Upgrade Guide
PydanticAI is still pre-version 1, so breaking changes will occur, however:
- We try to minimize them as much as possible.
- We use minor version bumps to signify breaking changes.
- Wherever possible we deprecate old features so code continues to work with deprecation warnings when changing the public API.
- We intend to release V1 in summer 2025, and then follow strict semantic versioning, e.g. no intentional breaking changes except in minor or patch versions.
Breaking Changes
Note
Here's a filtered list of the breaking changes for each version to help you upgrade PydanticAI.
v0.3.0 (2025-06-18)
See #1142 — Adds support for thinking parts.
We now convert the thinking blocks ("<think>..."</think>") in provider specific text parts to
PydanticAI ThinkingParts. Also, as part of this release, we made the choice to not send back the
ThinkingParts to the provider - the idea is to save costs on behalf of the user. In the future, we
intend to add a setting to customize this behavior.
v0.2.0 (2025-05-12)
See #1647 — usage makes sense as part of ModelResponse, and could be really useful in "messages" (really a sequence of requests and response). In this PR:
- Adds
usagetoModelResponse(field has a default factory ofUsage()so it'll work to load data that doesn't have usage) - changes the return type of
Model.requestto justModelResponseinstead oftuple[ModelResponse, Usage]
v0.1.0 (2025-04-15)
See #1248 — the attribute/parameter name result was renamed to output in many places. Hopefully all changes keep a deprecated attribute or parameter with the old name, so you should get many deprecation warnings.
See #1484 — format_as_xml was moved and made available to import from the package root, e.g. from pydantic_ai import format_as_xml.