Merge branch 'main' into add-googlemodel-google-specific-error-handling

Author: Kludex

.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
@@ -46,6 +45,10 @@ jobs:
       name: deploy-docs-preview
 
     steps:
+      - run: echo "$GITHUB_EVENT_JSON"
+        env:
+          GITHUB_EVENT_JSON: ${{ toJSON(github.event) }}
+
       - uses: actions/checkout@v4
 
       - uses: actions/setup-node@v4
@@ -54,20 +57,24 @@ 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
+      - id: download-artifact
+        uses: dawidd6/action-download-artifact@v6
         with:
           workflow: ci.yml
           name: site
           path: site
           commit: ${{ github.event.workflow_run.head_sha }}
           allow_forks: true
           workflow_conclusion: completed
+          if_no_artifact_found: warn
 
       - uses: cloudflare/wrangler-action@v3
         id: deploy
+        if: steps.download-artifact.outputs.found_artifact == 'true'
         with:
           apiToken: ${{ secrets.CLOUDFLARE_API_TOKEN }}
           environment: previews
@@ -77,12 +84,9 @@ jobs:
             --var GIT_COMMIT_SHA:${{ github.event.workflow_run.head_sha }}
             --var GIT_BRANCH:${{ github.event.workflow_run.head_branch }}
 
-      - run: echo "$GITHUB_EVENT_JSON"
-        env:
-          GITHUB_EVENT_JSON: ${{ toJSON(github.event) }}
-
       - name: Set preview URL
         run: uv run --no-project --with httpx .github/set_docs_pr_preview_url.py
+        if: steps.deploy.outcome == 'success'
         env:
           DEPLOY_OUTPUT: ${{ steps.deploy.outputs.command-output }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.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:
@@ -138,7 +142,7 @@ jobs:
   test:
     name: test on ${{ matrix.python-version }} (${{ matrix.install.name }})
     runs-on: ubuntu-latest
-    timeout-minutes: 15
+    timeout-minutes: 20
     strategy:
       fail-fast: false
       matrix:
@@ -151,24 +155,35 @@ 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
+          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:
+          path: ~/.cache/huggingface
+          key: hf-${{ runner.os }}-${{ hashFiles('**/uv.lock') }}
+          restore-keys: |
+            hf-${{ runner.os }}-
+
       - run: uv run ${{ matrix.install.command }} coverage run -m pytest --durations=100 -n auto --dist=loadgroup
         env:
           COVERAGE_FILE: .coverage/.coverage.${{ matrix.python-version }}-${{ matrix.install.name }}
@@ -183,21 +198,22 @@ jobs:
   test-lowest-versions:
     name: test on ${{ matrix.python-version }} (lowest-versions)
     runs-on: ubuntu-latest
-    timeout-minutes: 15
+    timeout-minutes: 20
     strategy:
       fail-fast: false
       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
+          cache-suffix: lowest-versions
 
       - uses: denoland/setup-deno@v2
         with:
@@ -206,8 +222,17 @@ jobs:
       - run: mkdir .coverage
 
       - run: uv sync --group dev
+
       - run: uv run mcp-run-python example --deps=numpy
 
+      - name: cache HuggingFace models
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/huggingface
+          key: hf-${{ runner.os }}-${{ hashFiles('**/uv.lock') }}
+          restore-keys: |
+            hf-${{ runner.os }}-
+
       - run: unset UV_FROZEN
 
       - run: uv run --all-extras --resolution lowest-direct coverage run -m pytest --durations=100 -n auto --dist=loadgroup
@@ -230,14 +255,23 @@ 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: ${{ matrix.python-version }}
           enable-cache: true
+          cache-suffix: examples
+
+      - name: cache HuggingFace models
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/huggingface
+          key: hf-${{ runner.os }}-${{ hashFiles('**/uv.lock') }}
+          restore-keys: |
+            hf-${{ runner.os }}-
 
       - run: uv run --all-extras python tests/import_examples.py
 
@@ -259,6 +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
@@ -314,6 +349,7 @@ jobs:
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
+          cache-suffix: docs-upload
 
       - uses: actions/download-artifact@v4
         with:
@@ -355,6 +391,7 @@ jobs:
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
+          cache-suffix: deploy-docs-preview
 
       - uses: actions/download-artifact@v4
         with:
@@ -402,6 +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:

.gitignore

@@ -10,7 +10,7 @@ env*/
 /TODO.md
 /postgres-data/
 .DS_Store
-examples/pydantic_ai_examples/.chat_app_messages.sqlite
+.chat_app_messages.sqlite
 .cache/
 .vscode/
 /question_graph_history.json

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
 )

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, 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).
+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, and Outlines. 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).
@@ -50,8 +50,8 @@ Designed to give your IDE or AI coding agent as much context as possible for aut
 5. **Powerful Evals**:
 Enables you to systematically test and [evaluate](https://ai.pydantic.dev/evals) the performance and accuracy of the agentic systems you build, and monitor the performance over time in Pydantic Logfire.
 
-6. **MCP, A2A, and AG-UI**:
-Integrates the [Model Context Protocol](https://ai.pydantic.dev/mcp/client), [Agent2Agent](https://ai.pydantic.dev/a2a), and [AG-UI](https://ai.pydantic.dev/ag-ui) standards to give your agent access to external tools and data, let it interoperate with other agents, and build interactive applications with streaming event-based communication.
+6. **MCP, A2A, and UI**:
+Integrates the [Model Context Protocol](https://ai.pydantic.dev/mcp/overview), [Agent2Agent](https://ai.pydantic.dev/a2a), and various [UI event stream](https://ai.pydantic.dev/ui/overview) standards to give your agent access to external tools and data, let it interoperate with other agents, and build interactive applications with streaming event-based communication.
 
 7. **Human-in-the-Loop Tool Approval**:
 Easily lets you flag that certain tool calls [require approval](https://ai.pydantic.dev/deferred-tools#human-in-the-loop-tool-approval) before they can proceed, possibly depending on tool call arguments, conversation history, or user preferences.

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-site/src/index.ts

@@ -55,6 +55,7 @@ const redirect_lookup: Record<string, string> = {
   '/examples': 'examples/setup/',
   '/mcp': '/mcp/overview/',
   '/models': '/models/overview/',
+  '/ag-ui': '/ui/ag-ui/'
 }
 
 function redirect(pathname: string): string | null {

docs-site/wrangler.toml

@@ -4,6 +4,7 @@ compatibility_date = "2025-06-17"
 routes = ["ai.pydantic.dev/*"]
 main = "src/index.ts"
 workers_dev = false
+preview_urls = true
 compatibility_flags = [ "nodejs_compat_v2" ]
 
 [vars]