tegwick
c38ecd9da3
Some checks failed
ci / check (push) Failing after 4s
CB-EV-0010. The pass's own verdict on the tier it ran at. Full-weight review withdrew the capability port the declaration was made to build. A tier-S pass has no step 2 and would have shipped it, and stage 2 would have found it unimplementable — which is what CommitWindow is already on record in this repo for doing. Two corrections of the survey's own numbers, compounding: AM-4a headroom 3,750 claimed -> 92,798 measured (25x) cheapest windowed 480,501 claimed -> 140,079 measured (3.4x) headline ratio 128x -> 1.5x (85x) The prediction from CB-EV-0009 §4 held: meta budget reads 0%, published in advance and unfalsified. A correction that is now a pattern: CB-EV-0009 reported CB-WP-0011 at 45 responses / $4.23 / 0.094; final is 71 / $7.02 / 0.099. Still the cheapest pass, so the conclusion stands. But that is the second consecutive evidence file to report its own pass's cost low — a pass cannot measure its own cost, and one quoting its own is quoting a floor. First priced tier comparison on a single subject: 0.123 $/response at L against 0.099 at S — 24% more, for a pass that found the two errors above. On one data point, step 2 is cheap. Not shipped, and said plainly: the emitted JavaScript has never been executed. The socket loop is tested end to end with synthetic HTTP and the page is asserted against as a parsed document, but no browser engine has run it. INTENT stage 1 therefore stays open even though all four of its named deliverables now exist. SH-3 reads 0.0% for a sixth consecutive pass and remains the oldest unargued number in the project. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
137 lines
5.7 KiB
TOML
137 lines
5.7 KiB
TOML
# The gate registry (ADR-0006 D3, CB-WP-0009 T02).
|
|
#
|
|
# A gate without an expiry is a permanent tax justified once. Every
|
|
# standing control mechanism gets an entry here saying what it checks,
|
|
# what it has actually **caught**, when its keep-or-kill argument is due,
|
|
# and what would retire it.
|
|
#
|
|
# `make gate-review` reports what is overdue and what has caught nothing.
|
|
# It reports; it does not fail the build — CB-RES-0005 §4: a gate that
|
|
# blocks the remedy when the metric breaches is a trap, not a gate.
|
|
#
|
|
# `caught` is the load-bearing field. An empty `caught` is not proof a
|
|
# gate is useless — it may be preventing rather than missing — but it
|
|
# means the argument has to be made out loud on `review_by`.
|
|
|
|
# Targets in `make all` that are build or acceptance steps rather than
|
|
# *control* gates — they measure the product, not how we work. Listed
|
|
# explicitly so a new target has to be classified rather than ignored;
|
|
# `loop-lint` fails when a target is in neither list.
|
|
not_control_gates = [
|
|
"check", "test", "sim", "bench-test", "size-metrics", "runtime-metrics",
|
|
"am6", "replay-test", "dep-weight", "self-tests", "env-test",
|
|
]
|
|
|
|
[[gate]]
|
|
id = "CB-01/CB-02"
|
|
name = "cost budget"
|
|
target = "cost-budget"
|
|
checks = "spend since the last commit; soft $10, hard $22"
|
|
added = "2026-07-30"
|
|
review_by = "2026-11-30"
|
|
caught = [
|
|
"CB-WP-0005: hard breach forced the Phase C re-plan",
|
|
"CB-WP-0006 T07: $12.06 in one task, the pass's most expensive",
|
|
]
|
|
retire_if = "two consecutive passes never approach the soft line, or commits get small enough that the window is always trivial"
|
|
|
|
[[gate]]
|
|
id = "SH-1/SH-2/SH-3"
|
|
name = "session-shape budget"
|
|
target = "shape-budget"
|
|
checks = "mean and p90 context, and batching rate, since the last commit"
|
|
added = "2026-08-01"
|
|
review_by = "2026-11-30"
|
|
caught = [
|
|
"first run fired HARD at 656,574 against a 300,000 ceiling, which is what prompted the compaction before CB-WP-0008",
|
|
]
|
|
retire_if = "context stops correlating with cost, or the model's context handling makes the number unactionable"
|
|
|
|
[[gate]]
|
|
id = "M-D1-MUT"
|
|
name = "mutation coverage of acceptance rows"
|
|
target = "mutation-check"
|
|
checks = "each acceptance row's assertion must go red for a stated reason when mutated"
|
|
added = "2026-07-31"
|
|
review_by = "2026-12-31"
|
|
caught = [
|
|
"AM-6 measuring contention, not throughput",
|
|
"AM-5's 61% measurement error under load",
|
|
"peak RSS over-reported 3x",
|
|
"K10's first round trip not reproducing",
|
|
"the bench workload existing twice",
|
|
"AM-2's expect matching its own passing output (EXPECT-VACUOUS)",
|
|
]
|
|
retire_if = "a full pass adds rows without finding anything, twice running — the harness costs real money per run"
|
|
|
|
[[gate]]
|
|
id = "DFD"
|
|
name = "single source of fact"
|
|
target = "facts-check"
|
|
checks = "every tagged number in the docs matches the tool that measures it"
|
|
added = "2026-07-31"
|
|
review_by = "2026-12-31"
|
|
caught = [
|
|
"gr_scenarios stale at 21 after CB-WP-0008 T03 added three scenarios",
|
|
]
|
|
retire_if = "the untagged-literal count reaches zero and stays there, meaning the docs stopped restating measured numbers"
|
|
|
|
[[gate]]
|
|
id = "AM-1b"
|
|
name = "kernel spec->code link"
|
|
target = "coverage"
|
|
checks = "every numbered K-rule is named in the source; binds 2026-08-31"
|
|
added = "2026-07-31"
|
|
review_by = "2026-08-31"
|
|
caught = [
|
|
"3 unlinked K-rules at introduction (15/18); 18/18 today",
|
|
]
|
|
retire_if = "it stays at 100% through two passes that add kernel rules — at that point it is measuring a habit, not enforcing one"
|
|
|
|
[[gate]]
|
|
id = "META-25"
|
|
name = "meta budget"
|
|
target = "status"
|
|
checks = "share of the trailing 3 passes spent on the loop itself; soft 25%"
|
|
added = "2026-08-01"
|
|
review_by = "2026-11-30"
|
|
caught = [
|
|
"its own cumulative-window defect, reported in CB-EV-0007 §3 and fixed by CB-WP-0009 T01",
|
|
]
|
|
retire_if = "product and meta stop being separable, or the share sits under the line for four passes without anyone consulting it"
|
|
|
|
[[gate]]
|
|
id = "LOOP-LINT"
|
|
name = "executable InnerLoop rules"
|
|
target = "loop-lint"
|
|
checks = "loadability, unmeasured verdicts, tier and chaos declarations, review trails, self-test entry points, and this registry"
|
|
added = "2026-07-30"
|
|
review_by = "2026-12-31"
|
|
caught = [
|
|
"four loadability breaches (401, 427, 406, 409 lines), each fixed structurally rather than by raising the limit",
|
|
"a reporting tool with no --self-test entry point (tools/repo.py)",
|
|
]
|
|
retire_if = "two passes run with no finding while artifacts keep growing — that would mean it is measuring the wrong properties"
|
|
|
|
[[gate]]
|
|
id = "CHAOS"
|
|
name = "the chaos roll"
|
|
target = ""
|
|
checks = "d4 on each tier declaration, 12-declaration calibration window"
|
|
added = "2026-07-30"
|
|
review_by = "2026-09-30"
|
|
caught = [
|
|
"CB-WP-0011: first fire in 6 declarations — d4=4 rolled stage 1 from structural L to S; the deleted survey would have opened on 2D toolkits while the existing text renderer was showing 24 of 41 view fields (CB-EV-0009 §1)",
|
|
"CB-WP-0012: d4=1, no override — and the contrast is the entry. Tier L at full weight deleted its own structural trigger: adversarial review withdrew the capability port the declaration was made to build (ADR-0007 D2), and corrected the survey's headline claim by 85x (128x -> 1.5x, CB-EV-0010 §2). Two passes on one subject at two tiers, priced: 0.123 $/response at L against 0.099 at S (CB-EV-0010 §5)",
|
|
]
|
|
retire_if = "the window closes with no overridden tier producing a different outcome than the argued one — the evaluation this window exists to make possible"
|
|
|
|
[[gate]]
|
|
id = "GATE-REVIEW"
|
|
name = "this registry"
|
|
target = "gate-review"
|
|
checks = "gates past their review date, and gates that have caught nothing"
|
|
added = "2026-08-01"
|
|
review_by = "2026-12-31"
|
|
caught = []
|
|
retire_if = "it has retired, tightened, or forced the re-justification of nothing by its review date — then it is a ritual, and ADR-0006 D4 says rituals cash out or go"
|