pydantic/pydantic-ai v2.62.0

v2.62.0 (2026-10-26)

on GitHub

What's Changed

⚠️ Compatibility Notes

• Change thinking effort mid-conversation via OpenAI configuration_update and Anthropic per-message output_config, recorded as ModelSettingsDeltaPart by @DouweM in #11111
• Add ModelRequestRejectedError, ModelAuthenticationError and ModelNotFoundError model error categories by @DouweM in #11081
• State loaded deferred capabilities' instructions in the system voice, append their changes, and show them to before_model_request by @DouweM in #11103
• Prefix hosted MCP capabilities' tool names with the service by default, configurable with tool_prefix by @DouweM in #10376
• Store the SummarizingCompaction summary as a CompactionPart instead of a system prompt, and send provider-less CompactionParts to every model by @DouweM in #10573
• Deliver realtime SystemPromptParts on each provider's operator channel with session.send() by @DouweM in #11379
• Preserve run identity when replaying Prefect capability operations by @dsfaccini in #11196
• Append changed MCP server instructions with on_change='append', and give an id-less URL MCPToolset its hostname as id by @DouweM in #10791
• Record Harness Memory snapshots in history once per changed run, so requests stay append-only by @DouweM in #10903
• Tell the realtime model a tool call failed on every provider, so it answers instead of going silent by @DouweM in #11086
• Reserve DBOS handler step positions during tool ctx.emit() by @dsfaccini in #11157
• Record GPT-Live speech as one SpeechPart instead of splitting it at each delegated tool call by @DouweM in #11187
• Deliver ctx.emit() events into the realtime session event stream by @DouweM in #11369
• Make realtime shared settings warn, raise or ignore like standard ModelSettings: forced tool_choice raises on Gemini Live, parallel_tool_calls=False warns by @DouweM in #11066
• Keep the prompt cache when changing thinking effort mid-conversation on OpenRouter, via its configuration_update system message by @DouweM in #11426
• Start GraphBuilder broadcast branches in .to() order instead of reversed, which can break replay of durable workflows paused across the upgrade by @DouweM in #11408
• Cache on_change='append' instruction blocks behind a second cache point after the static instructions by @DouweM in #11351
• Build Harness SystemReminders on request-scoped system prompts and deprecate cache_ttl by @DouweM in #9712
• Add CodeMode(monty_sandbox=...), which takes a remote Monty URL or a function that builds the pool, and deprecate monty_sandbox_url by @adtyavrdhn in #11141

🚀 Features

• Change thinking effort mid-conversation via OpenAI configuration_update and Anthropic per-message output_config, recorded as ModelSettingsDeltaPart by @DouweM in #11111
• Add ModelRequestRejectedError, ModelAuthenticationError and ModelNotFoundError model error categories by @DouweM in #11081
• Export conversation_id_from_run_id from pydantic_ai.durable_exec for third-party durability engines by @DouweM in #11338
• Run tool calls as Temporal child workflows via child_workflow tool metadata in TemporalDurability by @YHallouard in #7329
• Restrict tool_choice subsets with allowed_tools on OpenAI Chat Completions to preserve the prompt cache by @DouweM in #10396
• State loaded deferred capabilities' instructions in the system voice, append their changes, and show them to before_model_request by @DouweM in #11103
• Prefix hosted MCP capabilities' tool names with the service by default, configurable with tool_prefix by @DouweM in #10376
• Store the SummarizingCompaction summary as a CompactionPart instead of a system prompt, and send provider-less CompactionParts to every model by @DouweM in #10573
• Add tool_prefix to the MCP capability by @DouweM in #11364
• Let SubAgents run delegations as tasks the model can background, steer, answer and cancel, behind task_control by @mpfaffenberger in #10893
• Add Coder(task_control=) to turn on SubAgents task control by @mpfaffenberger in #11007
• Add StructuredContent user content, sent as its value to decision models by @DouweM in #10529
• Use the Pydantic AI Gateway's reported cost for RequestUsage.cost by @adtyavrdhn in #7337
• Let the model request a harness compaction at a natural break in the task with CompactOnRequest by @mpfaffenberger in #11422
• Deliver realtime SystemPromptParts on each provider's operator channel with session.send() by @DouweM in #11379
• Add AnthropicModel.compact_messages() for on-demand native compaction by @DouweM in #11432
• Add provider batch API support with a BatchModelRequests capability and a get_wrapper_model capability hook by @DouweM in #10672

🐛 Bug Fixes

• Break GraphRun iterator and ToolManager context reference cycles by @dsfaccini in #11158
• Preserve run identity when replaying Prefect capability operations by @dsfaccini in #11196
• Stop Agent.run_stream name inference from keeping deps alive until garbage collection by @dsfaccini in #11219
• Preserve Cohere response IDs in ModelResponse.provider_response_id by @dsfaccini in #11223
• Recognize deepseek-flash in DeepSeekProvider by @dsfaccini in #11249
• Close the whole AgentStream event stream when a consumer leaves node.stream() early by @adtyavrdhn in #11009
• Close inner event streams so a raising listener cancels in-flight tool calls by @Kludex in #8822
• Fix thinking=False on OpenRouter's anthropic/claude-sonnet-5.5, which can't turn reasoning off by @dsfaccini in #11261
• Append changed MCP server instructions with on_change='append', and give an id-less URL MCPToolset its hostname as id by @DouweM in #10791
• Keep a system prompt after the tool result it followed in AG-UI dump_messages() by @DouweM in #11188
• Cancel a suspended background job only once when a streamed continuation request fails by @DouweM in #11090
• Keep billed usage when a run stops before a continued response completes by @DouweM in #11068
• Classify Azure too_many_requests stream errors for FallbackModel by @pydanty in #11253
• Make google_proactive_audio work on the default Gemini provider with a separate v1alpha Live client by @DouweM in #11067
• Keep an empty response in place when AG-UI load_messages() reloads a dumped history by @DouweM in #11192
• Keep openai_previous_response_id chaining when a rewrite-mode instruction changes beside an on_change='append' block by @DouweM in #11331
• Record Harness Memory snapshots in history once per changed run, so requests stay append-only by @DouweM in #10903
• Tell the realtime model a tool call failed on every provider, so it answers instead of going silent by @DouweM in #11086
• Send the lowest effort for thinking=False on OpenRouter routes that make reasoning mandatory by @DouweM in #11347
• Reserve DBOS handler step positions during tool ctx.emit() by @dsfaccini in #11157
• Record GPT-Live speech as one SpeechPart instead of splitting it at each delegated tool call by @DouweM in #11187
• Keep history before a CompactionPart with an empty summary instead of treating it as a compaction boundary by @DouweM in #11368
• Replay local history into a fresh Gemini Live session when a reconnect has no resumption handle by @DouweM in #11074
• Inline tool schema definitions for Azure Grok deployments by @dsfaccini in #11155
• Fix AGUIAdapter.dump_messages injecting newlines between adjacent TextParts by @pydanty in #8660
• Keep a loaded deferred capability's instructions in a realtime session seeded with a standard run's history by @DouweM in #11387
• Split streamed AG-UI assistant messages at reasoning, compaction and preserved file parts, as AGUIAdapter.dump_messages does by @DouweM in #11391
• Give each UIMessage of a split request its own id in Vercel AI dump_messages() by @DouweM in #11193
• Let an explicit FileUrl media_type win over the downloaded Content-Type, and treat binary/octet-stream as unknown by @DouweM in #11407
• Deliver ctx.emit() events into the realtime session event stream by @DouweM in #11369
• Stop replaying a non-empty search_tools result as "No matching tools found" on Anthropic when its matches are no longer declared by @DouweM in #11411
• Show retry feedback in the SummarizingCompaction and RelevanceCompaction transcript by @DouweM in #11370
• Carry non-native thinking in a user turn for Claude on OpenAI-compatible providers via OpenAIChatModel and OpenAIResponsesModel by @DouweM in #11410
• Re-attach a dropped GPT-Live WebRTC sideband under the reconnect policy by @DouweM in #11070
• Make realtime shared settings warn, raise or ignore like standard ModelSettings: forced tool_choice raises on Gemini Live, parallel_tool_calls=False warns by @DouweM in #11066
• Preserve initial code in streamed code_interpreter_call events by @dsfaccini in #11166
• Keep ToolOutputLimits from reducing load_capability and search_tools returns, so loaded capabilities' tools unlock by @mpfaffenberger in #11446
• Keep the prompt cache when changing thinking effort mid-conversation on OpenRouter, via its configuration_update system message by @DouweM in #11426
• Start GraphBuilder broadcast branches in .to() order instead of reversed, which can break replay of durable workflows paused across the upgrade by @DouweM in #11408
• Keep the response that crosses a token or cost limit in capture_run_messages by @DouweM in #11413
• Cache on_change='append' instruction blocks behind a second cache point after the static instructions by @DouweM in #11351
• Keep ToolOutputLimits bands largest-first after combine, with the later band winning a shared threshold by @mpfaffenberger in #11453
• Forward nested ToolReturn.content from CodeMode run_code to the model instead of silently dropping it by @mpfaffenberger in #11456
• Preserve Gateway costs in Groq streams by @dsfaccini in #11473
• Count a ModelRetry raised after a BackgroundTools tool's step has ended toward max_retries by @mpfaffenberger in #11458
• Build Harness SystemReminders on request-scoped system prompts and deprecate cache_ttl by @DouweM in #9712
• Keep deferred capabilities loaded when SummarizingCompaction, SlidingWindowCompaction and RelevanceCompaction remove their load_capability exchange by @DouweM in #11394
• Strip the internal end-of-command marker from SSHWorkspaceBackend timeout and output-limit errors by @DouweM in #11479
• Report the same job from the harness Shell persistent shell tool after a durable (DBOS) replay by @mpfaffenberger in #11457

Full Changelog: v2.61.0...v2.62.0