[dependabot]

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

Release notes

Sourced from pydantic-ai's releases.

v2.61.0 (2026-10-23)

What's Changed

⚠️ Compatibility Notes

• Warn when a provider-specific thinking setting from a broader scope overrides thinking by @​dsfaccini in pydantic/pydantic-ai#10231
• Send the least thinking a model accepts for thinking=False on models that can't turn thinking off by @​DouweM in pydantic/pydantic-ai#11036
• Raise NotImplementedError for a file in a CohereModel tool return instead of dropping it by @​dsfaccini in pydantic/pydantic-ai#11114
• Keep concurrent workspace runs attached to their own Prefect environments by @​dsfaccini in pydantic/pydantic-ai#11160
• Keep bool and int inputs on separate Literal decision branches in pydantic_graph by @​dafyy321-pixel in pydantic/pydantic-ai#9091
• Deprecate google_multi_speaker on GoogleRealtimeModel, which no Gemini Live model supports by @​DouweM in pydantic/pydantic-ai#11064
• Accept async auth functions in the hosted MCP capabilities by @​mpfaffenberger in pydantic/pydantic-ai#10835
• Run the authoring checks in CapabilityStore.load_active and stop overwriting unreadable manifests by @​mpfaffenberger in pydantic/pydantic-ai#10731
• Keep the last valid authored capability on a failed re-author, share the CapabilityStore lock per directory, and let runs cancel authoring by @​mpfaffenberger in pydantic/pydantic-ai#10767
• Reject BrowserUse prohibited lists browser-use would match by exact hostname, and retry when redacted schema keys collide by @​mpfaffenberger in pydantic/pydantic-ai#10775
• Share one LocalStack container inside async with agent:, stop service-list bypasses and aws configure writes to ~/.aws, and cap aws_cli output by @​mpfaffenberger in pydantic/pydantic-ai#10828
• Make InputGuardrail redact the user's own prompt and close fail-open paths in guardrails by @​mpfaffenberger in pydantic/pydantic-ai#10841
• Keep CodeMode(dynamic_catalog=True) discoveries from rewriting the cached prompt by @​DouweM in pydantic/pydantic-ai#10906

🚀 Features

• Accept async auth functions in the hosted MCP capabilities by @​mpfaffenberger in pydantic/pydantic-ai#10835
• Add structured citations to TextPart by @​adtyavrdhn in pydantic/pydantic-ai#7434
• Normalize citations from Bedrock, OpenRouter, and xAI by @​adtyavrdhn in pydantic/pydantic-ai#7750
• Bound background and shell job logs with Shell.max_log_bytes by @​mpfaffenberger in pydantic/pydantic-ai#10712
• Replay citations in message history to the provider that produced them by @​adtyavrdhn in pydantic/pydantic-ai#7752
• Keep citations in the Vercel AI adapter by @​adtyavrdhn in pydantic/pydantic-ai#9639
• Add kimi-k3.1-pro and kimi-k3.1-pro-highspeed model names by @​dsfaccini in pydantic/pydantic-ai#11173
• Accept transport= in create_async_httpx2_client() and give the httpx2 retry transports its pool limits by @​DouweM in pydantic/pydantic-ai#11073
• Add RealtimeClientSecret.webrtc_url, which carries webrtcfilter=on on Azure OpenAI by @​DouweM in pydantic/pydantic-ai#11076
• Warn when a realtime session has capabilities that implement hooks it never calls by @​DouweM in pydantic/pydantic-ai#11094
• Add RealtimeModelProfile.supports_audio_output so text-only realtime models like Gemini's robotics streaming models default to text output by @​DouweM in pydantic/pydantic-ai#11102
• Make the durable engine extension surface public: operation types, ParameterTransports, DurableRunContext and run identity hooks by @​DouweM in pydantic/pydantic-ai#11088

🐛 Bug Fixes

• Keep streamed OpenRouter reasoning that arrives without reasoning_details by @​dsfaccini in pydantic/pydantic-ai#11104
• Raise a UserError instead of an AssertionError for an unconverted response SpeechPart in BedrockConverseModel by @​dsfaccini in pydantic/pydantic-ai#11107
• Raise NotImplementedError for a file in a CohereModel tool return instead of dropping it by @​dsfaccini in pydantic/pydantic-ai#11114
• Detect pydantic-ai-minted Gemini tool-call ids with TOOL_CALL_ID_PREFIX instead of a hardcoded 'pyd_ai_' by @​dsfaccini in pydantic/pydantic-ai#11109
• Keep bool and int inputs on separate Literal decision branches in pydantic_graph by @​dafyy321-pixel in pydantic/pydantic-ai#9091
• Support NativeOutput on every FireworksProvider model by @​pydanty in pydantic/pydantic-ai#10157
• Warn when a provider-specific thinking setting from a broader scope overrides thinking by @​dsfaccini in pydantic/pydantic-ai#10231
• Record the failed status on streamed XaiModel native tool return parts by @​dsfaccini in pydantic/pydantic-ai#11105
• Keep an OpenAIChatModel response with a non-standard finish_reason instead of raising UnexpectedModelBehavior by @​dsfaccini in pydantic/pydantic-ai#11119
• Make InputGuardrail redact the user's own prompt and close fail-open paths in guardrails by @​mpfaffenberger in pydantic/pydantic-ai#10841
• Run the authoring checks in CapabilityStore.load_active and stop overwriting unreadable manifests by @​mpfaffenberger in pydantic/pydantic-ai#10731
• Keep Linear(id=None) uncombined like GitHub(id=None) by @​mpfaffenberger in pydantic/pydantic-ai#10813
• Cancel the Exa runs a cancelled ExaAgent poll leaves behind, and stop retrying Exa errors the model can't fix by @​mpfaffenberger in pydantic/pydantic-ai#10840
• Keep dict key order in histories the step stores reload, so resumed runs keep the prompt cache by @​rscholz98 in pydantic/pydantic-ai#11137
• Start long quote-heavy Shell commands over SSHWorkspaceBackend, and return a command too long to start to the model by @​mpfaffenberger in pydantic/pydantic-ai#11004
• Name the operation in E2BSandbox probe timeouts and validate env and sandbox_timeout at construction by @​mpfaffenberger in pydantic/pydantic-ai#10811
• Rebuild the default ExaSearch and ExaAgent client on a new event loop, and build ExaAgent's once by @​mpfaffenberger in pydantic/pydantic-ai#10848
• Keep the last valid authored capability on a failed re-author, share the CapabilityStore lock per directory, and let runs cancel authoring by @​mpfaffenberger in pydantic/pydantic-ai#10767

... (truncated)

Changelog

Sourced from pydantic-ai'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.

Deprecations

Functionality deprecated in a V2 release keeps working until V3, and using it raises a PydanticAIDeprecationWarning naming its replacement. Resolving these as they appear is the smooth path to the next major, the same way resolving V1's warnings was the smooth path to this one.

Deprecated in V2, to be removed in V3

• [RetryPromptPart][pydantic_ai.messages.RetryPromptPart] is deprecated in favor of the two parts it conflated: a retry that answers a tool call is that call's own [ToolReturnPart][pydantic_ai.messages.ToolReturnPart] with outcome='retried', and one that answers no tool call is a [RetryFeedbackPart][pydantic_ai.messages.RetryFeedbackPart]. The old part reached the model as bare user text in the second case, which the model couldn't tell from something a person wrote (#6404, #7799). Pydantic AI no longer emits it, and constructing one warns.
  • What keeps working: a 'retry-prompt' part in a serialized history loads as whichever of the two it always meant, and an instance your own code holds, including one handed back through [DeferredToolResults][pydantic_ai.tools.DeferredToolResults], is translated the same way before it reaches a model. The direct helpers send it in that new shape too. Calling [Model.request()][pydantic_ai.models.Model.request] or [Model.count_tokens()][pydantic_ai.models.Model.count_tokens] yourself skips that translation but still works: a tool-bound one goes out as that call's retried result, and a tool-less one as the user text it always rendered as. [sanitize_messages][pydantic_ai.messages.sanitize_messages] keeps client-returned retry feedback: it translates a tool-less one into the RetryFeedbackPart it always meant, keeps a 'validation_error' or 'model_retry' part as sent (it reaches the model fenced, in the user voice), and demotes a 'no_output' part, the one cause rendered in the system voice, to that same fenced, attributed user text, since a client can forge it; pass strip_system_prompts=False to keep a 'no_output' part as sent.
  • What you need to change: isinstance(part, RetryPromptPart) no longer matches, so match the two parts above instead. Each records why the retry happened, and which attempt it is against which limit, in a [RetryInfo][pydantic_ai.messages.RetryInfo] on its retry field, which tool spans also carry as pydantic_ai.tool.retry.* attributes. [ToolRetryError.tool_retry][pydantic_ai.exceptions.ToolRetryError] holds one of those two parts, so read tool_name off it only after checking for a ToolReturnPart.
  • What the model now sees: a tool retry carries the serialized validation errors or the ModelRetry message, with no N validation errors: header and no Fix the errors and try again. suffix. One that answers no call arrives in the voice its cause calls for: validation errors and a ModelRetry message in the user voice, inside a <validation_errors> or <retry_feedback> fence behind one line saying the application, not the user, is speaking, and the framework's fixed request for usable output in the system voice. On providers without a native tool error channel, a retried tool call's validation errors go in the {"error": ...} wrapper as a JSON array rather than as a string holding one, and Anthropic and Bedrock get them as one text block. Client-returned retry feedback is kept by [sanitize_messages][pydantic_ai.messages.sanitize_messages] and the UI adapters rather than stripped, and a 'no_output' part among it goes out as fenced user text rather than in the system voice. Retries in a history stored before upgrading are rendered the new way too, since rendering happens when each request goes out, so a conversation's first request after upgrading misses the provider's prompt cache from its first retry onward, once. A [decision model][pydantic_ai.models.decision.DecisionModel] judges a retried tool call as that call's tool_return, where it had a retry entry. On ag-ui-protocol below 0.1.11, [AGUIAdapter.dump_messages][pydantic_ai.ui.ag_ui.AGUIAdapter.dump_messages] now also warns on a run that retried its own output. See Retries.
  • Vercel AI dumps keep a request's part order: [VercelAIAdapter.dump_messages][pydantic_ai.ui.vercel_ai.VercelAIAdapter.dump_messages] now writes a ModelRequest as one UIMessage per run of same-role parts, in the order they were authored, instead of putting every system part first. This applies with no retries at all: a request holding an enqueued SystemPromptPart after its UserPromptPart now dumps as a user message followed by a system message, and positional message ids shift with it. The request's metadata rides on its last user message, or its last message when it has none.

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:

... (truncated)

Commits

• dd82a00 List compatibility impact PRs under their change type in generated release ...
• 120891d Leave framework-owned __pydantic_ai__ metadata out of sanitize_messages o...
• 877d8a6 Make the durable engine extension surface public: operation types, `Parameter...
• 5a551b9 Attach a late GPT-Live WebRTC sideband that is no longer sent `session.starte...
• e817ef3 Add RealtimeModelProfile.supports_audio_output so text-only realtime models...
• 6523b9a Warn when a realtime session has capabilities that implement hooks it never c...
• 3e3a621 Add RealtimeClientSecret.webrtc_url, which carries webrtcfilter=on on Azu...
• 7ad0913 Support hang_up() for Azure OpenAI WebRTC calls (#11075)
• 2116207 Deprecate google_multi_speaker on GoogleRealtimeModel, which no Gemini Li...
• 1ce05aa Send the least thinking a model accepts for thinking=False on models that c...
• 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)