Merge remote-tracking branch 'origin/main' into investigate-3207-multi-agent-instructions

# Conflicts:
#	pydantic_ai_slim/pydantic_ai/_agent_graph.py

Author: dsfaccini

README.md

@@ -39,7 +39,7 @@ We built Pydantic AI with one simple aim: to bring that FastAPI feeling to GenAI
 [Pydantic Validation](https://docs.pydantic.dev/latest/) is the validation layer of the OpenAI SDK, the Google ADK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor and many more. _Why use the derivative when you can go straight to the source?_ :smiley:
 
 2. **Model-agnostic**:
-Supports virtually every [model](https://ai.pydantic.dev/models/overview) and provider: OpenAI, Anthropic, Gemini, DeepSeek, Grok, Cohere, Mistral, and Perplexity; Azure AI Foundry, Amazon Bedrock, Google Vertex AI, Ollama, LiteLLM, Groq, OpenRouter, Together AI, Fireworks AI, Cerebras, Hugging Face, GitHub, Heroku, Vercel, Nebius. If your favorite model or provider is not listed, you can easily implement a [custom model](https://ai.pydantic.dev/models/overview#custom-models).
+Supports virtually every [model](https://ai.pydantic.dev/models/overview) and provider: OpenAI, Anthropic, Gemini, DeepSeek, Grok, Cohere, Mistral, and Perplexity; Azure AI Foundry, Amazon Bedrock, Google Vertex AI, Ollama, LiteLLM, Groq, OpenRouter, Together AI, Fireworks AI, Cerebras, Hugging Face, GitHub, Heroku, Vercel, Nebius, OVHcloud. If your favorite model or provider is not listed, you can easily implement a [custom model](https://ai.pydantic.dev/models/overview#custom-models).
 
 3. **Seamless Observability**:
 Tightly [integrates](https://ai.pydantic.dev/logfire) with [Pydantic Logfire](https://pydantic.dev/logfire), our general-purpose OpenTelemetry observability platform, for real-time debugging, evals-based performance monitoring, and behavior, tracing, and cost tracking. If you already have an observability platform that supports OTel, you can [use that too](https://ai.pydantic.dev/logfire#alternative-observability-backends).

docs/api/providers.md

@@ -43,3 +43,5 @@
 ::: pydantic_ai.providers.litellm.LiteLLMProvider
 
 ::: pydantic_ai.providers.nebius.NebiusProvider
+
+::: pydantic_ai.providers.ovhcloud.OVHcloudProvider

docs/durable_execution/prefect.md

@@ -255,20 +255,23 @@ from prefect import flow
 from pydantic_ai import Agent
 from pydantic_ai.durable_exec.prefect import PrefectAgent
 
-agent = Agent(
-    'openai:gpt-4o',
-    name='daily_report_agent',
-    instructions='Generate a daily summary report.',
-)
-
-prefect_agent = PrefectAgent(agent)
 
 @flow
 async def daily_report_flow(user_prompt: str):
     """Generate a daily report using the agent."""
+    agent = Agent(  # (1)!
+        'openai:gpt-4o',
+        name='daily_report_agent',
+        instructions='Generate a daily summary report.',
+    )
+
+    prefect_agent = PrefectAgent(agent)
+
     result = await prefect_agent.run(user_prompt)
     return result.output
 
+
+
 # Serve the flow with a daily schedule
 if __name__ == '__main__':
     daily_report_flow.serve(
@@ -279,6 +282,8 @@ if __name__ == '__main__':
     )
 ```
 
+1. Each flow run executes in an isolated process, and all inputs and dependencies must be serializable. Because Agent instances cannot be serialized, instantiate the agent inside the flow rather than at the module level.
+
 The `serve()` method accepts scheduling options:
 
 - **`cron`**: Cron schedule string (e.g., `'0 9 * * *'` for daily at 9am)

docs/index.md

@@ -14,7 +14,7 @@ We built Pydantic AI with one simple aim: to bring that FastAPI feeling to GenAI
 [Pydantic Validation](https://docs.pydantic.dev/latest/) is the validation layer of the OpenAI SDK, the Google ADK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor and many more. _Why use the derivative when you can go straight to the source?_ :smiley:
 
 2. **Model-agnostic**:
-Supports virtually every [model](models/overview.md) and provider: OpenAI, Anthropic, Gemini, DeepSeek, Grok, Cohere, Mistral, and Perplexity; Azure AI Foundry, Amazon Bedrock, Google Vertex AI, Ollama, LiteLLM, Groq, OpenRouter, Together AI, Fireworks AI, Cerebras, Hugging Face, GitHub, Heroku, Vercel, Nebius. If your favorite model or provider is not listed, you can easily implement a [custom model](models/overview.md#custom-models).
+Supports virtually every [model](models/overview.md) and provider: OpenAI, Anthropic, Gemini, DeepSeek, Grok, Cohere, Mistral, and Perplexity; Azure AI Foundry, Amazon Bedrock, Google Vertex AI, Ollama, LiteLLM, Groq, OpenRouter, Together AI, Fireworks AI, Cerebras, Hugging Face, GitHub, Heroku, Vercel, Nebius, OVHcloud. If your favorite model or provider is not listed, you can easily implement a [custom model](models/overview.md#custom-models).
 
 3. **Seamless Observability**:
 Tightly [integrates](logfire.md) with [Pydantic Logfire](https://pydantic.dev/logfire), our general-purpose OpenTelemetry observability platform, for real-time debugging, evals-based performance monitoring, and behavior, tracing, and cost tracking. If you already have an observability platform that supports OTel, you can [use that too](logfire.md#alternative-observability-backends).

docs/mcp/client.md

@@ -58,15 +58,13 @@ server = MCPServerStreamableHTTP('http://localhost:8000/mcp')  # (1)!
 agent = Agent('openai:gpt-4o', toolsets=[server])  # (2)!
 
 async def main():
-    async with agent:  # (3)!
-        result = await agent.run('What is 7 plus 5?')
+    result = await agent.run('What is 7 plus 5?')
     print(result.output)
     #> The answer is 12.
 ```
 
 1. Define the MCP server with the URL used to connect.
 2. Create an agent with the MCP server attached.
-3. Create a client session to connect to the server.
 
 _(This example is complete, it can be run "as is" — you'll need to add `asyncio.run(main())` to run `main`)_
 
@@ -122,15 +120,13 @@ agent = Agent('openai:gpt-4o', toolsets=[server])  # (2)!
 
 
 async def main():
-    async with agent:  # (3)!
-        result = await agent.run('What is 7 plus 5?')
+    result = await agent.run('What is 7 plus 5?')
     print(result.output)
     #> The answer is 12.
 ```
 
 1. Define the MCP server with the URL used to connect.
 2. Create an agent with the MCP server attached.
-3. Create a client session to connect to the server.
 
 _(This example is complete, it can be run "as is" — you'll need to add `asyncio.run(main())` to run `main`)_
 
@@ -151,8 +147,7 @@ agent = Agent('openai:gpt-4o', toolsets=[server])
 
 
 async def main():
-    async with agent:
-        result = await agent.run('How many days between 2000-01-01 and 2025-03-18?')
+    result = await agent.run('How many days between 2000-01-01 and 2025-03-18?')
     print(result.output)
     #> There are 9,208 days between January 1, 2000, and March 18, 2025.
 ```
@@ -205,8 +200,7 @@ servers = load_mcp_servers('mcp_config.json')
 agent = Agent('openai:gpt-5', toolsets=servers)
 
 async def main():
-    async with agent:
-        result = await agent.run('What is 7 plus 5?')
+    result = await agent.run('What is 7 plus 5?')
     print(result.output)
 ```
 
@@ -247,8 +241,7 @@ agent = Agent(
 
 
 async def main():
-    async with agent:
-        result = await agent.run('Echo with deps set to 42', deps=42)
+    result = await agent.run('Echo with deps set to 42', deps=42)
     print(result.output)
     #> {"echo_deps":{"echo":"This is an echo message","deps":42}}
 ```
@@ -356,8 +349,7 @@ server = MCPServerSSE(
 agent = Agent('openai:gpt-4o', toolsets=[server])
 
 async def main():
-    async with agent:
-        result = await agent.run('How many days between 2000-01-01 and 2025-03-18?')
+    result = await agent.run('How many days between 2000-01-01 and 2025-03-18?')
     print(result.output)
     #> There are 9,208 days between January 1, 2000, and March 18, 2025.
 ```
@@ -454,9 +446,8 @@ agent = Agent('openai:gpt-4o', toolsets=[server])
 
 
 async def main():
-    async with agent:
-        agent.set_mcp_sampling_model()
-        result = await agent.run('Create an image of a robot in a punk style.')
+    agent.set_mcp_sampling_model()
+    result = await agent.run('Create an image of a robot in a punk style.')
     print(result.output)
     #> Image file written to robot_punk.svg.
 ```
@@ -598,9 +589,8 @@ agent = Agent('openai:gpt-4o', toolsets=[restaurant_server])
 
 async def main():
     """Run the agent to book a restaurant table."""
-    async with agent:
-        result = await agent.run('Book me a table')
-        print(f'\nResult: {result.output}')
+    result = await agent.run('Book me a table')
+    print(f'\nResult: {result.output}')
 
 
 if __name__ == '__main__':

docs/models/cohere.md

@@ -27,7 +27,7 @@ You can then use `CohereModel` by name:
 ```python
 from pydantic_ai import Agent
 
-agent = Agent('cohere:command')
+agent = Agent('cohere:command-r7b-12-2024')
 ...
 ```
 
@@ -37,7 +37,7 @@ Or initialise the model directly with just the model name:
 from pydantic_ai import Agent
 from pydantic_ai.models.cohere import CohereModel
 
-model = CohereModel('command')
+model = CohereModel('command-r7b-12-2024')
 agent = Agent(model)
 ...
 ```
@@ -51,7 +51,7 @@ from pydantic_ai import Agent
 from pydantic_ai.models.cohere import CohereModel
 from pydantic_ai.providers.cohere import CohereProvider
 
-model = CohereModel('command', provider=CohereProvider(api_key='your-api-key'))
+model = CohereModel('command-r7b-12-2024', provider=CohereProvider(api_key='your-api-key'))
 agent = Agent(model)
 ...
 ```
@@ -67,7 +67,7 @@ from pydantic_ai.providers.cohere import CohereProvider
 
 custom_http_client = AsyncClient(timeout=30)
 model = CohereModel(
-    'command',
+    'command-r7b-12-2024',
     provider=CohereProvider(api_key='your-api-key', http_client=custom_http_client),
 )
 agent = Agent(model)