fast-agent-mcp 0.0.7__tar.gz → 0.0.8__tar.gz

{fast_agent_mcp-0.0.7 → fast_agent_mcp-0.0.8}/.gitignore

@@ -178,3 +178,4 @@ project_contents.md
 examples/**/*.jsonl
 mcp_agent.config.yaml
 mcp_agent.secrets.yaml
+fastagent.secrets.yaml

{fast_agent_mcp-0.0.7 → fast_agent_mcp-0.0.8}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: fast-agent-mcp
-Version: 0.0.7
-Summary: Build, Test, Deploy composable MCP Agent Workflows.
+Version: 0.0.8
+Summary: Define, Prompt and Test MCP enabled Agents and Workflows
 Author-email: Shaun Smith <fastagent@llmindset.co.uk>, Sarmad Qadri <sarmad@lastmileai.dev>
 License:                                  Apache License
                                    Version 2.0, January 2004
@@ -219,7 +219,6 @@ Requires-Dist: opentelemetry-distro>=0.50b0
 Requires-Dist: opentelemetry-exporter-otlp-proto-http>=1.29.0
 Requires-Dist: pydantic-settings>=2.7.0
 Requires-Dist: pydantic>=2.10.4
-Requires-Dist: pyreadline3>=3.5.4
 Requires-Dist: pyyaml>=6.0.2
 Requires-Dist: rich>=13.9.4
 Requires-Dist: scikit-learn>=1.6.0
@@ -238,35 +237,37 @@ Description-Content-Type: text/markdown
 ## FastAgent
 
 <p align="center">
-<a href="https://pypi.org/project/mcp-agent/"><img src="https://img.shields.io/pypi/v/mcp-agent?color=%2334D058&label=pypi" /></a>
-<a href="https://github.com/lastmile-ai/mcp-agent/issues"><img src="https://img.shields.io/github/issues-raw/lastmile-ai/mcp-agent" /></a>
+<a href="https://pypi.org/project/fast-agent-mcp/"><img src="https://img.shields.io/pypi/v/fast-agent-mcp?color=%2334D058&label=pypi" /></a>
+<a href="https://github.com/evalstate/fast-agent/issues"><img src="https://img.shields.io/github/issues-raw/evalstate/fast-agent" /></a>
 <a href="https://lmai.link/discord/mcp-agent"><img src="https://shields.io/discord/1089284610329952357" alt="discord" /></a>
-<img alt="Pepy Total Downloads" src="https://img.shields.io/pepy/dt/mcp-agent?label=pypi%20%7C%20downloads"/>
-<a href="https://github.com/lastmile-ai/mcp-agent/blob/main/LICENSE"><img src="https://img.shields.io/pypi/l/mcp-agent" /></a>
+<img alt="Pepy Total Downloads" src="https://img.shields.io/pepy/dt/fast-agent-mcp?label=pypi%20%7C%20downloads"/>
+<a href="https://github.com/evalstate/fast-agent-mcp/blob/main/LICENSE"><img src="https://img.shields.io/pypi/l/fast-agent-mcp" /></a>
 </p>
 
 ## Overview
 
-**`mcp-agent`** is a simple, composable framework to build agents using [Model Context Protocol](https://modelcontextprotocol.io/introduction).
+**`fast-agent`** lets you define, test and compose agents and tools in minutes. 
 
-**Inspiration**: Anthropic announced 2 foundational updates for AI application developers:
+### Get started:
 
-1. [Model Context Protocol](https://www.anthropic.com/news/model-context-protocol) - a standardized interface to let any software be accessible to AI assistants via MCP servers.
-2. [Building Effective Agents](https://www.anthropic.com/research/building-effective-agents) - a seminal writeup on simple, composable patterns for building production-ready AI agents.
+Install the [uv package manager](https://docs.astral.sh/uv/).
 
-`mcp-agent` puts these two foundational pieces into an AI application framework:
+`uv pip install fast-agent-mcp` - download fast-agent
 
-1. It handles the pesky business of managing the lifecycle of MCP server connections so you don't have to.
-2. It implements every pattern described in Building Effective Agents, and does so in a _composable_ way, allowing you to chain these patterns together.
-3. **Bonus**: It implements [OpenAI's Swarm](https://github.com/openai/swarm) pattern for multi-agent orchestration, but in a model-agnostic way.
+`fast-agent setup` - setup an agent and configuration files.
 
-Altogether, this is the simplest and easiest way to build robust agent applications. Much like MCP, this project is in early development.
-We welcome all kinds of [contributions](/CONTRIBUTING.md), feedback and your help in growing this to become a new standard.
+`uv run agent.py` - run and interact with your first agent.
+
+`fast-agent bootstrap workflow` - generate example agents demonstrating each of the workflows from Anthropic's "[Building Effective Agents](https://www.anthropic.com/research/building-effective-agents)" paper.
+
+It's built on top of [mcp-agent](todo).
 
 ### llmindset.co.uk fork:
 
-- "FastAgent" style prototyping
-- Interactive Mode
+- "FastAgent" style prototyping, with per-agent models
+- Warm-up / Post-Workflow Agent Interactions
+- Quick Setup
+- Interactive Prompt Mode
 - Simple Model Selection with aliases
 - User/Assistant and Tool Call message display
 - MCP Sever Environment Variable support
@@ -274,49 +275,13 @@ We welcome all kinds of [contributions](/CONTRIBUTING.md), feedback and your hel
 - Comprehensive Progress display
 - JSONL file logging with secret revokation
 - OpenAI o1/o3-mini support with reasoning level
-- Enhaned Human Input Messaging and Handling
+- Enhanced Human Input Messaging and Handling
+- Declarative workflows
 
 ## Get Started
 
 We recommend using [uv](https://docs.astral.sh/uv/) to manage your Python projects:
 
-```bash
-uv add "mcp-agent"
-```
-
-Alternatively:
-
-```bash
-pip install mcp-agent
-```
-
-### Quickstart
-
-> [!TIP]
-> The [`examples`](/examples) directory has several example applications to get started with.
-> To run an example, clone this repo, then:
->
-> ```bash
-> cd examples/mcp_basic_agent # Or any other example
-> cp mcp_agent.secrets.yaml.example mcp_agent.secrets.yaml # Update API keys
-> uv run main.py
-> ```
-
 ## Table of Contents
 
-## Workflows
-
-mcp-agent provides implementations for every pattern in Anthropic’s [Building Effective Agents](https://www.anthropic.com/research/building-effective-agents), as well as the OpenAI [Swarm](https://github.com/openai/swarm) pattern.
-Each pattern is model-agnostic, and exposed as an `AugmentedLLM`, making everything very composable.
-
-</details>
-
-### Signaling and Human Input
-
-**Signaling**: The framework can pause/resume tasks. The agent or LLM might “signal” that it needs user input, so the workflow awaits. A developer may signal during a workflow to seek approval or review before continuing with a workflow.
-
-**Human Input**: If an Agent has a `human_input_callback`, the LLM can call a `__human_input__` tool to request user input mid-workflow.
-
-## Contributing
-
 We welcome any and all kinds of contributions. Please see the [CONTRIBUTING guidelines](./CONTRIBUTING.md) to get started.

fast_agent_mcp-0.0.8/README.md

@@ -0,0 +1,51 @@
+## FastAgent
+
+<p align="center">
+<a href="https://pypi.org/project/fast-agent-mcp/"><img src="https://img.shields.io/pypi/v/fast-agent-mcp?color=%2334D058&label=pypi" /></a>
+<a href="https://github.com/evalstate/fast-agent/issues"><img src="https://img.shields.io/github/issues-raw/evalstate/fast-agent" /></a>
+<a href="https://lmai.link/discord/mcp-agent"><img src="https://shields.io/discord/1089284610329952357" alt="discord" /></a>
+<img alt="Pepy Total Downloads" src="https://img.shields.io/pepy/dt/fast-agent-mcp?label=pypi%20%7C%20downloads"/>
+<a href="https://github.com/evalstate/fast-agent-mcp/blob/main/LICENSE"><img src="https://img.shields.io/pypi/l/fast-agent-mcp" /></a>
+</p>
+
+## Overview
+
+**`fast-agent`** lets you define, test and compose agents and tools in minutes. 
+
+### Get started:
+
+Install the [uv package manager](https://docs.astral.sh/uv/).
+
+`uv pip install fast-agent-mcp` - download fast-agent
+
+`fast-agent setup` - setup an agent and configuration files.
+
+`uv run agent.py` - run and interact with your first agent.
+
+`fast-agent bootstrap workflow` - generate example agents demonstrating each of the workflows from Anthropic's "[Building Effective Agents](https://www.anthropic.com/research/building-effective-agents)" paper.
+
+It's built on top of [mcp-agent](todo).
+
+### llmindset.co.uk fork:
+
+- "FastAgent" style prototyping, with per-agent models
+- Warm-up / Post-Workflow Agent Interactions
+- Quick Setup
+- Interactive Prompt Mode
+- Simple Model Selection with aliases
+- User/Assistant and Tool Call message display
+- MCP Sever Environment Variable support
+- MCP Roots support
+- Comprehensive Progress display
+- JSONL file logging with secret revokation
+- OpenAI o1/o3-mini support with reasoning level
+- Enhanced Human Input Messaging and Handling
+- Declarative workflows
+
+## Get Started
+
+We recommend using [uv](https://docs.astral.sh/uv/) to manage your Python projects:
+
+## Table of Contents
+
+We welcome any and all kinds of contributions. Please see the [CONTRIBUTING guidelines](./CONTRIBUTING.md) to get started.

{fast_agent_mcp-0.0.7 → fast_agent_mcp-0.0.8}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "fast-agent-mcp"
-version = "0.0.7"
-description = "Build, Test, Deploy composable MCP Agent Workflows."
+version = "0.0.8"
+description = "Define, Prompt and Test MCP enabled Agents and Workflows"
 readme = "README.md"
 license = { file = "LICENSE" }
 authors = [
@@ -27,7 +27,6 @@ dependencies = [
     "typer>=0.15.1",
     "numpy>=2.2.1",
     "scikit-learn>=1.6.0",
-    "pyreadline3>=3.5.4",
     "anthropic>=0.42.0",
     "openai>=1.63.2",
 ]
@@ -57,7 +56,13 @@ packages = ["src/mcp_agent"]
 [tool.hatch.build]
 include = [
     "src/mcp_agent/**/*.py",
+    "src/mcp_agent/**/*.yaml",
+    "src/mcp_agent/**/*.yml",
+    "src/mcp_agent/**/*.csv",
     "src/mcp_agent/resources/**/*.py",
+    "src/mcp_agent/resources/**/*.yaml",
+    "src/mcp_agent/resources/**/*.yml",
+    "src/mcp_agent/resources/**/*.csv",
 ]
 
 [dependency-groups]
@@ -77,6 +82,12 @@ fastagent = "mcp_agent.cli.__main__:app"
 silsila = "mcp_agent.cli.__main__:app"
 
 [tool.setuptools.package-data]
-mcp-agent = ["data/*.json"]
-mcp_agent = ["resources/examples/**/*.py"]  # Include all Python files in examples subdirectories
+mcp_agent = [
+    "data/*.json",
+    "resources/examples/**/*.py",
+    "resources/examples/**/*.yaml",
+    "resources/examples/**/*.yml",
+    "resources/examples/**/*.csv",
+    "resources/examples/**/mount-point/*.csv"
+]
 

{fast_agent_mcp-0.0.7 → fast_agent_mcp-0.0.8}/src/mcp_agent/agents/agent.py

@@ -43,6 +43,7 @@ class AgentConfig:
     model: Optional[str] = None
     use_history: bool = True
     default_request_params: Optional[RequestParams] = None
+    human_input: bool = False
 
     def __post_init__(self):
         """Ensure default_request_params exists with proper history setting"""
@@ -103,10 +104,13 @@ class Agent(MCPAggregator):
         # Map function names to tools
         self._function_tool_map: Dict[str, FastTool] = {}
 
-        self.human_input_callback: HumanInputCallback | None = human_input_callback
-        if not human_input_callback:
-            if self.context.human_input_handler:
-                self.human_input_callback = self.context.human_input_handler
+        if not self.config.human_input:
+            self.human_input_callback = None
+        else:
+            self.human_input_callback: HumanInputCallback | None = human_input_callback
+            if not human_input_callback:
+                if self.context.human_input_handler:
+                    self.human_input_callback = self.context.human_input_handler
 
     async def initialize(self):
         """

{fast_agent_mcp-0.0.7 → fast_agent_mcp-0.0.8}/src/mcp_agent/app.py

@@ -154,7 +154,11 @@ class MCPApp:
                 "agent_name": "mcp_application_loop",
             },
         )
-        await cleanup_context()
+        try:
+            await cleanup_context()
+        except asyncio.CancelledError:
+            self.logger.debug("Cleanup cancelled error during shutdown")
+
         self._context = None
         self._initialized = False
 

fast_agent_mcp-0.0.8/src/mcp_agent/cli/commands/bootstrap.py

@@ -0,0 +1,280 @@
+"""Bootstrap command to create example applications."""
+
+import shutil
+from pathlib import Path
+import typer
+from rich.console import Console
+from rich.table import Table
+from rich.panel import Panel
+
+app = typer.Typer(
+    help="Create example applications",
+    no_args_is_help=False,  # Allow showing our custom help instead
+)
+console = Console()
+
+EXAMPLE_TYPES = {
+    "workflow": {
+        "description": "Example workflows, demonstrating each of the patterns in Anthropic's\n"
+        "'Building Effective Agents' paper. Some agents use the 'fetch'\n"
+        "and filesystem MCP Servers.",
+        "files": [
+            "chaining.py",
+            "evaluator.py",
+            "human_input.py",
+            "orchestrator.py",
+            "parallel.py",
+            "router.py",
+        ],
+        "create_subdir": False,
+    },
+    "researcher": {
+        "description": "Research agent example with additional evaluation/optimization\n"
+        "example. Uses Brave Search and Docker MCP Servers.\n"
+        "Creates examples in a 'researcher' subdirectory.",
+        "files": [
+            "researcher.py",
+            "researcher-eval.py",
+            "mcp_agent.secrets.yaml.example",
+        ],
+        "create_subdir": True,
+    },
+    "data-analysis": {
+        "description": "Data analysis agent examples that demonstrate working with\n"
+        "datasets, performing statistical analysis, and generating visualizations.\n"
+        "Creates examples in a 'data-analysis' subdirectory with mount-point for data.\n"
+        "Uses MCP 'roots' feature for mapping",
+        "files": ["analysis.py", "fastagent.config.yaml"],
+        "mount_point_files": ["WA_Fn-UseC_-HR-Employee-Attrition.csv"],
+        "create_subdir": True,
+    },
+}
+
+
+def copy_example_files(
+    example_type: str, target_dir: Path, force: bool = False
+) -> list[str]:
+    """Copy example files from resources to target directory."""
+    created = []
+
+    # Determine if we should create a subdirectory for this example type
+    example_info = EXAMPLE_TYPES[example_type]
+    if example_info["create_subdir"]:
+        target_dir = target_dir / example_type
+        if not target_dir.exists():
+            target_dir.mkdir(parents=True)
+            console.print(f"Created subdirectory: {target_dir}")
+
+    # Create mount-point directory if needed
+    mount_point_files = example_info.get("mount_point_files", [])
+    if mount_point_files:
+        mount_point_dir = target_dir / "mount-point"
+        if not mount_point_dir.exists():
+            mount_point_dir.mkdir(parents=True)
+            console.print(f"Created mount-point directory: {mount_point_dir}")
+
+    # Use the resources directory from the package
+    source_dir = (
+        Path(__file__).parent.parent.parent
+        / "resources"
+        / "examples"
+        / ("workflows" if example_type == "workflow" else f"{example_type}")
+    )
+
+    if not source_dir.exists():
+        console.print(f"[red]Error: Source directory not found: {source_dir}[/red]")
+        return created
+
+    for filename in example_info["files"]:
+        source = source_dir / filename
+        target = target_dir / filename
+
+        try:
+            if not source.exists():
+                console.print(f"[red]Error: Source file not found: {source}[/red]")
+                continue
+
+            if target.exists() and not force:
+                console.print(f"[yellow]Skipping[/yellow] {filename} (already exists)")
+                continue
+
+            shutil.copy2(source, target)
+            created.append(str(target.relative_to(target_dir.parent)))
+            console.print(f"[green]Created[/green] {created[-1]}")
+
+        except Exception as e:
+            console.print(f"[red]Error copying {filename}: {str(e)}[/red]")
+
+    # Copy mount-point files if any
+    if mount_point_files:
+        source_mount_point = source_dir / "mount-point"
+        for filename in mount_point_files:
+            source = source_mount_point / filename
+            target = mount_point_dir / filename
+
+            try:
+                if not source.exists():
+                    console.print(f"[red]Error: Source file not found: {source}[/red]")
+                    continue
+
+                if target.exists() and not force:
+                    console.print(
+                        f"[yellow]Skipping[/yellow] mount-point/{filename} (already exists)"
+                    )
+                    continue
+
+                shutil.copy2(source, target)
+                created.append(f"{example_type}/mount-point/{filename}")
+                console.print(f"[green]Created[/green] mount-point/{filename}")
+
+            except Exception as e:
+                console.print(
+                    f"[red]Error copying mount-point/{filename}: {str(e)}[/red]"
+                )
+
+    return created
+
+
+def show_overview():
+    """Display an overview of available examples in a nicely formatted table."""
+    console.print("\n[bold cyan]FastAgent Example Applications[/bold cyan]")
+    console.print("Build agents and compose workflows through practical examples\n")
+
+    # Create a table for better organization
+    table = Table(
+        show_header=True, header_style="bold magenta", box=None, padding=(0, 2)
+    )
+    table.add_column("Example")
+    table.add_column("Description")
+    table.add_column("Files")
+
+    for name, info in EXAMPLE_TYPES.items():
+        files_list = "\n".join(f"• {f}" for f in info["files"])
+        if "mount_point_files" in info:
+            files_list += "\n[blue]mount-point:[/blue]\n" + "\n".join(
+                f"• {f}" for f in info["mount_point_files"]
+            )
+        table.add_row(f"[green]{name}[/green]", info["description"], files_list)
+
+    console.print(table)
+
+    # Show usage instructions in a panel
+    usage_text = (
+        "[bold]Commands:[/bold]\n"
+        "  fastagent bootstrap workflow DIR      Create workflow examples in DIR\n"
+        "  fastagent bootstrap researcher DIR    Create researcher example in 'researcher' subdirectory\n"
+        "  fastagent bootstrap data-analysis DIR Create data analysis examples in 'data-analysis' subdirectory\n\n"
+        "[bold]Options:[/bold]\n"
+        "  --force            Overwrite existing files\n\n"
+        "[bold]Examples:[/bold]\n"
+        "  fastagent bootstrap workflow .              Create in current directory\n"
+        "  fastagent bootstrap researcher .            Create in researcher subdirectory\n"
+        "  fastagent bootstrap data-analysis . --force Force overwrite files in data-analysis subdirectory"
+    )
+    console.print(Panel(usage_text, title="Usage", border_style="blue"))
+
+
+@app.command()
+def workflow(
+    directory: Path = typer.Argument(
+        Path("."),
+        help="Directory where workflow examples will be created",
+    ),
+    force: bool = typer.Option(
+        False, "--force", "-f", help="Force overwrite existing files"
+    ),
+):
+    """Create workflow pattern examples."""
+    target_dir = directory.resolve()
+    if not target_dir.exists():
+        target_dir.mkdir(parents=True)
+        console.print(f"Created directory: {target_dir}")
+
+    created = copy_example_files("workflow", target_dir, force)
+    _show_completion_message("workflow", created)
+
+
+@app.command()
+def researcher(
+    directory: Path = typer.Argument(
+        Path("."),
+        help="Directory where researcher examples will be created (in 'researcher' subdirectory)",
+    ),
+    force: bool = typer.Option(
+        False, "--force", "-f", help="Force overwrite existing files"
+    ),
+):
+    """Create researcher pattern examples."""
+    target_dir = directory.resolve()
+    if not target_dir.exists():
+        target_dir.mkdir(parents=True)
+        console.print(f"Created directory: {target_dir}")
+
+    created = copy_example_files("researcher", target_dir, force)
+    _show_completion_message("researcher", created)
+
+
+@app.command()
+def data_analysis(
+    directory: Path = typer.Argument(
+        Path("."),
+        help="Directory where data analysis examples will be created (creates 'data-analysis' subdirectory with mount-point)",
+    ),
+    force: bool = typer.Option(
+        False, "--force", "-f", help="Force overwrite existing files"
+    ),
+):
+    """Create data analysis examples with sample dataset."""
+    target_dir = directory.resolve()
+    if not target_dir.exists():
+        target_dir.mkdir(parents=True)
+        console.print(f"Created directory: {target_dir}")
+
+    created = copy_example_files("data-analysis", target_dir, force)
+    _show_completion_message("data-analysis", created)
+
+
+def _show_completion_message(example_type: str, created: list[str]):
+    """Show completion message and next steps."""
+    if created:
+        console.print("\n[green]Setup completed successfully![/green]")
+        console.print("\nCreated files:")
+        for f in created:
+            console.print(f"  - {f}")
+
+        console.print("\n[bold]Next Steps:[/bold]")
+        if example_type == "workflow":
+            console.print("1. Review chaining.py for the basic workflow example")
+            console.print("2. Check other examples:")
+            console.print("   - parallel.py: Run agents in parallel")
+            console.print("   - router.py: Route requests between agents")
+            console.print("   - evaluator.py: Add evaluation capabilities")
+            console.print("   - human_input.py: Incorporate human feedback")
+            console.print("3. Run an example with: uv run <example>.py")
+            console.print(
+                "4. Try a different model with --model=<model>, or update the agent config"
+            )
+
+        elif example_type == "researcher":
+            console.print(
+                "1. Set up the Brave MCP Server (get an API key from https://brave.com/search/api/)"
+            )
+            console.print("2. Try `uv run researcher.py` for the basic version")
+            console.print(
+                "3. Try `uv run researcher-eval.py` for the eval/optimize version"
+            )
+        elif example_type == "data-analysis":
+            console.print(
+                "1. Run uv `analysis.py` to perform data analysis and visualization"
+            )
+            console.print("2. The dataset is available in the mount-point directory:")
+            console.print("   - mount-point/WA_Fn-UseC_-HR-Employee-Attrition.csv")
+    else:
+        console.print("\n[yellow]No files were created.[/yellow]")
+
+
+@app.callback(invoke_without_command=True)
+def main(ctx: typer.Context):
+    """Create example applications and learn FastAgent patterns."""
+    if ctx.invoked_subcommand is None:
+        show_overview()

{fast_agent_mcp-0.0.7 → fast_agent_mcp-0.0.8}/src/mcp_agent/cli/commands/setup.py

@@ -22,28 +22,31 @@ FASTAGENT_CONFIG_TEMPLATE = """
 default_model: sonnet
 
 # Logging and Console Configuration:
-logging:
+logger:
     # level: "debug" | "info" | "warning" | "error"
     # type: "none" | "console" | "file" | "http"
     # path: "/path/to/logfile.jsonl"
 
     
     # Switch the progress display on or off
-    # progress_display: true
+    progress_display: true
 
     # Show chat User/Assistant messages on the console
-    # show_chat: true
+    show_chat: true
     # Show tool calls on the console
-    # show_tools: true
+    show_tools: true
     # Truncate long tool responses on the console 
-    # truncate_tools: true
+    truncate_tools: true
 
 # MCP Servers
 mcp:
     servers:
         fetch:
             command: "uvx"
-            args: ["mcp-server-fetch"]    
+            args: ["mcp-server-fetch"]
+        filesystem:
+            command: "npx"
+            args: ["-y", "@modelcontextprotocol/server-filesystem", "."]
 
 """
 
@@ -51,6 +54,8 @@ FASTAGENT_SECRETS_TEMPLATE = """
 # FastAgent Secrets Configuration
 # WARNING: Keep this file secure and never commit to version control
 
+# Alternatively set OPENAI_API_KEY and ANTHROPIC_API_KEY environment variables. Config file takes precedence.
+
 openai:
     api_key: <your-api-key-here>
 anthropic:
@@ -110,17 +115,14 @@ import asyncio
 from mcp_agent.core.fastagent import FastAgent
 
 # Create the application
-agent_app = FastAgent("FastAgent Example")
-# Uncomment the below to disable human input callback tool
-# agent_app.app._human_input_callback = None
+fast = FastAgent("FastAgent Example")
 
 
 # Define the agent
-@agent_app.agent(servers=["fetch"])
-# @agent_app.agent(servers=["fetch"])
+@fast.agent(servers=["fetch"])
 async def main():
-    # use the --model= command line switch to specify model
-    async with agent_app.run() as agent:
+    # use the --model command line switch or agent arguments to change model
+    async with fast.run() as agent:
         await agent()
 
 
@@ -217,11 +219,13 @@ def init(
 
     if created:
         console.print("\n[green]Setup completed successfully![/green]")
-        if "fastagent-secrets.yaml" in created:
+        if "fastagent.secrets.yaml" in created:
             console.print("\n[yellow]Important:[/yellow] Remember to:")
-            console.print("1. Add your API keys to fastagent-secrets.yaml")
             console.print(
-                "2. Keep fastagent-secrets.yaml secure and never commit it to version control"
+                "1. Add your API keys to fastagent-secrets.yaml or set OPENAI_API_KEY and ANTHROPIC_API_KEY environment variables"
+            )
+            console.print(
+                "2. Keep fastagent.secrets.yaml secure and never commit it to version control"
             )
         console.print("\nTo get started, run:")
         console.print("  uv run agent.py")