Latency harness for the deterministic hot path - #8
Merged
Conversation
Measures Tier 0 (phrase) and Tier 1 (rules) cold/median/p95 over the golden inputs on every CI run. Baseline: sub-millisecond. Gates are order-of-magnitude guards (50ms/250ms p95) that catch accidental network/model calls or complexity blowups in the offline path — the end-to-end Section 4 budgets land with the Phase 2 app harness. Suite: 147 passed. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes out MASTER_PLAN Phase 1: Tier 0/Tier 1 latency measured and printed in every CI run (baseline sub-millisecond), with order-of-magnitude p95 gates (50ms/250ms) so nothing heavy can sneak into the offline path unnoticed.
🤖 Generated with Claude Code