Merge branch 'main' into vercel-ai-chat

# Conflicts:
#	docs/ui/ag-ui.md
#	examples/pydantic_ai_examples/ag_ui/api/agentic_chat.py
#	examples/pydantic_ai_examples/ag_ui/api/tool_based_generative_ui.py

Author: DouweM

.github/workflows/after-ci.yml

@@ -16,7 +16,6 @@ jobs:
     steps:
       - uses: astral-sh/setup-uv@v5
         with:
-          enable-cache: true
           python-version: "3.12"
 
       - uses: dawidd6/action-download-artifact@v6
@@ -54,8 +53,9 @@ jobs:
 
       - uses: astral-sh/setup-uv@v5
         with:
-          enable-cache: true
           python-version: "3.12"
+          enable-cache: true
+          cache-suffix: deploy-docs-preview
 
       - uses: dawidd6/action-download-artifact@v6
         with:

.github/workflows/ci.yml

@@ -26,14 +26,15 @@ jobs:
         # Typecheck both Python 3.10 and 3.13. We've had issues due to not checking against both.
         python-version: ["3.10", "3.13"]
     env:
-      UV_PYTHON: ${{ matrix.python-version }}
       PYRIGHT_PYTHON: ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
 
       - uses: astral-sh/setup-uv@v5
         with:
+          python-version: ${{ matrix.python-version }}
           enable-cache: true
+          cache-suffix: lint
 
       - name: Install dependencies
         run: uv sync --all-extras --all-packages --group lint
@@ -56,6 +57,7 @@ jobs:
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
+          cache-suffix: mypy
 
       - name: Install dependencies
         run: uv sync --no-dev --group lint
@@ -70,6 +72,7 @@ jobs:
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
+          cache-suffix: docs
 
       - run: uv sync --group docs
 
@@ -107,6 +110,7 @@ jobs:
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
+          cache-suffix: live
 
       - uses: pydantic/ollama-action@v3
         with:
@@ -151,26 +155,27 @@ jobs:
           - name: all-extras
             command: "--all-extras"
     env:
-      UV_PYTHON: ${{ matrix.python-version }}
       CI: true
       COVERAGE_PROCESS_START: ./pyproject.toml
     steps:
       - uses: actions/checkout@v4
 
       - uses: astral-sh/setup-uv@v5
         with:
+          python-version: ${{ matrix.python-version }}
           enable-cache: true
-          prune-cache: false
+          cache-suffix: ${{ matrix.install.name }}
 
       - uses: denoland/setup-deno@v2
         with:
           deno-version: v2.x
 
       - run: mkdir .coverage
 
-      - run: uv run mcp-run-python example --deps=numpy
       - run: uv sync --only-dev
 
+      - run: uv run mcp-run-python example --deps=numpy
+
       - name: cache HuggingFace models
         uses: actions/cache@v4
         with:
@@ -199,16 +204,16 @@ jobs:
       matrix:
         python-version: ["3.10", "3.11", "3.12", "3.13"]
     env:
-      UV_PYTHON: ${{ matrix.python-version }}
       CI: true
       COVERAGE_PROCESS_START: ./pyproject.toml
     steps:
       - uses: actions/checkout@v4
 
       - uses: astral-sh/setup-uv@v5
         with:
+          python-version: ${{ matrix.python-version }}
           enable-cache: true
-          prune-cache: false
+          cache-suffix: lowest-versions
 
       - uses: denoland/setup-deno@v2
         with:
@@ -218,6 +223,8 @@ jobs:
 
       - run: uv sync --group dev
 
+      - run: uv run mcp-run-python example --deps=numpy
+
       - name: cache HuggingFace models
         uses: actions/cache@v4
         with:
@@ -226,8 +233,6 @@ jobs:
           restore-keys: |
             hf-${{ runner.os }}-
 
-      - run: uv run mcp-run-python example --deps=numpy
-
       - run: unset UV_FROZEN
 
       - run: uv run --all-extras --resolution lowest-direct coverage run -m pytest --durations=100 -n auto --dist=loadgroup
@@ -250,15 +255,15 @@ jobs:
       matrix:
         python-version: ["3.11", "3.12", "3.13"]
     env:
-      UV_PYTHON: ${{ matrix.python-version }}
       CI: true
     steps:
       - uses: actions/checkout@v4
 
       - uses: astral-sh/setup-uv@v5
         with:
+          python-version: ${{ matrix.python-version }}
           enable-cache: true
-          prune-cache: false
+          cache-suffix: all-extras
 
       - name: cache HuggingFace models
         uses: actions/cache@v4
@@ -288,6 +293,7 @@ jobs:
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
+          cache-suffix: dev
 
       - run: uv sync --group dev
       - run: uv run coverage combine
@@ -343,6 +349,7 @@ jobs:
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
+          cache-suffix: docs-upload
 
       - uses: actions/download-artifact@v4
         with:
@@ -384,6 +391,7 @@ jobs:
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
+          cache-suffix: deploy-docs-preview
 
       - uses: actions/download-artifact@v4
         with:
@@ -431,6 +439,7 @@ jobs:
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
+          cache-suffix: release
 
       - run: uv build --all-packages
 

.github/workflows/claude.yml

@@ -37,6 +37,7 @@ jobs:
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
+          cache-suffix: claude-code
 
       - uses: denoland/setup-deno@v2
         with:

.github/workflows/manually-deploy-docs.yml

@@ -13,6 +13,7 @@ jobs:
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
+          cache-suffix: docs
 
       - run: uv sync --group docs
 
@@ -54,6 +55,7 @@ jobs:
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
+          cache-suffix: docs-upload
 
       - uses: actions/download-artifact@v4
         with:

CLAUDE.md

@@ -28,7 +28,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 **Model Integration (`pydantic_ai_slim/pydantic_ai/models/`)**
 - Unified interface across providers: OpenAI, Anthropic, Google, Groq, Cohere, Mistral, Bedrock, HuggingFace
-- Model strings: `"openai:gpt-4o"`, `"anthropic:claude-3-5-sonnet"`, `"google:gemini-1.5-pro"`
+- Model strings: `"openai:gpt-5"`, `"anthropic:claude-sonnet-4-5"`, `"google:gemini-2.5-pro"`
 - `ModelRequestParameters` for configuration, `StreamedResponse` for streaming
 
 **Graph-based Execution (`pydantic_graph/` + `_agent_graph.py`)**
@@ -55,7 +55,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 class MyDeps:
     database: DatabaseConn
 
-agent = Agent('openai:gpt-4o', deps_type=MyDeps)
+agent = Agent('openai:gpt-5', deps_type=MyDeps)
 
 @agent.tool
 async def get_data(ctx: RunContext[MyDeps]) -> str:
@@ -69,7 +69,7 @@ class OutputModel(BaseModel):
     confidence: float
 
 agent: Agent[MyDeps, OutputModel] = Agent(
-    'openai:gpt-4o',
+    'openai:gpt-5',
     deps_type=MyDeps,
     output_type=OutputModel
 )

clai/README.md

@@ -70,7 +70,7 @@ positional arguments:
 options:
   -h, --help            show this help message and exit
   -m [MODEL], --model [MODEL]
-                        Model to use, in format "<provider>:<model>" e.g. "openai:gpt-4.1" or "anthropic:claude-sonnet-4-0". Defaults to "openai:gpt-4.1".
+                        Model to use, in format "<provider>:<model>" e.g. "openai:gpt-5" or "anthropic:claude-sonnet-4-5". Defaults to "openai:gpt-5".
   -a AGENT, --agent AGENT
                         Custom Agent to use, in format "module:variable", e.g. "mymodule.submodule:my_agent"
   -l, --list-models     List all available models and exit

docs/a2a.md

@@ -10,7 +10,7 @@ We also built a convenience method that expose Pydantic AI agents as A2A servers
 ```py {title="agent_to_a2a.py" hl_lines="4"}
 from pydantic_ai import Agent
 
-agent = Agent('openai:gpt-4.1', instructions='Be fun!')
+agent = Agent('openai:gpt-5', instructions='Be fun!')
 app = agent.to_a2a()
 ```
 
@@ -104,7 +104,7 @@ To expose a Pydantic AI agent as an A2A server, you can use the `to_a2a` method:
 ```python {title="agent_to_a2a.py"}
 from pydantic_ai import Agent
 
-agent = Agent('openai:gpt-4.1', instructions='Be fun!')
+agent = Agent('openai:gpt-5', instructions='Be fun!')
 app = agent.to_a2a()
 ```