-
Notifications
You must be signed in to change notification settings - Fork 965
Insights: pydantic/pydantic-ai
Overview
Could not load contribution data
Please try again later
3 Releases published by 2 people
-
v0.3.1 v0.3.1 (2025-06-18)
published
Jun 18, 2025 -
v0.3.2 v0.3.2 (2025-06-21)
published
Jun 21, 2025 -
v0.3.3 v0.3.3 (2025-06-24)
published
Jun 24, 2025
14 Pull requests merged by 8 people
-
Support
NativeOutputandPromptedOutputmodes in addition toToolOutput#1628 merged
Jun 24, 2025 -
Make Edge hashable
#2064 merged
Jun 24, 2025 -
note on self-hosting logfire
#2063 merged
Jun 24, 2025 -
document alternative otel backends
#2062 merged
Jun 24, 2025 -
Fix: Handled and pretty-printed exceptions without exiting the CLI.
#2055 merged
Jun 23, 2025 -
Include additional usage fields from OpenAI-compatible APIs in usage details
#2038 merged
Jun 23, 2025 -
docs: add API reference to
UserPromptNode#2052 merged
Jun 23, 2025 -
Improve Dynamic Instructions Documentation
#1819 merged
Jun 23, 2025 -
Adding docs for MCP sampling
#2027 merged
Jun 20, 2025 -
uprev
pytest-pretty#2030 merged
Jun 19, 2025 -
codespell fix
#2029 merged
Jun 19, 2025 -
Support MCP sampling
#1884 merged
Jun 19, 2025 -
fix: update
ThinkingPartwhen delta containssignature#2012 merged
Jun 18, 2025 -
docs: Update client.md
#2013 merged
Jun 18, 2025
13 Pull requests opened by 10 people
-
Scrubbing sensitive content
#2014 opened
Jun 18, 2025 -
Close #2021: correctly raise UsageLimitExceeded for google
#2022 opened
Jun 18, 2025 -
Toolsets
#2024 opened
Jun 19, 2025 -
deprecate call_id in favor of tool_call_id
#2028 opened
Jun 19, 2025 -
Set 'us-central1' by default on `GoogleProvider`
#2031 opened
Jun 19, 2025 -
Add `to_chat_completions` method
#2041 opened
Jun 20, 2025 -
Move `ThinkingPart` to preceed `TextPart` in `OpenAIResponsesModel`
#2043 opened
Jun 20, 2025 -
feat: AG-UI adapter
#2044 opened
Jun 20, 2025 -
Fix deprecated kwargs validation to prevent silent failures
#2047 opened
Jun 21, 2025 -
feat: add '/cp' command to copy last response to clipboard
#2049 opened
Jun 21, 2025 -
Improve docs index and README
#2058 opened
Jun 23, 2025 -
feat: add ToolReturn for customizable tool return
#2060 opened
Jun 24, 2025 -
Fix bug with google model safety handling
#2066 opened
Jun 24, 2025
19 Issues closed by 12 people
-
Structured outputs as an alternative to Tool Calling
#582 closed
Jun 24, 2025 -
Is it possible to change result_type of agent in a tool ?
#2061 closed
Jun 24, 2025 -
(openai.APITimeoutError) OpenAI requests time out, but Gemini/Anthropic requests work fine
#774 closed
Jun 24, 2025 -
Can't reproduce Annotated mermaid figure
#2046 closed
Jun 24, 2025 -
How to see a full LLM request body?
#2045 closed
Jun 24, 2025 -
Handle unhandled exceptions gracefully in CLI
#1959 closed
Jun 23, 2025 -
Retrieving log probabilities from token outputs
#2056 closed
Jun 23, 2025 -
How to insert nodes in iter
#2051 closed
Jun 23, 2025 -
Missing documentation for `UserPromptNode` et. al.
#1964 closed
Jun 23, 2025 -
Append "BinaryContent" to the prompt in an @agent.tool context ?
#1921 closed
Jun 23, 2025 -
Patter for using a provided httpx client instead of the default cached one
#2035 closed
Jun 20, 2025 -
Modifying AgentDeps using tools
#2036 closed
Jun 20, 2025 -
OpenAI Reasoning Models output no thinking parts
#2039 closed
Jun 20, 2025 -
Error in streaming output from connecting to the MCP server
#1860 closed
Jun 19, 2025 -
struggling with concurrent Gemini calls - seems to be auth race conditions
#2026 closed
Jun 19, 2025 -
Multi-turn user prompting
#2019 closed
Jun 19, 2025 -
More straightforward agent delegation
#2020 closed
Jun 18, 2025 -
Fix `ThinkingPartDelta.apply(ThinkingPart)` not updating `ThinkingPart.signature`
#2011 closed
Jun 18, 2025 -
Azure Provider requires environment variables
#1982 closed
Jun 18, 2025
18 Issues opened by 18 people
-
Tests errors when using pytest>=8.4.0
#2065 opened
Jun 24, 2025 -
Feature Request: mcp-run-python support streamable http
#2059 opened
Jun 24, 2025 -
Need custom endpoint support for Bedrock
#2057 opened
Jun 23, 2025 -
Feature Request: Repeated Evaluations in Evaluation Report
#2053 opened
Jun 23, 2025 -
Messages passed to history_processor functions include current run messages
#2050 opened
Jun 21, 2025 -
Make output_type be conditionally available
#2042 opened
Jun 20, 2025 -
Anthropic extended thinking: invalid request error when using tools
#2040 opened
Jun 20, 2025 -
How to store 'artifacts' with tool responses?
#2034 opened
Jun 19, 2025 -
Missing Support for Llama 3.3/4 Pythonic Tool Calling Format
#2033 opened
Jun 19, 2025 -
GoogleModel generates empty text parts that Vertex AI rejects with 400 error
#2032 opened
Jun 19, 2025 -
google-vertex provider now uses google-genai but fails due to no default location
#2023 opened
Jun 18, 2025 -
Incorrect exception type returned for gemini when token limit is exceeded
#2021 opened
Jun 18, 2025 -
Filter thoughts from responses for Gemini Models
#2018 opened
Jun 18, 2025 -
Add media processing settings to GoogleModelSettings
#2017 opened
Jun 18, 2025 -
Remove deprecated preview models from LatestGeminiModelNames
#2016 opened
Jun 18, 2025 -
Test using qwen2.5-14b, program freezes when setting agent parameter outputting type=UserProfile
#2015 opened
Jun 18, 2025
30 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
Add `builtin_tools` to `Agent`
#1722 commented on
Jun 20, 2025 • 7 new comments -
Retry prompt model response template
#2008 commented on
Jun 18, 2025 • 5 new comments -
Add Hugging Face as a provider
#1911 commented on
Jun 24, 2025 • 0 new comments -
Add `OpenRouterModel`
#1870 commented on
Jun 20, 2025 • 0 new comments -
Add ability to load conversation history within specified date ranges in CLI
#1981 commented on
Jun 24, 2025 • 0 new comments -
Structured Output Streaming Returning as Single Chunk(Bedrock Anthropic)
#1889 commented on
Jun 24, 2025 • 0 new comments -
Pre-validation tool response modifications
#1985 commented on
Jun 24, 2025 • 0 new comments -
Auto-fix incomplete JSON due to max_tokens through a prefilled followup LLM request
#2001 commented on
Jun 23, 2025 • 0 new comments -
Native temporal support
#1975 commented on
Jun 23, 2025 • 0 new comments -
Azure OpenAI API Streaming Response Causes AttributeError in pydantic-ai
#797 commented on
Jun 23, 2025 • 0 new comments -
Gemini causes 'Event loop is closed' when running inside an async context
#748 commented on
Jun 22, 2025 • 0 new comments -
MALFORMED_FUNCTION finishReason in Gemini candidate
#631 commented on
Jun 22, 2025 • 0 new comments -
Dynamic System prompts not being included on fresh runs with message_history
#1646 commented on
Jun 21, 2025 • 0 new comments -
Adding LiteLLM as model wrap just like how google-adk does it.
#1496 commented on
Jun 20, 2025 • 0 new comments -
Issue with LiteLLM and Agent Tool
#1071 commented on
Jun 20, 2025 • 0 new comments -
Prompt prefill/prefix
#836 commented on
Jun 20, 2025 • 0 new comments -
Claude Sonnet 3.5 & 4.0 fail to call tools in streaming mode (v0.2.14)
#1904 commented on
Jun 20, 2025 • 0 new comments -
Stop using graphs in agents
#1976 commented on
Jun 20, 2025 • 0 new comments -
Change streaming iter
#1977 commented on
Jun 20, 2025 • 0 new comments -
run_stream not working properly with tools in streaming mode
#1007 commented on
Jun 19, 2025 • 0 new comments -
Add a setting to remove prompts and completions from tracing
#1571 commented on
Jun 19, 2025 • 0 new comments -
Response parts are not timestamped
#1364 commented on
Jun 19, 2025 • 0 new comments -
Support Gemini generating multiple candidate responses
#2003 commented on
Jun 19, 2025 • 0 new comments -
Access ModelRequest-ModelResponse timestamps and duration as fields
#1996 commented on
Jun 18, 2025 • 0 new comments -
`Toolset`, take 3
#1973 commented on
Jun 18, 2025 • 0 new comments -
Extracting `new_messages()` in the middle of an `Agent.iter` run to support user-in-the-loop approval of tool calls
#1995 commented on
Jun 18, 2025 • 0 new comments -
Handoffs / sub-agent delegation
#1978 commented on
Jun 18, 2025 • 0 new comments -
Make hardcoded tool retry/error messages configurable
#2009 commented on
Jun 18, 2025 • 0 new comments -
Inconsistent naming between `FunctionToolCallEvent.call_id` and `FunctionToolResultEvent.tool_call_id`
#2007 commented on
Jun 18, 2025 • 0 new comments -
Gotcha: usage_limits must be in run* function
#1987 commented on
Jun 18, 2025 • 0 new comments