refactor: rename to dbx-agent-app, add eval bridge

- Rename import path: databricks_agents → dbx_agent_app
- Rename PyPI package: databricks-agent-deploy → dbx-agent-app
- Rename CLI command: databricks-agents → dbx-agent-app
- Add bridge module (dbx_agent_app.bridge.eval) with app_predict_fn()
  for mlflow.genai.evaluate() interop with official databricks-agents
- Update all src/, tests/, examples/, docs/, configs
- 186 tests passing

Author: stuagano

databricks-agents/.github/workflows/test.yml

@@ -42,7 +42,7 @@ jobs:
 
     - name: Run tests with pytest
       run: |
-        pytest tests/ -v --cov=databricks_agents --cov-report=xml --cov-report=term
+        pytest tests/ -v --cov=dbx_agent_app --cov-report=xml --cov-report=term
 
     - name: Upload coverage to Codecov
       uses: codecov/codecov-action@v4

databricks-agents/CLAUDE.md

@@ -1,8 +1,8 @@
-# databricks-agent-deploy
+# dbx-agent-app
 
 ## Project Overview
 
-Agent platform for Databricks Apps. Package name: `databricks-agent-deploy` (PyPI), import as `databricks_agents` (Python).
+Agent platform for Databricks Apps. Package name: `dbx-agent-app` (PyPI), import as `dbx_agent_app` (Python).
 
 Build agents with any framework (official Databricks SDK, LangGraph, CrewAI, plain FastAPI). Deploy the platform to discover, test, trace, and govern all of them.
 
@@ -27,7 +27,7 @@ This is NOT an agent-building SDK. It's the **control plane** for agents in your
 The recommended way to build agents. One decorator gives you `/invocations`, agent card, health, and MCP.
 
 ```python
-from databricks_agents import app_agent, AgentRequest, AgentResponse
+from dbx_agent_app import app_agent, AgentRequest, AgentResponse
 
 @app_agent(name="my_agent", description="Does stuff", capabilities=["search"])
 async def my_agent(request: AgentRequest) -> AgentResponse:
@@ -52,7 +52,7 @@ SDK types that replace `mlflow.types.responses` — no mlflow dependency needed:
 For agents using LangChain, replace `self.prep_msgs_for_llm()` with:
 
 ```python
-from databricks_agents.core.compat import to_langchain_messages
+from dbx_agent_app.core.compat import to_langchain_messages
 messages = to_langchain_messages(request)  # -> List[BaseMessage]
 ```
 
@@ -62,7 +62,7 @@ For agents that want full control over their FastAPI app:
 
 ```python
 from fastapi import FastAPI
-from databricks_agents import add_agent_card, add_mcp_endpoints
+from dbx_agent_app import add_agent_card, add_mcp_endpoints
 
 app = FastAPI()
 
@@ -75,20 +75,20 @@ add_mcp_endpoints(app, tools=[...])  # optional
 
 ## Project Structure
 
-- `src/databricks_agents/core/` — `@app_agent` decorator, wire types, helpers, compat
-- `src/databricks_agents/dashboard/` — **the platform app** (FastAPI + React SPA)
-- `src/databricks_agents/deploy/` — multi-agent deploy orchestration (agents.yaml)
-- `src/databricks_agents/discovery/` — workspace agent scanning
-- `src/databricks_agents/registry/` — Unity Catalog registration
-- `src/databricks_agents/mcp/` — MCP JSON-RPC server
-- `src/databricks_agents/cli.py` — CLI entry point
+- `src/dbx_agent_app/core/` — `@app_agent` decorator, wire types, helpers, compat
+- `src/dbx_agent_app/dashboard/` — **the platform app** (FastAPI + React SPA)
+- `src/dbx_agent_app/deploy/` — multi-agent deploy orchestration (agents.yaml)
+- `src/dbx_agent_app/discovery/` — workspace agent scanning
+- `src/dbx_agent_app/registry/` — Unity Catalog registration
+- `src/dbx_agent_app/mcp/` — MCP JSON-RPC server
+- `src/dbx_agent_app/cli.py` — CLI entry point
 - `examples/` — example agents using helpers + official framework
 - `tests/` — SDK tests
 
 ## Key Conventions
 
 - SDK dependencies stay minimal (FastAPI, uvicorn, pydantic, httpx, databricks-sdk)
-- mlflow is optional (`pip install databricks-agent-deploy[mlflow]`)
+- mlflow is optional (`pip install dbx-agent-app[mlflow]`)
 - The dashboard is the primary product, not a side feature
 - `agents.yaml` defines agent systems (topology, dependencies, wiring)
 - Examples use `@app_agent` decorator (preferred) or plain FastAPI + `add_agent_card()`
@@ -97,9 +97,9 @@ add_mcp_endpoints(app, tools=[...])  # optional
 ## CLI Commands
 
 ```
-databricks-agents deploy     # Deploy agents from agents.yaml
-databricks-agents status     # Show deployment status
-databricks-agents destroy    # Tear down deployed agents
-databricks-agents dashboard  # Launch platform locally (dev)
-databricks-agents platform   # Deploy platform as a Databricks App
+dbx-agent-app deploy     # Deploy agents from agents.yaml
+dbx-agent-app status     # Show deployment status
+dbx-agent-app destroy    # Tear down deployed agents
+dbx-agent-app dashboard  # Launch platform locally (dev)
+dbx-agent-app platform   # Deploy platform as a Databricks App
 ```

databricks-agents/CONTRIBUTING.md

@@ -1,6 +1,6 @@
-# Contributing to databricks-agents
+# Contributing to dbx-agent-app
 
-Thank you for your interest in contributing to databricks-agents! This project is a Databricks Labs initiative to make it easier to build discoverable AI agents on Databricks Apps.
+Thank you for your interest in contributing to dbx-agent-app! This project is a Databricks Labs initiative to make it easier to build discoverable AI agents on Databricks Apps.
 
 ## Development Setup
 

databricks-agents/DEPLOYMENT_GUIDE.md

@@ -12,8 +12,8 @@ This framework is ready for deployment to the [Databricks Labs Sandbox](https://
 ## Repository Structure
 
 ```
-databricks-agents/
-├── src/databricks_agents/        # Core framework
+dbx-agent-app/
+├── src/dbx_agent_app/        # Core framework
 │   ├── core/                      # @app_agent decorator, agent request/response types
 │   ├── discovery/                 # Agent discovery, A2A client
 │   ├── mcp/                       # MCP server, UC Functions
@@ -74,25 +74,25 @@ databricks-agents/
 git clone <current-location>
 
 # Add sandbox as remote
-cd databricks-agents
+cd dbx-agent-app
 git remote add sandbox git@github.com:databrickslabs/sandbox.git
 
 # Create feature branch
-git checkout -b databricks-agents-framework
+git checkout -b dbx-agent-app-framework
 
 # Push to sandbox
-git push sandbox databricks-agents-framework
+git push sandbox dbx-agent-app-framework
 ```
 
 ### 2. Create PR to sandbox/main
 
-**PR Title**: Add databricks-agents framework for building discoverable agents
+**PR Title**: Add dbx-agent-app framework for building discoverable agents
 
 **PR Description**:
 ```markdown
 ## Summary
 
-Adds `databricks-agents`, a lightweight Python framework for building discoverable AI agents on Databricks Apps. This framework makes it trivial to turn any Databricks App into a standards-compliant agent with auto-generated A2A protocol endpoints.
+Adds `dbx-agent-app`, a lightweight Python framework for building discoverable AI agents on Databricks Apps. This framework makes it trivial to turn any Databricks App into a standards-compliant agent with auto-generated A2A protocol endpoints.
 
 ## What It Does
 
@@ -104,18 +104,18 @@ Adds `databricks-agents`, a lightweight Python framework for building discoverab
 
 ## Key Files
 
-- `src/databricks_agents/core/decorator.py` - @app_agent decorator
-- `src/databricks_agents/core/types.py` - AgentRequest, AgentResponse types
-- `src/databricks_agents/discovery/` - Agent discovery and A2A client
-- `src/databricks_agents/registry/` - Unity Catalog integration
-- `src/databricks_agents/mcp/` - MCP server support
+- `src/dbx_agent_app/core/decorator.py` - @app_agent decorator
+- `src/dbx_agent_app/core/types.py` - AgentRequest, AgentResponse types
+- `src/dbx_agent_app/discovery/` - Agent discovery and A2A client
+- `src/dbx_agent_app/registry/` - Unity Catalog integration
+- `src/dbx_agent_app/mcp/` - MCP server support
 - `examples/` - Complete working examples
 - `tests/` - Test suite
 
 ## Example Usage
 
 ```python
-from databricks_agents import app_agent, AgentRequest, AgentResponse
+from dbx_agent_app import app_agent, AgentRequest, AgentResponse
 
 @app_agent(
     name="customer_research",

databricks-agents/FRAMEWORK_OVERVIEW.md

@@ -1,4 +1,4 @@
-# databricks-agents Framework Overview
+# dbx-agent-app Framework Overview
 
 ## What We've Built
 
@@ -21,8 +21,8 @@ This framework treats Databricks Apps as first-class agents, allowing them to:
 ## Framework Structure
 
 ```
-databricks-agents/
-├── src/databricks_agents/
+dbx-agent-app/
+├── src/dbx_agent_app/
 │   ├── core/
 │   │   ├── __init__.py
 │   │   ├── decorator.py            # @app_agent decorator
@@ -62,7 +62,7 @@ Python decorator that transforms an async function into an agent with auto-gener
 
 **Usage:**
 ```python
-from databricks_agents import app_agent, AgentRequest, AgentResponse
+from dbx_agent_app import app_agent, AgentRequest, AgentResponse
 
 @app_agent(
     name="my_agent",
@@ -84,7 +84,7 @@ Discovers agent-enabled apps in your workspace by:
 
 **Usage:**
 ```python
-from databricks_agents.discovery import AgentDiscovery
+from dbx_agent_app.discovery import AgentDiscovery
 
 discovery = AgentDiscovery(profile="my-profile")
 result = await discovery.discover_agents()
@@ -103,7 +103,7 @@ Communicates with agents using A2A protocol:
 
 **Usage:**
 ```python
-from databricks_agents.discovery import A2AClient
+from dbx_agent_app.discovery import A2AClient
 
 async with A2AClient() as client:
     card = await client.fetch_agent_card(agent_url)
@@ -138,7 +138,7 @@ Delegates to Databricks workspace OIDC provider for authentication
 ### Creating an Agent with @app_agent
 ```python
 # examples/customer_research_agent.py
-from databricks_agents import app_agent, AgentRequest, AgentResponse
+from dbx_agent_app import app_agent, AgentRequest, AgentResponse
 
 @app_agent(
     name="customer_research",
@@ -155,7 +155,7 @@ app = customer_research.app
 ```python
 # examples/plain_fastapi_agent.py
 from fastapi import FastAPI
-from databricks_agents import add_agent_card
+from dbx_agent_app import add_agent_card
 
 app = FastAPI()
 
@@ -174,7 +174,7 @@ add_agent_card(
 ### Discovering Agents
 ```python
 # examples/discover_agents.py
-from databricks_agents.discovery import AgentDiscovery
+from dbx_agent_app.discovery import AgentDiscovery
 
 discovery = AgentDiscovery(profile="my-profile")
 result = await discovery.discover_agents()

databricks-agents/README.md

@@ -1,10 +1,10 @@
-# databricks-agents
+# dbx-agent-app
 
 A lightweight Python framework for building discoverable AI agents on Databricks Apps that automatically expose A2A (Agent-to-Agent) protocol endpoints.
 
 ## What It Does
 
-The `databricks-agents` framework makes it trivial to turn a Databricks App into a discoverable, standards-compliant agent:
+The `dbx-agent-app` framework makes it trivial to turn a Databricks App into a discoverable, standards-compliant agent:
 
 - **Auto-generates A2A protocol endpoints** (`/.well-known/agent.json`, `/.well-known/openid-configuration`)
 - **Wraps FastAPI** to seamlessly integrate agent capabilities with your web app
@@ -31,21 +31,21 @@ The [A2A (Agent-to-Agent) protocol](https://a2a.so/) provides a standard way for
 ## Installation
 
 ```bash
-pip install databricks-agents
+pip install dbx-agent-app
 ```
 
 Or with development dependencies:
 
 ```bash
-pip install databricks-agents[dev]
+pip install dbx-agent-app[dev]
 ```
 
 ## Quick Start
 
 ### 1. Create an Agent
 
 ```python
-from databricks_agents import app_agent, AgentRequest, AgentResponse
+from dbx_agent_app import app_agent, AgentRequest, AgentResponse
 
 # Create your agent with capabilities
 @app_agent(
@@ -94,7 +94,7 @@ databricks apps deploy customer-research --source-code-path ./
 
 ```python
 import asyncio
-from databricks_agents.discovery import AgentDiscovery
+from dbx_agent_app.discovery import AgentDiscovery
 
 async def main():
     discovery = AgentDiscovery(profile="my-profile")
@@ -168,7 +168,7 @@ Standard health check endpoint:
 The `AgentDiscovery` class scans your workspace for agent-enabled apps:
 
 ```python
-from databricks_agents.discovery import AgentDiscovery
+from dbx_agent_app.discovery import AgentDiscovery
 
 # Initialize with optional profile
 discovery = AgentDiscovery(profile="my-profile")
@@ -196,7 +196,7 @@ if result.errors:
 Communicate with other agents using the A2A protocol:
 
 ```python
-from databricks_agents.discovery import A2AClient
+from dbx_agent_app.discovery import A2AClient
 
 async with A2AClient() as client:
     # Fetch an agent's card
@@ -222,7 +222,7 @@ For agents using plain FastAPI with the `add_agent_card()` helper, tools can be
 Example:
 
 ```python
-from databricks_agents import app_agent, AgentRequest, AgentResponse
+from dbx_agent_app import app_agent, AgentRequest, AgentResponse
 
 @app_agent(
     name="customer_research",

databricks-agents/docs/api/a2a-client.md

@@ -1,4 +1,4 @@
 # A2AClient
 
 !!! info "Coming Soon"
-    This page is under development. See the [source code](https://github.com/databricks-labs/databricks-agents) for current implementation details.
+    This page is under development. See the [source code](https://github.com/databricks-labs/dbx-agent-app) for current implementation details.

databricks-agents/docs/api/discovery.md

@@ -1,4 +1,4 @@
 # AgentDiscovery
 
 !!! info "Coming Soon"
-    This page is under development. See the [source code](https://github.com/databricks-labs/databricks-agents) for current implementation details.
+    This page is under development. See the [source code](https://github.com/databricks-labs/dbx-agent-app) for current implementation details.

databricks-agents/docs/api/uc-registry.md

@@ -1,4 +1,4 @@
 # UCAgentRegistry
 
 !!! info "Coming Soon"
-    This page is under development. See the [source code](https://github.com/databricks-labs/databricks-agents) for current implementation details.
+    This page is under development. See the [source code](https://github.com/databricks-labs/dbx-agent-app) for current implementation details.

databricks-agents/docs/contributing.md

@@ -1,4 +1,4 @@
 # Contributing
 
 !!! info "Coming Soon"
-    This page is under development. See the [source code](https://github.com/databricks-labs/databricks-agents) for current implementation details.
+    This page is under development. See the [source code](https://github.com/databricks-labs/dbx-agent-app) for current implementation details.