pydantic-ai 0.4.3__tar.gz → 0.4.4__tar.gz

{pydantic_ai-0.4.3 → pydantic_ai-0.4.4}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: pydantic-ai
-Version: 0.4.3
+Version: 0.4.4
 Summary: Agent Framework / shim to use Pydantic with LLMs
 Project-URL: Homepage, https://ai.pydantic.dev
 Project-URL: Source, https://github.com/pydantic/pydantic-ai
 Project-URL: Documentation, https://ai.pydantic.dev
 Project-URL: Changelog, https://github.com/pydantic/pydantic-ai/releases
-Author-email: Samuel Colvin <samuel@pydantic.dev>, Marcelo Trylesinski <marcelotryle@gmail.com>, David Montague <david@pydantic.dev>, Alex Hall <alex@pydantic.dev>
+Author-email: Samuel Colvin <samuel@pydantic.dev>, Marcelo Trylesinski <marcelotryle@gmail.com>, David Montague <david@pydantic.dev>, Alex Hall <alex@pydantic.dev>, Douwe Maan <douwe@pydantic.dev>
 License-Expression: MIT
 License-File: LICENSE
 Classifier: Development Status :: 4 - Beta
@@ -28,11 +28,11 @@ Classifier: Topic :: Internet
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.9
-Requires-Dist: pydantic-ai-slim[anthropic,bedrock,cli,cohere,evals,google,groq,huggingface,mcp,mistral,openai,vertexai]==0.4.3
+Requires-Dist: pydantic-ai-slim[ag-ui,anthropic,bedrock,cli,cohere,evals,google,groq,huggingface,mcp,mistral,openai,vertexai]==0.4.4
 Provides-Extra: a2a
 Requires-Dist: fasta2a>=0.4.1; extra == 'a2a'
 Provides-Extra: examples
-Requires-Dist: pydantic-ai-examples==0.4.3; extra == 'examples'
+Requires-Dist: pydantic-ai-examples==0.4.4; extra == 'examples'
 Provides-Extra: logfire
 Requires-Dist: logfire>=3.11.0; extra == 'logfire'
 Description-Content-Type: text/markdown
@@ -41,7 +41,7 @@ Description-Content-Type: text/markdown
   <a href="https://ai.pydantic.dev/">
     <picture>
       <source media="(prefers-color-scheme: dark)" srcset="https://ai.pydantic.dev/img/pydantic-ai-dark.svg">
-      <img src="https://ai.pydantic.dev/img/pydantic-ai-light.svg" alt="PydanticAI">
+      <img src="https://ai.pydantic.dev/img/pydantic-ai-light.svg" alt="Pydantic AI">
     </picture>
   </a>
 </div>
@@ -63,47 +63,47 @@ Description-Content-Type: text/markdown
 
 ---
 
-PydanticAI is a Python agent framework designed to make it less painful to build production grade applications with Generative AI.
+Pydantic AI is a Python agent framework designed to make it less painful to build production grade applications with Generative AI.
 
-FastAPI revolutionized web development by offering an innovative and ergonomic design, built on the foundation of [Pydantic](https://docs.pydantic.dev).
+FastAPI revolutionized web development by offering an innovative and ergonomic design, built on the foundation of [Pydantic Validation](https://docs.pydantic.dev).
 
-Similarly, virtually every agent framework and LLM library in Python uses Pydantic, yet when we began to use LLMs in [Pydantic Logfire](https://pydantic.dev/logfire), we couldn't find anything that gave us the same feeling.
+Similarly, virtually every agent framework and LLM library in Python uses Pydantic Validation, yet when we began to use LLMs in [Pydantic Logfire](https://pydantic.dev/logfire), we couldn't find anything that gave us the same feeling.
 
-We built PydanticAI with one simple aim: to bring that FastAPI feeling to GenAI app development.
+We built Pydantic AI with one simple aim: to bring that FastAPI feeling to GenAI app development.
 
-## Why use PydanticAI
+## Why use Pydantic AI
 
-* __Built by the Pydantic Team__
-Built by the team behind [Pydantic](https://docs.pydantic.dev/latest/) (the validation layer of the OpenAI SDK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor and many more).
+- **Built by the Pydantic Team**
+  Built by the team behind [Pydantic Validation](https://docs.pydantic.dev/latest/) (the validation layer of the OpenAI SDK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor and many more).
 
-* __Model-agnostic__
-Supports OpenAI, Anthropic, Gemini, Deepseek, Ollama, Groq, Cohere, and Mistral, and there is a simple interface to implement support for [other models](https://ai.pydantic.dev/models/).
+- **Model-agnostic**
+  Supports OpenAI, Anthropic, Gemini, Deepseek, Ollama, Groq, Cohere, and Mistral, and there is a simple interface to implement support for [other models](https://ai.pydantic.dev/models/).
 
-* __Pydantic Logfire Integration__
-Seamlessly [integrates](https://ai.pydantic.dev/logfire/) with [Pydantic Logfire](https://pydantic.dev/logfire) for real-time debugging, performance monitoring, and behavior tracking of your LLM-powered applications.
+- **Pydantic Logfire Integration**
+  Seamlessly [integrates](https://ai.pydantic.dev/logfire/) with [Pydantic Logfire](https://pydantic.dev/logfire) for real-time debugging, performance monitoring, and behavior tracking of your LLM-powered applications.
 
-* __Type-safe__
-Designed to make [type checking](https://ai.pydantic.dev/agents/#static-type-checking) as powerful and informative as possible for you.
+- **Type-safe**
+  Designed to make [type checking](https://ai.pydantic.dev/agents/#static-type-checking) as powerful and informative as possible for you.
 
-* __Python-centric Design__
-Leverages Python's familiar control flow and agent composition to build your AI-driven projects, making it easy to apply standard Python best practices you'd use in any other (non-AI) project.
+- **Python-centric Design**
+  Leverages Python's familiar control flow and agent composition to build your AI-driven projects, making it easy to apply standard Python best practices you'd use in any other (non-AI) project.
 
-* __Structured Responses__
-Harnesses the power of [Pydantic](https://docs.pydantic.dev/latest/) to [validate and structure](https://ai.pydantic.dev/output/#structured-output) model outputs, ensuring responses are consistent across runs.
+- **Structured Responses**
+  Harnesses the power of [Pydantic Validation](https://docs.pydantic.dev/latest/) to [validate and structure](https://ai.pydantic.dev/output/#structured-output) model outputs, ensuring responses are consistent across runs.
 
-* __Dependency Injection System__
-Offers an optional [dependency injection](https://ai.pydantic.dev/dependencies/) system to provide data and services to your agent's [system prompts](https://ai.pydantic.dev/agents/#system-prompts), [tools](https://ai.pydantic.dev/tools/) and [output validators](https://ai.pydantic.dev/output/#output-validator-functions).
-This is useful for testing and eval-driven iterative development.
+- **Dependency Injection System**
+  Offers an optional [dependency injection](https://ai.pydantic.dev/dependencies/) system to provide data and services to your agent's [system prompts](https://ai.pydantic.dev/agents/#system-prompts), [tools](https://ai.pydantic.dev/tools/) and [output validators](https://ai.pydantic.dev/output/#output-validator-functions).
+  This is useful for testing and eval-driven iterative development.
 
-* __Streamed Responses__
-Provides the ability to [stream](https://ai.pydantic.dev/output/#streamed-results) LLM outputs continuously, with immediate validation, ensuring rapid and accurate outputs.
+- **Streamed Responses**
+  Provides the ability to [stream](https://ai.pydantic.dev/output/#streamed-results) LLM outputs continuously, with immediate validation, ensuring rapid and accurate outputs.
 
-* __Graph Support__
-[Pydantic Graph](https://ai.pydantic.dev/graph) provides a powerful way to define graphs using typing hints, this is useful in complex applications where standard control flow can degrade to spaghetti code.
+- **Graph Support**
+  [Pydantic Graph](https://ai.pydantic.dev/graph) provides a powerful way to define graphs using typing hints, this is useful in complex applications where standard control flow can degrade to spaghetti code.
 
 ## Hello World Example
 
-Here's a minimal example of PydanticAI:
+Here's a minimal example of Pydantic AI:
 
 ```python
 from pydantic_ai import Agent
@@ -117,7 +117,7 @@ agent = Agent(
 )
 
 # Run the agent synchronously, conducting a conversation with the LLM.
-# Here the exchange should be very short: PydanticAI will send the system prompt and the user query to the LLM,
+# Here the exchange should be very short: Pydantic AI will send the system prompt and the user query to the LLM,
 # the model will return a text response. See below for a more complex run.
 result = agent.run_sync('Where does "hello world" come from?')
 print(result.output)
@@ -132,7 +132,7 @@ Not very interesting yet, but we can easily add "tools", dynamic system prompts,
 
 ## Tools & Dependency Injection Example
 
-Here is a concise example using PydanticAI to build a support agent for a bank:
+Here is a concise example using Pydantic AI to build a support agent for a bank:
 
 **(Better documented example [in the docs](https://ai.pydantic.dev/#tools-dependency-injection-example))**
 
@@ -226,8 +226,8 @@ async def main():
 
 ## Next Steps
 
-To try PydanticAI yourself, follow the instructions [in the examples](https://ai.pydantic.dev/examples/).
+To try Pydantic AI yourself, follow the instructions [in the examples](https://ai.pydantic.dev/examples/).
 
-Read the [docs](https://ai.pydantic.dev/agents/) to learn more about building applications with PydanticAI.
+Read the [docs](https://ai.pydantic.dev/agents/) to learn more about building applications with Pydantic AI.
 
-Read the [API Reference](https://ai.pydantic.dev/api/agent/) to understand PydanticAI's interface.
+Read the [API Reference](https://ai.pydantic.dev/api/agent/) to understand Pydantic AI's interface.

{pydantic_ai-0.4.3 → pydantic_ai-0.4.4}/README.md

@@ -2,7 +2,7 @@
   <a href="https://ai.pydantic.dev/">
     <picture>
       <source media="(prefers-color-scheme: dark)" srcset="https://ai.pydantic.dev/img/pydantic-ai-dark.svg">
-      <img src="https://ai.pydantic.dev/img/pydantic-ai-light.svg" alt="PydanticAI">
+      <img src="https://ai.pydantic.dev/img/pydantic-ai-light.svg" alt="Pydantic AI">
     </picture>
   </a>
 </div>
@@ -24,47 +24,47 @@
 
 ---
 
-PydanticAI is a Python agent framework designed to make it less painful to build production grade applications with Generative AI.
+Pydantic AI is a Python agent framework designed to make it less painful to build production grade applications with Generative AI.
 
-FastAPI revolutionized web development by offering an innovative and ergonomic design, built on the foundation of [Pydantic](https://docs.pydantic.dev).
+FastAPI revolutionized web development by offering an innovative and ergonomic design, built on the foundation of [Pydantic Validation](https://docs.pydantic.dev).
 
-Similarly, virtually every agent framework and LLM library in Python uses Pydantic, yet when we began to use LLMs in [Pydantic Logfire](https://pydantic.dev/logfire), we couldn't find anything that gave us the same feeling.
+Similarly, virtually every agent framework and LLM library in Python uses Pydantic Validation, yet when we began to use LLMs in [Pydantic Logfire](https://pydantic.dev/logfire), we couldn't find anything that gave us the same feeling.
 
-We built PydanticAI with one simple aim: to bring that FastAPI feeling to GenAI app development.
+We built Pydantic AI with one simple aim: to bring that FastAPI feeling to GenAI app development.
 
-## Why use PydanticAI
+## Why use Pydantic AI
 
-* __Built by the Pydantic Team__
-Built by the team behind [Pydantic](https://docs.pydantic.dev/latest/) (the validation layer of the OpenAI SDK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor and many more).
+- **Built by the Pydantic Team**
+  Built by the team behind [Pydantic Validation](https://docs.pydantic.dev/latest/) (the validation layer of the OpenAI SDK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor and many more).
 
-* __Model-agnostic__
-Supports OpenAI, Anthropic, Gemini, Deepseek, Ollama, Groq, Cohere, and Mistral, and there is a simple interface to implement support for [other models](https://ai.pydantic.dev/models/).
+- **Model-agnostic**
+  Supports OpenAI, Anthropic, Gemini, Deepseek, Ollama, Groq, Cohere, and Mistral, and there is a simple interface to implement support for [other models](https://ai.pydantic.dev/models/).
 
-* __Pydantic Logfire Integration__
-Seamlessly [integrates](https://ai.pydantic.dev/logfire/) with [Pydantic Logfire](https://pydantic.dev/logfire) for real-time debugging, performance monitoring, and behavior tracking of your LLM-powered applications.
+- **Pydantic Logfire Integration**
+  Seamlessly [integrates](https://ai.pydantic.dev/logfire/) with [Pydantic Logfire](https://pydantic.dev/logfire) for real-time debugging, performance monitoring, and behavior tracking of your LLM-powered applications.
 
-* __Type-safe__
-Designed to make [type checking](https://ai.pydantic.dev/agents/#static-type-checking) as powerful and informative as possible for you.
+- **Type-safe**
+  Designed to make [type checking](https://ai.pydantic.dev/agents/#static-type-checking) as powerful and informative as possible for you.
 
-* __Python-centric Design__
-Leverages Python's familiar control flow and agent composition to build your AI-driven projects, making it easy to apply standard Python best practices you'd use in any other (non-AI) project.
+- **Python-centric Design**
+  Leverages Python's familiar control flow and agent composition to build your AI-driven projects, making it easy to apply standard Python best practices you'd use in any other (non-AI) project.
 
-* __Structured Responses__
-Harnesses the power of [Pydantic](https://docs.pydantic.dev/latest/) to [validate and structure](https://ai.pydantic.dev/output/#structured-output) model outputs, ensuring responses are consistent across runs.
+- **Structured Responses**
+  Harnesses the power of [Pydantic Validation](https://docs.pydantic.dev/latest/) to [validate and structure](https://ai.pydantic.dev/output/#structured-output) model outputs, ensuring responses are consistent across runs.
 
-* __Dependency Injection System__
-Offers an optional [dependency injection](https://ai.pydantic.dev/dependencies/) system to provide data and services to your agent's [system prompts](https://ai.pydantic.dev/agents/#system-prompts), [tools](https://ai.pydantic.dev/tools/) and [output validators](https://ai.pydantic.dev/output/#output-validator-functions).
-This is useful for testing and eval-driven iterative development.
+- **Dependency Injection System**
+  Offers an optional [dependency injection](https://ai.pydantic.dev/dependencies/) system to provide data and services to your agent's [system prompts](https://ai.pydantic.dev/agents/#system-prompts), [tools](https://ai.pydantic.dev/tools/) and [output validators](https://ai.pydantic.dev/output/#output-validator-functions).
+  This is useful for testing and eval-driven iterative development.
 
-* __Streamed Responses__
-Provides the ability to [stream](https://ai.pydantic.dev/output/#streamed-results) LLM outputs continuously, with immediate validation, ensuring rapid and accurate outputs.
+- **Streamed Responses**
+  Provides the ability to [stream](https://ai.pydantic.dev/output/#streamed-results) LLM outputs continuously, with immediate validation, ensuring rapid and accurate outputs.
 
-* __Graph Support__
-[Pydantic Graph](https://ai.pydantic.dev/graph) provides a powerful way to define graphs using typing hints, this is useful in complex applications where standard control flow can degrade to spaghetti code.
+- **Graph Support**
+  [Pydantic Graph](https://ai.pydantic.dev/graph) provides a powerful way to define graphs using typing hints, this is useful in complex applications where standard control flow can degrade to spaghetti code.
 
 ## Hello World Example
 
-Here's a minimal example of PydanticAI:
+Here's a minimal example of Pydantic AI:
 
 ```python
 from pydantic_ai import Agent
@@ -78,7 +78,7 @@ agent = Agent(
 )
 
 # Run the agent synchronously, conducting a conversation with the LLM.
-# Here the exchange should be very short: PydanticAI will send the system prompt and the user query to the LLM,
+# Here the exchange should be very short: Pydantic AI will send the system prompt and the user query to the LLM,
 # the model will return a text response. See below for a more complex run.
 result = agent.run_sync('Where does "hello world" come from?')
 print(result.output)
@@ -93,7 +93,7 @@ Not very interesting yet, but we can easily add "tools", dynamic system prompts,
 
 ## Tools & Dependency Injection Example
 
-Here is a concise example using PydanticAI to build a support agent for a bank:
+Here is a concise example using Pydantic AI to build a support agent for a bank:
 
 **(Better documented example [in the docs](https://ai.pydantic.dev/#tools-dependency-injection-example))**
 
@@ -187,8 +187,8 @@ async def main():
 
 ## Next Steps
 
-To try PydanticAI yourself, follow the instructions [in the examples](https://ai.pydantic.dev/examples/).
+To try Pydantic AI yourself, follow the instructions [in the examples](https://ai.pydantic.dev/examples/).
 
-Read the [docs](https://ai.pydantic.dev/agents/) to learn more about building applications with PydanticAI.
+Read the [docs](https://ai.pydantic.dev/agents/) to learn more about building applications with Pydantic AI.
 
-Read the [API Reference](https://ai.pydantic.dev/api/agent/) to understand PydanticAI's interface.
+Read the [API Reference](https://ai.pydantic.dev/api/agent/) to understand Pydantic AI's interface.

{pydantic_ai-0.4.3 → pydantic_ai-0.4.4}/pyproject.toml

@@ -19,6 +19,7 @@ authors = [
     { name = "Marcelo Trylesinski", email = "marcelotryle@gmail.com" },
     { name = "David Montague", email = "david@pydantic.dev" },
     { name = "Alex Hall", email = "alex@pydantic.dev" },
+    { name = "Douwe Maan", email = "douwe@pydantic.dev" },
 ]
 license = "MIT"
 readme = "README.md"
@@ -46,7 +47,7 @@ requires-python = ">=3.9"
 
 [tool.hatch.metadata.hooks.uv-dynamic-versioning]
 dependencies = [
-    "pydantic-ai-slim[openai,vertexai,google,groq,anthropic,mistral,cohere,bedrock,huggingface,cli,mcp,evals]=={{ version }}",
+    "pydantic-ai-slim[openai,vertexai,google,groq,anthropic,mistral,cohere,bedrock,huggingface,cli,mcp,evals,ag-ui]=={{ version }}",
 ]
 
 [tool.hatch.metadata.hooks.uv-dynamic-versioning.optional-dependencies]
@@ -199,6 +200,8 @@ filterwarnings = [
     "error",
     # Issue with python-multipart - we don't want to bump the minimum version of starlette.
     "ignore::PendingDeprecationWarning:starlette",
+    # mistralai accesses model_fields on the instance, which is deprecated in Pydantic 2.11.
+    "ignore:Accessing the 'model_fields' attribute",
     # boto3
     "ignore::DeprecationWarning:botocore.*",
     "ignore::RuntimeWarning:pydantic_ai.mcp",

pydantic_ai-0.4.3/tests/cassettes/test_mcp/test_tool_returning_text_resource.yaml → pydantic_ai-0.4.4/tests/cassettes/test_mcp/test_agent_with_server_not_running.yaml

@@ -8,7 +8,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1882'
+      - '2501'
       content-type:
       - application/json
       host:
@@ -16,10 +16,9 @@ interactions:
     method: POST
     parsed_body:
       messages:
-      - content: Get me the product name
+      - content: What is 0 degrees Celsius in Fahrenheit?
         role: user
       model: gpt-4o
-      n: 1
       stream: false
       tool_choice: auto
       tools:
@@ -54,6 +53,13 @@ interactions:
             properties: {}
             type: object
         type: function
+      - function:
+          description: ''
+          name: get_audio_resource
+          parameters:
+            properties: {}
+            type: object
+        type: function
       - function:
           description: ''
           name: get_product_name
@@ -105,6 +111,25 @@ interactions:
             properties: {}
             type: object
         type: function
+      - function:
+          description: "Echo the run context.\n\n    Args:\n        ctx: Context object containing request and session information.\n\n
+            \   Returns:\n        Dictionary with an echo message and the deps.\n    "
+          name: echo_deps
+          parameters:
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: Use sampling callback.
+          name: use_sampling
+          parameters:
+            properties:
+              foo:
+                type: string
+            required:
+            - foo
+            type: object
+        type: function
     uri: https://api.openai.com/v1/chat/completions
   response:
     headers:
@@ -115,13 +140,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1068'
+      - '1086'
       content-type:
       - application/json
       openai-organization:
       - pydantic-28gund
       openai-processing-ms:
-      - '3650'
+      - '420'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -140,28 +165,28 @@ interactions:
           role: assistant
           tool_calls:
           - function:
-              arguments: '{}'
-              name: get_product_name
-            id: call_LaiWltzI39sdquflqeuF0EyE
+              arguments: '{"celsius":0}'
+              name: celsius_to_fahrenheit
+            id: call_hS0oexgCNI6TneJuPPuwn9jQ
             type: function
-      created: 1745961790
-      id: chatcmpl-BRmhyweJVYonarb7s9ckIMSHf2vHo
+      created: 1751491994
+      id: chatcmpl-BozMoBhgfC5D8QBjkiOwz5OxxrwQK
       model: gpt-4o-2024-08-06
       object: chat.completion
       service_tier: default
-      system_fingerprint: fp_f5bdcc3276
+      system_fingerprint: fp_a288987b44
       usage:
-        completion_tokens: 12
+        completion_tokens: 18
         completion_tokens_details:
           accepted_prediction_tokens: 0
           audio_tokens: 0
           reasoning_tokens: 0
           rejected_prediction_tokens: 0
-        prompt_tokens: 200
+        prompt_tokens: 268
         prompt_tokens_details:
           audio_tokens: 0
           cached_tokens: 0
-        total_tokens: 212
+        total_tokens: 286
     status:
       code: 200
       message: OK
@@ -174,31 +199,30 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '2117'
+      - '2748'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=LCwj6B2rTuTfMe.JFAULcM1w5d9_bQkgyyDVrYXlFWQ-1745961790-1.0.1.1-rLSFIG9L0nbQaHsDaUAe231glaNUGZIodlFyJvNpkdF95kQD8prfC.uNV9.d2ymwvSDsmdB57U6u9ShNfBes9Ev8kn6eYDTHyGzxCeAhZ_o;
-        _cfuvid=eK9nRUfAL4vFjm9wuH.RIQX41iZHZ8h1LCjqR.nSQzA-1745961790721-0.0.1.1-604800000
+      - __cf_bm=JOV7WG2Y48FZrZxdh0IZvA9mCj_ljIN3DhGMuC1pw6M-1751491995-1.0.1.1-zGPrLbzYx7y3iZT28xogbHO1KAIej60kPEwQ8ZxGMxv1r.ICtqI0T8WCnlyUccKfLSXB6ZTNQT05xCma8LSvq2pk4X2eEuSkYC1sPqbuLU8;
+        _cfuvid=LdoyX0uKYwM98NSSSvySlZAiJHCVHz_1krUGKbWmNHg-1751491995391-0.0.1.1-604800000
       host:
       - api.openai.com
     method: POST
     parsed_body:
       messages:
-      - content: Get me the product name
+      - content: What is 0 degrees Celsius in Fahrenheit?
         role: user
       - role: assistant
         tool_calls:
         - function:
-            arguments: '{}'
-            name: get_product_name
-          id: call_LaiWltzI39sdquflqeuF0EyE
+            arguments: '{"celsius":0}'
+            name: celsius_to_fahrenheit
+          id: call_hS0oexgCNI6TneJuPPuwn9jQ
           type: function
-      - content: PydanticAI
+      - content: '32.0'
         role: tool
-        tool_call_id: call_LaiWltzI39sdquflqeuF0EyE
+        tool_call_id: call_hS0oexgCNI6TneJuPPuwn9jQ
       model: gpt-4o
-      n: 1
       stream: false
       tool_choice: auto
       tools:
@@ -233,6 +257,13 @@ interactions:
             properties: {}
             type: object
         type: function
+      - function:
+          description: ''
+          name: get_audio_resource
+          parameters:
+            properties: {}
+            type: object
+        type: function
       - function:
           description: ''
           name: get_product_name
@@ -284,6 +315,25 @@ interactions:
             properties: {}
             type: object
         type: function
+      - function:
+          description: "Echo the run context.\n\n    Args:\n        ctx: Context object containing request and session information.\n\n
+            \   Returns:\n        Dictionary with an echo message and the deps.\n    "
+          name: echo_deps
+          parameters:
+            properties: {}
+            type: object
+        type: function
+      - function:
+          description: Use sampling callback.
+          name: use_sampling
+          parameters:
+            properties:
+              foo:
+                type: string
+            required:
+            - foo
+            type: object
+        type: function
     uri: https://api.openai.com/v1/chat/completions
   response:
     headers:
@@ -294,13 +344,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '839'
+      - '849'
       content-type:
       - application/json
       openai-organization:
       - pydantic-28gund
       openai-processing-ms:
-      - '631'
+      - '520'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -314,15 +364,15 @@ interactions:
         logprobs: null
         message:
           annotations: []
-          content: The product name is "PydanticAI".
+          content: 0 degrees Celsius is 32.0 degrees Fahrenheit.
           refusal: null
           role: assistant
-      created: 1745961791
-      id: chatcmpl-BRmhzqXFObpYwSzREMpJvX9kbDikR
+      created: 1751491998
+      id: chatcmpl-BozMsevK8quJblNOyNCaDQpdtDwI5
       model: gpt-4o-2024-08-06
       object: chat.completion
       service_tier: default
-      system_fingerprint: fp_f5bdcc3276
+      system_fingerprint: fp_a288987b44
       usage:
         completion_tokens: 12
         completion_tokens_details:
@@ -330,11 +380,11 @@ interactions:
           audio_tokens: 0
           reasoning_tokens: 0
           rejected_prediction_tokens: 0
-        prompt_tokens: 224
+        prompt_tokens: 300
         prompt_tokens_details:
           audio_tokens: 0
           cached_tokens: 0
-        total_tokens: 236
+        total_tokens: 312
     status:
       code: 200
       message: OK