Repository navigation
Description
#128 shipped composer-2.5, four per-repo spend limits and the review-deep escape hatch; #129 moved this repo's own self-caller onto it. Nothing changes for the other enrolled callers until each moves its pin — they are still reviewing with grok-4.6 at effort xhigh and no caps at all.
A pin-only bump is unsafe here
Each caller's concurrency group mirrors the callable's job if:, and review-deep is now in both. A caller that bumps the pin without adding review-deep to its own group expression buckets a deep review as other, where the next stray event cancels the live run before the job condition is evaluated — so cancel_previous never runs and the paid Cursor agent behind it keeps burning. Both edits go in one commit.
The correct expression is in the copy-paste template beside the job if: in .github/workflows/cursor-review.yml. The change per caller:
-contains(fromJSON('["review-now","review-p0","review-p1"]'), github.event.label.name)
+contains(fromJSON('["review-now","review-p0","review-p1","review-deep"]'), github.event.label.name)
plus the pin to 0a3aa8bfc (or later main).
Per caller
- Bump the pin and the group expression in the same commit
- Create the
review-deeplabel (it currently exists only in this repo) - Set
daily-capif 12/day is wrong for that repo — it is deliberately per-repo, because some need more oversight than others
Also still open
- composer-2.5 has not yet completed an end-to-end review. Its launch shape is verified live (
POST /v1/agentswith{"id":"composer-2.5","params":[{"id":"fast","value":"false"}]}and noeffortkey →201), and the model id is confirmed againstGET /v1/models, but no review has run start-to-finish on it: this repo has been over its own new daily cap since the pin landed. Watch the first review after the 24h window clears. review-deephas never been exercised end-to-end. Its three legs are each verified independently (the label is in the jobif:at the pinned SHA, the gate bypass is unit-tested, grok-4.6/xhigh launches in production) but their composition is not. Not worth a paid grok-xhigh run purely to test; worth watching the first genuine use.- Six stale
cursor-review-*branches on the remote from earlier sessions (budget-routing,callable,launch-shape,path-prefix,self-enroll,self-pin) — not mine to prune.
Context: the driver was 99 review agents launched against 2 implementation lanes in one evening. Unit economics are ~0.131% of the monthly pool per review, so the plan affords roughly 25 reviews/day; 139 ran on 2026-09-19.
Activity
loganrenz commentedon Sep 20, 2026
Caller audit — narduk-libs is the one urgent case, the other eight are routine
Evidence relayed from the portals program (two of its lanes), then verified here against the repos and the Cursor API rather than taken on trust.
synchronize852e0f0c(#120)246013d4(#125)a3557de7(#128)narduk-libs is on the oldest callable and it is the expensive one on every axis at once. At
852e0f0cthe jobif:is bare${{ inputs.enabled }}— no draft guard, nono-ai-reviewguard, no label gating — and itsfastinput defaults totrue. Combined withsynchronizein its triggers, that repo reviews every push, including pushes to drafts, at grok-4.6 / effort xhigh / fast true.fastis a real price multiplier on grok, not just on composer (verified, cursor.com/docs/models-and-pricing):fast: false(#128 default)grok fast is exactly 2× standard grok, and 5–8× the new default depending on the axis — cache read, which dominates an agentic review, is 5×. So a narduk-libs review costs roughly six times what the same review costs at the #128 default, and it runs on every push rather than once per head.
This was not in the #128 cost model, which assumed
fast=falseestate-wide. It does not change the measured baseline — that came from Cursor's own agent ledger, which counts launched agents at whatever price — but it does mean the spend was more concentrated in one repo than the reviews-per-PR multipliers suggested.Priority
synchronizeremoves push-review from a repo with active lanes, and on852e0f0citsreview-nowis inert — so those lanes currently have no working re-request path. Moving toa3557de7gives them a workingreview-nowandreview-deepin exchange. Land the pin, the group expression, and the label together.246013d4are routine: correct triggers already, but still grok-4.6/xhigh and no caps at all.Two related wastes, verified
reviews: []. Either finish the enrolment or close it; right now it is paying for coverage it does not have.CURSOR_CLOUD_AGENTS_API_KEYexits green in ~8s having reviewed nothing (reported for lakestat-us and narduk-data). Those runs cost no Cursor quota — a skipped run never launches an agent — but they make a check-context-based coverage metric read as covered when it is not. Worth a follow-up so "green" is not mistaken for "reviewed".Evidence from the portals master orchestrator session; pins, triggers, input defaults and prices re-verified here before recording.
Move the reviewer off the every-push grok-fast configuration (#618)
loganrenz commentedon Sep 20, 2026
Progress: narduk-libs done, buoys blocked upstream
narduk-libs — merged (#618,
911a9fcc). The estate's single biggest Cursor line item is closed.The measured number, from the new cap's own first run there: "27 review(s) in the last 24h, the cap is 12." The #128 analysis put the entire estate's affordable rate at ~25 reviews/day. One repo was running 27/day at ~6× the new default unit cost. That is the concrete shape of "13% of usage in an evening".
All four parts landed together — pin →
a3557de7,synchronizedropped,labeledadded (its absence is whyreview-nowwas inert there: no label could reach the job), and aconcurrencygroup verified as an exact string match against the canonical template.review-deeplabel created.buoys — change complete, blocked on a dependency (#258).
Two corrections to my earlier comment on that PR:
@narduk-enterprises/narduk-analytics@1.21.7ships.tsthat does not typecheck in a consumer's context (requireMutationBody's result collapses to{}). narduk-libs' own package lane passes because it typechecks inside that workspace. Filed as narduk-libs#621.buoys
mainpins the same1.21.7, so main is latently red — its last run predates this and has not re-run since 2026-09-19T23:12. Worth knowing before anyone opens a buoys PR expecting green.The enrolment change itself is correct and ready:
a3557de7, nosynchronize,labeledadded, group an exact template match, and the full class label set created (onlyno-ai-reviewexisted). Landing it as originally written would have enrolled buoys on the same 852e0f0 every-push grok-fast config narduk-libs just came off.Remaining
Eight callers on
246013d4— agent-infrastructure, fleet, lakestat-us, narduk-data, operator-portal, riverstatus, runners, stonx. Correct triggers already, but still grok-4.6/xhigh and no caps. Each needs the same four-part change plus areview-deeplabel.composer-2.5 still has not completed an end-to-end review — ironically prevented by the caps themselves, since every repo tried so far was over its window. The first PR in narduk-libs once its 24h drains (no more push-review feeding it) is the one to watch.
loganrenz commentedon Oct 8, 2026
Done: every caller in the 2026-09-20 audit moved to the spend-limited callable (narduk-libs#618, agent-infrastructure#1604, fleet#473, lakestat-us#143, narduk-data#496, operator-portal#398, riverstatus#211, runners#167, stonx#809, all merged 2026-09-20). The Actions reviewer was then retired estate-wide in #166 (2026-09-28) in favor of the runners PR review bot, so no caller is left on the uncapped config.