[dependabot]

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

Release notes

Sourced from pydantic-ai-slim's releases.

v2.54.0 (2026-10-02)

What's Changed

⚠️ Compatibility Notes

• Handle draft-7 list-form items in JsonSchemaTransformer, TestModel and Mistral streamed output, and make TestModel accept boolean subschemas and cap prefixItems at maxItems by @​dsfaccini in pydantic/pydantic-ai#9560
• Fix ImageGeneration under FallbackModel and dataclasses.replace, and compare Embedder by identity by @​dsfaccini in pydantic/pydantic-ai#9477
• Refuse a second durable execution engine on an agent before either binds by @​DouweM in pydantic/pydantic-ai#9391
• Make wrap_* hooks enclose complete stage lifecycles by @​adtyavrdhn in pydantic/pydantic-ai#7053
• Re-raise model errors from Temporal model activities with their original type in workflow code by @​DouweM in pydantic/pydantic-ai#9580
• End the run when a BackgroundTools tool raises an unexpected exception, as a sequential tool does by @​DouweM in pydantic/pydantic-ai#9434
• Drop the SubAgents agent_folders default-change warning: since v2.52.0 (#9023) the agents folder is not loaded by default, so pass agent_folders='agents' to keep loading it by @​DouweM in pydantic/pydantic-ai#9424

🚀 Features

• Tint clai2 file diffs from the selected /theme palette by @​mpfaffenberger in pydantic/pydantic-ai#9648
• Make clai2 /update always install the newest build and restart into it, resuming the session by @​mpfaffenberger in pydantic/pydantic-ai#9659
• Disable RepoContext inventory by default by @​DouweM in pydantic/pydantic-ai#9382
• Give the CodeMode missing-return-schema warning its own CodeModeReturnSchemaWarning category by @​DouweM in pydantic/pydantic-ai#9423
• Add cancel_and_resume example: cancel and resume a streaming run by @​DouweM in pydantic/pydantic-ai#7012
• Reconnect dropped OpenAILiveModel sessions by forking a stored session or replaying the history by @​DouweM in pydantic/pydantic-ai#9401
• Default Pydantic AI-created HTTP clients to the OpenAI SDK's connection pool limits, and make create_async_httpx2_client() public by @​DouweM in pydantic/pydantic-ai#9600
• Use gpt-live-transcribe for OpenAI realtime's default input_transcription_model='auto' and list gpt-transcribe by @​DouweM in pydantic/pydantic-ai#9402
• Support WebSearchTool on OpenAI GPT-Live through its delegated backend by @​DouweM in pydantic/pydantic-ai#9049
• Add native to ExaSearch and YouSearch to prefer the model's native web search, and web_search_tool() for WebSearch(local=...) by @​DouweM in pydantic/pydantic-ai#9386
• Add a double-Esc conversation rewind menu to clai2 by @​mpfaffenberger in pydantic/pydantic-ai#9688
• Allow deleting unused models from the clai2 /model menu by @​mpfaffenberger in pydantic/pydantic-ai#9696

🐛 Bug Fixes

• Fail closed in the shell realpath fallback when readlink cannot read a symlink by @​dsfaccini in pydantic/pydantic-ai#9613
• Stop importing the undeclared sniffio package in pydantic-evals and pydantic-ai-harness by @​pydanty in pydantic/pydantic-ai#9620
• Fall back from ImageGenerationTool to the local tool on Gemini text models, and keep tool output when a native tool falls back locally on Gemini 2.5 by @​dsfaccini in pydantic/pydantic-ai#9551
• Nest worktrees under their repository in the clai2 resume sidebar by @​mpfaffenberger in pydantic/pydantic-ai#9667
• Remove the clai2 resume-directory confirmation by @​mpfaffenberger in pydantic/pydantic-ai#9682
• Report clai2 startup plugin failures through observability by @​mpfaffenberger in pydantic/pydantic-ai#9681
• Show file diffs in compact clai2 tool output by @​mpfaffenberger in pydantic/pydantic-ai#9687
• Treat a null finish_reason on a SnowflakeModel response like an empty one by @​DouweM in pydantic/pydantic-ai#9590
• Refuse a LocalFileStore root another user owns, and log ToolOutputLimits spill and summarize fallbacks by @​DouweM in pydantic/pydantic-ai#9020
• State when the ConversationSearch default-scope warning will be removed by @​DouweM in pydantic/pydantic-ai#9383
• Warn when read_only=True removes every hosted MCP tool by @​DouweM in pydantic/pydantic-ai#9387
• Pin the request that started the current run, not the first prompt of the conversation, in the TrajectoryJudge window by @​DouweM in pydantic/pydantic-ai#9425
• Identify the search_tools tool by its tool_kind instead of its name by @​DouweM in pydantic/pydantic-ai#9603
• Find the tool search tool in CodeMode by its tool_kind, so a prefixed search tool still gets its notes by @​DouweM in pydantic/pydantic-ai#9604
• Log LLMReminder generation failures instead of silently falling back to GoalReanchor text by @​DouweM in pydantic/pydantic-ai#9024
• Include function tools run after the final result in run_stream() usage by @​DouweM in pydantic/pydantic-ai#9694
• Build the same ModelResponse from streamed and complete GoogleModel responses, and add Gemini 3 web search sources by @​DouweM in pydantic/pydantic-ai#9594
• Recover run state with RunCancelled.from_cancellation() when a DBOS workflow is cancelled by @​DouweM in pydantic/pydantic-ai#9394
• Make custom setup_logfire callbacks replay-safe and add replay_safe to LogfirePlugin by @​DouweM in pydantic/pydantic-ai#9698
• Raise ModelAPIError for undecodable 200 response bodies from Anthropic, Bedrock, Groq, Hugging Face, Google, and OpenAI embeddings and images by @​DouweM in pydantic/pydantic-ai#9350
• Keep the run state recoverable when Ctrl-C interrupts run_sync() by @​DouweM in pydantic/pydantic-ai#9605
• Clamp OpenAI realtime barge-in truncation at the profile's audio_output_sample_rate by @​DouweM in pydantic/pydantic-ai#9399
• Load a capability once when load_capability is called twice for it in one response by @​DouweM in pydantic/pydantic-ai#9397
• Keep a first-position ToolAvailabilityDeltaPart announcement out of the standing system prompt by @​DouweM in pydantic/pydantic-ai#9413

... (truncated)

Changelog

Sourced from pydantic-ai-slim's changelog.

---

description: "Pydantic AI upgrade guide and changelog: the breaking changes in each release, how to install V2, and the recommended path to migrate your code from V1."

Upgrade Guide

In September 2025, Pydantic AI reached V1 and committed to API stability: no changes that break your code until V2. V2 is now available, collecting the breaking and behavior changes that stability guarantee didn't allow. This guide is the canonical place to learn what's in V2, how to install it, and how to upgrade; for the guarantees behind these version numbers, see the Version Policy.

Breaking Changes

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

v2.0.0 (2026-06-23)

The stable V2.0 release. There are no new breaking or behavior changes since the betas; the full breaking-change list and recommended upgrade path are in the v2.0.0b1 entry below. Install it with:

uv add pydantic-ai

v2.0.0b7 (2026-06-10)

The seventh V2 beta, forked from v1.107.0. There are no new V2 breaking or behavior changes since v2.0.0b6 below — everything in that entry applies unchanged — but this beta picks up the latest V1 release on top, which adds Claude Fable 5 / Mythos 5 model support and OpenRouter prompt caching (CachePoint), plus known_model_names() and Anthropic fixes; see the v1.107.0 release notes for the full list.

Install it the same way, pinning the exact pre-release version:

pip/uv-add "pydantic-ai==2.0.0b7"

For the full breaking-change list and the recommended upgrade path, see the v2.0.0b1 entry below; the only difference is that the latest V1 to upgrade through first is now v1.107.0.

v2.0.0b6 (2026-06-04)

The sixth V2 beta, forked from v1.106.0. There are no new V2 breaking or behavior changes since v2.0.0b5 below — everything in that entry applies unchanged — but this beta picks up the latest V1 release on top, which adds api_host/timeout configuration and base seed mapping for the xAI provider, plus streaming and data-URI handling fixes; see the v1.106.0 release notes for the full list.

Install it the same way, pinning the exact pre-release version:

pip/uv-add "pydantic-ai==2.0.0b6"

For the full breaking-change list and the recommended upgrade path, see the v2.0.0b1 entry below; the only difference is that the latest V1 to upgrade through first is now v1.106.0.

v2.0.0b5 (2026-06-02)

The fifth V2 beta, forked from v1.105.0. There are no new V2 breaking or behavior changes since v2.0.0b4 below — everything in that entry (including the prepare-callbacks change) still applies — but this beta picks up the latest V1 release on top, which adds on-demand (deferred-loading) capabilities and Grok 4.3 reasoning_effort support, plus GoogleModelSettings.google_cached_content and Temporal gateway/ fixes; see the v1.105.0 release notes for the full list.

Install it the same way, pinning the exact pre-release version:

... (truncated)

Commits

• 6695132 Hold pydantic-ai-harness to the 100% coverage gate and strict-no-cover, a...
• 1ec8ce4 Normalize CRLF in the rewind menu preview test so it passes on Rich 15 (#9722)
• c4cc8bc Exempt the arguments and text TestModel generates from the scope requiremen...
• bdffc6c Keep BubblewrapWorkspace commands from running code on the SSH host through...
• fcbbc00 Return the live token from PKCESignIn.token() when another clai2 session ...
• a5258ce Name tests/test_docs_navigation.py as the check for harness navigation entr...
• de0dab7 Propagate a native cancel that lands during a command timeout's stop (#9675)
• 47f5715 Preserve text and reasoning part boundaries in OpenAIChatModel streams (#8729)
• 3184a7d Preserve dependency extras in clai2 archive updates (#9690)
• ee1b888 Allow deleting unused models from the clai2 /model menu (#9696)
• 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)

[dependabot]

Superseded by #62.