docs(observe): Voice observability concept revamp#702
Open
YashMohan23 wants to merge 3 commits into
Open
Conversation
- Remove the 'Trace a LiveKit voice app' card: its target /docs/traceai/auto/livekit is not live on this branch, and we don't card non-live pages. - Fix invalid card icon: compass -> layer-group (compass is not in this branch's Card.astro icon map, so it rendered blank). - CardGroup down to cols=2 per the count % 3 rule. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Split the run-on worked example into clean sentences; drop the captured-fields restatement the opener already covers. - Trim 'Why it matters' to the actual motivation; cut the decorative tricolon and the eval/alert/filter list already stated up top. - Link evals at its true first mention (the opener), not later. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- New 'Inside a voice call' section: a turn span breaks down into speech-to-text, the model call, and text-to-speech (grounded in the LiveKit/Pipecat auto-instrumentation), so a reader sees what a voice trace looks like inside, not just that a call is a trace. - New Mermaid of the call structure (replaces the two-paths plumbing diagram). - Two ingestion paths now a scannable table (managed Vapi/Retell vs LiveKit/Pipecat auto-instrumentation). - Cross-link to the observability model. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
YashMohan23
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What this is
Revamps the Voice observability concept page for depth, one-read clarity, and full compliance with the docs review checklist.
Changes
Inside a voice callsection — a turn span breaks down into speech-to-text, the model call, and text-to-speech (grounded in the LiveKit/Pipecat auto-instrumentation), so a reader sees what a voice trace looks like inside, not just that a call is a trace.compass→layer-group), dropped tocols={2}.evalsat its true first mention.Checklist
Concept (Explanation) page: minimal frontmatter, no "About", one Diátaxis mode, one Mermaid, forward "Keep exploring" cards, Vapi + Retell only (no ElevenLabs), no em-dashes, all links + icons valid, grounded in code.
Diátaxis: Explanation · depth 4 · ease medium.