arcade-mcp/toolkits/salesforce/evals/eval_get_account_data.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

222 lines
6.2 KiB
Python

from arcade_evals import (
BinaryCritic,
EvalRubric,
EvalSuite,
ExpectedToolCall,
tool_eval,
)
from arcade_tdk import ToolCatalog
import arcade_salesforce
from arcade_salesforce.tools import get_account_data_by_id, get_account_data_by_keywords
# Evaluation rubric
rubric = EvalRubric(
fail_threshold=0.85,
warn_threshold=0.95,
)
catalog = ToolCatalog()
catalog.add_module(arcade_salesforce)
@tool_eval()
def get_account_data_by_keywords_eval_suite() -> EvalSuite:
suite = EvalSuite(
name="get_account_data_by_keywords",
system_message=(
"You are an AI assistant with access to Salesforce tools. "
"Use them to help the user with their tasks."
),
catalog=catalog,
rubric=rubric,
)
suite.add_case(
name="Get account data by keywords",
user_message="Get information about the Acme account.",
expected_tool_calls=[
ExpectedToolCall(
func=get_account_data_by_keywords,
args={
"query": "Acme",
"page": 1,
},
),
],
rubric=rubric,
critics=[
BinaryCritic(critic_field="query", weight=0.5),
BinaryCritic(critic_field="page", weight=0.5),
],
)
suite.add_case(
name="Get account data by keywords with limit",
user_message="Get information of up to 3 accounts with the word 'Acme' in their name.",
expected_tool_calls=[
ExpectedToolCall(
func=get_account_data_by_keywords,
args={
"query": "Acme",
"limit": 3,
"page": 1,
},
),
],
rubric=rubric,
critics=[
BinaryCritic(critic_field="query", weight=1 / 3),
BinaryCritic(critic_field="limit", weight=1 / 3),
BinaryCritic(critic_field="page", weight=1 / 3),
],
)
suite.add_case(
name="Get summary of account activity",
user_message="Get a summary of the latest activities in the Acme account.",
expected_tool_calls=[
ExpectedToolCall(
func=get_account_data_by_keywords,
args={
"query": "Acme",
"page": 1,
},
),
],
rubric=rubric,
critics=[
BinaryCritic(critic_field="query", weight=0.5),
BinaryCritic(critic_field="page", weight=0.5),
],
)
suite.add_case(
name="Interactions with contacts of an account",
user_message="Get me the interactions with the contacts of the Acme account.",
expected_tool_calls=[
ExpectedToolCall(
func=get_account_data_by_keywords,
args={
"query": "Acme",
"page": 1,
},
),
],
rubric=rubric,
critics=[
BinaryCritic(critic_field="query", weight=0.5),
BinaryCritic(critic_field="page", weight=0.5),
],
)
suite.add_case(
name="Emails or calls with contacts of an account",
user_message="Were there any emails or calls with contacts of the Acme account this week?",
expected_tool_calls=[
ExpectedToolCall(
func=get_account_data_by_keywords,
args={
"query": "Acme",
"page": 1,
},
),
],
rubric=rubric,
critics=[
BinaryCritic(critic_field="query", weight=0.5),
BinaryCritic(critic_field="page", weight=0.5),
],
)
suite.add_case(
name="Get account status",
user_message="What's the status of the Acme account?",
expected_tool_calls=[
ExpectedToolCall(
func=get_account_data_by_keywords,
args={
"query": "Acme",
"page": 1,
},
),
],
rubric=rubric,
critics=[
BinaryCritic(critic_field="query", weight=0.5),
BinaryCritic(critic_field="page", weight=0.5),
],
)
suite.add_case(
name="Get overdue tasks",
user_message="Are there any tasks overdue for the Acme account?",
expected_tool_calls=[
ExpectedToolCall(
func=get_account_data_by_keywords,
args={
"query": "Acme",
"page": 1,
},
),
],
rubric=rubric,
critics=[
BinaryCritic(critic_field="query", weight=0.5),
BinaryCritic(critic_field="page", weight=0.5),
],
)
suite.add_case(
name="Get account closing likelihood",
user_message="What's the likelihood of the Acme account closing a deal?",
expected_tool_calls=[
ExpectedToolCall(
func=get_account_data_by_keywords,
args={
"query": "Acme",
"page": 1,
},
),
],
rubric=rubric,
critics=[
BinaryCritic(critic_field="query", weight=0.5),
BinaryCritic(critic_field="page", weight=0.5),
],
)
return suite
@tool_eval()
def get_account_data_by_id_eval_suite() -> EvalSuite:
suite = EvalSuite(
name="get_account_data_by_id",
system_message=(
"You are an AI assistant with access to Salesforce tools. "
"Use them to help the user with their tasks."
),
catalog=catalog,
rubric=rubric,
)
suite.add_case(
name="Get account data by ID",
user_message="Get information about the account with ID 001gK000003DIn0QAG.",
expected_tool_calls=[
ExpectedToolCall(
func=get_account_data_by_id,
args={
"account_id": "001gK000003DIn0QAG",
},
),
],
rubric=rubric,
critics=[
BinaryCritic(critic_field="account_id", weight=1.0),
],
)
return suite