4 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
jottakka
|
7472b18106
|
Fixing bug with multiple providers + stats for multiple runs (#752)
@EricGustin you can use this cli command:
```
uv run arcade evals mcp_building_evals_results/eval_toolkit_iteration_dict.py \
-p openai:gpt-4o,gpt-4o-mini \
-p anthropic:claude-sonnet-4-20250514 \
-k openai:$OPENAI_API_KEY \
-k anthropic:$ANTHROPIC_API_KEY \
-d \
--num-runs 3 \
--seed random \
--multi-run-pass-rule majority \
--max-concurrent 6 \
-o mcp_building_evals_results/results
```
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Medium Risk**
> Touches core eval execution and all result formatters while adding new
CLI inputs and output schema (`run_stats`/`critic_stats` and capture
`runs`), so regressions could affect evaluation results and report
compatibility despite being additive and validated.
>
> **Overview**
> Adds **multi-run evaluation support** to `arcade evals` via new flags
`--num-runs`, `--seed`, and `--multi-run-pass-rule`, with upfront
validation and plumbing through the CLI runner into eval/capture suite
execution.
>
> Fixes provider selection UX/bug by making `--use-provider/-p`
**repeatable** (instead of a space-delimited string), updates
docs/examples accordingly, and extends capture mode to optionally record
**per-run tool calls** (`CapturedRun`) when `num_runs > 1`.
>
> Enhances all output formatters (HTML/Markdown/Text/JSON) to
**propagate and display** per-case `run_stats` and `critic_stats`,
including new HTML UI for run tabs/cards and comparative tables showing
mean ± stddev when multi-run data is present.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
2ee1654b7d1fbb9538373507355636164b16a066. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
|
||
|
jottakka
|
98fad93d21
|
Adding MCP Servers supports to Arcade Evals (#689)
# MCP Server Tool Evaluation Support
## Overview
Add support for evaluating tools from remote MCP servers without
requiring Python callables. Enables direct evaluation of any
MCP-compatible tool server.
## What's New
### Core Features
- **`MCPToolRegistry`**: Evaluate tools from a single MCP server
- **`CompositeMCPRegistry`**: Evaluate tools from multiple MCP servers
simultaneously
- **Automatic loaders**: `load_from_stdio()` and `load_from_http()` to
fetch tools from running servers
- **Automatic namespacing**: Tools prefixed with server name (e.g.,
`server_tool_name`)
- **Smart name resolution**: Use short names if unique, full names if
ambiguous
- **OpenAI strict mode**: Automatic schema conversion prevents parameter
hallucinations
### Usage
**Automatic Loading:**
```python
from arcade_evals import load_from_stdio, MCPToolRegistry
# Load tools automatically from MCP server
tools = load_from_stdio(["npx", "-y", "@modelcontextprotocol/server-github"])
registry = MCPToolRegistry(tools)
```
**Single MCP Server:**
```python
from arcade_evals import MCPToolRegistry, ExpectedToolCall
registry = MCPToolRegistry(mcp_tools)
suite = EvalSuite(catalog=registry)
suite.add_case(
expected_tool_calls=[
ExpectedToolCall(tool_name="tool_name", args={...})
]
)
```
**Multiple MCP Servers:**
```python
from arcade_evals import CompositeMCPRegistry, load_from_stdio
# Load from multiple servers
github_tools = load_from_stdio(["npx", "-y", "@modelcontextprotocol/server-github"])
slack_tools = load_from_stdio(["npx", "-y", "@modelcontextprotocol/server-slack"])
composite = CompositeMCPRegistry(
tool_lists={
"github": github_tools,
"slack": slack_tools,
}
)
suite = EvalSuite(catalog=composite)
suite.add_case(
expected_tool_calls=[
ExpectedToolCall(tool_name="github_list_issues", args={...})
]
)
```
## Implementation
### Files Changed
- **`libs/arcade-evals/arcade_evals/registry.py`** (NEW): Registry
abstractions and implementations
- **`libs/arcade-evals/arcade_evals/loaders.py`** (NEW): Automatic tool
loading from MCP servers
- **`libs/arcade-evals/arcade_evals/eval.py`** (MODIFIED): Enhanced
`ExpectedToolCall` and evaluation logic
- **`libs/arcade-evals/arcade_evals/__init__.py`** (MODIFIED): Exported
new registries and loaders
### Key Technical Details
- Added `BaseToolRegistry` interface for abstraction
- `MCPToolRegistry` handles single server tools
- `CompositeMCPRegistry` manages multiple servers with collision
detection
- `load_from_stdio()` and `load_from_http()` for automatic tool
discovery
- Fixed name normalization bug: MCP tools use underscores (not dots)
- Optimized tool copying: 2.5x faster via shallow copy
## Testing
- ✅ 41 tests passing (25 new tests added)
- ✅ `test_eval_mcp_registry.py`: MCPToolRegistry functionality
- ✅ `test_eval_composite_mcp.py`: CompositeMCPRegistry with multiple
servers
- ✅ Verified backward compatibility with Python tools
## Backward Compatibility
✅ **100% backward compatible** - No breaking changes
## Breaking Changes
**None**
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Adds end-to-end eval UX: examples, a robust CLI runner, and rich
outputs.
>
> - **New examples**: `eval_arcade_gateway.py`,
`eval_stdio_mcp_server.py`, `eval_http_mcp_server.py`,
`eval_comprehensive_comparison.py` with timeouts, error handling, and
track-based comparisons; detailed `README.md`
> - **CLI runner**: `arcade_cli/evals_runner.py` to execute
evals/capture in parallel with progress, error isolation, failed-only
filtering, context inclusion, and multi-provider/model support
> - **Output formatters**: `arcade_cli/formatters/` (txt, md, html,
json) for evals and capture; comparative and multi-model HTML with tabs
and context rendering
> - **Display refactor**: `display.py` now supports writing multiple
formats, failed-only disclaimers, include-context, and improved console
summaries
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
ff8acf9c34a6b61462a019a1ee9df081006517d0. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: Francisco Liberal <francisco@arcade.dev>
Co-authored-by: Mateo Torres <torresmateo@gmail.com>
|
||
|
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> |
||
|
Sam Partee
|
b6b4cd0a4c
|
🏗️ Restructure: Multi-Package Architecture + uv Migration (#412)
### Overview Major restructuring from monolithic `arcade-ai` package to modular library architecture with standardized uv-based dependency management.  ### New Package Structure - **`arcade-tdk`** - Lightweight toolkit development kit (core decorators, auth) - **`arcade-core`** - Core execution engine and catalog functionality - **`arcade-serve`** - FastAPI/MCP server components - **`arcade-ai`** - Meta package that includes CLI functionality. Optionally include evals via the `evals` extra. Optionally include all packages via the `all` extra. ### Key Benefits - **Lighter Dependencies**: Toolkits now depend only on `arcade-tdk` (~2 deps) vs full `arcade-ai` (~30+ deps) - **Faster Builds**: uv provides 10-100x faster dependency resolution and installation - **Better Modularity**: Clear separation of concerns, consumers import only what they need - **Standard Tooling**: Eliminates custom poetry scripts, uses standard Python packaging ### Migration Impact - All 20 toolkits converted from poetry → uv with `arcade-tdk` dependencies plus `arcade-ai[evals]` and `arcade-serve` dev dependencies. When developing locally, devs should install toolkits via `make install-local`. - Modern Python 3.10+ type hints throughout - Standardized build system with hatchling backend - Enhanced Makefile with robust toolkit management commands - Removed `arcade dev` CLI command - Reduce the number of files created by `arcade new` and add an option to not generate a tests and evals folder. This foundation enables faster development cycles and cleaner dependency chains for the growing toolkit ecosystem. ### Todo After this PR is merged - [ ] Post-merge workflow(s) (release & publish containers, etc) - [ ] Release order plan. @EricGustin suggests releasing in the following order: 1. `arcade-core` version 0.1.0 2. `arcade-serve` version 0.1.0 and `arcade-tdk` version 0.1.0 3. `arcade-ai` version 2.0.0 4. Patch release for all toolkits (all changes in toolkits are internal refactors) - [ ] [Update docs](https://github.com/ArcadeAI/docs/pull/318) --------- Co-authored-by: Eric Gustin <eric@arcade.dev> Co-authored-by: Eric Gustin <34000337+EricGustin@users.noreply.github.com> |
Renamed from arcade/arcade/sdk/eval/eval.py (Browse further)