feat: active streams and waiting nodes

* 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.local.json

@@ -1,46 +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",
-      "Bash(python -m agent:*)",
-      "Bash(python agent.py:*)",
-      "Bash(python -c:*)",
-      "Bash(done)",
-      "Bash(xargs cat:*)",
-      "mcp__agent-builder__list_mcp_tools",
-      "mcp__agent-builder__add_mcp_server",
-      "Bash(gh issue list:*)",
-      "WebFetch(domain:github.com)",
-      "Bash(pip install:*)",
-      "Bash(python -m pytest:*)",
-      "Bash(git checkout:*)",
-      "Bash(git add:*)",
-      "Bash(git commit -m \"$\\(cat <<''EOF''\nfeat\\(tools\\): Add Excel tool for spreadsheet operations\n\nAdds a new Excel tool for reading and manipulating .xlsx/.xlsm files:\n- excel_read: Read Excel files with pagination and sheet selection\n- excel_write: Create new Excel files with data\n- excel_append: Append rows to existing files\n- excel_info: Get metadata about Excel files \\(sheets, columns, row counts\\)\n- excel_sheet_list: List all sheets in a workbook\n\nIncludes comprehensive test coverage \\(37 tests\\) and documentation.\n\nReferences #2805\n\nCo-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>\nEOF\n\\)\")",
-      "Bash(git push:*)",
-      "Bash(git pull:*)",
-      "Bash(git stash:*)",
-      "Bash(git merge:*)"
-    ]
-  },
-  "enableAllProjectMcpServers": true,
-  "enabledMcpjsonServers": [
-    "agent-builder",
-    "tools"
-  ]
-}

.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

@@ -1,361 +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: "2.0"
-  type: procedural
-  part_of: building-agents
-  requires: building-agents-core
----
-
-# Agent Construction - EXECUTE THESE STEPS
-
-**THIS IS AN EXECUTABLE WORKFLOW. DO NOT DISPLAY THIS FILE. EXECUTE THE STEPS BELOW.**
-
-When this skill is loaded, IMMEDIATELY begin executing Step 1. Do not explain what you will do - just do it.
-
----
-
-## STEP 1: Initialize Build Environment
-
-**EXECUTE THESE TOOL CALLS NOW:**
-
-1. Register the hive-tools MCP server:
-
-```
-mcp__agent-builder__add_mcp_server(
-    name="hive-tools",
-    transport="stdio",
-    command="python",
-    args='["mcp_server.py", "--stdio"]',
-    cwd="tools",
-    description="Hive tools MCP server"
-)
-```
-
-2. Create a build session (replace AGENT_NAME with the user's requested agent name in snake_case):
-
-```
-mcp__agent-builder__create_session(name="AGENT_NAME")
-```
-
-3. Discover available tools:
-
-```
-mcp__agent-builder__list_mcp_tools()
-```
-
-4. Create the package directory:
-
-```
-mkdir -p exports/AGENT_NAME/nodes
-```
-
-**AFTER completing these calls**, tell the user:
-
-> ✅ Build environment initialized
->
-> - Session created
-> - Available tools: [list the tools from step 3]
->
-> Proceeding to define the agent goal...
-
-**THEN immediately proceed to STEP 2.**
-
----
-
-## STEP 2: Define and Approve Goal
-
-**PROPOSE a goal to the user.** Based on what they asked for, propose:
-
-- Goal ID (kebab-case)
-- Goal name
-- Goal description
-- 3-5 success criteria (each with: id, description, metric, target, weight)
-- 2-4 constraints (each with: id, description, constraint_type, category)
-
-**FORMAT your proposal as a clear summary, then ask for approval:**
-
-> **Proposed Goal: [Name]**
->
-> [Description]
->
-> **Success Criteria:**
->
-> 1. [criterion 1]
-> 2. [criterion 2]
->    ...
->
-> **Constraints:**
->
-> 1. [constraint 1]
-> 2. [constraint 2]
->    ...
-
-**THEN call AskUserQuestion:**
-
-```
-AskUserQuestion(questions=[{
-    "question": "Do you approve this goal definition?",
-    "header": "Goal",
-    "options": [
-        {"label": "Approve", "description": "Goal looks good, proceed"},
-        {"label": "Modify", "description": "I want to change something"}
-    ],
-    "multiSelect": false
-}])
-```
-
-**WAIT for user response.**
-
-- If **Approve**: Call `mcp__agent-builder__set_goal(...)` with the goal details, then proceed to STEP 3
-- If **Modify**: Ask what they want to change, update proposal, ask again
-
----
-
-## STEP 3: Design Node Workflow
-
-**BEFORE designing nodes**, review the available tools from Step 1. Nodes can ONLY use tools that exist.
-
-**DESIGN the workflow** as a series of nodes. For each node, determine:
-
-- node_id (kebab-case)
-- name
-- description
-- node_type: `"llm_generate"` (no tools) or `"llm_tool_use"` (uses tools)
-- input_keys (what data this node receives)
-- output_keys (what data this node produces)
-- tools (ONLY tools that exist - empty list for llm_generate)
-- system_prompt
-
-**PRESENT the workflow to the user:**
-
-> **Proposed Workflow: [N] nodes**
->
-> 1. **[node-id]** - [description]
->
->    - Type: [llm_generate/llm_tool_use]
->    - Input: [keys]
->    - Output: [keys]
->    - Tools: [tools or "none"]
->
-> 2. **[node-id]** - [description]
->    ...
->
-> **Flow:** node1 → node2 → node3 → ...
-
-**THEN call AskUserQuestion:**
-
-```
-AskUserQuestion(questions=[{
-    "question": "Do you approve this workflow design?",
-    "header": "Workflow",
-    "options": [
-        {"label": "Approve", "description": "Workflow looks good, proceed to build nodes"},
-        {"label": "Modify", "description": "I want to change the workflow"}
-    ],
-    "multiSelect": false
-}])
-```
-
-**WAIT for user response.**
-
-- If **Approve**: Proceed to STEP 4
-- If **Modify**: Ask what they want to change, update design, ask again
-
----
-
-## STEP 4: Build Nodes One by One
-
-**FOR EACH node in the approved workflow:**
-
-1. **Call** `mcp__agent-builder__add_node(...)` with the node details
-
-   - input_keys and output_keys must be JSON strings: `'["key1", "key2"]'`
-   - tools must be a JSON string: `'["tool1"]'` or `'[]'`
-
-2. **Call** `mcp__agent-builder__test_node(...)` to validate:
-
-```
-mcp__agent-builder__test_node(
-    node_id="the-node-id",
-    test_input='{"key": "test value"}',
-    mock_llm_response='{"output_key": "test output"}'
-)
-```
-
-3. **Check result:**
-
-   - If valid: Tell user "✅ Node [id] validated" and continue to next node
-   - If invalid: Show errors, fix the node, re-validate
-
-4. **Show progress** after each node:
-
-```
-mcp__agent-builder__get_session_status()
-```
-
-> ✅ Node [X] of [Y] complete: [node-id]
-
-**AFTER all nodes are added and validated**, proceed to STEP 5.
-
----
-
-## STEP 5: Connect Edges
-
-**DETERMINE the edges** based on the workflow flow. For each connection:
-
-- edge_id (kebab-case)
-- source (node that outputs)
-- target (node that receives)
-- condition: `"on_success"`, `"always"`, `"on_failure"`, or `"conditional"`
-- condition_expr (Python expression, only if conditional)
-- priority (integer, lower = higher priority)
-
-**FOR EACH edge, call:**
-
-```
-mcp__agent-builder__add_edge(
-    edge_id="source-to-target",
-    source="source-node-id",
-    target="target-node-id",
-    condition="on_success",
-    condition_expr="",
-    priority=1
-)
-```
-
-**AFTER all edges are added, validate the graph:**
-
-```
-mcp__agent-builder__validate_graph()
-```
-
-- If valid: Tell user "✅ Graph structure validated" and proceed to STEP 6
-- If invalid: Show errors, fix edges, re-validate
-
----
-
-## STEP 6: Generate Agent Package
-
-**EXPORT the graph data:**
-
-```
-mcp__agent-builder__export_graph()
-```
-
-This returns JSON with all the goal, nodes, edges, and MCP server configurations.
-
-**THEN write the Python package files** using the exported data. Create these files in `exports/AGENT_NAME/`:
-
-1. `config.py` - Runtime configuration with model settings
-2. `nodes/__init__.py` - All NodeSpec definitions
-3. `agent.py` - Goal, edges, graph config, and agent class
-4. `__init__.py` - Package exports
-5. `__main__.py` - CLI interface
-6. `mcp_servers.json` - MCP server configurations
-7. `README.md` - Usage documentation
-
-**IMPORTANT entry_points format:**
-
-- MUST be: `{"start": "first-node-id"}`
-- NOT: `{"first-node-id": ["input_keys"]}` (WRONG)
-- NOT: `{"first-node-id"}` (WRONG - this is a set)
-
-**Use the example agent** at `.claude/skills/building-agents-construction/examples/online_research_agent/` as a template for file structure and patterns.
-
-**AFTER writing all files, tell the user:**
-
-> ✅ Agent package created: `exports/AGENT_NAME/`
->
-> **Files generated:**
->
-> - `__init__.py` - Package exports
-> - `agent.py` - Goal, nodes, edges, agent class
-> - `config.py` - Runtime configuration
-> - `__main__.py` - CLI interface
-> - `nodes/__init__.py` - Node definitions
-> - `mcp_servers.json` - MCP server config
-> - `README.md` - Usage documentation
->
-> **Test your agent:**
->
-> ```bash
-> cd /home/timothy/oss/hive
-> PYTHONPATH=core:exports python -m AGENT_NAME validate
-> PYTHONPATH=core:exports python -m AGENT_NAME info
-> ```
-
----
-
-## STEP 7: Verify and Test
-
-**RUN validation:**
-
-```bash
-cd /home/timothy/oss/hive && PYTHONPATH=core:exports python -m AGENT_NAME validate
-```
-
-- If valid: Agent is complete!
-- If errors: Fix the issues and re-run
-
-**SHOW final session summary:**
-
-```
-mcp__agent-builder__get_session_status()
-```
-
-**TELL the user the agent is ready** and suggest next steps:
-
-- Run with mock mode to test without API calls
-- Use `/testing-agent` skill for comprehensive testing
-- Use `/setup-credentials` if the agent needs API keys
-
----
-
-## REFERENCE: Node Types
-
-| Type           | tools param            | Use when                                       |
-| -------------- | ---------------------- | ---------------------------------------------- |
-| `llm_generate` | `'[]'`                 | Pure reasoning, JSON output, no external calls |
-| `llm_tool_use` | `'["tool1", "tool2"]'` | Needs to call MCP tools                        |
-
----
-
-## REFERENCE: Edge Conditions
-
-| Condition     | When edge is followed                 |
-| ------------- | ------------------------------------- |
-| `on_success`  | Source node completed successfully    |
-| `on_failure`  | Source node failed                    |
-| `always`      | Always, regardless of success/failure |
-| `conditional` | When condition_expr evaluates to True |
-
----
-
-## REFERENCE: System Prompt Best Practice
-
-For nodes with JSON output, include this in the system_prompt:
-
-```
-CRITICAL: Return ONLY raw JSON. NO markdown, NO code blocks.
-Just the JSON object starting with { and ending with }.
-
-Return this exact structure:
-{
-  "key1": "...",
-  "key2": "..."
-}
-```
-
----
-
-## COMMON MISTAKES TO AVOID
-
-1. **Using tools that don't exist** - Always check `mcp__agent-builder__list_mcp_tools()` first
-2. **Wrong entry_points format** - Must be `{"start": "node-id"}`, NOT a set or list
-3. **Skipping validation** - Always validate nodes and graph before proceeding
-4. **Not waiting for approval** - Always ask user before major steps
-5. **Displaying this file** - Execute the steps, don't show documentation

.claude/skills/building-agents-construction/examples/online_research_agent/README.md

@@ -1,80 +0,0 @@
-# Online Research Agent
-
-Deep-dive research agent that searches 10+ sources and produces comprehensive narrative reports with citations.
-
-## Features
-
-- Generates multiple search queries from a topic
-- Searches and fetches 15+ web sources
-- Evaluates and ranks sources by relevance
-- Synthesizes findings into themes
-- Writes narrative report with numbered citations
-- Quality checks for uncited claims
-- Saves report to local markdown file
-
-## Usage
-
-### CLI
-
-```bash
-# Show agent info
-python -m online_research_agent info
-
-# Validate structure
-python -m online_research_agent validate
-
-# Run research on a topic
-python -m online_research_agent run --topic "impact of AI on healthcare"
-
-# Interactive shell
-python -m online_research_agent shell
-```
-
-### Python API
-
-```python
-from online_research_agent import default_agent
-
-# Simple usage
-result = await default_agent.run({"topic": "climate change solutions"})
-
-# Check output
-if result.success:
-    print(f"Report saved to: {result.output['file_path']}")
-    print(result.output['final_report'])
-```
-
-## Workflow
-
-```
-parse-query → search-sources → fetch-content → evaluate-sources
-                                                      ↓
-                                write-report ← synthesize-findings
-                                      ↓
-                               quality-check → save-report
-```
-
-## Output
-
-Reports are saved to `./research_reports/` as markdown files with:
-
-1. Executive Summary
-2. Introduction
-3. Key Findings (by theme)
-4. Analysis
-5. Conclusion
-6. References
-
-## Requirements
-
-- Python 3.11+
-- LLM provider API key (Groq, Cerebras, etc.)
-- Internet access for web search/fetch
-
-## Configuration
-
-Edit `config.py` to change:
-
-- `model`: LLM model (default: groq/moonshotai/kimi-k2-instruct-0905)
-- `temperature`: Generation temperature (default: 0.7)
-- `max_tokens`: Max tokens per response (default: 16384)

.claude/skills/building-agents-construction/examples/online_research_agent/__init__.py

@@ -1,23 +0,0 @@
-"""
-Online Research Agent - Deep-dive research with narrative reports.
-
-Research any topic by searching multiple sources, synthesizing information,
-and producing a well-structured narrative report with citations.
-"""
-
-from .agent import OnlineResearchAgent, default_agent, goal, nodes, edges
-from .config import RuntimeConfig, AgentMetadata, default_config, metadata
-
-__version__ = "1.0.0"
-
-__all__ = [
-    "OnlineResearchAgent",
-    "default_agent",
-    "goal",
-    "nodes",
-    "edges",
-    "RuntimeConfig",
-    "AgentMetadata",
-    "default_config",
-    "metadata",
-]

.claude/skills/building-agents-construction/examples/online_research_agent/agent.py

@@ -1,429 +0,0 @@
-"""Agent graph construction for Online Research Agent."""
-
-from framework.graph import EdgeSpec, EdgeCondition, Goal, SuccessCriterion, Constraint
-from framework.graph.edge import GraphSpec
-from framework.graph.executor import ExecutionResult
-from framework.runtime.agent_runtime import AgentRuntime, create_agent_runtime
-from framework.runtime.execution_stream import EntryPointSpec
-from framework.llm import LiteLLMProvider
-from framework.runner.tool_registry import ToolRegistry
-
-from .config import default_config, metadata
-from .nodes import (
-    parse_query_node,
-    search_sources_node,
-    fetch_content_node,
-    evaluate_sources_node,
-    synthesize_findings_node,
-    write_report_node,
-    quality_check_node,
-    save_report_node,
-)
-
-# Goal definition
-goal = Goal(
-    id="comprehensive-online-research",
-    name="Comprehensive Online Research",
-    description="Research any topic by searching multiple sources, synthesizing information, and producing a well-structured narrative report with citations.",
-    success_criteria=[
-        SuccessCriterion(
-            id="source-coverage",
-            description="Query 10+ diverse sources",
-            metric="source_count",
-            target=">=10",
-            weight=0.20,
-        ),
-        SuccessCriterion(
-            id="relevance",
-            description="All sources directly address the query",
-            metric="relevance_score",
-            target="90%",
-            weight=0.25,
-        ),
-        SuccessCriterion(
-            id="synthesis",
-            description="Synthesize findings into coherent narrative",
-            metric="coherence_score",
-            target="85%",
-            weight=0.25,
-        ),
-        SuccessCriterion(
-            id="citations",
-            description="Include citations for all claims",
-            metric="citation_coverage",
-            target="100%",
-            weight=0.15,
-        ),
-        SuccessCriterion(
-            id="actionable",
-            description="Report answers the user's question",
-            metric="answer_completeness",
-            target="90%",
-            weight=0.15,
-        ),
-    ],
-    constraints=[
-        Constraint(
-            id="no-hallucination",
-            description="Only include information found in sources",
-            constraint_type="quality",
-            category="accuracy",
-        ),
-        Constraint(
-            id="source-attribution",
-            description="Every factual claim must cite its source",
-            constraint_type="quality",
-            category="accuracy",
-        ),
-        Constraint(
-            id="recency-preference",
-            description="Prefer recent sources when relevant",
-            constraint_type="quality",
-            category="relevance",
-        ),
-        Constraint(
-            id="no-paywalled",
-            description="Avoid sources that require payment to access",
-            constraint_type="functional",
-            category="accessibility",
-        ),
-    ],
-)
-
-# Node list
-nodes = [
-    parse_query_node,
-    search_sources_node,
-    fetch_content_node,
-    evaluate_sources_node,
-    synthesize_findings_node,
-    write_report_node,
-    quality_check_node,
-    save_report_node,
-]
-
-# Edge definitions
-edges = [
-    EdgeSpec(
-        id="parse-to-search",
-        source="parse-query",
-        target="search-sources",
-        condition=EdgeCondition.ON_SUCCESS,
-        priority=1,
-    ),
-    EdgeSpec(
-        id="search-to-fetch",
-        source="search-sources",
-        target="fetch-content",
-        condition=EdgeCondition.ON_SUCCESS,
-        priority=1,
-    ),
-    EdgeSpec(
-        id="fetch-to-evaluate",
-        source="fetch-content",
-        target="evaluate-sources",
-        condition=EdgeCondition.ON_SUCCESS,
-        priority=1,
-    ),
-    EdgeSpec(
-        id="evaluate-to-synthesize",
-        source="evaluate-sources",
-        target="synthesize-findings",
-        condition=EdgeCondition.ON_SUCCESS,
-        priority=1,
-    ),
-    EdgeSpec(
-        id="synthesize-to-write",
-        source="synthesize-findings",
-        target="write-report",
-        condition=EdgeCondition.ON_SUCCESS,
-        priority=1,
-    ),
-    EdgeSpec(
-        id="write-to-quality",
-        source="write-report",
-        target="quality-check",
-        condition=EdgeCondition.ON_SUCCESS,
-        priority=1,
-    ),
-    EdgeSpec(
-        id="quality-to-save",
-        source="quality-check",
-        target="save-report",
-        condition=EdgeCondition.ON_SUCCESS,
-        priority=1,
-    ),
-]
-
-# Graph configuration
-entry_node = "parse-query"
-entry_points = {"start": "parse-query"}
-pause_nodes = []
-terminal_nodes = ["save-report"]
-
-
-class OnlineResearchAgent:
-    """
-    Online Research Agent - Deep-dive research with narrative reports.
-
-    Uses AgentRuntime for multi-entrypoint support with HITL pause/resume.
-    """
-
-    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._runtime: AgentRuntime | None = None
-        self._graph: GraphSpec | None = None
-
-    def _build_entry_point_specs(self) -> list[EntryPointSpec]:
-        """Convert entry_points dict to EntryPointSpec list."""
-        specs = []
-        for ep_id, node_id in self.entry_points.items():
-            if ep_id == "start":
-                trigger_type = "manual"
-                name = "Start"
-            elif "_resume" in ep_id:
-                trigger_type = "resume"
-                name = f"Resume from {ep_id.replace('_resume', '')}"
-            else:
-                trigger_type = "manual"
-                name = ep_id.replace("-", " ").title()
-
-            specs.append(
-                EntryPointSpec(
-                    id=ep_id,
-                    name=name,
-                    entry_node=node_id,
-                    trigger_type=trigger_type,
-                    isolation_level="shared",
-                )
-            )
-        return specs
-
-    def _create_runtime(self, mock_mode=False) -> AgentRuntime:
-        """Create AgentRuntime instance."""
-        import json
-        from pathlib import Path
-
-        # Persistent storage in ~/.hive for telemetry and run history
-        storage_path = Path.home() / ".hive" / "online_research_agent"
-        storage_path.mkdir(parents=True, exist_ok=True)
-
-        tool_registry = ToolRegistry()
-
-        # Load MCP servers (always load, needed for tool validation)
-        agent_dir = Path(__file__).parent
-        mcp_config_path = agent_dir / "mcp_servers.json"
-
-        if mcp_config_path.exists():
-            with open(mcp_config_path) as f:
-                mcp_servers = json.load(f)
-
-            for server_config in mcp_servers.get("servers", []):
-                # Resolve relative cwd paths
-                cwd = server_config.get("cwd")
-                if cwd and not Path(cwd).is_absolute():
-                    server_config["cwd"] = str(agent_dir / cwd)
-                tool_registry.register_mcp_server(server_config)
-
-        llm = None
-        if not mock_mode:
-            # LiteLLMProvider uses environment variables for API keys
-            llm = LiteLLMProvider(
-                model=self.config.model,
-                api_key=self.config.api_key,
-                api_base=self.config.api_base,
-            )
-
-        self._graph = GraphSpec(
-            id="online-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,
-        )
-
-        # Create AgentRuntime with all entry points
-        self._runtime = create_agent_runtime(
-            graph=self._graph,
-            goal=self.goal,
-            storage_path=storage_path,
-            entry_points=self._build_entry_point_specs(),
-            llm=llm,
-            tools=list(tool_registry.get_tools().values()),
-            tool_executor=tool_registry.get_executor(),
-        )
-
-        return self._runtime
-
-    async def start(self, mock_mode=False) -> None:
-        """Start the agent runtime."""
-        if self._runtime is None:
-            self._create_runtime(mock_mode=mock_mode)
-        await self._runtime.start()
-
-    async def stop(self) -> None:
-        """Stop the agent runtime."""
-        if self._runtime is not None:
-            await self._runtime.stop()
-
-    async def trigger(
-        self,
-        entry_point: str,
-        input_data: dict,
-        correlation_id: str | None = None,
-        session_state: dict | None = None,
-    ) -> str:
-        """
-        Trigger execution at a specific entry point (non-blocking).
-
-        Args:
-            entry_point: Entry point ID (e.g., "start", "pause-node_resume")
-            input_data: Input data for the execution
-            correlation_id: Optional ID to correlate related executions
-            session_state: Optional session state to resume from (with paused_at, memory)
-
-        Returns:
-            Execution ID for tracking
-        """
-        if self._runtime is None or not self._runtime.is_running:
-            raise RuntimeError("Agent runtime not started. Call start() first.")
-        return await self._runtime.trigger(
-            entry_point, input_data, correlation_id, session_state=session_state
-        )
-
-    async def trigger_and_wait(
-        self,
-        entry_point: str,
-        input_data: dict,
-        timeout: float | None = None,
-        session_state: dict | None = None,
-    ) -> ExecutionResult | None:
-        """
-        Trigger execution and wait for completion.
-
-        Args:
-            entry_point: Entry point ID
-            input_data: Input data for the execution
-            timeout: Maximum time to wait (seconds)
-            session_state: Optional session state to resume from (with paused_at, memory)
-
-        Returns:
-            ExecutionResult or None if timeout
-        """
-        if self._runtime is None or not self._runtime.is_running:
-            raise RuntimeError("Agent runtime not started. Call start() first.")
-        return await self._runtime.trigger_and_wait(
-            entry_point, input_data, timeout, session_state=session_state
-        )
-
-    async def run(
-        self, context: dict, mock_mode=False, session_state=None
-    ) -> ExecutionResult:
-        """
-        Run the agent (convenience method for simple single execution).
-
-        For more control, use start() + trigger_and_wait() + stop().
-        """
-        await self.start(mock_mode=mock_mode)
-        try:
-            # Determine entry point based on session_state
-            if session_state and "paused_at" in session_state:
-                paused_node = session_state["paused_at"]
-                resume_key = f"{paused_node}_resume"
-                if resume_key in self.entry_points:
-                    entry_point = resume_key
-                else:
-                    entry_point = "start"
-            else:
-                entry_point = "start"
-
-            result = await self.trigger_and_wait(
-                entry_point, context, session_state=session_state
-            )
-            return result or ExecutionResult(success=False, error="Execution timeout")
-        finally:
-            await self.stop()
-
-    async def get_goal_progress(self) -> dict:
-        """Get goal progress across all executions."""
-        if self._runtime is None:
-            raise RuntimeError("Agent runtime not started")
-        return await self._runtime.get_goal_progress()
-
-    def get_stats(self) -> dict:
-        """Get runtime statistics."""
-        if self._runtime is None:
-            return {"running": False}
-        return self._runtime.get_stats()
-
-    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,
-            "multi_entrypoint": True,
-        }
-
-    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 pause in self.pause_nodes:
-            if pause not in node_ids:
-                errors.append(f"Pause node '{pause}' not found")
-
-        # Validate entry points
-        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 = OnlineResearchAgent()

.claude/skills/building-agents-construction/examples/online_research_agent/nodes/__init__.py

@@ -1,396 +0,0 @@
-"""Node definitions for Online Research Agent."""
-
-from framework.graph import NodeSpec
-
-# Node 1: Parse Query
-parse_query_node = NodeSpec(
-    id="parse-query",
-    name="Parse Query",
-    description="Analyze the research topic and generate 3-5 diverse search queries to cover different aspects",
-    node_type="llm_generate",
-    input_keys=["topic"],
-    output_keys=["search_queries", "research_focus", "key_aspects"],
-    output_schema={
-        "research_focus": {
-            "type": "string",
-            "required": True,
-            "description": "Brief statement of what we're researching",
-        },
-        "key_aspects": {
-            "type": "array",
-            "required": True,
-            "description": "List of 3-5 key aspects to investigate",
-        },
-        "search_queries": {
-            "type": "array",
-            "required": True,
-            "description": "List of 3-5 search queries",
-        },
-    },
-    system_prompt="""\
-You are a research query strategist. Given a research topic, analyze it and generate search queries.
-
-Your task:
-1. Understand the core research question
-2. Identify 3-5 key aspects to investigate
-3. Generate 3-5 diverse search queries that will find comprehensive information
-
-CRITICAL: Return ONLY raw JSON. NO markdown, NO code blocks.
-
-Return this JSON structure:
-{
-  "research_focus": "Brief statement of what we're researching",
-  "key_aspects": ["aspect1", "aspect2", "aspect3"],
-  "search_queries": [
-    "query 1 - broad overview",
-    "query 2 - specific angle",
-    "query 3 - recent developments",
-    "query 4 - expert opinions",
-    "query 5 - data/statistics"
-  ]
-}
-""",
-    tools=[],
-    max_retries=3,
-)
-
-# Node 2: Search Sources
-search_sources_node = NodeSpec(
-    id="search-sources",
-    name="Search Sources",
-    description="Execute web searches using the generated queries to find 15+ source URLs",
-    node_type="llm_tool_use",
-    input_keys=["search_queries", "research_focus"],
-    output_keys=["source_urls", "search_results_summary"],
-    output_schema={
-        "source_urls": {
-            "type": "array",
-            "required": True,
-            "description": "List of source URLs found",
-        },
-        "search_results_summary": {
-            "type": "string",
-            "required": True,
-            "description": "Brief summary of what was found",
-        },
-    },
-    system_prompt="""\
-You are a research assistant executing web searches. Use the web_search tool to find sources.
-
-Your task:
-1. Execute each search query using web_search tool
-2. Collect URLs from search results
-3. Aim for 15+ diverse sources
-
-After searching, return JSON with found sources:
-{
-  "source_urls": ["url1", "url2", ...],
-  "search_results_summary": "Brief summary of what was found"
-}
-""",
-    tools=["web_search"],
-    max_retries=3,
-)
-
-# Node 3: Fetch Content
-fetch_content_node = NodeSpec(
-    id="fetch-content",
-    name="Fetch Content",
-    description="Fetch and extract content from the discovered source URLs",
-    node_type="llm_tool_use",
-    input_keys=["source_urls", "research_focus"],
-    output_keys=["fetched_sources", "fetch_errors"],
-    output_schema={
-        "fetched_sources": {
-            "type": "array",
-            "required": True,
-            "description": "List of fetched source objects with url, title, content",
-        },
-        "fetch_errors": {
-            "type": "array",
-            "required": True,
-            "description": "List of URLs that failed to fetch",
-        },
-    },
-    system_prompt="""\
-You are a content fetcher. Use web_scrape tool to retrieve content from URLs.
-
-Your task:
-1. Fetch content from each source URL using web_scrape tool
-2. Extract the main content relevant to the research focus
-3. Track any URLs that failed to fetch
-
-After fetching, return JSON:
-{
-  "fetched_sources": [
-    {"url": "...", "title": "...", "content": "extracted text..."},
-    ...
-  ],
-  "fetch_errors": ["url that failed", ...]
-}
-""",
-    tools=["web_scrape"],
-    max_retries=3,
-)
-
-# Node 4: Evaluate Sources
-evaluate_sources_node = NodeSpec(
-    id="evaluate-sources",
-    name="Evaluate Sources",
-    description="Score sources for relevance and quality, filter to top 10",
-    node_type="llm_generate",
-    input_keys=["fetched_sources", "research_focus", "key_aspects"],
-    output_keys=["ranked_sources", "source_analysis"],
-    output_schema={
-        "ranked_sources": {
-            "type": "array",
-            "required": True,
-            "description": "List of ranked sources with scores",
-        },
-        "source_analysis": {
-            "type": "string",
-            "required": True,
-            "description": "Overview of source quality and coverage",
-        },
-    },
-    system_prompt="""\
-You are a source evaluator. Assess each source for quality and relevance.
-
-Scoring criteria:
-- Relevance to research focus (1-10)
-- Source credibility (1-10)
-- Information depth (1-10)
-- Recency if relevant (1-10)
-
-Your task:
-1. Score each source
-2. Rank by combined score
-3. Select top 10 sources
-4. Note what each source uniquely contributes
-
-Return JSON:
-{
-  "ranked_sources": [
-    {"url": "...", "title": "...", "content": "...", "score": 8.5, "unique_value": "..."},
-    ...
-  ],
-  "source_analysis": "Overview of source quality and coverage"
-}
-""",
-    tools=[],
-    max_retries=3,
-)
-
-# Node 5: Synthesize Findings
-synthesize_findings_node = NodeSpec(
-    id="synthesize-findings",
-    name="Synthesize Findings",
-    description="Extract key facts from sources and identify common themes",
-    node_type="llm_generate",
-    input_keys=["ranked_sources", "research_focus", "key_aspects"],
-    output_keys=["key_findings", "themes", "source_citations"],
-    output_schema={
-        "key_findings": {
-            "type": "array",
-            "required": True,
-            "description": "List of key findings with sources and confidence",
-        },
-        "themes": {
-            "type": "array",
-            "required": True,
-            "description": "List of themes with descriptions and supporting sources",
-        },
-        "source_citations": {
-            "type": "object",
-            "required": True,
-            "description": "Map of facts to supporting URLs",
-        },
-    },
-    system_prompt="""\
-You are a research synthesizer. Analyze multiple sources to extract insights.
-
-Your task:
-1. Identify key facts from each source
-2. Find common themes across sources
-3. Note contradictions or debates
-4. Build a citation map (fact -> source URL)
-
-Return JSON:
-{
-  "key_findings": [
-    {"finding": "...", "sources": ["url1", "url2"], "confidence": "high/medium/low"},
-    ...
-  ],
-  "themes": [
-    {"theme": "...", "description": "...", "supporting_sources": ["url1", ...]},
-    ...
-  ],
-  "source_citations": {
-    "fact or claim": ["supporting url1", "url2"],
-    ...
-  }
-}
-""",
-    tools=[],
-    max_retries=3,
-)
-
-# Node 6: Write Report
-write_report_node = NodeSpec(
-    id="write-report",
-    name="Write Report",
-    description="Generate a narrative report with proper citations",
-    node_type="llm_generate",
-    input_keys=[
-        "key_findings",
-        "themes",
-        "source_citations",
-        "research_focus",
-        "ranked_sources",
-    ],
-    output_keys=["report_content", "references"],
-    output_schema={
-        "report_content": {
-            "type": "string",
-            "required": True,
-            "description": "Full markdown report text with citations",
-        },
-        "references": {
-            "type": "array",
-            "required": True,
-            "description": "List of reference objects with number, url, title",
-        },
-    },
-    system_prompt="""\
-You are a research report writer. Create a well-structured narrative report.
-
-Report structure:
-1. Executive Summary (2-3 paragraphs)
-2. Introduction (context and scope)
-3. Key Findings (organized by theme)
-4. Analysis (synthesis and implications)
-5. Conclusion
-6. References (numbered list of all sources)
-
-Citation format: Use numbered citations like [1], [2] that correspond to the References section.
-
-IMPORTANT:
-- Every factual claim MUST have a citation
-- Write in clear, professional prose
-- Be objective and balanced
-- Highlight areas of consensus and debate
-
-Return JSON:
-{
-  "report_content": "Full markdown report text with citations...",
-  "references": [
-    {"number": 1, "url": "...", "title": "..."},
-    ...
-  ]
-}
-""",
-    tools=[],
-    max_retries=3,
-)
-
-# Node 7: Quality Check
-quality_check_node = NodeSpec(
-    id="quality-check",
-    name="Quality Check",
-    description="Verify all claims have citations and report is coherent",
-    node_type="llm_generate",
-    input_keys=["report_content", "references", "source_citations"],
-    output_keys=["quality_score", "issues", "final_report"],
-    output_schema={
-        "quality_score": {
-            "type": "number",
-            "required": True,
-            "description": "Quality score 0-1",
-        },
-        "issues": {
-            "type": "array",
-            "required": True,
-            "description": "List of issues found and fixed",
-        },
-        "final_report": {
-            "type": "string",
-            "required": True,
-            "description": "Corrected full report",
-        },
-    },
-    system_prompt="""\
-You are a quality assurance reviewer. Check the research report for issues.
-
-Check for:
-1. Uncited claims (factual statements without [n] citation)
-2. Broken citations (references to non-existent numbers)
-3. Coherence (logical flow between sections)
-4. Completeness (all key aspects covered)
-5. Accuracy (claims match source content)
-
-If issues found, fix them in the final report.
-
-Return JSON:
-{
-  "quality_score": 0.95,
-  "issues": [
-    {"type": "uncited_claim", "location": "paragraph 3", "fixed": true},
-    ...
-  ],
-  "final_report": "Corrected full report with all issues fixed..."
-}
-""",
-    tools=[],
-    max_retries=3,
-)
-
-# Node 8: Save Report
-save_report_node = NodeSpec(
-    id="save-report",
-    name="Save Report",
-    description="Write the final report to a local markdown file",
-    node_type="llm_tool_use",
-    input_keys=["final_report", "references", "research_focus"],
-    output_keys=["file_path", "save_status"],
-    output_schema={
-        "file_path": {
-            "type": "string",
-            "required": True,
-            "description": "Path where report was saved",
-        },
-        "save_status": {
-            "type": "string",
-            "required": True,
-            "description": "Status of save operation",
-        },
-    },
-    system_prompt="""\
-You are a file manager. Save the research report to disk.
-
-Your task:
-1. Generate a filename from the research focus (slugified, with date)
-2. Use the write_to_file tool to save the report as markdown
-3. Save to the ./research_reports/ directory
-
-Filename format: research_YYYY-MM-DD_topic-slug.md
-
-Return JSON:
-{
-  "file_path": "research_reports/research_2026-01-23_topic-name.md",
-  "save_status": "success"
-}
-""",
-    tools=["write_to_file"],
-    max_retries=3,
-)
-
-__all__ = [
-    "parse_query_node",
-    "search_sources_node",
-    "fetch_content_node",
-    "evaluate_sources_node",
-    "synthesize_findings_node",
-    "write_report_node",
-    "quality_check_node",
-    "save_report_node",
-]

.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

@@ -1,8 +1,8 @@
 {
   "hive-tools": {
     "transport": "stdio",
-    "command": "python",
-    "args": ["mcp_server.py", "--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

@@ -1,10 +1,10 @@
 ---
-name: setup-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 encrypted credential store at ~/.hive/credentials.
+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: "2.1"
+  version: "2.3"
   type: utility
 ---
 
@@ -31,47 +31,50 @@ Determine which agent needs credentials. The user will either:
 
 Locate the agent's directory under `exports/{agent_name}/`.
 
-### Step 2: Detect Required Credentials
+### Step 2: Detect Missing Credentials
 
-Read the agent's configuration to determine which tools and node types it uses:
+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.
 
-```python
-from core.framework.runner import AgentRunner
-
-runner = AgentRunner.load("exports/{agent_name}")
-validation = runner.validate()
-
-# validation.missing_credentials contains env var names
-# validation.warnings contains detailed messages with help URLs
+```
+check_missing_credentials(agent_path="exports/{agent_name}")
 ```
 
-Alternatively, check the credential store directly:
+The tool returns a JSON response:
 
-```python
-from core.framework.credentials import CredentialStore
-
-# Use encrypted storage (default: ~/.hive/credentials)
-store = CredentialStore.with_encrypted_storage()
-
-# Check what's available
-available = store.list_credentials()
-print(f"Available credentials: {available}")
-
-# Check if specific credential exists
-if store.is_available("hubspot"):
-    print("HubSpot credential found")
-else:
-    print("HubSpot credential missing")
+```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
+}
 ```
 
-To see all known credential specs (for help URLs and setup instructions):
+**If `ready` is true (nothing missing):** Report all credentials as configured and skip Steps 3-5. Example:
 
-```python
-from aden_tools.credentials import CREDENTIAL_SPECS
-
-for name, spec in CREDENTIAL_SPECS.items():
-    print(f"{name}: env_var={spec.env_var}, aden={spec.aden_supported}")
 ```
+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
 
@@ -104,8 +107,8 @@ Present the available options using AskUserQuestion:
 ```
 Choose how to configure HUBSPOT_ACCESS_TOKEN:
 
-  1) Aden Authorization Server (Recommended)
-     Secure OAuth2 flow via integration.adenhq.com
+  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
 
@@ -114,7 +117,7 @@ Choose how to configure HUBSPOT_ACCESS_TOKEN:
      - Requires creating a HubSpot Private App
      - Full control over scopes and permissions
 
-  3) Custom Credential Store (Advanced)
+  3) Local Credential Setup (Advanced)
      Programmatic configuration for CI/CD
      - For automated deployments
      - Requires manual API calls
@@ -122,7 +125,29 @@ Choose how to configure HUBSPOT_ACCESS_TOKEN:
 
 ### Step 4: Execute Auth Flow Based on User Choice
 
-#### Option 1: Aden Authorization Server
+#### 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.).
 
@@ -147,7 +172,7 @@ If not set, guide user to get one from Aden (this is where they do OAuth):
 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://integration.adenhq.com/setup
+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.).")
@@ -174,7 +199,7 @@ shell_type = detect_shell()  # 'bash', 'zsh', or 'unknown'
 success, config_path = add_env_var_to_shell_config(
     "ADEN_API_KEY",
     user_provided_key,
-    comment="Aden authorization server API key"
+    comment="Aden Platform (OAuth) API key"
 )
 
 if success:
@@ -183,6 +208,12 @@ if success:
     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
@@ -224,7 +255,7 @@ 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://integration.adenhq.com to connect HubSpot, then try again.")
+    print("Please visit https://hive.adenhq.com to connect HubSpot, then try again.")
 ```
 
 For more control over the sync process:
@@ -313,7 +344,7 @@ if not result.valid:
     # 2. Continue anyway (not recommended)
 ```
 
-**4.2d. Store in Encrypted Credential Store**
+**4.2d. Store in Local Encrypted Store**
 
 ```python
 from core.framework.credentials import CredentialStore, CredentialObject, CredentialKey
@@ -340,7 +371,7 @@ store.save_credential(cred)
 export HUBSPOT_ACCESS_TOKEN="the-value"
 ```
 
-#### Option 3: Custom Credential Store (Advanced)
+#### Option 3: Local Credential Setup (Advanced)
 
 For programmatic/CI/CD setups.
 
@@ -394,24 +425,38 @@ config_path.write_text(json.dumps(config, indent=2))
 
 ### Step 6: Verify All Credentials
 
-Run validation again to confirm everything is set:
+Use the `verify_credentials` MCP tool to confirm everything is properly configured:
 
-```python
-runner = AgentRunner.load("exports/{agent_name}")
-validation = runner.validate()
-assert not validation.missing_credentials, "Still missing credentials!"
+```
+verify_credentials(agent_path="exports/{agent_name}")
 ```
 
-Report the result to the user.
+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                    |
-| -------------- | --------------------------------------- | --------------------------------- |
-| `hubspot`      | `GET /crm/v3/objects/contacts?limit=1`  | Bearer token validity, CRM scopes |
-| `brave_search` | `GET /res/v1/web/search?q=test&count=1` | API key validity                  |
+| 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
@@ -424,12 +469,17 @@ result: HealthCheckResult = check_credential_health("hubspot", token_value)
 
 ## Encryption Key (HIVE_CREDENTIAL_KEY)
 
-The encrypted credential store requires `HIVE_CREDENTIAL_KEY` to encrypt/decrypt credentials.
+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` or a secrets manager)
+- The user MUST persist this key (e.g., in `~/.bashrc`/`~/.zshrc` or a secrets manager)
 - Without this key, stored credentials cannot be decrypted
-- This is the ONLY secret that should live in `~/.bashrc` or environment config
+
+**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:
 
@@ -442,8 +492,9 @@ If `HIVE_CREDENTIAL_KEY` is not set:
 - **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 encrypted credential store (`~/.hive/credentials`) for persistence
+- **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
@@ -456,7 +507,8 @@ All credential specs are defined in `tools/src/aden_tools/credentials/`:
 | ----------------- | ------------- | --------------------------------------------- | -------------- |
 | `llm.py`          | LLM Providers | `anthropic`                                   | No             |
 | `search.py`       | Search Tools  | `brave_search`, `google_search`, `google_cse` | No             |
-| `integrations.py` | Integrations  | `hubspot`                                     | Yes            |
+| `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.
@@ -507,66 +559,82 @@ token = store.get_key("hubspot", "access_token")
 ## Example Session
 
 ```
-User: /setup-credentials for my hubspot-agent
+User: /hive-credentials for my research-agent
 
-Agent: Let me check what credentials your hubspot-agent needs.
+Agent: Let me check what credentials your research-agent needs.
 
-[Runs validation, finds ANTHROPIC_API_KEY and HUBSPOT_ACCESS_TOKEN missing]
+[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: Your hubspot-agent requires 2 credentials:
+Agent: 2 of 4 required credentials are already configured. Only Google Custom
+Search needs setup (2 values).
 
-  1. ANTHROPIC_API_KEY - Anthropic API key for LLM calls
-  2. HUBSPOT_ACCESS_TOKEN - HubSpot access token
+--- Setting up Google Custom Search (google_search + google_cse) ---
 
-Let's set these up one at a time.
+This requires two values that work together.
 
---- Setting up ANTHROPIC_API_KEY ---
+[Checks HIVE_CREDENTIAL_KEY before storing]
+$ printenv HIVE_CREDENTIAL_KEY > /dev/null 2>&1 && echo "set" || echo "not set"
+set
 
-This credential only supports direct API key entry.
+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
 
-[Shows instructions for getting Anthropic API key]
-[AskUserQuestion: "Please provide your Anthropic API key:"]
-[User provides key]
-[Stores in credential store, exports to env]
-
---- Setting up HUBSPOT_ACCESS_TOKEN ---
-
-[AskUserQuestion with 3 options]
-
-Choose how to configure HUBSPOT_ACCESS_TOKEN:
-  1) Aden Authorization Server (Recommended)
-  2) Direct API Key
-  3) Custom Credential Store (Advanced)
-
-User: 1 (Aden)
-
-Agent: Great! Let me check if you have an Aden API key configured...
-
-[Checks for ADEN_API_KEY, not found]
-[Opens browser to integration.adenhq.com/setup]
-
-Agent: I've opened Aden's setup page. Please:
-  1. Sign in or create an account
-  2. Connect your HubSpot account (OAuth happens on Aden's site)
-  3. Copy the API key shown after setup
-
-[AskUserQuestion: "Please provide your Aden API key:"]
+[AskUserQuestion: "Please provide your Google API key:"]
 [User provides key]
 
-Agent: Would you like me to save this to your shell config (~/.zshrc) for future sessions?
+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)
 
-[User approves]
-[Saves to ~/.zshrc and ~/.hive/configuration.json]
+[AskUserQuestion: "Please provide your Google CSE ID:"]
+[User provides ID]
 
-Agent: Let me sync your credentials from Aden...
+[Runs health check with both values - GET /customsearch/v1?q=test&num=1 → 200 OK]
+[Stores both in local encrypted store, exports to env]
 
-[Syncs credentials from Aden server - OAuth already done on Aden's side]
-[Runs health check]
+✓ Google Custom Search credentials valid
 
-Agent: HubSpot credentials validated successfully!
+[Calls verify_credentials(agent_path="exports/research-agent")]
+→ Returns: ready: true, missing_credentials: []
 
 All credentials are now configured:
-  - ANTHROPIC_API_KEY: Stored in encrypted credential store
-  - HUBSPOT_ACCESS_TOKEN: Synced from Aden (OAuth completed on Aden)
-  - Validation passed - your agent is ready to run!
+  ✓ 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

@@ -1,32 +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
-    - setup-credentials
+    - 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** → `/building-agents-core` (optional)
-2. **Build Structure** → `/building-agents-construction`
-3. **Optimize Design** → `/building-agents-patterns` (optional)
-4. **Setup Credentials** → `/setup-credentials` (if agent uses tools requiring API keys)
-5. **Test & Validate** → `/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
 
@@ -37,25 +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
-"Set up API keys for my agent" → setup-credentials
-"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
@@ -63,12 +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
 
@@ -76,9 +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
 
@@ -106,7 +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)
 
@@ -120,7 +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)
@@ -140,53 +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
@@ -249,9 +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
 ```
@@ -260,19 +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
 ```
@@ -281,58 +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
@@ -342,13 +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"
@@ -356,9 +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:
@@ -368,7 +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/
@@ -417,10 +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
 
@@ -428,36 +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/examples/testing-youtube-agent.md

@@ -1,351 +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: Get Constraint Test Guidelines
-
-During the Goal stage (or early Eval), get test guidelines for constraints:
-
-```python
-result = generate_constraint_tests(
-    goal_id="youtube-research",
-    goal_json='<goal JSON above>',
-    agent_path="exports/youtube-research"
-)
-```
-
-**The result contains guidelines (not generated tests):**
-- `output_file`: Where to write tests
-- `file_header`: Imports and fixtures to use
-- `test_template`: Format for test functions
-- `constraints_formatted`: The constraints to test
-- `test_guidelines`: Rules for writing tests
-
-## Step 3: Write Constraint Tests
-
-Using the guidelines, write tests directly with the Write tool:
-
-```python
-# Write constraint tests using the provided file_header and guidelines
-Write(
-    file_path="exports/youtube-research/tests/test_constraints.py",
-    content='''
-"""Constraint tests for youtube-research agent."""
-
-import os
-import pytest
-from exports.youtube_research import default_agent
-
-
-pytestmark = pytest.mark.skipif(
-    not os.environ.get("ANTHROPIC_API_KEY") and not os.environ.get("MOCK_MODE"),
-    reason="API key required for real testing."
-)
-
-
-@pytest.mark.asyncio
-async def test_constraint_api_limits_respected():
-    """Verify API rate limits are not exceeded."""
-    import time
-    mock_mode = bool(os.environ.get("MOCK_MODE"))
-
-    for i in range(10):
-        result = await default_agent.run({"topic": f"test_{i}"}, mock_mode=mock_mode)
-        time.sleep(0.1)
-
-    # Should complete without rate limit errors
-    assert "rate limit" not in str(result).lower()
-
-
-@pytest.mark.asyncio
-async def test_constraint_content_safety_filter():
-    """Verify inappropriate content is filtered."""
-    mock_mode = bool(os.environ.get("MOCK_MODE"))
-    result = await default_agent.run({"topic": "general topic"}, mock_mode=mock_mode)
-
-    for video in result.videos:
-        assert video.safe_for_work is True
-        assert video.age_restricted is False
-'''
-)
-```
-
-## Step 4: Get Success Criteria Test Guidelines
-
-After the agent is built, get success criteria test guidelines:
-
-```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",
-    agent_path="exports/youtube-research"
-)
-```
-
-## Step 5: Write Success Criteria Tests
-
-Using the guidelines, write success criteria tests:
-
-```python
-Write(
-    file_path="exports/youtube-research/tests/test_success_criteria.py",
-    content='''
-"""Success criteria tests for youtube-research agent."""
-
-import os
-import pytest
-from exports.youtube_research import default_agent
-
-
-pytestmark = pytest.mark.skipif(
-    not os.environ.get("ANTHROPIC_API_KEY") and not os.environ.get("MOCK_MODE"),
-    reason="API key required for real testing."
-)
-
-
-@pytest.mark.asyncio
-async def test_find_videos_happy_path():
-    """Test finding videos for a common topic."""
-    mock_mode = bool(os.environ.get("MOCK_MODE"))
-    result = await default_agent.run({"topic": "machine learning"}, mock_mode=mock_mode)
-
-    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)
-
-
-@pytest.mark.asyncio
-async def test_find_videos_minimum_boundary():
-    """Test at minimum threshold (3 videos)."""
-    mock_mode = bool(os.environ.get("MOCK_MODE"))
-    result = await default_agent.run({"topic": "niche topic xyz"}, mock_mode=mock_mode)
-
-    assert len(result.videos) >= 3
-
-
-@pytest.mark.asyncio
-async def test_relevance_score_threshold():
-    """Test relevance scoring meets threshold."""
-    mock_mode = bool(os.environ.get("MOCK_MODE"))
-    result = await default_agent.run({"topic": "python programming"}, mock_mode=mock_mode)
-
-    for video in result.videos:
-        assert video.relevance_score > 0.8
-
-
-@pytest.mark.asyncio
-async def test_find_videos_no_results_graceful():
-    """Test graceful handling of no results."""
-    mock_mode = bool(os.environ.get("MOCK_MODE"))
-    result = await default_agent.run({"topic": "xyznonexistent123"}, mock_mode=mock_mode)
-
-    # Should not crash, return empty or message
-    assert result.videos == [] or result.message
-'''
-)
-```
-
-## Step 6: Run All Tests
-
-Execute all 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_name="test_find_videos_no_results_graceful",
-    agent_path="exports/youtube-research"
-)
-```
-
-**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. **Got guidelines** for constraint tests during Goal stage
-2. **Wrote** constraint tests using Write tool
-3. **Got guidelines** for success criteria tests during Eval stage
-4. **Wrote** success criteria tests using Write tool
-5. **Ran** tests in parallel
-6. **Debugged** the one failure
-7. **Categorized** as IMPLEMENTATION_ERROR
-8. **Fixed** the agent (not the goal)
-9. **Re-ran** Eval only (didn't restart full flow)
-10. **Passed** all tests
-
-The agent is now validated and ready for production use.

.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/skills/agent-workflow

@@ -1 +0,0 @@
-../../.claude/skills/agent-workflow

.cursor/skills/building-agents-construction

@@ -1 +0,0 @@
-../../.claude/skills/building-agents-construction

.cursor/skills/building-agents-core

@@ -1 +0,0 @@
-../../.claude/skills/building-agents-core

.cursor/skills/building-agents-patterns

@@ -1 +0,0 @@
-../../.claude/skills/building-agents-patterns

.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

.cursor/skills/testing-agent

@@ -1 +0,0 @@
-../../.claude/skills/testing-agent

.github/workflows/ci.yml

@@ -55,14 +55,10 @@ jobs:
       - name: Install uv
         uses: astral-sh/setup-uv@v4
 
-      - name: Install dependencies
+      - name: Install dependencies and run tests
         run: |
           cd core
           uv sync
-
-      - name: Run tests
-        run: |
-          cd core
           uv run pytest tests/ -v
 
   test-tools:
@@ -83,8 +79,7 @@ jobs:
         run: |
           cd tools
           uv sync --extra dev
-          uv pip install --python .venv/bin/python -e ../core
-          uv run --extra dev pytest tests/ -v
+          uv run pytest tests/ -v
 
   validate:
     name: Validate Agent Exports
@@ -127,7 +122,7 @@ jobs:
           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

.gitignore

@@ -54,7 +54,6 @@ __pycache__/
 *.egg-info/
 .eggs/
 *.egg
-uv.lock
 
 # Generated runtime data
 core/data/
@@ -69,4 +68,12 @@ exports/*
 
 .agent-builder-sessions/*
 
-.venv
+.claude/settings.local.json
+
+.venv
+
+docs/github-issues/*
+core/tests/*dumps/*
+
+screenshots/*
+

.mcp.json

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

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.6
+    rev: v0.15.0
     hooks:
       - id: ruff
         name: ruff lint (core)

CHANGELOG.md

@@ -1,41 +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.
 
+```bash
+# Launch the Coder directly
+hive code
 
-### Fixed
-- tools: Fixed web_scrape tool attempting to parse non-HTML content (PDF, JSON) as HTML (#487)
+# Or escalate from any running agent (TUI)
+Ctrl+E  # or /coder in chat
+```
 
-### Security
-- N/A
+The Coder ships with:
 
-## [0.1.0] - 2025-01-13
+- **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()`
 
-### Added
-- Initial release
+### Multi-Graph Agent Runtime
 
-[Unreleased]: https://github.com/adenhq/hive/compare/v0.1.0...HEAD
-[0.1.0]: https://github.com/adenhq/hive/releases/tag/v0.1.0
+`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

@@ -1,10 +1,10 @@
 # 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. 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. 
+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
 
@@ -35,15 +35,22 @@ You may submit PRs without prior assignment for:
 
 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 checks and tests:
+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)
    ```
-6. Commit your changes following our commit conventions
-7. Push to your fork and submit a Pull Request
+8. Commit your changes following our commit conventions
+9. Push to your fork and submit a Pull Request
 
 ## Development Setup
 
@@ -92,8 +99,7 @@ docs(readme): update installation instructions
 2. Update documentation if needed
 3. Add tests for new functionality
 4. Ensure `make check` and `make test` pass
-5. Update the CHANGELOG.md if applicable
-6. Request review from maintainers
+5. Request review from maintainers
 
 ### PR Title Format
 
@@ -120,12 +126,14 @@ 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
 
 > **Note:** When testing agents in `exports/`, always set PYTHONPATH:
 >
 > ```bash
-> PYTHONPATH=core:exports python -m agent_name test
+> PYTHONPATH=exports uv run python -m agent_name test
 > ```
 
 ```bash
@@ -138,8 +146,11 @@ 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.
@@ -152,4 +163,4 @@ By submitting a Pull Request, you agree that your contributions will be licensed
 
 Feel free to open an issue for questions or join our [Discord community](https://discord.com/invite/MXE49hrKDk).
 
-Thank you for contributing!
+Thank you for contributing!

Makefile

@@ -4,9 +4,11 @@ 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 (with auto-fix)
+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 .
@@ -19,8 +21,8 @@ check: ## Run all checks without modifying files (CI-safe)
 	cd tools && ruff format --check .
 
 test: ## Run all tests
-	cd core && python -m pytest tests/ -v
+	cd core && uv run python -m pytest tests/ -v
 
 install-hooks: ## Install pre-commit hooks
-	pip install pre-commit
+	uv pip install pre-commit
 	pre-commit install

PR.md

@@ -1,51 +0,0 @@
-## Summary
-- **Added HubSpot integration** — new HubSpot MCP tool with search, get, create, and update operations for contacts, companies, and deals. Includes OAuth2 provider for HubSpot credentials and credential store adapter for the tools layer.
-- **Replaced web_scrape tool with Playwright + stealth** — swapped httpx/BeautifulSoup for a headless Chromium browser using `playwright` (async API) and `playwright-stealth`, enabling JS-rendered page scraping and bot detection evasion
-- **Added empty response retry logic** — LLM provider now detects empty responses (e.g. Gemini returning 200 with no content on rate limit) and retries with exponential backoff, preventing hallucinated output from the cleanup LLM
-- **Added context-aware input compaction** — LLM nodes now estimate input token count before calling the model and progressively truncate the largest values if they exceed the context window budget
-- **Increased rate limit retries to 10** with verbose `[retry]` and `[compaction]` logging that includes model name, finish reason, and attempt count
-- **Updated setup scripts** — `scripts/setup-python.sh` now installs Playwright Chromium browser automatically for web scraping support
-- **Interactive quickstart onboarding** — `quickstart.sh` rewritten as bee-themed interactive wizard that detects existing API keys (including Claude Code subscription), lets user pick ONE default LLM provider, and saves configuration to `~/.hive/configuration.json`
-- **Fixed lint errors** across `hubspot_tool.py` (line length) and `agent_builder_server.py` (unused variable)
-
-## Changed files
-
-### HubSpot Integration
-- `tools/src/aden_tools/tools/hubspot_tool/` — New MCP tool: contacts, companies, and deals CRUD
-- `tools/src/aden_tools/tools/__init__.py` — Registered HubSpot tools
-- `tools/src/aden_tools/credentials/integrations.py` — HubSpot credential integration
-- `tools/src/aden_tools/credentials/__init__.py` — Updated credential exports
-- `core/framework/credentials/oauth2/hubspot_provider.py` — HubSpot OAuth2 provider
-- `core/framework/credentials/oauth2/__init__.py` — Registered HubSpot OAuth2 provider
-- `core/framework/runner/runner.py` — Updated runner for credential support
-
-### Web Scrape Rewrite
-- `tools/src/aden_tools/tools/web_scrape_tool/web_scrape_tool.py` — Playwright async rewrite
-- `tools/src/aden_tools/tools/web_scrape_tool/README.md` — Updated docs
-- `tools/pyproject.toml` — Added `playwright`, `playwright-stealth` deps
-- `tools/Dockerfile` — Added `playwright install chromium --with-deps`
-- `scripts/setup-python.sh` — Added Playwright Chromium browser install step
-
-### LLM Reliability
-- `core/framework/llm/litellm.py` — Empty response retry + max retries 10 + verbose logging
-- `core/framework/graph/node.py` — Input compaction via `_compact_inputs()`, `_estimate_tokens()`, `_get_context_limit()`
-
-### Quickstart & Setup
-- `quickstart.sh` — Interactive bee-themed onboarding wizard with single provider selection
-- `~/.hive/configuration.json` — New user config file for default LLM provider/model
-
-### Fixes
-- `core/framework/mcp/agent_builder_server.py` — Removed unused variable
-- `tools/src/aden_tools/tools/hubspot_tool/hubspot_tool.py` — Fixed E501 line length violations
-
-## Test plan
-- [ ] Run `make lint` — passes clean
-- [ ] Run `./quickstart.sh` and verify interactive flow works, config saved to `~/.hive/configuration.json`
-- [ ] Run `./scripts/setup-python.sh` and verify Playwright Chromium installs
-- [ ] Run `pytest tests/tools/test_web_scrape_tool.py -v`
-- [ ] Run agent against a JS-heavy site and verify `web_scrape` returns rendered content
-- [ ] Set `HUBSPOT_ACCESS_TOKEN` and verify HubSpot tool CRUD operations work
-- [ ] Trigger rate limit and verify `[retry]` logs appear with correct attempt counts
-- [ ] Run agent with large inputs and verify `[compaction]` logs show truncation
-
-🤖 Generated with [Claude Code](https://claude.com/claude-code)

README.md

@@ -1,5 +1,5 @@
 <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">
@@ -13,16 +13,19 @@
   <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)
-[![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>
@@ -30,15 +33,16 @@
   <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.
 
+https://github.com/user-attachments/assets/846c0cc7-ffd6-47fa-b4b7-495494857a55
+
 ## Who Is Hive For?
 
 Hive is designed for developers and teams who want to build **production-grade AI agents** without manually wiring complex workflows.
@@ -58,43 +62,36 @@ Hive may not be the best fit if you’re only experimenting with simple agent ch
 Use Hive when you need:
 
 - Long-running, autonomous agents
-- Multi-agent coordination
+- Strong guardrails, process, and controls
 - Continuous improvement based on failures
-- Strong monitoring, safety, and budget controls
+- Multi-agent coordination
 - A framework that evolves with your goals
 
-
-## What is Aden
-
-<p align="center">
-  <img width="100%" alt="Aden Architecture" src="docs/assets/aden-architecture-diagram.jpg" />
-</p>
-
-Aden is a platform for building, deploying, operating, and adapting AI agents:
-
-- **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
-
 ## 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
-- Claude Code or Cursor for utilizing agent skills
+- 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
@@ -105,45 +102,89 @@ cd hive
 ```
 
 This sets up:
+
 - **framework** - Core agent runtime and graph executor (in `core/.venv`)
 - **aden_tools** - MCP tools for agent capabilities (in `tools/.venv`)
-- All required Python dependencies
+- **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
 # Build an agent using Claude Code
-claude> /building-agents-construction
+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
 
-### Cursor IDE Support
+### Codex CLI
 
-Skills are also available in Cursor. To enable:
+Hive includes native support for [OpenAI Codex CLI](https://github.com/openai/codex) (v0.101.0+).
 
-1. Open Command Palette (`Cmd+Shift+P` / `Ctrl+Shift+P`)
-2. Run `MCP: Enable` to enable MCP servers
-3. Restart Cursor to load the MCP servers from `.cursor/mcp.json`
-4. Type `/` in Agent chat and search for skills (e.g., `/building-agents-construction`)
+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
-- **Adaptiveness** - Framework captures failures, calibrates according to the objectives, and evolves 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
 
 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.
@@ -180,161 +221,187 @@ flowchart LR
     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    | Outcome-evaluation and adaptiveness               |
+| 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. **Adaptiveness** → 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
 
-## Run pre-built Agents (Coming Soon)
+## Run Agents
 
-### Run a sample agent
-Aden Hive provides a list of featured agents that you can use and build on top of.
-
-### Run an agent shared by others
-Put the agent in `exports/` and run `PYTHONPATH=core:exports python -m your_agent_name run --input '{...}'`
-
-
-For building and running goal-driven agents with the framework:
+The `hive` CLI is the primary interface for running agents.
 
 ```bash
-# One-time setup
-./quickstart.sh
+# Browse and run agents interactively (Recommended)
+hive tui
 
-# This sets up:
-# - framework package (core runtime)
-# - aden_tools package (MCP tools)
-# - All Python 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-construction
+# 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/README.md) - System design and structure
 
 ## Roadmap
 
-Aden Hive Agent Framework aims to help developers build outcome-oriented, self-adaptive agents. See [ROADMAP.md](ROADMAP.md) for details.
+Aden Hive Agent Framework aims to help developers build outcome-oriented, self-adaptive agents. See [roadmap.md](docs/roadmap.md) for details.
 
 ```mermaid
-flowchart TD
-subgraph Foundation
-    direction LR
-    subgraph arch["Architecture"]
-        a1["Node-Based Architecture"]:::done
-        a2["Python SDK"]:::done
-        a3["LLM Integration"]:::done
-        a4["Communication Protocol"]:::done
-    end
-    subgraph ca["Coding Agent"]
-        b1["Goal Creation Session"]:::done
-        b2["Worker Agent Creation"]
-        b3["MCP Tools"]:::done
-    end
-    subgraph wa["Worker Agent"]
-        c1["Human-in-the-Loop"]:::done
-        c2["Callback Handlers"]:::done
-        c3["Intervention Points"]:::done
-        c4["Streaming Interface"]
-    end
-    subgraph cred["Credentials"]
-        d1["Setup Process"]:::done
-        d2["Pluggable Sources"]:::done
-        d3["Enterprise Secrets"]
-        d4["Integration Tools"]:::done
-    end
-    subgraph tools["Tools"]
-        e1["File Use"]:::done
-        e2["Memory STM/LTM"]:::done
-        e3["Web Search/Scraper"]:::done
-        e4["CSV/PDF"]:::done
-        e5["Excel/Email"]
-    end
-    subgraph core["Core"]
-        f1["Eval System"]
-        f2["Pydantic Validation"]:::done
-        f3["Documentation"]:::done
-        f4["Adaptiveness"]
-        f5["Sample Agents"]
-    end
-end
+flowchart TB
+    %% Main Entity
+    User([User])
 
-subgraph Expansion
-    direction LR
-    subgraph intel["Intelligence"]
-        g1["Guardrails"]
-        g2["Streaming Mode"]
-        g3["Image Generation"]
-        g4["Semantic Search"]
+    %% =========================================
+    %% EXTERNAL EVENT SOURCES
+    %% =========================================
+    subgraph ExtEventSource [External Event Source]
+        E_Sch["Schedulers"]
+        E_WH["Webhook"]
+        E_SSE["SSE"]
     end
-    subgraph mem["Memory Iteration"]
-        h1["Message Model & Sessions"]
-        h2["Storage Migration"]
-        h3["Context Building"]
-        h4["Proactive Compaction"]
-        h5["Token Tracking"]
-    end
-    subgraph evt["Event System"]
-        i1["Event Bus for Nodes"]
-    end
-    subgraph cas["Coding Agent Support"]
-        j1["Claude Code"]
-        j2["Cursor"]
-        j3["Opencode"]
-        j4["Antigravity"]
-    end
-    subgraph plat["Platform"]
-        k1["JavaScript/TypeScript SDK"]
-        k2["Custom Tool Integrator"]
-        k3["Windows Support"]
-    end
-    subgraph dep["Deployment"]
-        l1["Self-Hosted"]
-        l2["Cloud Services"]
-        l3["CI/CD Pipeline"]
-    end
-    subgraph tmpl["Templates"]
-        m1["Sales Agent"]
-        m2["Marketing Agent"]
-        m3["Analytics Agent"]
-        m4["Training Agent"]
-        m5["Smart Form Agent"]
-    end
-end
 
-classDef done fill:#9e9e9e,color:#fff,stroke:#757575
+    %% =========================================
+    %% 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. 
+**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
@@ -367,10 +434,6 @@ This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENS
 
 ## Frequently Asked Questions (FAQ)
 
-**Q: Does Hive depend on LangChain or other agent frameworks?**
-
-No. Hive 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.
-
 **Q: What LLM providers does Hive support?**
 
 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.
@@ -381,37 +444,25 @@ Yes! Hive supports local models through LiteLLM. Simply use the model name forma
 
 **Q: What makes Hive different from other agent frameworks?**
 
-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, and redeploys. This self-improving loop is unique to Aden.
+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: Is Hive open-source?**
 
 Yes, Hive is fully open-source under the Apache License 2.0. We actively encourage community contributions and collaboration.
 
-**Q: Does Hive collect data from users?**
-
-Hive 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.
-
-**Q: What deployment options does Hive support?**
-
-Hive supports self-hosted deployments via Python packages. See the [Environment Setup Guide](ENVIRONMENT_SETUP.md) for installation instructions. Cloud deployment options and Kubernetes-ready configurations are on the roadmap.
-
 **Q: Can Hive handle complex, production-scale use cases?**
 
 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 Hive support human-in-the-loop workflows?**
 
-Yes, Hive 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 Hive provide?**
-
-Hive 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 MCP tools for agent execution, including file operations, web search, data processing, and more.
+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 programming languages does Hive support?**
 
 The Hive framework is built in Python. A JavaScript/TypeScript SDK is on the roadmap.
 
-**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.
 
@@ -421,7 +472,7 @@ Hive provides granular budget controls including spending limits, throttles, and
 
 **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?**
 
@@ -435,10 +486,6 @@ Aden's adaptation loop begins working from the first execution. When an agent fa
 
 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.
 
-**Q: Does Aden offer enterprise support?**
-
-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.
-
 ---
 
 <p align="center">

ROADMAP.md

@@ -1,299 +0,0 @@
-# Product Roadmap
-
-Aden Agent Framework aims to help developers build outcome oriented, self-adaptive agents. Please find our roadmap here
-
-```mermaid
-flowchart TD
-subgraph Foundation
-    direction LR
-    subgraph arch["Architecture"]
-        a1["Node-Based Architecture"]:::done
-        a2["Python SDK"]:::done
-        a3["LLM Integration"]:::done
-        a4["Communication Protocol"]:::done
-    end
-    subgraph ca["Coding Agent"]
-        b1["Goal Creation Session"]:::done
-        b2["Worker Agent Creation"]
-        b3["MCP Tools"]:::done
-    end
-    subgraph wa["Worker Agent"]
-        c1["Human-in-the-Loop"]:::done
-        c2["Callback Handlers"]:::done
-        c3["Intervention Points"]:::done
-        c4["Streaming Interface"]
-    end
-    subgraph cred["Credentials"]
-        d1["Setup Process"]:::done
-        d2["Pluggable Sources"]:::done
-        d3["Enterprise Secrets"]
-        d4["Integration Tools"]:::done
-    end
-    subgraph tools["Tools"]
-        e1["File Use"]:::done
-        e2["Memory STM/LTM"]:::done
-        e3["Web Search/Scraper"]:::done
-        e4["CSV/PDF"]:::done
-        e5["Excel/Email"]
-    end
-    subgraph core["Core"]
-        f1["Eval System"]
-        f2["Pydantic Validation"]:::done
-        f3["Documentation"]:::done
-        f4["Adaptiveness"]
-        f5["Sample Agents"]
-    end
-end
-
-subgraph Expansion
-    direction LR
-    subgraph intel["Intelligence"]
-        g1["Guardrails"]
-        g2["Streaming Mode"]
-        g3["Image Generation"]
-        g4["Semantic Search"]
-    end
-    subgraph mem["Memory Iteration"]
-        h1["Message Model & Sessions"]
-        h2["Storage Migration"]
-        h3["Context Building"]
-        h4["Proactive Compaction"]
-        h5["Token Tracking"]
-    end
-    subgraph evt["Event System"]
-        i1["Event Bus for Nodes"]
-    end
-    subgraph cas["Coding Agent Support"]
-        j1["Claude Code"]
-        j2["Cursor"]
-        j3["Opencode"]
-        j4["Antigravity"]
-    end
-    subgraph plat["Platform"]
-        k1["JavaScript/TypeScript SDK"]
-        k2["Custom Tool Integrator"]
-        k3["Windows Support"]
-    end
-    subgraph dep["Deployment"]
-        l1["Self-Hosted"]
-        l2["Cloud Services"]
-        l3["CI/CD Pipeline"]
-    end
-    subgraph tmpl["Templates"]
-        m1["Sales Agent"]
-        m2["Marketing Agent"]
-        m3["Analytics Agent"]
-        m4["Training Agent"]
-        m5["Smart Form Agent"]
-    end
-end
-
-classDef done fill:#9e9e9e,color:#fff,stroke:#757575
-```
-
----
-
-## Phase 1: Foundation
-
-### Backbone Architecture
-- [ ] **Node-Based Architecture (Agent as a node)**
-    - [x] Object schema definition
-    - [x] Node wrapper SDK
-    - [x] Shared memory access
-    - [ ] Default monitoring hooks
-    - [x] Tool access layer
-    - [x] LLM integration layer (Natively supports all mainstream LLMs through LiteLLM)
-        - [x] Anthropic
-        - [x] OpenAI
-        - [x] Google
-- [x] **Communication protocol between nodes**
-- [x] **[Coding Agent] Goal Creation Session** (separate from coding session)
-    - [x] Instruction back and forth
-    - [x] Goal Object schema definition
-    - [x] Being able to generate the test cases
-    - [x] 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
-    - [x] 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
-    - [x] Request State Management
-
-### Credential Management
-- [x] **Credentials Setup Process**
-    - [x] Install Credential MCP
-- [x] **Pluggable Credential Sources**
-    - [x] **Abstraction & Local Sources**
-        - [x] Introduce `CredentialSource` base class
-        - [x] Refactor existing logic into `EnvVarSource`
-        - [x] Implementation of Source Priority Chain mechanism
-        - [ ] Foundation unit tests
-    - [ ] **Enterprise Secret Managers**
-        - [x] `VaultSource` (HashiCorp Vault)
-        - [ ] `AWSSecretsSource` (AWS Secrets Manager)
-        - [ ] `AzureKeyVaultSource` (Azure Key Vault)
-        - [ ] Management of optional provider dependencies
-    - [ ] **Advanced Features**
-        - [x] Credential expiration and auto-refresh
-        - [ ] Audit logging for compliance/tracking
-        - [ ] Per-environment configuration support
-    - [ ] **Documentation & DX**
-        - [ ] Comprehensive source documentation
-        - [ ] Example configurations for all providers
-    - [x] **Integration as tools coverage**
-        - [x] Gsuite Tools
-        - [x] Social Media
-            - [ ] Twitter(X)
-            - [x] Github
-            - [ ] Instagram
-        - [ ] SAAS
-            - [ ] Hubspot
-            - [ ] Slack
-            - [ ] Teams
-            - [ ] Zoom
-            - [ ] Stripe
-            - [ ] Salesforce
-
-> [!IMPORTANT]
-> **Community Contribution Wanted**: We appreciate help from the community to expand the "Integration as tools" capability. Leave an issue of the integration you want to support via Hive!
-
-### Essential Tools
-- [x] **File Use Tool Kit**
-- [X] **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)
-    - [x] Web Search
-    - [x] Web Scraper
-    - [x] CSV tools
-    - [x] PDF tools
-    - [ ] Excel tools
-    - [ ] Email Tools
-    - [ ] 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
-- [x] Natively Support data validation of LLMs output with Pydantic
-
-### Developer Experience
-- [ ] **MVP Features**
-    - [ ] Debugging mode
-    - [ ] CLI tools for memory management
-    - [ ] CLI tools for credential management
-- [ ] **MVP Resources & Documentation**
-    - [x] Quick start guide
-    - [x] Goal creation guide
-    - [x] Agent creation guide
-    - [x] GitHub Page setup
-    - [x] README with examples
-    - [x] Contributing guidelines
-    - [ ] Introduction Video
-
-### Adaptiveness
-- [ ] Runtime data feedback loop
-- [ ] Instant Developer Feedback for improvement
-
-### 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
-- [ ] Image Generation support
-- [ ] Take end user input Image and flatfile understand capability
-
-### Event-loop For Nodes (Opencode-style)
-- [ ] **Event bus**
-
-### Memory System Iteration
-- [ ] **Message Model & Session Management**
-    - [ ] Introduce `Message` class with structured content types
-    - [ ] Implement `Session` classes for conversation state
-- [ ] **Storage Migration**
-    - [ ] Implement granular per-message file persistence (`/message/[agentID]/...`)
-    - [ ] Migrate from monolithic run storage
-- [ ] **Context Building & Conversation Loop**
-    - [ ] Implement `Message.stream(sessionID)`
-    - [ ] Update `LLMNode.execute()` for full context building
-    - [ ] Implement `Message.toModelMessages()` conversion
-- [ ] **Proactive Compaction**
-    - [ ] Implement proactive overflow detection
-    - [ ] Develop backward-scanning pruning strategy (e.g., clearing old tool outputs)
-- [ ] **Enhanced Token Tracking**
-    - [ ] Extend `LLMResponse` to track reasoning and cache tokens
-    - [ ] Integrate granular token metrics into compaction logic
-
-### Coding Agent Support
-- [ ] Claude Code
-- [ ] Cursor
-- [ ] Opencode
-- [ ] Antigravity
-
-### 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)
-- [ ] Workder agent 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)
-
-### Cross-Platform
-- [ ] JavaScript / TypeScript Version SDK
-- [ ] Better windows support

core/.gitignore

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

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
@@ -136,16 +136,16 @@ Tests are generated using MCP tools (`generate_constraint_tests`, `generate_succ
 
 ```bash
 # Run tests against an agent
-python -m framework test-run <agent_path> --goal <goal_id> --parallel 4
+uv run python -m framework test-run <agent_path> --goal <goal_id> --parallel 4
 
 # Debug failed tests
-python -m framework test-debug <agent_path> <test_name>
+uv run python -m framework test-debug <agent_path> <test_name>
 
 # List tests for a goal
-python -m framework test-list <goal_id>
+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

@@ -4,34 +4,45 @@ 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 'function' nodes to define logic in pure Python, making it perfect
-for understanding the core runtime loop:
+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:
-    PYTHONPATH=core python core/examples/manual_agent.py
+    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 (Pure Python Functions)
-def greet(name: str) -> str:
+# 1. Define Node Logic (Custom NodeProtocol implementations)
+class GreeterNode(NodeProtocol):
     """Generate a simple greeting."""
-    return f"Hello, {name}!"
+
+    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})
 
 
-def uppercase(greeting: str) -> str:
+class UppercaserNode(NodeProtocol):
     """Convert text to uppercase."""
-    return greeting.upper()
+
+    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...")
+    print("Setting up Manual Agent...")
 
     # 2. Define the Goal
     # Every agent needs a goal with success criteria
@@ -55,8 +66,7 @@ async def main():
         id="greeter",
         name="Greeter",
         description="Generates a simple greeting",
-        node_type="function",
-        function="greet",  # Matches the registered function name
+        node_type="event_loop",
         input_keys=["name"],
         output_keys=["greeting"],
     )
@@ -65,8 +75,7 @@ async def main():
         id="uppercaser",
         name="Uppercaser",
         description="Converts greeting to uppercase",
-        node_type="function",
-        function="uppercase",
+        node_type="event_loop",
         input_keys=["greeting"],
         output_keys=["final_greeting"],
     )
@@ -98,23 +107,23 @@ async def main():
     runtime = Runtime(storage_path=Path("./agent_logs"))
     executor = GraphExecutor(runtime=runtime)
 
-    # 7. Register Function Implementations
-    # Connect string names in NodeSpecs to actual Python functions
-    executor.register_function("greeter", greet)
-    executor.register_function("uppercaser", uppercase)
+    # 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'...")
+    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("\n✅ Success!")
+        print("\nSuccess!")
         print(f"Path taken: {' -> '.join(result.path)}")
         print(f"Final output: {result.output.get('final_greeting')}")
     else:
-        print(f"\n❌ Failed: {result.error}")
+        print(f"\nFailed: {result.error}")
 
 
 if __name__ == "__main__":

core/examples/mcp_integration_example.py

@@ -122,7 +122,7 @@ async def example_4_custom_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",
         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"],
@@ -133,7 +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"],

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/agents/__init__.py

@@ -0,0 +1,13 @@
+"""Framework-provided agents."""
+
+from pathlib import Path
+
+FRAMEWORK_AGENTS_DIR = Path(__file__).parent
+
+
+def list_framework_agents() -> list[Path]:
+    """List all framework agent directories."""
+    return sorted(
+        [p for p in FRAMEWORK_AGENTS_DIR.iterdir() if p.is_dir() and (p / "agent.py").exists()],
+        key=lambda p: p.name,
+    )

core/framework/agents/credential_tester/__init__.py

@@ -0,0 +1,55 @@
+"""
+Credential Tester — verify credentials (Aden OAuth + local API keys) via live API calls.
+
+Interactive agent that lists all testable accounts, lets the user pick one,
+loads the provider's tools, and runs a chat session to test the credential.
+"""
+
+from .agent import (
+    CredentialTesterAgent,
+    _list_aden_accounts,
+    _list_env_fallback_accounts,
+    _list_local_accounts,
+    configure_for_account,
+    conversation_mode,
+    edges,
+    entry_node,
+    entry_points,
+    get_tools_for_provider,
+    goal,
+    identity_prompt,
+    list_connected_accounts,
+    loop_config,
+    nodes,
+    pause_nodes,
+    requires_account_selection,
+    skip_credential_validation,
+    terminal_nodes,
+)
+from .config import default_config
+
+__version__ = "1.0.0"
+
+__all__ = [
+    "CredentialTesterAgent",
+    "configure_for_account",
+    "conversation_mode",
+    "default_config",
+    "edges",
+    "entry_node",
+    "entry_points",
+    "get_tools_for_provider",
+    "goal",
+    "identity_prompt",
+    "list_connected_accounts",
+    "loop_config",
+    "nodes",
+    "pause_nodes",
+    "requires_account_selection",
+    "skip_credential_validation",
+    "terminal_nodes",
+    # Internal list helpers (exposed for testing)
+    "_list_aden_accounts",
+    "_list_local_accounts",
+    "_list_env_fallback_accounts",
+]

core/framework/agents/credential_tester/__main__.py

@@ -0,0 +1,148 @@
+"""CLI entry point for Credential Tester agent."""
+
+import asyncio
+import logging
+import sys
+
+import click
+
+from .agent import CredentialTesterAgent
+
+
+def setup_logging(verbose=False, debug=False):
+    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)
+
+
+def pick_account(agent: CredentialTesterAgent) -> dict | None:
+    """Interactive account picker. Returns selected account dict or None."""
+    accounts = agent.list_accounts()
+    if not accounts:
+        click.echo("No connected accounts found.")
+        click.echo("Set ADEN_API_KEY and connect accounts at https://app.adenhq.com")
+        return None
+
+    click.echo("\nConnected accounts:\n")
+    for i, acct in enumerate(accounts, 1):
+        provider = acct.get("provider", "?")
+        alias = acct.get("alias", "?")
+        identity = acct.get("identity", {})
+        detail_parts = [f"{k}: {v}" for k, v in identity.items() if v]
+        detail = f"  ({', '.join(detail_parts)})" if detail_parts else ""
+        click.echo(f"  {i}. {provider}/{alias}{detail}")
+
+    click.echo()
+    while True:
+        choice = click.prompt("Pick an account to test", type=int, default=1)
+        if 1 <= choice <= len(accounts):
+            return accounts[choice - 1]
+        click.echo(f"Invalid choice. Enter 1-{len(accounts)}.")
+
+
+@click.group()
+@click.version_option(version="1.0.0")
+def cli():
+    """Credential Tester — verify synced credentials via live API calls."""
+    pass
+
+
+@cli.command()
+@click.option("--verbose", "-v", is_flag=True)
+@click.option("--debug", is_flag=True)
+def tui(verbose, debug):
+    """Launch TUI to test a credential interactively."""
+    setup_logging(verbose=verbose, debug=debug)
+
+    try:
+        from framework.tui.app import AdenTUI
+    except ImportError:
+        click.echo("TUI requires 'textual'. Install with: pip install textual")
+        sys.exit(1)
+
+    agent = CredentialTesterAgent()
+    account = pick_account(agent)
+    if account is None:
+        sys.exit(1)
+
+    agent.select_account(account)
+    provider = account.get("provider", "?")
+    alias = account.get("alias", "?")
+    click.echo(f"\nTesting {provider}/{alias}...\n")
+
+    async def run_tui():
+        agent._setup()
+        runtime = agent._agent_runtime
+        await runtime.start()
+        try:
+            app = AdenTUI(runtime)
+            await app.run_async()
+        finally:
+            await runtime.stop()
+
+    asyncio.run(run_tui())
+
+
+@cli.command()
+@click.option("--verbose", "-v", is_flag=True)
+@click.option("--debug", is_flag=True)
+def shell(verbose, debug):
+    """Interactive CLI session to test a credential."""
+    setup_logging(verbose=verbose, debug=debug)
+    asyncio.run(_interactive_shell(verbose))
+
+
+async def _interactive_shell(verbose=False):
+    agent = CredentialTesterAgent()
+    account = pick_account(agent)
+    if account is None:
+        return
+
+    agent.select_account(account)
+    provider = account.get("provider", "?")
+    alias = account.get("alias", "?")
+
+    click.echo(f"\nTesting {provider}/{alias}")
+    click.echo("Type your requests or 'quit' to exit.\n")
+
+    await agent.start()
+
+    try:
+        result = await agent._agent_runtime.trigger_and_wait(
+            entry_point_id="start",
+            input_data={},
+        )
+        if result:
+            click.echo(f"\nSession ended: {'success' if result.success else result.error}")
+    except KeyboardInterrupt:
+        click.echo("\nGoodbye!")
+    finally:
+        await agent.stop()
+
+
+@cli.command(name="list")
+def list_accounts():
+    """List all connected accounts."""
+    agent = CredentialTesterAgent()
+    accounts = agent.list_accounts()
+
+    if not accounts:
+        click.echo("No connected accounts found.")
+        return
+
+    click.echo("\nConnected accounts:\n")
+    for acct in accounts:
+        provider = acct.get("provider", "?")
+        alias = acct.get("alias", "?")
+        identity = acct.get("identity", {})
+        detail_parts = [f"{k}: {v}" for k, v in identity.items() if v]
+        detail = f"  ({', '.join(detail_parts)})" if detail_parts else ""
+        click.echo(f"  {provider}/{alias}{detail}")
+
+
+if __name__ == "__main__":
+    cli()

core/framework/agents/credential_tester/agent.py

@@ -0,0 +1,621 @@
+"""Credential Tester agent — verify credentials via live API calls.
+
+Supports both Aden OAuth2-synced accounts AND locally-stored API key accounts.
+Aden accounts use account="alias" routing; local accounts inject the key into
+the session environment so tools read it without an account= parameter.
+
+When loaded via AgentRunner.load() (TUI picker, ``hive run``), the module-level
+``nodes`` / ``edges`` variables provide a static graph.  The TUI detects
+``requires_account_selection`` and shows an account picker *before* starting
+the agent.  ``configure_for_account()`` then scopes the node's tools to the
+selected provider.
+
+When used directly (``CredentialTesterAgent``), the graph is built dynamically
+after the user picks an account programmatically.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import TYPE_CHECKING
+
+from framework.graph import Goal, NodeSpec, SuccessCriterion
+from framework.graph.checkpoint_config import CheckpointConfig
+from framework.graph.edge import GraphSpec
+from framework.graph.executor import ExecutionResult
+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
+from .nodes import build_tester_node
+
+if TYPE_CHECKING:
+    from framework.runner import AgentRunner
+
+# ---------------------------------------------------------------------------
+# Goal
+# ---------------------------------------------------------------------------
+
+goal = Goal(
+    id="credential-tester",
+    name="Credential Tester",
+    description="Verify that a credential can make real API calls.",
+    success_criteria=[
+        SuccessCriterion(
+            id="api-call-success",
+            description="At least one API call succeeds using the credential",
+            metric="api_call_success",
+            target="true",
+            weight=1.0,
+        ),
+    ],
+    constraints=[],
+)
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+
+def get_tools_for_provider(provider_name: str) -> list[str]:
+    """Collect tool names for a credential by credential_id OR credential_group.
+
+    Matches on both ``credential_id`` (e.g. "google" → Gmail tools) and
+    ``credential_group`` (e.g. "google_custom_search" → all google search tools).
+    """
+    from aden_tools.credentials import CREDENTIAL_SPECS
+
+    tools: list[str] = []
+    for spec in CREDENTIAL_SPECS.values():
+        if spec.credential_id == provider_name or spec.credential_group == provider_name:
+            tools.extend(spec.tools)
+    return sorted(set(tools))
+
+
+def _list_aden_accounts() -> list[dict]:
+    """List active accounts from the Aden platform (requires ADEN_API_KEY)."""
+    import os
+
+    api_key = os.environ.get("ADEN_API_KEY")
+    if not api_key:
+        return []
+
+    try:
+        from framework.credentials.aden.client import AdenClientConfig, AdenCredentialClient
+
+        client = AdenCredentialClient(
+            AdenClientConfig(
+                base_url=os.environ.get("ADEN_API_URL", "https://api.adenhq.com"),
+            )
+        )
+        try:
+            integrations = client.list_integrations()
+        finally:
+            client.close()
+
+        return [
+            {
+                "provider": c.provider,
+                "alias": c.alias,
+                "identity": {"email": c.email} if c.email else {},
+                "integration_id": c.integration_id,
+                "source": "aden",
+            }
+            for c in integrations
+            if c.status == "active"
+        ]
+    except Exception:
+        return []
+
+
+def _list_local_accounts() -> list[dict]:
+    """List named local API key accounts from LocalCredentialRegistry."""
+    try:
+        from framework.credentials.local.registry import LocalCredentialRegistry
+
+        return [
+            info.to_account_dict() for info in LocalCredentialRegistry.default().list_accounts()
+        ]
+    except Exception:
+        return []
+
+
+def _list_env_fallback_accounts() -> list[dict]:
+    """Surface configured-but-unregistered credentials as testable entries.
+
+    Detects credentials available via env vars OR stored in the encrypted
+    store in the old flat format (e.g. ``brave_search`` with no alias).
+    These are users who haven't yet run ``save_account()`` but have a working key.
+    Shows with alias="default" and status="unknown".
+    """
+    import os
+
+    from aden_tools.credentials import CREDENTIAL_SPECS
+
+    # Collect IDs in encrypted store (includes old flat entries like "brave_search")
+    try:
+        from framework.credentials.storage import EncryptedFileStorage
+
+        encrypted_ids: set[str] = set(EncryptedFileStorage().list_all())
+    except Exception:
+        encrypted_ids = set()
+
+    def _is_configured(cred_name: str, spec) -> bool:
+        # 1. Env var present
+        if os.environ.get(spec.env_var):
+            return True
+        # 2. Old flat encrypted entry (no slash — new entries have {x}/{y})
+        if cred_name in encrypted_ids:
+            return True
+        return False
+
+    seen_groups: set[str] = set()
+    accounts: list[dict] = []
+
+    for cred_name, spec in CREDENTIAL_SPECS.items():
+        if not spec.direct_api_key_supported or not spec.tools:
+            continue
+
+        if spec.credential_group:
+            if spec.credential_group in seen_groups:
+                continue
+            group_available = all(
+                _is_configured(n, s)
+                for n, s in CREDENTIAL_SPECS.items()
+                if s.credential_group == spec.credential_group
+            )
+            if not group_available:
+                continue
+            seen_groups.add(spec.credential_group)
+            provider = spec.credential_group
+        else:
+            if not _is_configured(cred_name, spec):
+                continue
+            provider = cred_name
+
+        accounts.append(
+            {
+                "provider": provider,
+                "alias": "default",
+                "identity": {},
+                "integration_id": None,
+                "source": "local",
+                "status": "unknown",
+            }
+        )
+
+    return accounts
+
+
+def list_connected_accounts() -> list[dict]:
+    """List all testable accounts: Aden-synced + named local + env-var fallbacks."""
+    aden = _list_aden_accounts()
+    local = _list_local_accounts()
+
+    # Show env-var fallbacks only for credentials not already in the named registry
+    local_providers = {a["provider"] for a in local}
+    env_fallbacks = [
+        a for a in _list_env_fallback_accounts() if a["provider"] not in local_providers
+    ]
+
+    return aden + local + env_fallbacks
+
+
+# ---------------------------------------------------------------------------
+# Module-level hooks (read by AgentRunner.load / TUI)
+# ---------------------------------------------------------------------------
+
+skip_credential_validation = True
+"""Don't validate credentials at load time — we don't know which provider yet."""
+
+requires_account_selection = True
+"""Signal TUI to show account picker before starting the agent."""
+
+
+def configure_for_account(runner: AgentRunner, account: dict) -> None:
+    """Scope the tester node's tools to the selected provider.
+
+    Handles both Aden accounts (account= routing) and local accounts
+    (session-level env var injection, no account= parameter in prompt).
+    """
+    provider = account["provider"]
+    source = account.get("source", "aden")
+    alias = account.get("alias", "unknown")
+    identity = account.get("identity", {})
+    tools = get_tools_for_provider(provider)
+
+    if source == "aden":
+        tools.append("get_account_info")
+        email = identity.get("email", "")
+        detail = f" (email: {email})" if email else ""
+        _configure_aden_node(runner, provider, alias, detail, tools)
+    else:
+        status = account.get("status", "unknown")
+        _activate_local_account(provider, alias)
+        _configure_local_node(runner, provider, alias, identity, tools, status)
+
+
+def _activate_local_account(credential_id: str, alias: str) -> None:
+    """Inject a named local account's key into the session environment.
+
+    Handles three cases:
+    1. Named account in LocalCredentialRegistry (new format: {credential_id}/{alias})
+    2. Old flat credential in EncryptedFileStorage (id == credential_id, no alias)
+    3. Env var already set — skip injection (nothing to do)
+    """
+    import os
+
+    from aden_tools.credentials import CREDENTIAL_SPECS
+
+    # Collect specs for this credential (handles grouped credentials too)
+    group_specs = [
+        (cred_name, spec)
+        for cred_name, spec in CREDENTIAL_SPECS.items()
+        if spec.credential_group == credential_id
+        or spec.credential_id == credential_id
+        or cred_name == credential_id
+    ]
+    # Deduplicate — credential_id and credential_group may both match the same spec
+    seen_env_vars: set[str] = set()
+
+    try:
+        from framework.credentials.local.registry import LocalCredentialRegistry
+        from framework.credentials.storage import EncryptedFileStorage
+
+        registry = LocalCredentialRegistry.default()
+        flat_storage = EncryptedFileStorage()
+
+        for _cred_name, spec in group_specs:
+            if spec.env_var in seen_env_vars:
+                continue
+            # If env var is already set, nothing to do for this one
+            if os.environ.get(spec.env_var):
+                seen_env_vars.add(spec.env_var)
+                continue
+
+            seen_env_vars.add(spec.env_var)
+
+            # Determine key name based on spec
+            key_name = "api_key"
+            if spec.credential_group and "cse" in spec.env_var.lower():
+                key_name = "cse_id"
+
+            key: str | None = None
+
+            # 1. Try named account in registry (new format)
+            if alias != "default":
+                key = registry.get_key(credential_id, alias, key_name)
+            else:
+                # For "default" alias, check registry first, then fall back to flat store
+                key = registry.get_key(credential_id, "default", key_name)
+
+            # 2. Fall back to old flat encrypted entry (id == credential_id, no alias)
+            if key is None:
+                flat_cred = flat_storage.load(credential_id)
+                if flat_cred is not None:
+                    key = flat_cred.get_key(key_name) or flat_cred.get_default_key()
+
+            if key:
+                os.environ[spec.env_var] = key
+    except Exception:
+        pass
+
+
+def _configure_aden_node(
+    runner: AgentRunner,
+    provider: str,
+    alias: str,
+    detail: str,
+    tools: list[str],
+) -> None:
+    for node in runner.graph.nodes:
+        if node.id == "tester":
+            node.tools = sorted(set(tools))
+            node.system_prompt = f"""\
+You are a credential tester for the account: {provider}/{alias}{detail}
+
+# Instructions
+
+1. Suggest a simple read-only API call to verify the credential works \
+(e.g. list messages, list channels, list contacts).
+2. Execute the call when the user agrees.
+3. Report the result: success (with sample data) or failure (with error).
+4. Let the user request additional API calls to further test the credential.
+
+# Account routing
+
+IMPORTANT: Always pass `account="{alias}"` when calling any tool. \
+This routes the API call to the correct credential. Never use the email \
+or any other identifier — always use the alias exactly as shown.
+
+# Rules
+
+- Start with read-only operations (list, get) before write operations.
+- Always confirm with the user before performing write operations.
+- If a call fails, report the exact error — this helps diagnose credential issues.
+- Be concise. No emojis.
+"""
+            break
+
+    runner.intro_message = (
+        f"Testing {provider}/{alias}{detail} — "
+        f"{len(tools)} tools loaded. "
+        "I'll suggest a read-only API call to verify the credential works."
+    )
+
+
+def _configure_local_node(
+    runner: AgentRunner,
+    provider: str,
+    alias: str,
+    identity: dict,
+    tools: list[str],
+    status: str,
+) -> None:
+    identity_parts = [f"{k}: {v}" for k, v in identity.items() if v]
+    detail = f" ({', '.join(identity_parts)})" if identity_parts else ""
+    status_note = " [key not yet validated]" if status == "unknown" else ""
+
+    for node in runner.graph.nodes:
+        if node.id == "tester":
+            node.tools = sorted(set(tools))
+            node.system_prompt = f"""\
+You are a credential tester for the local API key: {provider}/{alias}{detail}{status_note}
+
+# Instructions
+
+1. Suggest a simple test call to verify the credential works \
+(e.g. search for "test", list items, get profile info).
+2. Execute the call when the user agrees.
+3. Report the result: success (with sample data) or failure (with error).
+4. Let the user request additional API calls to further test the credential.
+
+# Rules
+
+- Do NOT pass an `account` parameter — this credential is injected \
+directly into the session environment and tools read it automatically.
+- Start with read-only operations before write operations.
+- Always confirm with the user before performing write operations.
+- If a call fails, report the exact error — this helps diagnose credential issues.
+- Be concise. No emojis.
+"""
+            break
+
+    runner.intro_message = (
+        f"Testing {provider}/{alias}{detail} — "
+        f"{len(tools)} tools loaded. "
+        "I'll suggest a test API call to verify the credential works."
+    )
+
+
+# ---------------------------------------------------------------------------
+# Module-level graph variables (read by AgentRunner.load)
+# ---------------------------------------------------------------------------
+
+nodes = [
+    NodeSpec(
+        id="tester",
+        name="Credential Tester",
+        description=(
+            "Interactive credential testing — lets the user pick an account "
+            "and verify it via API calls."
+        ),
+        node_type="event_loop",
+        client_facing=True,
+        max_node_visits=0,
+        input_keys=[],
+        output_keys=[],
+        tools=["get_account_info"],
+        system_prompt="""\
+You are a credential tester. Your job is to help the user verify that their \
+connected accounts and API keys can make real API calls.
+
+# Startup
+
+1. Call ``get_account_info`` to list the user's connected accounts.
+2. Present the list and ask the user which account to test.
+3. Once they pick one, note the account's **alias** (e.g. "Timothy", "work-slack").
+4. Suggest a simple read-only API call to verify the credential works \
+(e.g. list messages, list channels, list contacts).
+5. Execute the call when the user agrees.
+6. Report the result: success (with sample data) or failure (with error).
+7. Let the user request additional API calls to further test the credential.
+
+# Account routing (Aden accounts only)
+
+IMPORTANT: For Aden-synced accounts, always pass the account's **alias** as the \
+``account`` parameter when calling any tool. For local API key accounts, do NOT \
+pass an account parameter — they are pre-injected into the session.
+
+# Rules
+
+- Start with read-only operations (list, get) before write operations.
+- Always confirm with the user before performing write operations.
+- If a call fails, report the exact error — this helps diagnose credential issues.
+- Be concise. No emojis.
+""",
+    ),
+]
+
+edges = []
+
+entry_node = "tester"
+entry_points = {"start": "tester"}
+pause_nodes = []
+terminal_nodes = []  # Forever-alive: loops until user exits
+
+conversation_mode = "continuous"
+identity_prompt = (
+    "You are a credential tester that verifies connected accounts and API keys "
+    "can make real API calls."
+)
+loop_config = {
+    "max_iterations": 50,
+    "max_tool_calls_per_turn": 10,
+    "max_history_tokens": 32000,
+}
+
+# ---------------------------------------------------------------------------
+# Programmatic agent class (used by __main__.py CLI)
+# ---------------------------------------------------------------------------
+
+
+class CredentialTesterAgent:
+    """Interactive agent that tests a specific credential via API calls.
+
+    Usage:
+        agent = CredentialTesterAgent()
+        accounts = agent.list_accounts()
+        agent.select_account(accounts[0])
+        await agent.start()
+        await agent.stop()
+    """
+
+    def __init__(self, config=None):
+        self.config = config or default_config
+        self._selected_account: dict | None = None
+        self._agent_runtime: AgentRuntime | None = None
+        self._tool_registry: ToolRegistry | None = None
+        self._storage_path: Path | None = None
+
+    def list_accounts(self) -> list[dict]:
+        """List all testable accounts (Aden + local named + env-var fallbacks)."""
+        return list_connected_accounts()
+
+    def select_account(self, account: dict) -> None:
+        """Select an account to test.
+
+        Args:
+            account: Account dict from list_accounts() with
+                     provider, alias, identity, source keys.
+        """
+        self._selected_account = account
+
+    @property
+    def selected_provider(self) -> str:
+        if self._selected_account is None:
+            raise RuntimeError("No account selected. Call select_account() first.")
+        return self._selected_account["provider"]
+
+    @property
+    def selected_alias(self) -> str:
+        if self._selected_account is None:
+            raise RuntimeError("No account selected. Call select_account() first.")
+        return self._selected_account.get("alias", "unknown")
+
+    def _build_graph(self) -> GraphSpec:
+        provider = self.selected_provider
+        alias = self.selected_alias
+        source = self._selected_account.get("source", "aden")
+        identity = self._selected_account.get("identity", {})
+        tools = get_tools_for_provider(provider)
+
+        if source == "local":
+            _activate_local_account(provider, alias)
+        elif source == "aden":
+            tools.append("get_account_info")
+
+        tester_node = build_tester_node(
+            provider=provider,
+            alias=alias,
+            tools=tools,
+            identity=identity,
+            source=source,
+        )
+
+        return GraphSpec(
+            id="credential-tester-graph",
+            goal_id=goal.id,
+            version="1.0.0",
+            entry_node="tester",
+            entry_points={"start": "tester"},
+            terminal_nodes=[],
+            pause_nodes=[],
+            nodes=[tester_node],
+            edges=[],
+            default_model=self.config.model,
+            max_tokens=self.config.max_tokens,
+            loop_config={
+                "max_iterations": 50,
+                "max_tool_calls_per_turn": 10,
+                "max_history_tokens": 32000,
+            },
+            conversation_mode="continuous",
+            identity_prompt=(
+                f"You are testing the {provider}/{alias} credential. "
+                "Help the user verify it works by making real API calls."
+            ),
+        )
+
+    def _setup(self) -> None:
+        if self._selected_account is None:
+            raise RuntimeError("No account selected. Call select_account() first.")
+
+        self._storage_path = Path.home() / ".hive" / "agents" / "credential_tester"
+        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)
+
+        extra_kwargs = getattr(self.config, "extra_kwargs", {}) or {}
+        llm = LiteLLMProvider(
+            model=self.config.model,
+            api_key=self.config.api_key,
+            api_base=self.config.api_base,
+            **extra_kwargs,
+        )
+
+        tool_executor = self._tool_registry.get_executor()
+        tools = list(self._tool_registry.get_tools().values())
+
+        graph = self._build_graph()
+
+        self._agent_runtime = create_agent_runtime(
+            graph=graph,
+            goal=goal,
+            storage_path=self._storage_path,
+            entry_points=[
+                EntryPointSpec(
+                    id="start",
+                    name="Test Credential",
+                    entry_node="tester",
+                    trigger_type="manual",
+                    isolation_level="isolated",
+                ),
+            ],
+            llm=llm,
+            tools=tools,
+            tool_executor=tool_executor,
+            checkpoint_config=CheckpointConfig(enabled=False),
+            graph_id="credential_tester",
+        )
+
+    async def start(self) -> None:
+        """Set up and start the agent runtime."""
+        if self._agent_runtime is None:
+            self._setup()
+        if not self._agent_runtime.is_running:
+            await self._agent_runtime.start()
+
+    async def stop(self) -> None:
+        """Stop the agent runtime."""
+        if self._agent_runtime and self._agent_runtime.is_running:
+            await self._agent_runtime.stop()
+        self._agent_runtime = None
+
+    async def run(self) -> ExecutionResult:
+        """Run the agent (convenience for single execution)."""
+        await self.start()
+        try:
+            result = await self._agent_runtime.trigger_and_wait(
+                entry_point_id="start",
+                input_data={},
+            )
+            return result or ExecutionResult(success=False, error="Execution timeout")
+        finally:
+            await self.stop()

core/framework/agents/credential_tester/config.py

@@ -0,0 +1,19 @@
+"""Runtime configuration for Credential Tester agent."""
+
+from dataclasses import dataclass
+
+from framework.config import RuntimeConfig
+
+
+@dataclass
+class AgentMetadata:
+    name: str = "Credential Tester"
+    version: str = "1.0.0"
+    description: str = (
+        "Test connected accounts by making real API calls. "
+        "Pick an account, verify credentials work, and explore available tools."
+    )
+
+
+metadata = AgentMetadata()
+default_config = RuntimeConfig(temperature=0.3)

core/framework/agents/credential_tester/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 with provider-specific tools"
+  }
+}

core/framework/agents/credential_tester/nodes/__init__.py

@@ -0,0 +1,84 @@
+"""Node definitions for Credential Tester agent."""
+
+from framework.graph import NodeSpec
+
+
+def build_tester_node(
+    provider: str,
+    alias: str,
+    tools: list[str],
+    identity: dict[str, str],
+    source: str = "aden",
+) -> NodeSpec:
+    """Build the tester node dynamically for the selected account.
+
+    Args:
+        provider: Provider / credential name (e.g. "google", "brave_search").
+        alias: User-set alias (e.g. "Timothy", "work").
+        tools: Tool names available for this provider.
+        identity: Identity dict (email, workspace, etc.) for context.
+        source: "aden" or "local" — controls routing instructions in the prompt.
+    """
+    detail_parts = [f"{k}: {v}" for k, v in identity.items() if v]
+    detail = f" ({', '.join(detail_parts)})" if detail_parts else ""
+
+    if source == "aden":
+        routing_section = f"""\
+# Account routing
+
+IMPORTANT: Always pass `account="{alias}"` when calling any tool. \
+This routes the API call to the correct credential. Never use the email \
+or any other identifier — always use the alias exactly as shown.
+"""
+    else:
+        routing_section = """\
+# Credential routing
+
+This is a local API key credential — do NOT pass an `account` parameter. \
+The key is pre-injected into the session environment and tools read it automatically.
+"""
+
+    account_label = "account" if source == "aden" else "local API key"
+
+    return NodeSpec(
+        id="tester",
+        name="Credential Tester",
+        description=(
+            f"Interactive testing node for {provider}/{alias}. "
+            f"Has access to all {provider} tools to verify the credential works."
+        ),
+        node_type="event_loop",
+        client_facing=True,
+        max_node_visits=0,
+        input_keys=[],
+        output_keys=[],
+        tools=tools,
+        system_prompt=f"""\
+You are a credential tester for the {account_label}: {provider}/{alias}{detail}
+
+Your job is to help the user verify that this credential works by making \
+real API calls using the available tools.
+
+{routing_section}
+# Instructions
+
+1. Start by greeting the user and confirming which account you're testing.
+2. Suggest a simple, safe, read-only API call to verify the credential works \
+(e.g. list messages, list channels, list contacts, search for "test").
+3. Execute the call when the user agrees.
+4. Report the result clearly: success (with sample data) or failure (with error).
+5. Let the user request additional API calls to further test the credential.
+
+# Available tools
+
+You have access to {len(tools)} tools for {provider}:
+{chr(10).join(f"- {t}" for t in tools)}
+
+# Rules
+
+- Start with read-only operations (list, get) before write operations (create, update, delete).
+- Always confirm with the user before performing write operations.
+- If a call fails, report the exact error — this helps diagnose credential issues.
+- Be concise. No emojis.
+""",
+    )

core/framework/agents/hive_coder/__init__.py

@@ -0,0 +1,44 @@
+"""
+Hive Coder — Native coding agent that builds Hive agent packages.
+
+Deeply understands the agent framework and produces complete Python packages
+with goals, nodes, edges, system prompts, MCP configuration, and tests
+from natural language specifications.
+"""
+
+from .agent import (
+    HiveCoderAgent,
+    conversation_mode,
+    default_agent,
+    edges,
+    entry_node,
+    entry_points,
+    goal,
+    identity_prompt,
+    loop_config,
+    nodes,
+    pause_nodes,
+    terminal_nodes,
+)
+from .config import AgentMetadata, RuntimeConfig, default_config, metadata
+
+__version__ = "1.0.0"
+
+__all__ = [
+    "HiveCoderAgent",
+    "default_agent",
+    "goal",
+    "nodes",
+    "edges",
+    "entry_node",
+    "entry_points",
+    "pause_nodes",
+    "terminal_nodes",
+    "conversation_mode",
+    "identity_prompt",
+    "loop_config",
+    "RuntimeConfig",
+    "AgentMetadata",
+    "default_config",
+    "metadata",
+]

core/framework/agents/hive_coder/__main__.py

@@ -0,0 +1,223 @@
+"""CLI entry point for Hive Coder agent."""
+
+import asyncio
+import json
+import logging
+import sys
+
+import click
+
+from .agent import HiveCoderAgent, default_agent
+
+
+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():
+    """Hive Coder — Build Hive agent packages from natural language."""
+    pass
+
+
+@cli.command()
+@click.option("--request", "-r", type=str, required=True, help="What agent to build")
+@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(request, mock, quiet, verbose, debug):
+    """Execute agent building from a request."""
+    if not quiet:
+        setup_logging(verbose=verbose, debug=debug)
+
+    context = {"user_request": request}
+
+    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 agent building."""
+    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.execution_stream import EntryPointSpec
+
+    async def run_with_tui():
+        agent = HiveCoderAgent()
+
+        agent._tool_registry = ToolRegistry()
+
+        storage_path = Path.home() / ".hive" / "agents" / "hive_coder"
+        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="Build Agent",
+                    entry_node="coder",
+                    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']) or '(forever-alive)'}")
+
+
+@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 agent building session (CLI, no TUI)."""
+    asyncio.run(_interactive_shell(verbose))
+
+
+async def _interactive_shell(verbose=False):
+    """Async interactive shell."""
+    setup_logging(verbose=verbose)
+
+    click.echo("=== Hive Coder ===")
+    click.echo("Describe the agent you want to build (or 'quit' to exit):\n")
+
+    agent = HiveCoderAgent()
+    await agent.start()
+
+    try:
+        while True:
+            try:
+                request = await asyncio.get_event_loop().run_in_executor(None, input, "Build> ")
+                if request.lower() in ["quit", "exit", "q"]:
+                    click.echo("Goodbye!")
+                    break
+
+                if not request.strip():
+                    continue
+
+                click.echo("\nBuilding agent...\n")
+
+                result = await agent.trigger_and_wait("default", {"user_request": request})
+
+                if result is None:
+                    click.echo("\n[Execution timed out]\n")
+                    continue
+
+                if result.success:
+                    output = result.output or {}
+                    agent_name = output.get("agent_name", "unknown")
+                    validation = output.get("validation_result", "unknown")
+                    click.echo(f"\nAgent '{agent_name}' built. Validation: {validation}\n")
+                else:
+                    click.echo(f"\nBuild 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()

core/framework/agents/hive_coder/agent.py

@@ -0,0 +1,356 @@
+"""Agent graph construction for Hive Coder."""
+
+from pathlib import Path
+
+from framework.graph import Constraint, Goal, SuccessCriterion
+from framework.graph.checkpoint_config import CheckpointConfig
+from framework.graph.edge import GraphSpec
+from framework.graph.executor import ExecutionResult
+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 coder_node, queen_node
+# ticket_receiver is no longer needed — the queen runs as an independent
+# GraphExecutor and receives escalation tickets via inject_event().
+# Keeping the import commented for reference:
+# from .ticket_receiver import TICKET_RECEIVER_ENTRY_POINT
+
+# Goal definition
+goal = Goal(
+    id="agent-builder",
+    name="Hive Agent Builder",
+    description=(
+        "Build complete, validated Hive agent packages from natural language "
+        "specifications. Produces production-ready Python packages with goals, "
+        "nodes, edges, system prompts, MCP configuration, and tests."
+    ),
+    success_criteria=[
+        SuccessCriterion(
+            id="valid-package",
+            description="Generated agent package passes structural validation",
+            metric="validation_pass",
+            target="true",
+            weight=0.30,
+        ),
+        SuccessCriterion(
+            id="complete-files",
+            description=(
+                "All required files generated: agent.py, config.py, "
+                "nodes/__init__.py, __init__.py, __main__.py, mcp_servers.json"
+            ),
+            metric="file_count",
+            target=">=6",
+            weight=0.25,
+        ),
+        SuccessCriterion(
+            id="user-satisfaction",
+            description="User reviews and approves the generated agent",
+            metric="user_approval",
+            target="true",
+            weight=0.25,
+        ),
+        SuccessCriterion(
+            id="framework-compliance",
+            description=(
+                "Generated code follows framework patterns: STEP 1/STEP 2 "
+                "for client-facing, correct imports, entry_points format"
+            ),
+            metric="pattern_compliance",
+            target="100%",
+            weight=0.20,
+        ),
+    ],
+    constraints=[
+        Constraint(
+            id="dynamic-tool-discovery",
+            description=(
+                "Always discover available tools dynamically via "
+                "discover_mcp_tools before referencing tools in agent designs"
+            ),
+            constraint_type="hard",
+            category="correctness",
+        ),
+        Constraint(
+            id="no-fabricated-tools",
+            description="Only reference tools that exist in hive-tools MCP",
+            constraint_type="hard",
+            category="correctness",
+        ),
+        Constraint(
+            id="valid-python",
+            description="All generated Python files must be syntactically correct",
+            constraint_type="hard",
+            category="correctness",
+        ),
+        Constraint(
+            id="self-verification",
+            description="Run validation after writing code; fix errors before presenting",
+            constraint_type="hard",
+            category="quality",
+        ),
+    ],
+)
+
+# Nodes: primary coder node only.  The queen runs as an independent
+# GraphExecutor with queen_node — not as part of this graph.
+nodes = [coder_node]
+
+# No edges needed — single forever-alive event_loop node
+edges = []
+
+# Graph configuration
+entry_node = "coder"
+entry_points = {"start": "coder"}
+pause_nodes = []
+terminal_nodes = []  # Forever-alive: loops until user exits
+
+# No async entry points needed — the queen is now an independent executor,
+# not a secondary graph receiving events via add_graph().
+async_entry_points = []
+
+# Module-level variables read by AgentRunner.load()
+conversation_mode = "continuous"
+identity_prompt = (
+    "You are Hive Coder, the best agent-building coding agent on the planet. "
+    "You deeply understand the Hive agent framework at the source code level "
+    "and produce production-ready agent packages from natural language. "
+    "You can dynamically discover available framework tools, inspect runtime "
+    "sessions and checkpoints from agents you build, and run their test suites. "
+    "You follow coding agent discipline: read before writing, verify "
+    "assumptions by reading actual code, adhere to project conventions, "
+    "self-verify with validation, and fix your own errors. You are concise, "
+    "direct, and technically rigorous. No emojis. No fluff."
+)
+loop_config = {
+    "max_iterations": 100,
+    "max_tool_calls_per_turn": 20,
+    "max_history_tokens": 32000,
+}
+
+
+# ---------------------------------------------------------------------------
+# Queen graph — runs as an independent persistent conversation in the TUI.
+# Loaded by _load_judge_and_queen() in app.py, NOT by AgentRunner.
+# ---------------------------------------------------------------------------
+
+queen_goal = Goal(
+    id="queen-manager",
+    name="Queen Manager",
+    description=(
+        "Manage the worker agent lifecycle and serve as the user's primary "
+        "interactive interface. Triage health escalations from the judge."
+    ),
+    success_criteria=[],
+    constraints=[],
+)
+
+queen_graph = GraphSpec(
+    id="queen-graph",
+    goal_id=queen_goal.id,
+    version="1.0.0",
+    entry_node="queen",
+    entry_points={"start": "queen"},
+    terminal_nodes=[],
+    pause_nodes=[],
+    nodes=[queen_node],
+    edges=[],
+    conversation_mode="continuous",
+    loop_config={
+        "max_iterations": 200,
+        "max_tool_calls_per_turn": 10,
+        "max_history_tokens": 32000,
+    },
+)
+
+
+class HiveCoderAgent:
+    """
+    Hive Coder — builds Hive agent packages from natural language.
+
+    Single-node architecture: the coder runs in a continuous while(true) loop.
+    The queen runs as an independent GraphExecutor (loaded by the TUI via
+    _load_judge_and_queen), not as part of this graph.
+    """
+
+    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.async_entry_points = async_entry_points
+        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="hive-coder-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=loop_config,
+            conversation_mode=conversation_mode,
+            identity_prompt=identity_prompt,
+            async_entry_points=self.async_entry_points,
+        )
+
+    def _setup(self, mock_mode=False) -> None:
+        """Set up the agent runtime."""
+        self._storage_path = Path.home() / ".hive" / "agents" / "hive_coder"
+        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,
+            graph_id="hive_coder",
+        )
+
+    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 = HiveCoderAgent()

core/framework/agents/hive_coder/config.py

@@ -1,4 +1,4 @@
-"""Runtime configuration."""
+"""Runtime configuration for Hive Coder agent."""
 
 import json
 from dataclasses import dataclass, field
@@ -24,7 +24,7 @@ def _load_preferred_model() -> str:
 class RuntimeConfig:
     model: str = field(default_factory=_load_preferred_model)
     temperature: float = 0.7
-    max_tokens: int = 8192
+    max_tokens: int = 40000
     api_key: str | None = None
     api_base: str | None = None
 
@@ -32,12 +32,20 @@ class RuntimeConfig:
 default_config = RuntimeConfig()
 
 
-# Agent metadata
 @dataclass
 class AgentMetadata:
-    name: str = "Online Research Agent"
+    name: str = "Hive Coder"
     version: str = "1.0.0"
-    description: str = "Research any topic by searching multiple sources, synthesizing information, and producing a well-structured narrative report with citations."
+    description: str = (
+        "Native coding agent that builds production-ready Hive agent packages "
+        "from natural language specifications. Deeply understands the agent framework "
+        "and produces complete Python packages with goals, nodes, edges, system prompts, "
+        "MCP configuration, and tests."
+    )
+    intro_message: str = (
+        "I'm Hive Coder — I build Hive agents. Describe what kind of agent "
+        "you want to create and I'll design, implement, and validate it for you."
+    )
 
 
 metadata = AgentMetadata()

core/framework/agents/hive_coder/mcp_servers.json

@@ -0,0 +1,9 @@
+{
+  "coder-tools": {
+    "transport": "stdio",
+    "command": "uv",
+    "args": ["run", "python", "coder_tools_server.py", "--stdio"],
+    "cwd": "../../../../tools",
+    "description": "Unsandboxed file system tools for code generation and validation"
+  }
+}