Skip to content

Actions: pydantic/pydantic-ai

Actions

GitHub Agent

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
agent.yml
502 workflow run results
502 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Multiple MCPServerTools is not supported GitHub Agent #453: Issue #3237 opened by DouweM
28s
28s
Downsides to passing dataclasses.dataclass to Agent.output_type? GitHub Agent #452: Issue #3234 opened by patrickkidd
23s
23s
Cannot Use authlib With MCP Clients GitHub Agent #451: Issue #3231 opened by awickham10
31s
31s
ModelHTTPError caused by OpenAI client: Item of type 'function_call' was provided without its required 'reasoning' item GitHub Agent #450: Issue #3230 opened by lukekh
25s
25s
Add method to get an agent's output JSON schema GitHub Agent #449: Issue #3225 opened by DouweM
28s
28s
RunUsage reports 0 tokens for Anthropic Models GitHub Agent #448: Issue #3223 opened by ifoukarakis
26s
26s
How to handle multi-turn conversation evals with Pydantic AI Evals GitHub Agent #447: Issue #3220 opened by xjose97x
28s
28s
Support for capture_run_messages to store incomplete results GitHub Agent #446: Issue #3219 opened by psg2
27s
27s
Agent run calling MCP list tools every time before calling the model provider GitHub Agent #445: Issue #3218 opened by psg2
27s
27s
Let built-in tools fallback on custom tools for models that don't support them GitHub Agent #444: Issue #3212 opened by DouweM
24s
24s
Using event_stream_handler creates leading empty text message part when using gpt-oss family models in AWS Bedrock GitHub Agent #443: Issue #3211 opened by daryllimyt
27s
27s
Using event_stream_handler causes text to appear before thinking for gpt-oss models on ollama/vllm GitHub Agent #442: Issue #3210 opened by daryllimyt
25s
25s
Feature request: Make provider dependencies optional (don't force anthropic on OpenAI users) GitHub Agent #441: Issue #3208 opened by MattiasHaughom
27s
27s
Instruction seems to be ignored in back to back agent calls with tool output GitHub Agent #440: Issue #3207 opened by nicolas-chaulet
24s
24s
Understanding the use of identifier in BinaryContent GitHub Agent #439: Issue #3205 opened by TuanDTr
21s
21s
How does the framework determine tool calls based on model response format? GitHub Agent #438: Issue #3204 opened by RhythmicWave
24s
24s
Mishandling of Gemini "RECITATION" Error GitHub Agent #437: Issue #3202 opened by boazk485
17s
17s
ModelRetry bug with pydantic AI, AG-UI, and Open AI GitHub Agent #436: Issue #3197 opened by bdhammel
19s
19s
Fix ai_q_and_a_run graph flow breaking early GitHub Agent #435: Issue #3195 opened by huynguyengl99
21s
21s
Pass allow_partial to custom output validators GitHub Agent #434: Issue #3194 opened by petersli
20s
20s
Support reasoning from LM Studio OpenAI Responses API with gpt-oss GitHub Agent #433: Issue #3191 opened by umut-firat
29s
29s
Can you add a user_prompt_processor to the agent? GitHub Agent #432: Issue #3190 opened by zhcn000000
30s
30s
Add dynamic weighting function to UsageLimits GitHub Agent #431: Issue #3189 opened by otto-sellerstam
37s
37s
MCP sampling calls are not nested under agent run span GitHub Agent #430: Issue #3186 opened by JohnCHarrington
19s
19s
Allow running agent with ModelResponse as last message GitHub Agent #429: Issue #3184 opened by fortzi
23s
23s