NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI, #633 most downloaded on PyPI
AI Agent Framework, the Pydantic way, slim package
Latest stable
2.66.0
Last release 14 days ago
04 Nov 2026
Ships on a steady schedule
a new release about every 9 days
Nearly every release is documented
notes for 60 of the last 60 stable releases
1 version withdrawn
withdrawn after publishing
2 years old
353 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
Enable URL and binary PDF for Mistral by @pintaf in https://github.com/pydantic/pydantic-ai/pull/2267
FileUrl.format to find the extension by @Kludex in https://github.com/pydantic/pydantic-ai/pull/2280CLAUDE.md by @Kludex in https://github.com/pydantic/pydantic-ai/pull/2281_estimate_string_tokens by @misrasaurabh1 in https://github.com/pydantic/pydantic-ai/pull/2156Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.4.5...v0.4.6
Add async with self in agent_to_a2a by @Kludex in https://github.com/pydantic/pydantic-ai/pull/2266
Your coding agent can read these notes before it upgrades. Set up the MCP server →
async with self in agent_to_a2a by @Kludex in https://github.com/pydantic/pydantic-ai/pull/2266format_as_xml defaults by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/2228Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.4.4...v0.4.5
Add Toolsets and Deferred Tools by @DouweM in https://github.com/pydantic/pydantic-ai/pull/2024
AgentRunResult._set_output_tool_return by 18798% by @misrasaurabh1 in https://github.com/pydantic/pydantic-ai/pull/2196Usage.opentelemetry_attributes by 85% by @misrasaurabh1 in https://github.com/pydantic/pydantic-ai/pull/2198Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.4.3...v0.4.4
Include content.1571 by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/2180
duckduckgo-search is renamed to ddgs by @basnijholt in https://github.com/pydantic/pydantic-ai/pull/2172tool_return_ta by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/2186Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.4.2...v0.4.3
Let model settings be passed to model classes by @svilupp in https://github.com/pydantic/pydantic-ai/pull/2136
settings be passed to model classes by @svilupp in https://github.com/pydantic/pydantic-ai/pull/2136StructuredDict for structured outputs with custom JSON schema by @fswair in https://github.com/pydantic/pydantic-ai/pull/2157Agent.iter() by @erosennin in https://github.com/pydantic/pydantic-ai/pull/2168_ensure_decodeable by 634% by @misrasaurabh1 in https://github.com/pydantic/pydantic-ai/pull/2155Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.4.1...v0.4.2
Support evaluating sync tasks by @dmontagu in https://github.com/pydantic/pydantic-ai/pull/2150
Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.4.0...v0.4.1
BREAKING CHANGE: Make EvaluationReport and ReportCase into generic dataclasses by @dmontagu in https://github.com/pydantic/pydantic-ai/pull/1799
EvaluationReport and ReportCase into generic dataclasses by @dmontagu in https://github.com/pydantic/pydantic-ai/pull/1799ToolDefinition.description optional and fix Bedrock description handling by @dmontagu in https://github.com/pydantic/pydantic-ai/pull/1507Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.3.7...v0.4.0
Raise consistent deprecation warnings by @Viicos in https://github.com/pydantic/pydantic-ai/pull/2148
AgentStream.stream_output (available inside agent.iter) stream validated output data instead of raising validation errors by @DouweM in https://github.com/pydantic/pydantic-ai/pull/2134model_request_stream_sync to direct API by @hewliyang in https://github.com/pydantic/pydantic-ai/pull/2116Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.3.6...v0.3.7
Deprecate {FunctionToolCallEvent,FunctionToolResultEvent}.call_id in favor of tool_call_id by @proever in https://github.com/pydantic/pydantic-ai/pull…
{FunctionToolCallEvent,FunctionToolResultEvent}.call_id in favor of tool_call_id by @proever in https://github.com/pydantic/pydantic-ai/pull/2028RetryPromptPart not tied to a tool call contains validation feedback rather than a user message by @hovi in https://github.com/pydantic/pydantic-ai/pull/2008Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.3.5...v0.3.6
Fix deprecation warning under Pydantic 2.11 by @medaminezghal in https://github.com/pydantic/pydantic-ai/pull/2076
GoogleProvider by @Kludex in https://github.com/pydantic/pydantic-ai/pull/2031ThinkingPart to preceed TextPart in OpenAIResponsesModel by @Kludex in https://github.com/pydantic/pydantic-ai/pull/2043Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.3.4...v0.3.5
Scrubbing sensitive content by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/2014
ThinkingPart back when using tool calls by @Kludex in https://github.com/pydantic/pydantic-ai/pull/2072Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.3.3...v0.3.4
Support NativeOutput and PromptedOutput modes in addition to ToolOutput by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1628
NativeOutput and PromptedOutput modes in addition to ToolOutput by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1628UserPromptNode by @Kludex in https://github.com/pydantic/pydantic-ai/pull/2052Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.3.2...v0.3.3
Support MCP sampling by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1884
Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.3.1...v0.3.2
Update Google models by @tacoo in https://github.com/pydantic/pydantic-ai/pull/2010
ThinkingPart when delta contains signature by @Kludex in https://github.com/pydantic/pydantic-ai/pull/2012Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.3.0...v0.3.1
See #1142 — Adds support for thinking parts.
See #1142 — Adds support for thinking parts.
We now convert the thinking blocks ("<think>..."</think>") in provider specific text parts to
PydanticAI ThinkingParts. Also, as part of this release, we made the choice to not send back the
ThinkingParts to the provider - the idea is to save costs on behalf of the user. In the future, we
intend to add a setting to customize this behavior.
Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.20...v0.3.0
Handle McpError from MCP tool calls by @ppcantidio in https://github.com/pydantic/pydantic-ai/pull/1999
McpError from MCP tool calls by @ppcantidio in https://github.com/pydantic/pydantic-ai/pull/1999process_tool_call hook to MCP servers to modify tool args, metadata, and return value by @stevenh in https://github.com/pydantic/pydantic-ai/pull/2000ModelSettings.timeout in GoogleModel by @DouweM in https://github.com/pydantic/pydantic-ai/pull/2006RunContext support to history processors by @Wh1isper in https://github.com/pydantic/pydantic-ai/pull/2002Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.19...v0.2.20
Proper check if callable is async by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1972
max_tokens to 4096 by default by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1994history_processors parameter to Agent for message processing by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1970Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.18...v0.2.19
Reuse last request from message history if no user prompt was provided by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1955
GoogleModel instead of GeminiModel on inference by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1881Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.17...v0.2.18
Add token usage metrics to InstrumentedModel by @alexmojaki in https://github.com/pydantic/pydantic-ai/pull/1898
InstrumentedModel by @alexmojaki in https://github.com/pydantic/pydantic-ai/pull/1898service_tier to OpenAIModelSettings by @empezarcero in https://github.com/pydantic/pydantic-ai/pull/1923httpx.AsyncClient in MCPServerHTTP by @mpfaffenberger in https://github.com/pydantic/pydantic-ai/pull/1925temperature and top_p to OpenAI reasoning models by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1956fileData (direct file URL) for GeminiModel and GoogleModel by @vricciardulli in https://github.com/pydantic/pydantic-ai/pull/1136Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.16...v0.2.17
Stop sharing tool retry count across all runs of the same agent by @dmontagu in https://github.com/pydantic/pydantic-ai/pull/1918
HerokuProvider by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1933stop_sequences to Google models by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1935Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.15...v0.2.16
Allow empty messages when using GoogleModel by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1922
GoogleModel by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1922Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.14...v0.2.15
Temporarily revert "Add support for MCP's Streamable HTTP transport (#1716)" by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1903
Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.13...v0.2.14
Make parallel_evaluation_example more robust by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1861
Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.12...v0.2.13
Add vendor_id and vendor_details.finish_reason to Gemini/Google model responses by @davide-andreoli in https://github.com/pydantic/pydantic-ai/pull/18
vendor_id and vendor_details.finish_reason to Gemini/Google model responses by @davide-andreoli in https://github.com/pydantic/pydantic-ai/pull/1800sse_read_timeout timedelta by @alexmojaki in https://github.com/pydantic/pydantic-ai/pull/1843output_type, as well as lists of functions and other types by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1785ModelProfile to let model-specific behaviors be configured independent of the model class by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1835Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.11...v0.2.12
Require mcp>=1.9.0 on the pydantic-ai-slim[mcp] extra by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1840
mcp>=1.9.0 on the pydantic-ai-slim[mcp] extra by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1840Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.10...v0.2.11
Update Google models by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1829
Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.9...v0.2.10
Cast non-textual responses in Agent.to_cli to str by @barp in https://github.com/pydantic/pydantic-ai/pull/1823
Agent.to_cli to str by @barp in https://github.com/pydantic/pydantic-ai/pull/1823labels for GeminiModel and GoogleModel on Vertex AI by @vricciardulli in https://github.com/pydantic/pydantic-ai/pull/1056Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.8...v0.2.9
Improve assertion on Anthropic by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1825
Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.7...v0.2.8
Support streaming tool calls from models that pass args as None when there are no function parameters by @DouweM in https://github.com/pydantic/pydant
n parameter from OpenAIModel requests by @kiqaps in https://github.com/pydantic/pydantic-ai/pull/1807tool_prefix option to MCP servers and error on conflicting tool names by @Wh1isper in https://github.com/pydantic/pydantic-ai/pull/1266RunContext to not be documented when require_parameter_descriptions=True as it's not passed to the model anyway by @Kevsnz in https://github.com/pydantic/pydantic-ai/pull/1750prog_name customizable by @fswair in https://github.com/pydantic/pydantic-ai/pull/1804AsyncBeta instead of AsyncAnthropic by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1818Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.6...v0.2.7
Add prepare_tools param to Agent class by @rmaceissoft in https://github.com/pydantic/pydantic-ai/pull/1474
prepare_tools param to Agent class by @rmaceissoft in https://github.com/pydantic/pydantic-ai/pull/1474GoogleModel by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1780prepare_tools to _prepare_tools by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1789Agent.to_cli() by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1791'openrouter' string to OpenAIModel provider param by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1792Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.5...v0.2.6
fasta2a: make capabilities required on AgentCard by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1733
capabilities required on AgentCard by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1733include_binary_content flag to InstrumentationSettings, rename OTel attribute key from content to binary_content for BinaryParts by @alexmojaki in https://github.com/pydantic/pydantic-ai/pull/1739vendor_id to the model response. by @peterHoburg in https://github.com/pydantic/pydantic-ai/pull/1547Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.4...v0.2.5
clai should not require OPENAI_API_KEY by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1724
clai should not require OPENAI_API_KEY by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1724Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.3...v0.2.4
cli: add current path to sys.path by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1703
sys.path by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1703include_metadata and include_expected_output by @lionpeloux in https://github.com/pydantic/pydantic-ai/pull/1700direct public API by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1599Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.2...v0.2.3
Add to_cli() method to Agent by @AndrewHannigan in https://github.com/pydantic/pydantic-ai/pull/1642
to_cli() method to Agent by @AndrewHannigan in https://github.com/pydantic/pydantic-ai/pull/1642Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.1...v0.2.2
Add AWS Profile Feature by @prescod in https://github.com/pydantic/pydantic-ai/pull/1634
~/.pydantic-ai by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1701BinaryContent information by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1603Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.2.0...v0.2.1
See #1647 — usage makes sense as part of ModelResponse, and could be really useful in "messages" (really a sequence of requests and response). In this
See #1647 — usage makes sense as part of ModelResponse, and could be really useful in "messages" (really a sequence of requests and response). In this PR:
usage to ModelResponse (field has a default factory of Usage() so it'll work to load data that doesn't have usage)Model.request to just ModelResponse instead of tuple[ModelResponse, Usage]ToolCallPartDelta.tool_call_id when known from previous delta by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1694Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.1.11...v0.2.0
Nothing published for this version
Switch CLI to clai by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1504
clai by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1504Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.1.10...v0.1.11
Allow setting temperature to 0 on BedrockConverseModel by @pandersen-uncharted in https://github.com/pydantic/pydantic-ai/pull/1631
temperature to 0 on BedrockConverseModel by @pandersen-uncharted in https://github.com/pydantic/pydantic-ai/pull/1631extra_headers to ModelSettings by @ramanan-ravi in https://github.com/pydantic/pydantic-ai/pull/1644thinking_config to GeminiModel by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1609Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.1.9...v0.1.10
Use the correct discriminator string in HandleResponseEvent by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1619
HandleResponseEvent by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1619base_url to Mistral Provider by @alibeyram in https://github.com/pydantic/pydantic-ai/pull/1617Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.1.8...v0.1.9
Support returning multi-modal content from tools by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1517
Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.1.7...v0.1.8
Allow multiple instructions and fix instruction concatenation in Agent by @HamzaFarhan in https://github.com/pydantic/pydantic-ai/pull/1591
use_attribute_docstrings=True by default on tools by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1605Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.1.6...v0.1.7
otel: send AudioUrl, VideoUrl, DocumentUrl and ImageUrl information by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1592
AudioUrl, VideoUrl, DocumentUrl and ImageUrl information by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1592Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.1.5...v0.1.6
Drop requests minimum version to 2.32.2 by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1588
requests minimum version to 2.32.2 by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1588Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.1.4...v0.1.5
Use report_case_name in span by @alexmojaki in https://github.com/pydantic/pydantic-ai/pull/1544
report_case_name in span by @alexmojaki in https://github.com/pydantic/pydantic-ai/pull/1544list type inside the Annotated on function_declarations field by @gitraffe in https://github.com/pydantic/pydantic-ai/pull/1570Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.1.3...v0.1.4
Return last text parts on empty message by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1408
prepare_env.py to Python file in mcp-run-python by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1461instructions by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1529extra_body to ModelSettings by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1538BinaryContent in message_history by @arde100 in https://github.com/pydantic/pydantic-ai/pull/1523Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.1.2...v0.1.3
Fix max length handling by @dmontagu in https://github.com/pydantic/pydantic-ai/pull/1510
BinaryContent by decoding base64 by @DouweM in https://github.com/pydantic/pydantic-ai/pull/1513StdioServerParameters.cwd param by @timesler in https://github.com/pydantic/pydantic-ai/pull/1514Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.1.1...v0.1.2
fix: Allow empty tool call args by @Wh1isper in https://github.com/pydantic/pydantic-ai/pull/1407
UserPromptNode by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1503additionalProperties by gemini by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1506Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.1.0...v0.1.1
BREAKING CHANGE: rename result -> output by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1248
BedrockConverseModel by @leandrodamascena in https://github.com/pydantic/pydantic-ai/pull/1435result -> output by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1248BedrockConverseModel): add additional configuration fields to Bedrock Runtime API by @leandrodamascena in https://github.com/pydantic/pydantic-ai/pull/1458gemini-2.5-pro-preview-03-25 model (paid version of gemini 2.5 pro) by @barapa in https://github.com/pydantic/pydantic-ai/pull/1473format_as_xml by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1484instructions parameter by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1360Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.0.55...v0.1.0
Allow empty user_prompt in run_stream by @lfloeer in https://github.com/pydantic/pydantic-ai/pull/1421
Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.0.54...v0.0.55
evals: error when opentelemetry-sdk is not installed by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1403
user_prompt optional by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1406stop_sequences to ModelSettings by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1419Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.0.53...v0.0.54
Improve some error messages by @dmontagu in https://github.com/pydantic/pydantic-ai/pull/1366
handle_stream.stream_output() in the CLI by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1376Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.0.52...v0.0.53
Add dependencies to evals by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1358
Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.0.51...v0.0.52
Match OpenAI models in strictness by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1356
mcp-run-python server to use deno by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1340Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.0.50...v0.0.51
Fix some issues with non-serializable inputs in evals by @dmontagu in https://github.com/pydantic/pydantic-ai/pull/1333
exclusiveMaximum/exclusiveMinimum from Gemini by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1341Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.0.49...v0.0.50
Add Gemini 2.5 pro and improve CLI by @samuelcolvin in https://github.com/pydantic/pydantic-ai/pull/1317
generate_summary and truncation to OpenAIResponsesModelSettings by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1328ImageUrl and DocumentUrl for Anthropic Models by @jnishiyama in https://github.com/pydantic/pydantic-ai/pull/1318Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.0.48...v0.0.49
Add OpenAI Responses API by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1256
Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.0.47...v0.0.48
Ensure model settings' prefixes are enforced by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1257
pydantic-evals package by @dmontagu in https://github.com/pydantic/pydantic-ai/pull/935PYTHONOPTIMIZE=1 by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1307Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.0.46...v0.0.47
Use different HTTP clients based on providers by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1242
headers, timeout, and sse_read_timeout to MCPServerHTTP by @JohnUiterwyk in https://github.com/pydantic/pydantic-ai/pull/1218get_running_loop instead of get_event_loop" by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1252Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.0.45...v0.0.46
Generate tool call id if not present by @Kludex in https://github.com/pydantic/pydantic-ai/pull/1229
user mapping in openai chat completion by @ovisek in https://github.com/pydantic/pydantic-ai/pull/1174Full Changelog: https://github.com/pydantic/pydantic-ai/compare/v0.0.44...v0.0.45
One column per month.