arcade-mcp/libs/tests/arcade_mcp_server/test_prompt.py
Eric Gustin 3424ec8219
MCP Local (#563)
Versions:
* arcade-mcp\==1.0.0rc1
* arcade-mcp-server\==1.0.0rc1
* arcade-core\==2.5.0rc1
* arcade-tdk\==2.6.0rc1
* arcade-serve\==2.2.0rc1

### Summary
Adds first-class MCP support across Arcade, introduces a new MCP server
and CLI, unifies the project under the arcade-mcp name, overhauls
templates/scaffolding, and improves developer tooling, secrets
management, and examples.

### Highlights
- **MCP Server & Core**
- New MCP server with stdio and HTTP/SSE transports, session management,
resumability, and lifecycle handling.
- FastAPI-like `MCPApp` for building servers with lazy init; integrated
worker+MCP HTTP app option.
- Middleware system (logging and error handling), robust exception
hierarchy, and Pydantic-based settings.
- Async-safe managers for tools, resources, and prompts backed by
registries and locks.
- Developer-facing, transport-agnostic runtime context interfaces (logs,
tools, prompts, resources, sampling, UI, notifications).
- Conversion from Arcade ToolDefinition to MCP tool schema; OpenAI JSON
tool schema converter.
  - Parser supports `@app.tool`/`@app.tool(...)` decorators.

- **CLI**
  - New `mcp` command to run MCP servers with stdio or HTTP/SSE.
- New `secret` command to set/list/unset tool secrets (supports .env
input, preserves original casing for lookups).
- `new` command refactored; option to create a full toolkit package with
scaffolding.
  - `chat` command removed.
- `serve.py` imports updated to `arcade_serve.fastapi.telemetry`;
version retrieval now uses `arcade-mcp`.
  - `show.py` refactor to use new local catalog utilities.
- `display_tool_details` improved: adds “Default” column and handles
nested properties.

- **Configuration & Discovery**
- New `configure.py` to set up Claude Desktop, Cursor, and VS Code to
connect to local or Arcade Cloud MCP servers.
- Discovery utilities to find/install toolkits, build `ToolCatalog`s,
analyze files for tools, load kits from directories (pyproject parsing),
and build minimal toolkits.
- Better handling of provider API key resolution and evaluation suite
loading.

- **Templates & Scaffolding**
- Reorganized template structure (minimal vs full); moved
`.pre-commit-config.yaml`, `.ruff.toml`, license, Makefile, README,
tests, and tools layout to correct paths.
  - Minimal template adds `.env.example` for runtime secret injection.
- Template pyproject updated for MCP servers; includes sample server
with greeting and secret-reveal tools.
  - Authorization flow in templates simplified.

- **Repo-wide Renaming & Examples**
- Migrates references from `arcade-ai` to `arcade-mcp` across READMEs,
scripts, and package metadata.
- Examples updated (LangChain/LangGraph/AI SDK/TypeScript) and package
name changed to `arcade-mcp-sdk`.

- **Evals & Core Utilities**
- Evals now use OpenAI tooling format (`OpenAIToolList`, `to_openai`);
`tool_eval` takes `provider_api_key`.
- Core utilities: fixed `does_function_return_value` by dedenting before
parse; version bump to `2.5.0rc1` and dependency cleanup.

- **Tooling & CI**
- `setup-uv-env` action splits toolkit vs contrib dependency
installation.
- Pre-commit: excludes `libs/arcade-mcp-server/mkdocs.yml` and
`libs/tests/` from YAML and Ruff hooks; Ruff per-file ignores (e.g.,
C901 in `libs/**/*.py`, TRY400 in server docs paths).
- Makefile updates for uv env setup, quality checks, tests, builds, and
new `shell` target.
  - Added Makefile to MCP server library to streamline dev workflow.

- **Cleanup**
  - Removed `claude.json` config.
- Simplified stdio entrypoint; removed unused imports (`arcade_gmail`,
`arcade_search`).

### Breaking Changes
- **CLI**: `chat` command removed; use `mcp`, `secret`, and updated
`new`.
- **Naming**: All users should update references from `arcade-ai` to
`arcade-mcp`.
- **Templates**: File paths moved; downstream scripts referencing old
template locations may need updates.

### Getting Started
- Run an MCP server:
  - `arcade mcp --stdio --toolkits your_toolkit`
  - `arcade mcp --http --toolkits your_toolkit`
- Manage secrets:
  - `arcade secret set your_toolkit KEY=value`
  - `arcade secret list your_toolkit`
  - `arcade secret unset your_toolkit KEY`
- Configure clients:
- `arcade configure` to set up Claude Desktop, Cursor, and VS Code for
local/Arcade Cloud MCP.

---------

Co-authored-by: Sam Partee <sam@arcade-ai.com>
Co-authored-by: Shub <125150494+shubcodes@users.noreply.github.com>
2025-09-25 15:28:15 -07:00

241 lines
8.9 KiB
Python

"""Tests for Prompt Manager implementation."""
import asyncio
import pytest
from arcade_mcp_server.exceptions import NotFoundError, PromptError
from arcade_mcp_server.managers.prompt import PromptManager
from arcade_mcp_server.types import (
GetPromptResult,
Prompt,
PromptArgument,
PromptMessage,
)
class TestPromptManager:
"""Test PromptManager class."""
@pytest.fixture
def prompt_manager(self):
"""Create a prompt manager instance."""
return PromptManager()
@pytest.fixture
def sample_prompt(self):
"""Create a sample prompt."""
return Prompt(
name="greeting",
description="A greeting prompt",
arguments=[
PromptArgument(name="name", description="The name to greet", required=True),
PromptArgument(
name="formal", description="Whether to use formal greeting", required=False
),
],
)
@pytest.fixture
def prompt_function(self):
"""Create a prompt function."""
async def greeting_prompt(args: dict[str, str]) -> list[PromptMessage]:
name = args.get("name", "")
formal_arg = args.get("formal", "false")
formal = str(formal_arg).lower() == "true"
if formal:
text = f"Good day, {name}. How may I assist you?"
else:
text = f"Hey {name}! What's up?"
return [PromptMessage(role="assistant", content={"type": "text", "text": text})]
return greeting_prompt
def test_manager_initialization(self):
"""Test prompt manager initialization."""
manager = PromptManager()
assert isinstance(manager, PromptManager)
@pytest.mark.asyncio
async def test_manager_lifecycle(self, prompt_manager):
"""Passive manager has no explicit lifecycle; ensure methods work."""
# Initially empty
prompts = await prompt_manager.list_prompts()
assert prompts == []
@pytest.mark.asyncio
async def test_add_prompt(self, prompt_manager, sample_prompt, prompt_function):
"""Test adding prompts."""
await prompt_manager.add_prompt(sample_prompt, prompt_function)
prompts = await prompt_manager.list_prompts()
assert len(prompts) == 1
assert prompts[0].name == sample_prompt.name
assert len(prompts[0].arguments) == 2
@pytest.mark.asyncio
async def test_remove_prompt(self, prompt_manager, sample_prompt, prompt_function):
"""Test removing prompts."""
await prompt_manager.add_prompt(sample_prompt, prompt_function)
removed = await prompt_manager.remove_prompt(sample_prompt.name)
assert removed.name == sample_prompt.name
prompts = await prompt_manager.list_prompts()
assert len(prompts) == 0
@pytest.mark.asyncio
async def test_get_prompt(self, prompt_manager, sample_prompt, prompt_function):
"""Test getting and executing prompts."""
await prompt_manager.add_prompt(sample_prompt, prompt_function)
result = await prompt_manager.get_prompt("greeting", {"name": "Alice", "formal": True})
assert isinstance(result, GetPromptResult)
assert len(result.messages) == 1
assert result.messages[0].role == "assistant"
assert "Good day, Alice" in result.messages[0].content["text"]
@pytest.mark.asyncio
async def test_get_prompt_default_args(self, prompt_manager, sample_prompt, prompt_function):
"""Test getting prompt with default arguments."""
await prompt_manager.add_prompt(sample_prompt, prompt_function)
result = await prompt_manager.get_prompt("greeting", {"name": "Bob"})
assert "Hey Bob!" in result.messages[0].content["text"]
@pytest.mark.asyncio
async def test_get_prompt_missing_required_args(
self, prompt_manager, sample_prompt, prompt_function
):
"""Test getting prompt without required arguments."""
await prompt_manager.add_prompt(sample_prompt, prompt_function)
with pytest.raises(PromptError):
await prompt_manager.get_prompt("greeting", {"formal": True})
@pytest.mark.asyncio
async def test_get_nonexistent_prompt(self, prompt_manager):
"""Test getting non-existent prompt."""
with pytest.raises(NotFoundError):
await prompt_manager.get_prompt("nonexistent", {})
@pytest.mark.asyncio
async def test_prompt_with_multiple_messages(self, prompt_manager):
"""Test prompt that returns multiple messages."""
prompt = Prompt(name="conversation", description="A conversation prompt")
async def conversation_prompt(args: dict[str, str]) -> list[PromptMessage]:
return [
PromptMessage(role="user", content={"type": "text", "text": "Hello!"}),
PromptMessage(role="assistant", content={"type": "text", "text": "Hi there!"}),
PromptMessage(role="user", content={"type": "text", "text": "How are you?"}),
PromptMessage(
role="assistant", content={"type": "text", "text": "I'm doing well, thanks!"}
),
]
await prompt_manager.add_prompt(prompt, conversation_prompt)
result = await prompt_manager.get_prompt("conversation", {})
assert len(result.messages) == 4
assert result.messages[0].role == "user"
assert result.messages[1].role == "assistant"
@pytest.mark.asyncio
async def test_prompt_with_image_content(self, prompt_manager):
"""Test prompt with image content."""
prompt = Prompt(
name="image_analysis",
description="Analyze an image",
arguments=[PromptArgument(name="image_url", required=True)],
)
async def image_prompt(args: dict[str, str]) -> list[PromptMessage]:
image_url = args.get("image_url", "")
return [
PromptMessage(
role="user",
content={"type": "image", "data": image_url, "mimeType": "image/jpeg"},
),
PromptMessage(
role="user", content={"type": "text", "text": "Please analyze this image"}
),
]
await prompt_manager.add_prompt(prompt, image_prompt)
result = await prompt_manager.get_prompt(
"image_analysis", {"image_url": "http://example.com/image.jpg"}
)
assert len(result.messages) == 2
assert result.messages[0].content["type"] == "image"
assert result.messages[1].content["type"] == "text"
@pytest.mark.asyncio
async def test_prompt_with_embedded_resource(self, prompt_manager):
"""Test prompt with embedded resources."""
prompt = Prompt(name="with_resource", description="Prompt with embedded resource")
async def resource_prompt(args: dict[str, str]) -> list[PromptMessage]:
return [
PromptMessage(
role="user",
content={
"type": "resource",
"resource": {"uri": "file:///data.txt", "text": "Sample data"},
},
)
]
await prompt_manager.add_prompt(prompt, resource_prompt)
result = await prompt_manager.get_prompt("with_resource", {})
assert result.messages[0].content["type"] == "resource"
assert result.messages[0].content["resource"]["uri"] == "file:///data.txt"
@pytest.mark.asyncio
async def test_concurrent_prompt_operations(self, prompt_manager):
"""Test concurrent prompt operations."""
prompts = []
for i in range(10):
prompt = Prompt(name=f"prompt_{i}", description=f"Prompt {i}")
async def func(args: dict[str, str], idx=i):
return [
PromptMessage(
role="assistant", content={"type": "text", "text": f"Response {idx}"}
)
]
prompts.append((prompt, func))
tasks = [prompt_manager.add_prompt(p, f) for p, f in prompts]
await asyncio.gather(*tasks)
listed = await prompt_manager.list_prompts()
assert len(listed) == 10
@pytest.mark.asyncio
async def test_list_prompts_initial(self, prompt_manager):
"""Passive manager lists prompts initially as empty."""
prompts = await prompt_manager.list_prompts()
assert prompts == []
@pytest.mark.asyncio
async def test_prompt_error_handling(self):
"""Test error handling in prompt functions."""
manager = PromptManager()
prompt = Prompt(name="error_prompt", description="Prompt that errors")
async def error_prompt(args: dict[str, str]):
raise RuntimeError("Prompt execution failed")
await manager.add_prompt(prompt, error_prompt)
with pytest.raises(PromptError):
await manager.get_prompt("error_prompt", {})