feat(integrations): add native Pydantic AI support by shashi-stackone · Pull Request #184 · StackOneHQ/stackone-ai-python

shashi-stackone · 2026-04-24T13:58:02Z

Summary

This PR R adds native Pydantic AI support to the SDK, parallel to the existing .openai() and .langchain() integrations. Users can now convert StackOne tools to pydantic_ai.tools.Tool instances with a single method call.

Context

Pydantic AI is removing its in-tree third-party integration in v2 see #5150, and the upstream PR #5175 that would have shipped StackOne support inside pydantic_ai.ext.stackone was closed by a maintainer with the recommendation that third-party adapters should live in separate packages. This PR delivers that native integration from the SDK side.

Usage

pip install 'stackone-ai[pydantic-ai]'

New optional extra pydantic-ai-slim>=1.83.0,<2.0.0. Lazy import; zero impact if the extra isn't installed.

Usage

Filtered via fetch_tools(...):

from pydantic_ai import Agent                                                  
from stackone_ai import StackOneToolSet               

toolset = StackOneToolSet()
tools = toolset.fetch_tools(
   actions=["workday_list_workers"],                                          
   account_ids=[account_id],
).to_pydantic_ai()                                                             
                                                     
agent = Agent("openai:gpt-5.4", tools=tools)

Full catalog / meta-tools via the method on StackOneToolSet:

All tools for the account

tools = toolset.pydantic_ai(account_ids=[account_id]) 
                                                                               
# Agent-driven discovery (two meta-tools: tool_search + tool_execute)          
toolset = StackOneToolSet(                                                     
    search={"method": "semantic"},                                             
    execute={"account_ids": [account_id]},            
)                                                                              
tools = toolset.pydantic_ai(mode="search_and_execute")

Non-breaking : No existing signatures changed, no existing tests touched. Shape matches the .to_openai_function() / .to_openai() / .openai() trio already in the SDK.

Docs and Examples

There is separate PR for the docs that demonstrate the usage and examples updated with latest API

Summary by cubic

Adds native Pydantic AI support so StackOne tools can be used directly with Agent, parallel to .openai() and .langchain(). Opt‑in via stackone-ai[pydantic-ai]; non‑breaking.

New Features
- Convert tools to Pydantic AI with .to_pydantic_ai() on Tools and .to_pydantic_ai_tool() on individual tools.
- StackOneToolSet.pydantic_ai(mode=None|"search_and_execute", account_ids=...) for full catalogs or meta search/execute tools.
- Improved type hints for Pydantic conversions and clearer import error when the extra isn’t installed.
- README and example updated; tests added for schema parity, execution, and toolset wiring.
Dependencies
- New optional extra pydantic-ai installs pydantic-ai-slim>=1.83.0,<2.0.0.
- Lazy import; no impact unless the extra is installed.
- Install with: pip install 'stackone-ai[pydantic-ai]'

^{Written for commit facd1c3. Summary will update on new commits. Review in cubic}

Copilot

Pull request overview

Adds a first-party Pydantic AI integration to the stackone-ai SDK, mirroring existing .openai() / .langchain() patterns so StackOne tools can be used as pydantic_ai.tools.Tool instances.

Changes:

Introduces StackOneTool.to_pydantic_ai_tool() and Tools.to_pydantic_ai() conversions.
Adds StackOneToolSet.pydantic_ai() for fetching full tools or meta “search_and_execute” tools as Pydantic AI tools.
Adds a pydantic-ai optional extra, plus tests, example usage, and README documentation.

Reviewed changes

Copilot reviewed 6 out of 7 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
`stackone_ai/models.py`	Adds `to_pydantic_ai_tool()` on `StackOneTool` and `to_pydantic_ai()` on `Tools` with lazy imports.
`stackone_ai/toolset.py`	Adds `StackOneToolSet.pydantic_ai()` method parallel to `.openai()` / `.langchain()`.
`tests/test_integrations_pydantic_ai.py`	New test coverage for conversion helpers and toolset behavior (skips if dependency missing).
`pyproject.toml`	Adds `pydantic-ai` optional extra (installs `pydantic-ai-slim`).
`uv.lock`	Updates lockfile to include the new extra and dependency marker entries.
`examples/pydantic_ai_integration.py`	Updates example to use the new `.to_pydantic_ai()` helper and improved install instructions.
`README.md`	Documents the Pydantic AI integration and shows recommended usage.

Comments suppressed due to low confidence (1)

pyproject.toml:48

The optional dependency constraints are inconsistent: the new pydantic-ai extra pins pydantic-ai-slim>=1.83.0,<2.0.0, but the existing examples extra still depends on pydantic-ai>=1.83.0 with no <2.0.0 upper bound. This can lead to stackone-ai[examples] resolving to Pydantic AI v2 later and breaking the included example/tests. Consider either (a) switching examples to pydantic-ai-slim as well, or (b) adding a matching <2.0.0 upper bound to pydantic-ai in examples.

mcp = ["mcp>=1.3.0"]
pydantic-ai = ["pydantic-ai-slim>=1.83.0,<2.0.0"]
examples = [
  "crewai>=0.102.0",
  "langchain-openai>=1.1.14",
  "langgraph>=1.1.6",
  "openai>=2.32.0",
  "pydantic-ai>=1.83.0",
  "python-dotenv>=1.0.1",
]

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

cubic-dev-ai

No issues found across 7 files

_{Auto-approved: Additive integration for Pydantic AI following established SDK patterns. Features lazy-loaded optional dependencies and comprehensive tests with no impact on core functionality.}

cubic-dev-ai

0 issues found across 2 files (changes from recent commits).

_{Auto-approved: Adds native Pydantic AI integration following existing adapter patterns. The change is non-breaking, well-tested, and uses lazy imports for zero impact on existing users.}

shashi-stackone added 2 commits April 24, 2026 11:53

Add Native Pydantic AI Integration to StackOne SDK

332b0d1

Keep the implementation minimum for now

0acb757

Copilot AI review requested due to automatic review settings April 24, 2026 13:58

Copilot started reviewing on behalf of shashi-stackone April 24, 2026 13:58 View session

Copilot AI reviewed Apr 24, 2026

View reviewed changes

Comment thread stackone_ai/toolset.py Outdated

cubic-dev-ai Bot previously approved these changes Apr 24, 2026

View reviewed changes

Type chcking enhancements for pydantic tools

facd1c3

shashi-stackone dismissed cubic-dev-ai[bot]’s stale review via facd1c3 April 28, 2026 10:05

cubic-dev-ai Bot approved these changes Apr 28, 2026

View reviewed changes

shashi-stackone merged commit 8216ab6 into main Apr 30, 2026
16 checks passed

shashi-stackone deleted the pydantic-native branch April 30, 2026 11:00

github-actions Bot mentioned this pull request Apr 30, 2026

chore(main): release stackone-ai 2.9.0 #186

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(integrations): add native Pydantic AI support#184

feat(integrations): add native Pydantic AI support#184
shashi-stackone merged 3 commits into
mainfrom
pydantic-native

shashi-stackone commented Apr 24, 2026 •

edited by cubic-dev-ai Bot

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

cubic-dev-ai Bot left a comment

Uh oh!

cubic-dev-ai Bot left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

shashi-stackone commented Apr 24, 2026 • edited by cubic-dev-ai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Context

Usage

Usage

All tools for the account

Docs and Examples

Summary by cubic

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

cubic-dev-ai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

cubic-dev-ai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

shashi-stackone commented Apr 24, 2026 •

edited by cubic-dev-ai Bot

Loading