Latency eval harness consumes PerfTrace (CL-5174) - #310
Merged
Conversation
TheGreatAxios
force-pushed
the
stack/w3a-cl-5169-dump-rollup
branch
from
August 4, 2026 16:22
480fee5 to
be80788
Compare
TheGreatAxios
force-pushed
the
stack/w4b-cl-5174-eval-harness
branch
2 times, most recently
from
August 4, 2026 17:18
f14089e to
67f312e
Compare
TheGreatAxios
force-pushed
the
stack/w3a-cl-5169-dump-rollup
branch
from
August 4, 2026 18:10
e5c4bd5 to
0de33bb
Compare
TheGreatAxios
force-pushed
the
stack/w4b-cl-5174-eval-harness
branch
from
August 4, 2026 18:11
67f312e to
2bf37e9
Compare
TheGreatAxios
force-pushed
the
stack/w3a-cl-5169-dump-rollup
branch
2 times, most recently
from
August 4, 2026 22:48
a5132c2 to
b0471c9
Compare
Eval helpers assert phase presence, nesting, and turn inference+tools regressions against a golden multi-tool fixture and the reactor observer pipeline.
Replace the live no-op relative-magnitude check with real wall ordering, add fail-path tests for assert helpers, drop pure rollup arithmetic re-tests, and document assert layer ownership vs rollup.test.ts.
TheGreatAxios
force-pushed
the
stack/w4b-cl-5174-eval-harness
branch
from
August 4, 2026 22:49
2bf37e9 to
a72f16a
Compare
TheGreatAxios
changed the base branch from
stack/w3a-cl-5169-dump-rollup
to
main
August 4, 2026 22:49
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stack
PerfTrace stack 4b/8 — base:
stack/w3a-cl-5169-dump-rollup(#307)Linear
https://linear.app/abklabs/issue/CL-5174/latency-eval-harness-consumes-perftrace
Summary
Assertion helpers for phase presence/magnitudes, multi-tool golden fixture, regression: turn has inference + tools when tools ran.
Test evidence
Merge note
Merge after #307 (CL-5169 dump/rollup).