Document time-to-first-token surfaces on the LLMs page#2050
Draft
dmontagu wants to merge 3 commits into
Draft
Conversation
Covers the First token headline card, the Time to first token charts on the LLM and agent detail pages, the driving attributes (gen_ai.client.operation.time_to_first_chunk with gen_ai.server.time_to_first_token fallback), and a troubleshooting row for empty charts. Ships with pydantic/platform#23856. Claude-Session: https://claude.ai/code/session_01NbiZJHnx65j4ibTDe6xr1T
Gives the TTFT paragraph its own heading (a stable #time-to-first-token anchor the product links to) and adds a warning admonition explaining the underlying OTel GenAI convention is at Development stability. Claude-Session: https://claude.ai/code/session_01NbiZJHnx65j4ibTDe6xr1T
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Documents the new time-to-first-token surfaces shipping with pydantic/platform#23856 (UI) and pydantic/pydantic-ai#5967 (SDK emission) in
docs/guides/web-ui/llms.md:gen_ai.client.operation.time_to_first_chunk(seconds) with thegen_ai.server.time_to_first_tokenfallback — matches themodel_callsmaterialized view's coalesce exactly.Merge timing
Should merge around when platform#23856 ships, since it describes the six-card layout that PR introduces.
https://claude.ai/code/session_01NbiZJHnx65j4ibTDe6xr1T