fix(pydantic-ai): Set system instructions after instructions are set on the request object

[alexander-alderman-webb]

Description

Add the test_invoke_agent_streaming_with_instructions test to ensure system instructions are set on the streaming path. The test is identical to test_invoke_agent_with_instructions except that agent.run_stream() is used instead of agent.run().

Remove the messages parameter from ai_client_span() and manually call _set_input_messages() on AI Client Spans.

Move functions required for _set_input_messages() from pydantic_ai.spans.* modules to pydantic_ai.utils.

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 🐛

• (pydantic-ai) Set system instructions after instructions are set on the request object by alexander-alderman-webb in #5947

Internal Changes 🔧

• (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 📊

✅ 13 passed | Total: 13 | Pass Rate: 100% | Execution Time: 6.83s

📊 Comparison with Base Branch

Metric	Change
Total Tests	—
Passed Tests	—
Failed Tests	—
Skipped Tests	—

✨ No test changes detected

All tests are passing successfully.

❌ Patch coverage is 3.23%. Project has 14900 uncovered lines.
✅ Project coverage is 29.8%. Comparing base (base) to head (head).

Files with missing lines (2)

File	Patch %	Lines
agent_run.py	0.00%	⚠️ 100 Missing
__init__.py	8.96%	⚠️ 61 Missing

Coverage diff

@@            Coverage Diff             @@
##          main       #PR       +/-##
==========================================
+ Coverage    25.09%    29.80%    +4.71%
==========================================
  Files          191       191         —
  Lines        21165     21224       +59
  Branches      6946      6966       +20
==========================================
+ Hits          5310      6324     +1014
- Misses       15855     14900      -955
- Partials       432       477       +45

---

Generated by Codecov Action

[cursor]

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

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.}

^{Reviewed by Cursor Bugbot for commit 49dc6f4. Configure here.}