instead of dict
-entry_points = {"parse-ticket"}
-# Error: ValidationError: Input should be a valid dictionary, got set
-
-# ❌ WRONG: Missing "start" key
-entry_points = {"entry": "parse-ticket"}
-# Error: Graph execution fails, cannot find entry point
-```
-
-### Validation Check
-
-After writing graph configuration, ALWAYS validate:
-
-```python
-# Check 1: Must be a dict
-assert isinstance(entry_points, dict), f"entry_points must be dict, got {type(entry_points)}"
-
-# Check 2: Must have "start" key
-assert "start" in entry_points, f"entry_points must have 'start' key, got keys: {entry_points.keys()}"
-
-# Check 3: "start" value must match entry_node
-assert entry_points["start"] == entry_node, f"entry_points['start']={entry_points['start']} must match entry_node={entry_node}"
-
-# Check 4: Value must be a string (node ID)
-assert isinstance(entry_points["start"], str), f"entry_points['start'] must be string, got {type(entry_points['start'])}"
-```
-
-**Why this matters:** GraphSpec uses Pydantic validation. The wrong format causes ValidationError at runtime, which blocks all agent execution and tests. This bug is not caught until you try to run the agent.
-
-## Building Session Management with MCP
-
-**MANDATORY**: Use the agent-builder MCP server's BuildSession system for automatic bookkeeping and persistence.
-
-### Available MCP Session Tools
-
-```python
-# Create new session (call FIRST before building)
-mcp__agent-builder__create_session(name="Support Ticket Agent")
-# Returns: session_id, automatically sets as active session
-
-# Get current session status (use for progress tracking)
-status = mcp__agent-builder__get_session_status()
-# Returns: {
-#   "session_id": "build_20250122_...",
-#   "name": "Support Ticket Agent",
-#   "has_goal": true,
-#   "node_count": 5,
-#   "edge_count": 7,
-#   "nodes": ["parse-ticket", "categorize", ...],
-#   "edges": [("parse-ticket", "categorize"), ...]
-# }
-
-# List all saved sessions
-mcp__agent-builder__list_sessions()
-
-# Load previous session
-mcp__agent-builder__load_session_by_id(session_id="build_...")
-
-# Delete session
-mcp__agent-builder__delete_session(session_id="build_...")
-```
-
-### How MCP Session Works
-
-The BuildSession class (in `core/framework/mcp/agent_builder_server.py`) automatically:
-- **Persists to disk** after every operation (`_save_session()` called automatically)
-- **Tracks all components**: goal, nodes, edges, mcp_servers
-- **Maintains timestamps**: created_at, last_modified
-- **Stores to**: `~/.claude-code-agent-builder/sessions/`
-
-When you call MCP tools like:
-- `mcp__agent-builder__set_goal(...)` - Automatically added to session.goal and saved
-- `mcp__agent-builder__add_node(...)` - Automatically added to session.nodes and saved
-- `mcp__agent-builder__add_edge(...)` - Automatically added to session.edges and saved
-
-**No manual bookkeeping needed** - the MCP server handles it all!
-
-### Show Progress to User
-
-```python
-# Get session status to show progress
-status = json.loads(mcp__agent-builder__get_session_status())
-
-print(f"\n📊 Building Progress:")
-print(f"   Session: {status['name']}")
-print(f"   Goal defined: {status['has_goal']}")
-print(f"   Nodes: {status['node_count']}")
-print(f"   Edges: {status['edge_count']}")
-print(f"   Nodes added: {', '.join(status['nodes'])}")
-```
-
-**Benefits:**
-- Automatic persistence - survive crashes/restarts
-- Clear audit trail - all operations logged
-- Session resume - continue from where you left off
-- Progress tracking built-in
-- No manual state management needed
-
-## Step-by-Step Guide
-
-### Step 1: Create Building Session & Package Structure
-
-When user requests an agent, **immediately create MCP session and package**:
-
-```python
-# 0. FIRST: Create MCP building session
-agent_name = "technical_research_agent"  # snake_case
-session_result = mcp__agent-builder__create_session(name=agent_name.replace('_', ' ').title())
-session_id = json.loads(session_result)["session_id"]
-print(f"✅ Created building session: {session_id}")
-
-# 1. Create directory
-package_path = f"exports/{agent_name}"
-
-Bash(f"mkdir -p {package_path}/nodes")
-
-# 2. Write skeleton files
-Write(
-    file_path=f"{package_path}/__init__.py",
-    content='''"""
-Agent package - will be populated as build progresses.
-"""
-'''
-)
-
-Write(
-    file_path=f"{package_path}/nodes/__init__.py",
-    content='''"""Node definitions."""
-from framework.graph import NodeSpec
-
-# Nodes will be added here as they are approved
-
-__all__ = []
-'''
-)
-
-Write(
-    file_path=f"{package_path}/agent.py",
-    content='''"""Agent graph construction."""
-from framework.graph import EdgeSpec, EdgeCondition, Goal, SuccessCriterion, Constraint
-from framework.graph.edge import GraphSpec
-from framework.graph.executor import GraphExecutor
-from framework.runtime import Runtime
-from framework.llm.anthropic import AnthropicProvider
-from framework.runner.tool_registry import ToolRegistry
-from aden_tools.credentials import CredentialManager
-
-# Goal will be added when defined
-# Nodes will be imported from .nodes
-# Edges will be added when approved
-# Agent class will be created when graph is complete
-'''
-)
-
-Write(
-    file_path=f"{package_path}/config.py",
-    content='''"""Runtime configuration."""
-from dataclasses import dataclass
-
-@dataclass
-class RuntimeConfig:
-    model: str = "claude-haiku-4-5-20251001"
-    temperature: float = 0.7
-    max_tokens: int = 4096
-
-default_config = RuntimeConfig()
-
-# Metadata will be added when goal is set
-'''
-)
-
-Write(
-    file_path=f"{package_path}/__main__.py",
-    content=CLI_TEMPLATE  # Full CLI template (see below)
-)
-```
-
-**Show user:**
-
-```
-✅ Package created: exports/technical_research_agent/
-📁 Files created:
-   - __init__.py (skeleton)
-   - __main__.py (CLI ready)
-   - agent.py (skeleton)
-   - nodes/__init__.py (empty)
-   - config.py (skeleton)
-
-You can open these files now and watch them grow as we build!
-```
-
-### Step 2: Define Goal
-
-Propose goal, get approval, **write immediately**:
-
-```python
-# After user approves goal...
-
-goal_code = f'''
-goal = Goal(
-    id="{goal_id}",
-    name="{name}",
-    description="{description}",
-    success_criteria=[
-        SuccessCriterion(
-            id="{sc.id}",
-            description="{sc.description}",
-            metric="{sc.metric}",
-            target="{sc.target}",
-            weight={sc.weight},
-        ),
-        # 3-5 success criteria total
-    ],
-    constraints=[
-        Constraint(
-            id="{c.id}",
-            description="{c.description}",
-            constraint_type="{c.constraint_type}",
-            category="{c.category}",
-        ),
-        # 1-5 constraints total
-    ],
-)
-'''
-
-# Append to agent.py
-Read(f"{package_path}/agent.py")  # Must read first
-Edit(
-    file_path=f"{package_path}/agent.py",
-    old_string="# Goal will be added when defined",
-    new_string=f"# Goal definition\n{goal_code}"
-)
-
-# Write metadata to config.py
-metadata_code = f'''
-@dataclass
-class AgentMetadata:
-    name: str = "{name}"
-    version: str = "1.0.0"
-    description: str = "{description}"
-
-metadata = AgentMetadata()
-'''
-
-Read(f"{package_path}/config.py")
-Edit(
-    file_path=f"{package_path}/config.py",
-    old_string="# Metadata will be added when goal is set",
-    new_string=f"# Agent metadata\n{metadata_code}"
-)
-```
-
-**Show user:**
-
-```
-✅ Goal written to agent.py
-✅ Metadata written to config.py
-
-Open exports/technical_research_agent/agent.py to see the goal!
-```
-
-**Note:** Goal is automatically tracked in MCP session. Use `mcp__agent-builder__get_session_status()` to check progress.
-
-### Step 3: Add Nodes (Incremental)
-
-**⚠️ CRITICAL VALIDATION REQUIREMENTS:**
-
-Before adding any node with tools:
-1. Call `mcp__agent-builder__list_mcp_tools()` to discover available tools
-2. Verify each tool exists in the response
-3. If a tool doesn't exist, inform the user and ask how to proceed
-
-After writing each node:
-4. **MANDATORY**: Validate with `mcp__agent-builder__test_node()` before proceeding
-5. **MANDATORY**: Check MCP session status to track progress
-6. Only proceed to next node after validation passes
-
-For each node, **write immediately after approval**:
-
-```python
-# After user approves node...
-
-node_code = f'''
-{node_id.replace('-', '_')}_node = NodeSpec(
-    id="{node_id}",
-    name="{name}",
-    description="{description}",
-    node_type="{node_type}",
-    input_keys={input_keys},
-    output_keys={output_keys},
-    system_prompt="""\\
-{system_prompt}
-""",
-    tools={tools},
-    max_retries={max_retries},
-)
-
-'''
-
-# Append to nodes/__init__.py
-Read(f"{package_path}/nodes/__init__.py")
-Edit(
-    file_path=f"{package_path}/nodes/__init__.py",
-    old_string="__all__ = []",
-    new_string=f"{node_code}\n__all__ = []"
-)
-
-# Update __all__ exports
-all_node_names = [n.replace('-', '_') + '_node' for n in approved_nodes]
-all_exports = f"__all__ = {all_node_names}"
-
-Edit(
-    file_path=f"{package_path}/nodes/__init__.py",
-    old_string="__all__ = []",
-    new_string=all_exports
-)
-```
-
-**Show user after each node:**
-
-```
-✅ Added analyze_request_node to nodes/__init__.py
-📊 Progress: 1/6 nodes added
-
-Open exports/technical_research_agent/nodes/__init__.py to see it!
-```
-
-**Repeat for each node.** User watches the file grow.
-
-#### MANDATORY: Validate Each Node with MCP Tools
-
-After writing EVERY node, you MUST validate before proceeding:
-
-```python
-# Node is already written to file. Now VALIDATE IT (REQUIRED):
-validation_result = json.loads(mcp__agent-builder__test_node(
-    node_id="analyze-request",
-    test_input='{"query": "test query"}',
-    mock_llm_response='{"analysis": "mock output"}'
-))
-
-# Check validation result
-if validation_result["valid"]:
-    # Show user validation passed
-    print(f"✅ Node validation passed: analyze-request")
-
-    # Show session progress
-    status = json.loads(mcp__agent-builder__get_session_status())
-    print(f"📊 Session progress: {status['node_count']} nodes added")
-else:
-    # STOP - Do not proceed until fixed
-    print(f"❌ Node validation FAILED:")
-    for error in validation_result["errors"]:
-        print(f"   - {error}")
-    print("⚠️ Must fix node before proceeding to next component")
-    # Ask user how to proceed
-```
-
-**CRITICAL:** Do NOT proceed to the next node until validation passes. Bugs caught here prevent wasted work later.
-
-### Step 4: Connect Edges
-
-After all nodes approved, add edges:
-
-```python
-# Generate edges code
-edges_code = "edges = [\n"
-for edge in approved_edges:
-    edges_code += f'''    EdgeSpec(
-        id="{edge.id}",
-        source="{edge.source}",
-        target="{edge.target}",
-        condition=EdgeCondition.{edge.condition.upper()},
-'''
-    if edge.condition_expr:
-        edges_code += f'        condition_expr="{edge.condition_expr}",\n'
-    edges_code += f'        priority={edge.priority},\n'
-    edges_code += '    ),\n'
-edges_code += "]\n"
-
-# Write to agent.py
-Read(f"{package_path}/agent.py")
-Edit(
-    file_path=f"{package_path}/agent.py",
-    old_string="# Edges will be added when approved",
-    new_string=f"# Edge definitions\n{edges_code}"
-)
-
-# Write entry points and terminal nodes
-# ⚠️ CRITICAL: entry_points format must be {"start": "node_id"}
-# Common mistake: {"node_id": ["input_keys"]} is WRONG
-# Correct format: {"start": "first-node-id"}
-# Reference: See exports/outbound_sales_agent/agent.py for example
-
-graph_config = f'''
-# Graph configuration
-entry_node = "{entry_node_id}"
-entry_points = {{"start": "{entry_node_id}"}}  # CRITICAL: Must be {{"start": "node-id"}}
-pause_nodes = {pause_nodes}
-terminal_nodes = {terminal_nodes}
-
-# Collect all nodes
-nodes = [
-    {', '.join(node_names)},
-]
-'''
-
-Edit(
-    file_path=f"{package_path}/agent.py",
-    old_string="# Agent class will be created when graph is complete",
-    new_string=graph_config
-)
-```
-
-**Show user:**
-
-```
-✅ Edges written to agent.py
-✅ Graph configuration added
-
-5 edges connecting 6 nodes
-```
-
-#### MANDATORY: Validate Graph Structure
-
-After writing edges, you MUST validate before proceeding to finalization:
-
-```python
-# Edges already written to agent.py. Now VALIDATE STRUCTURE (REQUIRED):
-graph_validation = json.loads(mcp__agent-builder__validate_graph())
-
-# Check for structural issues
-if graph_validation["valid"]:
-    print("✅ Graph structure validated successfully")
-
-    # Show session summary
-    status = json.loads(mcp__agent-builder__get_session_status())
-    print(f"   - Nodes: {status['node_count']}")
-    print(f"   - Edges: {status['edge_count']}")
-    print(f"   - Entry point: {entry_node_id}")
-else:
-    print("❌ Graph validation FAILED:")
-    for error in graph_validation["errors"]:
-        print(f"   ERROR: {error}")
-    print("\n⚠️ Must fix graph structure before finalizing agent")
-    # Ask user how to proceed
-
-# Additional validation: Check entry_points format
-if not isinstance(entry_points, dict):
-    print("❌ CRITICAL ERROR: entry_points must be a dict")
-    print(f"   Current value: {entry_points} (type: {type(entry_points)})")
-    print("   Correct format: {'start': 'node-id'}")
-    # STOP - This is the mistake that caused the support_ticket_agent bug
-
-if entry_points.get("start") != entry_node_id:
-    print("❌ CRITICAL ERROR: entry_points['start'] must match entry_node")
-    print(f"   entry_points: {entry_points}")
-    print(f"   entry_node: {entry_node_id}")
-    print("   They must be consistent!")
-```
-
-**CRITICAL:** Do NOT proceed to Step 5 (finalization) until graph validation passes. This checkpoint prevents structural bugs from reaching production.
-
-### Step 5: Finalize Agent Class
-
-**Pre-flight checks before finalization:**
-
-```python
-# MANDATORY: Verify all validations passed before finalizing
-print("\n🔍 Pre-finalization Checklist:")
-
-# Get current session status
-status = json.loads(mcp__agent-builder__get_session_status())
-
-checks_passed = True
-
-# Check 1: Goal defined
-if not status["has_goal"]:
-    print("❌ No goal defined")
-    checks_passed = False
-else:
-    print(f"✅ Goal defined: {status['goal_name']}")
-
-# Check 2: Nodes added
-if status["node_count"] == 0:
-    print("❌ No nodes added")
-    checks_passed = False
-else:
-    print(f"✅ {status['node_count']} nodes added: {', '.join(status['nodes'])}")
-
-# Check 3: Edges added
-if status["edge_count"] == 0:
-    print("❌ No edges added")
-    checks_passed = False
-else:
-    print(f"✅ {status['edge_count']} edges added")
-
-# Check 4: Entry points format correct
-if not isinstance(entry_points, dict) or "start" not in entry_points:
-    print("❌ CRITICAL: entry_points format incorrect")
-    print(f"   Current: {entry_points}")
-    print("   Required: {'start': 'node-id'}")
-    checks_passed = False
-else:
-    print(f"✅ Entry points valid: {entry_points}")
-
-if not checks_passed:
-    print("\n⚠️ CANNOT PROCEED to finalization until all checks pass")
-    print("   Fix the issues above first")
-    # Ask user how to proceed or stop here
-    return
-
-print("\n✅ All pre-flight checks passed - proceeding to finalization\n")
-```
-
-Write the agent class:
-
-````python
-agent_class_code = f'''
-
-class {agent_class_name}:
-    """
-    {agent_description}
-    """
-
-    def __init__(self, config=None):
-        self.config = config or default_config
-        self.goal = goal
-        self.nodes = nodes
-        self.edges = edges
-        self.entry_node = entry_node
-        self.entry_points = entry_points
-        self.pause_nodes = pause_nodes
-        self.terminal_nodes = terminal_nodes
-        self.executor = None
-
-    def _create_executor(self, mock_mode=False):
-        """Create executor instance."""
-        import tempfile
-        from pathlib import Path
-
-        storage_path = Path(tempfile.gettempdir()) / "{agent_name}"
-        storage_path.mkdir(parents=True, exist_ok=True)
-
-        runtime = Runtime(storage_path=storage_path)
-        tool_registry = ToolRegistry()
-
-        llm = None
-        if not mock_mode:
-            creds = CredentialManager()
-            if creds.is_available("anthropic"):
-                api_key = creds.get("anthropic")
-                llm = AnthropicProvider(api_key=api_key, model=self.config.model)
-
-        graph = GraphSpec(
-            id="{agent_name}-graph",
-            goal_id=self.goal.id,
-            version="1.0.0",
-            entry_node=self.entry_node,
-            entry_points=self.entry_points,
-            terminal_nodes=self.terminal_nodes,
-            pause_nodes=self.pause_nodes,
-            nodes=self.nodes,
-            edges=self.edges,
-            default_model=self.config.model,
-            max_tokens=self.config.max_tokens,
-        )
-
-        self.executor = GraphExecutor(
-            runtime=runtime,
-            llm=llm,
-            tools=list(tool_registry.get_tools().values()),
-            tool_executor=tool_registry.get_executor(),
-        )
-
-        self.graph = graph
-        return self.executor
-
-    async def run(self, context: dict, mock_mode=False, session_state=None):
-        """Run the agent."""
-        executor = self._create_executor(mock_mode=mock_mode)
-        result = await executor.execute(
-            graph=self.graph,
-            goal=self.goal,
-            input_data=context,
-            session_state=session_state,
-        )
-        return result
-
-    def info(self):
-        """Get agent information."""
-        return {{
-            "name": metadata.name,
-            "version": metadata.version,
-            "description": metadata.description,
-            "goal": {{
-                "name": self.goal.name,
-                "description": self.goal.description,
-            }},
-            "nodes": [n.id for n in self.nodes],
-            "edges": [e.id for e in self.edges],
-            "entry_node": self.entry_node,
-            "pause_nodes": self.pause_nodes,
-            "terminal_nodes": self.terminal_nodes,
-        }}
-
-    def validate(self):
-        """Validate agent structure."""
-        errors = []
-        warnings = []
-
-        node_ids = {{node.id for node in self.nodes}}
-        for edge in self.edges:
-            if edge.source not in node_ids:
-                errors.append(f"Edge {{edge.id}}: source '{{edge.source}}' not found")
-            if edge.target not in node_ids:
-                errors.append(f"Edge {{edge.id}}: target '{{edge.target}}' not found")
-
-        if self.entry_node not in node_ids:
-            errors.append(f"Entry node '{{self.entry_node}}' not found")
-
-        return {{
-            "valid": len(errors) == 0,
-            "errors": errors,
-            "warnings": warnings,
-        }}
-
-
-# Create default instance
-default_agent = {agent_class_name}()
-'''
-
-# Append agent class
-Read(f"{package_path}/agent.py")
-Edit(
-    file_path=f"{package_path}/agent.py",
-    old_string="nodes = [",
-    new_string=f"nodes = [\n{agent_class_code}"
-)
-
-# Finalize __init__.py exports
-init_content = f'''"""
-{agent_description}
-"""
-
-from .agent import {agent_class_name}, default_agent, goal, nodes, edges
-from .config import RuntimeConfig, AgentMetadata, default_config, metadata
-
-__version__ = "1.0.0"
-
-__all__ = [
-    "{agent_class_name}",
-    "default_agent",
-    "goal",
-    "nodes",
-    "edges",
-    "RuntimeConfig",
-    "AgentMetadata",
-    "default_config",
-    "metadata",
-]
-'''
-
-Read(f"{package_path}/__init__.py")
-Edit(
-    file_path=f"{package_path}/__init__.py",
-    old_string='"""',
-    new_string=init_content,
-    replace_all=True
-)
-
-# Write README
-readme_content = f'''# {agent_name.replace('_', ' ').title()}
-
-{agent_description}
-
-## Usage
-
-```bash
-# Show agent info
-python -m {agent_name} info
-
-# Validate structure
-python -m {agent_name} validate
-
-# Run agent
-python -m {agent_name} run --input '{{"key": "value"}}'
-
-# Interactive shell
-python -m {agent_name} shell
-````
-
-## As Python Module
-
-```python
-from {agent_name} import default_agent
-
-result = await default_agent.run({{"key": "value"}})
-```
-
-## Structure
-
-- `agent.py` - Goal, edges, graph construction
-- `nodes/__init__.py` - Node definitions
-- `config.py` - Runtime configuration
-- `__main__.py` - CLI interface
-  '''
-
-Write(
-file_path=f"{package_path}/README.md",
-content=readme_content
-)
-
-```
-
-**Show user:**
-
-```
-
-✅ Agent class written to agent.py
-✅ Package exports finalized in __init__.py
-✅ README.md generated
-
-🎉 Agent complete: exports/technical_research_agent/
-
-Commands:
-python -m technical_research_agent info
-python -m technical_research_agent validate
-python -m technical_research_agent run --input '{"topic": "..."}'
-```
-
-**Final session summary:**
-
-```python
-# Show final MCP session status
-status = json.loads(mcp__agent-builder__get_session_status())
-
-print("\n📊 Build Session Summary:")
-print(f"   Session ID: {status['session_id']}")
-print(f"   Agent: {status['name']}")
-print(f"   Goal: {status['goal_name']}")
-print(f"   Nodes: {status['node_count']}")
-print(f"   Edges: {status['edge_count']}")
-print(f"   MCP Servers: {status['mcp_servers_count']}")
-print("\n✅ Agent construction complete with full validation")
-print(f"\nSession saved to: ~/.claude-code-agent-builder/sessions/{status['session_id']}.json")
-````
-
-## CLI Template
-
-```python
-CLI_TEMPLATE = '''"""
-CLI entry point for agent.
-"""
-
-import asyncio
-import json
-import sys
-import click
-
-from .agent import default_agent
-
-@click.group()
-@click.version_option(version="1.0.0")
-def cli():
-    """Agent CLI."""
-    pass
-
-@cli.command()
-@click.option("--input", "-i", "input_json", type=str, required=True)
-@click.option("--mock", is_flag=True, help="Run in mock mode")
-@click.option("--quiet", "-q", is_flag=True, help="Only output result JSON")
-def run(input_json, mock, quiet):
-    """Execute the agent."""
-    try:
-        context = json.loads(input_json)
-    except json.JSONDecodeError as e:
-        click.echo(f"Error parsing input JSON: {e}", err=True)
-        sys.exit(1)
-
-    if not quiet:
-        click.echo(f"Running agent with input: {json.dumps(context)}")
-
-    result = asyncio.run(default_agent.run(context, mock_mode=mock))
-
-    output_data = {
-        "success": result.success,
-        "steps_executed": result.steps_executed,
-        "output": result.output,
-    }
-    if result.error:
-        output_data["error"] = result.error
-    if result.paused_at:
-        output_data["paused_at"] = result.paused_at
-
-    click.echo(json.dumps(output_data, indent=2, default=str))
-    sys.exit(0 if result.success else 1)
-
-@cli.command()
-@click.option("--json", "output_json", is_flag=True)
-def info(output_json):
-    """Show agent information."""
-    info_data = default_agent.info()
-    if output_json:
-        click.echo(json.dumps(info_data, indent=2))
-    else:
-        click.echo(f"Agent: {info_data['name']}")
-        click.echo(f"Description: {info_data['description']}")
-        click.echo(f"Nodes: {len(info_data['nodes'])}")
-        click.echo(f"Edges: {len(info_data['edges'])}")
-
-@cli.command()
-def validate():
-    """Validate agent structure."""
-    validation = default_agent.validate()
-    if validation["valid"]:
-        click.echo("✓ Agent is valid")
-    else:
-        click.echo("✗ Agent has errors:")
-        for error in validation["errors"]:
-            click.echo(f"  ERROR: {error}")
-    sys.exit(0 if validation["valid"] else 1)
-
-@cli.command()
-def shell():
-    """Interactive agent session."""
-    click.echo("Interactive mode - enter JSON input:")
-    # ... implementation
-
-if __name__ == "__main__":
-    cli()
-'''
-````
-
-## Testing During Build
-
-After nodes are added:
-
-```python
-# Test individual node
-python -c "
-from exports.my_agent.nodes import analyze_request_node
-print(analyze_request_node.id)
-print(analyze_request_node.input_keys)
-"
-
-# Validate current state
-PYTHONPATH=core:exports python -m my_agent validate
-
-# Show info
-PYTHONPATH=core:exports python -m my_agent info
-```
-
-## Approval Pattern
-
-Use AskUserQuestion for all approvals:
-
-```python
-response = AskUserQuestion(
-    questions=[{
-        "question": "Do you approve this [component]?",
-        "header": "Approve",
-        "options": [
-            {
-                "label": "✓ Approve (Recommended)",
-                "description": "Component looks good, proceed"
-            },
-            {
-                "label": "✗ Reject & Modify",
-                "description": "Need to make changes"
-            },
-            {
-                "label": "⏸ Pause & Review",
-                "description": "Need more time to review"
-            }
-        ],
-        "multiSelect": false
-    }]
-)
-```
-
-## Next Steps
-
-After completing construction:
-
-**If agent structure complete:**
-
-- Validate: `python -m agent_name validate`
-- Test basic execution: `python -m agent_name info`
-- Proceed to testing-agent skill for comprehensive tests
-
-**If implementation needed:**
-
-- Check for STATUS.md or IMPLEMENTATION_GUIDE.md in agent directory
-- May need Python functions or MCP tool integration
-
-## Related Skills
-
-- **building-agents-core** - Fundamental concepts
-- **building-agents-patterns** - Best practices and examples
-- **testing-agent** - Test and validate completed agents
-- **agent-workflow** - Complete workflow orchestrator

.claude/skills/building-agents-core/SKILL.md

@@ -1,303 +0,0 @@
----
-name: building-agents-core
-description: Core concepts for goal-driven agents - architecture, node types, tool discovery, and workflow overview. Use when starting agent development or need to understand agent fundamentals.
-license: Apache-2.0
-metadata:
-  author: hive
-  version: "1.0"
-  type: foundational
-  part_of: building-agents
----
-
-# Building Agents - Core Concepts
-
-Foundational knowledge for building goal-driven agents as Python packages.
-
-## Architecture: Python Services (Not JSON Configs)
-
-Agents are built as Python packages:
-
-```
-exports/my_agent/
-├── __init__.py          # Package exports
-├── __main__.py          # CLI (run, info, validate, shell)
-├── agent.py             # Graph construction (goal, edges, agent class)
-├── nodes/__init__.py    # Node definitions (NodeSpec)
-├── config.py            # Runtime config
-└── README.md            # Documentation
-```
-
-**Key Principle: Agent is visible and editable during build**
-
-- ✅ Files created immediately as components are approved
-- ✅ User can watch files grow in their editor
-- ✅ No session state - just direct file writes
-- ✅ No "export" step - agent is ready when build completes
-
-## Core Concepts
-
-### Goal
-
-Success criteria and constraints (written to agent.py)
-
-```python
-goal = Goal(
-    id="research-goal",
-    name="Technical Research Agent",
-    description="Research technical topics thoroughly",
-    success_criteria=[
-        SuccessCriterion(
-            id="completeness",
-            description="Cover all aspects of topic",
-            metric="coverage_score",
-            target=">=0.9",
-            weight=0.4,
-        ),
-        # 3-5 success criteria total
-    ],
-    constraints=[
-        Constraint(
-            id="accuracy",
-            description="All information must be verified",
-            constraint_type="hard",
-            category="quality",
-        ),
-        # 1-5 constraints total
-    ],
-)
-```
-
-### Node
-
-Unit of work (written to nodes/__init__.py)
-
-**Node Types:**
-
-- `llm_generate` - Text generation, parsing
-- `llm_tool_use` - Actions requiring tools
-- `router` - Conditional branching
-- `function` - Deterministic operations
-
-```python
-search_node = NodeSpec(
-    id="search-web",
-    name="Search Web",
-    description="Search for information online",
-    node_type="llm_tool_use",
-    input_keys=["query"],
-    output_keys=["search_results"],
-    system_prompt="Search the web for: {query}",
-    tools=["web_search"],
-    max_retries=3,
-)
-```
-
-### Edge
-
-Connection between nodes (written to agent.py)
-
-**Edge Conditions:**
-
-- `on_success` - Proceed if node succeeds
-- `on_failure` - Handle errors
-- `always` - Always proceed
-- `conditional` - Based on expression
-
-```python
-EdgeSpec(
-    id="search-to-analyze",
-    source="search-web",
-    target="analyze-results",
-    condition=EdgeCondition.ON_SUCCESS,
-    priority=1,
-)
-```
-
-### Pause/Resume
-
-Multi-turn conversations
-
-- **Pause nodes** - Stop execution, wait for user input
-- **Resume entry points** - Continue from pause with user's response
-
-```python
-# Example pause/resume configuration
-pause_nodes = ["request-clarification"]
-entry_points = {
-    "start": "analyze-request",
-    "request-clarification_resume": "process-clarification"
-}
-```
-
-## Tool Discovery & Validation
-
-**CRITICAL:** Before adding a node with tools, you MUST verify the tools exist.
-
-Tools are provided by MCP servers. Never assume a tool exists - always discover dynamically.
-
-### Step 1: Register MCP Server (if not already done)
-
-```python
-mcp__agent-builder__add_mcp_server(
-    name="tools",
-    transport="stdio",
-    command="python",
-    args='["mcp_server.py", "--stdio"]',
-    cwd="../tools"
-)
-```
-
-### Step 2: Discover Available Tools
-
-```python
-# List all tools from all registered servers
-mcp__agent-builder__list_mcp_tools()
-
-# Or list tools from a specific server
-mcp__agent-builder__list_mcp_tools(server_name="tools")
-```
-
-This returns available tools with their descriptions and parameters:
-
-```json
-{
-  "success": true,
-  "tools_by_server": {
-    "tools": [
-      {
-        "name": "web_search",
-        "description": "Search the web...",
-        "parameters": ["query"]
-      },
-      {
-        "name": "web_scrape",
-        "description": "Scrape a URL...",
-        "parameters": ["url"]
-      }
-    ]
-  },
-  "total_tools": 14
-}
-```
-
-### Step 3: Validate Before Adding Nodes
-
-Before writing a node with `tools=[...]`:
-
-1. Call `list_mcp_tools()` to get available tools
-2. Check each tool in your node exists in the response
-3. If a tool doesn't exist:
-   - **DO NOT proceed** with the node
-   - Inform the user: "The tool 'X' is not available. Available tools are: ..."
-   - Ask if they want to use an alternative or proceed without the tool
-
-### Tool Validation Anti-Patterns
-
-❌ **Never assume a tool exists** - always call `list_mcp_tools()` first
-❌ **Never write a node with unverified tools** - validate before writing
-❌ **Never silently drop tools** - if a tool doesn't exist, inform the user
-❌ **Never guess tool names** - use exact names from discovery response
-
-### Example Validation Flow
-
-```python
-# 1. User requests: "Add a node that searches the web"
-# 2. Discover available tools
-tools_response = mcp__agent-builder__list_mcp_tools()
-
-# 3. Check if web_search exists
-available = [t["name"] for tools in tools_response["tools_by_server"].values() for t in tools]
-if "web_search" not in available:
-    # Inform user and ask how to proceed
-    print("❌ 'web_search' not available. Available tools:", available)
-else:
-    # Proceed with node creation
-    # ...
-```
-
-## Workflow Overview: Incremental File Construction
-
-```
-1. CREATE PACKAGE → mkdir + write skeletons
-2. DEFINE GOAL → Write to agent.py + config.py
-3. FOR EACH NODE:
-   - Propose design
-   - User approves
-   - Write to nodes/__init__.py IMMEDIATELY ← FILE WRITTEN
-   - (Optional) Validate with test_node ← MCP VALIDATION
-   - User can open file and see it
-4. CONNECT EDGES → Update agent.py ← FILE WRITTEN
-   - (Optional) Validate with validate_graph ← MCP VALIDATION
-5. FINALIZE → Write agent class to agent.py ← FILE WRITTEN
-6. DONE - Agent ready at exports/my_agent/
-```
-
-**Files written immediately. MCP tools optional for validation/testing bookkeeping.**
-
-### The Key Difference
-
-**OLD (Bad):**
-
-```
-MCP add_node → Session State → MCP add_node → Session State → ...
-                                                                ↓
-                                                     MCP export_graph
-                                                                ↓
-                                                       Files appear
-```
-
-**NEW (Good):**
-
-```
-Write node to file → (Optional: MCP test_node) → Write node to file → ...
-       ↓                                               ↓
-  File visible                                    File visible
-  immediately                                     immediately
-```
-
-**Bottom line:** Use Write/Edit for construction, MCP for validation if needed.
-
-## When to Use This Skill
-
-Use building-agents-core when:
-- Starting a new agent project and need to understand fundamentals
-- Need to understand agent architecture before building
-- Want to validate tool availability before proceeding
-- Learning about node types, edges, and graph execution
-
-**Next Steps:**
-- Ready to build? → Use `building-agents-construction` skill
-- Need patterns and examples? → Use `building-agents-patterns` skill
-
-## MCP Tools for Validation
-
-After writing files, optionally use MCP tools for validation:
-
-**test_node** - Validate node configuration with mock inputs
-```python
-mcp__agent-builder__test_node(
-    node_id="search-web",
-    test_input='{"query": "test query"}',
-    mock_llm_response='{"results": "mock output"}'
-)
-```
-
-**validate_graph** - Check graph structure
-```python
-mcp__agent-builder__validate_graph()
-# Returns: unreachable nodes, missing connections, etc.
-```
-
-**create_session** - Track session state for bookkeeping
-```python
-mcp__agent-builder__create_session(session_name="my-build")
-```
-
-**Key Point:** Files are written FIRST. MCP tools are for validation only.
-
-## Related Skills
-
-- **building-agents-construction** - Step-by-step building process
-- **building-agents-patterns** - Best practices and examples
-- **agent-workflow** - Complete workflow orchestrator
-- **testing-agent** - Test and validate completed agents

.claude/skills/building-agents-patterns/SKILL.md

@@ -1,497 +0,0 @@
----
-name: building-agents-patterns
-description: Best practices, patterns, and examples for building goal-driven agents. Includes pause/resume architecture, hybrid workflows, anti-patterns, and handoff to testing. Use when optimizing agent design.
-license: Apache-2.0
-metadata:
-  author: hive
-  version: "1.0"
-  type: reference
-  part_of: building-agents
----
-
-# Building Agents - Patterns & Best Practices
-
-Design patterns, examples, and best practices for building robust goal-driven agents.
-
-**Prerequisites:** Complete agent structure using `building-agents-construction`.
-
-## Practical Example: Hybrid Workflow
-
-How to build a node using both direct file writes and optional MCP validation:
-
-```python
-# 1. WRITE TO FILE FIRST (Primary - makes it visible)
-node_code = '''
-search_node = NodeSpec(
-    id="search-web",
-    node_type="llm_tool_use",
-    input_keys=["query"],
-    output_keys=["search_results"],
-    system_prompt="Search the web for: {query}",
-    tools=["web_search"],
-)
-'''
-
-Edit(
-    file_path="exports/research_agent/nodes/__init__.py",
-    old_string="# Nodes will be added here",
-    new_string=node_code
-)
-
-print("✅ Added search_node to nodes/__init__.py")
-print("📁 Open exports/research_agent/nodes/__init__.py to see it!")
-
-# 2. OPTIONALLY VALIDATE WITH MCP (Secondary - bookkeeping)
-validation = mcp__agent-builder__test_node(
-    node_id="search-web",
-    test_input='{"query": "python tutorials"}',
-    mock_llm_response='{"search_results": [...mock results...]}'
-)
-
-print(f"✓ Validation: {validation['success']}")
-```
-
-**User experience:**
-
-- Immediately sees node in their editor (from step 1)
-- Gets validation feedback (from step 2)
-- Can edit the file directly if needed
-
-This combines visibility (files) with validation (MCP tools).
-
-## Pause/Resume Architecture
-
-For agents needing multi-turn conversations with user interaction:
-
-### Basic Pause/Resume Flow
-
-```python
-# Define pause nodes - execution stops at these nodes
-pause_nodes = ["request-clarification", "await-approval"]
-
-# Define entry points - where to resume from each pause
-entry_points = {
-    "start": "analyze-request",  # Initial entry
-    "request-clarification_resume": "process-clarification",  # Resume from clarification
-    "await-approval_resume": "execute-action",  # Resume from approval
-}
-```
-
-### Example: Multi-Turn Research Agent
-
-```python
-# Nodes
-nodes = [
-    NodeSpec(id="analyze-request", ...),
-    NodeSpec(id="request-clarification", ...),  # PAUSE NODE
-    NodeSpec(id="process-clarification", ...),
-    NodeSpec(id="generate-results", ...),
-    NodeSpec(id="await-approval", ...),  # PAUSE NODE
-    NodeSpec(id="execute-action", ...),
-]
-
-# Edges with resume flows
-edges = [
-    EdgeSpec(
-        id="analyze-to-clarify",
-        source="analyze-request",
-        target="request-clarification",
-        condition=EdgeCondition.CONDITIONAL,
-        condition_expr="needs_clarification == true",
-    ),
-    # When resumed, goes to process-clarification
-    EdgeSpec(
-        id="clarify-to-process",
-        source="request-clarification",
-        target="process-clarification",
-        condition=EdgeCondition.ALWAYS,
-    ),
-    EdgeSpec(
-        id="results-to-approval",
-        source="generate-results",
-        target="await-approval",
-        condition=EdgeCondition.ALWAYS,
-    ),
-    # When resumed, goes to execute-action
-    EdgeSpec(
-        id="approval-to-execute",
-        source="await-approval",
-        target="execute-action",
-        condition=EdgeCondition.ALWAYS,
-    ),
-]
-
-# Configuration
-pause_nodes = ["request-clarification", "await-approval"]
-entry_points = {
-    "start": "analyze-request",
-    "request-clarification_resume": "process-clarification",
-    "await-approval_resume": "execute-action",
-}
-```
-
-### Running Pause/Resume Agents
-
-```python
-# Initial run - will pause at first pause node
-result1 = await agent.run(
-    context={"query": "research topic"},
-    session_state=None
-)
-
-# Check if paused
-if result1.paused_at:
-    print(f"Paused at: {result1.paused_at}")
-
-    # Resume with user input
-    result2 = await agent.run(
-        context={"user_response": "clarification details"},
-        session_state=result1.session_state  # Pass previous state
-    )
-```
-
-## Anti-Patterns
-
-### What NOT to Do
-
-❌ **Don't rely on `export_graph`** - Write files immediately, not at end
-```python
-# BAD: Building in session state, exporting at end
-mcp__agent-builder__add_node(...)
-mcp__agent-builder__add_node(...)
-mcp__agent-builder__export_graph()  # Files appear only now
-
-# GOOD: Writing files immediately
-Write(file_path="...", content=node_code)  # File visible now
-Write(file_path="...", content=node_code)  # File visible now
-```
-
-❌ **Don't hide code in session** - Write to files as components approved
-```python
-# BAD: Accumulating changes invisibly
-session.add_component(component1)
-session.add_component(component2)
-# User can't see anything yet
-
-# GOOD: Incremental visibility
-Edit(file_path="...", ...)  # User sees change 1
-Edit(file_path="...", ...)  # User sees change 2
-```
-
-❌ **Don't wait to write files** - Agent visible from first step
-```python
-# BAD: Building everything before writing
-design_all_nodes()
-design_all_edges()
-write_everything_at_once()
-
-# GOOD: Write as you go
-write_package_structure()  # Visible
-write_goal()  # Visible
-write_node_1()  # Visible
-write_node_2()  # Visible
-```
-
-❌ **Don't batch everything** - Write incrementally
-```python
-# BAD: Batching all nodes
-nodes = [design_node_1(), design_node_2(), ...]
-write_all_nodes(nodes)
-
-# GOOD: One at a time with user feedback
-write_node_1()  # User approves
-write_node_2()  # User approves
-write_node_3()  # User approves
-```
-
-### MCP Tools - Correct Usage
-
-**MCP tools OK for:**
-✅ `test_node` - Validate node configuration with mock inputs
-✅ `validate_graph` - Check graph structure
-✅ `create_session` - Track session state for bookkeeping
-✅ Other validation tools
-
-**Just don't:** Use MCP as the primary construction method or rely on export_graph
-
-## Best Practices
-
-### 1. Show Progress After Each Write
-
-```python
-# After writing a node
-print("✅ Added analyze_request_node to nodes/__init__.py")
-print("📊 Progress: 1/6 nodes added")
-print("📁 Open exports/my_agent/nodes/__init__.py to see it!")
-```
-
-### 2. Let User Open Files During Build
-
-```python
-# Encourage file inspection
-print("✅ Goal written to agent.py")
-print("")
-print("💡 Tip: Open exports/my_agent/agent.py in your editor to see the goal!")
-```
-
-### 3. Write Incrementally - One Component at a Time
-
-```python
-# Good flow
-write_package_structure()
-show_user("Package created")
-
-write_goal()
-show_user("Goal written")
-
-for node in nodes:
-    get_approval(node)
-    write_node(node)
-    show_user(f"Node {node.id} written")
-```
-
-### 4. Test As You Build
-
-```python
-# After adding several nodes
-print("💡 You can test current state with:")
-print("  PYTHONPATH=core:exports python -m my_agent validate")
-print("  PYTHONPATH=core:exports python -m my_agent info")
-```
-
-### 5. Keep User Informed
-
-```python
-# Clear status updates
-print("🔨 Creating package structure...")
-print("✅ Package created: exports/my_agent/")
-print("")
-print("📝 Next: Define agent goal")
-```
-
-## Continuous Monitoring Agents
-
-For agents that run continuously without terminal nodes:
-
-```python
-# No terminal nodes - loops forever
-terminal_nodes = []
-
-# Workflow loops back to start
-edges = [
-    EdgeSpec(id="monitor-to-check", source="monitor", target="check-condition"),
-    EdgeSpec(id="check-to-wait", source="check-condition", target="wait"),
-    EdgeSpec(id="wait-to-monitor", source="wait", target="monitor"),  # Loop
-]
-
-# Entry node only
-entry_node = "monitor"
-entry_points = {"start": "monitor"}
-pause_nodes = []
-```
-
-**Example: File Monitor**
-
-```python
-nodes = [
-    NodeSpec(id="list-files", ...),
-    NodeSpec(id="check-new-files", node_type="router", ...),
-    NodeSpec(id="process-files", ...),
-    NodeSpec(id="wait-interval", node_type="function", ...),
-]
-
-edges = [
-    EdgeSpec(id="list-to-check", source="list-files", target="check-new-files"),
-    EdgeSpec(
-        id="check-to-process",
-        source="check-new-files",
-        target="process-files",
-        condition=EdgeCondition.CONDITIONAL,
-        condition_expr="new_files_count > 0",
-    ),
-    EdgeSpec(
-        id="check-to-wait",
-        source="check-new-files",
-        target="wait-interval",
-        condition=EdgeCondition.CONDITIONAL,
-        condition_expr="new_files_count == 0",
-    ),
-    EdgeSpec(id="process-to-wait", source="process-files", target="wait-interval"),
-    EdgeSpec(id="wait-to-list", source="wait-interval", target="list-files"),  # Loop back
-]
-
-terminal_nodes = []  # No terminal - runs forever
-```
-
-## Complex Routing Patterns
-
-### Multi-Condition Router
-
-```python
-router_node = NodeSpec(
-    id="decision-router",
-    node_type="router",
-    input_keys=["analysis_result"],
-    output_keys=["decision"],
-    system_prompt="""
-    Based on the analysis result, decide the next action:
-    - If confidence > 0.9: route to "execute"
-    - If 0.5 <= confidence <= 0.9: route to "review"
-    - If confidence < 0.5: route to "clarify"
-
-    Return: {"decision": "execute|review|clarify"}
-    """,
-)
-
-# Edges for each route
-edges = [
-    EdgeSpec(
-        id="router-to-execute",
-        source="decision-router",
-        target="execute-action",
-        condition=EdgeCondition.CONDITIONAL,
-        condition_expr="decision == 'execute'",
-        priority=1,
-    ),
-    EdgeSpec(
-        id="router-to-review",
-        source="decision-router",
-        target="human-review",
-        condition=EdgeCondition.CONDITIONAL,
-        condition_expr="decision == 'review'",
-        priority=2,
-    ),
-    EdgeSpec(
-        id="router-to-clarify",
-        source="decision-router",
-        target="request-clarification",
-        condition=EdgeCondition.CONDITIONAL,
-        condition_expr="decision == 'clarify'",
-        priority=3,
-    ),
-]
-```
-
-## Error Handling Patterns
-
-### Graceful Failure with Fallback
-
-```python
-# Primary node with error handling
-nodes = [
-    NodeSpec(id="api-call", max_retries=3, ...),
-    NodeSpec(id="fallback-cache", ...),
-    NodeSpec(id="report-error", ...),
-]
-
-edges = [
-    # Success path
-    EdgeSpec(
-        id="api-success",
-        source="api-call",
-        target="process-results",
-        condition=EdgeCondition.ON_SUCCESS,
-    ),
-    # Fallback on failure
-    EdgeSpec(
-        id="api-to-fallback",
-        source="api-call",
-        target="fallback-cache",
-        condition=EdgeCondition.ON_FAILURE,
-        priority=1,
-    ),
-    # Report if fallback also fails
-    EdgeSpec(
-        id="fallback-to-error",
-        source="fallback-cache",
-        target="report-error",
-        condition=EdgeCondition.ON_FAILURE,
-        priority=1,
-    ),
-]
-```
-
-## Performance Optimization
-
-### Parallel Node Execution
-
-```python
-# Use multiple edges from same source for parallel execution
-edges = [
-    EdgeSpec(
-        id="start-to-search1",
-        source="start",
-        target="search-source-1",
-        condition=EdgeCondition.ALWAYS,
-    ),
-    EdgeSpec(
-        id="start-to-search2",
-        source="start",
-        target="search-source-2",
-        condition=EdgeCondition.ALWAYS,
-    ),
-    EdgeSpec(
-        id="start-to-search3",
-        source="start",
-        target="search-source-3",
-        condition=EdgeCondition.ALWAYS,
-    ),
-    # Converge results
-    EdgeSpec(
-        id="search1-to-merge",
-        source="search-source-1",
-        target="merge-results",
-    ),
-    EdgeSpec(
-        id="search2-to-merge",
-        source="search-source-2",
-        target="merge-results",
-    ),
-    EdgeSpec(
-        id="search3-to-merge",
-        source="search-source-3",
-        target="merge-results",
-    ),
-]
-```
-
-## Handoff to Testing
-
-When agent is complete, transition to testing phase:
-
-```python
-print("""
-✅ Agent complete: exports/my_agent/
-
-Next steps:
-1. Switch to testing-agent skill
-2. Generate and approve tests
-3. Run evaluation
-4. Debug any failures
-
-Command: "Test the agent at exports/my_agent/"
-""")
-```
-
-### Pre-Testing Checklist
-
-Before handing off to testing-agent:
-
-- [ ] Agent structure validates: `python -m agent_name validate`
-- [ ] All nodes defined in nodes/__init__.py
-- [ ] All edges connect valid nodes
-- [ ] Entry node specified
-- [ ] Agent can be imported: `from exports.agent_name import default_agent`
-- [ ] README.md with usage instructions
-- [ ] CLI commands work (info, validate)
-
-## Related Skills
-
-- **building-agents-core** - Fundamental concepts
-- **building-agents-construction** - Step-by-step building
-- **testing-agent** - Test and validate agents
-- **agent-workflow** - Complete workflow orchestrator
-
----
-
-**Remember: Agent is actively constructed, visible the whole time. No hidden state. No surprise exports. Just transparent, incremental file building.**

.claude/skills/hive-concepts/SKILL.md

@@ -0,0 +1,399 @@
+---
+name: hive-concepts
+description: Core concepts for goal-driven agents - architecture, node types (event_loop, function), tool discovery, and workflow overview. Use when starting agent development or need to understand agent fundamentals.
+license: Apache-2.0
+metadata:
+  author: hive
+  version: "2.0"
+  type: foundational
+  part_of: hive
+---
+
+# Building Agents - Core Concepts
+
+Foundational knowledge for building goal-driven agents as Python packages.
+
+## Architecture: Python Services (Not JSON Configs)
+
+Agents are built as Python packages:
+
+```
+exports/my_agent/
+├── __init__.py          # Package exports
+├── __main__.py          # CLI (run, info, validate, shell)
+├── agent.py             # Graph construction (goal, edges, agent class)
+├── nodes/__init__.py    # Node definitions (NodeSpec)
+├── config.py            # Runtime config
+└── README.md            # Documentation
+```
+
+**Key Principle: Agent is visible and editable during build**
+
+- Files created immediately as components are approved
+- User can watch files grow in their editor
+- No session state - just direct file writes
+- No "export" step - agent is ready when build completes
+
+## Core Concepts
+
+### Goal
+
+Success criteria and constraints (written to agent.py)
+
+```python
+goal = Goal(
+    id="research-goal",
+    name="Technical Research Agent",
+    description="Research technical topics thoroughly",
+    success_criteria=[
+        SuccessCriterion(
+            id="completeness",
+            description="Cover all aspects of topic",
+            metric="coverage_score",
+            target=">=0.9",
+            weight=0.4,
+        ),
+        # 3-5 success criteria total
+    ],
+    constraints=[
+        Constraint(
+            id="accuracy",
+            description="All information must be verified",
+            constraint_type="hard",
+            category="quality",
+        ),
+        # 1-5 constraints total
+    ],
+)
+```
+
+### Node
+
+Unit of work (written to nodes/__init__.py)
+
+**Node Types:**
+
+- `event_loop` — Multi-turn streaming loop with tool execution and judge-based evaluation. Works with or without tools.
+- `function` — Deterministic Python operations. No LLM involved.
+
+```python
+search_node = NodeSpec(
+    id="search-web",
+    name="Search Web",
+    description="Search for information and extract results",
+    node_type="event_loop",
+    input_keys=["query"],
+    output_keys=["search_results"],
+    system_prompt="Search the web for: {query}. Use the web_search tool to find results, then call set_output to store them.",
+    tools=["web_search"],
+)
+```
+
+**NodeSpec Fields for Event Loop Nodes:**
+
+| Field | Default | Description |
+|-------|---------|-------------|
+| `client_facing` | `False` | If True, streams output to user and blocks for input between turns |
+| `nullable_output_keys` | `[]` | Output keys that may remain unset (for mutually exclusive outputs) |
+| `max_node_visits` | `1` | Max times this node executes per run. Set >1 for feedback loop targets |
+
+### Edge
+
+Connection between nodes (written to agent.py)
+
+**Edge Conditions:**
+
+- `on_success` — Proceed if node succeeds (most common)
+- `on_failure` — Handle errors
+- `always` — Always proceed
+- `conditional` — Based on expression evaluating node output
+
+**Edge Priority:**
+
+Priority controls evaluation order when multiple edges leave the same node. Higher priority edges are evaluated first. Use negative priority for feedback edges (edges that loop back to earlier nodes).
+
+```python
+# Forward edge (evaluated first)
+EdgeSpec(
+    id="review-to-campaign",
+    source="review",
+    target="campaign-builder",
+    condition=EdgeCondition.CONDITIONAL,
+    condition_expr="output.get('approved_contacts') is not None",
+    priority=1,
+)
+
+# Feedback edge (evaluated after forward edges)
+EdgeSpec(
+    id="review-feedback",
+    source="review",
+    target="extractor",
+    condition=EdgeCondition.CONDITIONAL,
+    condition_expr="output.get('redo_extraction') is not None",
+    priority=-1,
+)
+```
+
+### Client-Facing Nodes
+
+For multi-turn conversations with the user, set `client_facing=True` on a node. The node will:
+- Stream its LLM output directly to the end user
+- Block for user input between conversational turns
+- Resume when new input is injected via `inject_event()`
+
+```python
+intake_node = NodeSpec(
+    id="intake",
+    name="Intake",
+    description="Gather requirements from the user",
+    node_type="event_loop",
+    client_facing=True,
+    input_keys=[],
+    output_keys=["repo_url", "project_url"],
+    system_prompt="You are the intake agent. Ask the user for the repo URL and project URL.",
+)
+```
+
+> **Legacy Note:** The old `pause_nodes` / `entry_points` pattern still works but `client_facing=True` is preferred for new agents.
+
+**STEP 1 / STEP 2 Prompt Pattern:** For client-facing nodes, structure the system prompt with two explicit phases:
+
+```python
+system_prompt="""\
+**STEP 1 — Respond to the user (text only, NO tool calls):**
+[Present information, ask questions, etc.]
+
+**STEP 2 — After the user responds, call set_output:**
+[Call set_output with the structured outputs]
+"""
+```
+
+This prevents the LLM from calling `set_output` prematurely before the user has had a chance to respond.
+
+### Node Design: Fewer, Richer Nodes
+
+Prefer fewer nodes that do more work over many thin single-purpose nodes:
+
+- **Bad**: 8 thin nodes (parse query → search → fetch → evaluate → synthesize → write → check → save)
+- **Good**: 4 rich nodes (intake → research → review → report)
+
+Why: Each node boundary requires serializing outputs and passing context. Fewer nodes means the LLM retains full context of its work within the node. A research node that searches, fetches, and analyzes keeps all the source material in its conversation history.
+
+### nullable_output_keys for Cross-Edge Inputs
+
+When a node receives inputs that only arrive on certain edges (e.g., `feedback` only comes from a review → research feedback loop, not from intake → research), mark those keys as `nullable_output_keys`:
+
+```python
+research_node = NodeSpec(
+    id="research",
+    input_keys=["research_brief", "feedback"],
+    nullable_output_keys=["feedback"],  # Not present on first visit
+    max_node_visits=3,
+    ...
+)
+```
+
+## Event Loop Architecture Concepts
+
+### How EventLoopNode Works
+
+An event loop node runs a multi-turn loop:
+1. LLM receives system prompt + conversation history
+2. LLM responds (text and/or tool calls)
+3. Tool calls are executed, results added to conversation
+4. Judge evaluates: ACCEPT (exit loop), RETRY (loop again), or ESCALATE
+5. Repeat until judge ACCEPTs or max_iterations reached
+
+### EventLoopNode Runtime
+
+EventLoopNodes are **auto-created** by `GraphExecutor` at runtime. You do NOT need to manually register them. Both `GraphExecutor` (direct) and `AgentRuntime` / `create_agent_runtime()` handle event_loop nodes automatically.
+
+```python
+# Direct execution — executor auto-creates EventLoopNodes
+from framework.graph.executor import GraphExecutor
+from framework.runtime.core import Runtime
+
+runtime = Runtime(storage_path)
+executor = GraphExecutor(
+    runtime=runtime,
+    llm=llm,
+    tools=tools,
+    tool_executor=tool_executor,
+    storage_path=storage_path,
+)
+result = await executor.execute(graph=graph, goal=goal, input_data=input_data)
+
+# TUI execution — AgentRuntime also works
+from framework.runtime.agent_runtime import create_agent_runtime
+runtime = create_agent_runtime(
+    graph=graph, goal=goal, storage_path=storage_path,
+    entry_points=[...], llm=llm, tools=tools, tool_executor=tool_executor,
+)
+```
+
+### set_output
+
+Nodes produce structured outputs by calling `set_output(key, value)` — a synthetic tool injected by the framework. When the LLM calls `set_output`, the value is stored in the output accumulator and made available to downstream nodes via shared memory.
+
+`set_output` is NOT a real tool — it is excluded from `real_tool_results`. For client-facing nodes, this means a turn where the LLM only calls `set_output` (no other tools) is treated as a conversational boundary and will block for user input.
+
+### JudgeProtocol
+
+**The judge is the SOLE mechanism for acceptance decisions.** Do not add ad-hoc framework gating, output rollback, or premature rejection logic. If the LLM calls `set_output` too early, fix it with better prompts or a custom judge — not framework-level guards.
+
+The judge controls when a node's loop exits:
+- **Implicit judge** (default, no judge configured): ACCEPTs when the LLM finishes with no tool calls and all required output keys are set
+- **SchemaJudge**: Validates outputs against a Pydantic model
+- **Custom judges**: Implement `evaluate(context) -> JudgeVerdict`
+
+### LoopConfig
+
+Controls loop behavior:
+- `max_iterations` (default 50) — prevents infinite loops
+- `max_tool_calls_per_turn` (default 10) — limits tool calls per LLM response
+- `tool_call_overflow_margin` (default 0.5) — wiggle room before discarding extra tool calls (50% means hard cutoff at 150% of limit)
+- `stall_detection_threshold` (default 3) — detects repeated identical responses
+- `max_history_tokens` (default 32000) — triggers conversation compaction
+
+### Data Tools (Spillover Management)
+
+When tool results exceed the context window, the framework automatically saves them to a spillover directory and truncates with a hint. Nodes that produce or consume large data should include the data tools:
+
+- `save_data(filename, data)` — Write data to a file in the data directory
+- `load_data(filename, offset=0, limit=50)` — Read data with line-based pagination
+- `list_data_files()` — List available data files
+- `serve_file_to_user(filename, label="")` — Get a clickable file:// URI for the user
+
+Note: `data_dir` is a framework-injected context parameter — the LLM never sees or passes it. `GraphExecutor.execute()` sets it per-execution via `contextvars`, so data tools and spillover always share the same session-scoped directory.
+
+These are real MCP tools (not synthetic). Add them to nodes that handle large tool results:
+
+```python
+research_node = NodeSpec(
+    ...
+    tools=["web_search", "web_scrape", "load_data", "save_data", "list_data_files"],
+)
+```
+
+### Fan-Out / Fan-In
+
+Multiple ON_SUCCESS edges from the same source create parallel execution. All branches run concurrently via `asyncio.gather()`. Parallel event_loop nodes must have disjoint `output_keys`.
+
+### max_node_visits
+
+Controls how many times a node can execute in one graph run. Default is 1. Set higher for nodes that are targets of feedback edges (review-reject loops). Set 0 for unlimited (guarded by max_steps).
+
+## Tool Discovery & Validation
+
+**CRITICAL:** Before adding a node with tools, you MUST verify the tools exist.
+
+Tools are provided by MCP servers. Never assume a tool exists - always discover dynamically.
+
+### Step 1: Register MCP Server (if not already done)
+
+```python
+mcp__agent-builder__add_mcp_server(
+    name="tools",
+    transport="stdio",
+    command="python",
+    args='["mcp_server.py", "--stdio"]',
+    cwd="../tools"
+)
+```
+
+### Step 2: Discover Available Tools
+
+```python
+# List all tools from all registered servers
+mcp__agent-builder__list_mcp_tools()
+
+# Or list tools from a specific server
+mcp__agent-builder__list_mcp_tools(server_name="tools")
+```
+
+### Step 3: Validate Before Adding Nodes
+
+Before writing a node with `tools=[...]`:
+
+1. Call `list_mcp_tools()` to get available tools
+2. Check each tool in your node exists in the response
+3. If a tool doesn't exist:
+   - **DO NOT proceed** with the node
+   - Inform the user: "The tool 'X' is not available. Available tools are: ..."
+   - Ask if they want to use an alternative or proceed without the tool
+
+### Tool Validation Anti-Patterns
+
+- **Never assume a tool exists** - always call `list_mcp_tools()` first
+- **Never write a node with unverified tools** - validate before writing
+- **Never silently drop tools** - if a tool doesn't exist, inform the user
+- **Never guess tool names** - use exact names from discovery response
+
+## Workflow Overview: Incremental File Construction
+
+```
+1. CREATE PACKAGE → mkdir + write skeletons
+2. DEFINE GOAL → Write to agent.py + config.py
+3. FOR EACH NODE:
+   - Propose design (event_loop for LLM work, function for deterministic)
+   - User approves
+   - Write to nodes/__init__.py IMMEDIATELY
+   - (Optional) Validate with test_node
+4. CONNECT EDGES → Update agent.py
+   - Use priority for feedback edges (negative priority)
+   - (Optional) Validate with validate_graph
+5. FINALIZE → Write agent class to agent.py
+6. DONE - Agent ready at exports/my_agent/
+```
+
+**Files written immediately. MCP tools optional for validation/testing bookkeeping.**
+
+## When to Use This Skill
+
+Use hive-concepts when:
+- Starting a new agent project and need to understand fundamentals
+- Need to understand agent architecture before building
+- Want to validate tool availability before proceeding
+- Learning about node types, edges, and graph execution
+
+**Next Steps:**
+- Ready to build? → Use `hive-create` skill
+- Need patterns and examples? → Use `hive-patterns` skill
+
+## MCP Tools for Validation
+
+After writing files, optionally use MCP tools for validation:
+
+**test_node** - Validate node configuration with mock inputs
+```python
+mcp__agent-builder__test_node(
+    node_id="search-web",
+    test_input='{"query": "test query"}',
+    mock_llm_response='{"results": "mock output"}'
+)
+```
+
+**validate_graph** - Check graph structure
+```python
+mcp__agent-builder__validate_graph()
+# Returns: unreachable nodes, missing connections, event_loop validation, etc.
+```
+
+**configure_loop** - Set event loop parameters
+```python
+mcp__agent-builder__configure_loop(
+    max_iterations=50,
+    max_tool_calls_per_turn=10,
+    stall_detection_threshold=3,
+    max_history_tokens=32000
+)
+```
+
+**Key Point:** Files are written FIRST. MCP tools are for validation only.
+
+## Related Skills
+
+- **hive-create** - Step-by-step building process
+- **hive-patterns** - Best practices: judges, feedback edges, fan-out, context management
+- **hive** - Complete workflow orchestrator
+- **hive-test** - Test and validate completed agents

.claude/skills/hive-create/examples/deep_research_agent/__init__.py

@@ -0,0 +1,24 @@
+"""
+Deep Research Agent - Interactive, rigorous research with TUI conversation.
+
+Research any topic through multi-source web search, quality evaluation,
+and synthesis. Features client-facing TUI interaction at key checkpoints
+for user guidance and iterative deepening.
+"""
+
+from .agent import DeepResearchAgent, default_agent, goal, nodes, edges
+from .config import RuntimeConfig, AgentMetadata, default_config, metadata
+
+__version__ = "1.0.0"
+
+__all__ = [
+    "DeepResearchAgent",
+    "default_agent",
+    "goal",
+    "nodes",
+    "edges",
+    "RuntimeConfig",
+    "AgentMetadata",
+    "default_config",
+    "metadata",
+]

.claude/skills/hive-create/examples/deep_research_agent/__main__.py

@@ -0,0 +1,241 @@
+"""
+CLI entry point for Deep Research Agent.
+
+Uses AgentRuntime for multi-entrypoint support with HITL pause/resume.
+"""
+
+import asyncio
+import json
+import logging
+import sys
+import click
+
+from .agent import default_agent, DeepResearchAgent
+
+
+def setup_logging(verbose=False, debug=False):
+    """Configure logging for execution visibility."""
+    if debug:
+        level, fmt = logging.DEBUG, "%(asctime)s %(name)s: %(message)s"
+    elif verbose:
+        level, fmt = logging.INFO, "%(message)s"
+    else:
+        level, fmt = logging.WARNING, "%(levelname)s: %(message)s"
+    logging.basicConfig(level=level, format=fmt, stream=sys.stderr)
+    logging.getLogger("framework").setLevel(level)
+
+
+@click.group()
+@click.version_option(version="1.0.0")
+def cli():
+    """Deep Research Agent - Interactive, rigorous research with TUI conversation."""
+    pass
+
+
+@cli.command()
+@click.option("--topic", "-t", type=str, required=True, help="Research topic")
+@click.option("--mock", is_flag=True, help="Run in mock mode")
+@click.option("--quiet", "-q", is_flag=True, help="Only output result JSON")
+@click.option("--verbose", "-v", is_flag=True, help="Show execution details")
+@click.option("--debug", is_flag=True, help="Show debug logging")
+def run(topic, mock, quiet, verbose, debug):
+    """Execute research on a topic."""
+    if not quiet:
+        setup_logging(verbose=verbose, debug=debug)
+
+    context = {"topic": topic}
+
+    result = asyncio.run(default_agent.run(context, mock_mode=mock))
+
+    output_data = {
+        "success": result.success,
+        "steps_executed": result.steps_executed,
+        "output": result.output,
+    }
+    if result.error:
+        output_data["error"] = result.error
+
+    click.echo(json.dumps(output_data, indent=2, default=str))
+    sys.exit(0 if result.success else 1)
+
+
+@cli.command()
+@click.option("--mock", is_flag=True, help="Run in mock mode")
+@click.option("--verbose", "-v", is_flag=True, help="Show execution details")
+@click.option("--debug", is_flag=True, help="Show debug logging")
+def tui(mock, verbose, debug):
+    """Launch the TUI dashboard for interactive research."""
+    setup_logging(verbose=verbose, debug=debug)
+
+    try:
+        from framework.tui.app import AdenTUI
+    except ImportError:
+        click.echo(
+            "TUI requires the 'textual' package. Install with: pip install textual"
+        )
+        sys.exit(1)
+
+    from pathlib import Path
+
+    from framework.llm import LiteLLMProvider
+    from framework.runner.tool_registry import ToolRegistry
+    from framework.runtime.agent_runtime import create_agent_runtime
+    from framework.runtime.event_bus import EventBus
+    from framework.runtime.execution_stream import EntryPointSpec
+
+    async def run_with_tui():
+        agent = DeepResearchAgent()
+
+        # Build graph and tools
+        agent._event_bus = EventBus()
+        agent._tool_registry = ToolRegistry()
+
+        storage_path = Path.home() / ".hive" / "agents" / "deep_research_agent"
+        storage_path.mkdir(parents=True, exist_ok=True)
+
+        mcp_config_path = Path(__file__).parent / "mcp_servers.json"
+        if mcp_config_path.exists():
+            agent._tool_registry.load_mcp_config(mcp_config_path)
+
+        llm = None
+        if not mock:
+            llm = LiteLLMProvider(
+                model=agent.config.model,
+                api_key=agent.config.api_key,
+                api_base=agent.config.api_base,
+            )
+
+        tools = list(agent._tool_registry.get_tools().values())
+        tool_executor = agent._tool_registry.get_executor()
+        graph = agent._build_graph()
+
+        runtime = create_agent_runtime(
+            graph=graph,
+            goal=agent.goal,
+            storage_path=storage_path,
+            entry_points=[
+                EntryPointSpec(
+                    id="start",
+                    name="Start Research",
+                    entry_node="intake",
+                    trigger_type="manual",
+                    isolation_level="isolated",
+                ),
+            ],
+            llm=llm,
+            tools=tools,
+            tool_executor=tool_executor,
+        )
+
+        await runtime.start()
+
+        try:
+            app = AdenTUI(runtime)
+            await app.run_async()
+        finally:
+            await runtime.stop()
+
+    asyncio.run(run_with_tui())
+
+
+@cli.command()
+@click.option("--json", "output_json", is_flag=True)
+def info(output_json):
+    """Show agent information."""
+    info_data = default_agent.info()
+    if output_json:
+        click.echo(json.dumps(info_data, indent=2))
+    else:
+        click.echo(f"Agent: {info_data['name']}")
+        click.echo(f"Version: {info_data['version']}")
+        click.echo(f"Description: {info_data['description']}")
+        click.echo(f"\nNodes: {', '.join(info_data['nodes'])}")
+        click.echo(f"Client-facing: {', '.join(info_data['client_facing_nodes'])}")
+        click.echo(f"Entry: {info_data['entry_node']}")
+        click.echo(f"Terminal: {', '.join(info_data['terminal_nodes'])}")
+
+
+@cli.command()
+def validate():
+    """Validate agent structure."""
+    validation = default_agent.validate()
+    if validation["valid"]:
+        click.echo("Agent is valid")
+        if validation["warnings"]:
+            for warning in validation["warnings"]:
+                click.echo(f"  WARNING: {warning}")
+    else:
+        click.echo("Agent has errors:")
+        for error in validation["errors"]:
+            click.echo(f"  ERROR: {error}")
+    sys.exit(0 if validation["valid"] else 1)
+
+
+@cli.command()
+@click.option("--verbose", "-v", is_flag=True)
+def shell(verbose):
+    """Interactive research session (CLI, no TUI)."""
+    asyncio.run(_interactive_shell(verbose))
+
+
+async def _interactive_shell(verbose=False):
+    """Async interactive shell."""
+    setup_logging(verbose=verbose)
+
+    click.echo("=== Deep Research Agent ===")
+    click.echo("Enter a topic to research (or 'quit' to exit):\n")
+
+    agent = DeepResearchAgent()
+    await agent.start()
+
+    try:
+        while True:
+            try:
+                topic = await asyncio.get_event_loop().run_in_executor(
+                    None, input, "Topic> "
+                )
+                if topic.lower() in ["quit", "exit", "q"]:
+                    click.echo("Goodbye!")
+                    break
+
+                if not topic.strip():
+                    continue
+
+                click.echo("\nResearching...\n")
+
+                result = await agent.trigger_and_wait("start", {"topic": topic})
+
+                if result is None:
+                    click.echo("\n[Execution timed out]\n")
+                    continue
+
+                if result.success:
+                    output = result.output
+                    if "report_content" in output:
+                        click.echo("\n--- Report ---\n")
+                        click.echo(output["report_content"])
+                        click.echo("\n")
+                    if "references" in output:
+                        click.echo("--- References ---\n")
+                        for ref in output.get("references", []):
+                            click.echo(
+                                f"  [{ref.get('number', '?')}] {ref.get('title', '')} - {ref.get('url', '')}"
+                            )
+                        click.echo("\n")
+                else:
+                    click.echo(f"\nResearch failed: {result.error}\n")
+
+            except KeyboardInterrupt:
+                click.echo("\nGoodbye!")
+                break
+            except Exception as e:
+                click.echo(f"Error: {e}", err=True)
+                import traceback
+
+                traceback.print_exc()
+    finally:
+        await agent.stop()
+
+
+if __name__ == "__main__":
+    cli()

.claude/skills/hive-create/examples/deep_research_agent/agent.py

@@ -0,0 +1,358 @@
+"""Agent graph construction for Deep Research Agent."""
+
+from pathlib import Path
+
+from framework.graph import EdgeSpec, EdgeCondition, Goal, SuccessCriterion, Constraint
+from framework.graph.edge import GraphSpec
+from framework.graph.executor import ExecutionResult
+from framework.graph.checkpoint_config import CheckpointConfig
+from framework.llm import LiteLLMProvider
+from framework.runner.tool_registry import ToolRegistry
+from framework.runtime.agent_runtime import AgentRuntime, create_agent_runtime
+from framework.runtime.execution_stream import EntryPointSpec
+
+from .config import default_config, metadata
+from .nodes import (
+    intake_node,
+    research_node,
+    review_node,
+    report_node,
+)
+
+# Goal definition
+goal = Goal(
+    id="rigorous-interactive-research",
+    name="Rigorous Interactive Research",
+    description=(
+        "Research any topic by searching diverse sources, analyzing findings, "
+        "and producing a cited report — with user checkpoints to guide direction."
+    ),
+    success_criteria=[
+        SuccessCriterion(
+            id="source-diversity",
+            description="Use multiple diverse, authoritative sources",
+            metric="source_count",
+            target=">=5",
+            weight=0.25,
+        ),
+        SuccessCriterion(
+            id="citation-coverage",
+            description="Every factual claim in the report cites its source",
+            metric="citation_coverage",
+            target="100%",
+            weight=0.25,
+        ),
+        SuccessCriterion(
+            id="user-satisfaction",
+            description="User reviews findings before report generation",
+            metric="user_approval",
+            target="true",
+            weight=0.25,
+        ),
+        SuccessCriterion(
+            id="report-completeness",
+            description="Final report answers the original research questions",
+            metric="question_coverage",
+            target="90%",
+            weight=0.25,
+        ),
+    ],
+    constraints=[
+        Constraint(
+            id="no-hallucination",
+            description="Only include information found in fetched sources",
+            constraint_type="quality",
+            category="accuracy",
+        ),
+        Constraint(
+            id="source-attribution",
+            description="Every claim must cite its source with a numbered reference",
+            constraint_type="quality",
+            category="accuracy",
+        ),
+        Constraint(
+            id="user-checkpoint",
+            description="Present findings to the user before writing the final report",
+            constraint_type="functional",
+            category="interaction",
+        ),
+    ],
+)
+
+# Node list
+nodes = [
+    intake_node,
+    research_node,
+    review_node,
+    report_node,
+]
+
+# Edge definitions
+edges = [
+    # intake -> research
+    EdgeSpec(
+        id="intake-to-research",
+        source="intake",
+        target="research",
+        condition=EdgeCondition.ON_SUCCESS,
+        priority=1,
+    ),
+    # research -> review
+    EdgeSpec(
+        id="research-to-review",
+        source="research",
+        target="review",
+        condition=EdgeCondition.ON_SUCCESS,
+        priority=1,
+    ),
+    # review -> research (feedback loop)
+    EdgeSpec(
+        id="review-to-research-feedback",
+        source="review",
+        target="research",
+        condition=EdgeCondition.CONDITIONAL,
+        condition_expr="needs_more_research == True",
+        priority=1,
+    ),
+    # review -> report (user satisfied)
+    EdgeSpec(
+        id="review-to-report",
+        source="review",
+        target="report",
+        condition=EdgeCondition.CONDITIONAL,
+        condition_expr="needs_more_research == False",
+        priority=2,
+    ),
+    # report -> research (user wants deeper research on current topic)
+    EdgeSpec(
+        id="report-to-research",
+        source="report",
+        target="research",
+        condition=EdgeCondition.CONDITIONAL,
+        condition_expr="str(next_action).lower() == 'more_research'",
+        priority=2,
+    ),
+    # report -> intake (user wants a new topic — default when not more_research)
+    EdgeSpec(
+        id="report-to-intake",
+        source="report",
+        target="intake",
+        condition=EdgeCondition.CONDITIONAL,
+        condition_expr="str(next_action).lower() != 'more_research'",
+        priority=1,
+    ),
+]
+
+# Graph configuration
+entry_node = "intake"
+entry_points = {"start": "intake"}
+pause_nodes = []
+terminal_nodes = []
+
+
+class DeepResearchAgent:
+    """
+    Deep Research Agent — 4-node pipeline with user checkpoints.
+
+    Flow: intake -> research -> review -> report
+                      ^           |
+                      +-- feedback loop (if user wants more)
+
+    Uses AgentRuntime for proper session management:
+    - Session-scoped storage (sessions/{session_id}/)
+    - Checkpointing for resume capability
+    - Runtime logging
+    - Data folder for save_data/load_data
+    """
+
+    def __init__(self, config=None):
+        self.config = config or default_config
+        self.goal = goal
+        self.nodes = nodes
+        self.edges = edges
+        self.entry_node = entry_node
+        self.entry_points = entry_points
+        self.pause_nodes = pause_nodes
+        self.terminal_nodes = terminal_nodes
+        self._graph: GraphSpec | None = None
+        self._agent_runtime: AgentRuntime | None = None
+        self._tool_registry: ToolRegistry | None = None
+        self._storage_path: Path | None = None
+
+    def _build_graph(self) -> GraphSpec:
+        """Build the GraphSpec."""
+        return GraphSpec(
+            id="deep-research-agent-graph",
+            goal_id=self.goal.id,
+            version="1.0.0",
+            entry_node=self.entry_node,
+            entry_points=self.entry_points,
+            terminal_nodes=self.terminal_nodes,
+            pause_nodes=self.pause_nodes,
+            nodes=self.nodes,
+            edges=self.edges,
+            default_model=self.config.model,
+            max_tokens=self.config.max_tokens,
+            loop_config={
+                "max_iterations": 100,
+                "max_tool_calls_per_turn": 20,
+                "max_history_tokens": 32000,
+            },
+            conversation_mode="continuous",
+            identity_prompt=(
+                "You are a rigorous research agent. You search for information "
+                "from diverse, authoritative sources, analyze findings critically, "
+                "and produce well-cited reports. You never fabricate information — "
+                "every claim must trace back to a source you actually retrieved."
+            ),
+        )
+
+    def _setup(self, mock_mode=False) -> None:
+        """Set up the agent runtime with sessions, checkpoints, and logging."""
+        self._storage_path = Path.home() / ".hive" / "agents" / "deep_research_agent"
+        self._storage_path.mkdir(parents=True, exist_ok=True)
+
+        self._tool_registry = ToolRegistry()
+
+        mcp_config_path = Path(__file__).parent / "mcp_servers.json"
+        if mcp_config_path.exists():
+            self._tool_registry.load_mcp_config(mcp_config_path)
+
+        llm = None
+        if not mock_mode:
+            llm = LiteLLMProvider(
+                model=self.config.model,
+                api_key=self.config.api_key,
+                api_base=self.config.api_base,
+            )
+
+        tool_executor = self._tool_registry.get_executor()
+        tools = list(self._tool_registry.get_tools().values())
+
+        self._graph = self._build_graph()
+
+        checkpoint_config = CheckpointConfig(
+            enabled=True,
+            checkpoint_on_node_start=False,
+            checkpoint_on_node_complete=True,
+            checkpoint_max_age_days=7,
+            async_checkpoint=True,
+        )
+
+        entry_point_specs = [
+            EntryPointSpec(
+                id="default",
+                name="Default",
+                entry_node=self.entry_node,
+                trigger_type="manual",
+                isolation_level="shared",
+            )
+        ]
+
+        self._agent_runtime = create_agent_runtime(
+            graph=self._graph,
+            goal=self.goal,
+            storage_path=self._storage_path,
+            entry_points=entry_point_specs,
+            llm=llm,
+            tools=tools,
+            tool_executor=tool_executor,
+            checkpoint_config=checkpoint_config,
+        )
+
+    async def start(self, mock_mode=False) -> None:
+        """Set up and start the agent runtime."""
+        if self._agent_runtime is None:
+            self._setup(mock_mode=mock_mode)
+        if not self._agent_runtime.is_running:
+            await self._agent_runtime.start()
+
+    async def stop(self) -> None:
+        """Stop the agent runtime and clean up."""
+        if self._agent_runtime and self._agent_runtime.is_running:
+            await self._agent_runtime.stop()
+        self._agent_runtime = None
+
+    async def trigger_and_wait(
+        self,
+        entry_point: str = "default",
+        input_data: dict | None = None,
+        timeout: float | None = None,
+        session_state: dict | None = None,
+    ) -> ExecutionResult | None:
+        """Execute the graph and wait for completion."""
+        if self._agent_runtime is None:
+            raise RuntimeError("Agent not started. Call start() first.")
+
+        return await self._agent_runtime.trigger_and_wait(
+            entry_point_id=entry_point,
+            input_data=input_data or {},
+            session_state=session_state,
+        )
+
+    async def run(
+        self, context: dict, mock_mode=False, session_state=None
+    ) -> ExecutionResult:
+        """Run the agent (convenience method for single execution)."""
+        await self.start(mock_mode=mock_mode)
+        try:
+            result = await self.trigger_and_wait(
+                "default", context, session_state=session_state
+            )
+            return result or ExecutionResult(success=False, error="Execution timeout")
+        finally:
+            await self.stop()
+
+    def info(self):
+        """Get agent information."""
+        return {
+            "name": metadata.name,
+            "version": metadata.version,
+            "description": metadata.description,
+            "goal": {
+                "name": self.goal.name,
+                "description": self.goal.description,
+            },
+            "nodes": [n.id for n in self.nodes],
+            "edges": [e.id for e in self.edges],
+            "entry_node": self.entry_node,
+            "entry_points": self.entry_points,
+            "pause_nodes": self.pause_nodes,
+            "terminal_nodes": self.terminal_nodes,
+            "client_facing_nodes": [n.id for n in self.nodes if n.client_facing],
+        }
+
+    def validate(self):
+        """Validate agent structure."""
+        errors = []
+        warnings = []
+
+        node_ids = {node.id for node in self.nodes}
+        for edge in self.edges:
+            if edge.source not in node_ids:
+                errors.append(f"Edge {edge.id}: source '{edge.source}' not found")
+            if edge.target not in node_ids:
+                errors.append(f"Edge {edge.id}: target '{edge.target}' not found")
+
+        if self.entry_node not in node_ids:
+            errors.append(f"Entry node '{self.entry_node}' not found")
+
+        for terminal in self.terminal_nodes:
+            if terminal not in node_ids:
+                errors.append(f"Terminal node '{terminal}' not found")
+
+        for ep_id, node_id in self.entry_points.items():
+            if node_id not in node_ids:
+                errors.append(
+                    f"Entry point '{ep_id}' references unknown node '{node_id}'"
+                )
+
+        return {
+            "valid": len(errors) == 0,
+            "errors": errors,
+            "warnings": warnings,
+        }
+
+
+# Create default instance
+default_agent = DeepResearchAgent()

.claude/skills/hive-create/examples/deep_research_agent/config.py

@@ -0,0 +1,26 @@
+"""Runtime configuration."""
+
+from dataclasses import dataclass
+
+from framework.config import RuntimeConfig
+
+default_config = RuntimeConfig()
+
+
+@dataclass
+class AgentMetadata:
+    name: str = "Deep Research Agent"
+    version: str = "1.0.0"
+    description: str = (
+        "Interactive research agent that rigorously investigates topics through "
+        "multi-source search, quality evaluation, and synthesis - with TUI conversation "
+        "at key checkpoints for user guidance and feedback."
+    )
+    intro_message: str = (
+        "Hi! I'm your deep research assistant. Tell me a topic and I'll investigate it "
+        "thoroughly — searching multiple sources, evaluating quality, and synthesizing "
+        "a comprehensive report. What would you like me to research?"
+    )
+
+
+metadata = AgentMetadata()

.claude/skills/hive-create/examples/deep_research_agent/mcp_servers.json

@@ -0,0 +1,9 @@
+{
+  "hive-tools": {
+    "transport": "stdio",
+    "command": "uv",
+    "args": ["run", "python", "mcp_server.py", "--stdio"],
+    "cwd": "../../tools",
+    "description": "Hive tools MCP server providing web_search, web_scrape, and write_to_file"
+  }
+}

.claude/skills/hive-create/examples/deep_research_agent/nodes/__init__.py

@@ -0,0 +1,204 @@
+"""Node definitions for Deep Research Agent."""
+
+from framework.graph import NodeSpec
+
+# Node 1: Intake (client-facing)
+# Brief conversation to clarify what the user wants researched.
+intake_node = NodeSpec(
+    id="intake",
+    name="Research Intake",
+    description="Discuss the research topic with the user, clarify scope, and confirm direction",
+    node_type="event_loop",
+    client_facing=True,
+    max_node_visits=0,
+    input_keys=["topic"],
+    output_keys=["research_brief"],
+    success_criteria=(
+        "The research brief is specific and actionable: it states the topic, "
+        "the key questions to answer, the desired scope, and depth."
+    ),
+    system_prompt="""\
+You are a research intake specialist. The user wants to research a topic.
+Have a brief conversation to clarify what they need.
+
+**STEP 1 — Read and respond (text only, NO tool calls):**
+1. Read the topic provided
+2. If it's vague, ask 1-2 clarifying questions (scope, angle, depth)
+3. If it's already clear, confirm your understanding and ask the user to confirm
+
+Keep it short. Don't over-ask.
+
+**STEP 2 — After the user confirms, call set_output:**
+- set_output("research_brief", "A clear paragraph describing exactly what to research, \
+what questions to answer, what scope to cover, and how deep to go.")
+""",
+    tools=[],
+)
+
+# Node 2: Research
+# The workhorse — searches the web, fetches content, analyzes sources.
+# One node with both tools avoids the context-passing overhead of 5 separate nodes.
+research_node = NodeSpec(
+    id="research",
+    name="Research",
+    description="Search the web, fetch source content, and compile findings",
+    node_type="event_loop",
+    max_node_visits=0,
+    input_keys=["research_brief", "feedback"],
+    output_keys=["findings", "sources", "gaps"],
+    nullable_output_keys=["feedback"],
+    success_criteria=(
+        "Findings reference at least 3 distinct sources with URLs. "
+        "Key claims are substantiated by fetched content, not generated."
+    ),
+    system_prompt="""\
+You are a research agent. Given a research brief, find and analyze sources.
+
+If feedback is provided, this is a follow-up round — focus on the gaps identified.
+
+Work in phases:
+1. **Search**: Use web_search with 3-5 diverse queries covering different angles.
+   Prioritize authoritative sources (.edu, .gov, established publications).
+2. **Fetch**: Use web_scrape on the most promising URLs (aim for 5-8 sources).
+   Skip URLs that fail. Extract the substantive content.
+3. **Analyze**: Review what you've collected. Identify key findings, themes,
+   and any contradictions between sources.
+
+Important:
+- Work in batches of 3-4 tool calls at a time — never more than 10 per turn
+- After each batch, assess whether you have enough material
+- Prefer quality over quantity — 5 good sources beat 15 thin ones
+- Track which URL each finding comes from (you'll need citations later)
+- Call set_output for each key in a SEPARATE turn (not in the same turn as other tool calls)
+
+When done, use set_output (one key at a time, separate turns):
+- set_output("findings", "Structured summary: key findings with source URLs for each claim. \
+Include themes, contradictions, and confidence levels.")
+- set_output("sources", [{"url": "...", "title": "...", "summary": "..."}])
+- set_output("gaps", "What aspects of the research brief are NOT well-covered yet, if any.")
+""",
+    tools=[
+        "web_search",
+        "web_scrape",
+        "load_data",
+        "save_data",
+        "append_data",
+        "list_data_files",
+    ],
+)
+
+# Node 3: Review (client-facing)
+# Shows the user what was found and asks whether to dig deeper or proceed.
+review_node = NodeSpec(
+    id="review",
+    name="Review Findings",
+    description="Present findings to user and decide whether to research more or write the report",
+    node_type="event_loop",
+    client_facing=True,
+    max_node_visits=0,
+    input_keys=["findings", "sources", "gaps", "research_brief"],
+    output_keys=["needs_more_research", "feedback"],
+    success_criteria=(
+        "The user has been presented with findings and has explicitly indicated "
+        "whether they want more research or are ready for the report."
+    ),
+    system_prompt="""\
+Present the research findings to the user clearly and concisely.
+
+**STEP 1 — Present (your first message, text only, NO tool calls):**
+1. **Summary** (2-3 sentences of what was found)
+2. **Key Findings** (bulleted, with confidence levels)
+3. **Sources Used** (count and quality assessment)
+4. **Gaps** (what's still unclear or under-covered)
+
+End by asking: Are they satisfied, or do they want deeper research? \
+Should we proceed to writing the final report?
+
+**STEP 2 — After the user responds, call set_output:**
+- set_output("needs_more_research", "true")  — if they want more
+- set_output("needs_more_research", "false") — if they're satisfied
+- set_output("feedback", "What the user wants explored further, or empty string")
+""",
+    tools=[],
+)
+
+# Node 4: Report (client-facing)
+# Writes an HTML report, serves the link to the user, and answers follow-ups.
+report_node = NodeSpec(
+    id="report",
+    name="Write & Deliver Report",
+    description="Write a cited HTML report from the findings and present it to the user",
+    node_type="event_loop",
+    client_facing=True,
+    max_node_visits=0,
+    input_keys=["findings", "sources", "research_brief"],
+    output_keys=["delivery_status", "next_action"],
+    success_criteria=(
+        "An HTML report has been saved, the file link has been presented to the user, "
+        "and the user has indicated what they want to do next."
+    ),
+    system_prompt="""\
+Write a research report as an HTML file and present it to the user.
+
+IMPORTANT: save_data requires TWO separate arguments: filename and data.
+Call it like: save_data(filename="report.html", data="<html>...</html>")
+Do NOT use _raw, do NOT nest arguments inside a JSON string.
+
+**STEP 1 — Write and save the HTML report (tool calls, NO text to user yet):**
+
+Build a clean HTML document. Keep the HTML concise — aim for clarity over length.
+Use minimal embedded CSS (a few lines of style, not a full framework).
+
+Report structure:
+- Title & date
+- Executive Summary (2-3 paragraphs)
+- Key Findings (organized by theme, with [n] citation links)
+- Analysis (synthesis, implications)
+- Conclusion (key takeaways)
+- References (numbered list with clickable URLs)
+
+Requirements:
+- Every factual claim must cite its source with [n] notation
+- Be objective — present multiple viewpoints where sources disagree
+- Answer the original research questions from the brief
+
+Save the HTML:
+  save_data(filename="report.html", data="<html>...</html>")
+
+Then get the clickable link:
+  serve_file_to_user(filename="report.html", label="Research Report")
+
+If save_data fails, simplify and shorten the HTML, then retry.
+
+**STEP 2 — Present the link to the user (text only, NO tool calls):**
+
+Tell the user the report is ready and include the file:// URI from
+serve_file_to_user so they can click it to open. Give a brief summary
+of what the report covers. Ask if they have questions or want to continue.
+
+**STEP 3 — After the user responds:**
+- Answer any follow-up questions from the research material
+- When the user is ready to move on, ask what they'd like to do next:
+  - Research a new topic?
+  - Dig deeper into the current topic?
+- Then call set_output:
+  - set_output("delivery_status", "completed")
+  - set_output("next_action", "new_topic")       — if they want a new topic
+  - set_output("next_action", "more_research")   — if they want deeper research
+""",
+    tools=[
+        "save_data",
+        "append_data",
+        "edit_data",
+        "serve_file_to_user",
+        "load_data",
+        "list_data_files",
+    ],
+)
+
+__all__ = [
+    "intake_node",
+    "research_node",
+    "review_node",
+    "report_node",
+]

.claude/skills/hive-credentials/SKILL.md

@@ -0,0 +1,640 @@
+---
+name: hive-credentials
+description: Set up and install credentials for an agent. Detects missing credentials from agent config, collects them from the user, and stores them securely in the local encrypted store at ~/.hive/credentials.
+license: Apache-2.0
+metadata:
+  author: hive
+  version: "2.3"
+  type: utility
+---
+
+# Setup Credentials
+
+Interactive credential setup for agents with multiple authentication options. Detects what's missing, offers auth method choices, validates with health checks, and stores credentials securely.
+
+## When to Use
+
+- Before running or testing an agent for the first time
+- When `AgentRunner.run()` fails with "missing required credentials"
+- When a user asks to configure credentials for an agent
+- After building a new agent that uses tools requiring API keys
+
+## Workflow
+
+### Step 1: Identify the Agent
+
+Determine which agent needs credentials. The user will either:
+
+- Name the agent directly (e.g., "set up credentials for hubspot-agent")
+- Have an agent directory open (check `exports/` for agent dirs)
+- Be working on an agent in the current session
+
+Locate the agent's directory under `exports/{agent_name}/`.
+
+### Step 2: Detect Missing Credentials
+
+Use the `check_missing_credentials` MCP tool to detect what the agent needs and what's already configured. This tool loads the agent, inspects its required tools and node types, maps them to credentials via `CREDENTIAL_SPECS`, and checks both the encrypted store and environment variables.
+
+```
+check_missing_credentials(agent_path="exports/{agent_name}")
+```
+
+The tool returns a JSON response:
+
+```json
+{
+  "agent": "exports/{agent_name}",
+  "missing": [
+    {
+      "credential_name": "brave_search",
+      "env_var": "BRAVE_SEARCH_API_KEY",
+      "description": "Brave Search API key for web search",
+      "help_url": "https://brave.com/search/api/",
+      "tools": ["web_search"]
+    }
+  ],
+  "available": [
+    {
+      "credential_name": "anthropic",
+      "env_var": "ANTHROPIC_API_KEY",
+      "source": "encrypted_store"
+    }
+  ],
+  "total_missing": 1,
+  "ready": false
+}
+```
+
+**If `ready` is true (nothing missing):** Report all credentials as configured and skip Steps 3-5. Example:
+
+```
+All required credentials are already configured:
+  ✓ anthropic (ANTHROPIC_API_KEY)
+  ✓ brave_search (BRAVE_SEARCH_API_KEY)
+Your agent is ready to run!
+```
+
+**If credentials are missing:** Continue to Step 3 with the `missing` list.
+
+### Step 3: Present Auth Options for Each Missing Credential
+
+For each missing credential, check what authentication methods are available:
+
+```python
+from aden_tools.credentials import CREDENTIAL_SPECS
+
+spec = CREDENTIAL_SPECS.get("hubspot")
+if spec:
+    # Determine available auth options
+    auth_options = []
+    if spec.aden_supported:
+        auth_options.append("aden")
+    if spec.direct_api_key_supported:
+        auth_options.append("direct")
+    auth_options.append("custom")  # Always available
+
+    # Get setup info
+    setup_info = {
+        "env_var": spec.env_var,
+        "description": spec.description,
+        "help_url": spec.help_url,
+        "api_key_instructions": spec.api_key_instructions,
+    }
+```
+
+Present the available options using AskUserQuestion:
+
+```
+Choose how to configure HUBSPOT_ACCESS_TOKEN:
+
+  1) Aden Platform (OAuth) (Recommended)
+     Secure OAuth2 flow via hive.adenhq.com
+     - Quick setup with automatic token refresh
+     - No need to manage API keys manually
+
+  2) Direct API Key
+     Enter your own API key manually
+     - Requires creating a HubSpot Private App
+     - Full control over scopes and permissions
+
+  3) Local Credential Setup (Advanced)
+     Programmatic configuration for CI/CD
+     - For automated deployments
+     - Requires manual API calls
+```
+
+### Step 4: Execute Auth Flow Based on User Choice
+
+#### Prerequisite: Ensure HIVE_CREDENTIAL_KEY Is Available
+
+Before storing any credentials, verify `HIVE_CREDENTIAL_KEY` is set (needed to encrypt/decrypt the local store). Check both the current session and shell config:
+
+```bash
+# Check current session
+printenv HIVE_CREDENTIAL_KEY > /dev/null 2>&1 && echo "session: set" || echo "session: not set"
+
+# Check shell config files
+for f in ~/.zshrc ~/.bashrc ~/.profile; do [ -f "$f" ] && grep -q 'HIVE_CREDENTIAL_KEY' "$f" && echo "$f"; done
+```
+
+- **In current session** — proceed to store credentials
+- **In shell config but NOT in current session** — run `source ~/.zshrc` (or `~/.bashrc`) first, then proceed
+- **Not set anywhere** — `EncryptedFileStorage` will auto-generate one. After storing, tell the user to persist it: `export HIVE_CREDENTIAL_KEY="{generated_key}"` in their shell profile
+
+> **⚠️ IMPORTANT: After adding `HIVE_CREDENTIAL_KEY` to the user's shell config, always display:**
+> ```
+> ⚠️  Environment variables were added to your shell config.
+>     Open a NEW TERMINAL for them to take effect outside this session.
+> ```
+
+#### Option 1: Aden Platform (OAuth)
+
+This is the recommended flow for supported integrations (HubSpot, etc.).
+
+**How Aden OAuth Works:**
+
+The ADEN_API_KEY represents a user who has already completed OAuth authorization on Aden's platform. When users sign up and connect integrations on Aden, those OAuth tokens are stored server-side. Having an ADEN_API_KEY means:
+
+1. User has an Aden account
+2. User has already authorized integrations (HubSpot, etc.) via OAuth on Aden
+3. We just need to sync those credentials down to the local credential store
+
+**4.1a. Check for ADEN_API_KEY**
+
+```python
+import os
+aden_key = os.environ.get("ADEN_API_KEY")
+```
+
+If not set, guide user to get one from Aden (this is where they do OAuth):
+
+```python
+from aden_tools.credentials import open_browser, get_aden_setup_url
+
+# Open browser to Aden - user will sign up and connect integrations there
+url = get_aden_setup_url()  # https://hive.adenhq.com
+success, msg = open_browser(url)
+
+print("Please sign in to Aden and connect your integrations (HubSpot, etc.).")
+print("Once done, copy your API key and return here.")
+```
+
+Ask user to provide the ADEN_API_KEY they received.
+
+**4.1b. Save ADEN_API_KEY to Shell Config**
+
+With user approval, persist ADEN_API_KEY to their shell config:
+
+```python
+from aden_tools.credentials import (
+    detect_shell,
+    add_env_var_to_shell_config,
+    get_shell_source_command,
+)
+
+shell_type = detect_shell()  # 'bash', 'zsh', or 'unknown'
+
+# Ask user for approval before modifying shell config
+# If approved:
+success, config_path = add_env_var_to_shell_config(
+    "ADEN_API_KEY",
+    user_provided_key,
+    comment="Aden Platform (OAuth) API key"
+)
+
+if success:
+    source_cmd = get_shell_source_command()
+    print(f"Saved to {config_path}")
+    print(f"Run: {source_cmd}")
+```
+
+> **⚠️ IMPORTANT: After adding `ADEN_API_KEY` to the user's shell config, always display:**
+> ```
+> ⚠️  Environment variables were added to your shell config.
+>     Open a NEW TERMINAL for them to take effect outside this session.
+> ```
+
+Also save to `~/.hive/configuration.json` for the framework:
+
+```python
+import json
+from pathlib import Path
+
+config_path = Path.home() / ".hive" / "configuration.json"
+config = json.loads(config_path.read_text()) if config_path.exists() else {}
+
+config["aden"] = {
+    "api_key_configured": True,
+    "api_url": "https://api.adenhq.com"
+}
+
+config_path.parent.mkdir(parents=True, exist_ok=True)
+config_path.write_text(json.dumps(config, indent=2))
+```
+
+**4.1c. Sync Credentials from Aden Server**
+
+Since the user has already authorized integrations on Aden, use the one-liner factory method:
+
+```python
+from core.framework.credentials import CredentialStore
+
+# This single call handles everything:
+# - Creates encrypted local storage at ~/.hive/credentials
+# - Configures Aden client from ADEN_API_KEY env var
+# - Syncs all credentials from Aden server automatically
+store = CredentialStore.with_aden_sync(
+    base_url="https://api.adenhq.com",
+    auto_sync=True,  # Syncs on creation
+)
+
+# Check what was synced
+synced = store.list_credentials()
+print(f"Synced credentials: {synced}")
+
+# If the required credential wasn't synced, the user hasn't authorized it on Aden yet
+if "hubspot" not in synced:
+    print("HubSpot not found in your Aden account.")
+    print("Please visit https://hive.adenhq.com to connect HubSpot, then try again.")
+```
+
+For more control over the sync process:
+
+```python
+from core.framework.credentials import CredentialStore
+from core.framework.credentials.aden import (
+    AdenCredentialClient,
+    AdenClientConfig,
+    AdenSyncProvider,
+)
+
+# Create client (API key loaded from ADEN_API_KEY env var)
+client = AdenCredentialClient(AdenClientConfig(
+    base_url="https://api.adenhq.com",
+))
+
+# Create provider and store
+provider = AdenSyncProvider(client=client)
+store = CredentialStore.with_encrypted_storage()
+
+# Manual sync
+synced_count = provider.sync_all(store)
+print(f"Synced {synced_count} credentials from Aden")
+```
+
+**4.1d. Run Health Check**
+
+```python
+from aden_tools.credentials import check_credential_health
+
+# Get the token from the store
+cred = store.get_credential("hubspot")
+token = cred.keys["access_token"].value.get_secret_value()
+
+result = check_credential_health("hubspot", token)
+if result.valid:
+    print("HubSpot credentials validated successfully!")
+else:
+    print(f"Validation failed: {result.message}")
+    # Offer to retry the OAuth flow
+```
+
+#### Option 2: Direct API Key
+
+For users who prefer manual API key management.
+
+**4.2a. Show Setup Instructions**
+
+```python
+from aden_tools.credentials import CREDENTIAL_SPECS
+
+spec = CREDENTIAL_SPECS.get("hubspot")
+if spec and spec.api_key_instructions:
+    print(spec.api_key_instructions)
+# Output:
+# To get a HubSpot Private App token:
+# 1. Go to HubSpot Settings > Integrations > Private Apps
+# 2. Click "Create a private app"
+# 3. Name your app (e.g., "Hive Agent")
+# ...
+
+if spec and spec.help_url:
+    print(f"More info: {spec.help_url}")
+```
+
+**4.2b. Collect API Key from User**
+
+Use AskUserQuestion to securely collect the API key:
+
+```
+Please provide your HubSpot access token:
+(This will be stored securely in ~/.hive/credentials)
+```
+
+**4.2c. Run Health Check Before Storing**
+
+```python
+from aden_tools.credentials import check_credential_health
+
+result = check_credential_health("hubspot", user_provided_token)
+if not result.valid:
+    print(f"Warning: {result.message}")
+    # Ask user if they want to:
+    # 1. Try a different token
+    # 2. Continue anyway (not recommended)
+```
+
+**4.2d. Store in Local Encrypted Store**
+
+```python
+from core.framework.credentials import CredentialStore, CredentialObject, CredentialKey
+from pydantic import SecretStr
+
+store = CredentialStore.with_encrypted_storage()
+
+cred = CredentialObject(
+    id="hubspot",
+    name="HubSpot Access Token",
+    keys={
+        "access_token": CredentialKey(
+            name="access_token",
+            value=SecretStr(user_provided_token),
+        )
+    },
+)
+store.save_credential(cred)
+```
+
+**4.2e. Export to Current Session**
+
+```bash
+export HUBSPOT_ACCESS_TOKEN="the-value"
+```
+
+#### Option 3: Local Credential Setup (Advanced)
+
+For programmatic/CI/CD setups.
+
+**4.3a. Show Documentation**
+
+```
+For advanced credential management, you can use the CredentialStore API directly:
+
+  from core.framework.credentials import CredentialStore, CredentialObject, CredentialKey
+  from pydantic import SecretStr
+
+  store = CredentialStore.with_encrypted_storage()
+
+  cred = CredentialObject(
+      id="hubspot",
+      name="HubSpot Access Token",
+      keys={"access_token": CredentialKey(name="access_token", value=SecretStr("..."))}
+  )
+  store.save_credential(cred)
+
+For CI/CD environments:
+  - Set HIVE_CREDENTIAL_KEY for encryption
+  - Pre-populate ~/.hive/credentials programmatically
+  - Or use environment variables directly (HUBSPOT_ACCESS_TOKEN)
+
+Documentation: See core/framework/credentials/README.md
+```
+
+### Step 5: Record Configuration Method
+
+Track which auth method was used for each credential in `~/.hive/configuration.json`:
+
+```python
+import json
+from pathlib import Path
+from datetime import datetime
+
+config_path = Path.home() / ".hive" / "configuration.json"
+config = json.loads(config_path.read_text()) if config_path.exists() else {}
+
+if "credential_methods" not in config:
+    config["credential_methods"] = {}
+
+config["credential_methods"]["hubspot"] = {
+    "method": "aden",  # or "direct" or "custom"
+    "configured_at": datetime.now().isoformat(),
+}
+
+config_path.write_text(json.dumps(config, indent=2))
+```
+
+### Step 6: Verify All Credentials
+
+Use the `verify_credentials` MCP tool to confirm everything is properly configured:
+
+```
+verify_credentials(agent_path="exports/{agent_name}")
+```
+
+The tool returns:
+
+```json
+{
+  "agent": "exports/{agent_name}",
+  "ready": true,
+  "missing_credentials": [],
+  "warnings": [],
+  "errors": []
+}
+```
+
+If `ready` is true, report success. If `missing_credentials` is non-empty, identify what failed and loop back to Step 3 for the remaining credentials.
+
+## Health Check Reference
+
+Health checks validate credentials by making lightweight API calls:
+
+| Credential      | Endpoint                                | What It Checks                    |
+| --------------- | --------------------------------------- | --------------------------------- |
+| `anthropic`     | `POST /v1/messages`                     | API key validity                  |
+| `brave_search`  | `GET /res/v1/web/search?q=test&count=1` | API key validity                  |
+| `google_search` | `GET /customsearch/v1?q=test&num=1`     | API key + CSE ID validity         |
+| `github`        | `GET /user`                             | Token validity, user identity     |
+| `hubspot`       | `GET /crm/v3/objects/contacts?limit=1`  | Bearer token validity, CRM scopes |
+| `resend`        | `GET /domains`                          | API key validity                  |
+
+```python
+from aden_tools.credentials import check_credential_health, HealthCheckResult
+
+result: HealthCheckResult = check_credential_health("hubspot", token_value)
+# result.valid: bool
+# result.message: str
+# result.details: dict (status_code, rate_limited, etc.)
+```
+
+## Encryption Key (HIVE_CREDENTIAL_KEY)
+
+The local encrypted store requires `HIVE_CREDENTIAL_KEY` to encrypt/decrypt credentials.
+
+- If the user doesn't have one, `EncryptedFileStorage` will auto-generate one and log it
+- The user MUST persist this key (e.g., in `~/.bashrc`/`~/.zshrc` or a secrets manager)
+- Without this key, stored credentials cannot be decrypted
+
+**Shell config rule:** Only TWO keys belong in shell config (`~/.zshrc`/`~/.bashrc`):
+- `HIVE_CREDENTIAL_KEY` — encryption key for the credential store
+- `ADEN_API_KEY` — Aden platform auth key (needed before the store can sync)
+
+All other API keys (Brave, Google, HubSpot, etc.) must go in the encrypted store only. **Never offer to add them to shell config.**
+
+If `HIVE_CREDENTIAL_KEY` is not set:
+
+1. Let the store generate one
+2. Tell the user to save it: `export HIVE_CREDENTIAL_KEY="{generated_key}"`
+3. Recommend adding it to `~/.bashrc` or their shell profile
+
+## Security Rules
+
+- **NEVER** log, print, or echo credential values in tool output
+- **NEVER** store credentials in plaintext files, git-tracked files, or agent configs
+- **NEVER** hardcode credentials in source code
+- **NEVER** offer to save API keys to shell config (`~/.zshrc`/`~/.bashrc`) — the **only** keys that belong in shell config are `HIVE_CREDENTIAL_KEY` and `ADEN_API_KEY`. All other credentials (Brave, Google, HubSpot, GitHub, Resend, etc.) go in the encrypted store only.
+- **ALWAYS** use `SecretStr` from Pydantic when handling credential values in Python
+- **ALWAYS** use the local encrypted store (`~/.hive/credentials`) for persistence
+- **ALWAYS** run health checks before storing credentials (when possible)
+- **ALWAYS** verify credentials were stored by re-running validation, not by reading them back
+- When modifying `~/.bashrc` or `~/.zshrc`, confirm with the user first
+
+## Credential Sources Reference
+
+All credential specs are defined in `tools/src/aden_tools/credentials/`:
+
+| File              | Category      | Credentials                                   | Aden Supported |
+| ----------------- | ------------- | --------------------------------------------- | -------------- |
+| `llm.py`          | LLM Providers | `anthropic`                                   | No             |
+| `search.py`       | Search Tools  | `brave_search`, `google_search`, `google_cse` | No             |
+| `email.py`        | Email         | `resend`                                      | No             |
+| `integrations.py` | Integrations  | `github`, `hubspot`, `google_calendar_oauth`  | No / Yes       |
+
+**Note:** Additional LLM providers (Cerebras, Groq, OpenAI) are handled by LiteLLM via environment
+variables (`CEREBRAS_API_KEY`, `GROQ_API_KEY`, `OPENAI_API_KEY`) but are not yet in CREDENTIAL_SPECS.
+Add them to `llm.py` as needed.
+
+To check what's registered:
+
+```python
+from aden_tools.credentials import CREDENTIAL_SPECS
+for name, spec in CREDENTIAL_SPECS.items():
+    print(f"{name}: aden={spec.aden_supported}, direct={spec.direct_api_key_supported}")
+```
+
+## Migration: CredentialManager → CredentialStore
+
+**CredentialManager is deprecated.** Use CredentialStore instead.
+
+| Old (Deprecated)                          | New (Recommended)                                                    |
+| ----------------------------------------- | -------------------------------------------------------------------- |
+| `CredentialManager()`                     | `CredentialStore.with_encrypted_storage()`                           |
+| `creds.get("hubspot")`                    | `store.get("hubspot")` or `store.get_key("hubspot", "access_token")` |
+| `creds.validate_for_tools(tools)`         | Use `store.is_available(cred_id)` per credential                     |
+| `creds.get_auth_options("hubspot")`       | Check `CREDENTIAL_SPECS["hubspot"].aden_supported`                   |
+| `creds.get_setup_instructions("hubspot")` | Access `CREDENTIAL_SPECS["hubspot"]` directly                        |
+
+**Why migrate?**
+
+- **CredentialStore** supports encrypted storage, multi-key credentials, template resolution, and automatic token refresh
+- **CredentialManager** only reads from environment variables and .env files (no encryption, no refresh)
+- **CredentialStoreAdapter** exists for backward compatibility during migration
+
+```python
+# Old way (deprecated)
+from aden_tools.credentials import CredentialManager
+creds = CredentialManager()
+token = creds.get("hubspot")
+
+# New way (recommended)
+from core.framework.credentials import CredentialStore
+store = CredentialStore.with_encrypted_storage()
+token = store.get("hubspot")
+
+# With Aden sync (recommended for OAuth integrations)
+store = CredentialStore.with_aden_sync()
+token = store.get_key("hubspot", "access_token")
+```
+
+## Example Session
+
+```
+User: /hive-credentials for my research-agent
+
+Agent: Let me check what credentials your research-agent needs.
+
+[Calls check_missing_credentials(agent_path="exports/research-agent")]
+→ Returns:
+  available: anthropic (encrypted_store), brave_search (encrypted_store)
+  missing: google_search (GOOGLE_API_KEY), google_cse (GOOGLE_CSE_ID)
+  ready: false
+
+Agent: 2 of 4 required credentials are already configured. Only Google Custom
+Search needs setup (2 values).
+
+--- Setting up Google Custom Search (google_search + google_cse) ---
+
+This requires two values that work together.
+
+[Checks HIVE_CREDENTIAL_KEY before storing]
+$ printenv HIVE_CREDENTIAL_KEY > /dev/null 2>&1 && echo "set" || echo "not set"
+set
+
+First, the Google API Key:
+1. Go to https://console.cloud.google.com/apis/credentials
+2. Create a new project (or select an existing one)
+3. Enable the "Custom Search API" from the API Library
+4. Go to Credentials > Create Credentials > API Key
+5. Copy the generated API key
+
+[AskUserQuestion: "Please provide your Google API key:"]
+[User provides key]
+
+Now, the Custom Search Engine ID:
+1. Go to https://programmablesearchengine.google.com/controlpanel/all
+2. Click "Add" to create a new search engine
+3. Under "What to search", select "Search the entire web"
+4. Give your search engine a name
+5. Click "Create"
+6. Copy the Search Engine ID (cx value)
+
+[AskUserQuestion: "Please provide your Google CSE ID:"]
+[User provides ID]
+
+[Runs health check with both values - GET /customsearch/v1?q=test&num=1 → 200 OK]
+[Stores both in local encrypted store, exports to env]
+
+✓ Google Custom Search credentials valid
+
+[Calls verify_credentials(agent_path="exports/research-agent")]
+→ Returns: ready: true, missing_credentials: []
+
+All credentials are now configured:
+  ✓ anthropic (ANTHROPIC_API_KEY) — already in encrypted store
+  ✓ brave_search (BRAVE_SEARCH_API_KEY) — already in encrypted store
+  ✓ google_search (GOOGLE_API_KEY) — stored in encrypted store
+  ✓ google_cse (GOOGLE_CSE_ID) — stored in encrypted store
+
+┌─────────────────────────────────────────────────────────────────────────────┐
+│                      ✅ CREDENTIALS CONFIGURED                              │
+├─────────────────────────────────────────────────────────────────────────────┤
+│                                                                             │
+│     OPEN A NEW TERMINAL before running commands below.                      │
+│     Environment variables were saved to your shell config but               │
+│     only take effect in new terminal sessions.                              │
+│                                                                             │
+│  NEXT STEPS:                                                                │
+│                                                                             │
+│  1. RUN YOUR AGENT:                                                         │
+│                                                                             │
+│     hive tui                                                                │
+│                                                                             │
+│  2. IF YOU ENCOUNTER ISSUES, USE THE DEBUGGER:                              │
+│                                                                             │
+│     /hive-debugger                                                          │
+│                                                                             │
+│     The debugger analyzes runtime logs, identifies retry loops, tool        │
+│     failures, stalled execution, and provides actionable fix suggestions.   │
+│                                                                             │
+└─────────────────────────────────────────────────────────────────────────────┘
+```

.claude/skills/hive-patterns/SKILL.md

@@ -0,0 +1,385 @@
+---
+name: hive-patterns
+description: Best practices, patterns, and examples for building goal-driven agents. Includes client-facing interaction, feedback edges, judge patterns, fan-out/fan-in, context management, and anti-patterns.
+license: Apache-2.0
+metadata:
+  author: hive
+  version: "2.0"
+  type: reference
+  part_of: hive
+---
+
+# Building Agents - Patterns & Best Practices
+
+Design patterns, examples, and best practices for building robust goal-driven agents.
+
+**Prerequisites:** Complete agent structure using `hive-create`.
+
+## Practical Example: Hybrid Workflow
+
+How to build a node using both direct file writes and optional MCP validation:
+
+```python
+# 1. WRITE TO FILE FIRST (Primary - makes it visible)
+node_code = '''
+search_node = NodeSpec(
+    id="search-web",
+    node_type="event_loop",
+    input_keys=["query"],
+    output_keys=["search_results"],
+    system_prompt="Search the web for: {query}. Use web_search, then call set_output to store results.",
+    tools=["web_search"],
+)
+'''
+
+Edit(
+    file_path="exports/research_agent/nodes/__init__.py",
+    old_string="# Nodes will be added here",
+    new_string=node_code
+)
+
+# 2. OPTIONALLY VALIDATE WITH MCP (Secondary - bookkeeping)
+validation = mcp__agent-builder__test_node(
+    node_id="search-web",
+    test_input='{"query": "python tutorials"}',
+    mock_llm_response='{"search_results": [...mock results...]}'
+)
+```
+
+**User experience:**
+
+- Immediately sees node in their editor (from step 1)
+- Gets validation feedback (from step 2)
+- Can edit the file directly if needed
+
+## Multi-Turn Interaction Patterns
+
+For agents needing multi-turn conversations with users, use `client_facing=True` on event_loop nodes.
+
+### Client-Facing Nodes
+
+A client-facing node streams LLM output to the user and blocks for user input between conversational turns. This replaces the old pause/resume pattern.
+
+```python
+# Client-facing node with STEP 1/STEP 2 prompt pattern
+intake_node = NodeSpec(
+    id="intake",
+    name="Intake",
+    description="Gather requirements from the user",
+    node_type="event_loop",
+    client_facing=True,
+    input_keys=["topic"],
+    output_keys=["research_brief"],
+    system_prompt="""\
+You are an intake specialist.
+
+**STEP 1 — Read and respond (text only, NO tool calls):**
+1. Read the topic provided
+2. If it's vague, ask 1-2 clarifying questions
+3. If it's clear, confirm your understanding
+
+**STEP 2 — After the user confirms, call set_output:**
+- set_output("research_brief", "Clear description of what to research")
+""",
+)
+
+# Internal node runs without user interaction
+research_node = NodeSpec(
+    id="research",
+    name="Research",
+    description="Search and analyze sources",
+    node_type="event_loop",
+    input_keys=["research_brief"],
+    output_keys=["findings", "sources"],
+    system_prompt="Research the topic using web_search and web_scrape...",
+    tools=["web_search", "web_scrape", "load_data", "save_data"],
+)
+```
+
+**How it works:**
+
+- Client-facing nodes stream LLM text to the user and block for input after each response
+- User input is injected via `node.inject_event(text)`
+- When the LLM calls `set_output` to produce structured outputs, the judge evaluates and ACCEPTs
+- Internal nodes (non-client-facing) run their entire loop without blocking
+- `set_output` is a synthetic tool — a turn with only `set_output` calls (no real tools) triggers user input blocking
+
+**STEP 1/STEP 2 pattern:** Always structure client-facing prompts with explicit phases. STEP 1 is text-only conversation. STEP 2 calls `set_output` after user confirmation. This prevents the LLM from calling `set_output` prematurely before the user responds.
+
+### When to Use client_facing
+
+| Scenario                            | client_facing | Why                    |
+| ----------------------------------- | :-----------: | ---------------------- |
+| Gathering user requirements         |      Yes      | Need user input        |
+| Human review/approval checkpoint    |      Yes      | Need human decision    |
+| Data processing (scanning, scoring) |      No       | Runs autonomously      |
+| Report generation                   |      No       | No user input needed   |
+| Final confirmation before action    |      Yes      | Need explicit approval |
+
+> **Legacy Note:** The `pause_nodes` / `entry_points` pattern still works for backward compatibility but `client_facing=True` is preferred for new agents.
+
+## Edge-Based Routing and Feedback Loops
+
+### Conditional Edge Routing
+
+Multiple conditional edges from the same source replace the old `router` node type. Each edge checks a condition on the node's output.
+
+```python
+# Node with mutually exclusive outputs
+review_node = NodeSpec(
+    id="review",
+    name="Review",
+    node_type="event_loop",
+    client_facing=True,
+    output_keys=["approved_contacts", "redo_extraction"],
+    nullable_output_keys=["approved_contacts", "redo_extraction"],
+    max_node_visits=3,
+    system_prompt="Present the contact list to the operator. If they approve, call set_output('approved_contacts', ...). If they want changes, call set_output('redo_extraction', 'true').",
+)
+
+# Forward edge (positive priority, evaluated first)
+EdgeSpec(
+    id="review-to-campaign",
+    source="review",
+    target="campaign-builder",
+    condition=EdgeCondition.CONDITIONAL,
+    condition_expr="output.get('approved_contacts') is not None",
+    priority=1,
+)
+
+# Feedback edge (negative priority, evaluated after forward edges)
+EdgeSpec(
+    id="review-feedback",
+    source="review",
+    target="extractor",
+    condition=EdgeCondition.CONDITIONAL,
+    condition_expr="output.get('redo_extraction') is not None",
+    priority=-1,
+)
+```
+
+**Key concepts:**
+
+- `nullable_output_keys`: Lists output keys that may remain unset. The node sets exactly one of the mutually exclusive keys per execution.
+- `max_node_visits`: Must be >1 on the feedback target (extractor) so it can re-execute. Default is 1.
+- `priority`: Positive = forward edge (evaluated first). Negative = feedback edge. The executor tries forward edges first; if none match, falls back to feedback edges.
+
+### Routing Decision Table
+
+| Pattern                | Old Approach            | New Approach                                  |
+| ---------------------- | ----------------------- | --------------------------------------------- |
+| Conditional branching  | `router` node           | Conditional edges with `condition_expr`       |
+| Binary approve/reject  | `pause_nodes` + resume  | `client_facing=True` + `nullable_output_keys` |
+| Loop-back on rejection | Manual entry_points     | Feedback edge with `priority=-1`              |
+| Multi-way routing      | Router with routes dict | Multiple conditional edges with priorities    |
+
+## Judge Patterns
+
+**Core Principle: The judge is the SOLE mechanism for acceptance decisions.** Never add ad-hoc framework gating to compensate for LLM behavior. If the LLM calls `set_output` prematurely, fix the system prompt or use a custom judge. Anti-patterns to avoid:
+
+- Output rollback logic
+- `_user_has_responded` flags
+- Premature set_output rejection
+- Interaction protocol injection into system prompts
+
+Judges control when an event_loop node's loop exits. Choose based on validation needs.
+
+### Implicit Judge (Default)
+
+When no judge is configured, the implicit judge ACCEPTs when:
+
+- The LLM finishes its response with no tool calls
+- All required output keys have been set via `set_output`
+
+Best for simple nodes where "all outputs set" is sufficient validation.
+
+### SchemaJudge
+
+Validates outputs against a Pydantic model. Use when you need structural validation.
+
+```python
+from pydantic import BaseModel
+
+class ScannerOutput(BaseModel):
+    github_users: list[dict]  # Must be a list of user objects
+
+class SchemaJudge:
+    def __init__(self, output_model: type[BaseModel]):
+        self._model = output_model
+
+    async def evaluate(self, context: dict) -> JudgeVerdict:
+        missing = context.get("missing_keys", [])
+        if missing:
+            return JudgeVerdict(
+                action="RETRY",
+                feedback=f"Missing output keys: {missing}. Use set_output to provide them.",
+            )
+        try:
+            self._model.model_validate(context["output_accumulator"])
+            return JudgeVerdict(action="ACCEPT")
+        except ValidationError as e:
+            return JudgeVerdict(action="RETRY", feedback=str(e))
+```
+
+### When to Use Which Judge
+
+| Judge           | Use When                              | Example                |
+| --------------- | ------------------------------------- | ---------------------- |
+| Implicit (None) | Output keys are sufficient validation | Simple data extraction |
+| SchemaJudge     | Need structural validation of outputs | API response parsing   |
+| Custom          | Domain-specific validation logic      | Score must be 0.0-1.0  |
+
+## Fan-Out / Fan-In (Parallel Execution)
+
+Multiple ON_SUCCESS edges from the same source trigger parallel execution. All branches run concurrently via `asyncio.gather()`.
+
+```python
+# Scanner fans out to Profiler and Scorer in parallel
+EdgeSpec(id="scanner-to-profiler", source="scanner", target="profiler",
+         condition=EdgeCondition.ON_SUCCESS)
+EdgeSpec(id="scanner-to-scorer", source="scanner", target="scorer",
+         condition=EdgeCondition.ON_SUCCESS)
+
+# Both fan in to Extractor
+EdgeSpec(id="profiler-to-extractor", source="profiler", target="extractor",
+         condition=EdgeCondition.ON_SUCCESS)
+EdgeSpec(id="scorer-to-extractor", source="scorer", target="extractor",
+         condition=EdgeCondition.ON_SUCCESS)
+```
+
+**Requirements:**
+
+- Parallel event_loop nodes must have **disjoint output_keys** (no key written by both)
+- Only one parallel branch may contain a `client_facing` node
+- Fan-in node receives outputs from all completed branches in shared memory
+
+## Context Management Patterns
+
+### Tiered Compaction
+
+EventLoopNode automatically manages context window usage with tiered compaction:
+
+1. **Pruning** — Old tool results replaced with compact placeholders (zero-cost, no LLM call)
+2. **Normal compaction** — LLM summarizes older messages
+3. **Aggressive compaction** — Keeps only recent messages + summary
+4. **Emergency** — Hard reset with tool history preservation
+
+### Spillover Pattern
+
+The framework automatically truncates large tool results and saves full content to a spillover directory. The LLM receives a truncation message with instructions to use `load_data` to read the full result.
+
+For explicit data management, use the data tools (real MCP tools, not synthetic):
+
+```python
+# save_data, load_data, list_data_files, serve_file_to_user are real MCP tools
+# data_dir is auto-injected by the framework — the LLM never sees it
+
+# Saving large results
+save_data(filename="sources.json", data=large_json_string)
+
+# Reading with pagination (line-based offset/limit)
+load_data(filename="sources.json", offset=0, limit=50)
+
+# Listing available files
+list_data_files()
+
+# Serving a file to the user as a clickable link
+serve_file_to_user(filename="report.html", label="Research Report")
+```
+
+Add data tools to nodes that handle large tool results:
+
+```python
+research_node = NodeSpec(
+    ...
+    tools=["web_search", "web_scrape", "load_data", "save_data", "list_data_files"],
+)
+```
+
+`data_dir` is a framework context parameter — auto-injected at call time. `GraphExecutor.execute()` sets it per-execution via `ToolRegistry.set_execution_context(data_dir=...)` (using `contextvars` for concurrency safety), ensuring it matches the session-scoped spillover directory.
+
+## Anti-Patterns
+
+### What NOT to Do
+
+- **Don't rely on `export_graph`** — Write files immediately, not at end
+- **Don't hide code in session** — Write to files as components are approved
+- **Don't wait to write files** — Agent visible from first step
+- **Don't batch everything** — Write incrementally, one component at a time
+- **Don't create too many thin nodes** — Prefer fewer, richer nodes (see below)
+- **Don't add framework gating for LLM behavior** — Fix prompts or use judges instead
+
+### Fewer, Richer Nodes
+
+A common mistake is splitting work into too many small single-purpose nodes. Each node boundary requires serializing outputs, losing in-context information, and adding edge complexity.
+
+| Bad (8 thin nodes)  | Good (4 rich nodes)                 |
+| ------------------- | ----------------------------------- |
+| parse-query         | intake (client-facing)              |
+| search-sources      | research (search + fetch + analyze) |
+| fetch-content       | review (client-facing)              |
+| evaluate-sources    | report (write + deliver)            |
+| synthesize-findings |                                     |
+| write-report        |                                     |
+| quality-check       |                                     |
+| save-report         |                                     |
+
+**Why fewer nodes are better:**
+
+- The LLM retains full context of its work within a single node
+- A research node that searches, fetches, and analyzes keeps all source material in its conversation history
+- Fewer edges means simpler graph and fewer failure points
+- Data tools (`save_data`/`load_data`) handle context window limits within a single node
+
+### MCP Tools - Correct Usage
+
+**MCP tools OK for:**
+
+- `test_node` — Validate node configuration with mock inputs
+- `validate_graph` — Check graph structure
+- `configure_loop` — Set event loop parameters
+- `create_session` — Track session state for bookkeeping
+
+**Just don't:** Use MCP as the primary construction method or rely on export_graph
+
+## Error Handling Patterns
+
+### Graceful Failure with Fallback
+
+```python
+edges = [
+    # Success path
+    EdgeSpec(id="api-success", source="api-call", target="process-results",
+             condition=EdgeCondition.ON_SUCCESS),
+    # Fallback on failure
+    EdgeSpec(id="api-to-fallback", source="api-call", target="fallback-cache",
+             condition=EdgeCondition.ON_FAILURE, priority=1),
+    # Report if fallback also fails
+    EdgeSpec(id="fallback-to-error", source="fallback-cache", target="report-error",
+             condition=EdgeCondition.ON_FAILURE, priority=1),
+]
+```
+
+## Handoff to Testing
+
+When agent is complete, transition to testing phase:
+
+### Pre-Testing Checklist
+
+- [ ] Agent structure validates: `uv run python -m agent_name validate`
+- [ ] All nodes defined in nodes/**init**.py
+- [ ] All edges connect valid nodes with correct priorities
+- [ ] Feedback edge targets have `max_node_visits > 1`
+- [ ] Client-facing nodes have meaningful system prompts
+- [ ] Agent can be imported: `from exports.agent_name import default_agent`
+
+## Related Skills
+
+- **hive-concepts** — Fundamental concepts (node types, edges, event loop architecture)
+- **hive-create** — Step-by-step building process
+- **hive-test** — Test and validate agents
+- **hive** — Complete workflow orchestrator
+
+---
+
+**Remember: Agent is actively constructed, visible the whole time. No hidden state. No surprise exports. Just transparent, incremental file building.**

.claude/skills/hive-test/SKILL.md

@@ -0,0 +1,940 @@
+---
+name: hive-test
+description: Iterative agent testing with session recovery. Execute, analyze, fix, resume from checkpoints. Use when testing an agent, debugging test failures, or verifying fixes without re-running from scratch.
+---
+
+# Agent Testing
+
+Test agents iteratively: execute, analyze failures, fix, resume from checkpoint, repeat.
+
+## When to Use
+
+- Testing a newly built agent against its goal
+- Debugging a failing agent iteratively
+- Verifying fixes without re-running expensive early nodes
+- Running final regression tests before deployment
+
+## Prerequisites
+
+1. Agent package at `exports/{agent_name}/` (built with `/hive-create`)
+2. Credentials configured (`/hive-credentials`)
+3. `ANTHROPIC_API_KEY` set (or appropriate LLM provider key)
+
+**Path distinction** (critical — don't confuse these):
+- `exports/{agent_name}/` — agent source code (edit here)
+- `~/.hive/agents/{agent_name}/` — runtime data: sessions, checkpoints, logs (read here)
+
+---
+
+## The Iterative Test Loop
+
+This is the core workflow. Don't re-run the entire agent when a late node fails — analyze, fix, and resume from the last clean checkpoint.
+
+```
+┌──────────────────────────────────────┐
+│ PHASE 1: Generate Test Scenarios     │
+│ Goal → synthetic test inputs + tests │
+└──────────────┬───────────────────────┘
+               ↓
+┌──────────────────────────────────────┐
+│ PHASE 2: Execute                     │◄────────────────┐
+│ Run agent (CLI or pytest)            │                 │
+└──────────────┬───────────────────────┘                 │
+               ↓                                         │
+          Pass? ──yes──► PHASE 6: Final Verification     │
+               │                                         │
+               no                                        │
+               ↓                                         │
+┌──────────────────────────────────────┐                 │
+│ PHASE 3: Analyze                     │                 │
+│ Session + runtime logs + checkpoints │                 │
+└──────────────┬───────────────────────┘                 │
+               ↓                                         │
+┌──────────────────────────────────────┐                 │
+│ PHASE 4: Fix                         │                 │
+│ Prompt / code / graph / goal         │                 │
+└──────────────┬───────────────────────┘                 │
+               ↓                                         │
+┌──────────────────────────────────────┐                 │
+│ PHASE 5: Recover & Resume            │─────────────────┘
+│ Checkpoint resume OR fresh re-run    │
+└──────────────────────────────────────┘
+```
+
+---
+
+### Phase 1: Generate Test Scenarios
+
+Create synthetic tests from the agent's goal, constraints, and success criteria.
+
+#### Step 1a: Read the goal
+
+```python
+# Read goal from agent.py
+Read(file_path="exports/{agent_name}/agent.py")
+# Extract the Goal definition and convert to JSON string
+```
+
+#### Step 1b: Get test guidelines
+
+```python
+# Get constraint test guidelines
+generate_constraint_tests(
+    goal_id="your-goal-id",
+    goal_json='{"id": "...", "constraints": [...]}',
+    agent_path="exports/{agent_name}"
+)
+
+# Get success criteria test guidelines
+generate_success_tests(
+    goal_id="your-goal-id",
+    goal_json='{"id": "...", "success_criteria": [...]}',
+    node_names="intake,research,review,report",
+    tool_names="web_search,web_scrape",
+    agent_path="exports/{agent_name}"
+)
+```
+
+These return `file_header`, `test_template`, `constraints_formatted`/`success_criteria_formatted`, and `test_guidelines`. They do NOT generate test code — you write the tests.
+
+#### Step 1c: Write tests
+
+```python
+Write(
+    file_path=result["output_file"],
+    content=result["file_header"] + "\n\n" + your_test_code
+)
+```
+
+#### Test writing rules
+
+- Every test MUST be `async` with `@pytest.mark.asyncio`
+- Every test MUST accept `runner, auto_responder, mock_mode` fixtures
+- Use `await auto_responder.start()` before running, `await auto_responder.stop()` in `finally`
+- Use `await runner.run(input_dict)` — this goes through AgentRunner → AgentRuntime → ExecutionStream
+- Access output via `result.output.get("key")` — NEVER `result.output["key"]`
+- `result.success=True` means no exception, NOT goal achieved — always check output
+- Write 8-15 tests total, not 30+
+- Each real test costs ~3 seconds + LLM tokens
+- NEVER use `default_agent.run()` — it bypasses the runtime (no sessions, no logs, client-facing nodes hang)
+
+#### Step 1d: Check existing tests
+
+Before generating, check if tests already exist:
+
+```python
+list_tests(
+    goal_id="your-goal-id",
+    agent_path="exports/{agent_name}"
+)
+```
+
+---
+
+### Phase 2: Execute
+
+Two execution paths, use the right one for your situation.
+
+#### Iterative debugging (for complex agents)
+
+Run the agent via CLI. This creates sessions with checkpoints at `~/.hive/agents/{agent_name}/sessions/`:
+
+```bash
+uv run hive run exports/{agent_name} --input '{"query": "test topic"}'
+```
+
+Sessions and checkpoints are saved automatically.
+
+**Client-facing nodes**: Agents with `client_facing=True` nodes (interactive conversation) work in headless mode when run from a real terminal — the agent streams output to stdout and reads user input from stdin via a `>>> ` prompt. In non-interactive shells (like Claude Code's Bash tool), client-facing nodes will hang because there is no stdin. For testing interactive agents from Claude Code, use `run_tests` with mock mode or have the user run the agent manually in their terminal.
+
+#### Automated regression (for CI or final verification)
+
+Use the `run_tests` MCP tool to run all pytest tests:
+
+```python
+run_tests(
+    goal_id="your-goal-id",
+    agent_path="exports/{agent_name}"
+)
+```
+
+Returns structured results:
+```json
+{
+  "overall_passed": false,
+  "summary": {"total": 12, "passed": 10, "failed": 2, "pass_rate": "83.3%"},
+  "test_results": [{"test_name": "test_success_source_diversity", "status": "failed"}],
+  "failures": [{"test_name": "test_success_source_diversity", "details": "..."}]
+}
+```
+
+**Options:**
+```python
+# Run only constraint tests
+run_tests(goal_id, agent_path, test_types='["constraint"]')
+
+# Stop on first failure
+run_tests(goal_id, agent_path, fail_fast=True)
+
+# Parallel execution
+run_tests(goal_id, agent_path, parallel=4)
+```
+
+**Note:** `run_tests` uses `AgentRunner` with `tmp_path` storage, so sessions are isolated per test run. For checkpoint-based recovery with persistent sessions, use CLI execution. Use `run_tests` for quick regression checks and final verification.
+
+---
+
+### Phase 3: Analyze Failures
+
+When a test fails, drill down systematically. Don't guess — use the tools.
+
+#### Step 3a: Get error category
+
+```python
+debug_test(
+    goal_id="your-goal-id",
+    test_name="test_success_source_diversity",
+    agent_path="exports/{agent_name}"
+)
+```
+
+Returns error category (`IMPLEMENTATION_ERROR`, `ASSERTION_FAILURE`, `TIMEOUT`, `IMPORT_ERROR`, `API_ERROR`) plus full traceback and suggestions.
+
+#### Step 3b: Find the failed session
+
+```python
+list_agent_sessions(
+    agent_work_dir="~/.hive/agents/{agent_name}",
+    status="failed",
+    limit=5
+)
+```
+
+Returns session list with IDs, timestamps, current_node (where it failed), execution_quality.
+
+#### Step 3c: Inspect session state
+
+```python
+get_agent_session_state(
+    agent_work_dir="~/.hive/agents/{agent_name}",
+    session_id="session_20260209_143022_abc12345"
+)
+```
+
+Returns execution path, which node was current, step count, timestamps — but excludes memory values (to avoid context bloat). Shows `memory_keys` and `memory_size` instead.
+
+#### Step 3d: Examine runtime logs (L2/L3)
+
+```python
+# L2: Per-node success/failure, retry counts
+query_runtime_log_details(
+    agent_work_dir="~/.hive/agents/{agent_name}",
+    run_id="session_20260209_143022_abc12345",
+    needs_attention_only=True
+)
+
+# L3: Exact LLM responses, tool call inputs/outputs
+query_runtime_log_raw(
+    agent_work_dir="~/.hive/agents/{agent_name}",
+    run_id="session_20260209_143022_abc12345",
+    node_id="research"
+)
+```
+
+#### Step 3e: Inspect memory data
+
+```python
+# See what data a node actually produced
+get_agent_session_memory(
+    agent_work_dir="~/.hive/agents/{agent_name}",
+    session_id="session_20260209_143022_abc12345",
+    key="research_results"
+)
+```
+
+#### Step 3f: Find recovery points
+
+```python
+list_agent_checkpoints(
+    agent_work_dir="~/.hive/agents/{agent_name}",
+    session_id="session_20260209_143022_abc12345",
+    is_clean="true"
+)
+```
+
+Returns checkpoint summaries with IDs, types (`node_start`, `node_complete`), which node, and `is_clean` flag. Clean checkpoints are safe resume points.
+
+#### Step 3g: Compare checkpoints (optional)
+
+To understand what changed between two points in execution:
+
+```python
+compare_agent_checkpoints(
+    agent_work_dir="~/.hive/agents/{agent_name}",
+    session_id="session_20260209_143022_abc12345",
+    checkpoint_id_before="cp_node_complete_research_143030",
+    checkpoint_id_after="cp_node_complete_review_143115"
+)
+```
+
+Returns memory diff (added/removed/changed keys) and execution path diff.
+
+---
+
+### Phase 4: Fix Based on Root Cause
+
+Use the analysis from Phase 3 to determine what to fix and where.
+
+| Root Cause | What to Fix | Where to Edit |
+|------------|------------|---------------|
+| **Prompt issue** — LLM produces wrong output format, misses instructions | Node `system_prompt` | `exports/{agent}/nodes/__init__.py` |
+| **Code bug** — TypeError, KeyError, logic error in Python | Agent code | `exports/{agent}/agent.py`, `nodes/__init__.py` |
+| **Graph issue** — wrong routing, missing edge, bad condition_expr | Edges, node config | `exports/{agent}/agent.py` |
+| **Tool issue** — MCP tool fails, wrong config, missing credential | Tool config | `exports/{agent}/mcp_servers.json`, `/hive-credentials` |
+| **Goal issue** — success criteria too strict/vague, wrong constraints | Goal definition | `exports/{agent}/agent.py` (goal section) |
+| **Test issue** — test expectations don't match actual agent behavior | Test code | `exports/{agent}/tests/test_*.py` |
+
+#### Fix strategies by error category
+
+**IMPLEMENTATION_ERROR** (TypeError, AttributeError, KeyError):
+```python
+# Read the failing code
+Read(file_path="exports/{agent_name}/nodes/__init__.py")
+
+# Fix the bug
+Edit(
+    file_path="exports/{agent_name}/nodes/__init__.py",
+    old_string="results.get('videos')",
+    new_string="(results or {}).get('videos', [])"
+)
+```
+
+**ASSERTION_FAILURE** (test assertions fail but agent ran successfully):
+- Check if the agent's output is actually wrong → fix the prompt
+- Check if the test's expectations are unrealistic → fix the test
+- Use `get_agent_session_memory` to see what the agent actually produced
+
+**TIMEOUT / STALL** (agent runs too long):
+- Check `node_visit_counts` for feedback loops hitting max_node_visits
+- Check L3 logs for tool calls that hang
+- Reduce `max_iterations` in loop_config or fix the prompt to converge faster
+
+**API_ERROR** (connection, rate limit, auth):
+- Verify credentials with `/hive-credentials`
+- Check MCP server configuration
+
+---
+
+### Phase 5: Recover & Resume
+
+After fixing the agent, decide whether to resume or re-run.
+
+#### When to resume from checkpoint
+
+Resume when ALL of these are true:
+- The fix is to a node that comes AFTER existing clean checkpoints
+- Clean checkpoints exist (from a CLI execution with checkpointing)
+- The early nodes are expensive (web scraping, API calls, long LLM chains)
+
+```bash
+# Resume from the last clean checkpoint before the failing node
+uv run hive run exports/{agent_name} \
+  --resume-session session_20260209_143022_abc12345 \
+  --checkpoint cp_node_complete_research_143030
+```
+
+This skips all nodes before the checkpoint and only re-runs the fixed node onward.
+
+#### When to re-run from scratch
+
+Re-run when ANY of these are true:
+- The fix is to the entry node or an early node
+- No checkpoints exist (e.g., agent was run via `run_tests`)
+- The agent is fast (2-3 nodes, completes in seconds)
+- You changed the graph structure (added/removed nodes/edges)
+
+```bash
+uv run hive run exports/{agent_name} --input '{"query": "test topic"}'
+```
+
+#### Inspecting a checkpoint before resuming
+
+```python
+get_agent_checkpoint(
+    agent_work_dir="~/.hive/agents/{agent_name}",
+    session_id="session_20260209_143022_abc12345",
+    checkpoint_id="cp_node_complete_research_143030"
+)
+```
+
+Returns the full checkpoint: shared_memory snapshot, execution_path, current_node, next_node, is_clean.
+
+#### Loop back to Phase 2
+
+After resuming or re-running, check if the fix worked. If not, go back to Phase 3.
+
+---
+
+### Phase 6: Final Verification
+
+Once the iterative fix loop converges (the agent produces correct output), run the full automated test suite:
+
+```python
+run_tests(
+    goal_id="your-goal-id",
+    agent_path="exports/{agent_name}"
+)
+```
+
+All tests should pass. If not, repeat the loop for remaining failures.
+
+---
+
+## Credential Requirements
+
+**CRITICAL: Testing requires ALL credentials the agent depends on.** This includes both the LLM API key AND any tool-specific credentials (HubSpot, Brave Search, etc.).
+
+### Prerequisites
+
+Before running agent tests, you MUST collect ALL required credentials from the user.
+
+**Step 1: LLM API Key (always required)**
+```bash
+export ANTHROPIC_API_KEY="your-key-here"
+```
+
+**Step 2: Tool-specific credentials (depends on agent's tools)**
+
+Inspect the agent's `mcp_servers.json` and tool configuration to determine which tools the agent uses, then check for all required credentials:
+
+```python
+from aden_tools.credentials import CredentialManager, CREDENTIAL_SPECS
+
+creds = CredentialManager()
+
+# Determine which tools the agent uses (from agent.json or mcp_servers.json)
+agent_tools = [...]  # e.g., ["hubspot_search_contacts", "web_search", ...]
+
+# Find all missing credentials for those tools
+missing = creds.get_missing_for_tools(agent_tools)
+```
+
+Common tool credentials:
+| Tool | Env Var | Help URL |
+|------|---------|----------|
+| HubSpot CRM | `HUBSPOT_ACCESS_TOKEN` | https://developers.hubspot.com/docs/api/private-apps |
+| Brave Search | `BRAVE_SEARCH_API_KEY` | https://brave.com/search/api/ |
+| Google Search | `GOOGLE_SEARCH_API_KEY` + `GOOGLE_SEARCH_CX` | https://developers.google.com/custom-search |
+
+**Why ALL credentials are required:**
+- Tests need to execute the agent's LLM nodes to validate behavior
+- Tools with missing credentials will return error dicts instead of real data
+- Mock mode bypasses everything, providing no confidence in real-world performance
+
+### Mock Mode Limitations
+
+Mock mode (`--mock` flag or `MOCK_MODE=1`) is **ONLY for structure validation**:
+
+- Validates graph structure (nodes, edges, connections)
+- Validates that `AgentRunner.load()` succeeds and the agent is importable
+- Does NOT execute event_loop agents — MockLLMProvider never calls `set_output`, so event_loop nodes loop forever
+- Does NOT test LLM reasoning, content quality, or constraint validation
+- Does NOT test real API integrations or tool use
+
+**Bottom line:** If you're testing whether an agent achieves its goal, you MUST use real credentials.
+
+### Enforcing Credentials in Tests
+
+When writing tests, **ALWAYS include credential checks**:
+
+```python
+import os
+import pytest
+from aden_tools.credentials import CredentialManager
+
+pytestmark = pytest.mark.skipif(
+    not CredentialManager().is_available("anthropic") and not os.environ.get("MOCK_MODE"),
+    reason="API key required for real testing. Set ANTHROPIC_API_KEY or use MOCK_MODE=1."
+)
+
+
+@pytest.fixture(scope="session", autouse=True)
+def check_credentials():
+    """Ensure ALL required credentials are set for real testing."""
+    creds = CredentialManager()
+    mock_mode = os.environ.get("MOCK_MODE")
+
+    if not creds.is_available("anthropic"):
+        if mock_mode:
+            print("\nRunning in MOCK MODE - structure validation only")
+        else:
+            pytest.fail(
+                "\nANTHROPIC_API_KEY not set!\n"
+                "Set API key: export ANTHROPIC_API_KEY='your-key-here'\n"
+                "Or run structure validation: MOCK_MODE=1 pytest exports/{agent}/tests/"
+            )
+
+    if not mock_mode:
+        agent_tools = []  # Update per agent
+        missing = creds.get_missing_for_tools(agent_tools)
+        if missing:
+            lines = ["\nMissing tool credentials!"]
+            for name in missing:
+                spec = creds.specs.get(name)
+                if spec:
+                    lines.append(f"  {spec.env_var} - {spec.description}")
+            pytest.fail("\n".join(lines))
+```
+
+### User Communication
+
+When the user asks to test an agent, **ALWAYS check for ALL credentials first**:
+
+1. **Identify the agent's tools** from `mcp_servers.json`
+2. **Check ALL required credentials** using `CredentialManager`
+3. **Ask the user to provide any missing credentials** before proceeding
+4. Collect ALL missing credentials in a single prompt — not one at a time
+
+---
+
+## Safe Test Patterns
+
+### OutputCleaner
+
+The framework automatically validates and cleans node outputs using a fast LLM at edge traversal time. Tests should still use safe patterns because OutputCleaner may not catch all issues.
+
+### Safe Access (REQUIRED)
+
+```python
+# UNSAFE - will crash on missing keys
+approval = result.output["approval_decision"]
+category = result.output["analysis"]["category"]
+
+# SAFE - use .get() with defaults
+output = result.output or {}
+approval = output.get("approval_decision", "UNKNOWN")
+
+# SAFE - type check before operations
+analysis = output.get("analysis", {})
+if isinstance(analysis, dict):
+    category = analysis.get("category", "unknown")
+
+# SAFE - handle JSON parsing trap (LLM response as string)
+import json
+recommendation = output.get("recommendation", "{}")
+if isinstance(recommendation, str):
+    try:
+        parsed = json.loads(recommendation)
+        if isinstance(parsed, dict):
+            approval = parsed.get("approval_decision", "UNKNOWN")
+    except json.JSONDecodeError:
+        approval = "UNKNOWN"
+elif isinstance(recommendation, dict):
+    approval = recommendation.get("approval_decision", "UNKNOWN")
+
+# SAFE - type check before iteration
+items = output.get("items", [])
+if isinstance(items, list):
+    for item in items:
+        ...
+```
+
+### Helper Functions for conftest.py
+
+```python
+import json
+import re
+
+def _parse_json_from_output(result, key):
+    """Parse JSON from agent output (framework may store full LLM response as string)."""
+    response_text = result.output.get(key, "")
+    json_text = re.sub(r'```json\s*|\s*```', '', response_text).strip()
+    try:
+        return json.loads(json_text)
+    except (json.JSONDecodeError, AttributeError, TypeError):
+        return result.output.get(key)
+
+def safe_get_nested(result, key_path, default=None):
+    """Safely get nested value from result.output."""
+    output = result.output or {}
+    current = output
+    for key in key_path:
+        if isinstance(current, dict):
+            current = current.get(key)
+        elif isinstance(current, str):
+            try:
+                json_text = re.sub(r'```json\s*|\s*```', '', current).strip()
+                parsed = json.loads(json_text)
+                if isinstance(parsed, dict):
+                    current = parsed.get(key)
+                else:
+                    return default
+            except json.JSONDecodeError:
+                return default
+        else:
+            return default
+    return current if current is not None else default
+
+# Make available in tests
+pytest.parse_json_from_output = _parse_json_from_output
+pytest.safe_get_nested = safe_get_nested
+```
+
+### ExecutionResult Fields
+
+**`result.success=True` means NO exception, NOT goal achieved**
+
+```python
+# WRONG
+assert result.success
+
+# RIGHT
+assert result.success, f"Agent failed: {result.error}"
+output = result.output or {}
+approval = output.get("approval_decision")
+assert approval == "APPROVED", f"Expected APPROVED, got {approval}"
+```
+
+All fields:
+- `success: bool` — Completed without exception (NOT goal achieved!)
+- `output: dict` — Complete memory snapshot (may contain raw strings)
+- `error: str | None` — Error message if failed
+- `steps_executed: int` — Number of nodes executed
+- `total_tokens: int` — Cumulative token usage
+- `total_latency_ms: int` — Total execution time
+- `path: list[str]` — Node IDs traversed (may repeat in feedback loops)
+- `paused_at: str | None` — Node ID if paused
+- `session_state: dict` — State for resuming
+- `node_visit_counts: dict[str, int]` — Visit counts per node (feedback loop testing)
+- `execution_quality: str` — "clean", "degraded", or "failed"
+
+### Test Count Guidance
+
+**Write 8-15 tests, not 30+**
+
+- 2-3 tests per success criterion
+- 1 happy path test
+- 1 boundary/edge case test
+- 1 error handling test (optional)
+
+Each real test costs ~3 seconds + LLM tokens. 12 tests = ~36 seconds, $0.12.
+
+---
+
+## Test Patterns
+
+### Happy Path
+```python
+@pytest.mark.asyncio
+async def test_happy_path(runner, auto_responder, mock_mode):
+    """Test normal successful execution."""
+    await auto_responder.start()
+    try:
+        result = await runner.run({"query": "python tutorials"})
+    finally:
+        await auto_responder.stop()
+    assert result.success, f"Agent failed: {result.error}"
+    output = result.output or {}
+    assert output.get("report"), "No report produced"
+```
+
+### Boundary Condition
+```python
+@pytest.mark.asyncio
+async def test_minimum_sources(runner, auto_responder, mock_mode):
+    """Test at minimum source threshold."""
+    await auto_responder.start()
+    try:
+        result = await runner.run({"query": "niche topic"})
+    finally:
+        await auto_responder.stop()
+    assert result.success, f"Agent failed: {result.error}"
+    output = result.output or {}
+    sources = output.get("sources", [])
+    if isinstance(sources, list):
+        assert len(sources) >= 3, f"Expected >= 3 sources, got {len(sources)}"
+```
+
+### Error Handling
+```python
+@pytest.mark.asyncio
+async def test_empty_input(runner, auto_responder, mock_mode):
+    """Test graceful handling of empty input."""
+    await auto_responder.start()
+    try:
+        result = await runner.run({"query": ""})
+    finally:
+        await auto_responder.stop()
+    # Agent should either fail gracefully or produce an error message
+    output = result.output or {}
+    assert not result.success or output.get("error"), "Should handle empty input"
+```
+
+### Feedback Loop
+```python
+@pytest.mark.asyncio
+async def test_feedback_loop_terminates(runner, auto_responder, mock_mode):
+    """Test that feedback loops don't run forever."""
+    await auto_responder.start()
+    try:
+        result = await runner.run({"query": "test"})
+    finally:
+        await auto_responder.stop()
+    visits = result.node_visit_counts or {}
+    for node_id, count in visits.items():
+        assert count <= 5, f"Node {node_id} visited {count} times — possible infinite loop"
+```
+
+---
+
+## MCP Tool Reference
+
+### Phase 1: Test Generation
+
+```python
+# Check existing tests
+list_tests(goal_id, agent_path)
+
+# Get constraint test guidelines (returns templates, NOT generated tests)
+generate_constraint_tests(goal_id, goal_json, agent_path)
+# Returns: output_file, file_header, test_template, constraints_formatted, test_guidelines
+
+# Get success criteria test guidelines
+generate_success_tests(goal_id, goal_json, node_names, tool_names, agent_path)
+# Returns: output_file, file_header, test_template, success_criteria_formatted, test_guidelines
+```
+
+### Phase 2: Execution
+
+```python
+# Automated regression (no checkpoints, fresh runs)
+run_tests(goal_id, agent_path, test_types='["all"]', parallel=-1, fail_fast=False)
+
+# Run only specific test types
+run_tests(goal_id, agent_path, test_types='["constraint"]')
+run_tests(goal_id, agent_path, test_types='["success"]')
+```
+
+```bash
+# Iterative debugging with checkpoints (via CLI)
+uv run hive run exports/{agent_name} --input '{"query": "test"}'
+```
+
+### Phase 3: Analysis
+
+```python
+# Debug a specific failed test
+debug_test(goal_id, test_name, agent_path)
+
+# Find failed sessions
+list_agent_sessions(agent_work_dir, status="failed", limit=5)
+
+# Inspect session state (excludes memory values)
+get_agent_session_state(agent_work_dir, session_id)
+
+# Inspect memory data
+get_agent_session_memory(agent_work_dir, session_id, key="research_results")
+
+# Runtime logs: L1 summaries
+query_runtime_logs(agent_work_dir, status="needs_attention")
+
+# Runtime logs: L2 per-node details
+query_runtime_log_details(agent_work_dir, run_id, needs_attention_only=True)
+
+# Runtime logs: L3 tool/LLM raw data
+query_runtime_log_raw(agent_work_dir, run_id, node_id="research")
+
+# Find clean checkpoints
+list_agent_checkpoints(agent_work_dir, session_id, is_clean="true")
+
+# Compare checkpoints (memory diff)
+compare_agent_checkpoints(agent_work_dir, session_id, cp_before, cp_after)
+```
+
+### Phase 5: Recovery
+
+```python
+# Inspect checkpoint before resuming
+get_agent_checkpoint(agent_work_dir, session_id, checkpoint_id)
+# Empty checkpoint_id = latest checkpoint
+```
+
+```bash
+# Resume from checkpoint via CLI (headless)
+uv run hive run exports/{agent_name} \
+  --resume-session {session_id} --checkpoint {checkpoint_id}
+```
+
+---
+
+## Anti-Patterns
+
+| Don't | Do Instead |
+|-------|-----------|
+| Use `default_agent.run()` in tests | Use `runner.run()` with `auto_responder` fixtures (goes through AgentRuntime) |
+| Re-run entire agent when a late node fails | Resume from last clean checkpoint |
+| Treat `result.success` as goal achieved | Check `result.output` for actual criteria |
+| Access `result.output["key"]` directly | Use `result.output.get("key")` |
+| Fix random things hoping tests pass | Analyze L2/L3 logs to find root cause first |
+| Write 30+ tests | Write 8-15 focused tests |
+| Skip credential check | Use `/hive-credentials` before testing |
+| Confuse `exports/` with `~/.hive/agents/` | Code in `exports/`, runtime data in `~/.hive/` |
+| Use `run_tests` for iterative debugging | Use headless CLI with checkpoints for iterative debugging |
+| Use headless CLI for final regression | Use `run_tests` for automated regression |
+| Use `--tui` from Claude Code | Use headless `run` command — TUI hangs in non-interactive shells |
+| Test client-facing nodes from Claude Code | Use mock mode, or have the user run the agent in their terminal |
+| Run tests without reading goal first | Always understand the goal before writing tests |
+| Skip Phase 3 analysis and guess | Use session + log tools to identify root cause |
+
+---
+
+## Example Walkthrough: Deep Research Agent
+
+A complete iteration showing the test loop for an agent with nodes: `intake → research → review → report`.
+
+### Phase 1: Generate tests
+
+```python
+# Read the goal
+Read(file_path="exports/deep_research_agent/agent.py")
+
+# Get success criteria test guidelines
+result = generate_success_tests(
+    goal_id="rigorous-interactive-research",
+    goal_json='{"id": "rigorous-interactive-research", "success_criteria": [{"id": "source-diversity", "target": ">=5"}, {"id": "citation-coverage", "target": "100%"}, {"id": "report-completeness", "target": "90%"}]}',
+    node_names="intake,research,review,report",
+    tool_names="web_search,web_scrape",
+    agent_path="exports/deep_research_agent"
+)
+
+# Write tests
+Write(
+    file_path=result["output_file"],
+    content=result["file_header"] + "\n\n" + test_code
+)
+```
+
+### Phase 2: First execution
+
+```python
+run_tests(
+    goal_id="rigorous-interactive-research",
+    agent_path="exports/deep_research_agent",
+    fail_fast=True
+)
+```
+
+Result: `test_success_source_diversity` fails — agent only found 2 sources instead of 5.
+
+### Phase 3: Analyze
+
+```python
+# Debug the failing test
+debug_test(
+    goal_id="rigorous-interactive-research",
+    test_name="test_success_source_diversity",
+    agent_path="exports/deep_research_agent"
+)
+# → ASSERTION_FAILURE: Expected >= 5 sources, got 2
+
+# Find the session
+list_agent_sessions(
+    agent_work_dir="~/.hive/agents/deep_research_agent",
+    status="completed",
+    limit=1
+)
+# → session_20260209_150000_abc12345
+
+# See what the research node produced
+get_agent_session_memory(
+    agent_work_dir="~/.hive/agents/deep_research_agent",
+    session_id="session_20260209_150000_abc12345",
+    key="research_results"
+)
+# → Only 2 web_search calls made, each returned 1 source
+
+# Check the LLM's behavior in the research node
+query_runtime_log_raw(
+    agent_work_dir="~/.hive/agents/deep_research_agent",
+    run_id="session_20260209_150000_abc12345",
+    node_id="research"
+)
+# → LLM called web_search only twice, then called set_output
+```
+
+Root cause: The research node's prompt doesn't tell the LLM to search for at least 5 diverse sources. It stops after the first couple of searches.
+
+### Phase 4: Fix the prompt
+
+```python
+Read(file_path="exports/deep_research_agent/nodes/__init__.py")
+
+Edit(
+    file_path="exports/deep_research_agent/nodes/__init__.py",
+    old_string='system_prompt="Search for information on the user\'s topic."',
+    new_string='system_prompt="Search for information on the user\'s topic. You MUST find at least 5 diverse, authoritative sources. Use multiple different search queries to ensure source diversity. Do not stop searching until you have at least 5 distinct sources."'
+)
+```
+
+### Phase 5: Resume from checkpoint
+
+For this example, the fix is to the `research` node. If we had run via CLI with checkpointing, we could resume from the checkpoint after `intake` to skip re-running intake:
+
+```bash
+# Check if clean checkpoint exists after intake
+list_agent_checkpoints(
+    agent_work_dir="~/.hive/agents/deep_research_agent",
+    session_id="session_20260209_150000_abc12345",
+    is_clean="true"
+)
+# → cp_node_complete_intake_150005
+
+# Resume from after intake, re-run research with fixed prompt
+uv run hive run exports/deep_research_agent \
+  --resume-session session_20260209_150000_abc12345 \
+  --checkpoint cp_node_complete_intake_150005
+```
+
+Or for this simple case (intake is fast), just re-run:
+
+```bash
+uv run hive run exports/deep_research_agent --input '{"topic": "test"}'
+```
+
+### Phase 6: Final verification
+
+```python
+run_tests(
+    goal_id="rigorous-interactive-research",
+    agent_path="exports/deep_research_agent"
+)
+# → All 12 tests pass
+```
+
+---
+
+## Test File Structure
+
+```
+exports/{agent_name}/
+├── agent.py              ← Agent to test (goal, nodes, edges)
+├── nodes/__init__.py     ← Node implementations (prompts, config)
+├── config.py             ← Agent configuration
+├── mcp_servers.json      ← Tool server config
+└── tests/
+    ├── conftest.py           ← Shared fixtures + safe access helpers
+    ├── test_constraints.py   ← Constraint tests
+    ├── test_success_criteria.py  ← Success criteria tests
+    └── test_edge_cases.py    ← Edge case tests
+```
+
+## Integration with Other Skills
+
+| Scenario | From | To | Action |
+|----------|------|----|--------|
+| Agent built, ready to test | `/hive-create` | `/hive-test` | Generate tests, start loop |
+| Prompt fix needed | `/hive-test` Phase 4 | Direct edit | Edit `nodes/__init__.py`, resume |
+| Goal definition wrong | `/hive-test` Phase 4 | `/hive-create` | Update goal, may need rebuild |
+| Missing credentials | `/hive-test` Phase 3 | `/hive-credentials` | Set up credentials |
+| Complex runtime failure | `/hive-test` Phase 3 | `/hive-debugger` | Deep L1/L2/L3 analysis |
+| All tests pass | `/hive-test` Phase 6 | Done | Agent validated |

.claude/skills/hive-test/examples/testing-youtube-agent.md

@@ -0,0 +1,333 @@
+# Example: Iterative Testing of a Research Agent
+
+This example walks through the full iterative test loop for a research agent that searches the web, reviews findings, and produces a cited report.
+
+## Agent Structure
+
+```
+exports/deep_research_agent/
+├── agent.py          # Goal + graph: intake → research → review → report
+├── nodes/__init__.py # Node definitions (system_prompt, input/output keys)
+├── config.py         # Model config
+├── mcp_servers.json  # Tools: web_search, web_scrape
+└── tests/            # Test files (we'll create these)
+```
+
+**Goal:** "Rigorous Interactive Research" — find 5+ diverse sources, cite every claim, produce a complete report.
+
+---
+
+## Phase 1: Generate Tests
+
+### Read the goal
+
+```python
+Read(file_path="exports/deep_research_agent/agent.py")
+# Extract: goal_id="rigorous-interactive-research"
+# success_criteria: source-diversity (>=5), citation-coverage (100%), report-completeness (90%)
+# constraints: no-hallucination, source-attribution
+```
+
+### Get test guidelines
+
+```python
+result = generate_success_tests(
+    goal_id="rigorous-interactive-research",
+    goal_json='{"id": "rigorous-interactive-research", "success_criteria": [{"id": "source-diversity", "description": "Use multiple diverse sources", "target": ">=5"}, {"id": "citation-coverage", "description": "Every claim cites its source", "target": "100%"}, {"id": "report-completeness", "description": "Report answers the research questions", "target": "90%"}]}',
+    node_names="intake,research,review,report",
+    tool_names="web_search,web_scrape",
+    agent_path="exports/deep_research_agent"
+)
+```
+
+### Write tests
+
+```python
+Write(
+    file_path="exports/deep_research_agent/tests/test_success_criteria.py",
+    content=result["file_header"] + '''
+
+@pytest.mark.asyncio
+async def test_success_source_diversity(runner, auto_responder, mock_mode):
+    """At least 5 diverse sources are found."""
+    await auto_responder.start()
+    try:
+        result = await runner.run({"query": "impact of remote work on productivity"})
+    finally:
+        await auto_responder.stop()
+    assert result.success, f"Agent failed: {result.error}"
+    output = result.output or {}
+    sources = output.get("sources", [])
+    if isinstance(sources, list):
+        assert len(sources) >= 5, f"Expected >= 5 sources, got {len(sources)}"
+
+@pytest.mark.asyncio
+async def test_success_citation_coverage(runner, auto_responder, mock_mode):
+    """Every factual claim in the report cites its source."""
+    await auto_responder.start()
+    try:
+        result = await runner.run({"query": "climate change effects on agriculture"})
+    finally:
+        await auto_responder.stop()
+    assert result.success, f"Agent failed: {result.error}"
+    output = result.output or {}
+    report = output.get("report", "")
+    # Check that report contains numbered references
+    assert "[1]" in str(report) or "[source" in str(report).lower(), "Report lacks citations"
+
+@pytest.mark.asyncio
+async def test_success_report_completeness(runner, auto_responder, mock_mode):
+    """Report addresses the original research question."""
+    query = "pros and cons of nuclear energy"
+    await auto_responder.start()
+    try:
+        result = await runner.run({"query": query})
+    finally:
+        await auto_responder.stop()
+    assert result.success, f"Agent failed: {result.error}"
+    output = result.output or {}
+    report = output.get("report", "")
+    assert len(str(report)) > 200, f"Report too short: {len(str(report))} chars"
+
+@pytest.mark.asyncio
+async def test_empty_query_handling(runner, auto_responder, mock_mode):
+    """Agent handles empty input gracefully."""
+    await auto_responder.start()
+    try:
+        result = await runner.run({"query": ""})
+    finally:
+        await auto_responder.stop()
+    output = result.output or {}
+    assert not result.success or output.get("error"), "Should handle empty query"
+
+@pytest.mark.asyncio
+async def test_feedback_loop_terminates(runner, auto_responder, mock_mode):
+    """Feedback loop between review and research terminates."""
+    await auto_responder.start()
+    try:
+        result = await runner.run({"query": "quantum computing basics"})
+    finally:
+        await auto_responder.stop()
+    visits = result.node_visit_counts or {}
+    for node_id, count in visits.items():
+        assert count <= 5, f"Node {node_id} visited {count} times"
+'''
+)
+```
+
+---
+
+## Phase 2: First Execution
+
+```python
+run_tests(
+    goal_id="rigorous-interactive-research",
+    agent_path="exports/deep_research_agent",
+    fail_fast=True
+)
+```
+
+**Result:**
+```json
+{
+  "overall_passed": false,
+  "summary": {"total": 5, "passed": 3, "failed": 2, "pass_rate": "60.0%"},
+  "failures": [
+    {"test_name": "test_success_source_diversity", "details": "AssertionError: Expected >= 5 sources, got 2"},
+    {"test_name": "test_success_citation_coverage", "details": "AssertionError: Report lacks citations"}
+  ]
+}
+```
+
+---
+
+## Phase 3: Analyze (Iteration 1)
+
+### Debug the first failure
+
+```python
+debug_test(
+    goal_id="rigorous-interactive-research",
+    test_name="test_success_source_diversity",
+    agent_path="exports/deep_research_agent"
+)
+# Category: ASSERTION_FAILURE — Expected >= 5 sources, got 2
+```
+
+### Find the session and inspect memory
+
+```python
+list_agent_sessions(
+    agent_work_dir="~/.hive/agents/deep_research_agent",
+    status="completed",
+    limit=1
+)
+# → session_20260209_150000_abc12345
+
+get_agent_session_memory(
+    agent_work_dir="~/.hive/agents/deep_research_agent",
+    session_id="session_20260209_150000_abc12345",
+    key="research_results"
+)
+# → Only 2 sources found. LLM stopped searching after 2 queries.
+```
+
+### Check LLM behavior in the research node
+
+```python
+query_runtime_log_raw(
+    agent_work_dir="~/.hive/agents/deep_research_agent",
+    run_id="session_20260209_150000_abc12345",
+    node_id="research"
+)
+# → LLM called web_search twice, got results, immediately called set_output.
+# → Prompt doesn't instruct it to find at least 5 sources.
+```
+
+**Root cause:** The research node's system_prompt doesn't specify minimum source requirements.
+
+---
+
+## Phase 4: Fix (Iteration 1)
+
+```python
+Read(file_path="exports/deep_research_agent/nodes/__init__.py")
+
+# Fix the research node prompt
+Edit(
+    file_path="exports/deep_research_agent/nodes/__init__.py",
+    old_string='system_prompt="Search for information on the user\'s topic using web search."',
+    new_string='system_prompt="Search for information on the user\'s topic using web search. You MUST find at least 5 diverse, authoritative sources. Use multiple different search queries with varied keywords. Do NOT call set_output until you have gathered at least 5 distinct sources from different domains."'
+)
+```
+
+---
+
+## Phase 5: Recover & Resume (Iteration 1)
+
+The fix is to the `research` node. Since this was a `run_tests` execution (no checkpoints), we re-run from scratch:
+
+```python
+run_tests(
+    goal_id="rigorous-interactive-research",
+    agent_path="exports/deep_research_agent",
+    fail_fast=True
+)
+```
+
+**Result:**
+```json
+{
+  "overall_passed": false,
+  "summary": {"total": 5, "passed": 4, "failed": 1, "pass_rate": "80.0%"},
+  "failures": [
+    {"test_name": "test_success_citation_coverage", "details": "AssertionError: Report lacks citations"}
+  ]
+}
+```
+
+Source diversity now passes. Citation coverage still fails.
+
+---
+
+## Phase 3: Analyze (Iteration 2)
+
+```python
+debug_test(
+    goal_id="rigorous-interactive-research",
+    test_name="test_success_citation_coverage",
+    agent_path="exports/deep_research_agent"
+)
+# Category: ASSERTION_FAILURE — Report lacks citations
+
+# Check what the report node produced
+list_agent_sessions(
+    agent_work_dir="~/.hive/agents/deep_research_agent",
+    status="completed",
+    limit=1
+)
+# → session_20260209_151500_def67890
+
+get_agent_session_memory(
+    agent_work_dir="~/.hive/agents/deep_research_agent",
+    session_id="session_20260209_151500_def67890",
+    key="report"
+)
+# → Report text exists but uses no numbered references.
+# → Sources are in memory but report node doesn't cite them.
+```
+
+**Root cause:** The report node's prompt doesn't instruct the LLM to include numbered citations.
+
+---
+
+## Phase 4: Fix (Iteration 2)
+
+```python
+Edit(
+    file_path="exports/deep_research_agent/nodes/__init__.py",
+    old_string='system_prompt="Write a comprehensive report based on the research findings."',
+    new_string='system_prompt="Write a comprehensive report based on the research findings. You MUST include numbered citations [1], [2], etc. for every factual claim. At the end, include a References section listing all sources with their URLs. Every claim must be traceable to a specific source."'
+)
+```
+
+---
+
+## Phase 5: Resume (Iteration 2)
+
+The fix is to the `report` node (the last node). To demonstrate checkpoint recovery, run via CLI:
+
+```bash
+# Run via CLI to get checkpoints
+uv run hive run exports/deep_research_agent --input '{"topic": "climate change effects"}'
+
+# After it runs, find the clean checkpoint before report
+list_agent_checkpoints(
+    agent_work_dir="~/.hive/agents/deep_research_agent",
+    session_id="session_20260209_152000_ghi34567",
+    is_clean="true"
+)
+# → cp_node_complete_review_152100 (after review, before report)
+
+# Resume — skips intake, research, review entirely
+uv run hive run exports/deep_research_agent \
+  --resume-session session_20260209_152000_ghi34567 \
+  --checkpoint cp_node_complete_review_152100
+```
+
+Only the `report` node re-runs with the fixed prompt, using research data from the checkpoint.
+
+---
+
+## Phase 6: Final Verification
+
+```python
+run_tests(
+    goal_id="rigorous-interactive-research",
+    agent_path="exports/deep_research_agent"
+)
+```
+
+**Result:**
+```json
+{
+  "overall_passed": true,
+  "summary": {"total": 5, "passed": 5, "failed": 0, "pass_rate": "100.0%"}
+}
+```
+
+All tests pass.
+
+---
+
+## Summary
+
+| Iteration | Failure | Root Cause | Fix | Recovery |
+|-----------|---------|------------|-----|----------|
+| 1 | Source diversity (2 < 5) | Research prompt too vague | Added "at least 5 sources" to prompt | Re-run (no checkpoints) |
+| 2 | No citations in report | Report prompt lacks citation instructions | Added citation requirements | Checkpoint resume (skipped 3 nodes) |
+
+**Key takeaways:**
+- Phase 3 analysis (session memory + L3 logs) identified root causes without guessing
+- Checkpoint recovery in iteration 2 saved time by skipping 3 expensive nodes
+- Final `run_tests` confirms all scenarios pass end-to-end

.claude/skills/hive/SKILL.md

@@ -1,30 +1,53 @@
 ---
-name: agent-workflow
-description: Complete workflow for building, implementing, and testing goal-driven agents. Orchestrates building-agents-* and testing-agent skills. Use when starting a new agent project, unsure which skill to use, or need end-to-end guidance.
+name: hive
+description: Complete workflow for building, implementing, and testing goal-driven agents. Orchestrates hive-* skills. Use when starting a new agent project, unsure which skill to use, or need end-to-end guidance.
 license: Apache-2.0
 metadata:
   author: hive
   version: "2.0"
   type: workflow-orchestrator
   orchestrates:
-    - building-agents-core
-    - building-agents-construction
-    - building-agents-patterns
-    - testing-agent
+    - hive-concepts
+    - hive-create
+    - hive-patterns
+    - hive-test
+    - hive-credentials
+    - hive-debugger
 ---
 
 # Agent Development Workflow
 
+**THIS IS AN EXECUTABLE WORKFLOW. DO NOT explore the codebase or read source files. ROUTE to the correct skill IMMEDIATELY.**
+
+When this skill is loaded, **ALWAYS use the AskUserQuestion tool** to present options:
+
+```
+Use AskUserQuestion with these options:
+- "Build a new agent" → Then invoke /hive-create
+- "Test an existing agent" → Then invoke /hive-test
+- "Learn agent concepts" → Then invoke /hive-concepts
+- "Optimize agent design" → Then invoke /hive-patterns
+- "Set up credentials" → Then invoke /hive-credentials
+- "Debug a failing agent" → Then invoke /hive-debugger
+- "Other" (please describe what you want to achieve)
+```
+
+**DO NOT:** Read source files, explore the codebase, search for code, or do any investigation before routing. The sub-skills handle all of that.
+
+---
+
 Complete Standard Operating Procedure (SOP) for building production-ready goal-driven agents.
 
 ## Overview
 
 This workflow orchestrates specialized skills to take you from initial concept to production-ready agent:
 
-1. **Understand Concepts** (5-10 min) → `/building-agents-core` (optional)
-2. **Build Structure** (15-30 min) → `/building-agents-construction`
-3. **Optimize Design** (10-15 min) → `/building-agents-patterns` (optional)
-4. **Test & Validate** (20-40 min) → `/testing-agent`
+1. **Understand Concepts** → `/hive-concepts` (optional)
+2. **Build Structure** → `/hive-create`
+3. **Optimize Design** → `/hive-patterns` (optional)
+4. **Setup Credentials** → `/hive-credentials` (if agent uses tools requiring API keys)
+5. **Test & Validate** → `/hive-test`
+6. **Debug Issues** → `/hive-debugger` (if agent fails at runtime)
 
 ## When to Use This Workflow
 
@@ -35,24 +58,26 @@ Use this meta-skill when:
 - Want consistent, repeatable agent builds
 
 **Skip this workflow** if:
-- You only need to test an existing agent → use `/testing-agent` directly
+- You only need to test an existing agent → use `/hive-test` directly
 - You know exactly which phase you're in → use specific skill directly
 
 ## Quick Decision Tree
 
 ```
-"Need to understand agent concepts" → building-agents-core
-"Build a new agent" → building-agents-construction
-"Optimize my agent design" → building-agents-patterns
-"Test my agent" → testing-agent
+"Need to understand agent concepts" → hive-concepts
+"Build a new agent" → hive-create
+"Optimize my agent design" → hive-patterns
+"Need client-facing nodes or feedback loops" → hive-patterns
+"Set up API keys for my agent" → hive-credentials
+"Test my agent" → hive-test
+"My agent is failing/stuck/has errors" → hive-debugger
 "Not sure what I need" → Read phases below, then decide
 "Agent has structure but needs implementation" → See agent directory STATUS.md
 ```
 
 ## Phase 0: Understand Concepts (Optional)
 
-**Duration**: 5-10 minutes
-**Skill**: `/building-agents-core`
+**Skill**: `/hive-concepts`
 **Input**: Questions about agent architecture
 
 ### When to Use
@@ -60,12 +85,12 @@ Use this meta-skill when:
 - First time building an agent
 - Need to understand node types, edges, goals
 - Want to validate tool availability
-- Learning about pause/resume architecture
+- Learning about event loop architecture and client-facing nodes
 
 ### What This Phase Provides
 
 - Architecture overview (Python packages, not JSON)
-- Core concepts (Goal, Node, Edge, Pause/Resume)
+- Core concepts (Goal, Node, Edge, Event Loop, Judges)
 - Tool discovery and validation procedures
 - Workflow overview
 
@@ -73,9 +98,8 @@ Use this meta-skill when:
 
 ## Phase 1: Build Agent Structure
 
-**Duration**: 15-30 minutes
-**Skill**: `/building-agents-construction`
-**Input**: User requirements ("Build an agent that...")
+**Skill**: `/hive-create`
+**Input**: User requirements ("Build an agent that...") or a template to start from
 
 ### What This Phase Does
 
@@ -103,7 +127,7 @@ Creates the complete agent architecture:
 - ✅ 1-5 constraints defined
 - ✅ 5-10 nodes specified in nodes/__init__.py
 - ✅ 8-15 edges connecting workflow
-- ✅ Validated structure (passes `python -m agent_name validate`)
+- ✅ Validated structure (passes `uv run python -m agent_name validate`)
 - ✅ README.md with usage instructions
 - ✅ CLI commands (info, validate, run, shell)
 
@@ -117,7 +141,7 @@ You're ready for Phase 2 when:
 
 ### Common Outputs
 
-The building-agents-construction skill produces:
+The hive-create skill produces:
 ```
 exports/agent_name/
 ├── __init__.py          (package exports)
@@ -137,53 +161,52 @@ exports/agent_name/
 → You may need to add Python functions or MCP tools (not covered by current skills)
 
 **If want to optimize design:**
-→ Proceed to Phase 1.5 (building-agents-patterns)
+→ Proceed to Phase 1.5 (hive-patterns)
 
 **If ready to test:**
 → Proceed to Phase 2
 
 ## Phase 1.5: Optimize Design (Optional)
 
-**Duration**: 10-15 minutes
-**Skill**: `/building-agents-patterns`
+**Skill**: `/hive-patterns`
 **Input**: Completed agent structure
 
 ### When to Use
 
-- Want to add pause/resume functionality
+- Want to add client-facing blocking or feedback edges
+- Need judge patterns for output validation
+- Want fan-out/fan-in (parallel execution)
 - Need error handling patterns
-- Want to optimize performance
-- Need examples of complex routing
 - Want best practices guidance
 
 ### What This Phase Provides
 
-- Practical examples and patterns
-- Pause/resume architecture
-- Error handling strategies
+- Client-facing interaction patterns
+- Feedback edge routing with nullable output keys
+- Judge patterns (implicit, SchemaJudge)
+- Fan-out/fan-in parallel execution
+- Context management and spillover patterns
 - Anti-patterns to avoid
-- Performance optimization techniques
 
 **Skip this phase** if your agent design is straightforward.
 
 ## Phase 2: Test & Validate
 
-**Duration**: 20-40 minutes
-**Skill**: `/testing-agent`
+**Skill**: `/hive-test`
 **Input**: Working agent from Phase 1
 
 ### What This Phase Does
 
-Creates comprehensive test suite:
-- Constraint tests (verify hard requirements)
-- Success criteria tests (measure goal achievement)
-- Edge case tests (handle failures gracefully)
-- Integration tests (end-to-end workflows)
+Guides the creation and execution of a comprehensive test suite:
+- Constraint tests
+- Success criteria tests
+- Edge case tests
+- Integration tests
 
 ### Process
 
 1. **Analyze agent** - Read goal, constraints, success criteria
-2. **Generate tests** - Create pytest files in `exports/agent_name/tests/`
+2. **Generate tests** - The calling agent writes pytest files in `exports/agent_name/tests/` using hive-test guidelines and templates
 3. **User approval** - Review and approve each test
 4. **Run evaluation** - Execute tests and collect results
 5. **Debug failures** - Identify and fix issues
@@ -246,9 +269,9 @@ You're done when:
 
 ```
 User: "Build an agent that monitors files"
-→ Use /building-agents-construction
+→ Use /hive-create
 → Agent structure created
-→ Use /testing-agent
+→ Use /hive-test
 → Tests created and passing
 → Done: Production-ready agent
 ```
@@ -257,19 +280,32 @@ User: "Build an agent that monitors files"
 
 ```
 User: "Build an agent (first time)"
-→ Use /building-agents-core (understand concepts)
-→ Use /building-agents-construction (build structure)
-→ Use /building-agents-patterns (optimize design)
-→ Use /testing-agent (validate)
+→ Use /hive-concepts (understand concepts)
+→ Use /hive-create (build structure)
+→ Use /hive-patterns (optimize design)
+→ Use /hive-test (validate)
 → Done: Production-ready agent
 ```
 
+### Pattern 1c: Build from Template
+
+```
+User: "Build an agent based on the deep research template"
+→ Use /hive-create
+→ Select "From a template" path
+→ Pick template, name new agent
+→ Review/modify goal, nodes, graph
+→ Agent exported with customizations
+→ Use /hive-test
+→ Done: Customized agent
+```
+
 ### Pattern 2: Test Existing Agent
 
 ```
 User: "Test my agent at exports/my_agent"
 → Skip Phase 1
-→ Use /testing-agent directly
+→ Use /hive-test directly
 → Tests created
 → Done: Validated agent
 ```
@@ -278,58 +314,71 @@ User: "Test my agent at exports/my_agent"
 
 ```
 User: "Build an agent"
-→ Use /building-agents-construction (Phase 1)
+→ Use /hive-create (Phase 1)
 → Implementation needed (see STATUS.md)
 → [User implements functions]
-→ Use /testing-agent (Phase 2)
+→ Use /hive-test (Phase 2)
 → Tests reveal bugs
 → [Fix bugs manually]
 → Re-run tests
 → Done: Working agent
 ```
 
-### Pattern 4: Complex Agent with Patterns
+### Pattern 4: Agent with Review Loops and HITL Checkpoints
 
 ```
-User: "Build an agent with multi-turn conversations"
-→ Use /building-agents-core (learn pause/resume)
-→ Use /building-agents-construction (build structure)
-→ Use /building-agents-patterns (implement pause/resume pattern)
-→ Use /testing-agent (validate conversation flows)
-→ Done: Complex conversational agent
+User: "Build an agent with human review and feedback loops"
+→ Use /hive-concepts (learn event loop, client-facing nodes)
+→ Use /hive-create (build structure with feedback edges)
+→ Use /hive-patterns (implement client-facing + feedback patterns)
+→ Use /hive-test (validate review flows and edge routing)
+→ Done: Agent with HITL checkpoints and review loops
 ```
 
 ## Skill Dependencies
 
 ```
-agent-workflow (meta-skill)
+hive (meta-skill)
     │
-    ├── building-agents-core (foundational)
-    │   ├── Architecture concepts
-    │   ├── Node/Edge/Goal definitions
+    ├── hive-concepts (foundational)
+    │   ├── Architecture concepts (event loop, judges)
+    │   ├── Node types (event_loop, function)
+    │   ├── Edge routing and priority
     │   ├── Tool discovery procedures
     │   └── Workflow overview
     │
-    ├── building-agents-construction (procedural)
+    ├── hive-create (procedural)
     │   ├── Creates package structure
     │   ├── Defines goal
-    │   ├── Adds nodes incrementally
-    │   ├── Connects edges
+    │   ├── Adds nodes (event_loop, function)
+    │   ├── Connects edges with priority routing
     │   ├── Finalizes agent class
-    │   └── Requires: building-agents-core
+    │   └── Requires: hive-concepts
     │
-    ├── building-agents-patterns (reference)
-    │   ├── Best practices
-    │   ├── Pause/resume patterns
-    │   ├── Error handling
-    │   ├── Anti-patterns
-    │   └── Performance optimization
+    ├── hive-patterns (reference)
+    │   ├── Client-facing interaction patterns
+    │   ├── Feedback edges and review loops
+    │   ├── Judge patterns (implicit, SchemaJudge)
+    │   ├── Fan-out/fan-in parallel execution
+    │   └── Context management and anti-patterns
     │
-    └── testing-agent
-        ├── Reads agent goal
-        ├── Generates tests
-        ├── Runs evaluation
-        └── Reports results
+    ├── hive-credentials (utility)
+    │   ├── Detects missing credentials
+    │   ├── Offers auth method choices (Aden OAuth, direct API key)
+    │   ├── Stores securely in ~/.hive/credentials
+    │   └── Validates with health checks
+    │
+    ├── hive-test (validation)
+    │   ├── Reads agent goal
+    │   ├── Generates tests
+    │   ├── Runs evaluation
+    │   └── Reports results
+    │
+    └── hive-debugger (troubleshooting)
+        ├── Monitors runtime logs (L1/L2/L3)
+        ├── Identifies retry loops, tool failures
+        ├── Categorizes issues (10 categories)
+        └── Provides fix recommendations
 ```
 
 ## Troubleshooting
@@ -339,13 +388,13 @@ agent-workflow (meta-skill)
 - Check node IDs match between nodes/__init__.py and agent.py
 - Verify all edges reference valid node IDs
 - Ensure entry_node exists in nodes list
-- Run: `PYTHONPATH=core:exports python -m agent_name validate`
+- Run: `PYTHONPATH=exports uv run python -m agent_name validate`
 
 ### "Agent has structure but won't run"
 
 - Check for STATUS.md or IMPLEMENTATION_GUIDE.md in agent directory
 - Implementation may be needed (Python functions or MCP tools)
-- This is expected - building-agents-construction creates structure, not implementation
+- This is expected - hive-create creates structure, not implementation
 - See implementation guide for completion options
 
 ### "Tests are failing"
@@ -353,9 +402,16 @@ agent-workflow (meta-skill)
 - Review test output for specific failures
 - Check agent goal and success criteria
 - Verify constraints are met
-- Use `/testing-agent` to debug and iterate
+- Use `/hive-test` to debug and iterate
 - Fix agent code and re-run tests
 
+### "Agent is failing at runtime"
+
+- Use `/hive-debugger` to analyze runtime logs
+- The debugger identifies retry loops, tool failures, and stalled execution
+- Get actionable fix recommendations with code changes
+- Monitor the agent in real-time during TUI sessions
+
 ### "Not sure which phase I'm in"
 
 Run these checks:
@@ -365,7 +421,7 @@ Run these checks:
 ls exports/my_agent/agent.py
 
 # Check if it validates
-PYTHONPATH=core:exports python -m my_agent validate
+PYTHONPATH=exports uv run python -m my_agent validate
 
 # Check if tests exist
 ls exports/my_agent/tests/
@@ -414,10 +470,10 @@ You're done with the workflow when:
 
 ## Additional Resources
 
-- **building-agents-core**: See `.claude/skills/building-agents-core/SKILL.md`
-- **building-agents-construction**: See `.claude/skills/building-agents-construction/SKILL.md`
-- **building-agents-patterns**: See `.claude/skills/building-agents-patterns/SKILL.md`
-- **testing-agent**: See `.claude/skills/testing-agent/SKILL.md`
+- **hive-concepts**: See `.claude/skills/hive-concepts/SKILL.md`
+- **hive-create**: See `.claude/skills/hive-create/SKILL.md`
+- **hive-patterns**: See `.claude/skills/hive-patterns/SKILL.md`
+- **hive-test**: See `.claude/skills/hive-test/SKILL.md`
 - **Agent framework docs**: See `core/README.md`
 - **Example agents**: See `exports/` directory
 
@@ -425,36 +481,46 @@ You're done with the workflow when:
 
 This workflow provides a proven path from concept to production-ready agent:
 
-1. **Learn** with `/building-agents-core` → Understand fundamentals (optional)
-2. **Build** with `/building-agents-construction` → Get validated structure
-3. **Optimize** with `/building-agents-patterns` → Apply best practices (optional)
-4. **Test** with `/testing-agent` → Get verified functionality
+1. **Learn** with `/hive-concepts` → Understand fundamentals (optional)
+2. **Build** with `/hive-create` → Get validated structure
+3. **Optimize** with `/hive-patterns` → Apply best practices (optional)
+4. **Configure** with `/hive-credentials` → Set up API keys (if needed)
+5. **Test** with `/hive-test` → Get verified functionality
+6. **Debug** with `/hive-debugger` → Fix runtime issues (if needed)
 
 The workflow is **flexible** - skip phases as needed, iterate freely, and adapt to your specific requirements. The goal is **production-ready agents** built with **consistent, repeatable processes**.
 
 ## Skill Selection Guide
 
-**Choose building-agents-core when:**
+**Choose hive-concepts when:**
 - First time building agents
-- Need to understand architecture
+- Need to understand event loop architecture
 - Validating tool availability
-- Learning about node types and edges
+- Learning about node types, edges, and judges
 
-**Choose building-agents-construction when:**
+**Choose hive-create when:**
 - Actually building an agent
 - Have clear requirements
 - Ready to write code
 - Want step-by-step guidance
+- Want to start from an existing template and customize it
 
-**Choose building-agents-patterns when:**
+**Choose hive-patterns when:**
 - Agent structure complete
-- Need advanced patterns
-- Implementing pause/resume
-- Optimizing performance
+- Need client-facing nodes or feedback edges
+- Implementing review loops or fan-out/fan-in
+- Want judge patterns or context management
 - Want best practices
 
-**Choose testing-agent when:**
+**Choose hive-test when:**
 - Agent structure complete
 - Ready to validate functionality
 - Need comprehensive test coverage
-- Debugging agent behavior
+- Testing feedback loops, output keys, or fan-out
+
+**Choose hive-debugger when:**
+- Agent is failing or stuck at runtime
+- Seeing retry loops or escalations
+- Tool calls are failing
+- Need to understand why a node isn't completing
+- Want real-time monitoring of agent execution

.claude/skills/hive/examples/file-monitor-example.md

@@ -1,6 +1,6 @@
 # Example: File Monitor Agent
 
-This example shows the complete agent-workflow in action for building a file monitoring agent.
+This example shows the complete /hive workflow in action for building a file monitoring agent.
 
 ## Initial Request
 
@@ -12,7 +12,7 @@ User: "Build an agent that monitors ~/Downloads and copies new files to ~/Docume
 
 ### Step 1: Create Structure
 
-Agent invokes `/building-agents` skill and:
+Agent invokes `/hive-create` skill and:
 
 1. Creates `exports/file_monitor_agent/` package
 2. Writes skeleton files (__init__.py, __main__.py, agent.py, etc.)
@@ -75,10 +75,10 @@ initialize → list → identify → check
 ### Step 5: Finalize
 
 ```bash
-$ PYTHONPATH=core:exports python -m file_monitor_agent validate
+$ PYTHONPATH=exports uv run python -m file_monitor_agent validate
 ✓ Agent is valid
 
-$ PYTHONPATH=core:exports python -m file_monitor_agent info
+$ PYTHONPATH=exports uv run python -m file_monitor_agent info
 Agent: File Monitor & Copy Agent
 Nodes: 7
 Edges: 8
@@ -107,7 +107,7 @@ exports/file_monitor_agent/
 
 ### Step 1: Analyze Agent
 
-Agent invokes `/testing-agent` skill and:
+Agent invokes `/hive-test` skill and:
 
 1. Reads goal from `exports/file_monitor_agent/agent.py`
 2. Identifies 4 success criteria to test
@@ -131,7 +131,7 @@ Tests approved incrementally by user.
 ### Step 3: Run Tests
 
 ```bash
-$ PYTHONPATH=core:exports pytest exports/file_monitor_agent/tests/
+$ PYTHONPATH=exports uv run pytest exports/file_monitor_agent/tests/
 
 test_constraints.py::test_preserves_originals     PASSED
 test_constraints.py::test_handles_errors          PASSED
@@ -162,7 +162,7 @@ test_edge_cases.py::test_large_files              PASSED
 ./RUN_AGENT.sh
 
 # Or manually
-PYTHONPATH=core:exports:tools/src python -m file_monitor_agent run
+PYTHONPATH=exports uv run python -m file_monitor_agent run
 ```
 
 **Capabilities:**

.claude/skills/testing-agent/SKILL.md

@@ -1,955 +0,0 @@
----
-name: testing-agent
-description: Run goal-based evaluation tests for agents. Use when you need to verify an agent meets its goals, debug failing tests, or iterate on agent improvements based on test results.
----
-
-# ⛔ MANDATORY: USE MCP TOOLS ONLY
-
-**STOP. Read this before doing anything else.**
-
-You MUST use MCP tools for ALL testing operations. Never write test files directly.
-
-## Required MCP Workflow
-
-1. `mcp__agent-builder__list_tests` - Check what tests exist
-2. `mcp__agent-builder__generate_constraint_tests` or `mcp__agent-builder__generate_success_tests` - Generate tests
-3. `mcp__agent-builder__get_pending_tests` - Review pending tests
-4. `mcp__agent-builder__approve_tests` - Approve tests (this writes the files)
-5. `mcp__agent-builder__run_tests` - Execute tests
-6. `mcp__agent-builder__debug_test` - Debug failures
-
-## ❌ WRONG - Never Do This
-
-```python
-# WRONG: Writing test file directly with Write tool
-Write(file_path="exports/agent/tests/test_foo.py", content="def test_...")
-```
-
-```python
-# WRONG: Running pytest directly via Bash
-Bash(command="pytest exports/agent/tests/ -v")
-```
-
-```python
-# WRONG: Creating test code manually
-test_code = """
-def test_something():
-    assert True
-"""
-```
-
-## ✅ CORRECT - Always Do This
-
-```python
-# CORRECT: Generate tests via MCP tool
-mcp__agent-builder__generate_constraint_tests(
-    goal_id="my-goal",
-    goal_json='{"id": "...", "constraints": [...]}',
-    agent_path="exports/my_agent"
-)
-
-# CORRECT: Approve tests via MCP tool (this writes files)
-mcp__agent-builder__approve_tests(
-    goal_id="my-goal",
-    approvals='[{"test_id": "test-1", "action": "approve"}]'
-)
-
-# CORRECT: Run tests via MCP tool
-mcp__agent-builder__run_tests(
-    goal_id="my-goal",
-    agent_path="exports/my_agent"
-)
-
-# CORRECT: Debug failures via MCP tool
-mcp__agent-builder__debug_test(
-    goal_id="my-goal",
-    test_name="test_constraint_foo",
-    agent_path="exports/my_agent"
-)
-```
-
-## Self-Check Before Every Action
-
-Before you take any testing action, ask yourself:
-- Am I about to write `def test_...`? → **STOP, use `generate_*_tests` instead**
-- Am I about to use `Write` for a test file? → **STOP, use `approve_tests` instead**
-- Am I about to run `pytest` via Bash? → **STOP, use `run_tests` instead**
-
----
-
-# Testing Agents with MCP Tools
-
-Run goal-based evaluation tests for agents built with the building-agents skill.
-
-**Key Principle: Tests are generated via MCP tools and written as Python files**
-- ✅ Generate tests: `generate_constraint_tests`, `generate_success_tests`
-- ✅ Review and approve: `get_pending_tests`, `approve_tests` → writes to Python files
-- ✅ Run tests: `run_tests` (runs pytest via subprocess)
-- ✅ Debug failures: `debug_test` (re-runs single test with verbose output)
-- ✅ List tests: `list_tests` (scans Python test files)
-- ✅ Tests stored in `exports/{agent}/tests/test_*.py`
-
-## Architecture: Python Test Files
-
-```
-exports/my_agent/
-├── __init__.py
-├── agent.py              ← Agent to test
-├── nodes/__init__.py
-├── config.py
-├── __main__.py
-└── tests/                ← Test files written by MCP tools
-    ├── conftest.py       # Shared fixtures (auto-created)
-    ├── test_constraints.py
-    ├── test_success_criteria.py
-    └── test_edge_cases.py
-```
-
-**Tests import the agent directly:**
-```python
-import pytest
-from exports.my_agent import default_agent
-
-
-@pytest.mark.asyncio
-async def test_happy_path(mock_mode):
-    result = await default_agent.run({"query": "test"}, mock_mode=mock_mode)
-    assert result.success
-    assert len(result.output) > 0
-```
-
-## Why MCP Tools Are Required
-
-- Tests are generated with proper imports, fixtures, and API key enforcement
-- Approval workflow ensures user review before file creation
-- `run_tests` parses pytest output into structured results for iteration
-- `debug_test` provides formatted output with actionable debugging info
-- `conftest.py` is auto-created with proper fixtures
-
-## Quick Start
-
-1. **Check existing tests** - `list_tests(goal_id, agent_path)`
-2. **Generate test files** - `generate_constraint_tests` or `generate_success_tests`
-3. **User reviews and approves** - `get_pending_tests` → `approve_tests`
-4. **Run tests** - `run_tests(goal_id, agent_path)`
-5. **Debug failures** - `debug_test(goal_id, test_name, agent_path)`
-6. **Iterate** - Repeat steps 4-5 until all pass
-
-## ⚠️ API Key Requirement for Real Testing
-
-**CRITICAL: Real LLM testing requires an API key.** Mock mode only validates structure and does NOT test actual agent behavior.
-
-### Prerequisites
-
-Before running agent tests, you MUST set your API key:
-
-```bash
-export ANTHROPIC_API_KEY="your-key-here"
-```
-
-**Why API keys are required:**
-- Tests need to execute the agent's LLM nodes to validate behavior
-- Mock mode bypasses LLM calls, providing no confidence in real-world performance
-- Success criteria (personalization, reasoning quality, constraint adherence) can only be tested with real LLM calls
-
-### Mock Mode Limitations
-
-Mock mode (`--mock` flag or `mock_mode=True`) is **ONLY for structure validation**:
-
-✓ Validates graph structure (nodes, edges, connections)
-✓ Tests that code doesn't crash on execution
-✗ Does NOT test LLM message generation
-✗ Does NOT test reasoning or decision-making quality
-✗ Does NOT test constraint validation (length limits, format rules)
-✗ Does NOT test real API integrations or tool use
-✗ Does NOT test personalization or content quality
-
-**Bottom line:** If you're testing whether an agent achieves its goal, you MUST use a real API key.
-
-### Enforcing API Key in Tests
-
-When generating tests, **ALWAYS include API key checks**:
-
-```python
-import os
-import pytest
-from aden_tools.credentials import CredentialManager
-
-# At the top of every test file
-pytestmark = pytest.mark.skipif(
-    not CredentialManager().is_available("anthropic") and not os.environ.get("MOCK_MODE"),
-    reason="API key required for real testing. Set ANTHROPIC_API_KEY or use MOCK_MODE=1 for structure validation only."
-)
-
-
-@pytest.fixture(scope="session", autouse=True)
-def check_api_key():
-    """Ensure API key is set for real testing."""
-    creds = CredentialManager()
-    if not creds.is_available("anthropic"):
-        if os.environ.get("MOCK_MODE"):
-            print("\n⚠️  Running in MOCK MODE - structure validation only")
-            print("   This does NOT test LLM behavior or agent quality")
-            print("   Set ANTHROPIC_API_KEY for real testing\n")
-        else:
-            pytest.fail(
-                "\n❌ ANTHROPIC_API_KEY not set!\n\n"
-                "Real testing requires an API key. Choose one:\n"
-                "1. Set API key (RECOMMENDED):\n"
-                "   export ANTHROPIC_API_KEY='your-key-here'\n"
-                "2. Run structure validation only:\n"
-                "   MOCK_MODE=1 pytest exports/{agent}/tests/\n\n"
-                "Note: Mock mode does NOT validate agent behavior or quality."
-            )
-```
-
-### User Communication
-
-When the user asks to test an agent, **ALWAYS check for the API key first**:
-
-```python
-from aden_tools.credentials import CredentialManager
-
-# Before running any tests
-creds = CredentialManager()
-if not creds.is_available("anthropic"):
-    print("⚠️  No ANTHROPIC_API_KEY found!")
-    print()
-    print("Testing requires a real API key to validate agent behavior.")
-    print()
-    print("Options:")
-    print("1. Set your API key (RECOMMENDED):")
-    print("   export ANTHROPIC_API_KEY='your-key-here'")
-    print()
-    print("2. Run in mock mode (structure validation only):")
-    print("   MOCK_MODE=1 pytest exports/{agent}/tests/")
-    print()
-    print("Mock mode does NOT test:")
-    print("  - LLM message generation")
-    print("  - Reasoning or decision quality")
-    print("  - Constraint validation")
-    print("  - Real API integrations")
-
-    # Ask user what to do
-    AskUserQuestion(...)
-```
-
-## The Three-Stage Flow
-
-```
-┌─────────────────────────────────────────────────────────────────────────┐
-│                           GOAL STAGE                                     │
-│  (building-agents skill)                                                 │
-│                                                                          │
-│  1. User defines goal with success_criteria and constraints             │
-│  2. Goal written to agent.py immediately                                │
-│  3. Generate CONSTRAINT TESTS → Write to tests/ → USER APPROVAL         │
-│     Files created: exports/{agent}/tests/test_constraints.py            │
-└─────────────────────────────────────────────────────────────────────────┘
-                                   ↓
-┌─────────────────────────────────────────────────────────────────────────┐
-│                          AGENT STAGE                                     │
-│  (building-agents skill)                                                 │
-│                                                                          │
-│  Build nodes + edges, written immediately to files                      │
-│  Constraint tests can run during development:                           │
-│    run_tests(goal_id, agent_path, test_types='["constraint"]')          │
-└─────────────────────────────────────────────────────────────────────────┘
-                                   ↓
-┌─────────────────────────────────────────────────────────────────────────┐
-│                           EVAL STAGE (this skill)                        │
-│                                                                          │
-│  1. Generate SUCCESS_CRITERIA TESTS → Write to tests/ → USER APPROVAL   │
-│     Files created: exports/{agent}/tests/test_success_criteria.py       │
-│  2. Run all tests: run_tests(goal_id, agent_path)                       │
-│  3. On failure → debug_test(goal_id, test_name, agent_path)             │
-│  4. Iterate: Edit agent code → Re-run run_tests (instant feedback)      │
-└─────────────────────────────────────────────────────────────────────────┘
-```
-
-## Step-by-Step: Testing an Agent
-
-### Step 1: Check Existing Tests
-
-**ALWAYS check first** before generating new tests:
-
-```python
-mcp__agent-builder__list_tests(
-    goal_id="your-goal-id",
-    agent_path="exports/your_agent"
-)
-```
-
-This shows what test files already exist. If tests exist:
-- Review the list to see what's covered
-- Ask user if they want to add more or run existing tests
-
-### Step 2: Generate Constraint Tests (Goal Stage)
-
-After goal is defined, generate constraint tests using the MCP tool:
-
-```python
-# First, read the goal from agent.py to get the goal JSON
-goal_code = Read(file_path="exports/your_agent/agent.py")
-# Extract the goal definition and convert to JSON
-
-# Generate constraint tests via MCP tool
-mcp__agent-builder__generate_constraint_tests(
-    goal_id="your-goal-id",
-    goal_json='{"id": "goal-id", "name": "...", "constraints": [...]}',
-    agent_path="exports/your_agent"
-)
-```
-
-**Response includes:**
-- `generated_count`: Number of tests generated
-- `tests`: List with id, test_name, description, confidence, test_code_preview
-- `next_step`: "Call approve_tests to approve, modify, or reject each test"
-- `output_file`: Where tests will be written when approved
-
-**USER APPROVAL REQUIRED**: Review generated tests and approve:
-
-```python
-# Review pending tests
-mcp__agent-builder__get_pending_tests(goal_id="your-goal-id")
-
-# Approve tests (this writes them to files)
-mcp__agent-builder__approve_tests(
-    goal_id="your-goal-id",
-    approvals='[{"test_id": "test-1", "action": "approve"}, {"test_id": "test-2", "action": "approve"}]'
-)
-```
-
-**Approval actions:**
-- `approve` - Accept test as-is, write to file
-- `modify` - Accept with changes: `{"test_id": "...", "action": "modify", "modified_code": "..."}`
-- `reject` - Reject with reason: `{"test_id": "...", "action": "reject", "reason": "..."}`
-- `skip` - Skip for now
-
-### Step 3: Generate Success Criteria Tests (Eval Stage)
-
-After agent is fully built, generate success criteria tests:
-
-```python
-# Generate success criteria tests via MCP tool
-mcp__agent-builder__generate_success_tests(
-    goal_id="your-goal-id",
-    goal_json='{"id": "goal-id", "name": "...", "success_criteria": [...]}',
-    node_names="analyze_request,search_web,format_results",
-    tool_names="web_search,web_scrape",
-    agent_path="exports/your_agent"
-)
-```
-
-**USER APPROVAL REQUIRED**: Same approval flow as constraint tests:
-
-```python
-# Review and approve
-mcp__agent-builder__get_pending_tests(goal_id="your-goal-id")
-mcp__agent-builder__approve_tests(
-    goal_id="your-goal-id",
-    approvals='[{"test_id": "...", "action": "approve"}]'
-)
-```
-
-### Step 4: Test Fixtures (conftest.py)
-
-**conftest.py is auto-created** when you approve tests via `approve_tests`. It includes:
-- API key enforcement fixtures
-- `mock_mode` fixture
-- `credentials` fixture
-- `sample_inputs` fixture
-
-You do NOT need to create conftest.py manually - the MCP tool handles this.
-
-### Step 5: Run Tests
-
-**Use the MCP tool to run tests** (not pytest directly):
-
-```python
-mcp__agent-builder__run_tests(
-    goal_id="your-goal-id",
-    agent_path="exports/your_agent"
-)
-
-**Response includes structured results:**
-```json
-{
-  "goal_id": "your-goal-id",
-  "overall_passed": false,
-  "summary": {
-    "total": 12,
-    "passed": 10,
-    "failed": 2,
-    "skipped": 0,
-    "errors": 0,
-    "pass_rate": "83.3%"
-  },
-  "test_results": [
-    {"file": "test_constraints.py", "test_name": "test_constraint_api_rate_limits", "status": "passed"},
-    {"file": "test_success_criteria.py", "test_name": "test_success_find_relevant_results", "status": "failed"}
-  ],
-  "failures": [
-    {"test_name": "test_success_find_relevant_results", "details": "AssertionError: Expected 3-5 results..."}
-  ]
-}
-```
-
-**Options for `run_tests`:**
-```python
-# Run only constraint tests
-mcp__agent-builder__run_tests(
-    goal_id="your-goal-id",
-    agent_path="exports/your_agent",
-    test_types='["constraint"]'
-)
-
-# Run with parallel workers
-mcp__agent-builder__run_tests(
-    goal_id="your-goal-id",
-    agent_path="exports/your_agent",
-    parallel=4
-)
-
-# Stop on first failure
-mcp__agent-builder__run_tests(
-    goal_id="your-goal-id",
-    agent_path="exports/your_agent",
-    fail_fast=True
-)
-```
-
-### Step 6: Debug Failed Tests
-
-**Use the MCP tool to debug** (not Bash/pytest directly):
-
-```python
-mcp__agent-builder__debug_test(
-    goal_id="your-goal-id",
-    test_name="test_success_find_relevant_results",
-    agent_path="exports/your_agent"
-)
-```
-
-**Response includes:**
-- Full verbose output from the test
-- Stack trace with exact line numbers
-- Captured logs and prints
-- Suggestions for fixing the issue
-
-### Step 7: Categorize Errors
-
-When a test fails, categorize the error to guide iteration:
-
-```python
-def categorize_test_failure(test_output, agent_code):
-    """Categorize test failure to guide iteration."""
-
-    # Read test output and agent code
-    failure_info = {
-        "test_name": "...",
-        "error_message": "...",
-        "stack_trace": "...",
-    }
-
-    # Pattern-based categorization
-    if any(pattern in failure_info["error_message"].lower() for pattern in [
-        "typeerror", "attributeerror", "keyerror", "valueerror",
-        "null", "none", "undefined", "tool call failed"
-    ]):
-        category = "IMPLEMENTATION_ERROR"
-        guidance = {
-            "stage": "Agent",
-            "action": "Fix the bug in agent code",
-            "files_to_edit": ["agent.py", "nodes/__init__.py"],
-            "restart_required": False,
-            "description": "Code bug - fix and re-run tests"
-        }
-
-    elif any(pattern in failure_info["error_message"].lower() for pattern in [
-        "assertion", "expected", "got", "should be", "success criteria"
-    ]):
-        category = "LOGIC_ERROR"
-        guidance = {
-            "stage": "Goal",
-            "action": "Update goal definition",
-            "files_to_edit": ["agent.py (goal section)"],
-            "restart_required": True,
-            "description": "Goal definition is wrong - update and rebuild"
-        }
-
-    elif any(pattern in failure_info["error_message"].lower() for pattern in [
-        "timeout", "rate limit", "empty", "boundary", "edge case"
-    ]):
-        category = "EDGE_CASE"
-        guidance = {
-            "stage": "Eval",
-            "action": "Add edge case test and fix handling",
-            "files_to_edit": ["agent.py", "tests/test_edge_cases.py"],
-            "restart_required": False,
-            "description": "New scenario - add test and handle it"
-        }
-
-    else:
-        category = "UNKNOWN"
-        guidance = {
-            "stage": "Unknown",
-            "action": "Manual investigation required",
-            "restart_required": False
-        }
-
-    return {
-        "category": category,
-        "guidance": guidance,
-        "failure_info": failure_info
-    }
-```
-
-**Show categorization to user:**
-
-```python
-AskUserQuestion(
-    questions=[{
-        "question": f"Test failed with {category}. How would you like to proceed?",
-        "header": "Test Failure",
-        "options": [
-            {
-                "label": "Fix code directly (Recommended)" if category == "IMPLEMENTATION_ERROR" else "Update goal",
-                "description": guidance["description"]
-            },
-            {
-                "label": "Show detailed error info",
-                "description": "View full stack trace and logs"
-            },
-            {
-                "label": "Skip for now",
-                "description": "Continue with other tests"
-            }
-        ],
-        "multiSelect": false
-    }]
-)
-```
-
-### Step 8: Iterate Based on Error Category
-
-#### IMPLEMENTATION_ERROR → Fix Agent Code
-
-```python
-# 1. Show user the exact file and line that failed
-print(f"Error in: exports/{agent_name}/nodes/__init__.py:42")
-print(f"Issue: 'NoneType' object has no attribute 'get'")
-
-# 2. Read the problematic code
-code = Read(file_path=f"exports/{agent_name}/nodes/__init__.py")
-
-# 3. User can fix directly, or you suggest a fix:
-Edit(
-    file_path=f"exports/{agent_name}/nodes/__init__.py",
-    old_string="if results.get('videos'):",
-    new_string="if results and results.get('videos'):"
-)
-
-# 4. Re-run tests immediately (instant feedback!)
-mcp__agent-builder__run_tests(
-    goal_id="your-goal-id",
-    agent_path=f"exports/{agent_name}"
-)
-```
-
-#### LOGIC_ERROR → Update Goal
-
-```python
-# 1. Show user the goal definition
-goal_code = Read(file_path=f"exports/{agent_name}/agent.py")
-
-# 2. Discuss what needs to change in success_criteria or constraints
-
-# 3. Edit the goal
-Edit(
-    file_path=f"exports/{agent_name}/agent.py",
-    old_string='target="3-5 videos"',
-    new_string='target="1-5 videos"'  # More realistic
-)
-
-# 4. May need to regenerate agent nodes if goal changed significantly
-# This requires going back to building-agents skill
-```
-
-#### EDGE_CASE → Add Test and Fix
-
-```python
-# 1. Create new edge case test with API key enforcement
-edge_case_test = '''
-@pytest.mark.asyncio
-async def test_edge_case_empty_results(mock_mode):
-    """Test: Agent handles no results gracefully"""
-    result = await default_agent.run({{"query": "xyzabc123nonsense"}}, mock_mode=mock_mode)
-
-    # Should succeed with empty results, not crash
-    assert result.success or result.error is not None
-    if result.success:
-        assert result.output.get("message") == "No results found"
-'''
-
-# 2. Add to test file
-Edit(
-    file_path=f"exports/{agent_name}/tests/test_edge_cases.py",
-    old_string="# Add edge case tests here",
-    new_string=edge_case_test
-)
-
-# 3. Fix agent to handle edge case
-# Edit agent code to handle empty results
-
-# 4. Re-run tests
-```
-
-## Test File Templates (Reference Only)
-
-**⚠️ Do NOT copy-paste these templates directly.** Use `generate_constraint_tests` and `generate_success_tests` MCP tools to create properly structured tests with correct imports and fixtures.
-
-These templates show the structure of generated tests for reference only.
-
-### Constraint Test Template
-
-```python
-"""Constraint tests for {agent_name}.
-
-These tests validate that the agent respects its defined constraints.
-Requires ANTHROPIC_API_KEY for real testing.
-"""
-
-import os
-import pytest
-from exports.{agent_name} import default_agent
-from aden_tools.credentials import CredentialManager
-
-
-# Enforce API key for real testing
-pytestmark = pytest.mark.skipif(
-    not CredentialManager().is_available("anthropic") and not os.environ.get("MOCK_MODE"),
-    reason="API key required. Set ANTHROPIC_API_KEY or use MOCK_MODE=1."
-)
-
-
-@pytest.mark.asyncio
-async def test_constraint_{constraint_id}():
-    """Test: {constraint_description}"""
-    # Test implementation based on constraint type
-    mock_mode = bool(os.environ.get("MOCK_MODE"))
-    result = await default_agent.run({{"test": "input"}}, mock_mode=mock_mode)
-
-    # Assert constraint is respected
-    assert True  # Replace with actual check
-```
-
-### Success Criteria Test Template
-
-```python
-"""Success criteria tests for {agent_name}.
-
-These tests validate that the agent achieves its defined success criteria.
-Requires ANTHROPIC_API_KEY for real testing - mock mode cannot validate success criteria.
-"""
-
-import os
-import pytest
-from exports.{agent_name} import default_agent
-from aden_tools.credentials import CredentialManager
-
-
-# Enforce API key for real testing
-pytestmark = pytest.mark.skipif(
-    not CredentialManager().is_available("anthropic") and not os.environ.get("MOCK_MODE"),
-    reason="API key required. Set ANTHROPIC_API_KEY or use MOCK_MODE=1."
-)
-
-
-@pytest.mark.asyncio
-async def test_success_{criteria_id}():
-    """Test: {criteria_description}"""
-    mock_mode = bool(os.environ.get("MOCK_MODE"))
-    result = await default_agent.run({{"test": "input"}}, mock_mode=mock_mode)
-
-    assert result.success, f"Agent failed: {{result.error}}"
-
-    # Verify success criterion met
-    # e.g., assert metric meets target
-    assert True  # Replace with actual check
-```
-
-### Edge Case Test Template
-
-```python
-"""Edge case tests for {agent_name}.
-
-These tests validate agent behavior in unusual or boundary conditions.
-Requires ANTHROPIC_API_KEY for real testing.
-"""
-
-import os
-import pytest
-from exports.{agent_name} import default_agent
-from aden_tools.credentials import CredentialManager
-
-
-# Enforce API key for real testing
-pytestmark = pytest.mark.skipif(
-    not CredentialManager().is_available("anthropic") and not os.environ.get("MOCK_MODE"),
-    reason="API key required. Set ANTHROPIC_API_KEY or use MOCK_MODE=1."
-)
-
-
-@pytest.mark.asyncio
-async def test_edge_case_{scenario_name}():
-    """Test: Agent handles {scenario_description}"""
-    mock_mode = bool(os.environ.get("MOCK_MODE"))
-    result = await default_agent.run({{"edge": "case_input"}}, mock_mode=mock_mode)
-
-    # Verify graceful handling
-    assert result.success or result.error is not None
-```
-
-## Interactive Build + Test Loop
-
-During agent construction (Agent stage), you can run constraint tests incrementally:
-
-```python
-# After adding first node
-print("Added search_node. Running relevant constraint tests...")
-mcp__agent-builder__run_tests(
-    goal_id="your-goal-id",
-    agent_path=f"exports/{agent_name}",
-    test_types='["constraint"]'
-)
-
-# After adding second node
-print("Added filter_node. Running all constraint tests...")
-mcp__agent-builder__run_tests(
-    goal_id="your-goal-id",
-    agent_path=f"exports/{agent_name}",
-    test_types='["constraint"]'
-)
-```
-
-This provides **immediate feedback** during development, catching issues early.
-
-## Common Test Patterns
-
-**Note:** All test patterns should include API key enforcement via conftest.py.
-
-### Happy Path Test
-```python
-@pytest.mark.asyncio
-async def test_happy_path(mock_mode):
-    """Test normal successful execution"""
-    result = await default_agent.run({{"query": "python tutorials"}}, mock_mode=mock_mode)
-    assert result.success
-    assert len(result.output) > 0
-```
-
-### Boundary Condition Test
-```python
-@pytest.mark.asyncio
-async def test_boundary_minimum(mock_mode):
-    """Test at minimum threshold"""
-    result = await default_agent.run({{"query": "very specific niche topic"}}, mock_mode=mock_mode)
-    assert result.success
-    assert len(result.output.get("results", [])) >= 1
-```
-
-### Error Handling Test
-```python
-@pytest.mark.asyncio
-async def test_error_handling(mock_mode):
-    """Test graceful error handling"""
-    result = await default_agent.run({{"query": ""}}, mock_mode=mock_mode)  # Invalid input
-    assert not result.success or result.output.get("error") is not None
-```
-
-### Performance Test
-```python
-@pytest.mark.asyncio
-async def test_performance_latency(mock_mode):
-    """Test response time is acceptable"""
-    import time
-    start = time.time()
-    result = await default_agent.run({{"query": "test"}}, mock_mode=mock_mode)
-    duration = time.time() - start
-    assert duration < 5.0, f"Took {{duration}}s, expected <5s"
-```
-
-## Integration with building-agents
-
-### Handoff Points
-
-| Scenario | From | To | Action |
-|----------|------|-----|--------|
-| Agent built, ready to test | building-agents | testing-agent | Generate success tests |
-| LOGIC_ERROR found | testing-agent | building-agents | Update goal, rebuild |
-| IMPLEMENTATION_ERROR found | testing-agent | Direct fix | Edit agent files, re-run tests |
-| EDGE_CASE found | testing-agent | testing-agent | Add edge case test |
-| All tests pass | testing-agent | Done | Agent validated ✅ |
-
-### Iteration Speed Comparison
-
-| Scenario | Old Approach | New Approach |
-|----------|--------------|--------------|
-| **Bug Fix** | Rebuild via MCP tools (14 min) | Edit Python file, pytest (2 min) |
-| **Add Test** | Generate via MCP, export (5 min) | Write test file directly (1 min) |
-| **Debug** | Read subprocess logs | pdb, breakpoints, prints |
-| **Inspect** | Limited visibility | Full Python introspection |
-
-## Anti-Patterns
-
-### MCP Tool Enforcement
-
-| Don't | Do Instead |
-|-------|------------|
-| ❌ Write test files with Write tool | ✅ Use `generate_*_tests` + `approve_tests` |
-| ❌ Run pytest via Bash | ✅ Use `run_tests` MCP tool |
-| ❌ Debug tests with Bash pytest -vvs | ✅ Use `debug_test` MCP tool |
-| ❌ Edit test files directly | ✅ Use `approve_tests` with `action: "modify"` |
-| ❌ Check for tests with Glob | ✅ Use `list_tests` MCP tool |
-
-### General Testing
-
-| Don't | Do Instead |
-|-------|------------|
-| ❌ Auto-approve generated tests | ✅ Always require user approval via approve_tests |
-| ❌ Treat all failures the same | ✅ Use debug_test to categorize and iterate appropriately |
-| ❌ Rebuild entire agent for small bugs | ✅ Edit code directly, re-run tests |
-| ❌ Run tests without API key | ✅ Always set ANTHROPIC_API_KEY first |
-| ❌ Skip user review of generated tests | ✅ Show test code to user before approving |
-
-## Workflow Summary
-
-```
-1. Check existing tests: list_tests(goal_id, agent_path)
-   → Scans exports/{agent}/tests/test_*.py
-   ↓
-2. Generate tests: generate_constraint_tests, generate_success_tests
-   → Returns pending tests (stored in memory)
-   ↓
-3. Review and approve: get_pending_tests → approve_tests → USER APPROVAL
-   → Writes approved tests to exports/{agent}/tests/test_*.py
-   ↓
-4. Run tests: run_tests(goal_id, agent_path)
-   → Executes: pytest exports/{agent}/tests/ -v
-   ↓
-5. Debug failures: debug_test(goal_id, test_name, agent_path)
-   → Re-runs single test with verbose output
-   ↓
-6. Fix based on category:
-   - IMPLEMENTATION_ERROR → Edit agent code directly
-   - ASSERTION_FAILURE → Fix agent logic or update test
-   - IMPORT_ERROR → Check package structure
-   - API_ERROR → Check API keys and connectivity
-   ↓
-7. Re-run tests: run_tests(goal_id, agent_path)
-   ↓
-8. Repeat until all pass ✅
-```
-
-## MCP Tools Reference
-
-```python
-# Check existing tests (scans Python test files)
-mcp__agent-builder__list_tests(
-    goal_id="your-goal-id",
-    agent_path="exports/your_agent"
-)
-
-# Generate constraint tests (returns pending tests for approval)
-mcp__agent-builder__generate_constraint_tests(
-    goal_id="your-goal-id",
-    goal_json='{"id": "...", "constraints": [...]}',
-    agent_path="exports/your_agent"
-)
-
-# Generate success criteria tests
-mcp__agent-builder__generate_success_tests(
-    goal_id="your-goal-id",
-    goal_json='{"id": "...", "success_criteria": [...]}',
-    node_names="node1,node2",
-    tool_names="tool1,tool2",
-    agent_path="exports/your_agent"
-)
-
-# Review pending tests
-mcp__agent-builder__get_pending_tests(goal_id="your-goal-id")
-
-# Approve tests → writes to Python files at exports/{agent}/tests/
-mcp__agent-builder__approve_tests(
-    goal_id="your-goal-id",
-    approvals='[{"test_id": "...", "action": "approve"}]'
-)
-
-# Run tests via pytest subprocess
-mcp__agent-builder__run_tests(
-    goal_id="your-goal-id",
-    agent_path="exports/your_agent"
-)
-
-# Debug a failed test (re-runs with verbose output)
-mcp__agent-builder__debug_test(
-    goal_id="your-goal-id",
-    test_name="test_constraint_foo",
-    agent_path="exports/your_agent"
-)
-```
-
-## run_tests Options
-
-```python
-# Run only constraint tests
-mcp__agent-builder__run_tests(
-    goal_id="your-goal-id",
-    agent_path="exports/your_agent",
-    test_types='["constraint"]'
-)
-
-# Run only success criteria tests
-mcp__agent-builder__run_tests(
-    goal_id="your-goal-id",
-    agent_path="exports/your_agent",
-    test_types='["success"]'
-)
-
-# Run with pytest-xdist parallelism (requires pytest-xdist)
-mcp__agent-builder__run_tests(
-    goal_id="your-goal-id",
-    agent_path="exports/your_agent",
-    parallel=4
-)
-
-# Stop on first failure
-mcp__agent-builder__run_tests(
-    goal_id="your-goal-id",
-    agent_path="exports/your_agent",
-    fail_fast=True
-)
-```
-
-## Direct pytest Commands
-
-You can also run tests directly with pytest (the MCP tools use pytest internally):
-
-```bash
-# Run all tests
-pytest exports/your_agent/tests/ -v
-
-# Run specific test file
-pytest exports/your_agent/tests/test_constraints.py -v
-
-# Run specific test
-pytest exports/your_agent/tests/test_constraints.py::test_constraint_foo -vvs
-
-# Run in mock mode (structure validation only)
-MOCK_MODE=1 pytest exports/your_agent/tests/ -v
-```
-
----
-
-**MCP tools generate tests, write them to Python files, and run them via pytest.**

.claude/skills/testing-agent/examples/testing-youtube-agent.md

@@ -1,348 +0,0 @@
-# Example: Testing a YouTube Research Agent
-
-This example walks through testing a YouTube research agent that finds relevant videos based on a topic.
-
-## Prerequisites
-
-- Agent built with building-agents skill at `exports/youtube-research/`
-- Goal defined with success criteria and constraints
-
-## Step 1: Load the Goal
-
-First, load the goal that was defined during the Goal stage:
-
-```json
-{
-    "id": "youtube-research",
-    "name": "YouTube Research Agent",
-    "description": "Find relevant YouTube videos on a given topic",
-    "success_criteria": [
-        {
-            "id": "find_videos",
-            "description": "Find 3-5 relevant videos",
-            "metric": "video_count",
-            "target": "3-5",
-            "weight": 1.0
-        },
-        {
-            "id": "relevance",
-            "description": "Videos must be relevant to the topic",
-            "metric": "relevance_score",
-            "target": ">0.8",
-            "weight": 0.8
-        }
-    ],
-    "constraints": [
-        {
-            "id": "api_limits",
-            "description": "Must not exceed YouTube API rate limits",
-            "constraint_type": "hard",
-            "category": "technical"
-        },
-        {
-            "id": "content_safety",
-            "description": "Must filter out inappropriate content",
-            "constraint_type": "hard",
-            "category": "safety"
-        }
-    ]
-}
-```
-
-## Step 2: Generate Constraint Tests
-
-During the Goal stage (or early Eval), generate tests for constraints:
-
-```python
-result = generate_constraint_tests(
-    goal_id="youtube-research",
-    goal_json='<goal JSON above>'
-)
-```
-
-**Generated tests (awaiting approval):**
-
-```
-┌─────────────────────────────────────────────────────────────────┐
-│ Generated Constraint Tests (2 tests)                             │
-├─────────────────────────────────────────────────────────────────┤
-│ [1/2] test_constraint_api_limits_respected                       │
-│       Constraint: api_limits                                     │
-│       Confidence: 88%                                            │
-│                                                                  │
-│       def test_constraint_api_limits_respected(agent):           │
-│           """Verify API rate limits are not exceeded."""         │
-│           import time                                            │
-│           for i in range(10):                                    │
-│               result = agent.run({"topic": f"test_{i}"})         │
-│               time.sleep(0.1)                                    │
-│           # Should complete without rate limit errors            │
-│           assert "rate limit" not in str(result).lower()         │
-│                                                                  │
-│       [a]pprove  [r]eject  [e]dit  [s]kip                       │
-├─────────────────────────────────────────────────────────────────┤
-│ [2/2] test_constraint_content_safety_filter                      │
-│       Constraint: content_safety                                 │
-│       Confidence: 91%                                            │
-│                                                                  │
-│       def test_constraint_content_safety_filter(agent):          │
-│           """Verify inappropriate content is filtered."""        │
-│           result = agent.run({"topic": "general topic"})         │
-│           for video in result.videos:                            │
-│               assert video.safe_for_work is True                 │
-│               assert video.age_restricted is False               │
-│                                                                  │
-│       [a]pprove  [r]eject  [e]dit  [s]kip                       │
-└─────────────────────────────────────────────────────────────────┘
-```
-
-## Step 3: Approve Constraint Tests
-
-Review and approve each test:
-
-```python
-result = approve_tests(
-    goal_id="youtube-research",
-    approvals='[
-        {"test_id": "test_constraint_api_001", "action": "approve"},
-        {"test_id": "test_constraint_content_001", "action": "approve"}
-    ]'
-)
-```
-
-## Step 4: Generate Success Criteria Tests
-
-After the agent is built, generate success criteria tests:
-
-```python
-result = generate_success_tests(
-    goal_id="youtube-research",
-    goal_json='<goal JSON>',
-    node_names="search_node,filter_node,rank_node,format_node",
-    tool_names="youtube_search,video_details,channel_info"
-)
-```
-
-**Generated tests (awaiting approval):**
-
-```
-┌─────────────────────────────────────────────────────────────────┐
-│ Generated Success Criteria Tests (4 tests)                       │
-├─────────────────────────────────────────────────────────────────┤
-│ [1/4] test_find_videos_happy_path                               │
-│       Criteria: find_videos                                      │
-│       Confidence: 95%                                            │
-│                                                                  │
-│       def test_find_videos_happy_path(agent):                    │
-│           """Test finding videos for a common topic."""          │
-│           result = agent.run({"topic": "machine learning"})      │
-│           assert result.success                                  │
-│           assert 3 <= len(result.videos) <= 5                    │
-│           assert all(v.title for v in result.videos)             │
-│           assert all(v.video_id for v in result.videos)          │
-│                                                                  │
-│       [a]pprove  [r]eject  [e]dit  [s]kip                       │
-├─────────────────────────────────────────────────────────────────┤
-│ [2/4] test_find_videos_minimum_boundary                          │
-│       Criteria: find_videos                                      │
-│       Confidence: 87%                                            │
-│                                                                  │
-│       def test_find_videos_minimum_boundary(agent):              │
-│           """Test at minimum threshold (3 videos)."""            │
-│           result = agent.run({"topic": "niche topic xyz"})       │
-│           assert len(result.videos) >= 3                         │
-│                                                                  │
-│       [a]pprove  [r]eject  [e]dit  [s]kip                       │
-├─────────────────────────────────────────────────────────────────┤
-│ [3/4] test_relevance_score_threshold                             │
-│       Criteria: relevance                                        │
-│       Confidence: 92%                                            │
-│                                                                  │
-│       def test_relevance_score_threshold(agent):                 │
-│           """Test relevance scoring meets threshold."""          │
-│           result = agent.run({"topic": "python programming"})    │
-│           for video in result.videos:                            │
-│               assert video.relevance_score > 0.8                 │
-│                                                                  │
-│       [a]pprove  [r]eject  [e]dit  [s]kip                       │
-├─────────────────────────────────────────────────────────────────┤
-│ [4/4] test_find_videos_no_results_graceful                       │
-│       Criteria: find_videos                                      │
-│       Confidence: 84%                                            │
-│                                                                  │
-│       def test_find_videos_no_results_graceful(agent):           │
-│           """Test graceful handling of no results."""            │
-│           result = agent.run({"topic": "xyznonexistent123"})     │
-│           # Should not crash, return empty or message            │
-│           assert result.videos == [] or result.message           │
-│                                                                  │
-│       [a]pprove  [r]eject  [e]dit  [s]kip                       │
-└─────────────────────────────────────────────────────────────────┘
-```
-
-## Step 5: Approve Success Criteria Tests
-
-```python
-result = approve_tests(
-    goal_id="youtube-research",
-    approvals='[
-        {"test_id": "test_success_001", "action": "approve"},
-        {"test_id": "test_success_002", "action": "approve"},
-        {"test_id": "test_success_003", "action": "approve"},
-        {"test_id": "test_success_004", "action": "approve"}
-    ]'
-)
-```
-
-## Step 6: Run All Tests
-
-Execute all approved tests:
-
-```python
-result = run_tests(
-    goal_id="youtube-research",
-    agent_path="exports/youtube-research",
-    test_types='["all"]',
-    parallel=4
-)
-```
-
-**Results:**
-
-```json
-{
-    "goal_id": "youtube-research",
-    "overall_passed": false,
-    "summary": {
-        "total": 6,
-        "passed": 5,
-        "failed": 1,
-        "pass_rate": "83.3%"
-    },
-    "duration_ms": 4521,
-    "results": [
-        {"test_id": "test_constraint_api_001", "passed": true, "duration_ms": 1234},
-        {"test_id": "test_constraint_content_001", "passed": true, "duration_ms": 456},
-        {"test_id": "test_success_001", "passed": true, "duration_ms": 789},
-        {"test_id": "test_success_002", "passed": true, "duration_ms": 654},
-        {"test_id": "test_success_003", "passed": true, "duration_ms": 543},
-        {"test_id": "test_success_004", "passed": false, "duration_ms": 845,
-         "error_category": "IMPLEMENTATION_ERROR",
-         "error_message": "TypeError: 'NoneType' object has no attribute 'videos'"}
-    ]
-}
-```
-
-## Step 7: Debug the Failed Test
-
-```python
-result = debug_test(
-    goal_id="youtube-research",
-    test_id="test_success_004"
-)
-```
-
-**Debug Output:**
-
-```json
-{
-    "test_id": "test_success_004",
-    "test_name": "test_find_videos_no_results_graceful",
-    "input": {"topic": "xyznonexistent123"},
-    "expected": "Empty list or message",
-    "actual": {"error": "TypeError: 'NoneType' object has no attribute 'videos'"},
-    "passed": false,
-    "error_message": "TypeError: 'NoneType' object has no attribute 'videos'",
-    "error_category": "IMPLEMENTATION_ERROR",
-    "stack_trace": "Traceback (most recent call last):\n  File \"filter_node.py\", line 42\n    for video in result.videos:\nTypeError: 'NoneType' object has no attribute 'videos'",
-    "logs": [
-        {"timestamp": "2026-01-20T10:00:01", "node": "search_node", "level": "INFO", "msg": "Searching for: xyznonexistent123"},
-        {"timestamp": "2026-01-20T10:00:02", "node": "search_node", "level": "WARNING", "msg": "No results found"},
-        {"timestamp": "2026-01-20T10:00:02", "node": "filter_node", "level": "ERROR", "msg": "NoneType error"}
-    ],
-    "runtime_data": {
-        "execution_path": ["start", "search_node", "filter_node"],
-        "node_outputs": {
-            "search_node": null
-        }
-    },
-    "suggested_fix": "Add null check in filter_node before accessing .videos attribute",
-    "iteration_guidance": {
-        "stage": "Agent",
-        "action": "Fix the code in nodes/edges",
-        "restart_required": false,
-        "description": "The goal is correct, but filter_node doesn't handle null results from search_node."
-    }
-}
-```
-
-## Step 8: Iterate Based on Category
-
-Since this is an **IMPLEMENTATION_ERROR**, we:
-
-1. **Don't restart** the Goal → Agent → Eval flow
-2. **Fix the agent** using building-agents skill:
-   - Modify `filter_node` to handle null results
-3. **Re-run Eval** (tests only)
-
-### Fix in building-agents:
-
-```python
-# Update the filter_node to handle null
-add_node(
-    node_id="filter_node",
-    name="Filter Node",
-    description="Filter and rank videos",
-    node_type="function",
-    input_keys=["search_results"],
-    output_keys=["filtered_videos"],
-    system_prompt="""
-    Filter videos by relevance.
-    IMPORTANT: Handle case where search_results is None or empty.
-    Return empty list if no results.
-    """
-)
-```
-
-### Re-export and re-test:
-
-```python
-# Re-export the fixed agent
-export_graph(path="exports/youtube-research")
-
-# Re-run tests
-result = run_tests(
-    goal_id="youtube-research",
-    agent_path="exports/youtube-research",
-    test_types='["all"]'
-)
-```
-
-**Updated Results:**
-
-```json
-{
-    "goal_id": "youtube-research",
-    "overall_passed": true,
-    "summary": {
-        "total": 6,
-        "passed": 6,
-        "failed": 0,
-        "pass_rate": "100.0%"
-    }
-}
-```
-
-## Summary
-
-1. **Generated** constraint tests during Goal stage
-2. **Generated** success criteria tests during Eval stage
-3. **Approved** all tests with user review
-4. **Ran** tests in parallel
-5. **Debugged** the one failure
-6. **Categorized** as IMPLEMENTATION_ERROR
-7. **Fixed** the agent (not the goal)
-8. **Re-ran** Eval only (didn't restart full flow)
-9. **Passed** all tests
-
-The agent is now validated and ready for production use.

.claude/skills/triage-issue/SKILL.md

@@ -0,0 +1,145 @@
+# Triage Issue Skill
+
+Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.
+
+## Trigger
+
+User provides a GitHub issue URL or number, e.g.:
+- `/triage-issue 1970`
+- `/triage-issue https://github.com/adenhq/hive/issues/1970`
+
+## Workflow
+
+### Step 1: Fetch Issue Details
+
+```bash
+gh issue view <number> --repo adenhq/hive --json title,body,state,labels,author
+```
+
+Extract:
+- Title
+- Body (the claim/bug report)
+- Current state
+- Labels
+- Author
+
+If issue is already closed, inform user and stop.
+
+### Step 2: Analyze the Claim
+
+Read the issue body and identify:
+1. **The core claim** - What is the user asserting?
+2. **Technical specifics** - File paths, function names, code snippets mentioned
+3. **Expected behavior** - What do they think should happen?
+4. **Severity claimed** - Security issue? Bug? Feature request?
+
+### Step 3: Investigate the Codebase
+
+For each technical claim:
+1. Find the referenced code using Grep/Glob/Read
+2. Understand the actual implementation
+3. Check if the claim accurately describes the behavior
+4. Look for related tests, documentation, or design decisions
+
+### Step 4: Evaluate Validity
+
+Categorize the issue as one of:
+
+| Category | Action |
+|----------|--------|
+| **Valid Bug** | Do NOT close. Inform user this is a real issue. |
+| **Valid Feature Request** | Do NOT close. Suggest labeling appropriately. |
+| **Misunderstanding** | Prepare technical explanation for why behavior is correct. |
+| **Fundamentally Flawed** | Prepare critique explaining the technical impossibility or design rationale. |
+| **Duplicate** | Find the original issue and prepare duplicate notice. |
+| **Incomplete** | Prepare request for more information. |
+
+### Step 5: Draft Response
+
+For issues to be closed, draft a response that:
+
+1. **Acknowledges the concern** - Don't be dismissive
+2. **Explains the actual behavior** - With code references
+3. **Provides technical rationale** - Why it works this way
+4. **References industry standards** - If applicable
+5. **Offers alternatives** - If there's a better approach for the user
+
+Use this template:
+
+```markdown
+## Analysis
+
+[Brief summary of what was investigated]
+
+## Technical Details
+
+[Explanation with code references]
+
+## Why This Is Working As Designed
+
+[Rationale]
+
+## Recommendation
+
+[What the user should do instead, if applicable]
+
+---
+*This issue was reviewed and closed by the maintainers.*
+```
+
+### Step 6: User Review
+
+Present the draft to the user with:
+
+```
+## Issue #<number>: <title>
+
+**Claim:** <summary of claim>
+
+**Finding:** <valid/invalid/misunderstanding/etc>
+
+**Draft Response:**
+<the markdown response>
+
+---
+Do you want me to post this comment and close the issue?
+```
+
+Use AskUserQuestion with options:
+- "Post and close" - Post comment, close issue
+- "Edit response" - Let user modify the response
+- "Skip" - Don't take action
+
+### Step 7: Execute Action
+
+If user approves:
+
+```bash
+# Post comment
+gh issue comment <number> --repo adenhq/hive --body "<response>"
+
+# Close issue
+gh issue close <number> --repo adenhq/hive --reason "not planned"
+```
+
+Report success with link to the issue.
+
+## Important Guidelines
+
+1. **Never close valid issues** - If there's any merit to the claim, don't close it
+2. **Be respectful** - The reporter took time to file the issue
+3. **Be technical** - Provide code references and evidence
+4. **Be educational** - Help them understand, don't just dismiss
+5. **Check twice** - Make sure you understand the code before declaring something invalid
+6. **Consider edge cases** - Maybe their environment reveals a real issue
+
+## Example Critiques
+
+### Security Misunderstanding
+> "The claim that secrets are exposed in plaintext misunderstands the encryption architecture. While `SecretStr` is used for logging protection, actual encryption is provided by Fernet (AES-128-CBC) at the storage layer. The code path is: serialize → encrypt → write. Only encrypted bytes touch disk."
+
+### Impossible Request
+> "The requested feature would require [X] which violates [fundamental constraint]. This is not a limitation of our implementation but a fundamental property of [technology/protocol]."
+
+### Already Handled
+> "This scenario is already handled by [code reference]. The reporter may be using an older version or misconfigured environment."

.codex/config.toml

@@ -0,0 +1,7 @@
+# Project-level Codex config for Hive.
+# Keep this file minimal: MCP connectivity + skill discovery.
+
+[mcp_servers.agent-builder]
+command = "uv"
+args = ["run", "--directory", "core", "-m", "framework.mcp.agent_builder_server"]
+cwd = "."

.cursor/mcp.json

@@ -0,0 +1,20 @@
+{
+  "mcpServers": {
+    "agent-builder": {
+      "command": "python",
+      "args": ["-m", "framework.mcp.agent_builder_server"],
+      "cwd": "core",
+      "env": {
+        "PYTHONPATH": "../tools/src"
+      }
+    },
+    "tools": {
+      "command": "python",
+      "args": ["mcp_server.py", "--stdio"],
+      "cwd": "tools",
+      "env": {
+        "PYTHONPATH": "src"
+      }
+    }
+  }
+}

.cursor/skills/hive

@@ -0,0 +1 @@
+../../.claude/skills/hive

.cursor/skills/hive-concepts

@@ -0,0 +1 @@
+../../.claude/skills/hive-concepts

.cursor/skills/hive-create

@@ -0,0 +1 @@
+../../.claude/skills/hive-create

.cursor/skills/hive-credentials

@@ -0,0 +1 @@
+../../.claude/skills/hive-credentials

.cursor/skills/hive-patterns

@@ -0,0 +1 @@
+../../.claude/skills/hive-patterns

.cursor/skills/hive-test

@@ -0,0 +1 @@
+../../.claude/skills/hive-test

.cursorrules

@@ -0,0 +1,18 @@
+This project uses ruff for Python linting and formatting.
+
+Rules:
+- Line length: 100 characters
+- Python target: 3.11+
+- Use double quotes for strings
+- Sort imports with isort (ruff I rules): stdlib, third-party, first-party (framework), local
+- Combine as-imports
+- Use type hints on all function signatures
+- Use `from __future__ import annotations` for modern type syntax
+- Raise exceptions with `from` in except blocks (B904)
+- No unused imports (F401), no unused variables (F841)
+- Prefer list/dict/set comprehensions over map/filter (C4)
+
+Run `make lint` to auto-fix, `make check` to verify without modifying files.
+Run `make format` to apply ruff formatting.
+
+The ruff config lives in core/pyproject.toml under [tool.ruff].

.editorconfig

@@ -11,6 +11,9 @@ indent_size = 2
 insert_final_newline = true
 trim_trailing_whitespace = true
 
+[*.py]
+indent_size = 4
+
 [*.md]
 trim_trailing_whitespace = false
 

.gitattributes

@@ -0,0 +1,124 @@
+# Normalize line endings for all text files
+* text=auto
+
+# Source code
+*.py text diff=python
+*.js text
+*.ts text
+*.jsx text
+*.tsx text
+*.json text
+*.yaml text
+*.yml text
+*.toml text
+*.ini text
+*.cfg text
+
+# Shell scripts (must use LF)
+*.sh text eol=lf
+quickstart.sh text eol=lf
+
+# PowerShell scripts (Windows-friendly)
+*.ps1 text eol=lf
+*.psm1 text eol=lf
+
+# Windows batch files (must use CRLF)
+*.bat text eol=crlf
+*.cmd text eol=crlf
+
+# Documentation
+*.md text
+*.txt text
+*.rst text
+*.tex text
+
+# Configuration files
+.gitignore text
+.gitattributes text
+.editorconfig text
+Dockerfile text
+docker-compose.yml text
+requirements*.txt text
+pyproject.toml text
+setup.py text
+setup.cfg text
+MANIFEST.in text
+LICENSE text
+README* text
+CHANGELOG* text
+CONTRIBUTING* text
+CODE_OF_CONDUCT* text
+
+# Web files
+*.html text
+*.css text
+*.scss text
+*.sass text
+
+# Data files
+*.xml text
+*.csv text
+*.sql text
+
+# Graphics (binary)
+*.png binary
+*.jpg binary
+*.jpeg binary
+*.gif binary
+*.ico binary
+*.svg binary
+*.eps binary
+*.bmp binary
+*.tif binary
+*.tiff binary
+
+# Archives (binary)
+*.zip binary
+*.tar binary
+*.gz binary
+*.bz2 binary
+*.7z binary
+*.rar binary
+
+# Python compiled (binary)
+*.pyc binary
+*.pyo binary
+*.pyd binary
+*.whl binary
+*.egg binary
+
+# System libraries (binary)
+*.so binary
+*.dll binary
+*.dylib binary
+*.lib binary
+*.a binary
+
+# Documents (binary)
+*.pdf binary
+*.doc binary
+*.docx binary
+*.ppt binary
+*.pptx binary
+*.xls binary
+*.xlsx binary
+
+# Fonts (binary)
+*.ttf binary
+*.otf binary
+*.woff binary
+*.woff2 binary
+*.eot binary
+
+# Audio/Video (binary)
+*.mp3 binary
+*.mp4 binary
+*.wav binary
+*.avi binary
+*.mov binary
+*.flv binary
+
+# Database files (binary)
+*.db binary
+*.sqlite binary
+*.sqlite3 binary

.github/CODEOWNERS

@@ -8,7 +8,6 @@
 /hive/ @adenhq/maintainers
 
 # Infrastructure
-/docker-compose*.yml @adenhq/maintainers
 /.github/ @adenhq/maintainers
 
 # Documentation

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,9 +1,10 @@
 ---
 name: Bug Report
 about: Report a bug to help us improve
-title: '[Bug]: '
-labels: bug
+title: "[Bug]: "
+labels: bug, enhancement
 assignees: ''
+
 ---
 
 ## Describe the Bug

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,9 +1,10 @@
 ---
 name: Feature Request
 about: Suggest a new feature or enhancement
-title: '[Feature]: '
+title: "[Feature]: "
 labels: enhancement
 assignees: ''
+
 ---
 
 ## Problem Statement

.github/ISSUE_TEMPLATE/integration-request.md

@@ -0,0 +1,71 @@
+---
+name: Integration Request
+about: Suggest a new integration
+title: "[Integration]:"
+labels: ''
+assignees: ''
+
+---
+
+## Service                                                                                      
+                                                                                                 
+ Name and brief description of the service and what it enables agents to do.                     
+                                                                                                 
+ **Description:** [e.g., "API key for Slack Bot" — short one-liner for the credential spec]      
+                                                                                                 
+ ## Credential Identity                                                                          
+                                                                                                 
+ - **credential_id:** [e.g., `slack`]                                                            
+ - **env_var:** [e.g., `SLACK_BOT_TOKEN`]                                                        
+ - **credential_key:** [e.g., `access_token`, `api_key`, `bot_token`]                            
+                                                                                                 
+ ## Tools                                                                                        
+                                                                                                 
+ Tool function names that require this credential:                                               
+                                                                                                 
+ - [e.g., `slack_send_message`]                                                                  
+ - [e.g., `slack_list_channels`]                                                                 
+                                                                                                 
+ ## Auth Methods                                                                                 
+                                                                                                 
+ - **Direct API key supported:** Yes / No                                                        
+ - **Aden OAuth supported:** Yes / No                                                            
+                                                                                                 
+ If Aden OAuth is supported, describe the OAuth scopes/permissions required.                     
+                                                                                                 
+ ## How to Get the Credential                                                                    
+                                                                                                 
+ Link where users obtain the key/token:                                                          
+                                                                                                 
+ [e.g., https://api.slack.com/apps]                                                              
+                                                                                                 
+ Step-by-step instructions:                                                                      
+                                                                                                 
+ 1. Go to ...                                                                                    
+ 2. Create a ...                                                                                 
+ 3. Select scopes/permissions: ...                                                               
+ 4. Copy the key/token                                                                           
+                                                                                                 
+ ## Health Check                                                                                 
+                                                                                                 
+ A lightweight API call to validate the credential (no writes, no charges).                      
+                                                                                                 
+ - **Endpoint:** [e.g., `https://slack.com/api/auth.test`]                                       
+ - **Method:** [e.g., `GET` or `POST`]                                                           
+ - **Auth header:** [e.g., `Authorization: Bearer {token}` or `X-Api-Key: {key}`]                
+ - **Parameters (if any):** [e.g., `?limit=1`]                                                   
+ - **200 means:** [e.g., key is valid]                                                           
+ - **401 means:** [e.g., invalid or expired]                                                     
+ - **429 means:** [e.g., rate limited but key is valid]                                          
+                                                                                                 
+ ## Credential Group                                                                             
+                                                                                                 
+ Does this require multiple credentials configured together? (e.g., Google Custom Search needs   
+ both an API key and a CSE ID)                                                                   
+                                                                                                 
+ - [ ] No, single credential                                                                     
+ - [ ] Yes — list the other credential IDs in the group:                                         
+                                                                                                 
+ ## Additional Context                                                                           
+                                                                                                 
+ Links to API docs, rate limits, free tier availability, or anything else relevant.

.github/workflows/auto-close-duplicates.yml

@@ -0,0 +1,34 @@
+name: Auto-close duplicate issues
+description: Auto-closes issues that are duplicates of existing issues
+on:
+  schedule:
+    - cron: "0 */6 * * *"
+  workflow_dispatch:
+
+jobs:
+  auto-close-duplicates:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Setup Bun
+        uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+
+      - name: Run auto-close-duplicates tests
+        run: bun test scripts/auto-close-duplicates
+
+      - name: Auto-close duplicate issues
+        run: bun run scripts/auto-close-duplicates.ts
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_REPOSITORY_OWNER: ${{ github.repository_owner }}
+          GITHUB_REPOSITORY_NAME: ${{ github.event.repository.name }}
+          STATSIG_API_KEY: ${{ secrets.STATSIG_API_KEY }}

.github/workflows/ci.yml

@@ -21,21 +21,48 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: '3.11'
-          cache: 'pip'
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
 
       - name: Install dependencies
-        run: |
-          cd core
-          pip install -e .
-          pip install -r requirements-dev.txt
+        run: uv sync --project core --group dev
 
-      - name: Run ruff
+      - name: Ruff lint
         run: |
-          cd core
-          ruff check .
+          uv run --project core ruff check core/
+          uv run --project core ruff check tools/
+
+      - name: Ruff format
+        run: |
+          uv run --project core ruff format --check core/
+          uv run --project core ruff format --check tools/
 
   test:
     name: Test Python Framework
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-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 core
+          uv sync
+          uv run pytest tests/ -v
+
+  test-tools:
+    name: Test Tools
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
@@ -44,23 +71,20 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: '3.11'
-          cache: 'pip'
 
-      - name: Install dependencies
-        run: |
-          cd core
-          pip install -e .
-          pip install -r requirements-dev.txt
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
 
-      - name: Run tests
+      - name: Install dependencies and run tests
         run: |
-          cd core
-          pytest tests/ -v
+          cd tools
+          uv sync --extra dev
+          uv run 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
 
@@ -68,20 +92,43 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: '3.11'
-          cache: 'pip'
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
 
       - name: Install dependencies
         run: |
           cd core
-          pip install -e .
-          pip install -r requirements-dev.txt
+          uv sync
 
       - name: Validate exported agents
         run: |
           # Check that agent exports have valid structure
-          for agent_dir in exports/*/; do
+          if [ ! -d "exports" ]; then
+            echo "No exports/ directory found, skipping validation"
+            exit 0
+          fi
+
+          shopt -s nullglob
+          agent_dirs=(exports/*/)
+          shopt -u nullglob
+
+          if [ ${#agent_dirs[@]} -eq 0 ]; then
+            echo "No agent directories in exports/, skipping validation"
+            exit 0
+          fi
+
+          validated=0
+          for agent_dir in "${agent_dirs[@]}"; do
             if [ -f "$agent_dir/agent.json" ]; then
               echo "Validating $agent_dir"
-              python -c "import json; json.load(open('$agent_dir/agent.json'))"
+              uv run python -c "import json; json.load(open('$agent_dir/agent.json'))"
+              validated=$((validated + 1))
             fi
           done
+
+          if [ "$validated" -eq 0 ]; then
+            echo "No agent.json files found in exports/, skipping validation"
+          else
+            echo "Validated $validated agent(s)"
+          fi

.github/workflows/claude-issue-triage.yml

@@ -0,0 +1,103 @@
+name: Issue Triage
+
+on:
+  issues:
+    types: [opened]
+
+jobs:
+  triage:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write
+      id-token: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Triage and check for duplicates
+        uses: anthropics/claude-code-action@v1
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          allowed_non_write_users: "*"
+          prompt: |
+            Analyze this new issue and perform triage tasks.
+
+            Issue: #${{ github.event.issue.number }}
+            Repository: ${{ github.repository }}
+
+            ## Your Tasks:
+
+            ### 1. Get issue details
+            Use mcp__github__get_issue to get the full details of issue #${{ github.event.issue.number }}
+
+            ### 2. Check for duplicates
+            Search for similar existing issues using mcp__github__search_issues with relevant keywords from the issue title and body.
+
+            Criteria for duplicates:
+            - Same bug or error being reported
+            - Same feature request (even if worded differently)
+            - Same question being asked
+            - Issues describing the same root problem
+
+            If you find a duplicate:
+            - Add a comment using EXACTLY this format (required for auto-close to work):
+              "Found a possible duplicate of #<issue_number>: <brief explanation of why it's a duplicate>"
+            - Do NOT apply the "duplicate" label yet (the auto-close script will add it after 12 hours if no objections)
+            - Suggest the user react with a thumbs-down if they disagree
+
+            ### 3. Check for Low-Quality / AI Spam
+            Analyze the issue quality. We are receiving many low-effort, AI-generated spam issues.
+            Flag the issue as INVALID if it matches these criteria:
+            - **Vague/Generic**: Title is "Fix bug" or "Error" without specific context.
+            - **Hallucinated**: Refers to files or features that do not exist in this repo.
+            - **Template Filler**: Body contains "Insert description here" or unrelated gibberish.
+            - **Low Effort**: No reproduction steps, no logs, only 1-2 sentences.
+
+            If identified as spam/low-quality:
+            - Add the "invalid" label.
+            - Add a comment:
+              "This issue has been automatically flagged as low-quality or potentially AI-generated spam. It lacks specific details (logs, reproduction steps, file references) required for us to help. Please open a new issue following the template exactly if this is a legitimate request."
+            - Do NOT proceed to other steps.
+
+            ### 4. Check for invalid issues (General)
+            If the issue is not spam but still lacks information:
+            - Add the "invalid" label
+            - Comment asking for clarification
+
+            ### 5. Categorize with labels (if NOT a duplicate or spam)
+            Apply appropriate labels based on the issue content. Use ONLY these labels:
+            - bug: Something isn't working
+            - enhancement: New feature or request
+            - question: Further information is requested
+            - documentation: Improvements or additions to documentation
+            - good first issue: Good for newcomers (if issue is well-defined and small scope)
+            - help wanted: Extra attention is needed (if issue needs community input)
+            - backlog: Tracked for the future, but not currently planned or prioritized
+
+            ### 6. Estimate size (if NOT a duplicate, spam, or invalid)
+            Apply exactly ONE size label to help contributors match their capacity to the task:
+            - "size: small": Docs, typos, single-file fixes, config changes
+            - "size: medium": Bug fixes with tests, adding a single tool, changes within one package
+            - "size: large": Cross-package changes (core + tools), new modules, complex logic, architectural refactors
+
+            You may apply multiple labels if appropriate (e.g., "bug", "size: small", and "good first issue").
+
+            ## Tools Available:
+            - mcp__github__get_issue: Get issue details
+            - mcp__github__search_issues: Search for similar issues
+            - mcp__github__list_issues: List recent issues if needed
+            - mcp__github__add_issue_comment: Add a comment
+            - mcp__github__update_issue: Add labels
+            - mcp__github__get_issue_comments: Get existing comments
+
+            Be thorough but efficient. Focus on accurate categorization and finding true duplicates.
+
+          claude_args: |
+            --model claude-haiku-4-5-20251001
+            --allowedTools "mcp__github__get_issue,mcp__github__search_issues,mcp__github__list_issues,mcp__github__add_issue_comment,mcp__github__update_issue,mcp__github__get_issue_comments"

.github/workflows/pr-check-command.yml

@@ -0,0 +1,204 @@
+name: PR Check Command
+
+on:
+  issue_comment:
+    types: [created]
+
+jobs:
+  check-pr:
+    # Only run on PR comments that start with /check
+    if: github.event.issue.pull_request && startsWith(github.event.comment.body, '/check')
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+      issues: write
+      checks: write
+      statuses: write
+
+    steps:
+      - name: Check PR requirements
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const prNumber = context.payload.issue.number;
+            console.log(`Triggered by /check comment on PR #${prNumber}`);
+
+            // Fetch PR data
+            const { data: pr } = await github.rest.pulls.get({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              pull_number: prNumber,
+            });
+
+            const prBody = pr.body || '';
+            const prTitle = pr.title || '';
+            const prAuthor = pr.user.login;
+            const headSha = pr.head.sha;
+
+            // Create a check run in progress
+            const { data: checkRun } = await github.rest.checks.create({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              name: 'check-requirements',
+              head_sha: headSha,
+              status: 'in_progress',
+              started_at: new Date().toISOString(),
+            });
+
+            // Extract issue numbers
+            const issuePattern = /(?:close[sd]?|fix(?:e[sd])?|resolve[sd]?)?\s*#(\d+)/gi;
+            const allText = `${prTitle} ${prBody}`;
+            const matches = [...allText.matchAll(issuePattern)];
+            const issueNumbers = [...new Set(matches.map(m => parseInt(m[1], 10)))];
+
+            console.log(`PR #${prNumber}:`);
+            console.log(`  Author: ${prAuthor}`);
+            console.log(`  Found issue references: ${issueNumbers.length > 0 ? issueNumbers.join(', ') : 'none'}`);
+
+            if (issueNumbers.length === 0) {
+              const message = `## PR Closed - Requirements Not Met
+
+            This PR has been automatically closed because it doesn't meet the requirements.
+
+            **Missing:** No linked issue found.
+
+            **To fix:**
+            1. Create or find an existing issue for this work
+            2. Assign yourself to the issue
+            3. Re-open this PR and add \`Fixes #123\` in the description
+
+            **Why is this required?** See #472 for details.`;
+
+              await github.rest.issues.createComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: prNumber,
+                body: message,
+              });
+
+              await github.rest.pulls.update({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                pull_number: prNumber,
+                state: 'closed',
+              });
+
+              // Update check run to failure
+              await github.rest.checks.update({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                check_run_id: checkRun.id,
+                status: 'completed',
+                conclusion: 'failure',
+                completed_at: new Date().toISOString(),
+                output: {
+                  title: 'Missing linked issue',
+                  summary: 'PR must reference an issue (e.g., `Fixes #123`)',
+                },
+              });
+
+              core.setFailed('PR must reference an issue');
+              return;
+            }
+
+            // Check if PR author is assigned to any linked issue
+            let issueWithAuthorAssigned = null;
+            let issuesWithoutAuthor = [];
+
+            for (const issueNum of issueNumbers) {
+              try {
+                const { data: issue } = await github.rest.issues.get({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: issueNum,
+                });
+
+                const assigneeLogins = (issue.assignees || []).map(a => a.login);
+                if (assigneeLogins.includes(prAuthor)) {
+                  issueWithAuthorAssigned = issueNum;
+                  console.log(`  Issue #${issueNum} has PR author ${prAuthor} as assignee`);
+                  break;
+                } else {
+                  issuesWithoutAuthor.push({
+                    number: issueNum,
+                    assignees: assigneeLogins
+                  });
+                  console.log(`  Issue #${issueNum} assignees: ${assigneeLogins.length > 0 ? assigneeLogins.join(', ') : 'none'}`);
+                }
+              } catch (error) {
+                console.log(`  Issue #${issueNum} not found`);
+              }
+            }
+
+            if (!issueWithAuthorAssigned) {
+              const issueList = issuesWithoutAuthor.map(i =>
+                `#${i.number} (assignees: ${i.assignees.length > 0 ? i.assignees.join(', ') : 'none'})`
+              ).join(', ');
+
+              const message = `## PR Closed - Requirements Not Met
+
+            This PR has been automatically closed because it doesn't meet the requirements.
+
+            **PR Author:** @${prAuthor}
+            **Found issues:** ${issueList}
+            **Problem:** The PR author must be assigned to the linked issue.
+
+            **To fix:**
+            1. Assign yourself (@${prAuthor}) to one of the linked issues
+            2. Re-open this PR
+
+            **Why is this required?** See #472 for details.`;
+
+              await github.rest.issues.createComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: prNumber,
+                body: message,
+              });
+
+              await github.rest.pulls.update({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                pull_number: prNumber,
+                state: 'closed',
+              });
+
+              // Update check run to failure
+              await github.rest.checks.update({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                check_run_id: checkRun.id,
+                status: 'completed',
+                conclusion: 'failure',
+                completed_at: new Date().toISOString(),
+                output: {
+                  title: 'PR author not assigned to issue',
+                  summary: `PR author @${prAuthor} must be assigned to one of the linked issues: ${issueList}`,
+                },
+              });
+
+              core.setFailed('PR author must be assigned to the linked issue');
+            } else {
+              await github.rest.issues.createComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: prNumber,
+                body: `✅ PR requirements met! Issue #${issueWithAuthorAssigned} has @${prAuthor} as assignee.`,
+              });
+
+              // Update check run to success
+              await github.rest.checks.update({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                check_run_id: checkRun.id,
+                status: 'completed',
+                conclusion: 'success',
+                completed_at: new Date().toISOString(),
+                output: {
+                  title: 'Requirements met',
+                  summary: `Issue #${issueWithAuthorAssigned} has @${prAuthor} as assignee.`,
+                },
+              });
+
+              console.log(`PR requirements met!`);
+            }

.github/workflows/pr-requirements-backfill.yml

@@ -0,0 +1,138 @@
+name: PR Requirements Backfill
+
+on:
+  workflow_dispatch:
+
+jobs:
+  check-all-open-prs:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+      issues: write
+
+    steps:
+      - name: Check all open PRs
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const { data: pullRequests } = await github.rest.pulls.list({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              state: 'open',
+              per_page: 100,
+            });
+
+            console.log(`Found ${pullRequests.length} open PRs`);
+
+            for (const pr of pullRequests) {
+              const prNumber = pr.number;
+              const prBody = pr.body || '';
+              const prTitle = pr.title || '';
+              const prAuthor = pr.user.login;
+
+              console.log(`\nChecking PR #${prNumber}: ${prTitle}`);
+
+              // Extract issue numbers from body and title
+              const issuePattern = /(?:close[sd]?|fix(?:e[sd])?|resolve[sd]?)?\s*#(\d+)/gi;
+              const allText = `${prTitle} ${prBody}`;
+              const matches = [...allText.matchAll(issuePattern)];
+              const issueNumbers = [...new Set(matches.map(m => parseInt(m[1], 10)))];
+
+              console.log(`  Found issue references: ${issueNumbers.length > 0 ? issueNumbers.join(', ') : 'none'}`);
+
+              if (issueNumbers.length === 0) {
+                console.log(`  ❌ No linked issue - closing PR`);
+
+                const message = `## PR Closed - Requirements Not Met
+
+            This PR has been automatically closed because it doesn't meet the requirements.
+
+            **Missing:** No linked issue found.
+
+            **To fix:**
+            1. Create or find an existing issue for this work
+            2. Assign yourself to the issue
+            3. Re-open this PR and add \`Fixes #123\` in the description`;
+
+                await github.rest.issues.createComment({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: prNumber,
+                  body: message,
+                });
+
+                await github.rest.pulls.update({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  pull_number: prNumber,
+                  state: 'closed',
+                });
+
+                continue;
+              }
+
+              // Check if any linked issue has the PR author as assignee
+              let issueWithAuthorAssigned = null;
+              let issuesWithoutAuthor = [];
+
+              for (const issueNum of issueNumbers) {
+                try {
+                  const { data: issue } = await github.rest.issues.get({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issueNum,
+                  });
+
+                  const assigneeLogins = (issue.assignees || []).map(a => a.login);
+                  if (assigneeLogins.includes(prAuthor)) {
+                    issueWithAuthorAssigned = issueNum;
+                    break;
+                  } else {
+                    issuesWithoutAuthor.push({
+                      number: issueNum,
+                      assignees: assigneeLogins
+                    });
+                  }
+                } catch (error) {
+                  console.log(`  Issue #${issueNum} not found or inaccessible`);
+                }
+              }
+
+              if (!issueWithAuthorAssigned) {
+                const issueList = issuesWithoutAuthor.map(i =>
+                  `#${i.number} (assignees: ${i.assignees.length > 0 ? i.assignees.join(', ') : 'none'})`
+                ).join(', ');
+
+                console.log(`  ❌ PR author not assigned to any linked issue - closing PR`);
+
+                const message = `## PR Closed - Requirements Not Met
+
+            This PR has been automatically closed because it doesn't meet the requirements.
+
+            **PR Author:** @${prAuthor}
+            **Found issues:** ${issueList}
+            **Problem:** The PR author must be assigned to the linked issue.
+
+            **To fix:**
+            1. Assign yourself (@${prAuthor}) to one of the linked issues
+            2. Re-open this PR`;
+
+                await github.rest.issues.createComment({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: prNumber,
+                  body: message,
+                });
+
+                await github.rest.pulls.update({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  pull_number: prNumber,
+                  state: 'closed',
+                });
+              } else {
+                console.log(`  ✅ PR requirements met! Issue #${issueWithAuthorAssigned} has ${prAuthor} as assignee.`);
+              }
+            }
+
+            console.log('\nBackfill complete!');

.github/workflows/pr-requirements.yml

@@ -0,0 +1,189 @@
+name: PR Requirements Check
+
+on:
+  pull_request_target:
+    types: [opened, reopened, edited, synchronize]
+
+jobs:
+  check-requirements:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+      issues: write
+
+    steps:
+      - name: Check PR has linked issue with assignee
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const pr = context.payload.pull_request;
+            const prNumber = pr.number;
+            const prBody = pr.body || '';
+            const prTitle = pr.title || '';
+            const prLabels = (pr.labels || []).map(l => l.name);
+
+            // Allow micro-fix and documentation PRs without a linked issue
+            const isMicroFix = prLabels.includes('micro-fix') || /micro-fix/i.test(prTitle);
+            const isDocumentation = prLabels.includes('documentation') || /\bdocs?\b/i.test(prTitle);
+            if (isMicroFix || isDocumentation) {
+              const reason = isMicroFix ? 'micro-fix' : 'documentation';
+              console.log(`PR #${prNumber} is a ${reason}, skipping issue requirement.`);
+              return;
+            }
+
+            // Extract issue numbers from body and title
+            // Matches: fixes #123, closes #123, resolves #123, or plain #123
+            const issuePattern = /(?:close[sd]?|fix(?:e[sd])?|resolve[sd]?)?\s*#(\d+)/gi;
+
+            const allText = `${prTitle} ${prBody}`;
+            const matches = [...allText.matchAll(issuePattern)];
+            const issueNumbers = [...new Set(matches.map(m => parseInt(m[1], 10)))];
+
+            console.log(`PR #${prNumber}:`);
+            console.log(`  Found issue references: ${issueNumbers.length > 0 ? issueNumbers.join(', ') : 'none'}`);
+
+            if (issueNumbers.length === 0) {
+              const message = `## PR Closed - Requirements Not Met
+
+            This PR has been automatically closed because it doesn't meet the requirements.
+
+            **Missing:** No linked issue found.
+
+            **To fix:**
+            1. Create or find an existing issue for this work
+            2. Assign yourself to the issue
+            3. Re-open this PR and add \`Fixes #123\` in the description
+
+            **Exception:** To bypass this requirement, you can:
+            - Add the \`micro-fix\` label or include \`micro-fix\` in your PR title for trivial fixes
+            - Add the \`documentation\` label or include \`doc\`/\`docs\` in your PR title for documentation changes
+
+            **Micro-fix requirements** (must meet ALL):
+            | Qualifies | Disqualifies |
+            |-----------|--------------|
+            | < 20 lines changed | Any functional bug fix |
+            | Typos & Documentation & Linting | Refactoring for "clean code" |
+            | No logic/API/DB changes | New features (even tiny ones) |
+
+            **Why is this required?** See #472 for details.`;
+
+              const comments = await github.rest.issues.listComments({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: prNumber,
+              });
+
+              const botComment = comments.data.find(
+                (c) => c.user.type === 'Bot' && c.body.includes('PR Closed - Requirements Not Met')
+              );
+
+              if (!botComment) {
+                await github.rest.issues.createComment({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: prNumber,
+                  body: message,
+                });
+              }
+
+              await github.rest.pulls.update({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                pull_number: prNumber,
+                state: 'closed',
+              });
+
+              core.setFailed('PR must reference an issue');
+              return;
+            }
+
+            // Check if any linked issue has the PR author as assignee
+            const prAuthor = pr.user.login;
+            let issueWithAuthorAssigned = null;
+            let issuesWithoutAuthor = [];
+
+            for (const issueNum of issueNumbers) {
+              try {
+                const { data: issue } = await github.rest.issues.get({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: issueNum,
+                });
+
+                const assigneeLogins = (issue.assignees || []).map(a => a.login);
+                if (assigneeLogins.includes(prAuthor)) {
+                  issueWithAuthorAssigned = issueNum;
+                  console.log(`  Issue #${issueNum} has PR author ${prAuthor} as assignee`);
+                  break;
+                } else {
+                  issuesWithoutAuthor.push({
+                    number: issueNum,
+                    assignees: assigneeLogins
+                  });
+                  console.log(`  Issue #${issueNum} assignees: ${assigneeLogins.length > 0 ? assigneeLogins.join(', ') : 'none'} (PR author: ${prAuthor})`);
+                }
+              } catch (error) {
+                console.log(`  Issue #${issueNum} not found or inaccessible`);
+              }
+            }
+
+            if (!issueWithAuthorAssigned) {
+              const issueList = issuesWithoutAuthor.map(i =>
+                `#${i.number} (assignees: ${i.assignees.length > 0 ? i.assignees.join(', ') : 'none'})`
+              ).join(', ');
+
+              const message = `## PR Closed - Requirements Not Met
+
+            This PR has been automatically closed because it doesn't meet the requirements.
+
+            **PR Author:** @${prAuthor}
+            **Found issues:** ${issueList}
+            **Problem:** The PR author must be assigned to the linked issue.
+
+            **To fix:**
+            1. Assign yourself (@${prAuthor}) to one of the linked issues
+            2. Re-open this PR
+
+            **Exception:** To bypass this requirement, you can:
+            - Add the \`micro-fix\` label or include \`micro-fix\` in your PR title for trivial fixes
+            - Add the \`documentation\` label or include \`doc\`/\`docs\` in your PR title for documentation changes
+
+            **Micro-fix requirements** (must meet ALL):
+            | Qualifies | Disqualifies |
+            |-----------|--------------|
+            | < 20 lines changed | Any functional bug fix |
+            | Typos & Documentation & Linting | Refactoring for "clean code" |
+            | No logic/API/DB changes | New features (even tiny ones) |
+
+            **Why is this required?** See #472 for details.`;
+
+              const comments = await github.rest.issues.listComments({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: prNumber,
+              });
+
+              const botComment = comments.data.find(
+                (c) => c.user.type === 'Bot' && c.body.includes('PR Closed - Requirements Not Met')
+              );
+
+              if (!botComment) {
+                await github.rest.issues.createComment({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: prNumber,
+                  body: message,
+                });
+              }
+
+              await github.rest.pulls.update({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                pull_number: prNumber,
+                state: 'closed',
+              });
+
+              core.setFailed('PR author must be assigned to the linked issue');
+            } else {
+              console.log(`PR requirements met! Issue #${issueWithAuthorAssigned} has ${prAuthor} as assignee.`);
+            }

.github/workflows/release.yml

@@ -21,18 +21,19 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: '3.11'
-          cache: 'pip'
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
 
       - name: Install dependencies
         run: |
           cd core
-          pip install -e .
-          pip install -r requirements-dev.txt
+          uv sync
 
       - name: Run tests
         run: |
           cd core
-          pytest tests/ -v
+          uv run pytest tests/ -v
 
       - name: Generate changelog
         id: changelog

.gitignore

@@ -46,6 +46,7 @@ coverage/
 
 # TypeScript
 *.tsbuildinfo
+vite.config.d.ts
 
 # Python
 __pycache__/
@@ -54,7 +55,6 @@ __pycache__/
 *.egg-info/
 .eggs/
 *.egg
-uv.lock
 
 # Generated runtime data
 core/data/
@@ -69,4 +69,12 @@ exports/*
 
 .agent-builder-sessions/*
 
+.claude/settings.local.json
+
 .venv
+
+docs/github-issues/*
+core/tests/*dumps/*
+
+screenshots/*
+

.mcp.json

@@ -1,20 +1,9 @@
 {
   "mcpServers": {
     "agent-builder": {
-      "command": "python",
-      "args": ["-m", "framework.mcp.agent_builder_server"],
-      "cwd": "core",
-      "env": {
-        "PYTHONPATH": "../tools/src"
-      }
-    },
-    "tools": {
-      "command": "python",
-      "args": ["mcp_server.py", "--stdio"],
-      "cwd": "tools",
-      "env": {
-        "PYTHONPATH": "src"
-      }
+      "command": "uv",
+      "args": ["run", "-m", "framework.mcp.agent_builder_server"],
+      "cwd": "core"
     }
   }
 }

.opencode/mcp.json

@@ -0,0 +1,30 @@
+{
+  "mcpServers": {
+    "agent-builder": {
+      "command": "uv",
+      "args": [
+        "run",
+        "python",
+        "-m",
+        "framework.mcp.agent_builder_server"
+      ],
+      "cwd": "core",
+      "env": {
+        "PYTHONPATH": "../tools/src"
+      }
+    },
+    "tools": {
+      "command": "uv",
+      "args": [
+        "run",
+        "python",
+        "mcp_server.py",
+        "--stdio"
+      ],
+      "cwd": "tools",
+      "env": {
+        "PYTHONPATH": "src"
+      }
+    }
+  }
+}

.opencode/skills/hive

@@ -0,0 +1 @@
+../../.claude/skills/hive

.opencode/skills/hive-concepts

@@ -0,0 +1 @@
+../../.claude/skills/hive-concepts

.opencode/skills/hive-create

@@ -0,0 +1 @@
+../../.claude/skills/hive-create

.opencode/skills/hive-credentials

@@ -0,0 +1 @@
+../../.claude/skills/hive-credentials

.opencode/skills/hive-debugger

@@ -0,0 +1 @@
+../../.claude/skills/hive-debugger

.opencode/skills/hive-patterns

@@ -0,0 +1 @@
+../../.claude/skills/hive-patterns

.opencode/skills/hive-test

@@ -0,0 +1 @@
+../../.claude/skills/hive-test

.opencode/skills/triage-issue

@@ -0,0 +1 @@
+../../.claude/skills/triage-issue

.pre-commit-config.yaml

@@ -0,0 +1,18 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.15.0
+    hooks:
+      - id: ruff
+        name: ruff lint (core)
+        args: [--fix]
+        files: ^core/
+      - id: ruff
+        name: ruff lint (tools)
+        args: [--fix]
+        files: ^tools/
+      - id: ruff-format
+        name: ruff format (core)
+        files: ^core/
+      - id: ruff-format
+        name: ruff format (tools)
+        files: ^tools/

.python-version

@@ -0,0 +1 @@
+3.11

.vscode/extensions.json

@@ -0,0 +1,7 @@
+{
+  "recommendations": [
+    "charliermarsh.ruff",
+    "editorconfig.editorconfig",
+    "ms-python.python"
+  ]
+}

CHANGELOG.md

@@ -1,40 +1,207 @@
-# Changelog
+# Release Notes
 
-All notable changes to this project will be documented in this file.
+**Release Date:** February 18, 2026
+**Tag:** v0.5.1
 
-The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
-and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+## The Hive Gets a Brain
 
-## [Unreleased]
+v0.5.1 is our most ambitious release yet. Hive agents can now **build other agents** -- the new Hive Coder meta-agent writes, tests, and fixes agent packages from natural language. The runtime grows multi-graph support so one session can orchestrate multiple agents simultaneously. The TUI gets a complete overhaul with an in-app agent picker, live streaming, and seamless escalation to the Coder. And we're now provider-agnostic: Claude Code subscriptions, OpenAI-compatible endpoints, and any LiteLLM-supported model work out of the box.
 
-### Added
-- Initial project structure
-- React frontend (honeycomb) with Vite and TypeScript
-- Node.js backend (hive) with Express and TypeScript
-- Docker Compose configuration for local development
-- Configuration system via `config.yaml`
-- GitHub Actions CI/CD workflows
-- Comprehensive documentation
+---
 
-### Changed
-- N/A
+## Highlights
 
-### Deprecated
-- N/A
+### Hive Coder -- The Agent That Builds Agents
 
-### Removed
-- N/A
+A native meta-agent that lives inside the framework at `core/framework/agents/hive_coder/`. Give it a natural-language specification and it produces a complete agent package -- goal definition, node prompts, edge routing, MCP tool wiring, tests, and all boilerplate files.
 
-### Fixed
-- N/A
+```bash
+# Launch the Coder directly
+hive code
 
-### Security
-- N/A
+# Or escalate from any running agent (TUI)
+Ctrl+E  # or /coder in chat
+```
 
-## [0.1.0] - 2025-01-13
+The Coder ships with:
 
-### Added
-- Initial release
+- **Reference documentation** -- anti-patterns, construction guide, and design patterns baked into its system prompt
+- **Guardian watchdog** -- an event-driven monitor that catches agent failures and triggers automatic remediation
+- **Coder Tools MCP server** -- file I/O, fuzzy-match editing, git snapshots, and sandboxed shell execution (`tools/coder_tools_server.py`)
+- **Test generation** -- structural tests for forever-alive agents that don't hang on `runner.run()`
 
-[Unreleased]: https://github.com/adenhq/hive/compare/v0.1.0...HEAD
-[0.1.0]: https://github.com/adenhq/hive/releases/tag/v0.1.0
+### Multi-Graph Agent Runtime
+
+`AgentRuntime` now supports loading, managing, and switching between multiple agent graphs within a single session. Six new lifecycle tools give agents (and the TUI) full control:
+
+```python
+# Load a second agent into the runtime
+await runtime.add_graph("exports/deep_research_agent")
+
+# Tools available to agents:
+# load_agent, unload_agent, start_agent, restart_agent, list_agents, get_user_presence
+```
+
+The Hive Coder uses multi-graph internally -- when you escalate from a worker agent, the Coder loads as a separate graph while the worker stays alive in the background.
+
+### TUI Revamp
+
+The Terminal UI gets a ground-up rebuild with five major additions:
+
+- **Agent Picker** (Ctrl+A) -- tabbed modal screen for browsing Your Agents, Framework agents, and Examples with metadata badges (node count, tool count, session count, tags)
+- **Runtime-optional startup** -- TUI launches without a pre-loaded agent, showing the picker on first open
+- **Live streaming pane** -- dedicated RichLog widget shows LLM tokens as they arrive, replacing the old one-token-per-line display
+- **PDF attachments** -- `/attach` and `/detach` commands with native OS file dialog (macOS, Linux, Windows)
+- **Multi-graph commands** -- `/graphs`, `/graph <id>`, `/load <path>`, `/unload <id>` for managing agent graphs in-session
+
+### Provider-Agnostic LLM Support
+
+Hive is no longer Anthropic-only. v0.5.1 adds first-class support for:
+
+- **Claude Code subscriptions** -- `use_claude_code_subscription: true` in `~/.hive/configuration.json` reads OAuth tokens from `~/.claude/.credentials.json` with automatic refresh
+- **OpenAI-compatible endpoints** -- `api_base` config routes traffic through any compatible API (Azure OpenAI, vLLM, Ollama, etc.)
+- **Any LiteLLM model** -- `RuntimeConfig` now passes `api_key`, `api_base`, and `extra_kwargs` through to LiteLLM
+
+The quickstart script auto-detects Claude Code subscriptions and ZAI Code installations.
+
+---
+
+## What's New
+
+### Architecture & Runtime
+
+- **Hive Coder meta-agent** -- Natural-language agent builder with reference docs, guardian watchdog, and `hive code` CLI command. (@TimothyZhang7)
+- **Multi-graph agent sessions** -- `add_graph`/`remove_graph` on AgentRuntime with 6 lifecycle tools (`load_agent`, `unload_agent`, `start_agent`, `restart_agent`, `list_agents`, `get_user_presence`). (@TimothyZhang7)
+- **Claude Code subscription support** -- OAuth token refresh via `use_claude_code_subscription` config, auto-detection in quickstart, LiteLLM header patching. (@TimothyZhang7)
+- **OpenAI-compatible endpoint support** -- `api_base` and `extra_kwargs` in `RuntimeConfig` for any OpenAI-compatible API. (@TimothyZhang7)
+- **Remove deprecated node types** -- Delete `FlexibleGraphExecutor`, `WorkerNode`, `HybridJudge`, `CodeSandbox`, `Plan`, `FunctionNode`, `LLMNode`, `RouterNode`. Deprecated types (`llm_tool_use`, `llm_generate`, `function`, `router`, `human_input`) now raise `RuntimeError` with migration guidance. (@TimothyZhang7)
+- **Interactive credential setup** -- Guided `CredentialSetupSession` with health checks and encrypted storage, accessible via `hive setup-credentials` or automatic prompting on credential errors. (@RichardTang-Aden)
+- **Pre-start confirmation prompt** -- Interactive prompt before agent execution allowing credential updates or abort. (@RichardTang-Aden)
+- **Event bus multi-graph support** -- `graph_id` on events, `filter_graph` on subscriptions, `ESCALATION_REQUESTED` event type, `exclude_own_graph` filter. (@TimothyZhang7)
+
+### TUI Improvements
+
+- **In-app agent picker** (Ctrl+A) -- Tabbed modal for browsing agents with metadata badges (nodes, tools, sessions, tags). (@TimothyZhang7)
+- **Runtime-optional TUI startup** -- Launches without a pre-loaded agent, shows agent picker on startup. (@TimothyZhang7)
+- **Hive Coder escalation** (Ctrl+E) -- Escalate to Hive Coder and return; also available via `/coder` and `/back` chat commands. (@TimothyZhang7)
+- **PDF attachment support** -- `/attach` and `/detach` commands with native OS file dialog. (@TimothyZhang7)
+- **Streaming output pane** -- Dedicated RichLog widget for live LLM token streaming. (@TimothyZhang7)
+- **Multi-graph TUI commands** -- `/graphs`, `/graph <id>`, `/load <path>`, `/unload <id>`. (@TimothyZhang7)
+- **Agent Guardian watchdog** -- Event-driven monitor that catches secondary agent failures and triggers automatic remediation, with `--no-guardian` CLI flag. (@TimothyZhang7)
+
+### New Tool Integrations
+
+| Tool                   | Description                                                                                                                                                            | Contributor        |
+| ---------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------ |
+| **Discord**            | 4 MCP tools (`discord_list_guilds`, `discord_list_channels`, `discord_send_message`, `discord_get_messages`) with rate-limit retry and channel filtering               | @mishrapravin114   |
+| **Exa Search API**     | 4 AI-powered search tools (`exa_search`, `exa_find_similar`, `exa_get_contents`, `exa_answer`) with neural/keyword search, domain filters, and citation-backed answers | @JeetKaria06       |
+| **Razorpay**           | 6 payment processing tools for payments, invoices, payment links, and refunds with HTTP Basic Auth                                                                     | @shivamshahi07     |
+| **Google Docs**        | Document creation, reading, and editing with OAuth credential support                                                                                                  | @haliaeetusvocifer |
+| **Gmail enhancements** | Expanded mail operations for inbox management                                                                                                                          | @bryanadenhq       |
+
+### Infrastructure
+
+- **Default node type → `event_loop`** -- `NodeSpec.node_type` defaults to `"event_loop"` instead of `"llm_tool_use"`. (@TimothyZhang7)
+- **Default `max_node_visits` → 0 (unlimited)** -- Nodes default to unlimited visits, reducing friction for feedback loops and forever-alive agents. (@TimothyZhang7)
+- **Remove `function` field from NodeSpec** -- Follows deprecation of `FunctionNode`. (@TimothyZhang7)
+- **LiteLLM OAuth patch** -- Correct header construction for OAuth tokens (remove `x-api-key` when Bearer token is present). (@TimothyZhang7)
+- **Orchestrator config centralization** -- Reads `api_key`, `api_base`, `extra_kwargs` from centralized `~/.hive/configuration.json`. (@TimothyZhang7)
+- **System prompt datetime injection** -- All system prompts now include current date/time for time-aware agent behavior. (@TimothyZhang7)
+- **Utils module exports** -- Proper `__init__.py` exports for the utils module. (@Siddharth2624)
+- **Increased default max_tokens** -- Opus 4.6 defaults to 32768, Sonnet 4.5 to 16384 (up from 8192). (@TimothyZhang7)
+
+---
+
+## Bug Fixes
+
+- Flush WIP accumulator outputs on cancel/failure so edge conditions see correct values on resume
+- Stall detection state preserved across resume (no more resets on checkpoint restore)
+- Skip client-facing blocking for event-triggered executions (timer/webhook)
+- Executor retry override scoped to actual EventLoopNode instances only
+- Add `_awaiting_input` flag to EventLoopNode to prevent input injection race conditions
+- Fix TUI streaming display (tokens no longer appear one-per-line)
+- Fix `_return_from_escalation` crash when ChatRepl widgets not yet mounted
+- Fix tools registration problems for Google Docs credentials (@RichardTang-Aden)
+- Fix email agent version conflicts (@RichardTang-Aden)
+- Fix coder tool timeouts (120s for tests, 300s cap for commands)
+
+## Documentation
+
+- Clarify installation and prevent root pip install misuse (@paarths-collab)
+
+---
+
+## Agent Updates
+
+- **Email Inbox Management** -- Consolidate `gmail_inbox_guardian` and `inbox_management` into a single unified agent with updated prompts and config. (@RichardTang-Aden, @bryanadenhq)
+- **Job Hunter** -- Updated node prompts, config, and agent metadata; added PDF resume selection. (@bryanadenhq)
+- **Deep Research Agent** -- Revised node implementations with updated prompts and output handling.
+- **Tech News Reporter** -- Revised node prompts for improved output quality.
+- **Vulnerability Assessment** -- Expanded prompts with more detailed assessment instructions. (@bryanadenhq)
+
+---
+
+## Breaking Changes
+
+- **Deprecated node types raise `RuntimeError`** -- `llm_tool_use`, `llm_generate`, `function`, `router`, `human_input` now fail instead of warning. Migrate to `event_loop`.
+- **`NodeSpec.node_type` defaults to `"event_loop"`** (was `"llm_tool_use"`)
+- **`NodeSpec.max_node_visits` defaults to `0` / unlimited** (was `1`)
+- **`NodeSpec.function` field removed** -- `FunctionNode` is deleted; use event_loop nodes with tools instead.
+
+---
+
+## Community Contributors
+
+A huge thank you to everyone who contributed to this release:
+
+- **Richard Tang** (@RichardTang-Aden) -- Interactive credential setup, pre-start confirmation, email agent consolidation, tool registration fixes, lint and formatting
+- **Pravin Mishra** (@mishrapravin114) -- Discord integration with 4 MCP tools
+- **Jeet Karia** (@JeetKaria06) -- Exa Search API integration with 4 AI-powered search tools
+- **Shivam Shahi** (@shivamshahi07) -- Razorpay payment processing integration
+- **Siddharth Varshney** (@Siddharth2624) -- Utils module exports
+- **@haliaeetusvocifer** -- Google Docs integration with OAuth support
+- **Bryan** (@bryanadenhq) -- PDF selection, inbox agent fixes, Job Hunter and Vulnerability Assessment updates
+- **@paarths-collab** -- Documentation improvements
+
+---
+
+## Upgrading
+
+```bash
+git pull origin main
+uv sync
+```
+
+### Migration Guide
+
+If your agents use deprecated node types, update them:
+
+```python
+# Before (v0.5.0) -- these now raise RuntimeError
+NodeSpec(node_type="llm_tool_use", ...)
+NodeSpec(node_type="function", function=my_func, ...)
+
+# After (v0.5.1) -- use event_loop for everything
+NodeSpec(node_type="event_loop", ...)  # or just omit node_type (it's the default now)
+```
+
+If your agents set `max_node_visits=1` explicitly, they'll still work. The only change is the _default_ -- new agents without an explicit value now get unlimited visits.
+
+To try the new Hive Coder:
+
+```bash
+# Launch Coder directly
+hive code
+
+# Or from TUI -- press Ctrl+E to escalate
+hive tui
+```
+
+---
+
+## What's Next
+
+- **Agent-to-agent communication** -- one agent's output triggers another agent's entry point
+- **Cost visibility** -- detailed runtime log of LLM costs per node and per session
+- **Persistent webhook subscriptions** -- survive agent restarts without re-registering
+- **Remote agent deployment** -- run agents as long-lived services with HTTP APIs

CONTRIBUTING.md

@@ -1,34 +1,70 @@
 # Contributing to Aden Agent Framework
 
-Thank you for your interest in contributing to the Aden Agent Framework! This document provides guidelines and information for contributors.
+Thank you for your interest in contributing to the Aden Agent Framework! This document provides guidelines and information for contributors. We’re especially looking for help building tools, integrations ([check #2805](https://github.com/adenhq/hive/issues/2805)), and example agents for the framework. If you’re interested in extending its functionality, this is the perfect place to start. 
 
 ## Code of Conduct
 
-By participating in this project, you agree to abide by our [Code of Conduct](CODE_OF_CONDUCT.md).
+By participating in this project, you agree to abide by our [Code of Conduct](docs/CODE_OF_CONDUCT.md).
+
+## Issue Assignment Policy
+
+To prevent duplicate work and respect contributors' time, we require issue assignment before submitting PRs.
+
+### How to Claim an Issue
+
+1. **Find an Issue:** Browse existing issues or create a new one
+2. **Claim It:** Leave a comment (e.g., *"I'd like to work on this!"*)
+3. **Wait for Assignment:** A maintainer will assign you within 24 hours. Issues with reproducible steps or proposals are prioritized.
+4. **Submit Your PR:** Once assigned, you're ready to contribute
+
+> **Note:** PRs for unassigned issues may be delayed or closed if someone else was already assigned.
+
+### Exceptions (No Assignment Needed)
+
+You may submit PRs without prior assignment for:
+- **Documentation:** Fixing typos or clarifying instructions — add the `documentation` label or include `doc`/`docs` in your PR title to bypass the linked issue requirement
+- **Micro-fixes:** Add the `micro-fix` label or include `micro-fix` in your PR title to bypass the linked issue requirement. Micro-fixes must meet **all** qualification criteria:
+
+  | Qualifies | Disqualifies |
+  |-----------|--------------|
+  | < 20 lines changed | Any functional bug fix |
+  | Typos & Documentation & Linting | Refactoring for "clean code" |
+  | No logic/API/DB changes | New features (even tiny ones) |
 
 ## Getting Started
 
 1. Fork the repository
 2. Clone your fork: `git clone https://github.com/YOUR_USERNAME/hive.git`
-3. Create a feature branch: `git checkout -b feature/your-feature-name`
-4. Make your changes
-5. Run tests: `PYTHONPATH=core:exports python -m pytest`
-6. Commit your changes following our commit conventions
-7. Push to your fork and submit a Pull Request
+3. Add the upstream repository: `git remote add upstream https://github.com/adenhq/hive.git`
+4. Sync with upstream to ensure you're starting from the latest code:
+   ```bash
+   git fetch upstream
+   git checkout main
+   git merge upstream/main
+   ```
+5. Create a feature branch: `git checkout -b feature/your-feature-name`
+6. Make your changes
+7. Run checks and tests:
+   ```bash
+   make check    # Lint and format checks (ruff check + ruff format --check on core/ and tools/)
+   make test     # Core tests (cd core && pytest tests/ -v)
+   ```
+8. Commit your changes following our commit conventions
+9. Push to your fork and submit a Pull Request
 
 ## Development Setup
 
 ```bash
-# Install Python packages
-./scripts/setup-python.sh
-
-# Verify installation
-python -c "import framework; import aden_tools; print('✓ Setup complete')"
-
-# Install Claude Code skills (optional)
+# Install Python packages and verify setup
 ./quickstart.sh
 ```
 
+> **Windows Users:**  
+> If you are on native Windows, it is recommended to use **WSL (Windows Subsystem for Linux)**.  
+> Alternatively, make sure to run PowerShell or Git Bash with Python 3.11+ installed, and disable "App Execution Aliases" in Windows settings.
+
+> **Tip:** Installing Claude Code skills is optional for running existing agents, but required if you plan to **build new agents**.
+
 ## Commit Convention
 
 We follow [Conventional Commits](https://www.conventionalcommits.org/):
@@ -59,10 +95,10 @@ docs(readme): update installation instructions
 
 ## Pull Request Process
 
-1. Update documentation if needed
-2. Add tests for new functionality
-3. Ensure all tests pass
-4. Update the CHANGELOG.md if applicable
+1. **Get assigned to the issue first** (see [Issue Assignment Policy](#issue-assignment-policy))
+2. Update documentation if needed
+3. Add tests for new functionality
+4. Ensure `make check` and `make test` pass
 5. Request review from maintainers
 
 ### PR Title Format
@@ -75,7 +111,7 @@ feat(component): add new feature description
 ## Project Structure
 
 - `core/` - Core framework (agent runtime, graph executor, protocols)
-- `tools/` - MCP Tools Package (19 tools for agent capabilities)
+- `tools/` - MCP Tools Package (tools for agent capabilities)
 - `exports/` - Agent packages and examples
 - `docs/` - Documentation
 - `scripts/` - Build and utility scripts
@@ -90,19 +126,39 @@ feat(component): add new feature description
 - Use meaningful variable and function names
 - Keep functions focused and small
 
+For linting and formatting (Ruff, pre-commit hooks), see [Linting & Formatting Setup](docs/contributing-lint-setup.md).
+
 ## Testing
 
-```bash
-# Run all tests for the framework
-cd core && python -m pytest
+> **Note:** When testing agents in `exports/`, always set PYTHONPATH:
+>
+> ```bash
+> PYTHONPATH=exports uv run python -m agent_name test
+> ```
 
-# Run all tests for tools
-cd tools && python -m pytest
+```bash
+# Run lint and format checks (mirrors CI lint job)
+make check
+
+# Run core framework tests (mirrors CI test job)
+make test
+
+# Or run tests directly
+cd core && pytest tests/ -v
+
+# Run tools package tests (when contributing to tools/)
+cd tools && uv run pytest tests/ -v
 
 # Run tests for a specific agent
-PYTHONPATH=core:exports python -m agent_name test
+PYTHONPATH=exports uv run python -m agent_name test
 ```
 
+> **CI also validates** that all exported agent JSON files (`exports/*/agent.json`) are well-formed JSON. Ensure your agent exports are valid before submitting.
+
+## Contributor License Agreement
+
+By submitting a Pull Request, you agree that your contributions will be licensed under the Aden Agent Framework license.
+
 ## Questions?
 
 Feel free to open an issue for questions or join our [Discord community](https://discord.com/invite/MXE49hrKDk).

ENVIRONMENT_SETUP.md

@@ -1,347 +0,0 @@
-# Agent Development Environment Setup
-
-Complete setup guide for building and running goal-driven agents with the Aden Agent Framework.
-
-## Quick Setup
-
-```bash
-# Run the automated setup script
-./scripts/setup-python.sh
-```
-
-This will:
-
-- Check Python version (requires 3.11+)
-- Install the core framework package (`framework`)
-- Install the tools package (`aden_tools`)
-- Fix package compatibility issues (openai + litellm)
-- Verify all installations
-
-## Manual Setup (Alternative)
-
-If you prefer to set up manually or the script fails:
-
-### 1. Install Core Framework
-
-```bash
-cd core
-pip install -e .
-```
-
-### 2. Install Tools Package
-
-```bash
-cd tools
-pip install -e .
-```
-
-### 3. Upgrade OpenAI Package
-
-```bash
-# litellm requires openai >= 1.0.0
-pip install --upgrade "openai>=1.0.0"
-```
-
-### 4. Verify Installation
-
-```bash
-python -c "import framework; print('✓ framework OK')"
-python -c "import aden_tools; print('✓ aden_tools OK')"
-python -c "import litellm; print('✓ litellm OK')"
-```
-
-## Requirements
-
-### Python Version
-
-- **Minimum:** Python 3.11
-- **Recommended:** Python 3.11 or 3.12
-- **Tested on:** Python 3.11, 3.12, 3.13
-
-### System Requirements
-
-- pip (latest version)
-- 2GB+ RAM
-- Internet connection (for LLM API calls)
-
-### API Keys (Optional)
-
-For running agents with real LLMs:
-
-```bash
-export ANTHROPIC_API_KEY="your-key-here"
-```
-
-## Running Agents
-
-All agent commands must be run from the project root with `PYTHONPATH` set:
-
-```bash
-# From /home/timothy/oss/hive/ directory
-PYTHONPATH=core:exports python -m agent_name COMMAND
-```
-
-### Example: Support Ticket Agent
-
-```bash
-# Validate agent structure
-PYTHONPATH=core:exports python -m support_ticket_agent validate
-
-# Show agent information
-PYTHONPATH=core:exports python -m support_ticket_agent info
-
-# Run agent with input
-PYTHONPATH=core:exports python -m support_ticket_agent run --input '{
-  "ticket_content": "My login is broken. Error 401.",
-  "customer_id": "CUST-123",
-  "ticket_id": "TKT-456"
-}'
-
-# Run in mock mode (no LLM calls)
-PYTHONPATH=core:exports python -m support_ticket_agent run --mock --input '{...}'
-```
-
-### Example: Other Agents
-
-```bash
-# Market Research Agent
-PYTHONPATH=core:exports python -m market_research_agent info
-
-# Outbound Sales Agent
-PYTHONPATH=core:exports python -m outbound_sales_agent validate
-
-# Personal Assistant Agent
-PYTHONPATH=core:exports python -m personal_assistant_agent run --input '{...}'
-```
-
-## Building New Agents
-
-Use Claude Code CLI with the agent building skills:
-
-### 1. Install Skills (One-time)
-
-```bash
-./quickstart.sh
-```
-
-This installs:
-
-- `/building-agents` - Build new agents
-- `/testing-agent` - Test agents
-
-### 2. Build an Agent
-
-```
-claude> /building-agents
-```
-
-Follow the prompts to:
-
-1. Define your agent's goal
-2. Design the workflow nodes
-3. Connect edges
-4. Generate the agent package
-
-### 3. Test Your Agent
-
-```
-claude> /testing-agent
-```
-
-Creates comprehensive test suites for your agent.
-
-## Troubleshooting
-
-### "ModuleNotFoundError: No module named 'framework'"
-
-**Solution:** Install the core package:
-
-```bash
-cd core && pip install -e .
-```
-
-### "ModuleNotFoundError: No module named 'aden_tools'"
-
-**Solution:** Install the tools package:
-
-```bash
-cd tools && pip install -e .
-```
-
-Or run the setup script:
-
-```bash
-./scripts/setup-python.sh
-```
-
-### "ModuleNotFoundError: No module named 'openai.\_models'"
-
-**Cause:** Outdated `openai` package (0.27.x) incompatible with `litellm`
-
-**Solution:** Upgrade openai:
-
-```bash
-pip install --upgrade "openai>=1.0.0"
-```
-
-### "No module named 'support_ticket_agent'"
-
-**Cause:** Not running from project root or missing PYTHONPATH
-
-**Solution:** Ensure you're in `/home/timothy/oss/hive/` and use:
-
-```bash
-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
-
-**Solution:** Reinstall packages properly:
-
-```bash
-# Remove broken installations
-pip uninstall -y framework tools
-
-# Reinstall correctly
-cd /home/timothy/oss/hive
-./scripts/setup-python.sh
-```
-
-## Package Structure
-
-The Hive framework consists of three Python packages:
-
-```
-hive/
-├── core/                    # Core framework (runtime, graph executor, LLM providers)
-│   ├── framework/
-│   ├── pyproject.toml
-│   └── requirements.txt
-│
-├── tools/                   # Tools and MCP servers
-│   ├── src/
-│   │   └── aden_tools/     # Actual package location
-│   ├── pyproject.toml
-│   └── README.md
-│
-└── exports/                 # Agent packages (your agents go here)
-    ├── support_ticket_agent/
-    ├── market_research_agent/
-    ├── outbound_sales_agent/
-    └── personal_assistant_agent/
-```
-
-### Why PYTHONPATH is Required
-
-The packages are installed in **editable mode** (`pip install -e`), which means:
-
-- `framework` and `aden_tools` are globally importable (no PYTHONPATH needed)
-- `exports` is NOT installed as a package (PYTHONPATH required)
-
-This design allows agents in `exports/` to be:
-
-- Developed independently
-- Version controlled separately
-- Deployed as standalone packages
-
-## Development Workflow
-
-### 1. Setup (Once)
-
-```bash
-./scripts/setup-python.sh
-```
-
-### 2. Build Agent (Claude Code)
-
-```
-claude> /building-agents
-Enter goal: "Build an agent that processes customer support tickets"
-```
-
-### 3. Validate Agent
-
-```bash
-PYTHONPATH=core:exports python -m support_ticket_agent validate
-```
-
-### 4. Test Agent
-
-```
-claude> /testing-agent
-```
-
-### 5. Run Agent
-
-```bash
-PYTHONPATH=core:exports python -m support_ticket_agent run --input '{...}'
-```
-
-## IDE Setup
-
-### VSCode
-
-Add to `.vscode/settings.json`:
-
-```json
-{
-  "python.analysis.extraPaths": [
-    "${workspaceFolder}/core",
-    "${workspaceFolder}/exports"
-  ],
-  "python.autoComplete.extraPaths": [
-    "${workspaceFolder}/core",
-    "${workspaceFolder}/exports"
-  ]
-}
-```
-
-### PyCharm
-
-1. Open Project Settings → Project Structure
-2. Mark `core` as Sources Root
-3. Mark `exports` as Sources Root
-
-## Environment Variables
-
-### Required for LLM Operations
-
-```bash
-export ANTHROPIC_API_KEY="sk-ant-..."
-```
-
-### Optional Configuration
-
-```bash
-# Credentials storage location (default: ~/.aden/credentials)
-export ADEN_CREDENTIALS_PATH="/custom/path"
-
-# Agent storage location (default: /tmp)
-export AGENT_STORAGE_PATH="/custom/storage"
-```
-
-## Additional Resources
-
-- **Framework Documentation:** [core/README.md](core/README.md)
-- **Tools Documentation:** [tools/README.md](tools/README.md)
-- **Example Agents:** [exports/](exports/)
-- **Agent Building Guide:** [.claude/skills/building-agents-construction/SKILL.md](.claude/skills/building-agents-construction/SKILL.md)
-- **Testing Guide:** [.claude/skills/testing-agent/SKILL.md](.claude/skills/testing-agent/SKILL.md)
-
-## Contributing
-
-When contributing agent packages:
-
-1. Place agents in `exports/agent_name/`
-2. Follow the standard agent structure (see existing agents)
-3. Include README.md with usage instructions
-4. Add tests if using `/testing-agent`
-5. Document required environment variables
-
-## Support
-
-- **Issues:** https://github.com/adenhq/hive/issues
-- **Discord:** https://discord.com/invite/MXE49hrKDk
-- **Documentation:** https://docs.adenhq.com/

Makefile

@@ -0,0 +1,34 @@
+.PHONY: lint format check test install-hooks help frontend-dev frontend-build
+
+help: ## Show this help
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | \
+		awk 'BEGIN {FS = ":.*?## "}; {printf "  \033[36m%-15s\033[0m %s\n", $$1, $$2}'
+
+lint: ## Run ruff linter and formatter (with auto-fix)
+	cd core && ruff check --fix .
+	cd tools && ruff check --fix .
+	cd core && ruff format .
+	cd tools && ruff format .
+
+format: ## Run ruff formatter
+	cd core && ruff format .
+	cd tools && ruff format .
+
+check: ## Run all checks without modifying files (CI-safe)
+	cd core && ruff check .
+	cd tools && ruff check .
+	cd core && ruff format --check .
+	cd tools && ruff format --check .
+
+test: ## Run all tests
+	cd core && uv run python -m pytest tests/ -v
+
+install-hooks: ## Install pre-commit hooks
+	uv pip install pre-commit
+	pre-commit install
+
+frontend-dev: ## Start frontend dev server
+	cd core/frontend && npm run dev
+
+frontend-build: ## Build frontend for production
+	cd core/frontend && npm run build

README.md

@@ -1,27 +1,31 @@
 <p align="center">
-  <img width="100%" alt="Hive Banner" src="https://storage.googleapis.com/aden-prod-assets/website/aden-title-card.png" />
+  <img width="100%" alt="Hive Banner" src="https://github.com/user-attachments/assets/a027429b-5d3c-4d34-88e4-0feaeaabbab3" />
 </p>
 
 <p align="center">
   <a href="README.md">English</a> |
-  <a href="README.zh-CN.md">简体中文</a> |
-  <a href="README.es.md">Español</a> |
-  <a href="README.pt.md">Português</a> |
-  <a href="README.ja.md">日本語</a> |
-  <a href="README.ru.md">Русский</a>
+  <a href="docs/i18n/zh-CN.md">简体中文</a> |
+  <a href="docs/i18n/es.md">Español</a> |
+  <a href="docs/i18n/hi.md">हिन्दी</a> |
+  <a href="docs/i18n/pt.md">Português</a> |
+  <a href="docs/i18n/ja.md">日本語</a> |
+  <a href="docs/i18n/ru.md">Русский</a> |
+  <a href="docs/i18n/ko.md">한국어</a>
 </p>
 
-[![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/)
+<p align="center">
+  <a href="https://github.com/adenhq/hive/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="Apache 2.0 License" /></a>
+  <a href="https://www.ycombinator.com/companies/aden"><img src="https://img.shields.io/badge/Y%20Combinator-Aden-orange" alt="Y Combinator" /></a>
+  <a href="https://discord.com/invite/MXE49hrKDk"><img src="https://img.shields.io/discord/1172610340073242735?logo=discord&labelColor=%235462eb&logoColor=%23f5f5f5&color=%235462eb" alt="Discord" /></a>
+  <a href="https://x.com/aden_hq"><img src="https://img.shields.io/twitter/follow/teamaden?logo=X&color=%23f5f5f5" alt="Twitter Follow" /></a>
+  <a href="https://www.linkedin.com/company/teamaden/"><img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff" alt="LinkedIn" /></a>
+  <img src="https://img.shields.io/badge/MCP-102_Tools-00ADD8?style=flat-square" alt="MCP" />
+</p>
 
 <p align="center">
   <img src="https://img.shields.io/badge/AI_Agents-Self--Improving-brightgreen?style=flat-square" alt="AI Agents" />
   <img src="https://img.shields.io/badge/Multi--Agent-Systems-blue?style=flat-square" alt="Multi-Agent" />
-  <img src="https://img.shields.io/badge/Goal--Driven-Development-purple?style=flat-square" alt="Goal-Driven" />
+  <img src="https://img.shields.io/badge/Headless-Development-purple?style=flat-square" alt="Headless" />
   <img src="https://img.shields.io/badge/Human--in--the--Loop-orange?style=flat-square" alt="HITL" />
   <img src="https://img.shields.io/badge/Production--Ready-red?style=flat-square" alt="Production" />
 </p>
@@ -29,264 +33,383 @@
   <img src="https://img.shields.io/badge/OpenAI-supported-412991?style=flat-square&logo=openai" alt="OpenAI" />
   <img src="https://img.shields.io/badge/Anthropic-supported-d4a574?style=flat-square" alt="Anthropic" />
   <img src="https://img.shields.io/badge/Google_Gemini-supported-4285F4?style=flat-square&logo=google" alt="Gemini" />
-  <img src="https://img.shields.io/badge/MCP-19_Tools-00ADD8?style=flat-square" alt="MCP" />
 </p>
 
 ## Overview
 
-Build reliable, self-improving AI agents without hardcoding workflows. Define your goal through conversation with a coding agent, and the framework generates a node graph with dynamically created connection code. When things break, the framework captures failure data, evolves the agent through the coding agent, and redeploys. Built-in human-in-the-loop nodes, credential management, and real-time monitoring give you control without sacrificing adaptability.
+Build autonomous, reliable, self-improving AI agents without hardcoding workflows. Define your goal through conversation with a coding agent, and the framework generates a node graph with dynamically created connection code. When things break, the framework captures failure data, evolves the agent through the coding agent, and redeploys. Built-in human-in-the-loop nodes, credential management, and real-time monitoring give you control without sacrificing adaptability.
 
 Visit [adenhq.com](https://adenhq.com) for complete documentation, examples, and guides.
 
-## What is Aden
+https://github.com/user-attachments/assets/846c0cc7-ffd6-47fa-b4b7-495494857a55
 
-<p align="center">
-  <img width="100%" alt="Aden Architecture" src="docs/assets/aden-architecture-diagram.jpg" />
-</p>
+## Who Is Hive For?
 
-Aden is a platform for building, deploying, operating, and adapting AI agents:
+Hive is designed for developers and teams who want to build **production-grade AI agents** without manually wiring complex workflows.
 
-- **Build** - A Coding Agent generates specialized Worker Agents (Sales, Marketing, Ops) from natural language goals
-- **Deploy** - Headless deployment with CI/CD integration and full API lifecycle management
-- **Operate** - Real-time monitoring, observability, and runtime guardrails keep agents reliable
-- **Adapt** - Continuous evaluation, supervision, and adaptation ensure agents improve over time
-- **Infra** - Shared memory, LLM integrations, tools, and skills power every agent
+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
+- Strong guardrails, process, and controls
+- Continuous improvement based on failures
+- Multi-agent coordination
+- A framework that evolves with your goals
 
 ## Quick Links
 
 - **[Documentation](https://docs.adenhq.com/)** - Complete guides and API reference
 - **[Self-Hosting Guide](https://docs.adenhq.com/getting-started/quickstart)** - Deploy Hive on your infrastructure
 - **[Changelog](https://github.com/adenhq/hive/releases)** - Latest updates and releases
-<!-- - **[Roadmap](https://adenhq.com/roadmap)** - Upcoming features and plans -->
+- **[Roadmap](docs/roadmap.md)** - Upcoming features and plans
 - **[Report Issues](https://github.com/adenhq/hive/issues)** - Bug reports and feature requests
+- **[Contributing](CONTRIBUTING.md)** - How to contribute and submit PRs
 
 ## Quick Start
 
 ### Prerequisites
 
-- [Python 3.11+](https://www.python.org/downloads/) for agent development
-- [Docker](https://docs.docker.com/get-docker/) (v20.10+) - Optional, for containerized tools
+- Python 3.11+ for agent development
+- Claude Code, Codex CLI, or Cursor for utilizing agent skills
+
+> **Note for Windows Users:** It is strongly recommended to use **WSL (Windows Subsystem for Linux)** or **Git Bash** to run this framework. Some core automation scripts may not execute correctly in standard Command Prompt or PowerShell.
 
 ### Installation
 
+> **Note**
+> Hive uses a `uv` workspace layout and is not installed with `pip install`.
+> Running `pip install -e .` from the repository root will create a placeholder package and Hive will not function correctly.
+> Please use the quickstart script below to set up the environment.
+
 ```bash
 # Clone the repository
 git clone https://github.com/adenhq/hive.git
 cd hive
 
-# Run Python environment setup
-./scripts/setup-python.sh
+# Run quickstart setup
+./quickstart.sh
 ```
 
-This installs:
-- **framework** - Core agent runtime and graph executor
-- **aden_tools** - 19 MCP tools for agent capabilities
-- All required dependencies
+This sets up:
+
+- **framework** - Core agent runtime and graph executor (in `core/.venv`)
+- **aden_tools** - MCP tools for agent capabilities (in `tools/.venv`)
+- **credential store** - Encrypted API key storage (`~/.hive/credentials`)
+- **LLM provider** - Interactive default model configuration
+- All required Python dependencies with `uv`
 
 ### Build Your First Agent
 
 ```bash
-# Install Claude Code skills (one-time)
-./quickstart.sh
-
 # Build an agent using Claude Code
-claude> /building-agents
+claude> /hive
 
 # Test your agent
-claude> /testing-agent
+claude> /hive-debugger
 
-# Run your agent
-PYTHONPATH=core:exports python -m your_agent_name run --input '{...}'
+# (at separate terminal) Launch the interactive dashboard
+hive tui
+
+# Or run directly
+hive run exports/your_agent_name --input '{"key": "value"}'
 ```
 
-**[📖 Complete Setup Guide](ENVIRONMENT_SETUP.md)** - Detailed instructions for agent development
+## Coding Agent Support
+
+### Codex CLI
+
+Hive includes native support for [OpenAI Codex CLI](https://github.com/openai/codex) (v0.101.0+).
+
+1. **Config:** `.codex/config.toml` with `agent-builder` MCP server (tracked in git)
+2. **Skills:** `.agents/skills/` symlinks to Hive skills (tracked in git)
+3. **Launch:** Run `codex` in the repo root, then type `use hive`
+
+Example:
+
+```
+codex> use hive
+```
+
+### Opencode
+
+Hive includes native support for [Opencode](https://github.com/opencode-ai/opencode).
+
+1. **Setup:** Run the quickstart script
+2. **Launch:** Open Opencode in the project root.
+3. **Activate:** Type `/hive` in the chat to switch to the Hive Agent.
+4. **Verify:** Ask the agent _"List your tools"_ to confirm the connection.
+
+The agent has access to all Hive skills and can scaffold agents, add tools, and debug workflows directly from the chat.
+
+**[📖 Complete Setup Guide](docs/environment-setup.md)** - Detailed instructions for agent development
+
+### Antigravity IDE Support
+
+Skills and MCP servers are also available in [Antigravity IDE](https://antigravity.google/) (Google's AI-powered IDE). **Easiest:** open a terminal in the hive repo folder and run (use `./` — the script is inside the repo):
+
+```bash
+./scripts/setup-antigravity-mcp.sh
+```
+
+**Important:** Always restart/refresh Antigravity IDE after running the setup script—MCP servers only load on startup. After restart, **agent-builder** and **tools** MCP servers should connect. Skills are under `.agent/skills/` (symlinks to `.claude/skills/`). See [docs/antigravity-setup.md](docs/antigravity-setup.md) for manual setup and troubleshooting.
 
 ## Features
 
-- **Goal-Driven Development** - Define objectives in natural language; the coding agent generates the agent graph and connection code to achieve them
-- **Self-Adapting Agents** - Framework captures failures, updates objectives and updates the agent graph
-- **Dynamic Node Connections** - No predefined edges; connection code is generated by any capable LLM based on your goals
+- **[Goal-Driven Development](docs/key_concepts/goals_outcome.md)** - Define objectives in natural language; the coding agent generates the agent graph and connection code to achieve them
+- **[Adaptiveness](docs/key_concepts/evolution.md)** - Framework captures failures, calibrates according to the objectives, and evolves the agent graph
+- **[Dynamic Node Connections](docs/key_concepts/graph.md)** - No predefined edges; connection code is generated by any capable LLM based on your goals
 - **SDK-Wrapped Nodes** - Every node gets shared memory, local RLM memory, monitoring, tools, and LLM access out of the box
-- **Human-in-the-Loop** - Intervention nodes that pause execution for human input with configurable timeouts and escalation
+- **[Human-in-the-Loop](docs/key_concepts/graph.md#human-in-the-loop)** - Intervention nodes that pause execution for human input with configurable timeouts and escalation
 - **Real-time Observability** - WebSocket streaming for live monitoring of agent execution, decisions, and node-to-node communication
+- **Interactive TUI Dashboard** - Terminal-based dashboard with live graph view, event log, and chat interface for agent interaction
 - **Cost & Budget Control** - Set spending limits, throttles, and automatic model degradation policies
 - **Production-Ready** - Self-hostable, built for scale and reliability
 
+## Integration
+
+<a href="https://github.com/adenhq/hive/tree/main/tools/src/aden_tools/tools"><img width="100%" alt="Integration" src="https://github.com/user-attachments/assets/a1573f93-cf02-4bb8-b3d5-b305b05b1e51" /></a>
+
+Hive is built to be model-agnostic and system-agnostic.
+
+- **LLM flexibility** - Hive Framework is designed to support various types of LLMs, including hosted and local models through LiteLLM-compatible providers.
+- **Business system connectivity** - Hive Framework is designed to connect to all kinds of business systems as tools, such as CRM, support, messaging, data, file, and internal APIs via MCP.
+
 ## Why Aden
 
-Traditional agent frameworks require you to manually design workflows, define agent interactions, and handle failures reactively. Aden flips this paradigm—**you describe outcomes, and the system builds itself**.
+Hive focuses on generating agents that run real business processes rather than generic agents. Instead of requiring you to manually design workflows, define agent interactions, and handle failures reactively, Hive flips the paradigm: **you describe outcomes, and the system builds itself**—delivering an outcome-driven, adaptive experience with an easy-to-use set of tools and integrations.
 
 ```mermaid
 flowchart LR
-    subgraph BUILD["🏗️ BUILD"]
-        GOAL["Define Goal<br/>+ Success Criteria"] --> NODES["Add Nodes<br/>LLM/Router/Function"]
-        NODES --> EDGES["Connect Edges<br/>on_success/failure/conditional"]
-        EDGES --> TEST["Test & Validate"] --> APPROVE["Approve & Export"]
-    end
+    GOAL["Define Goal"] --> GEN["Auto-Generate Graph"]
+    GEN --> EXEC["Execute Agents"]
+    EXEC --> MON["Monitor & Observe"]
+    MON --> CHECK{{"Pass?"}}
+    CHECK -- "Yes" --> DONE["Deliver Result"]
+    CHECK -- "No" --> EVOLVE["Evolve Graph"]
+    EVOLVE --> EXEC
 
-    subgraph EXPORT["📦 EXPORT"]
-        direction TB
-        JSON["agent.json<br/>(GraphSpec)"]
-        TOOLS["tools.py<br/>(Functions)"]
-        MCP["mcp_servers.json<br/>(Integrations)"]
-    end
+    GOAL -.- V1["Natural Language"]
+    GEN -.- V2["Instant Architecture"]
+    EXEC -.- V3["Easy Integrations"]
+    MON -.- V4["Full visibility"]
+    EVOLVE -.- V5["Adaptability"]
+    DONE -.- V6["Reliable outcomes"]
 
-    subgraph RUN["🚀 RUNTIME"]
-        LOAD["AgentRunner<br/>Load + Parse"] --> SETUP["Setup Runtime<br/>+ ToolRegistry"]
-        SETUP --> EXEC["GraphExecutor<br/>Execute Nodes"]
-
-        subgraph DECISION["Decision Recording"]
-            DEC1["runtime.decide()<br/>intent → options → choice"]
-            DEC2["runtime.record_outcome()<br/>success, result, metrics"]
-        end
-    end
-
-    subgraph INFRA["⚙️ INFRASTRUCTURE"]
-        CTX["NodeContext<br/>memory • llm • tools"]
-        STORE[("FileStorage<br/>Runs & Decisions")]
-    end
-
-    APPROVE --> EXPORT
-    EXPORT --> LOAD
-    EXEC --> DECISION
-    EXEC --> CTX
-    DECISION --> STORE
-    STORE -.->|"Analyze & Improve"| NODES
-
-    style BUILD fill:#ffbe42,stroke:#cc5d00,stroke-width:3px,color:#333
-    style EXPORT fill:#fff59d,stroke:#ed8c00,stroke-width:2px,color:#333
-    style RUN fill:#ffb100,stroke:#cc5d00,stroke-width:3px,color:#333
-    style DECISION fill:#ffcc80,stroke:#ed8c00,stroke-width:2px,color:#333
-    style INFRA fill:#e8763d,stroke:#cc5d00,stroke-width:3px,color:#fff
-    style STORE fill:#ed8c00,stroke:#cc5d00,stroke-width:2px,color:#fff
+    style GOAL fill:#ffbe42,stroke:#cc5d00,stroke-width:2px,color:#333
+    style GEN fill:#ffb100,stroke:#cc5d00,stroke-width:2px,color:#333
+    style EXEC fill:#ff9800,stroke:#cc5d00,stroke-width:2px,color:#fff
+    style MON fill:#ff9800,stroke:#cc5d00,stroke-width:2px,color:#fff
+    style CHECK fill:#fff59d,stroke:#ed8c00,stroke-width:2px,color:#333
+    style DONE fill:#4caf50,stroke:#2e7d32,stroke-width:2px,color:#fff
+    style EVOLVE fill:#e8763d,stroke:#cc5d00,stroke-width:2px,color:#fff
+    style V1 fill:#fff,stroke:#ed8c00,stroke-width:1px,color:#cc5d00
+    style V2 fill:#fff,stroke:#ed8c00,stroke-width:1px,color:#cc5d00
+    style V3 fill:#fff,stroke:#ed8c00,stroke-width:1px,color:#cc5d00
+    style V4 fill:#fff,stroke:#ed8c00,stroke-width:1px,color:#cc5d00
+    style V5 fill:#fff,stroke:#ed8c00,stroke-width:1px,color:#cc5d00
+    style V6 fill:#fff,stroke:#ed8c00,stroke-width:1px,color:#cc5d00
 ```
 
-### The Aden Advantage
+### The Hive Advantage
 
-| Traditional Frameworks     | Aden                                   |
+| Traditional Frameworks     | Hive                                   |
 | -------------------------- | -------------------------------------- |
 | Hardcode agent workflows   | Describe goals in natural language     |
 | Manual graph definition    | Auto-generated agent graphs            |
-| Reactive error handling    | Proactive self-evolution               |
+| Reactive error handling    | Outcome-evaluation and adaptiveness    |
 | Static tool configurations | Dynamic SDK-wrapped nodes              |
 | Separate monitoring setup  | Built-in real-time observability       |
 | DIY budget management      | Integrated cost controls & degradation |
 
 ### How It Works
 
-1. **Define Your Goal** → Describe what you want to achieve in plain English
-2. **Coding Agent Generates** → Creates the agent graph, connection code, and test cases
-3. **Workers Execute** → SDK-wrapped nodes run with full observability and tool access
+1. **[Define Your Goal](docs/key_concepts/goals_outcome.md)** → Describe what you want to achieve in plain English
+2. **Coding Agent Generates** → Creates the [agent graph](docs/key_concepts/graph.md), connection code, and test cases
+3. **[Workers Execute](docs/key_concepts/worker_agent.md)** → SDK-wrapped nodes run with full observability and tool access
 4. **Control Plane Monitors** → Real-time metrics, budget enforcement, policy management
-5. **Self-Improve** → On failure, the system evolves the graph and redeploys automatically
+5. **[Adaptiveness](docs/key_concepts/evolution.md)** → On failure, the system evolves the graph and redeploys automatically
 
-## How Aden Compares
+## Run Agents
 
-Aden takes a fundamentally different approach to agent development. While most frameworks require you to hardcode workflows or manually define agent graphs, Aden uses a **coding agent to generate your entire agent system** from natural language goals. When agents fail, the framework doesn't just log errors—it **automatically evolves the agent graph** and redeploys.
-
-### Comparison Table
-
-| Framework                           | Category                  | Approach                                                        | Aden Difference                                           |
-| ----------------------------------- | ------------------------- | --------------------------------------------------------------- | --------------------------------------------------------- |
-| **LangChain, LlamaIndex, Haystack** | Component Libraries       | Predefined components for RAG/LLM apps; manual connection logic | Generates entire graph and connection code upfront        |
-| **CrewAI, AutoGen, Swarm**          | Multi-Agent Orchestration | Role-based agents with predefined collaboration patterns        | Dynamically creates agents/connections; adapts on failure |
-| **PydanticAI, Mastra, Agno**        | Type-Safe Frameworks      | Structured outputs and validation for known workflows           | Evolving workflows; structure emerges through iteration   |
-| **Agent Zero, Letta**               | Personal AI Assistants    | Memory and learning; OS-as-tool or stateful memory focus        | Production multi-agent systems with self-healing          |
-| **CAMEL**                           | Research Framework        | Emergent behavior in large-scale simulations (up to 1M agents)  | Production-oriented with reliable execution and recovery  |
-| **TEN Framework, Genkit**           | Infrastructure Frameworks | Real-time multimodal (TEN) or full-stack AI (Genkit)            | Higher abstraction—generates and evolves agent logic      |
-| **GPT Engineer, Motia**             | Code Generation           | Code from specs (GPT Engineer) or "Step" primitive (Motia)      | Self-adapting graphs with automatic failure recovery      |
-| **Trading Agents**                  | Domain-Specific           | Hardcoded trading firm roles on LangGraph                       | Domain-agnostic; generates structures for any use case    |
-
-### When to Choose Aden
-
-Choose Aden when you need:
-
-- Agents that **self-improve from failures** without manual intervention
-- **Goal-driven development** where you describe outcomes, not workflows
-- **Production reliability** with automatic recovery and redeployment
-- **Rapid iteration** on agent architectures without rewriting code
-- **Full observability** with real-time monitoring and human oversight
-
-Choose other frameworks when you need:
-
-- **Type-safe, predictable workflows** (PydanticAI, Mastra)
-- **RAG and document processing** (LlamaIndex, Haystack)
-- **Research on agent emergence** (CAMEL)
-- **Real-time voice/multimodal** (TEN Framework)
-- **Simple component chaining** (LangChain, Swarm)
-
-## Project Structure
-
-```
-hive/
-├── core/                   # Core framework - Agent runtime, graph executor, protocols
-├── tools/                  # MCP Tools Package - 19 tools for agent capabilities
-├── exports/                # Agent packages - Pre-built agents and examples
-├── docs/                   # Documentation and guides
-├── scripts/                # Build and utility scripts
-├── .claude/                # Claude Code skills for building agents
-├── ENVIRONMENT_SETUP.md    # Python setup guide for agent development
-├── DEVELOPER.md            # Developer guide
-├── CONTRIBUTING.md         # Contribution guidelines
-└── ROADMAP.md              # Product roadmap
-```
-
-## Development
-
-### Python Agent Development
-
-For building and running goal-driven agents with the framework:
+The `hive` CLI is the primary interface for running agents.
 
 ```bash
-# One-time setup
-./scripts/setup-python.sh
+# Browse and run agents interactively (Recommended)
+hive tui
 
-# This installs:
-# - framework package (core runtime)
-# - aden_tools package (19 MCP tools)
-# - All dependencies
+# Run a specific agent directly
+hive run exports/my_agent --input '{"task": "Your input here"}'
 
-# Build new agents using Claude Code skills
-claude> /building-agents
+# Run a specific agent with the TUI dashboard
+hive run exports/my_agent --tui
 
-# Test agents
-claude> /testing-agent
-
-# Run agents
-PYTHONPATH=core:exports python -m agent_name run --input '{...}'
+# Interactive REPL
+hive shell
 ```
 
-See [ENVIRONMENT_SETUP.md](ENVIRONMENT_SETUP.md) for complete setup instructions.
+The TUI scans both `exports/` and `examples/templates/` for available agents.
+
+> **Using Python directly (alternative):** You can also run agents with `PYTHONPATH=exports uv run python -m agent_name run --input '{...}'`
+
+See [environment-setup.md](docs/environment-setup.md) for complete setup instructions.
 
 ## Documentation
 
-- **[Developer Guide](DEVELOPER.md)** - Comprehensive guide for developers
+- **[Developer Guide](docs/developer-guide.md)** - Comprehensive guide for developers
 - [Getting Started](docs/getting-started.md) - Quick setup instructions
+- [TUI Guide](docs/tui-selection-guide.md) - Interactive dashboard usage
 - [Configuration Guide](docs/configuration.md) - All configuration options
-- [Architecture Overview](docs/architecture.md) - System design and structure
+- [Architecture Overview](docs/architecture/README.md) - System design and structure
 
 ## Roadmap
 
-Aden Agent Framework aims to help developers build outcome oriented, self-adaptive agents. Please find our roadmap here
-
-[ROADMAP.md](ROADMAP.md)
+Aden Hive Agent Framework aims to help developers build outcome-oriented, self-adaptive agents. See [roadmap.md](docs/roadmap.md) for details.
 
 ```mermaid
-timeline
-    title Aden Agent Framework Roadmap
-    section Foundation
-        Architecture : Node-Based Architecture : Python SDK : LLM Integration (OpenAI, Anthropic, Google) : Communication Protocol
-        Coding Agent : Goal Creation Session : Worker Agent Creation : MCP Tools Integration
-        Worker Agent : Human-in-the-Loop : Callback Handlers : Intervention Points : Streaming Interface
-        Tools : File Use : Memory (STM/LTM) : Web Search : Web Scraper : Audit Trail
-        Core : Eval System : Pydantic Validation : Docker Deployment : Documentation : Sample Agents
-    section Expansion
-        Intelligence : Guardrails : Streaming Mode : Semantic Search
-        Platform : JavaScript SDK : Custom Tool Integrator : Credential Store
-        Deployment : Self-Hosted : Cloud Services : CI/CD Pipeline
-        Templates : Sales Agent : Marketing Agent : Analytics Agent : Training Agent : Smart Form Agent
+flowchart TB
+    %% Main Entity
+    User([User])
+
+    %% =========================================
+    %% EXTERNAL EVENT SOURCES
+    %% =========================================
+    subgraph ExtEventSource [External Event Source]
+        E_Sch["Schedulers"]
+        E_WH["Webhook"]
+        E_SSE["SSE"]
+    end
+
+    %% =========================================
+    %% SYSTEM NODES
+    %% =========================================
+    subgraph WorkerBees [Worker Bees]
+        WB_C["Conversation"]
+        WB_SP["System prompt"]
+
+        subgraph Graph [Graph]
+            direction TB
+            N1["Node"] --> N2["Node"] --> N3["Node"]
+            N1 -.-> AN["Active Node"]
+            N2 -.-> AN
+            N3 -.-> AN
+
+            %% Nested Event Loop Node
+            subgraph EventLoopNode [Event Loop Node]
+                ELN_L["listener"]
+                ELN_SP["System Prompt<br/>(Task)"]
+                ELN_EL["Event loop"]
+                ELN_C["Conversation"]
+            end
+        end
+    end
+
+    subgraph JudgeNode [Judge]
+        J_C["Criteria"]
+        J_P["Principles"]
+        J_EL["Event loop"] <--> J_S["Scheduler"]
+    end
+
+    subgraph QueenBee [Queen Bee]
+        QB_SP["System prompt"]
+        QB_EL["Event loop"]
+        QB_C["Conversation"]
+    end
+
+    subgraph Infra [Infra]
+        SA["Sub Agent"]
+        TR["Tool Registry"]
+        WTM["Write through Conversation Memory<br/>(Logs/RAM/Harddrive)"]
+        SM["Shared Memory<br/>(State/Harddrive)"]
+        EB["Event Bus<br/>(RAM)"]
+        CS["Credential Store<br/>(Harddrive/Cloud)"]
+    end
+
+    subgraph PC [PC]
+        B["Browser"]
+        CB["Codebase<br/>v 0.0.x ... v n.n.n"]
+    end
+
+    %% =========================================
+    %% CONNECTIONS & DATA FLOW
+    %% =========================================
+
+    %% External Event Routing
+    E_Sch --> ELN_L
+    E_WH --> ELN_L
+    E_SSE --> ELN_L
+    ELN_L -->|"triggers"| ELN_EL
+
+    %% User Interactions
+    User -->|"Talk"| WB_C
+    User -->|"Talk"| QB_C
+    User -->|"Read/Write Access"| CS
+
+    %% Inter-System Logic
+    ELN_C <-->|"Mirror"| WB_C
+    WB_C -->|"Focus"| AN
+
+    WorkerBees -->|"Inquire"| JudgeNode
+    JudgeNode -->|"Approve"| WorkerBees
+
+    %% Judge Alignments
+    J_C <-.->|"aligns"| WB_SP
+    J_P <-.->|"aligns"| QB_SP
+
+    %% Escalate path
+    J_EL -->|"Report (Escalate)"| QB_EL
+
+    %% Pub/Sub Logic
+    AN -->|"publish"| EB
+    EB -->|"subscribe"| QB_C
+
+    %% Infra and Process Spawning
+    ELN_EL -->|"Spawn"| SA
+    SA -->|"Inform"| ELN_EL
+    SA -->|"Starts"| B
+    B -->|"Report"| ELN_EL
+    TR -->|"Assigned"| ELN_EL
+    CB -->|"Modify Worker Bee"| WB_C
+
+    %% =========================================
+    %% SHARED MEMORY & LOGS ACCESS
+    %% =========================================
+
+    %% Worker Bees Access (link to node inside Graph subgraph)
+    AN <-->|"Read/Write"| WTM
+    AN <-->|"Read/Write"| SM
+
+    %% Queen Bee Access
+    QB_C <-->|"Read/Write"| WTM
+    QB_EL <-->|"Read/Write"| SM
+
+    %% Credentials Access
+    CS -->|"Read Access"| QB_C
 ```
 
+## Contributing
+
+We welcome contributions from the community! We’re especially looking for help building tools, integrations, and example agents for the framework ([check #2805](https://github.com/adenhq/hive/issues/2805)). If you’re interested in extending its functionality, this is the perfect place to start. Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
+
+**Important:** Please get assigned to an issue before submitting a PR. Comment on an issue to claim it, and a maintainer will assign you. Issues with reproducible steps and proposals are prioritized. This helps prevent duplicate work.
+
+1. Find or create an issue and get assigned
+2. Fork the repository
+3. Create your feature branch (`git checkout -b feature/amazing-feature`)
+4. Commit your changes (`git commit -m 'Add amazing feature'`)
+5. Push to the branch (`git push origin feature/amazing-feature`)
+6. Open a Pull Request
+
 ## Community & Support
 
 We use [Discord](https://discord.com/invite/MXE49hrKDk) for support, feature requests, and community discussions.
@@ -295,16 +418,6 @@ We use [Discord](https://discord.com/invite/MXE49hrKDk) for support, feature req
 - Twitter/X - [@adenhq](https://x.com/aden_hq)
 - LinkedIn - [Company Page](https://www.linkedin.com/company/teamaden/)
 
-## Contributing
-
-We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
-
-1. Fork the repository
-2. Create your feature branch (`git checkout -b feature/amazing-feature`)
-3. Commit your changes (`git commit -m 'Add amazing feature'`)
-4. Push to the branch (`git push origin feature/amazing-feature`)
-5. Open a Pull Request
-
 ## Join Our Team
 
 **We're hiring!** Join us in engineering, research, and go-to-market roles.
@@ -321,69 +434,57 @@ This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENS
 
 ## Frequently Asked Questions (FAQ)
 
-**Q: Does Aden depend on LangChain or other agent frameworks?**
+**Q: What LLM providers does Hive support?**
 
-No. Aden is built from the ground up with no dependencies on LangChain, CrewAI, or other agent frameworks. The framework is designed to be lean and flexible, generating agent graphs dynamically rather than relying on predefined components.
+Hive supports 100+ LLM providers through LiteLLM integration, including OpenAI (GPT-4, GPT-4o), Anthropic (Claude models), Google Gemini, DeepSeek, Mistral, Groq, and many more. Simply set the appropriate API key environment variable and specify the model name.
 
-**Q: What LLM providers does Aden support?**
+**Q: Can I use Hive with local AI models like Ollama?**
 
-Aden supports 100+ LLM providers through LiteLLM integration, including OpenAI (GPT-4, GPT-4o), Anthropic (Claude models), Google Gemini, Mistral, Groq, and many more. Simply set the appropriate API key environment variable and specify the model name.
+Yes! Hive supports local models through LiteLLM. Simply use the model name format `ollama/model-name` (e.g., `ollama/llama3`, `ollama/mistral`) and ensure Ollama is running locally.
 
-**Q: Can I use Aden with local AI models like Ollama?**
+**Q: What makes Hive different from other agent frameworks?**
 
-Yes! Aden supports local models through LiteLLM. Simply use the model name format `ollama/model-name` (e.g., `ollama/llama3`, `ollama/mistral`) and ensure Ollama is running locally.
+Hive generates your entire agent system from natural language goals using a coding agent—you don't hardcode workflows or manually define graphs. When agents fail, the framework automatically captures failure data, [evolves the agent graph](docs/key_concepts/evolution.md), and redeploys. This self-improving loop is unique to Aden.
 
-**Q: What makes Aden different from other agent frameworks?**
+**Q: Is Hive open-source?**
 
-Aden generates your entire agent system from natural language goals using a coding agent—you don't hardcode workflows or manually define graphs. When agents fail, the framework automatically captures failure data, evolves the agent graph, and redeploys. This self-improving loop is unique to Aden.
+Yes, Hive is fully open-source under the Apache License 2.0. We actively encourage community contributions and collaboration.
 
-**Q: Is Aden open-source?**
+**Q: Can Hive handle complex, production-scale use cases?**
 
-Yes, Aden is fully open-source under the Apache License 2.0. We actively encourage community contributions and collaboration.
+Yes. Hive is explicitly designed for production environments with features like automatic failure recovery, real-time observability, cost controls, and horizontal scaling support. The framework handles both simple automations and complex multi-agent workflows.
 
-**Q: Does Aden collect data from users?**
+**Q: Does Hive support human-in-the-loop workflows?**
 
-Aden collects telemetry data for monitoring and observability purposes, including token usage, latency metrics, and cost tracking. Content capture (prompts and responses) is configurable and stored with team-scoped data isolation. All data stays within your infrastructure when self-hosted.
+Yes, Hive fully supports [human-in-the-loop](docs/key_concepts/graph.md#human-in-the-loop) workflows through intervention nodes that pause execution for human input. These include configurable timeouts and escalation policies, allowing seamless collaboration between human experts and AI agents.
 
-**Q: What deployment options does Aden support?**
+**Q: What programming languages does Hive support?**
 
-Aden supports Docker Compose deployment out of the box, with both production and development configurations. Self-hosted deployments work on any infrastructure supporting Docker. Cloud deployment options and Kubernetes-ready configurations are on the roadmap.
+The Hive framework is built in Python. A JavaScript/TypeScript SDK is on the roadmap.
 
-**Q: Can Aden handle complex, production-scale use cases?**
-
-Yes. Aden is explicitly designed for production environments with features like automatic failure recovery, real-time observability, cost controls, and horizontal scaling support. The framework handles both simple automations and complex multi-agent workflows.
-
-**Q: Does Aden support human-in-the-loop workflows?**
-
-Yes, Aden fully supports human-in-the-loop workflows through intervention nodes that pause execution for human input. These include configurable timeouts and escalation policies, allowing seamless collaboration between human experts and AI agents.
-
-**Q: What monitoring and debugging tools does Aden provide?**
-
-Aden includes comprehensive observability features: real-time WebSocket streaming for live agent execution monitoring, TimescaleDB-powered analytics for cost and performance metrics, health check endpoints for Kubernetes integration, and 19 MCP tools for budget management, agent status, and policy control.
-
-**Q: What programming languages does Aden support?**
-
-Aden provides SDKs for both Python and JavaScript/TypeScript. The Python SDK includes integration templates for LangGraph, LangFlow, and LiveKit. The backend is Node.js/TypeScript, and the frontend is React/TypeScript.
-
-**Q: Can Aden agents interact with external tools and APIs?**
+**Q: Can Hive agents interact with external tools and APIs?**
 
 Yes. Aden's SDK-wrapped nodes provide built-in tool access, and the framework supports flexible tool ecosystems. Agents can integrate with external APIs, databases, and services through the node architecture.
 
-**Q: How does cost control work in Aden?**
+**Q: How does cost control work in Hive?**
 
-Aden provides granular budget controls including spending limits, throttles, and automatic model degradation policies. You can set budgets at the team, agent, or workflow level, with real-time cost tracking and alerts.
+Hive provides granular budget controls including spending limits, throttles, and automatic model degradation policies. You can set budgets at the team, agent, or workflow level, with real-time cost tracking and alerts.
 
 **Q: Where can I find examples and documentation?**
 
-Visit [docs.adenhq.com](https://docs.adenhq.com/) for complete guides, API reference, and getting started tutorials. The repository also includes documentation in the `docs/` folder and a comprehensive [DEVELOPER.md](DEVELOPER.md) guide.
+Visit [docs.adenhq.com](https://docs.adenhq.com/) for complete guides, API reference, and getting started tutorials. The repository also includes documentation in the `docs/` folder and a comprehensive [developer guide](docs/developer-guide.md).
 
 **Q: How can I contribute to Aden?**
 
 Contributions are welcome! Fork the repository, create your feature branch, implement your changes, and submit a pull request. See [CONTRIBUTING.md](CONTRIBUTING.md) for detailed guidelines.
 
-**Q: Does Aden offer enterprise support?**
+**Q: When will my team start seeing results from Aden's adaptive agents?**
 
-For enterprise inquiries, contact the Aden team through [adenhq.com](https://adenhq.com) or join our [Discord community](https://discord.com/invite/MXE49hrKDk) for support and discussions.
+Aden's adaptation loop begins working from the first execution. When an agent fails, the framework captures the failure data, helping developers evolve the agent graph through the coding agent. How quickly this translates to measurable results depends on the complexity of your use case, the quality of your goal definitions, and the volume of executions generating feedback.
+
+**Q: How does Hive compare to other agent frameworks?**
+
+Hive focuses on generating agents that run real business processes, rather than generic agents. This vision emphasizes outcome-driven design, adaptability, and an easy-to-use set of tools and integrations.
 
 ---
 

README.zh-CN.md

@@ -1,339 +0,0 @@
-<p align="center">
-  <img width="100%" alt="Hive Banner" src="https://storage.googleapis.com/aden-prod-assets/website/aden-title-card.png" />
-</p>
-
-<p align="center">
-  <a href="README.md">English</a> |
-  <a href="README.zh-CN.md">简体中文</a> |
-  <a href="README.es.md">Español</a> |
-  <a href="README.pt.md">Português</a> |
-  <a href="README.ja.md">日本語</a> |
-  <a href="README.ru.md">Русский</a>
-</p>
-
-[![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/)
-
-<p align="center">
-  <img src="https://img.shields.io/badge/AI_Agents-Self--Improving-brightgreen?style=flat-square" alt="AI Agents" />
-  <img src="https://img.shields.io/badge/Multi--Agent-Systems-blue?style=flat-square" alt="Multi-Agent" />
-  <img src="https://img.shields.io/badge/Goal--Driven-Development-purple?style=flat-square" alt="Goal-Driven" />
-  <img src="https://img.shields.io/badge/Human--in--the--Loop-orange?style=flat-square" alt="HITL" />
-  <img src="https://img.shields.io/badge/Production--Ready-red?style=flat-square" alt="Production" />
-</p>
-<p align="center">
-  <img src="https://img.shields.io/badge/OpenAI-supported-412991?style=flat-square&logo=openai" alt="OpenAI" />
-  <img src="https://img.shields.io/badge/Anthropic-supported-d4a574?style=flat-square" alt="Anthropic" />
-  <img src="https://img.shields.io/badge/Google_Gemini-supported-4285F4?style=flat-square&logo=google" alt="Gemini" />
-  <img src="https://img.shields.io/badge/MCP-19_Tools-00ADD8?style=flat-square" alt="MCP" />
-</p>
-
-## 概述
-
-构建可靠的、自我改进的 AI 智能体，无需硬编码工作流。通过与编码智能体对话来定义目标，框架会生成带有动态创建连接代码的节点图。当出现问题时，框架会捕获故障数据，通过编码智能体进化智能体，并重新部署。内置的人机协作节点、凭证管理和实时监控让您在保持适应性的同时拥有完全控制权。
-
-访问 [adenhq.com](https://adenhq.com) 获取完整文档、示例和指南。
-
-## 什么是 Aden
-
-<p align="center">
-  <img width="100%" alt="Aden Architecture" src="docs/assets/aden-architecture-diagram.jpg" />
-</p>
-
-Aden 是一个用于构建、部署、运营和适应 AI 智能体的平台：
-
-- **构建** - 编码智能体根据自然语言目标生成专业的工作智能体（销售、营销、运营）
-- **部署** - 无头部署，支持 CI/CD 集成和完整的 API 生命周期管理
-- **运营** - 实时监控、可观测性和运行时护栏确保智能体可靠运行
-- **适应** - 持续评估、监督和适应确保智能体随时间改进
-- **基础设施** - 共享内存、LLM 集成、工具和技能为每个智能体提供支持
-
-## 快速链接
-
-- **[文档](https://docs.adenhq.com/)** - 完整指南和 API 参考
-- **[自托管指南](https://docs.adenhq.com/getting-started/quickstart)** - 在您的基础设施上部署 Hive
-- **[更新日志](https://github.com/adenhq/hive/releases)** - 最新更新和版本
-<!-- - **[路线图](https://adenhq.com/roadmap)** - 即将推出的功能和计划 -->
-- **[报告问题](https://github.com/adenhq/hive/issues)** - Bug 报告和功能请求
-
-## 快速开始
-
-### 前置要求
-
-- [Python 3.11+](https://www.python.org/downloads/) - 用于智能体开发
-- [Docker](https://docs.docker.com/get-docker/) (v20.10+) - 可选，用于容器化工具
-
-### 安装
-
-```bash
-# 克隆仓库
-git clone https://github.com/adenhq/hive.git
-cd hive
-
-# 运行 Python 环境设置
-./scripts/setup-python.sh
-```
-
-这将安装：
-- **framework** - 核心智能体运行时和图执行器
-- **aden_tools** - 19 个 MCP 工具提供智能体能力
-- 所有必需的依赖项
-
-### 构建您的第一个智能体
-
-```bash
-# 安装 Claude Code 技能（一次性）
-./quickstart.sh
-
-# 使用 Claude Code 构建智能体
-claude> /building-agents
-
-# 测试您的智能体
-claude> /testing-agent
-
-# 运行您的智能体
-PYTHONPATH=core:exports python -m your_agent_name run --input '{...}'
-```
-
-**[📖 完整设置指南](ENVIRONMENT_SETUP.md)** - 智能体开发的详细说明
-
-## 功能特性
-
-- **目标驱动开发** - 用自然语言定义目标；编码智能体生成智能体图和连接代码来实现它们
-- **自适应智能体** - 框架捕获故障，更新目标并更新智能体图
-- **动态节点连接** - 没有预定义边；连接代码由任何有能力的 LLM 根据您的目标生成
-- **SDK 封装节点** - 每个节点开箱即用地获得共享内存、本地 RLM 内存、监控、工具和 LLM 访问
-- **人机协作** - 干预节点暂停执行以等待人工输入，支持可配置的超时和升级
-- **实时可观测性** - WebSocket 流式传输用于实时监控智能体执行、决策和节点间通信
-- **成本与预算控制** - 设置支出限制、节流和自动模型降级策略
-- **生产就绪** - 可自托管，为规模和可靠性而构建
-
-## 为什么选择 Aden
-
-传统智能体框架要求您手动设计工作流、定义智能体交互并被动处理故障。Aden 颠覆了这一范式——**您描述结果，系统自动构建自己**。
-
-```mermaid
-flowchart LR
-    subgraph BUILD["🏗️ BUILD"]
-        GOAL["Define Goal<br/>+ Success Criteria"] --> NODES["Add Nodes<br/>LLM/Router/Function"]
-        NODES --> EDGES["Connect Edges<br/>on_success/failure/conditional"]
-        EDGES --> TEST["Test & Validate"] --> APPROVE["Approve & Export"]
-    end
-
-    subgraph EXPORT["📦 EXPORT"]
-        direction TB
-        JSON["agent.json<br/>(GraphSpec)"]
-        TOOLS["tools.py<br/>(Functions)"]
-        MCP["mcp_servers.json<br/>(Integrations)"]
-    end
-
-    subgraph RUN["🚀 RUNTIME"]
-        LOAD["AgentRunner<br/>Load + Parse"] --> SETUP["Setup Runtime<br/>+ ToolRegistry"]
-        SETUP --> EXEC["GraphExecutor<br/>Execute Nodes"]
-
-        subgraph DECISION["Decision Recording"]
-            DEC1["runtime.decide()<br/>intent → options → choice"]
-            DEC2["runtime.record_outcome()<br/>success, result, metrics"]
-        end
-    end
-
-    subgraph INFRA["⚙️ INFRASTRUCTURE"]
-        CTX["NodeContext<br/>memory • llm • tools"]
-        STORE[("FileStorage<br/>Runs & Decisions")]
-    end
-
-    APPROVE --> EXPORT
-    EXPORT --> LOAD
-    EXEC --> DECISION
-    EXEC --> CTX
-    DECISION --> STORE
-    STORE -.->|"Analyze & Improve"| NODES
-
-    style BUILD fill:#ffbe42,stroke:#cc5d00,stroke-width:3px,color:#333
-    style EXPORT fill:#fff59d,stroke:#ed8c00,stroke-width:2px,color:#333
-    style RUN fill:#ffb100,stroke:#cc5d00,stroke-width:3px,color:#333
-    style DECISION fill:#ffcc80,stroke:#ed8c00,stroke-width:2px,color:#333
-    style INFRA fill:#e8763d,stroke:#cc5d00,stroke-width:3px,color:#fff
-    style STORE fill:#ed8c00,stroke:#cc5d00,stroke-width:2px,color:#fff
-```
-
-### Aden 的优势
-
-| 传统框架 | Aden |
-|----------|------|
-| 硬编码智能体工作流 | 用自然语言描述目标 |
-| 手动图定义 | 自动生成智能体图 |
-| 被动错误处理 | 主动自我进化 |
-| 静态工具配置 | 动态 SDK 封装节点 |
-| 单独设置监控 | 内置实时可观测性 |
-| DIY 预算管理 | 集成成本控制和降级 |
-
-### 工作原理
-
-1. **定义目标** → 用简单英语描述您想要实现的目标
-2. **编码智能体生成** → 创建智能体图、连接代码和测试用例
-3. **工作节点执行** → SDK 封装节点以完全可观测性和工具访问运行
-4. **控制平面监控** → 实时指标、预算执行、策略管理
-5. **自我改进** → 失败时，系统进化图并自动重新部署
-
-## Aden 与其他框架的比较
-
-Aden 在智能体开发方面采取了根本不同的方法。虽然大多数框架要求您硬编码工作流或手动定义智能体图，但 Aden 使用**编码智能体从自然语言目标生成整个智能体系统**。当智能体失败时，框架不仅记录错误——它会**自动进化智能体图**并重新部署。
-
-> **注意：** 详细的框架比较表和常见问题解答，请参阅英文版 [README.md](README.md)。
-
-### 何时选择 Aden
-
-选择 Aden 当您需要：
-
-- 智能体从失败中**自我改进**而无需人工干预
-- **目标驱动的开发**，您描述结果而非工作流
-- 具有自动恢复和重新部署的**生产可靠性**
-- 无需重写代码即可**快速迭代**智能体架构
-- 具有实时监控和人工监督的**完整可观测性**
-
-选择其他框架当您需要：
-
-- **类型安全、可预测的工作流**（PydanticAI、Mastra）
-- **RAG 和文档处理**（LlamaIndex、Haystack）
-- **智能体涌现的研究**（CAMEL）
-- **实时语音/多模态**（TEN Framework）
-- **简单的组件链接**（LangChain、Swarm）
-
-## 项目结构
-
-```
-hive/
-├── core/                   # 核心框架 - 智能体运行时、图执行器、协议
-├── tools/                  # MCP 工具包 - 19 个工具提供智能体能力
-├── exports/                # 智能体包 - 预构建的智能体和示例
-├── docs/                   # 文档和指南
-├── scripts/                # 构建和实用脚本
-├── .claude/                # Claude Code 技能用于构建智能体
-├── ENVIRONMENT_SETUP.md    # 智能体开发的 Python 设置指南
-├── DEVELOPER.md            # 开发者指南
-├── CONTRIBUTING.md         # 贡献指南
-└── ROADMAP.md              # 产品路线图
-```
-
-## 开发
-
-### Python 智能体开发
-
-使用框架构建和运行目标驱动的智能体：
-
-```bash
-# 一次性设置
-./scripts/setup-python.sh
-
-# 这将安装：
-# - framework 包（核心运行时）
-# - aden_tools 包（19 个 MCP 工具）
-# - 所有依赖项
-
-# 使用 Claude Code 技能构建新智能体
-claude> /building-agents
-
-# 测试智能体
-claude> /testing-agent
-
-# 运行智能体
-PYTHONPATH=core:exports python -m agent_name run --input '{...}'
-```
-
-完整设置说明请参阅 [ENVIRONMENT_SETUP.md](ENVIRONMENT_SETUP.md)。
-
-## 文档
-
-- **[开发者指南](DEVELOPER.md)** - 开发者综合指南
-- [入门指南](docs/getting-started.md) - 快速设置说明
-- [配置指南](docs/configuration.md) - 所有配置选项
-- [架构概述](docs/architecture.md) - 系统设计和结构
-
-## 路线图
-
-Aden 智能体框架旨在帮助开发者构建面向结果的、自适应的智能体。请在此查看我们的路线图
-
-[ROADMAP.md](ROADMAP.md)
-
-```mermaid
-timeline
-    title Aden Agent Framework Roadmap
-    section Foundation
-        Architecture : Node-Based Architecture : Python SDK : LLM Integration (OpenAI, Anthropic, Google) : Communication Protocol
-        Coding Agent : Goal Creation Session : Worker Agent Creation : MCP Tools Integration
-        Worker Agent : Human-in-the-Loop : Callback Handlers : Intervention Points : Streaming Interface
-        Tools : File Use : Memory (STM/LTM) : Web Search : Web Scraper : Audit Trail
-        Core : Eval System : Pydantic Validation : Docker Deployment : Documentation : Sample Agents
-    section Expansion
-        Intelligence : Guardrails : Streaming Mode : Semantic Search
-        Platform : JavaScript SDK : Custom Tool Integrator : Credential Store
-        Deployment : Self-Hosted : Cloud Services : CI/CD Pipeline
-        Templates : Sales Agent : Marketing Agent : Analytics Agent : Training Agent : Smart Form Agent
-```
-
-## 社区与支持
-
-我们使用 [Discord](https://discord.com/invite/MXE49hrKDk) 进行支持、功能请求和社区讨论。
-
-- Discord - [加入我们的社区](https://discord.com/invite/MXE49hrKDk)
-- Twitter/X - [@adenhq](https://x.com/aden_hq)
-- LinkedIn - [公司主页](https://www.linkedin.com/company/teamaden/)
-
-## 贡献
-
-我们欢迎贡献！请参阅 [CONTRIBUTING.md](CONTRIBUTING.md) 了解指南。
-
-1. Fork 仓库
-2. 创建功能分支 (`git checkout -b feature/amazing-feature`)
-3. 提交更改 (`git commit -m 'Add amazing feature'`)
-4. 推送到分支 (`git push origin feature/amazing-feature`)
-5. 创建 Pull Request
-
-## 加入我们的团队
-
-**我们正在招聘！** 加入我们的工程、研究和市场推广团队。
-
-[查看开放职位](https://jobs.adenhq.com/a8cec478-cdbc-473c-bbd4-f4b7027ec193/applicant)
-
-## 安全
-
-有关安全问题，请参阅 [SECURITY.md](SECURITY.md)。
-
-## 许可证
-
-本项目采用 Apache License 2.0 许可证 - 详情请参阅 [LICENSE](LICENSE) 文件。
-
-## 常见问题 (FAQ)
-
-> **注意：** 完整的常见问题解答，请参阅英文版 [README.md](README.md)。
-
-**问：Aden 是否依赖 LangChain 或其他智能体框架？**
-
-不。Aden 从头开始构建，不依赖 LangChain、CrewAI 或其他智能体框架。该框架设计精简灵活，动态生成智能体图而非依赖预定义组件。
-
-**问：Aden 支持哪些 LLM 提供商？**
-
-Aden 通过 LiteLLM 集成支持 100 多个 LLM 提供商，包括 OpenAI（GPT-4、GPT-4o）、Anthropic（Claude 模型）、Google Gemini、Mistral、Groq 等。只需设置适当的 API 密钥环境变量并指定模型名称即可。
-
-**问：Aden 是开源的吗？**
-
-是的，Aden 在 Apache License 2.0 下完全开源。我们积极鼓励社区贡献和协作。
-
-**问：Aden 与其他智能体框架有何不同？**
-
-Aden 使用编码智能体从自然语言目标生成整个智能体系统——您无需硬编码工作流或手动定义图。当智能体失败时，框架会自动捕获故障数据、进化智能体图并重新部署。这种自我改进循环是 Aden 独有的。
-
-**问：Aden 支持人机协作工作流吗？**
-
-是的，Aden 通过干预节点完全支持人机协作工作流，这些节点会暂停执行以等待人工输入。包括可配置的超时和升级策略，实现人类专家与 AI 智能体的无缝协作。
-
----
-
-<p align="center">
-  用 🔥 热情打造于旧金山
-</p>

ROADMAP.md

@@ -1,150 +0,0 @@
-Product Roadmap
-
-Aden Agent Framework aims to help developers build outcome oriented, self-adaptive agents. Please find our roadmap here
-
-```mermaid
-timeline
-    title Aden Agent Framework Roadmap
-    section Foundation
-        Architecture : Node-Based Architecture : Python SDK : LLM Integration (OpenAI, Anthropic, Google) : Communication Protocol
-        Coding Agent : Goal Creation Session : Worker Agent Creation : MCP Tools Integration
-        Worker Agent : Human-in-the-Loop : Callback Handlers : Intervention Points : Streaming Interface
-        Tools : File Use : Memory (STM/LTM) : Web Search : Web Scraper : Audit Trail
-        Core : Eval System : Pydantic Validation : Docker Deployment : Documentation : Sample Agents
-    section Expansion
-        Intelligence : Guardrails : Streaming Mode : Semantic Search
-        Platform : JavaScript SDK : Custom Tool Integrator : Credential Store
-        Deployment : Self-Hosted : Cloud Services : CI/CD Pipeline
-        Templates : Sales Agent : Marketing Agent : Analytics Agent : Training Agent : Smart Form Agent
-```
-
----
-
-## Phase 1: Foundation
-
-### Backbone Architecture
-- [ ] **Node-Based Architecture (Agent as a node)**
-    - [x] Object schema definition
-    - [x] Node wrapper SDK
-    - [ ] Shared memory access
-    - [ ] Default monitoring hooks
-    - [ ] Tool access layer
-    - [x] LLM integration layer (Natively supports all mainstream LLMs through LiteLLM)
-        - [x] Anthropic
-        - [x] OpenAI
-        - [x] Google
-- [ ] **Communication protocol between nodes**
-- [ ] **[Coding Agent] Goal Creation Session** (separate from coding session)
-    - [ ] Instruction back and forth
-    - [x] Goal Object schema definition
-    - [ ] Being able to generate the test cases
-    - [ ] Test case validation for worker agent (Outcome driven)
-- [ ] **[Coding Agent] Worker Agent Creation**
-    - [x] Coding Agent tools
-    - [ ] Use Template Agent as a start
-    - [x] Use our MCP tools
-- [ ] **[Worker Agent] Human-in-the-Loop**
-    - [x] Worker Agents request with questions and options
-    - [x] Callback Handler System to receive events throughout execution
-    - [ ] Tool-Based Intervention Points (tool to pause execution and request human input)
-    - [x] Multiple entrypoint for different event source (e.g. Human input, webhook)
-    - [ ] Streaming Interface for Real-time Monitoring
-    - [ ] Request State Management
-
-### Essential Tools
-- [x] **File Use Tool Kit**
-- [ ] **Memory Tools**
-    - [x] STM Layer Tool (state-based short-term memory)
-    - [x] LTM Layer Tool (RLM - long-term memory)
-- [ ] **Infrastructure Tools**
-    - [x] Runtime Log Tool (logs for coding agent)
-    - [ ] Audit Trail Tool (decision timeline generation)
-    - [ ] Web Search
-    - [ ] Web Scraper
-    - [ ] Recipe for "Add your own tools"
-
-### Memory & File System
-- [x] DB for long-term persistent memory (Filesystem as durable scratchpad pattern)
-- [x] Session Local memory isolation
-
-### Eval System (Basic)
-- [x] Test Driven - Run test case for all agent iteration
-- [ ] Failure recording mechanism
-- [ ] SDK for defining failure conditions
-- [ ] Basic observability hooks
-- [ ] User-driven log analysis (OSS approach)
-
-### Data Validation
-- [ ] Natively Support data validation of LLMs output with Pydantic
-
-### Developer Experience
-- [ ] **Debugging mode**
-- [ ] **Documentation**
-    - [ ] Quick start guide
-    - [ ] Goal creation guide
-    - [ ] Agent creation guide
-    - [ ] GitHub Page setup
-    - [ ] README with examples
-    - [ ] Contributing guidelines
-- [ ] **Distribution**
-    - [ ] PyPI package
-    - [ ] Docker image on Docker Hub
-
-### Sample Agents
-- [ ] Knowledge Agent
-- [ ] Blog Writer Agent
-- [ ] SDR Agent
-
----
-
-## Phase 2: Expansion
-
-### Basic Guardrails
-- [ ] Support Basic Monitoring from Agent node SDK
-- [ ] SDK guardrail implementation (in node)
-- [ ] Guardrail type support (Determined Condition as Guardrails)
-
-### Agent Capability
-- [ ] Streaming mode support
-
-### Cross-Platform
-- [ ] JavaScript / TypeScript Version SDK
-
-### File System Enhancement
-- [ ] Semantic Search integration
-- [ ] Interactive File System in product (frontend integration)
-
-### More Worker Tools
-- [ ] Custom Tool Integrator
-- [ ] Integration as a tool (Credential Store & Support)
-- [ ] **Core Agent Tools**
-    - [ ] Node Discovery Tool (find other agents in the graph)
-    - [ ] HITL Tool (pause execution for human approval)
-    - [ ] Wake-up Tool (resume agent tasks)
-
-### Deployment (Self-Hosted)
-- [ ] Docker container standardization
-- [ ] Headless backend execution
-- [ ] Exposed API for frontend attachment
-- [ ] Local monitoring & observability
-- [ ] Basic lifecycle APIs (Start, Stop, Pause, Resume)
-
-### Deployment (Cloud)
-- [ ] Cloud Service Options
-- [ ] Support deployment to 3rd-party platforms
-- [ ] Self-deploy + orchestrator connection
-- [ ] **CI/CD Pipeline**
-    - [ ] Automated test execution
-    - [ ] Agent version control
-    - [ ] All tests must pass for deployment
-
-### Developer Experience Enhancement
-- [ ] Tool usage documentation
-- [ ] Discord Support Channel
-
-### More Agent Templates
-- [ ] GTM Sales Agent (workflow)
-- [ ] GTM Marketing Agent (workflow)
-- [ ] Analytics Agent
-- [ ] Training Agent
-- [ ] Smart Entry / Form Agent (self-evolution emphasis)

core/.gitignore

@@ -1,4 +1,5 @@
 exports/
 docs/
+.agent-builder-sessions/
 .pytest_cache/
 **/__pycache__/

core/.mcp.json

@@ -3,12 +3,12 @@
     "agent-builder": {
       "command": "python",
       "args": ["-m", "framework.mcp.agent_builder_server"],
-      "cwd": "/home/timothy/oss/hive/core"
+      "cwd": "core"
     },
     "tools": {
       "command": "python",
       "args": ["-m", "aden_tools.mcp_server", "--stdio"],
-      "cwd": "/home/timothy/oss/hive/tools"
+      "cwd": "tools"
     }
   }
 }

core/MCP_BUILDER_TOOLS_GUIDE.md

@@ -82,7 +82,7 @@ Register an MCP server as a tool source for your agent.
     "example_tool"
   ],
   "total_mcp_servers": 1,
-  "note": "MCP server 'tools' registered with 6 tools. These tools can now be used in llm_tool_use nodes."
+  "note": "MCP server 'tools' registered with 6 tools. These tools can now be used in event_loop nodes."
 }
 ```
 
@@ -149,7 +149,7 @@ List tools available from registered MCP servers.
     ]
   },
   "total_tools": 6,
-  "note": "Use these tool names in the 'tools' parameter when adding llm_tool_use nodes"
+  "note": "Use these tool names in the 'tools' parameter when adding event_loop nodes"
 }
 ```
 
@@ -246,7 +246,7 @@ Here's a complete workflow for building an agent with MCP tools:
     "node_id": "web-searcher",
     "name": "Web Search",
     "description": "Search the web for information",
-    "node_type": "llm_tool_use",
+    "node_type": "event_loop",
     "input_keys": "[\"query\"]",
     "output_keys": "[\"search_results\"]",
     "system_prompt": "Search for {query} using the web_search tool",

core/MCP_INTEGRATION_GUIDE.md

@@ -119,7 +119,7 @@ builder = WorkflowBuilder()
 builder.add_node(
     node_id="researcher",
     name="Web Researcher",
-    node_type="llm_tool_use",
+    node_type="event_loop",
     system_prompt="Research the topic using web_search",
     tools=["web_search"],  # Tool from tools MCP server
     input_keys=["topic"],
@@ -137,7 +137,7 @@ Tools from MCP servers can be referenced in your agent.json just like built-in t
     {
       "id": "searcher",
       "name": "Web Searcher",
-      "node_type": "llm_tool_use",
+      "node_type": "event_loop",
       "system_prompt": "Search for information about {topic}",
       "tools": ["web_search", "web_scrape"],
       "input_keys": ["topic"],

core/MCP_SERVER_GUIDE.md

@@ -103,31 +103,20 @@ Add a processing node to the agent graph.
 - `node_id` (string, required): Unique node identifier
 - `name` (string, required): Human-readable name
 - `description` (string, required): What this node does
-- `node_type` (string, required): One of: `llm_generate`, `llm_tool_use`, `router`, `function`
+- `node_type` (string, required): Must be `event_loop` (the only valid type)
 - `input_keys` (string, required): JSON array of input variable names
 - `output_keys` (string, required): JSON array of output variable names
-- `system_prompt` (string, optional): System prompt for LLM nodes
-- `tools` (string, optional): JSON array of tool names for tool_use nodes
-- `routes` (string, optional): JSON object of route mappings for router nodes
+- `system_prompt` (string, optional): System prompt for the LLM
+- `tools` (string, optional): JSON array of tool names
+- `client_facing` (boolean, optional): Set to true for human-in-the-loop interaction
 
-**Node Types:**
+**Node Type:**
 
-1. **llm_generate**: Uses LLM to generate output from inputs
-   - Requires: `system_prompt`
-   - Tools: Not used
-
-2. **llm_tool_use**: Uses LLM with tools to accomplish tasks
-   - Requires: `system_prompt`, `tools`
-   - Tools: Array of tool names (e.g., `["web_search", "web_fetch"]`)
-
-3. **router**: LLM-powered routing to different paths
-   - Requires: `system_prompt`, `routes`
-   - Routes: Object mapping route names to target node IDs
-   - Example: `{"pass": "success_node", "fail": "retry_node"}`
-
-4. **function**: Executes a pre-defined function
-   - System prompt describes the function behavior
-   - No LLM calls, pure computation
+**event_loop**: LLM-powered node with self-correction loop
+- Requires: `system_prompt`
+- Optional: `tools` (array of tool names, e.g., `["web_search", "web_fetch"]`)
+- Optional: `client_facing` (set to true for HITL / user interaction)
+- Supports: iterative refinement, judge-based evaluation, tool use, streaming
 
 **Example:**
 ```json
@@ -135,7 +124,7 @@ Add a processing node to the agent graph.
   "node_id": "search_sources",
   "name": "Search Sources",
   "description": "Searches for relevant sources on the topic",
-  "node_type": "llm_tool_use",
+  "node_type": "event_loop",
   "input_keys": "[\"topic\", \"search_queries\"]",
   "output_keys": "[\"sources\", \"source_count\"]",
   "system_prompt": "Search for sources using the provided queries...",
@@ -198,7 +187,7 @@ Export the validated graph as an agent specification.
 
 **What it does:**
 1. Validates the graph
-2. Auto-generates missing edges from router routes
+2. Validates edge connectivity
 3. Writes files to disk:
    - `exports/{agent-name}/agent.json` - Full agent specification
    - `exports/{agent-name}/README.md` - Auto-generated documentation
@@ -252,47 +241,6 @@ Test the complete agent graph with sample inputs.
 
 ---
 
-### Evaluation Rules
-
-#### `add_evaluation_rule`
-Add a rule for the HybridJudge to evaluate node outputs.
-
-**Parameters:**
-- `rule_id` (string, required): Unique rule identifier
-- `description` (string, required): What this rule checks
-- `condition` (string, required): Python expression to evaluate
-- `action` (string, required): Action to take: `accept`, `retry`, `escalate`
-- `priority` (integer, optional): Rule priority (default: 0)
-- `feedback_template` (string, optional): Feedback message template
-
-**Condition Examples:**
-- `'result.get("success") == True'` - Check for success flag
-- `'result.get("error_type") == "timeout"'` - Check error type
-- `'len(result.get("data", [])) > 0'` - Check for non-empty data
-
-**Example:**
-```json
-{
-  "rule_id": "timeout_retry",
-  "description": "Retry on timeout errors",
-  "condition": "result.get('error_type') == 'timeout'",
-  "action": "retry",
-  "priority": 10,
-  "feedback_template": "Timeout occurred, retrying..."
-}
-```
-
-#### `list_evaluation_rules`
-List all configured evaluation rules.
-
-#### `remove_evaluation_rule`
-Remove an evaluation rule.
-
-**Parameters:**
-- `rule_id` (string, required): Rule to remove
-
----
-
 ## Example Workflow
 
 Here's a complete workflow for building a research agent:
@@ -320,7 +268,7 @@ add_node(
     node_id="planner",
     name="Research Planner",
     description="Creates research strategy",
-    node_type="llm_generate",
+    node_type="event_loop",
     input_keys='["topic"]',
     output_keys='["strategy", "queries"]',
     system_prompt="Analyze topic and create research plan..."
@@ -330,7 +278,7 @@ add_node(
     node_id="searcher",
     name="Search Sources",
     description="Find relevant sources",
-    node_type="llm_tool_use",
+    node_type="event_loop",
     input_keys='["queries"]',
     output_keys='["sources"]',
     system_prompt="Search for sources...",
@@ -359,10 +307,9 @@ The exported agent will be saved to `exports/research-agent/`.
 
 1. **Start with the goal**: Define clear success criteria before building nodes
 2. **Test nodes individually**: Use `test_node` to verify each node works
-3. **Use router nodes for branching**: Don't create edges manually for routers - define routes and they'll be auto-generated
-4. **Add evaluation rules**: Help the judge evaluate outputs deterministically
-5. **Validate early, validate often**: Run `validate_graph` after adding nodes/edges
-6. **Check exports**: Review the generated README.md to verify your agent structure
+3. **Use conditional edges for branching**: Define condition_expr on edges for decision points
+4. **Validate early, validate often**: Run `validate_graph` after adding nodes/edges
+5. **Check exports**: Review the generated README.md to verify your agent structure
 
 ---
 

core/README.md

@@ -14,7 +14,7 @@ Framework provides a runtime framework that captures **decisions**, not just act
 ## Installation
 
 ```bash
-pip install -e .
+uv pip install -e .
 ```
 
 ## MCP Server Setup
@@ -45,13 +45,13 @@ If you prefer manual setup:
 
 ```bash
 # Install framework
-pip install -e .
+uv pip install -e .
 
 # Install MCP dependencies
-pip install mcp fastmcp
+uv pip install mcp fastmcp
 
 # Test the server
-python -m framework.mcp.agent_builder_server
+uv run python -m framework.mcp.agent_builder_server
 ```
 
 ### Using with MCP Clients
@@ -73,7 +73,7 @@ To use the agent builder with Claude Desktop or other MCP clients, add this to y
 The MCP server provides tools for:
 - Creating agent building sessions
 - Defining goals with success criteria
-- Adding nodes (llm_generate, llm_tool_use, router, function)
+- Adding nodes (event_loop only)
 - Connecting nodes with edges
 - Validating and exporting agent graphs
 - Testing nodes and full agent graphs
@@ -86,13 +86,13 @@ Run an LLM-powered calculator:
 
 ```bash
 # Single calculation
-python -m framework calculate "2 + 3 * 4"
+uv run python -m framework calculate "2 + 3 * 4"
 
 # Interactive mode
-python -m framework interactive
+uv run python -m framework interactive
 
 # Analyze runs with Builder
-python -m framework analyze calculator
+uv run python -m framework analyze calculator
 ```
 
 ### Using the Runtime
@@ -132,24 +132,20 @@ runtime.end_run(success=True, narrative="Successfully processed all data")
 
 The framework includes a goal-based testing framework for validating agent behavior.
 
+Tests are generated using MCP tools (`generate_constraint_tests`, `generate_success_tests`) which return guidelines. Claude writes tests directly using the Write tool based on these guidelines.
+
 ```bash
-# Generate tests from a goal definition
-python -m framework test-generate goal.json
-
-# Interactively approve generated tests
-python -m framework test-approve <goal_id>
-
 # Run tests against an agent
-python -m framework test-run <agent_path> --parallel 4
+uv run python -m framework test-run <agent_path> --goal <goal_id> --parallel 4
 
 # Debug failed tests
-python -m framework test-debug <goal_id> <test_id>
+uv run python -m framework test-debug <agent_path> <test_name>
 
-# List tests by status
-python -m framework test-list <goal_id>
+# List tests for a goal
+uv run python -m framework test-list <goal_id>
 ```
 
-For detailed testing workflows, see the [testing-agent skill](.claude/skills/testing-agent/SKILL.md).
+For detailed testing workflows, see the [hive-test skill](../.claude/skills/hive-test/SKILL.md).
 
 ### Analyzing Agent Behavior with Builder
 

core/demos/event_loop_wss_demo.py

@@ -0,0 +1,740 @@
+#!/usr/bin/env python3
+"""
+EventLoopNode WebSocket Demo
+
+Real LLM, real FileConversationStore, real EventBus.
+Streams EventLoopNode execution to a browser via WebSocket.
+
+Usage:
+    cd /home/timothy/oss/hive/core
+    python demos/event_loop_wss_demo.py
+
+    Then open http://localhost:8765 in your browser.
+"""
+
+import asyncio
+import json
+import logging
+import sys
+import tempfile
+from http import HTTPStatus
+from pathlib import Path
+
+import httpx
+import websockets
+from bs4 import BeautifulSoup
+from websockets.http11 import Request, Response
+
+# Add core, tools, and hive root to path
+_CORE_DIR = Path(__file__).resolve().parent.parent
+_HIVE_DIR = _CORE_DIR.parent
+sys.path.insert(0, str(_CORE_DIR))  # framework.*
+sys.path.insert(0, str(_HIVE_DIR / "tools" / "src"))  # aden_tools.*
+sys.path.insert(0, str(_HIVE_DIR))  # core.framework.* (for aden_tools imports)
+
+import os  # noqa: E402
+
+from aden_tools.credentials import CREDENTIAL_SPECS, CredentialStoreAdapter  # noqa: E402
+from core.framework.credentials import CredentialStore  # noqa: E402
+
+from framework.credentials.storage import (  # noqa: E402
+    CompositeStorage,
+    EncryptedFileStorage,
+    EnvVarStorage,
+)
+from framework.graph.event_loop_node import EventLoopNode, LoopConfig  # noqa: E402
+from framework.graph.node import NodeContext, NodeSpec, SharedMemory  # noqa: E402
+from framework.llm.litellm import LiteLLMProvider  # noqa: E402
+from framework.llm.provider import Tool  # noqa: E402
+from framework.runner.tool_registry import ToolRegistry  # noqa: E402
+from framework.runtime.core import Runtime  # noqa: E402
+from framework.runtime.event_bus import EventBus, EventType  # noqa: E402
+from framework.storage.conversation_store import FileConversationStore  # noqa: E402
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(name)s %(message)s")
+logger = logging.getLogger("demo")
+
+# -------------------------------------------------------------------------
+# Persistent state (shared across WebSocket connections)
+# -------------------------------------------------------------------------
+
+STORE_DIR = Path(tempfile.mkdtemp(prefix="hive_demo_"))
+STORE = FileConversationStore(STORE_DIR / "conversation")
+RUNTIME = Runtime(STORE_DIR / "runtime")
+LLM = LiteLLMProvider(model="claude-sonnet-4-5-20250929")
+
+# -------------------------------------------------------------------------
+# Tool Registry — real tools via ToolRegistry (same pattern as GraphExecutor)
+# -------------------------------------------------------------------------
+
+TOOL_REGISTRY = ToolRegistry()
+
+# Credential store: Aden sync (OAuth2 tokens) + encrypted files + env var fallback
+_env_mapping = {name: spec.env_var for name, spec in CREDENTIAL_SPECS.items()}
+_local_storage = CompositeStorage(
+    primary=EncryptedFileStorage(),
+    fallbacks=[EnvVarStorage(env_mapping=_env_mapping)],
+)
+
+if os.environ.get("ADEN_API_KEY"):
+    try:
+        from framework.credentials.aden import (  # noqa: E402
+            AdenCachedStorage,
+            AdenClientConfig,
+            AdenCredentialClient,
+            AdenSyncProvider,
+        )
+
+        _client = AdenCredentialClient(AdenClientConfig(base_url="https://api.adenhq.com"))
+        _provider = AdenSyncProvider(client=_client)
+        _storage = AdenCachedStorage(
+            local_storage=_local_storage,
+            aden_provider=_provider,
+        )
+        _cred_store = CredentialStore(storage=_storage, providers=[_provider], auto_refresh=True)
+        _synced = _provider.sync_all(_cred_store)
+        logger.info("Synced %d credentials from Aden", _synced)
+    except Exception as e:
+        logger.warning("Aden sync unavailable: %s", e)
+        _cred_store = CredentialStore(storage=_local_storage)
+else:
+    logger.info("ADEN_API_KEY not set, using local credential storage")
+    _cred_store = CredentialStore(storage=_local_storage)
+
+CREDENTIALS = CredentialStoreAdapter(_cred_store)
+
+# Debug: log which credentials resolved
+for _name in ["brave_search", "hubspot", "anthropic"]:
+    _val = CREDENTIALS.get(_name)
+    if _val:
+        logger.debug("credential %s: OK (len=%d)", _name, len(_val))
+    else:
+        logger.debug("credential %s: not found", _name)
+
+# --- web_search (Brave Search API) ---
+
+TOOL_REGISTRY.register(
+    name="web_search",
+    tool=Tool(
+        name="web_search",
+        description=(
+            "Search the web for current information. "
+            "Returns titles, URLs, and snippets from search results."
+        ),
+        parameters={
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "description": "The search query (1-500 characters)",
+                },
+                "num_results": {
+                    "type": "integer",
+                    "description": "Number of results to return (1-20, default 10)",
+                },
+            },
+            "required": ["query"],
+        },
+    ),
+    executor=lambda inputs: _exec_web_search(inputs),
+)
+
+
+def _exec_web_search(inputs: dict) -> dict:
+    api_key = CREDENTIALS.get("brave_search")
+    if not api_key:
+        return {"error": "brave_search credential not configured"}
+    query = inputs.get("query", "")
+    num_results = min(inputs.get("num_results", 10), 20)
+    resp = httpx.get(
+        "https://api.search.brave.com/res/v1/web/search",
+        params={"q": query, "count": num_results},
+        headers={"X-Subscription-Token": api_key, "Accept": "application/json"},
+        timeout=30.0,
+    )
+    if resp.status_code != 200:
+        return {"error": f"Brave API HTTP {resp.status_code}"}
+    data = resp.json()
+    results = [
+        {
+            "title": item.get("title", ""),
+            "url": item.get("url", ""),
+            "snippet": item.get("description", ""),
+        }
+        for item in data.get("web", {}).get("results", [])[:num_results]
+    ]
+    return {"query": query, "results": results, "total": len(results)}
+
+
+# --- web_scrape (httpx + BeautifulSoup, no playwright for sync compat) ---
+
+TOOL_REGISTRY.register(
+    name="web_scrape",
+    tool=Tool(
+        name="web_scrape",
+        description=(
+            "Scrape and extract text content from a webpage URL. "
+            "Returns the page title and main text content."
+        ),
+        parameters={
+            "type": "object",
+            "properties": {
+                "url": {
+                    "type": "string",
+                    "description": "URL of the webpage to scrape",
+                },
+                "max_length": {
+                    "type": "integer",
+                    "description": "Maximum text length (default 50000)",
+                },
+            },
+            "required": ["url"],
+        },
+    ),
+    executor=lambda inputs: _exec_web_scrape(inputs),
+)
+
+_SCRAPE_HEADERS = {
+    "User-Agent": (
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+        "AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/131.0.0.0 Safari/537.36"
+    ),
+    "Accept": "text/html,application/xhtml+xml",
+}
+
+
+def _exec_web_scrape(inputs: dict) -> dict:
+    url = inputs.get("url", "")
+    max_length = max(1000, min(inputs.get("max_length", 50000), 500000))
+    if not url.startswith(("http://", "https://")):
+        url = "https://" + url
+    try:
+        resp = httpx.get(url, timeout=30.0, follow_redirects=True, headers=_SCRAPE_HEADERS)
+        if resp.status_code != 200:
+            return {"error": f"HTTP {resp.status_code}"}
+        soup = BeautifulSoup(resp.text, "html.parser")
+        for tag in soup(["script", "style", "nav", "footer", "header", "aside", "noscript"]):
+            tag.decompose()
+        title = soup.title.get_text(strip=True) if soup.title else ""
+        main = (
+            soup.find("article")
+            or soup.find("main")
+            or soup.find(attrs={"role": "main"})
+            or soup.find("body")
+        )
+        text = main.get_text(separator=" ", strip=True) if main else ""
+        text = " ".join(text.split())
+        if len(text) > max_length:
+            text = text[:max_length] + "..."
+        return {"url": url, "title": title, "content": text, "length": len(text)}
+    except httpx.TimeoutException:
+        return {"error": "Request timed out"}
+    except Exception as e:
+        return {"error": f"Scrape failed: {e}"}
+
+
+# --- HubSpot CRM tools (optional, requires HUBSPOT_ACCESS_TOKEN) ---
+
+_HUBSPOT_API = "https://api.hubapi.com"
+
+
+def _hubspot_headers() -> dict | None:
+    token = CREDENTIALS.get("hubspot")
+    if token:
+        logger.debug("HubSpot token: %s...%s (len=%d)", token[:8], token[-4:], len(token))
+    else:
+        logger.debug("HubSpot token: not found")
+    if not token:
+        return None
+    return {
+        "Authorization": f"Bearer {token}",
+        "Content-Type": "application/json",
+        "Accept": "application/json",
+    }
+
+
+def _exec_hubspot_search(inputs: dict) -> dict:
+    headers = _hubspot_headers()
+    if not headers:
+        return {"error": "HUBSPOT_ACCESS_TOKEN not set"}
+    object_type = inputs.get("object_type", "contacts")
+    query = inputs.get("query", "")
+    limit = min(inputs.get("limit", 10), 100)
+    body: dict = {"limit": limit}
+    if query:
+        body["query"] = query
+    try:
+        resp = httpx.post(
+            f"{_HUBSPOT_API}/crm/v3/objects/{object_type}/search",
+            headers=headers,
+            json=body,
+            timeout=30.0,
+        )
+        if resp.status_code != 200:
+            return {"error": f"HubSpot API HTTP {resp.status_code}: {resp.text[:200]}"}
+        return resp.json()
+    except httpx.TimeoutException:
+        return {"error": "Request timed out"}
+    except Exception as e:
+        return {"error": f"HubSpot error: {e}"}
+
+
+TOOL_REGISTRY.register(
+    name="hubspot_search",
+    tool=Tool(
+        name="hubspot_search",
+        description=(
+            "Search HubSpot CRM objects (contacts, companies, or deals). "
+            "Returns matching records with their properties."
+        ),
+        parameters={
+            "type": "object",
+            "properties": {
+                "object_type": {
+                    "type": "string",
+                    "description": "CRM object type: 'contacts', 'companies', or 'deals'",
+                },
+                "query": {
+                    "type": "string",
+                    "description": "Search query (name, email, domain, etc.)",
+                },
+                "limit": {
+                    "type": "integer",
+                    "description": "Max results (1-100, default 10)",
+                },
+            },
+            "required": ["object_type"],
+        },
+    ),
+    executor=lambda inputs: _exec_hubspot_search(inputs),
+)
+
+logger.info(
+    "ToolRegistry loaded: %s",
+    ", ".join(TOOL_REGISTRY.get_registered_names()),
+)
+
+
+# -------------------------------------------------------------------------
+# HTML page (embedded)
+# -------------------------------------------------------------------------
+
+HTML_PAGE = (  # noqa: E501
+    """<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<title>EventLoopNode Live Demo</title>
+<style>
+  * { box-sizing: border-box; margin: 0; padding: 0; }
+  body {
+    font-family: 'SF Mono', 'Fira Code', monospace;
+    background: #0d1117; color: #c9d1d9;
+    height: 100vh; display: flex; flex-direction: column;
+  }
+  header {
+    background: #161b22; padding: 12px 20px;
+    border-bottom: 1px solid #30363d;
+    display: flex; align-items: center; gap: 16px;
+  }
+  header h1 { font-size: 16px; color: #58a6ff; font-weight: 600; }
+  .status {
+    font-size: 12px; padding: 3px 10px; border-radius: 12px;
+    background: #21262d; color: #8b949e;
+  }
+  .status.running { background: #1a4b2e; color: #3fb950; }
+  .status.done { background: #1a3a5c; color: #58a6ff; }
+  .status.error { background: #4b1a1a; color: #f85149; }
+  .chat { flex: 1; overflow-y: auto; padding: 16px; }
+  .msg {
+    margin: 8px 0; padding: 10px 14px; border-radius: 8px;
+    line-height: 1.6; white-space: pre-wrap; word-wrap: break-word;
+  }
+  .msg.user { background: #1a3a5c; color: #58a6ff; }
+  .msg.assistant { background: #161b22; color: #c9d1d9; }
+  .msg.event {
+    background: transparent; color: #8b949e; font-size: 11px;
+    padding: 4px 14px; border-left: 3px solid #30363d;
+  }
+  .msg.event.loop { border-left-color: #58a6ff; }
+  .msg.event.tool { border-left-color: #d29922; }
+  .msg.event.stall { border-left-color: #f85149; }
+  .input-bar {
+    padding: 12px 16px; background: #161b22;
+    border-top: 1px solid #30363d; display: flex; gap: 8px;
+  }
+  .input-bar input {
+    flex: 1; background: #0d1117; border: 1px solid #30363d;
+    color: #c9d1d9; padding: 8px 12px; border-radius: 6px;
+    font-family: inherit; font-size: 14px; outline: none;
+  }
+  .input-bar input:focus { border-color: #58a6ff; }
+  .input-bar button {
+    background: #238636; color: #fff; border: none;
+    padding: 8px 20px; border-radius: 6px; cursor: pointer;
+    font-family: inherit; font-weight: 600;
+  }
+  .input-bar button:hover { background: #2ea043; }
+  .input-bar button:disabled {
+    background: #21262d; color: #484f58; cursor: not-allowed;
+  }
+  .input-bar button.clear { background: #da3633; }
+  .input-bar button.clear:hover { background: #f85149; }
+</style>
+</head>
+<body>
+  <header>
+    <h1>EventLoopNode Live</h1>
+    <span id="status" class="status">Idle</span>
+    <span id="iter" class="status" style="display:none">Step 0</span>
+  </header>
+  <div id="chat" class="chat"></div>
+  <div class="input-bar">
+    <input id="input" type="text"
+           placeholder="Ask anything..." autofocus />
+    <button id="go" onclick="run()">Send</button>
+    <button class="clear"
+            onclick="clearConversation()">Clear</button>
+  </div>
+
+<script>
+let ws = null;
+let currentAssistantEl = null;
+let iterCount = 0;
+const chat = document.getElementById('chat');
+const status = document.getElementById('status');
+const iterEl = document.getElementById('iter');
+const goBtn = document.getElementById('go');
+const inputEl = document.getElementById('input');
+
+inputEl.addEventListener('keydown', e => {
+  if (e.key === 'Enter') run();
+});
+
+function setStatus(text, cls) {
+  status.textContent = text;
+  status.className = 'status ' + cls;
+}
+
+function addMsg(text, cls) {
+  const el = document.createElement('div');
+  el.className = 'msg ' + cls;
+  el.textContent = text;
+  chat.appendChild(el);
+  chat.scrollTop = chat.scrollHeight;
+  return el;
+}
+
+function connect() {
+  ws = new WebSocket('ws://' + location.host + '/ws');
+  ws.onopen = () => {
+    setStatus('Ready', 'done');
+    goBtn.disabled = false;
+  };
+  ws.onmessage = handleEvent;
+  ws.onerror = () => { setStatus('Error', 'error'); };
+  ws.onclose = () => {
+    setStatus('Reconnecting...', '');
+    goBtn.disabled = true;
+    setTimeout(connect, 2000);
+  };
+}
+
+function handleEvent(msg) {
+  const evt = JSON.parse(msg.data);
+
+  if (evt.type === 'llm_text_delta') {
+    if (currentAssistantEl) {
+      currentAssistantEl.textContent += evt.content;
+      chat.scrollTop = chat.scrollHeight;
+    }
+  }
+  else if (evt.type === 'ready') {
+    setStatus('Ready', 'done');
+    if (currentAssistantEl && !currentAssistantEl.textContent)
+      currentAssistantEl.remove();
+    goBtn.disabled = false;
+  }
+  else if (evt.type === 'node_loop_iteration') {
+    iterCount = evt.iteration || (iterCount + 1);
+    iterEl.textContent = 'Step ' + iterCount;
+    iterEl.style.display = '';
+  }
+  else if (evt.type === 'tool_call_started') {
+    var info = evt.tool_name + '('
+      + JSON.stringify(evt.tool_input).slice(0, 120) + ')';
+    addMsg('TOOL  ' + info, 'event tool');
+  }
+  else if (evt.type === 'tool_call_completed') {
+    var preview = (evt.result || '').slice(0, 200);
+    var cls = evt.is_error ? 'stall' : 'tool';
+    addMsg('RESULT  ' + evt.tool_name + ': ' + preview,
+           'event ' + cls);
+    currentAssistantEl = addMsg('', 'assistant');
+  }
+  else if (evt.type === 'result') {
+    setStatus('Session ended', evt.success ? 'done' : 'error');
+    if (evt.error) addMsg('ERROR  ' + evt.error, 'event stall');
+    if (currentAssistantEl && !currentAssistantEl.textContent)
+      currentAssistantEl.remove();
+    goBtn.disabled = false;
+  }
+  else if (evt.type === 'node_stalled') {
+    addMsg('STALLED  ' + evt.reason, 'event stall');
+  }
+  else if (evt.type === 'cleared') {
+    chat.innerHTML = '';
+    iterCount = 0;
+    iterEl.textContent = 'Step 0';
+    iterEl.style.display = 'none';
+    setStatus('Ready', 'done');
+    goBtn.disabled = false;
+  }
+}
+
+function run() {
+  const text = inputEl.value.trim();
+  if (!text || !ws || ws.readyState !== 1) return;
+  addMsg(text, 'user');
+  currentAssistantEl = addMsg('', 'assistant');
+  inputEl.value = '';
+  setStatus('Running', 'running');
+  goBtn.disabled = true;
+  ws.send(JSON.stringify({ topic: text }));
+}
+
+function clearConversation() {
+  if (ws && ws.readyState === 1) {
+    ws.send(JSON.stringify({ command: 'clear' }));
+  }
+}
+
+connect();
+</script>
+</body>
+</html>"""
+)
+
+
+# -------------------------------------------------------------------------
+# WebSocket handler
+# -------------------------------------------------------------------------
+
+
+async def handle_ws(websocket):
+    """Persistent WebSocket: long-lived EventLoopNode with client_facing blocking."""
+    global STORE
+
+    # -- Event forwarding (WebSocket ← EventBus) ----------------------------
+    bus = EventBus()
+
+    async def forward_event(event):
+        try:
+            payload = {"type": event.type.value, **event.data}
+            if event.node_id:
+                payload["node_id"] = event.node_id
+            await websocket.send(json.dumps(payload))
+        except Exception:
+            pass
+
+    bus.subscribe(
+        event_types=[
+            EventType.NODE_LOOP_STARTED,
+            EventType.NODE_LOOP_ITERATION,
+            EventType.NODE_LOOP_COMPLETED,
+            EventType.LLM_TEXT_DELTA,
+            EventType.TOOL_CALL_STARTED,
+            EventType.TOOL_CALL_COMPLETED,
+            EventType.NODE_STALLED,
+        ],
+        handler=forward_event,
+    )
+
+    # -- Per-connection state -----------------------------------------------
+    node = None
+    loop_task = None
+
+    tools = list(TOOL_REGISTRY.get_tools().values())
+    tool_executor = TOOL_REGISTRY.get_executor()
+
+    node_spec = NodeSpec(
+        id="assistant",
+        name="Chat Assistant",
+        description="A conversational assistant that remembers context across messages",
+        node_type="event_loop",
+        client_facing=True,
+        system_prompt=(
+            "You are a helpful assistant with access to tools. "
+            "You can search the web, scrape webpages, and query HubSpot CRM. "
+            "Use tools when the user asks for current information or external data. "
+            "You have full conversation history, so you can reference previous messages."
+        ),
+    )
+
+    # -- Ready callback: subscribe to CLIENT_INPUT_REQUESTED on the bus ---
+    async def on_input_requested(event):
+        try:
+            await websocket.send(json.dumps({"type": "ready"}))
+        except Exception:
+            pass
+
+    bus.subscribe(
+        event_types=[EventType.CLIENT_INPUT_REQUESTED],
+        handler=on_input_requested,
+    )
+
+    async def start_loop(first_message: str):
+        """Create an EventLoopNode and run it as a background task."""
+        nonlocal node, loop_task
+
+        memory = SharedMemory()
+        ctx = NodeContext(
+            runtime=RUNTIME,
+            node_id="assistant",
+            node_spec=node_spec,
+            memory=memory,
+            input_data={},
+            llm=LLM,
+            available_tools=tools,
+        )
+        node = EventLoopNode(
+            event_bus=bus,
+            config=LoopConfig(max_iterations=10_000, max_history_tokens=32_000),
+            conversation_store=STORE,
+            tool_executor=tool_executor,
+        )
+        await node.inject_event(first_message)
+
+        async def _run():
+            try:
+                result = await node.execute(ctx)
+                try:
+                    await websocket.send(
+                        json.dumps(
+                            {
+                                "type": "result",
+                                "success": result.success,
+                                "output": result.output,
+                                "error": result.error,
+                                "tokens": result.tokens_used,
+                            }
+                        )
+                    )
+                except Exception:
+                    pass
+                logger.info(f"Loop ended: success={result.success}, tokens={result.tokens_used}")
+            except websockets.exceptions.ConnectionClosed:
+                logger.info("Loop stopped: WebSocket closed")
+            except Exception as e:
+                logger.exception("Loop error")
+                try:
+                    await websocket.send(
+                        json.dumps(
+                            {
+                                "type": "result",
+                                "success": False,
+                                "error": str(e),
+                                "output": {},
+                            }
+                        )
+                    )
+                except Exception:
+                    pass
+
+        loop_task = asyncio.create_task(_run())
+
+    async def stop_loop():
+        """Signal the node and wait for the loop task to finish."""
+        nonlocal node, loop_task
+        if loop_task and not loop_task.done():
+            if node:
+                node.signal_shutdown()
+            try:
+                await asyncio.wait_for(loop_task, timeout=5.0)
+            except (TimeoutError, asyncio.CancelledError):
+                loop_task.cancel()
+        node = None
+        loop_task = None
+
+    # -- Message loop (runs for the lifetime of this WebSocket) -------------
+    try:
+        async for raw in websocket:
+            try:
+                msg = json.loads(raw)
+            except Exception:
+                continue
+
+            # Clear command
+            if msg.get("command") == "clear":
+                import shutil
+
+                await stop_loop()
+                await STORE.close()
+                conv_dir = STORE_DIR / "conversation"
+                if conv_dir.exists():
+                    shutil.rmtree(conv_dir)
+                STORE = FileConversationStore(conv_dir)
+                await websocket.send(json.dumps({"type": "cleared"}))
+                logger.info("Conversation cleared")
+                continue
+
+            topic = msg.get("topic", "")
+            if not topic:
+                continue
+
+            if node is None:
+                # First message — spin up the loop
+                logger.info(f"Starting persistent loop: {topic}")
+                await start_loop(topic)
+            else:
+                # Subsequent message — inject into the running loop
+                logger.info(f"Injecting message: {topic}")
+                await node.inject_event(topic)
+
+    except websockets.exceptions.ConnectionClosed:
+        pass
+    finally:
+        await stop_loop()
+        logger.info("WebSocket closed, loop stopped")
+
+
+# -------------------------------------------------------------------------
+# HTTP handler for serving the HTML page
+# -------------------------------------------------------------------------
+
+
+async def process_request(connection, request: Request):
+    """Serve HTML on GET /, upgrade to WebSocket on /ws."""
+    if request.path == "/ws":
+        return None  # let websockets handle the upgrade
+    # Serve the HTML page for any other path
+    return Response(
+        HTTPStatus.OK,
+        "OK",
+        websockets.Headers({"Content-Type": "text/html; charset=utf-8"}),
+        HTML_PAGE.encode(),
+    )
+
+
+# -------------------------------------------------------------------------
+# Main
+# -------------------------------------------------------------------------
+
+
+async def main():
+    port = 8765
+    async with websockets.serve(
+        handle_ws,
+        "0.0.0.0",
+        port,
+        process_request=process_request,
+    ):
+        logger.info(f"Demo running at http://localhost:{port}")
+        logger.info("Open in your browser and enter a topic to research.")
+        await asyncio.Future()  # run forever
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

core/demos/handoff_demo.py

@@ -0,0 +1,930 @@
+#!/usr/bin/env python3
+"""
+Two-Node ContextHandoff Demo
+
+Demonstrates ContextHandoff between two EventLoopNode instances:
+  Node A (Researcher) → ContextHandoff → Node B (Analyst)
+
+Real LLM, real FileConversationStore, real EventBus.
+Streams both nodes to a browser via WebSocket.
+
+Usage:
+    cd /home/timothy/oss/hive/core
+    python demos/handoff_demo.py
+
+    Then open http://localhost:8766 in your browser.
+"""
+
+import asyncio
+import json
+import logging
+import sys
+import tempfile
+from http import HTTPStatus
+from pathlib import Path
+
+import httpx
+import websockets
+from bs4 import BeautifulSoup
+from websockets.http11 import Request, Response
+
+# Add core, tools, and hive root to path
+_CORE_DIR = Path(__file__).resolve().parent.parent
+_HIVE_DIR = _CORE_DIR.parent
+sys.path.insert(0, str(_CORE_DIR))  # framework.*
+sys.path.insert(0, str(_HIVE_DIR / "tools" / "src"))  # aden_tools.*
+sys.path.insert(0, str(_HIVE_DIR))  # core.framework.* (for aden_tools imports)
+
+from aden_tools.credentials import CREDENTIAL_SPECS, CredentialStoreAdapter  # noqa: E402
+from core.framework.credentials import CredentialStore  # noqa: E402
+
+from framework.credentials.storage import (  # noqa: E402
+    CompositeStorage,
+    EncryptedFileStorage,
+    EnvVarStorage,
+)
+from framework.graph.context_handoff import ContextHandoff  # noqa: E402
+from framework.graph.conversation import NodeConversation  # noqa: E402
+from framework.graph.event_loop_node import EventLoopNode, LoopConfig  # noqa: E402
+from framework.graph.node import NodeContext, NodeSpec, SharedMemory  # noqa: E402
+from framework.llm.litellm import LiteLLMProvider  # noqa: E402
+from framework.llm.provider import Tool  # noqa: E402
+from framework.runner.tool_registry import ToolRegistry  # noqa: E402
+from framework.runtime.core import Runtime  # noqa: E402
+from framework.runtime.event_bus import EventBus, EventType  # noqa: E402
+from framework.storage.conversation_store import FileConversationStore  # noqa: E402
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(name)s %(message)s")
+logger = logging.getLogger("handoff_demo")
+
+# -------------------------------------------------------------------------
+# Persistent state
+# -------------------------------------------------------------------------
+
+STORE_DIR = Path(tempfile.mkdtemp(prefix="hive_handoff_"))
+RUNTIME = Runtime(STORE_DIR / "runtime")
+LLM = LiteLLMProvider(model="claude-sonnet-4-5-20250929")
+
+# -------------------------------------------------------------------------
+# Credentials
+# -------------------------------------------------------------------------
+
+# Composite credential store: encrypted files (primary) + env vars (fallback)
+_env_mapping = {name: spec.env_var for name, spec in CREDENTIAL_SPECS.items()}
+_composite = CompositeStorage(
+    primary=EncryptedFileStorage(),
+    fallbacks=[EnvVarStorage(env_mapping=_env_mapping)],
+)
+CREDENTIALS = CredentialStoreAdapter(CredentialStore(storage=_composite))
+
+for _name in ["brave_search", "hubspot"]:
+    _val = CREDENTIALS.get(_name)
+    if _val:
+        logger.debug("credential %s: OK (len=%d)", _name, len(_val))
+    else:
+        logger.debug("credential %s: not found", _name)
+
+# -------------------------------------------------------------------------
+# Tool Registry — web_search + web_scrape for Node A (Researcher)
+# -------------------------------------------------------------------------
+
+TOOL_REGISTRY = ToolRegistry()
+
+
+def _exec_web_search(inputs: dict) -> dict:
+    api_key = CREDENTIALS.get("brave_search")
+    if not api_key:
+        return {"error": "brave_search credential not configured"}
+    query = inputs.get("query", "")
+    num_results = min(inputs.get("num_results", 10), 20)
+    resp = httpx.get(
+        "https://api.search.brave.com/res/v1/web/search",
+        params={"q": query, "count": num_results},
+        headers={
+            "X-Subscription-Token": api_key,
+            "Accept": "application/json",
+        },
+        timeout=30.0,
+    )
+    if resp.status_code != 200:
+        return {"error": f"Brave API HTTP {resp.status_code}"}
+    data = resp.json()
+    results = [
+        {
+            "title": item.get("title", ""),
+            "url": item.get("url", ""),
+            "snippet": item.get("description", ""),
+        }
+        for item in data.get("web", {}).get("results", [])[:num_results]
+    ]
+    return {"query": query, "results": results, "total": len(results)}
+
+
+TOOL_REGISTRY.register(
+    name="web_search",
+    tool=Tool(
+        name="web_search",
+        description=(
+            "Search the web for current information. "
+            "Returns titles, URLs, and snippets from search results."
+        ),
+        parameters={
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "description": "The search query (1-500 characters)",
+                },
+                "num_results": {
+                    "type": "integer",
+                    "description": "Number of results (1-20, default 10)",
+                },
+            },
+            "required": ["query"],
+        },
+    ),
+    executor=lambda inputs: _exec_web_search(inputs),
+)
+
+_SCRAPE_HEADERS = {
+    "User-Agent": (
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+        "AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/131.0.0.0 Safari/537.36"
+    ),
+    "Accept": "text/html,application/xhtml+xml",
+}
+
+
+def _exec_web_scrape(inputs: dict) -> dict:
+    url = inputs.get("url", "")
+    max_length = max(1000, min(inputs.get("max_length", 50000), 500000))
+    if not url.startswith(("http://", "https://")):
+        url = "https://" + url
+    try:
+        resp = httpx.get(
+            url,
+            timeout=30.0,
+            follow_redirects=True,
+            headers=_SCRAPE_HEADERS,
+        )
+        if resp.status_code != 200:
+            return {"error": f"HTTP {resp.status_code}"}
+        soup = BeautifulSoup(resp.text, "html.parser")
+        for tag in soup(["script", "style", "nav", "footer", "header", "aside", "noscript"]):
+            tag.decompose()
+        title = soup.title.get_text(strip=True) if soup.title else ""
+        main = (
+            soup.find("article")
+            or soup.find("main")
+            or soup.find(attrs={"role": "main"})
+            or soup.find("body")
+        )
+        text = main.get_text(separator=" ", strip=True) if main else ""
+        text = " ".join(text.split())
+        if len(text) > max_length:
+            text = text[:max_length] + "..."
+        return {
+            "url": url,
+            "title": title,
+            "content": text,
+            "length": len(text),
+        }
+    except httpx.TimeoutException:
+        return {"error": "Request timed out"}
+    except Exception as e:
+        return {"error": f"Scrape failed: {e}"}
+
+
+TOOL_REGISTRY.register(
+    name="web_scrape",
+    tool=Tool(
+        name="web_scrape",
+        description=(
+            "Scrape and extract text content from a webpage URL. "
+            "Returns the page title and main text content."
+        ),
+        parameters={
+            "type": "object",
+            "properties": {
+                "url": {
+                    "type": "string",
+                    "description": "URL of the webpage to scrape",
+                },
+                "max_length": {
+                    "type": "integer",
+                    "description": "Maximum text length (default 50000)",
+                },
+            },
+            "required": ["url"],
+        },
+    ),
+    executor=lambda inputs: _exec_web_scrape(inputs),
+)
+
+logger.info(
+    "ToolRegistry loaded: %s",
+    ", ".join(TOOL_REGISTRY.get_registered_names()),
+)
+
+# -------------------------------------------------------------------------
+# Node Specs
+# -------------------------------------------------------------------------
+
+RESEARCHER_SPEC = NodeSpec(
+    id="researcher",
+    name="Researcher",
+    description="Researches a topic using web search and scraping tools",
+    node_type="event_loop",
+    input_keys=["topic"],
+    output_keys=["research_summary"],
+    system_prompt=(
+        "You are a thorough research assistant. Your job is to research "
+        "the given topic using the web_search and web_scrape tools.\n\n"
+        "1. Search for relevant information on the topic\n"
+        "2. Scrape 1-2 of the most promising URLs for details\n"
+        "3. Synthesize your findings into a comprehensive summary\n"
+        "4. Use set_output with key='research_summary' to save your "
+        "findings\n\n"
+        "Be thorough but efficient. Aim for 2-4 search/scrape calls, "
+        "then summarize and set_output."
+    ),
+)
+
+ANALYST_SPEC = NodeSpec(
+    id="analyst",
+    name="Analyst",
+    description="Analyzes research findings and provides insights",
+    node_type="event_loop",
+    input_keys=["context"],
+    output_keys=["analysis"],
+    system_prompt=(
+        "You are a strategic analyst. You receive research findings from "
+        "a previous researcher and must:\n\n"
+        "1. Identify key themes and patterns\n"
+        "2. Assess the reliability and significance of the findings\n"
+        "3. Provide actionable insights and recommendations\n"
+        "4. Use set_output with key='analysis' to save your analysis\n\n"
+        "Be concise but insightful. Focus on what matters most."
+    ),
+)
+
+
+# -------------------------------------------------------------------------
+# HTML page
+# -------------------------------------------------------------------------
+
+HTML_PAGE = (  # noqa: E501
+    """<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<title>ContextHandoff Demo</title>
+<style>
+  * {
+    box-sizing: border-box;
+    margin: 0;
+    padding: 0;
+  }
+  body {
+    font-family: 'SF Mono', 'Fira Code', monospace;
+    background: #0d1117;
+    color: #c9d1d9;
+    height: 100vh;
+    display: flex;
+    flex-direction: column;
+  }
+  header {
+    background: #161b22;
+    padding: 12px 20px;
+    border-bottom: 1px solid #30363d;
+    display: flex;
+    align-items: center;
+    gap: 16px;
+  }
+  header h1 {
+    font-size: 16px;
+    color: #58a6ff;
+    font-weight: 600;
+  }
+  .badge {
+    font-size: 12px;
+    padding: 3px 10px;
+    border-radius: 12px;
+    background: #21262d;
+    color: #8b949e;
+  }
+  .badge.researcher {
+    background: #1a3a5c;
+    color: #58a6ff;
+  }
+  .badge.analyst {
+    background: #1a4b2e;
+    color: #3fb950;
+  }
+  .badge.handoff {
+    background: #3d1f00;
+    color: #d29922;
+  }
+  .badge.done {
+    background: #21262d;
+    color: #8b949e;
+  }
+  .badge.error {
+    background: #4b1a1a;
+    color: #f85149;
+  }
+  .chat {
+    flex: 1;
+    overflow-y: auto;
+    padding: 16px;
+  }
+  .msg {
+    margin: 8px 0;
+    padding: 10px 14px;
+    border-radius: 8px;
+    line-height: 1.6;
+    white-space: pre-wrap;
+    word-wrap: break-word;
+  }
+  .msg.user {
+    background: #1a3a5c;
+    color: #58a6ff;
+  }
+  .msg.assistant {
+    background: #161b22;
+    color: #c9d1d9;
+  }
+  .msg.assistant.analyst-msg {
+    border-left: 3px solid #3fb950;
+  }
+  .msg.event {
+    background: transparent;
+    color: #8b949e;
+    font-size: 11px;
+    padding: 4px 14px;
+    border-left: 3px solid #30363d;
+  }
+  .msg.event.loop {
+    border-left-color: #58a6ff;
+  }
+  .msg.event.tool {
+    border-left-color: #d29922;
+  }
+  .msg.event.stall {
+    border-left-color: #f85149;
+  }
+  .handoff-banner {
+    margin: 16px 0;
+    padding: 16px;
+    background: #1c1200;
+    border: 1px solid #d29922;
+    border-radius: 8px;
+    text-align: center;
+  }
+  .handoff-banner h3 {
+    color: #d29922;
+    font-size: 14px;
+    margin-bottom: 8px;
+  }
+  .handoff-banner p, .result-banner p {
+    color: #8b949e;
+    font-size: 12px;
+    line-height: 1.5;
+    max-height: 200px;
+    overflow-y: auto;
+    white-space: pre-wrap;
+    text-align: left;
+  }
+  .result-banner {
+    margin: 16px 0;
+    padding: 16px;
+    background: #0a2614;
+    border: 1px solid #3fb950;
+    border-radius: 8px;
+  }
+  .result-banner h3 {
+    color: #3fb950;
+    font-size: 14px;
+    margin-bottom: 8px;
+    text-align: center;
+  }
+  .result-banner .label {
+    color: #58a6ff;
+    font-size: 11px;
+    font-weight: 600;
+    margin-top: 10px;
+    margin-bottom: 2px;
+  }
+  .result-banner .tokens {
+    color: #484f58;
+    font-size: 11px;
+    text-align: center;
+    margin-top: 10px;
+  }
+  .input-bar {
+    padding: 12px 16px;
+    background: #161b22;
+    border-top: 1px solid #30363d;
+    display: flex;
+    gap: 8px;
+  }
+  .input-bar input {
+    flex: 1;
+    background: #0d1117;
+    border: 1px solid #30363d;
+    color: #c9d1d9;
+    padding: 8px 12px;
+    border-radius: 6px;
+    font-family: inherit;
+    font-size: 14px;
+    outline: none;
+  }
+  .input-bar input:focus {
+    border-color: #58a6ff;
+  }
+  .input-bar button {
+    background: #238636;
+    color: #fff;
+    border: none;
+    padding: 8px 20px;
+    border-radius: 6px;
+    cursor: pointer;
+    font-family: inherit;
+    font-weight: 600;
+  }
+  .input-bar button:hover {
+    background: #2ea043;
+  }
+  .input-bar button:disabled {
+    background: #21262d;
+    color: #484f58;
+    cursor: not-allowed;
+  }
+</style>
+</head>
+<body>
+  <header>
+    <h1>ContextHandoff Demo</h1>
+    <span id="phase" class="badge">Idle</span>
+    <span id="iter" class="badge" style="display:none">Step 0</span>
+  </header>
+  <div id="chat" class="chat"></div>
+  <div class="input-bar">
+    <input id="input" type="text"
+           placeholder="Enter a research topic..." autofocus />
+    <button id="go" onclick="run()">Research</button>
+  </div>
+
+<script>
+let ws = null;
+let currentAssistantEl = null;
+let iterCount = 0;
+let currentPhase = 'idle';
+const chat = document.getElementById('chat');
+const phase = document.getElementById('phase');
+const iterEl = document.getElementById('iter');
+const goBtn = document.getElementById('go');
+const inputEl = document.getElementById('input');
+
+inputEl.addEventListener('keydown', e => {
+  if (e.key === 'Enter') run();
+});
+
+function setPhase(text, cls) {
+  phase.textContent = text;
+  phase.className = 'badge ' + cls;
+  currentPhase = cls;
+}
+
+function addMsg(text, cls) {
+  const el = document.createElement('div');
+  el.className = 'msg ' + cls;
+  el.textContent = text;
+  chat.appendChild(el);
+  chat.scrollTop = chat.scrollHeight;
+  return el;
+}
+
+function addHandoffBanner(summary) {
+  const banner = document.createElement('div');
+  banner.className = 'handoff-banner';
+  const h3 = document.createElement('h3');
+  h3.textContent = 'Context Handoff: Researcher -> Analyst';
+  const p = document.createElement('p');
+  p.textContent = summary || 'Passing research context...';
+  banner.appendChild(h3);
+  banner.appendChild(p);
+  chat.appendChild(banner);
+  chat.scrollTop = chat.scrollHeight;
+}
+
+function addResultBanner(researcher, analyst, tokens) {
+  const banner = document.createElement('div');
+  banner.className = 'result-banner';
+  const h3 = document.createElement('h3');
+  h3.textContent = 'Pipeline Complete';
+  banner.appendChild(h3);
+
+  if (researcher && researcher.research_summary) {
+    const lbl = document.createElement('div');
+    lbl.className = 'label';
+    lbl.textContent = 'RESEARCH SUMMARY';
+    banner.appendChild(lbl);
+    const p = document.createElement('p');
+    p.textContent = researcher.research_summary;
+    banner.appendChild(p);
+  }
+
+  if (analyst && analyst.analysis) {
+    const lbl = document.createElement('div');
+    lbl.className = 'label';
+    lbl.textContent = 'ANALYSIS';
+    lbl.style.color = '#3fb950';
+    banner.appendChild(lbl);
+    const p = document.createElement('p');
+    p.textContent = analyst.analysis;
+    banner.appendChild(p);
+  }
+
+  if (tokens) {
+    const t = document.createElement('div');
+    t.className = 'tokens';
+    t.textContent = 'Total tokens: ' + tokens.toLocaleString();
+    banner.appendChild(t);
+  }
+
+  chat.appendChild(banner);
+  chat.scrollTop = chat.scrollHeight;
+}
+
+function connect() {
+  ws = new WebSocket('ws://' + location.host + '/ws');
+  ws.onopen = () => {
+    setPhase('Ready', 'done');
+    goBtn.disabled = false;
+  };
+  ws.onmessage = handleEvent;
+  ws.onerror = () => { setPhase('Error', 'error'); };
+  ws.onclose = () => {
+    setPhase('Reconnecting...', '');
+    goBtn.disabled = true;
+    setTimeout(connect, 2000);
+  };
+}
+
+function handleEvent(msg) {
+  const evt = JSON.parse(msg.data);
+
+  if (evt.type === 'phase') {
+    if (evt.phase === 'researcher') {
+      setPhase('Researcher', 'researcher');
+    } else if (evt.phase === 'handoff') {
+      setPhase('Handoff', 'handoff');
+    } else if (evt.phase === 'analyst') {
+      setPhase('Analyst', 'analyst');
+    }
+    iterCount = 0;
+    iterEl.style.display = 'none';
+  }
+  else if (evt.type === 'llm_text_delta') {
+    if (currentAssistantEl) {
+      currentAssistantEl.textContent += evt.content;
+      chat.scrollTop = chat.scrollHeight;
+    }
+  }
+  else if (evt.type === 'node_loop_iteration') {
+    iterCount = evt.iteration || (iterCount + 1);
+    iterEl.textContent = 'Step ' + iterCount;
+    iterEl.style.display = '';
+  }
+  else if (evt.type === 'tool_call_started') {
+    var info = evt.tool_name + '('
+      + JSON.stringify(evt.tool_input).slice(0, 120) + ')';
+    addMsg('TOOL  ' + info, 'event tool');
+  }
+  else if (evt.type === 'tool_call_completed') {
+    var preview = (evt.result || '').slice(0, 200);
+    var cls = evt.is_error ? 'stall' : 'tool';
+    addMsg(
+      'RESULT  ' + evt.tool_name + ': ' + preview,
+      'event ' + cls
+    );
+    var assistCls = currentPhase === 'analyst'
+      ? 'assistant analyst-msg' : 'assistant';
+    currentAssistantEl = addMsg('', assistCls);
+  }
+  else if (evt.type === 'handoff_context') {
+    addHandoffBanner(evt.summary);
+    var assistCls = 'assistant analyst-msg';
+    currentAssistantEl = addMsg('', assistCls);
+  }
+  else if (evt.type === 'node_result') {
+    if (evt.node_id === 'researcher') {
+      if (currentAssistantEl
+          && !currentAssistantEl.textContent) {
+        currentAssistantEl.remove();
+      }
+    }
+  }
+  else if (evt.type === 'done') {
+    setPhase('Done', 'done');
+    iterEl.style.display = 'none';
+    if (currentAssistantEl
+        && !currentAssistantEl.textContent) {
+      currentAssistantEl.remove();
+    }
+    currentAssistantEl = null;
+    addResultBanner(
+      evt.researcher, evt.analyst, evt.total_tokens
+    );
+    goBtn.disabled = false;
+    inputEl.placeholder = 'Enter another topic...';
+  }
+  else if (evt.type === 'error') {
+    setPhase('Error', 'error');
+    addMsg('ERROR  ' + evt.message, 'event stall');
+    goBtn.disabled = false;
+  }
+  else if (evt.type === 'node_stalled') {
+    addMsg('STALLED  ' + evt.reason, 'event stall');
+  }
+}
+
+function run() {
+  const text = inputEl.value.trim();
+  if (!text || !ws || ws.readyState !== 1) return;
+  chat.innerHTML = '';
+  addMsg(text, 'user');
+  currentAssistantEl = addMsg('', 'assistant');
+  inputEl.value = '';
+  goBtn.disabled = true;
+  ws.send(JSON.stringify({ topic: text }));
+}
+
+connect();
+</script>
+</body>
+</html>"""
+)
+
+
+# -------------------------------------------------------------------------
+# WebSocket handler — sequential Node A → Handoff → Node B
+# -------------------------------------------------------------------------
+
+
+async def handle_ws(websocket):
+    """Run the two-node handoff pipeline per user message."""
+    try:
+        async for raw in websocket:
+            try:
+                msg = json.loads(raw)
+            except Exception:
+                continue
+
+            topic = msg.get("topic", "")
+            if not topic:
+                continue
+
+            logger.info(f"Starting handoff pipeline for: {topic}")
+
+            try:
+                await _run_pipeline(websocket, topic)
+            except websockets.exceptions.ConnectionClosed:
+                logger.info("WebSocket closed during pipeline")
+                return
+            except Exception as e:
+                logger.exception("Pipeline error")
+                try:
+                    await websocket.send(json.dumps({"type": "error", "message": str(e)}))
+                except Exception:
+                    pass
+
+    except websockets.exceptions.ConnectionClosed:
+        pass
+
+
+async def _run_pipeline(websocket, topic: str):
+    """Execute: Node A (research) → ContextHandoff → Node B (analysis)."""
+    import shutil
+
+    # Fresh stores for each run
+    run_dir = Path(tempfile.mkdtemp(prefix="hive_run_", dir=STORE_DIR))
+    store_a = FileConversationStore(run_dir / "node_a")
+    store_b = FileConversationStore(run_dir / "node_b")
+
+    # Shared event bus
+    bus = EventBus()
+
+    async def forward_event(event):
+        try:
+            payload = {"type": event.type.value, **event.data}
+            if event.node_id:
+                payload["node_id"] = event.node_id
+            await websocket.send(json.dumps(payload))
+        except Exception:
+            pass
+
+    bus.subscribe(
+        event_types=[
+            EventType.NODE_LOOP_STARTED,
+            EventType.NODE_LOOP_ITERATION,
+            EventType.NODE_LOOP_COMPLETED,
+            EventType.LLM_TEXT_DELTA,
+            EventType.TOOL_CALL_STARTED,
+            EventType.TOOL_CALL_COMPLETED,
+            EventType.NODE_STALLED,
+        ],
+        handler=forward_event,
+    )
+
+    tools = list(TOOL_REGISTRY.get_tools().values())
+    tool_executor = TOOL_REGISTRY.get_executor()
+
+    # ---- Phase 1: Researcher ------------------------------------------------
+    await websocket.send(json.dumps({"type": "phase", "phase": "researcher"}))
+
+    node_a = EventLoopNode(
+        event_bus=bus,
+        judge=None,  # implicit judge: accept when output_keys filled
+        config=LoopConfig(
+            max_iterations=20,
+            max_tool_calls_per_turn=10,
+            max_history_tokens=32_000,
+        ),
+        conversation_store=store_a,
+        tool_executor=tool_executor,
+    )
+
+    ctx_a = NodeContext(
+        runtime=RUNTIME,
+        node_id="researcher",
+        node_spec=RESEARCHER_SPEC,
+        memory=SharedMemory(),
+        input_data={"topic": topic},
+        llm=LLM,
+        available_tools=tools,
+    )
+
+    result_a = await node_a.execute(ctx_a)
+    logger.info(
+        "Researcher done: success=%s, tokens=%s",
+        result_a.success,
+        result_a.tokens_used,
+    )
+
+    await websocket.send(
+        json.dumps(
+            {
+                "type": "node_result",
+                "node_id": "researcher",
+                "success": result_a.success,
+                "output": result_a.output,
+            }
+        )
+    )
+
+    if not result_a.success:
+        await websocket.send(
+            json.dumps(
+                {
+                    "type": "error",
+                    "message": f"Researcher failed: {result_a.error}",
+                }
+            )
+        )
+        return
+
+    # ---- Phase 2: Context Handoff -------------------------------------------
+    await websocket.send(json.dumps({"type": "phase", "phase": "handoff"}))
+
+    # Restore the researcher's conversation from store
+    conversation_a = await NodeConversation.restore(store_a)
+    if conversation_a is None:
+        await websocket.send(
+            json.dumps(
+                {
+                    "type": "error",
+                    "message": "Failed to restore researcher conversation",
+                }
+            )
+        )
+        return
+
+    handoff_engine = ContextHandoff(llm=LLM)
+    handoff_context = handoff_engine.summarize_conversation(
+        conversation=conversation_a,
+        node_id="researcher",
+        output_keys=["research_summary"],
+    )
+
+    formatted_handoff = ContextHandoff.format_as_input(handoff_context)
+    logger.info(
+        "Handoff: %d turns, ~%d tokens, keys=%s",
+        handoff_context.turn_count,
+        handoff_context.total_tokens_used,
+        list(handoff_context.key_outputs.keys()),
+    )
+
+    # Send handoff context to browser
+    await websocket.send(
+        json.dumps(
+            {
+                "type": "handoff_context",
+                "summary": handoff_context.summary[:500],
+                "turn_count": handoff_context.turn_count,
+                "tokens": handoff_context.total_tokens_used,
+                "key_outputs": handoff_context.key_outputs,
+            }
+        )
+    )
+
+    # ---- Phase 3: Analyst ---------------------------------------------------
+    await websocket.send(json.dumps({"type": "phase", "phase": "analyst"}))
+
+    node_b = EventLoopNode(
+        event_bus=bus,
+        judge=None,  # implicit judge
+        config=LoopConfig(
+            max_iterations=10,
+            max_tool_calls_per_turn=5,
+            max_history_tokens=32_000,
+        ),
+        conversation_store=store_b,
+    )
+
+    ctx_b = NodeContext(
+        runtime=RUNTIME,
+        node_id="analyst",
+        node_spec=ANALYST_SPEC,
+        memory=SharedMemory(),
+        input_data={"context": formatted_handoff},
+        llm=LLM,
+        available_tools=[],
+    )
+
+    result_b = await node_b.execute(ctx_b)
+    logger.info(
+        "Analyst done: success=%s, tokens=%s",
+        result_b.success,
+        result_b.tokens_used,
+    )
+
+    # ---- Done ---------------------------------------------------------------
+    await websocket.send(
+        json.dumps(
+            {
+                "type": "done",
+                "researcher": result_a.output,
+                "analyst": result_b.output,
+                "total_tokens": ((result_a.tokens_used or 0) + (result_b.tokens_used or 0)),
+            }
+        )
+    )
+
+    # Clean up temp stores
+    try:
+        shutil.rmtree(run_dir)
+    except Exception:
+        pass
+
+
+# -------------------------------------------------------------------------
+# HTTP handler
+# -------------------------------------------------------------------------
+
+
+async def process_request(connection, request: Request):
+    """Serve HTML on GET /, upgrade to WebSocket on /ws."""
+    if request.path == "/ws":
+        return None
+    return Response(
+        HTTPStatus.OK,
+        "OK",
+        websockets.Headers({"Content-Type": "text/html; charset=utf-8"}),
+        HTML_PAGE.encode(),
+    )
+
+
+# -------------------------------------------------------------------------
+# Main
+# -------------------------------------------------------------------------
+
+
+async def main():
+    port = 8766
+    async with websockets.serve(
+        handle_ws,
+        "0.0.0.0",
+        port,
+        process_request=process_request,
+    ):
+        logger.info(f"Handoff demo at http://localhost:{port}")
+        logger.info("Enter a research topic to start the pipeline.")
+        await asyncio.Future()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

core/examples/manual_agent.py

@@ -0,0 +1,132 @@
+"""
+Minimal Manual Agent Example
+----------------------------
+This example demonstrates how to build and run an agent programmatically
+without using the Claude Code CLI or external LLM APIs.
+
+It uses custom NodeProtocol implementations to define logic in pure Python,
+making it perfect for understanding the core runtime loop:
+Setup -> Graph definition -> Execution -> Result
+
+Run with:
+    uv run python core/examples/manual_agent.py
+"""
+
+import asyncio
+
+from framework.graph import EdgeCondition, EdgeSpec, Goal, GraphSpec, NodeSpec
+from framework.graph.executor import GraphExecutor
+from framework.graph.node import NodeContext, NodeProtocol, NodeResult
+from framework.runtime.core import Runtime
+
+
+# 1. Define Node Logic (Custom NodeProtocol implementations)
+class GreeterNode(NodeProtocol):
+    """Generate a simple greeting."""
+
+    async def execute(self, ctx: NodeContext) -> NodeResult:
+        name = ctx.input_data.get("name", "World")
+        greeting = f"Hello, {name}!"
+        ctx.memory.write("greeting", greeting)
+        return NodeResult(success=True, output={"greeting": greeting})
+
+
+class UppercaserNode(NodeProtocol):
+    """Convert text to uppercase."""
+
+    async def execute(self, ctx: NodeContext) -> NodeResult:
+        greeting = ctx.input_data.get("greeting") or ctx.memory.read("greeting") or ""
+        result = greeting.upper()
+        ctx.memory.write("final_greeting", result)
+        return NodeResult(success=True, output={"final_greeting": result})
+
+
+async def main():
+    print("Setting up Manual Agent...")
+
+    # 2. Define the Goal
+    # Every agent needs a goal with success criteria
+    goal = Goal(
+        id="greet-user",
+        name="Greet User",
+        description="Generate a friendly uppercase greeting",
+        success_criteria=[
+            {
+                "id": "greeting_generated",
+                "description": "Greeting produced",
+                "metric": "custom",
+                "target": "any",
+            }
+        ],
+    )
+
+    # 3. Define Nodes
+    # Nodes describe steps in the process
+    node1 = NodeSpec(
+        id="greeter",
+        name="Greeter",
+        description="Generates a simple greeting",
+        node_type="event_loop",
+        input_keys=["name"],
+        output_keys=["greeting"],
+    )
+
+    node2 = NodeSpec(
+        id="uppercaser",
+        name="Uppercaser",
+        description="Converts greeting to uppercase",
+        node_type="event_loop",
+        input_keys=["greeting"],
+        output_keys=["final_greeting"],
+    )
+
+    # 4. Define Edges
+    # Edges define the flow between nodes
+    edge1 = EdgeSpec(
+        id="greet-to-upper",
+        source="greeter",
+        target="uppercaser",
+        condition=EdgeCondition.ON_SUCCESS,
+    )
+
+    # 5. Create Graph
+    # The graph works like a blueprint connecting nodes and edges
+    graph = GraphSpec(
+        id="greeting-agent",
+        goal_id="greet-user",
+        entry_node="greeter",
+        terminal_nodes=["uppercaser"],
+        nodes=[node1, node2],
+        edges=[edge1],
+    )
+
+    # 6. Initialize Runtime & Executor
+    # Runtime handles state/memory; Executor runs the graph
+    from pathlib import Path
+
+    runtime = Runtime(storage_path=Path("./agent_logs"))
+    executor = GraphExecutor(runtime=runtime)
+
+    # 7. Register Node Implementations
+    # Connect node IDs in the graph to actual Python implementations
+    executor.register_node("greeter", GreeterNode())
+    executor.register_node("uppercaser", UppercaserNode())
+
+    # 8. Execute Agent
+    print("Executing agent with input: name='Alice'...")
+
+    result = await executor.execute(graph=graph, goal=goal, input_data={"name": "Alice"})
+
+    # 9. Verify Results
+    if result.success:
+        print("\nSuccess!")
+        print(f"Path taken: {' -> '.join(result.path)}")
+        print(f"Final output: {result.output.get('final_greeting')}")
+    else:
+        print(f"\nFailed: {result.error}")
+
+
+if __name__ == "__main__":
+    # Optional: Enable logging to see internal decision flow
+    # logging.basicConfig(level=logging.INFO)
+    asyncio.run(main())

core/examples/mcp_integration_example.py

@@ -37,9 +37,9 @@ async def example_1_programmatic_registration():
     print(f"\nAvailable tools: {list(tools.keys())}")
 
     # Run the agent with MCP tools available
-    result = await runner.run({
-        "objective": "Search for 'Claude AI' and summarize the top 3 results"
-    })
+    result = await runner.run(
+        {"objective": "Search for 'Claude AI' and summarize the top 3 results"}
+    )
 
     print(f"\nAgent result: {result}")
 
@@ -78,10 +78,8 @@ async def example_3_config_file():
 
     # Copy example config (in practice, you'd place this in your agent folder)
     import shutil
-    shutil.copy(
-        "examples/mcp_servers.json",
-        test_agent_path / "mcp_servers.json"
-    )
+
+    shutil.copy("examples/mcp_servers.json", test_agent_path / "mcp_servers.json")
 
     # Load agent - MCP servers will be auto-discovered
     runner = AgentRunner.load(test_agent_path)
@@ -101,34 +99,30 @@ async def example_4_custom_agent_with_mcp_tools():
     """Example 4: Build custom agent that uses MCP tools"""
     print("\n=== Example 4: Custom Agent with MCP Tools ===\n")
 
-    from framework.builder.workflow import WorkflowBuilder
+    from framework.builder.workflow import GraphBuilder
 
     # Create a workflow builder
-    builder = WorkflowBuilder()
+    builder = GraphBuilder()
 
     # Define goal
     builder.set_goal(
         goal_id="web-researcher",
         name="Web Research Agent",
-        description="Search the web and summarize findings"
+        description="Search the web and summarize findings",
     )
 
     # Add success criteria
     builder.add_success_criterion(
-        "search-results",
-        "Successfully retrieve at least 3 web search results"
-    )
-    builder.add_success_criterion(
-        "summary",
-        "Provide a clear, concise summary of the findings"
+        "search-results", "Successfully retrieve at least 3 web search results"
     )
+    builder.add_success_criterion("summary", "Provide a clear, concise summary of the findings")
 
     # Add nodes that will use MCP tools
     builder.add_node(
         node_id="web-searcher",
         name="Web Search",
         description="Search the web for information",
-        node_type="llm_tool_use",
+        node_type="event_loop",
         system_prompt="Search for {query} and return the top results. Use the web_search tool.",
         tools=["web_search"],  # This tool comes from tools MCP server
         input_keys=["query"],
@@ -139,7 +133,7 @@ async def example_4_custom_agent_with_mcp_tools():
         node_id="summarizer",
         name="Summarize Results",
         description="Summarize the search results",
-        node_type="llm_generate",
+        node_type="event_loop",
         system_prompt="Summarize the following search results in 2-3 sentences: {search_results}",
         input_keys=["search_results"],
         output_keys=["summary"],
@@ -192,6 +186,7 @@ async def main():
     except Exception as e:
         print(f"\nError running example: {e}")
         import traceback
+
         traceback.print_exc()
 
 

core/examples/mcp_servers.json

@@ -4,8 +4,8 @@
       "name": "tools",
       "description": "Aden tools including web search, file operations, and PDF reading",
       "transport": "stdio",
-      "command": "python",
-      "args": ["mcp_server.py", "--stdio"],
+      "command": "uv",
+      "args": ["run", "python", "mcp_server.py", "--stdio"],
       "cwd": "../tools",
       "env": {
         "BRAVE_SEARCH_API_KEY": "${BRAVE_SEARCH_API_KEY}"

core/framework/__init__.py

@@ -22,24 +22,22 @@ The framework includes a Goal-Based Testing system (Goal → Agent → Eval):
 See `framework.testing` for details.
 """
 
-from framework.schemas.decision import Decision, Option, Outcome, DecisionEvaluation
-from framework.schemas.run import Run, RunSummary, Problem
-from framework.runtime.core import Runtime
 from framework.builder.query import BuilderQuery
-from framework.llm import LLMProvider, AnthropicProvider
-from framework.runner import AgentRunner, AgentOrchestrator
+from framework.llm import AnthropicProvider, LLMProvider
+from framework.runner import AgentOrchestrator, AgentRunner
+from framework.runtime.core import Runtime
+from framework.schemas.decision import Decision, DecisionEvaluation, Option, Outcome
+from framework.schemas.run import Problem, Run, RunSummary
 
 # Testing framework
 from framework.testing import (
+    ApprovalStatus,
+    DebugTool,
+    ErrorCategory,
     Test,
     TestResult,
-    TestSuiteResult,
     TestStorage,
-    ApprovalStatus,
-    ErrorCategory,
-    ConstraintTestGenerator,
-    SuccessCriteriaTestGenerator,
-    DebugTool,
+    TestSuiteResult,
 )
 
 __all__ = [
@@ -68,7 +66,5 @@ __all__ = [
     "TestStorage",
     "ApprovalStatus",
     "ErrorCategory",
-    "ConstraintTestGenerator",
-    "SuccessCriteriaTestGenerator",
     "DebugTool",
 ]