build(deps): bump pydantic-ai from 1.107.0 to 2.12.0 in /pydantic-ai

[dependabot]

Bumps pydantic-ai from 1.107.0 to 2.12.0.

Release notes

Sourced from pydantic-ai's releases.

v2.12.0 (2026-07-16)

What's Changed

🚀 Features

• Add Moonshot AI kimi-k3 model by @​dsfaccini in pydantic/pydantic-ai#6551
• Emit EnqueuedMessagesEvent when enqueued messages are delivered into the run by @​DouweM in pydantic/pydantic-ai#6256
• feat: add DeferredToolCallEvent and DeferredToolResultEvent to AgentStreamEvent by @​YHallouard in pydantic/pydantic-ai#5588

🐛 Bug Fixes

• Fix ToolReturnPart serialization to use field aliases so wire output matches return_schema by @​pydanty[bot] in pydantic/pydantic-ai#6543
• Fix tool binding for POSITIONAL_OR_KEYWORD params with *args by @​pydanty[bot] in pydantic/pydantic-ai#6541
• fix(mistral): defer streamed output emission when text ends mid-integer-token by @​Mukller in pydantic/pydantic-ai#6519
• Derive capability-contributed toolset id from the capability for durable execution by @​dsfaccini in pydantic/pydantic-ai#6408
• Fix GoogleModel per-Part media_resolution forwarding in vendor_metadata by @​pydanty[bot] in pydantic/pydantic-ai#6525

New Contributors

• @​Mukller made their first contribution in pydantic/pydantic-ai#6519
• @​YHallouard made their first contribution in pydantic/pydantic-ai#5588

Full Changelog: pydantic/pydantic-ai@v2.11.0...v2.12.0

v2.11.0 (2026-07-15)

What's Changed

🚀 Features

• feat: export HistoryProcessor and add actionable hints to usage-limit and tool-retry errors by @​DouweM in pydantic/pydantic-ai#6346

🐛 Bug Fixes

• Fix MistralStreamedResponse streamed number/integer validation to accept int-valued numbers and reject bools by @​pydanty[bot] in pydantic/pydantic-ai#6479
• fix(onboarding): suggest Agent('test') when provider credentials are missing by @​DouweM in pydantic/pydantic-ai#6342
• fix(anthropic): transform native output schema when reached via profile={"default_structured_output_mode": "native"} by @​dsfaccini in pydantic/pydantic-ai#6521
• Fix Bedrock profile={'default_structured_output_mode': 'native'} sending untransformed schema by @​dsfaccini in pydantic/pydantic-ai#6539

Full Changelog: pydantic/pydantic-ai@v2.10.0...v2.11.0

v2.10.0 (2026-07-14)

What's Changed

🚀 Features

• Make message_history provider-valid out of the box (repair tool-call/result pairing) by @​DouweM in pydantic/pydantic-ai#6319
• Add support for OpenAI background mode and handle Anthropic stop_reason=pause_turn by @​DouweM in pydantic/pydantic-ai#6303

🐛 Bug Fixes

• Fix has_values() returning True for all-zero usage details by @​sean-kim05 in pydantic/pydantic-ai#6466
• Fix RenamedToolset silently dropping a tool on a name collision by @​sean-kim05 in pydantic/pydantic-ai#6462
• Preserve invalid UTF-8 bytes in instrumentation serialization by @​alexmojaki in pydantic/pydantic-ai#6483
• Fix event-loop affinity in run_stream_sync by @​adtyavrdhn in pydantic/pydantic-ai#6454
• Attach xAI ToolCallPart to the preceding reasoning message by @​dsfaccini in pydantic/pydantic-ai#5924
• Filter unconfigured Anthropic native tool calls by @​hxaxd in pydantic/pydantic-ai#6463

... (truncated)

Changelog

Sourced from pydantic-ai's changelog.

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:

pip/uv-add "pydantic-ai==2.0.0b5"

... (truncated)

Commits

• b8b7858 Remove Groq models decommissioned after 2026-07-17 (`meta-llama/llama-4-scout...
• ed3b9af Fix GoogleModel per-Part media_resolution forwarding in vendor_metadata...
• 5a6a877 Derive capability-contributed toolset id from the capability for durable ex...
• 6cf92b9 test: assert prompt-cache prefix byte-stability across UI-adapter round-trips...
• a045f41 feat: add DeferredToolCallEvent and DeferredToolResultEvent to `AgentStre...
• 3484380 Emit EnqueuedMessagesEvent when enqueued messages are delivered into the ru...
• 0c90274 Use full issue/PR links in comments instead of #nnnn shorthand (#6548)
• 0f0b4c5 Add Moonshot AI kimi-k3 model (#6551)
• 2776927 fix(mistral): defer streamed output emission when text ends mid-integer-token...
• 0ae81f7 Make sentence-transformers CI coverage hermetic (#6545)
• Additional commits viewable in compare view

[mwbrooks]

There are breaking changes and related to #132 - we'll need to upgrade the app's implementation to support 2.0.0