fix(ai-trace): Minimize system prompts in trace input#114701
Merged
obostjancic merged 6 commits intomasterfrom May 4, 2026
Merged
Conversation
Keep AI input sections open while rendering system prompt messages inside a collapsed disclosure by default. User messages remain visible so the trace drawer still shows the active prompt context without an extra click.\n\nRefs TET-2282\nCo-Authored-By: OpenAI Codex <noreply@openai.com>
Normalize structured system fields as system messages so they use the same collapsed rendering path as string system prompts. This keeps user prompts visible while minimizing system prompt content by default.\n\nRefs TET-2282\nCo-Authored-By: OpenAI Codex <noreply@openai.com>
Cast the focused AI input test fixture through unknown before treating it as a trace node. The fixture intentionally includes only the fields exercised by AIInputSection.\n\nRefs TET-2282\nCo-Authored-By: OpenAI Codex <noreply@openai.com>
Remove the nested disclosure affordance for system messages and rely on the existing show-more clipping behavior for structured system prompt values. String system prompts keep rendering as normal message content.\n\nRefs TET-2282\nCo-Authored-By: OpenAI Codex <noreply@openai.com>
Wrap all rendered system prompt content in the show-more clipping container. This covers gen_ai.system_instructions values that are strings but render as JSON, where the JSON renderer expands keys by default.\n\nRefs TET-2282\nCo-Authored-By: OpenAI Codex <noreply@openai.com>
…prompt-by-default-in-llm-trace-view
constantinius
approved these changes
May 4, 2026
3 tasks
cleptric
pushed a commit
that referenced
this pull request
May 5, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Render system prompt messages in the AI input section behind a collapsed disclosure by default. User messages remain visible, so trace details still show the active prompt context without forcing users to expand the whole Input section.
Structured
systemfields now normalize as system messages too, so object-shaped system prompts use the same collapsed rendering path as string prompts.Before:

After:

Fixes TET-2282