v1.0.0b1 (2025-08-30)

What's Changed

• Drop support for Python 3.9 by @Kludex in #2725
• Add support for human-in-the-loop tool call approval by @DouweM in #2581
• Deprecate OpenAIModelProfile.openai_supports_sampling_settings by @Kludex in #2730
• Gracefully handle errors in evals by @dmontagu in #2295
• Include logfire with pydantic-ai package by @Kludex in #2683
• Remove errors when passing Retrying instead of RetryConfig to TenacityTransport by @DouweM in #2717
• Default InstrumentationSettings version to 2 by @alexmojaki in #2726
• Remove cases and averages from eval span by @DouweM in #2715
• Make many more dataclasses kw-only by @dmontagu in #2738

Full Changelog: v0.8.1...v1.0.0b1

v0.8.1 (2025-08-29)

What's Changed

• Add gen_ai.system_instructions attribute to agent run spans by @alexmojaki in #2699
• Bump temporalio to 1.16.0 by @DouweM in #2703
• Rename StreamedRunResult methods to be consistent with AgentStream by @DouweM in #2692
• Deprecate specifying a model name without a provider prefix, and the vertexai provider name by @DouweM in #2711
• Rename ModelResponse.provider_request_id to provider_response_id by @DouweM in #2710
• docs: Add message_history parameter documentation for CLI methods by @ryx2 in #2695

Full Changelog: v0.8.0...v0.8.1

v0.8.0 (2025-08-26)

What's Changed

• Add elicitation callback support to MCP servers by @yamanahlawat in #2373
• Add message_history parameter to agent.to_cli() by @ryx2 in #2674
• Properly deserialize complex tool arguments with Temporal by @DouweM in #2686
• Fix serialization / deserialization of FileUrl.media_type by @mwildehahn in #2677
• Handle missing token details in vLLM/OpenAI-compatible APIs by @DouweM in #2669
• Make AgentStreamEvent union of ModelResponseStreamEvent and HandleResponseEvent by @DouweM in #2689

Full Changelog: v0.7.6...v0.8.0

v0.7.6 (2025-08-26)

What's Changed

• Replace all_messages_events with pydantic_ai.all_messages for InstrumentationSettings(version=2) by @alexmojaki in #2658
• Fix inability to call response.raise_for_status in AsyncTenacityTransport by @dmontagu in #2668
• Deprecate OpenAIModel in favor of OpenAIChatModel by @Kludex in #2676
• anthropic: drop new lines on empty system prompt by @Kludex in #2678
• fix(bedrock): skip SystemPromptPart with empty content by @essamgouda97 in #2672
• BREAKING CHANGE: Fix tenacity implementation for improved retry behavior by @dmontagu in #2670
• Add Cerebras provider by @Kludex in #2643

New Contributors

• @essamgouda97 made their first contribution in #2672

Full Changelog: v0.7.5...v0.7.6

v0.7.5 (2025-08-25)

What's Changed

• Handle 'STOP' finish_reason in GeminiStreamedResponse by @ArneZsng in #2631
• Add price() method to ModelResponse by @Kludex in #2584
• Include thoughts tokens in output_tokens for Google models by @alexmojaki in #2634
• Add span_id and trace_id to EvaluationReport by @Kludex in #2627
• Allow proper type on AnthropicProvider when using Bedrock by @akoshel in #2490
• Use new OpenTelemetry GenAI chat span attribute conventions by @alexmojaki in #2349
• Ensure content is always set for assistant tool call messages for OpenAI. by @vimota in #2641

New Contributors

• @ArneZsng made their first contribution in #2631
• @akoshel made their first contribution in #2490
• @vimota made their first contribution in #2641

Full Changelog: v0.7.4...v0.7.5

v0.7.4 (2025-08-20)

What's Changed

• Fix bug with google model safety handling by @dmontagu in #2066
• Add takes_ctx arg to Tool.from_schema by @dedeswim in #2615
• feat: support Google's url_context builtin tool by @vinnymeller in #2604
• Add missing UrlContextTool into all by @Kludex in #2617
• Drop assertion on Google streaming by @Kludex in #2618

New Contributors

• @dedeswim made their first contribution in #2615
• @vinnymeller made their first contribution in #2604
• @ivo-1 made their first contribution in #2610

Full Changelog: v0.7.3...v0.7.4

v0.7.3 (2025-08-19)

What's Changed

• Deprecate Usage in favour of RequestUsage and RunUsage by @samuelcolvin in #2378
• Make FallbackModel accept string model names by @vikigenius in #2564
• Move system_prompt_role from OpenAIModel to OpenAIModelProfile by @Kludex in #2573
• Add /cp command to CLI to copy last response to clipboard by @07pepa in #2386
• Pin temporalio to 1.15.0 as plugins API is still experimental by @DouweM in #2582
• Use _provider.name instead of _system by @Kludex in #2596

New Contributors

• @vikigenius made their first contribution in #2564
• @07pepa made their first contribution in #2386
• @jscheel made their first contribution in #2576
• @cyonii made their first contribution in #2579

Full Changelog: v0.7.2...v0.7.3

v0.7.2 (2025-08-14)

What's Changed

• Let message history end on ModelResponse and execute pending tool calls by @DouweM in #2562
• Ignore leading whitespace when streaming from Qwen or DeepSeek by @DouweM in #2554
• Stop calling MCP server get_tools ahead of agent run span by @DouweM in #2545
• Remove anthropic-beta default header set in AnthropicModel by @jerry-reevo in #2544
• Add OllamaProvider by @DouweM in #2554
• Add profile and settings to HuggingfaceModel by @DouweM in #2554
• Ask model to try again if it produced a response without text or tool calls, only thinking by @ethanabrooks in #2556
• Forward max_uses parameter to Anthropic WebSearchTool by @eballesteros in #2561

New Contributors

• @ethanabrooks made their first contribution in #2556
• @eballesteros made their first contribution in #2561

Full Changelog: v0.7.1...v0.7.2

v0.7.1 (2025-08-13)

What's Changed

• Add new OpenAI GPT-5 models by @medaminezghal in #2503
• Add support for OpenAI verbosity parameter in Responses API by @ryx2 in #2493
• Add support for "openai-responses" model inference string by @Kludex in #2528
• Add UsageLimits.count_tokens_before_request using Gemini count_tokens API by @kauabh in #2137
• Fix FallbackModel to respect each model's model settings by @jerry-reevo in #2540

New Contributors

• @spike-spiegel-21 made their first contribution in #2529
• @ryx2 made their first contribution in #2493

Full Changelog: v0.7.0...v0.7.1

v0.7.0 (2025-08-12)

What's Changed

• Let Agent be run in a Temporal workflow by moving model requests, tool calls, and MCP to Temporal activities by @DouweM in #2225
• Let toolsets be built dynamically based on run context by @strawgate in #2366
• Add event_stream_handler to agent and run methods by @DouweM in #2458
• History processor replaces message history by @AlexEnrique in #2324
• Add AbstractAgent and WrapperAgent by @DouweM in #2458
• Add Agent.override(tools=...) by @DouweM in #2458
• Bump mcp-run-python by @Kludex in #2470
• Fix error when using GPT-5 with a temperature setting by @DouweM in #2483
• Fix KeyError when parsing video metadata without audio track in Google models by @jerry-heygen in #2507
• Make OpenAIResponsesModelSettings.openai_builtin_tools work again by @DouweM in #2520

New Contributors

• @AlexEnrique made their first contribution in #2324
• @jerry-heygen made their first contribution in #2507

Full Changelog: v0.6.2...v0.7.0