fix(pydantic-ai): Use first-class hooks when available

[alexander-alderman-webb]

Description

Resolve tox failure by using the pydantic-ai hooks when available. See the failing run in #5945

See changes to instruction setting in https://github.com/pydantic/pydantic-ai/pull/4123/changes#diff-71730070455237accebd709ba7fe41ce60edbd238af02e7d86a208cf8f10ab12. Per-run system instructions are now added inside ModelRequestNode.run and ModelRequestNode.stream, and are therefore not available before the functions run.

Issues

Reminders

• Please add tests to validate your changes, and lint your code using tox -e linters.
• Add GH Issue ID & Linear ID (if applicable)
• PR title should use conventional commit style (feat:, fix:, ref:, meta:)
• For external contributors: CONTRIBUTING.md, Sentry SDK development docs, Discord community

[github-actions]

Semver Impact of This PR

🟢 Patch (bug fixes)

📋 Changelog Preview

This is how your changes will appear in the changelog.
Entries from this PR are highlighted with a left border (blockquote style).

---

New Features ✨

• (ai) Redact base64 data URLs in image_url content blocks by ericapisani in #5953
• (integrations) Instrument pyreqwest tracing by servusdei2018 in #5682

Bug Fixes 🐛

Anthropic

• Capture exceptions for stream() calls by alexander-alderman-webb in #5950
• Stop setting transaction status when child span fails by alexander-alderman-webb in #5717
• Only finish relevant spans in .create() patches by alexander-alderman-webb in #5716

Other

• (pydantic-ai) Use first-class hooks when available by alexander-alderman-webb in #5947

• (wsgi) Respect HTTP_X_FORWARDED_PROTO in request.url construction by sl0thentr0py in #5963

Internal Changes 🔧

• (anthropic) Separate sync and async .create() patches by alexander-alderman-webb in #5715
• (openai) Split token counting by API for easier deprecation by ericapisani in #5930
• (opentelemetry) Ignore mypy error by alexander-alderman-webb in #5927
• Fix license metadata in setup.py by sl0thentr0py in #5934
• Update validate-pr workflow by stephanie-anderson in #5931

---

_{🤖 This preview updates automatically when you update the PR.}

[github-actions]

Codecov Results 📊

✅ 115 passed | Total: 115 | Pass Rate: 100% | Execution Time: 13.76s

All tests are passing successfully.

❌ Patch coverage is 4.23%. Project has 15878 uncovered lines.

Files with missing lines (2)

File	Patch %	Lines
agent_run.py	0.00%	⚠️ 100 Missing
__init__.py	9.21%	⚠️ 69 Missing

---

Generated by Codecov Action

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

Autofix Details

Bugbot Autofix prepared a fix for the issue found in the latest run.

• ✅ Fixed: Streaming path sets input messages before model execution
  • Moved _set_input_messages in the streaming wrapper to execute after the original stream context finishes so instruction mutations done during execution are captured.

Or push these changes by commenting:

@cursor push 6153a56a6a

Preview (6153a56a6a)

diff --git a/sentry_sdk/integrations/pydantic_ai/patches/graph_nodes.py b/sentry_sdk/integrations/pydantic_ai/patches/graph_nodes.py
--- a/sentry_sdk/integrations/pydantic_ai/patches/graph_nodes.py
+++ b/sentry_sdk/integrations/pydantic_ai/patches/graph_nodes.py
@@ -91,13 +91,13 @@
 
             # Create chat span for streaming request
             with ai_client_span(None, model, model_settings) as span:
-                if messages:
-                    _set_input_messages(span, messages)
-
                 # Call the original stream method
                 async with original_stream_method(self, ctx) as stream:
                     yield stream
 
+                if messages:
+                    _set_input_messages(span, messages)
+
                 # After streaming completes, update span with response data
                 # The ModelRequestNode stores the final response in _result
                 model_response = None

_{This Bugbot Autofix run was free. To enable autofix for future PRs, go to the Cursor dashboard.}

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit ef7802a. Configure here.}

[cursor]

Tests create agents before hooks are registered

Medium Severity

Several tool-related tests call get_test_agent() before sentry_init(), so the agent is constructed before register_hooks patches Agent.__init__. These agents never receive the Hooks capability. When hooks are available, the fallback patches (_patch_graph_nodes, _patch_model_request) are skipped, so no gen_ai.chat spans are created. Assertions iterating over chat_spans (e.g., checking gen_ai.request.available_tools or gen_ai.response.streaming) pass vacuously because the list is empty. Affected tests include test_agent_with_tools, test_agent_with_tools_streaming, test_agent_with_tool_model_retry, test_agent_with_tool_validation_error, test_without_pii_tools, and test_include_prompts_false_with_tools.

Additional Locations (2)

• tests/integrations/pydantic_ai/test_pydantic_ai.py#L522-L523
• tests/integrations/pydantic_ai/test_pydantic_ai.py#L455-L456

 

^{Reviewed by Cursor Bugbot for commit ef7802a. Configure here.}