arcade-mcp/toolkits/microsoft/evals/outlook_mail/eval_send.py
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

127 lines
4.5 KiB
Python

from arcade_evals import (
BinaryCritic,
EvalRubric,
EvalSuite,
ExpectedToolCall,
SimilarityCritic,
tool_eval,
)
from arcade_tdk import ToolCatalog
from arcade_microsoft.outlook_mail import (
create_and_send_email,
reply_to_email,
send_draft_email,
)
from arcade_microsoft.outlook_mail.enums import ReplyType
from evals.outlook_mail.additional_messages import (
list_emails_with_pagination_token_additional_messages,
)
# Evaluation rubric
rubric = EvalRubric(
fail_threshold=0.9,
warn_threshold=0.95,
)
catalog = ToolCatalog()
catalog.add_tool(create_and_send_email, "Microsoft")
catalog.add_tool(send_draft_email, "Microsoft")
catalog.add_tool(reply_to_email, "Microsoft")
@tool_eval()
def outlook_mail_send_eval_suite() -> EvalSuite:
"""Create an evaluation suite for Outlook Mail tools."""
suite = EvalSuite(
name="Outlook Mail Send Evaluation",
system_message=("You are an AI that has access to tools to send, read, and write emails."),
catalog=catalog,
rubric=rubric,
)
suite.add_case(
name="Create draft email",
user_message=(
"send an email to j@arcade.dev and e@arcade.dev. Title it 'Hello friends' and have it "
"say 'I've gathered you all here to celebrate the launch of the new Arcade platform.'"
),
expected_tool_calls=[
ExpectedToolCall(
func=create_and_send_email,
args={
"subject": "Hello friends",
"body": "I've gathered you all here to celebrate the launch of the new Arcade platform.", # noqa: E501
"to_recipients": ["j@arcade.dev", "e@arcade.dev"],
},
)
],
critics=[
SimilarityCritic(critic_field="subject", weight=0.3),
SimilarityCritic(critic_field="body", weight=0.3),
BinaryCritic(critic_field="to_recipients", weight=0.4),
],
)
suite.add_case(
name="Update draft email",
user_message=(
"forward the draft AQMkADAwATM0MDAAMi04Y2Y1LTQ3MTEALTAwAi0wMAoARgAAAyXxSd3UxTpCkDpGouEg0JMHAFuxokOLZRtDncM4_x_WeUwAAAIBDwAAAFuxokOLZRtDncM4_x_WeUwAAAAC-dpvAAAA " # noqa: E501
),
expected_tool_calls=[
ExpectedToolCall(
func=send_draft_email,
args={
"message_id": "AQMkADAwATM0MDAAMi04Y2Y1LTQ3MTEALTAwAi0wMAoARgAAAyXxSd3UxTpCkDpGouEg0JMHAFuxokOLZRtDncM4_x_WeUwAAAIBDwAAAFuxokOLZRtDncM4_x_WeUwAAAAC-dpvAAAA", # noqa: E501
},
)
],
critics=[
BinaryCritic(critic_field="message_id", weight=1),
],
)
suite.add_case(
name="Reply all to email",
user_message=("Reply to everyone - 'sounds good to me'"),
expected_tool_calls=[
ExpectedToolCall(
func=reply_to_email,
args={
"message_id": "AQMkADAwATM0MDAAMi04Y2Y1LTQ3MTEALTAwAi0wMAoARgAAAyXxSd3UxTpCkDpGouEg0JMHAFuxokOLZRtDncM4_x_WeUwAAAIBDAAAAFuxokOLZRtDncM4_x_WeUwAAAABc_ezAAAA", # noqa: E501
"body": "sounds good to me",
"reply_type": ReplyType.REPLY_ALL,
},
)
],
critics=[
BinaryCritic(critic_field="message_id", weight=1 / 3),
SimilarityCritic(critic_field="body", weight=1 / 3),
BinaryCritic(critic_field="reply_type", weight=1 / 3),
],
additional_messages=list_emails_with_pagination_token_additional_messages,
)
suite.add_case(
name="Reply to email",
user_message=("Reply to the account security team - 'sounds good to me'"),
expected_tool_calls=[
ExpectedToolCall(
func=reply_to_email,
args={
"message_id": "AQMkADAwATM0MDAAMi04Y2Y1LTQ3MTEALTAwAi0wMAoARgAAAyXxSd3UxTpCkDpGouEg0JMHAFuxokOLZRtDncM4_x_WeUwAAAIBDAAAAFuxokOLZRtDncM4_x_WeUwAAAABc_ezAAAA", # noqa: E501
"body": "sounds good to me",
"reply_type": ReplyType.REPLY,
},
)
],
critics=[
BinaryCritic(critic_field="message_id", weight=1 / 3),
SimilarityCritic(critic_field="body", weight=1 / 3),
BinaryCritic(critic_field="reply_type", weight=1 / 3),
],
additional_messages=list_emails_with_pagination_token_additional_messages,
)
return suite