Commit graph

7 commits

Author SHA1 Message Date
Francisco Or Something
dc4607daa4
feat(telemetry): add developer messages to tool error spans (#831)
## Summary
- Add shared span attributes for tool error diagnostics, including
developer-facing messages when present.
- Wire those attributes through MCP server, worker RunTool, and HTTP
CallTool spans while keeping default MCP response content public-only.
- Cover no-leak response behavior, non-recording spans, outputless
worker responses, and the shared attribute contract.

## Verification
- `uv run ruff format ...`
- `uv run ruff check ...`
- `uv run pytest -W ignore
libs/tests/arcade_mcp_server/test_debug_exposure_integration.py
libs/tests/core/test_log_extras.py
libs/tests/worker/test_worker_base.py`

Made with [Cursor](https://cursor.com)

<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> **Medium Risk**
> Adds new telemetry attributes that propagate tool error messages
(including optional developer_message) into active spans across MCP
server and worker execution paths; risk is mainly around potential
leakage of sensitive developer messages into tracing backends and
changes to observability contracts.
> 
> **Overview**
> Adds a shared
`arcade_core.log_extras.build_tool_error_span_attributes()` helper and
wires it into tool error paths so the current OpenTelemetry span is
annotated with stable `tool_error_*` attributes (including
`developer_message` when present).
> 
> MCP tool calls now record these span attributes on failure while
keeping default MCP response content sanitized, and `arcade-serve`
records the same attributes on both `RunTool` and HTTP `CallTool` spans
(handling `output=None`). Versions and dependency constraints are bumped
to consume the new core helper, with tests added/updated to lock the
span-attribute contract and verify behavior for non-recording spans and
no-leak responses.
> 
> <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit
33a53991d72140a662152f508dc53e9b769b9f07. Bugbot is set up for automated
code reviews on this repo. Configure
[here](https://www.cursor.com/dashboard/bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
2026-04-29 20:41:07 -03:00
Francisco Or Something
1492c80fc5
TOO-627: Improve error messages for agents and Datadog (#814)
## Summary

- Improve tool call error messages across 4 libraries (arcade-core,
arcade-tdk, arcade-mcp-server, arcade-serve) so agents can self-correct
and Datadog can facet on structured fields
- Guard empty error messages, enrich input validation errors with
field-level detail, fix `@tool` decorator fallback formatting, surface
`additional_prompt_content` in MCP responses, and add structured log
extras for Datadog
- Addresses the 3 worst error patterns: generic "Error in tool input
deserialization", bare `KeyError` values, and empty `FatalToolError`
messages

**Linear:** TOO-627
**Plan:** `docs/plans/2026-04-08-improve-error-messages-handoff.md`

## Tasks

- [ ] Task 1: Guard empty error messages (arcade-core)
- [ ] Task 2: Enrich input validation error messages (arcade-core)
- [ ] Task 3: Improve `@tool` decorator error fallback (arcade-tdk)
- [ ] Task 4: Fix MCP agent-facing error response (arcade-mcp-server)
- [ ] Task 5: Add structured log extras in BaseWorker (arcade-serve)
- [ ] Task 6: Add structured log extras in MCP server
(arcade-mcp-server)

## Test plan

- [ ] Each task has dedicated unit tests verifying the new behavior
- [ ] `make test` passes after all tasks
- [ ] `make check` (ruff + mypy) passes
- [ ] Verify the 3 worst error patterns now produce actionable messages

🤖 Generated with [Claude Code](https://claude.com/claude-code)

<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> **Medium Risk**
> Touches cross-library error formatting and logging behavior used in
production tool execution paths; while mostly additive/guardrails, it
changes agent-visible messages and Datadog log facets, which could
impact client expectations and alerting.
> 
> **Overview**
> Improves tool-call error handling across core/runtime, MCP transport,
worker transport, and the TDK to make agent-visible failures more
actionable while *reducing sensitive-data leakage*.
> 
> In `arcade-core`, empty error messages now get placeholders,
`ToolOutputFactory.fail*` defaults blank messages, and input validation
errors are rewritten as field-level summaries that intentionally omit
rejected values (avoiding Pydantic echo of secrets). The `@tool`
fallback in `arcade-tdk` no longer surfaces `str(exception)` to agents;
it returns exception *type-only* in `message` while preserving full
detail in `developer_message`.
> 
> Adds a shared `build_tool_error_log_extra` helper and updates
`arcade-serve` + `arcade-mcp-server` to emit consistent structured
WARNING logs (`error_*`, `tool_name`, optional toolkit/version) for
Datadog, while MCP error responses now append
`additional_prompt_content` and force `structuredContent=None` on
failures per spec. Includes extensive new tests and bumps package
versions (`arcade-core` 4.6.2, `arcade-tdk` 3.6.1, `arcade-mcp-server`
1.19.3, `arcade-serve` 3.2.3).
> 
> <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit
e5c7ebcaf56176cfbd8e6d1f2b6295352abd0ec0. Bugbot is set up for automated
code reviews on this repo. Configure
[here](https://www.cursor.com/dashboard/bugbot).</sup>
<!-- /CURSOR_SUMMARY -->

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-13 20:10:51 -03:00
jottakka
bcee0f556f
Left over fixes for Windows Papercut PR (#781)
<!-- CURSOR_SUMMARY -->
> [!NOTE]
> **Low Risk**
> Mostly CI/test and CLI output tweaks, plus a small refactor to reuse
existing subprocess termination logic; low risk with minor potential for
CI environment/version compatibility issues.
> 
> **Overview**
> Expands CI coverage by adding Python `3.13` and `3.14` to the GitHub
Actions matrices (main tests, install test, and no-auth CLI
integration), and removes a redundant editable install step in the
no-auth workflow.
> 
> Cleans up Windows subprocess handling by dropping
`arcade_cli.deploy._graceful_terminate` and calling the shared
`arcade_core.subprocess_utils.graceful_terminate_process` directly, with
corresponding test updates.
> 
> Improves `arcade new` scaffolding guidance by printing numbered “Next
steps” with explicit stdio/HTTP run options, and adds/updates CLI tests
to assert this output. Also bumps package version to `1.11.2` and
tightens pre-commit `ruff` excludes (no longer excluding `_scratch`).
> 
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
55c2ae106f13e5657acdbebf63e00d74c171181f. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
2026-02-26 13:24:15 -03:00
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>
2026-01-07 20:26:23 -03:00
Eric Gustin
7fb097f20f
Use monkeypatch for tests that use ARCADE_WORKER_SECRET (#694)
Reverts the updates to unit tests in
https://github.com/ArcadeAI/arcade-mcp/pull/691 and replaces with
monkeypatch. They inadvertently changed global process state during the
test run causing failure of post-merge and failure of PyPI publish. See
https://github.com/ArcadeAI/arcade-mcp/actions/runs/19651637906/job/56283833231
to see what failed
2025-11-24 17:22:17 -08:00
Eric Gustin
44660d18ce
Only serve worker endpoints if secret is set (#691)
Default to `ARCADE_WORKER_SECRET` being unset. This env var must be
explicitly set now. Once it is set, the `worker/` endpoints will be
served.
2025-11-24 14:39:14 -08:00
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.

![arcade-ai Monorepo
(2)](https://github.com/user-attachments/assets/25f102b0-bb87-4a04-9701-d227d05664b1)

### 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>
2025-06-11 16:48:17 -07:00
Renamed from arcade/tests/worker/test_worker_base.py (Browse further)