GitNexus/.github
Gergo Magyar aefb162280 docs(bench): no drop ratchet needed; correct a stale CI claim (#2766)
Two findings, both negative, both worth recording so they are not
re-litigated.

NO RATCHET. The plan's R10 set a ZERO supported-shape drop target, and
review correctly found it contradicts R12: a site whose normalized name
matches more than one class MUST decline, a decline records a drop, and
names like Service/Handler/Client collide routinely in large Go and Java
codebases. The proposed repair was a ratchet — the count may not rise
above the last measured value.

Neither is needed. `measure.mjs --check` already asserts EXACT MATCH
against the committed baseline, which is strictly stronger: the count
cannot rise or fall without a deliberate `--update-baseline`, and that
path prints an instruction to explain the movement. A ratchet would be a
weakening, not a fix. The gate now also covers `callDropsByShape`, since
the shape census joined the gated projection.

STALE CI CLAIM. The gate's comment named `repos[0]` as a shape that
"emits no edge AND no drop". That stopped being true in this series:
Case 0's gate now accepts a minted receiver chain instead of testing the
receiver's punctuation, so subscript receivers record a drop and are
countable — 13 shapes moved INVISIBLE -> VISIBLE. `?.` and explicit type
args are still invisible on some languages, so the shape arm still earns
its keep, but the example was wrong and a wrong example in a gate comment
is how the next person mis-reasons about what the gate covers.

DEFERRED, explicitly: the `impact` risk-cutoff recalibration. Added edges
push symbols toward the absolute cutoffs (`directCount >= 30`,
`impacted.length >= 200`), so edits read HIGHER risk without being more
dangerous. Real, but measuring it honestly needs a corpus large enough
for those thresholds to bind, and the committed fixtures are nowhere near
200 impacted symbols. Recorded as owed rather than inventing a number
from fixtures that cannot exercise it.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-01 16:28:31 +00:00
..
actions ci: update setup composites to setup-node v6 (#2451) 2026-07-14 17:11:26 +01:00
claude-canary-runtime ci: move Node pins to the 22.18 floor 2026-07-21 10:09:34 +00:00
gitnexus-review-runtime ci: move Node pins to the 22.18 floor 2026-07-21 10:09:34 +00:00
ISSUE_TEMPLATE docs: agent development framework, GitHub templates, eval refactor (#479) 2026-03-25 06:48:41 +00:00
prompts feat(review): add PR reviewer swarm agents (#1851) 2026-05-29 18:24:16 +01:00
scripts fix(ci): stop the placeholder review, verify citations, repair once (#2733) 2026-07-28 18:51:01 +01:00
workflows docs(bench): no drop ratchet needed; correct a stale CI claim (#2766) 2026-08-01 16:28:31 +00:00
actionlint.yaml fix(eval): self-hosted skill-evolution runner + sandbox Python 3 trust fix (#2600) 2026-07-21 14:40:20 +01:00
CODEOWNERS Update code owners in CODEOWNERS file 2026-07-02 08:05:15 +01:00
dependabot.yml chore(deps): bump github/codeql-action/analyze from 4.36.2 to 4.37.0 (#2506) 2026-07-17 11:40:51 +01:00
FUNDING.yml Fix duplicate GitHub funding entries 2026-07-02 08:03:31 +01:00
PULL_REQUEST_TEMPLATE.md docs: agent development framework, GitHub templates, eval refactor (#479) 2026-03-25 06:48:41 +00:00
release-drafter.yml ci: standardize workflow concurrency and automate release-note labeling (#837) 2026-04-15 13:24:53 +01:00
release.yml feat: configure prettier with pre-commit hook (#563) 2026-03-28 14:58:04 +00:00
vendored-grammars.json fix(lang-kotlin): support fun interface extraction via tree-sitter-kotlin re-vendor (#2271) 2026-06-23 10:01:28 +01:00
zizmor.yml fix(lang-kotlin): support fun interface extraction via tree-sitter-kotlin re-vendor (#2271) 2026-06-23 10:01:28 +01:00