Chore(deps): update pydantic-ai-slim requirement from <2,>=1.96.1 to >=1.98.0,<2

[dependabot]

Updates the requirements on pydantic-ai-slim to permit the latest version.

Release notes

Sourced from pydantic-ai-slim's releases.

v1.98.0 (2026-05-18)

What's Changed

🚀 Features

• Add OpenAI Responses input token counting (OpenAIResponsesModel.count_tokens) by @​colesmcintosh in pydantic/pydantic-ai#3951
• Replace Agent tool_retries=/output_retries= with retries: int | AgentRetries by @​Kludex in pydantic/pydantic-ai#5500

🐛 Bug Fixes

• fix(mcp): Don't require fastmcp.server at runtime by @​Kymi808 in pydantic/pydantic-ai#5514

🆕 V2 Preparation

• Deprecate pydantic_ai.ext.aci (tool_from_aci and ACIToolset) by @​dsfaccini in pydantic/pydantic-ai#5510

New Contributors

• @​Kymi808 made their first contribution in pydantic/pydantic-ai#5514

Full Changelog: pydantic/pydantic-ai@v1.97.0...v1.98.0

Changelog

Sourced from pydantic-ai-slim's changelog.

Upgrade Guide

In September 2025, Pydantic AI reached V1, which means we're committed to API stability: we will not introduce changes that break your code until V2. For more information, review our Version Policy.

Breaking Changes

Here's a filtered list of the breaking changes for each version to help you upgrade Pydantic AI.

v1.0.1 (2025-09-05)

The following breaking change was accidentally left out of v1.0.0:

• See #2808 - Remove Python evaluator from pydantic_evals for security reasons

v1.0.0 (2025-09-04)

• See #2725 - Drop support for Python 3.9
• See #2738 - Make many dataclasses require keyword arguments
• See #2715 - Remove cases and averages attributes from pydantic_evals spans
• See #2798 - Change ModelRequest.parts and ModelResponse.parts types from list to Sequence
• See #2726 - Default InstrumentationSettings version to 2
• See #2717 - Remove errors when passing AsyncRetrying or Retrying object to AsyncTenacityTransport or TenacityTransport instead of RetryConfig

v0.x.x

Before V1, minor versions were used to introduce breaking changes:

v0.8.0 (2025-08-26)

See #2689 - AgentStreamEvent was expanded to be a union of ModelResponseStreamEvent and HandleResponseEvent, simplifying the event_stream_handler function signature. Existing code accepting AgentStreamEvent | HandleResponseEvent will continue to work.

v0.7.6 (2025-08-26)

The following breaking change was inadvertently released in a patch version rather than a minor version:

See #2670 - TenacityTransport and AsyncTenacityTransport now require the use of pydantic_ai.retries.RetryConfig (which is just a TypedDict containing the kwargs to tenacity.retry) instead of tenacity.Retrying or tenacity.AsyncRetrying.

v0.7.0 (2025-08-12)

See #2458 - pydantic_ai.models.StreamedResponse now yields a FinalResultEvent along with the existing PartStartEvent and PartDeltaEvent. If you're using pydantic_ai.direct.model_request_stream or pydantic_ai.direct.model_request_stream_sync, you may need to update your code to account for this.

See #2458 - pydantic_ai.models.Model.request_stream now receives a run_context argument. If you've implemented a custom Model subclass, you will need to account for this.

See #2458 - pydantic_ai.models.StreamedResponse now requires a model_request_parameters field and constructor argument. If you've implemented a custom Model subclass and implemented request_stream, you will need to account for this.

v0.6.0 (2025-08-06)

This release was meant to clean some old deprecated code, so we can get a step closer to V1.

See #2440 - The next method was removed from the Graph class. Use async with graph.iter(...) as run: run.next() instead.

... (truncated)

Commits

• 2f461ec Add OpenAI Responses input token counting (#3951)
• f458346 fix(mcp): Don't require fastmcp.server at runtime (#5514)
• 24c8cdc Replace Agent tool_retries=/output_retries= with `retries: int | AgentR...
• 8cc76d8 Deprecate pydantic_ai.ext.aci (tool_from_aci and ACIToolset) ahead of v...
• 206453a Deprecate Agent.to_a2a() and fasta2a optional dependency group; point use...
• e60a9aa v2 prep: rewrite docs/graph.md to use the builder API (#5465)
• 33ef15d Deprecate stream_responses() for stream_response(); new singular yields `...
• c68c12f Move pydantic_graph.beta API out of beta, deprecate old API (#5306)
• e6bc869 Add MCPToolset that uses fastmcp-slim[client], deprecate MCPServer* and...
• 890c07c Set ModelResponse.state to incomplete while response is still streaming (...
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[claude]

Code Review: Bump pydantic-ai-slim lower bound to >=1.98.0

Scope: Single-line change in requirements/base.txt, bumping the minimum version of pydantic-ai-slim from >=1.96.1 to >=1.98.0.

---

Critical Issue — Potential breaking change: output_retries= parameter

v1.98.0 ships a breaking API change: it replaces Agent's tool_retries= / output_retries= constructor parameters with a unified retries: int | AgentRetries parameter (upstream PR pydantic/pydantic-ai#5500).

The codebase currently passes output_retries=STRUCTURED_OUTPUT_RETRIES directly in two callsites:

opencontractserver/llms/agents/pydantic_ai_agents.py (~line 1723):

structured_agent = make_pydantic_ai_agent(
    ...
    output_retries=STRUCTURED_OUTPUT_RETRIES,   # <-- deprecated/removed in v1.98.0
)

make_pydantic_ai_agent forwards all **kwargs verbatim to PydanticAIAgent(...), so output_retries= reaches the constructor directly. If v1.98.0 removed the parameter, this will raise a TypeError at runtime on every structured extraction run, breaking the DataCell pipeline.

opencontractserver/tests/test_pydantic_ai_agents.py (~lines 1304, 1308, 1345, 1660):
Several test assertions check that output_retries is present in constructor kwargs. If the production code is migrated to the new retries= API, these tests must be updated — otherwise they will silently stop verifying the retry budget is actually applied.

opencontractserver/constants/llm.py (~line 13):
The docstring comment references `pydantic-ai's ``output_retries```. This will become stale and misleading if the migration proceeds.

Recommended action before merging:

1. Check whether output_retries= was removed or merely deprecated (with a warning) in v1.98.0.
2. If removed: migrate to retries=STRUCTURED_OUTPUT_RETRIES (confirming the semantics are equivalent for the structured-output use case).
3. Update test assertions and the llm.py constant docstring to reflect the new parameter name.
4. Run the test suite against v1.98.0 before merging.

---

Other v1.98.0 changes — no issues found

A search across the repository confirms the remaining v1.98.0 changes are safe:

• No imports of pydantic_ai.ext.aci, tool_from_aci, or ACIToolset (deprecated in this release).
• No usage of Agent.to_a2a() or fasta2a.
• The MCP test file does not import pydantic-ai's MCPServer* toolset classes.
• The fastmcp.server lazy-import fix and OpenAI token-counting update don't touch any APIs used here.

---

Positive observations

• The requirement comment is excellent — it documents the mistralai PyPI 404 incident, why pydantic-ai-slim is used over the meta-package, and points to issue Wrap PydanticAIAgent construction to fail loud on system_prompt regression #1451 for upper-bound decisions.
• The make_pydantic_ai_agent factory is a well-designed chokepoint: once the output_retries= → retries= migration is done, there's only one line to change.
• Keeping the upper bound at <2 is correct given pydantic-ai's active V2 preparation visible in this release.

---

Verdict

Do not merge as-is. Please verify whether output_retries= was removed or merely deprecated in v1.98.0, and if necessary migrate pydantic_ai_agents.py:~1723 plus the related test assertions before landing this bump. Merging without that check risks silently breaking structured extraction in production.

[dependabot]

Superseded by #1725.