build(deps): bump pydantic-ai from 1.107.0 to 2.17.0 in /pydantic-ai

[dependabot]

Bumps pydantic-ai from 1.107.0 to 2.17.0.

Release notes

Sourced from pydantic-ai's releases.

v2.17.0 (2026-07-23)

What's Changed

🚀 Features

• Make RequestUsage and RunUsage support arbitrary fields for upcoming genai-prices by @​alexmojaki in pydantic/pydantic-ai#6683
• Cache per-message OTel serialization to avoid O(n²) instrumentation cost by @​dsfaccini in pydantic/pydantic-ai#6635

🐛 Bug Fixes

• Fix ContentFilterError for real Model Armor response blocks (finishReason: MODEL_ARMOR) and record moderation wire-truth cassettes by @​dsfaccini in pydantic/pydantic-ai#6679

Full Changelog: pydantic/pydantic-ai@v2.16.0...v2.17.0

v2.16.0 (2026-07-22)

What's Changed

🚀 Features

• Add mistral_prompt_cache_key setting and pass parallel_tool_calls to the Mistral SDK by @​lionpeloux in pydantic/pydantic-ai#6654
• Add ToolFailed for model-visible failures without retries by @​adtyavrdhn in pydantic/pydantic-ai#5585
• Add optional run_id= to agent runs, durable wrappers, and UI adapters by @​grahamcracker1234 in pydantic/pydantic-ai#6615
• Hoist openai_moderation to OpenAIChatModelSettings and expose Chat Completions moderation results in provider_details by @​dsfaccini in pydantic/pydantic-ai#6658
• feat(google): add Model Armor support for Google Cloud via GoogleModelSettings by @​Alex-Resch in pydantic/pydantic-ai#5691
• Add gemini-3.6-flash and gemini-3.5-flash-lite models by @​dsfaccini in pydantic/pydantic-ai#6668

🐛 Bug Fixes

• Raise a consistent ctx.enqueue() error inside durable units across Temporal, DBOS, and Prefect by @​DouweM in pydantic/pydantic-ai#6666
• Preserve $ref sibling keywords when inlining $defs by @​lntutor in pydantic/pydantic-ai#6592
• Guard ctx.enqueue() from an event_stream_handler inside DBOS steps / Prefect tasks by @​DouweM in pydantic/pydantic-ai#6671
• Preserve failed tool outcomes across AG-UI message round trips by @​dsfaccini in pydantic/pydantic-ai#6659
• Fix tool retry counts across skipped steps by @​zcxGGmu in pydantic/pydantic-ai#6582

📦 Dependencies

• Bump pillow, pyasn1, and setuptools to resolve Dependabot alerts by @​hramezani in pydantic/pydantic-ai#6657

New Contributors

• @​AKSHITAK1040 made their first contribution in pydantic/pydantic-ai#6633
• @​grahamcracker1234 made their first contribution in pydantic/pydantic-ai#6615
• @​sergioperezcheco made their first contribution in pydantic/pydantic-ai#6585
• @​lntutor made their first contribution in pydantic/pydantic-ai#6592
• @​zcxGGmu made their first contribution in pydantic/pydantic-ai#6582

Full Changelog: pydantic/pydantic-ai@v2.15.0...v2.16.0

v2.15.0 (2026-07-21)

What's Changed

🚀 Features

• feat(openai): support explicit prompt caching for gpt-5.6 by @​Wh1isper in pydantic/pydantic-ai#6423
• Inline text-like files in MistralModel prompts by @​pulphix in pydantic/pydantic-ai#6556
• Support overriding the tool-retry budget at run/iter/override time by @​dsfaccini in pydantic/pydantic-ai#6072

... (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

• 801814a Cache per-message OTel serialization to avoid O(n²) instrumentation cost (#...
• c2b3e8b Normalize the non-deterministic Tasks completed output in the `ReduceFirstV...
• 4e3f8fd chore: use specific pyright: ignore rule codes and document `run_stream_syn...
• 4080ce0 docs(tests): pin recorded facts in test assertions, not cassettes (#6691)
• b3beece Add regression test for tool return answering a call across an intervening re...
• b6b9710 Fix ContentFilterError for real Model Armor response blocks (`finishReason:...
• c672b7b Make RequestUsage and RunUsage support arbitrary fields for upcoming gena...
• 61d751e ci: make bots.yml agent-config guard unconditional and TOCTOU-safe (#6680)
• 15aa534 Fix tool retry counts across skipped steps (#6582)
• 6162d19 Preserve failed tool outcomes across AG-UI message round trips (#6659)
• 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