fix(tracing): Strip runtime turn context from observable input messages

[sergical]

Summary

• Strips <runtime-turn-context> content parts from user messages before serializing to gen_ai.input.messages on gen_ai.chat spans.
• Unwraps <current-instruction> to extract just the user's actual text.
• Strips <thread-background>, <session-context>, <turn-context> blocks so prior assistant responses don't bleed into user messages.

After this change, the Conversations view shows clean user messages instead of internal runtime metadata.

Context

The Sentry Conversations view reads gen_ai.input.messages from gen_ai.chat spans and extracts user messages via messages.findLast(m => m.role === 'user'). Junior's user messages contained:

1. A <runtime-turn-context> content part with skills, config, and capabilities (separate content part — now dropped)
2. XML wrappers around the user text: <thread-background> (prior conversation history including assistant responses), <session-context>, <turn-context>, and <current-instruction> (now unwrapped/stripped)

The runtime context is still available via gen_ai.system_instructions on the span, so no observability is lost.

Test plan

• Unit test: verifies all XML blocks are stripped and only user instruction text remains
• Existing traced-stream tests pass (9/9)
• Typecheck passes
• Verify clean user messages in Conversations view after deploy

🤖 Generated with Claude Code

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
junior-docs	Ready	Preview, Comment	May 22, 2026 7:18pm

[dcramer]

im not totally understanding of the problem

i dont want the messages being sent to sentry to be at all different than the actual messages sent upstream, but if we have a giant xml tag wrapping everything thats probably some minor cleanup to be done (i havent hand audited the prompt)

[sergical]

maybe a non issue, when i look at it, i see duplication between content on subsequent user turns via the xml tags, but idk if thats just the expected ux or we can clean it up a bit 🤷

Mostly created as a draft to share with Ogi and see what their feedback is like

[dcramer]

do you mean in the thread transcript bits? if there is i def think this is more of a bug in the context gathering than a need for a change in reporting

definitely the reporting should never falsify records