Conversation
`run_agentic_what_if` already computed `pass_power_k`; the evaluator never read it, asking `if not summary.pass_at_k` for the verdict. `--gate power` on a flaky item therefore reported a pass on the strength of one good run out of K -- the exact case the gate exists to catch, reporting the opposite of what happened. The evaluator now takes `gate` like every other multi-run kind, asks `gate_passed(...)`, and carries the gate's note into the assertion message, which matters here because the message body describes the BEST run and under pass^K that can be one that passed. It also stamps the gate on the run metadata and publishes pass@K/pass^K/gate_passed, so a gated run is readable in Langfuse rather than only in the exit code. The default is unchanged: without --gate this is pass@K exactly as before, pinned by a test alongside the power case. The power test fails against the previous code. Found by CodeRabbit on #1798, where the same gap was fixed for forecasting. `agentic_anomaly_detection` has it too and is fixed on its own branch, #1801, because that evaluator does not exist on master yet. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
Warning Review limit reached
This review includes 3 billable files and costs up to $0.75. Or wait 33 minutes for your next included review. View limit detailsLimit details: You’ve used the included review currently available. Review configuration: ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Advanced Run ID: 📒 Files selected for processing (3)
Comment |
Tomkess
added a commit
that referenced
this pull request
Sep 24, 2026
`run_agentic_anomaly_detection` already computed `pass_power_k`; the evaluator never read it, asking `if not summary.pass_at_k` for the verdict, so `--gate power` on a flaky item reported a pass on the strength of one good run out of K. Wired the same way as the other multi-run kinds: the evaluator takes `gate`, the dispatch passes it, `gate_passed(...)` decides, the gate's note goes into the assertion message -- which matters because the body describes the BEST run, and under pass^K that can be one that passed -- and pass@K/pass^K/gate_passed reach Langfuse alongside the run metadata stamp. The default is unchanged: without --gate this is pass@K exactly as before, pinned by a test beside the power case. The power test fails against the previous code. Found by CodeRabbit on #1798. Forecasting is fixed there; what-if, which is already on master, in #1831. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## master #1831 +/- ##
=======================================
Coverage 83.08% 83.08%
=======================================
Files 330 330
Lines 21763 21767 +4
=======================================
+ Hits 18082 18086 +4
Misses 3681 3681 ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
Tomkess
added a commit
that referenced
this pull request
Sep 24, 2026
`run_agentic_anomaly_detection` already computed `pass_power_k`; the evaluator never read it, asking `if not summary.pass_at_k` for the verdict, so `--gate power` on a flaky item reported a pass on the strength of one good run out of K. Wired the same way as the other multi-run kinds: the evaluator takes `gate`, the dispatch passes it, `gate_passed(...)` decides, the gate's note goes into the assertion message -- which matters because the body describes the BEST run, and under pass^K that can be one that passed -- and pass@K/pass^K/gate_passed reach Langfuse alongside the run metadata stamp. The default is unchanged: without --gate this is pass@K exactly as before, pinned by a test beside the power case. The power test fails against the previous code. Found by CodeRabbit on #1798. Forecasting is fixed there; what-if, which is already on master, in #1831. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> (cherry picked from commit 5632da8)
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.
The bug
run_agentic_what_ifcomputespass_power_k. The evaluator never read it:So
--gate poweron a flaky item passes on one good run out of K — the exact case the gate exists to catch, and the report says the opposite of what happened.This is live: what-if merged this morning in #1799.
The fix
What-if now does what the other eight multi-run kinds already do:
gate: EvalGate = DEFAULT_GATE, and the dispatch passes itgate_passed(...)for the verdictgate_failure_note(...)into the assertion message — this matters, because the message body describes the best run, which under pass^K can be a run that passed, so without the note a failing item reads like a passing oneDefault behaviour is unchanged. Without
--gatethis is pass@K exactly as before, pinned by its own test.Verification
Three tests: the power gate failing a 1-of-2 item,
anystill passing the same item, and the default matchingany. Reverting the one-line verdict change makes the power test fail, so it is testing the fix rather than the scaffolding.1209 tests pass,
ruff checkandruff format --checkclean.Related
Found by CodeRabbit on #1798, where the same gap is fixed for forecasting.
agentic_anomaly_detectionhas it too — fixed on #1801, since that evaluator is not on master yet. After those three, the only ungated kind isagentic_conversation, which is ungated by design.🤖 Generated with Claude Code