# 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", "am7", "am8", "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"
name = "session-shape budget"
target = "shape-budget"
checks = "mean and p90 context since the last commit (SH-3 retired as a gate, ADR-0008 D1 — still reported as a diagnostic)"
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",
  "CB-WP-0013: SH-3 retired from this gate. Its window is *since the last commit*, which during a pass is implementation work, and batching needs two calls whose inputs are known at once — which is orientation work. Measured: 0 batched turns in 150 in-pass responses across three passes, against 37.5% in the gap between two of them. A floor the window structurally excludes is not a target (ADR-0008 D1)",
]
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)",
  "CB-WP-0015: the two clauses it had reported inert since CB-WP-0005 — AM-7's scaling ratio (a test named `replay_100k_events_is_linear_and_fast` that computed both throughputs, printed both, and never divided one by the other) and AM-8's N=10 (the runner did two). Both now red, 10/14, and the >=10-of-14 prediction met for the first time",
  "CB-WP-0015: AM-4a's own mutation, stale since ADR-0008 D3 moved the target 250,000 -> 161,000 in CB-WP-0013. Reported HARNESS-BROKEN and refused to publish a score, which is the harness catching itself. The build-free half of that check is now a --self-test assertion, so it runs in `make all` instead of only on a full run",
]
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-20"
name = "meta budget"
target = "status"
checks = "share of the trailing 5 passes spent on the loop itself; soft 20%. Purpose (InnerLoop v1.7): most spend on the task at hand, some on control, review and improving the process that carries the work forward"
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",
  "CB-WP-0019: it had a threshold and no stated purpose, which is why the number was argued three times. The maintainer set 80/20; writing that down exposed that the ratio and the window are a pair — one meta pass among three at parity cost already reads 33%, so 20% over a trailing 3 would have silently also demanded it be half-price. Now 20% over a trailing 5, which is one pass in five at normal cost",
]
retire_if = "product and meta stop being separable, or the share sits under the line for four passes without anyone consulting it"

# The phase setting (CB-WP-0019 T05). Uncomment, argue, and date it to move
# the split for a phase — stage 0 and a stabilisation phase do not deserve
# the same ratio. It REVERTS to META_SOFT_PCT on `review_by` unless
# re-argued, and `status.py --self-test` refuses one with no reason or no
# expiry, because a threshold anyone may move is not a threshold.
#
#   meta_phase = { pct = 35, reason = "why this phase differs", review_by = "YYYY-MM-DD" }

[[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 = "d8 on each tier declaration, 12-declaration calibration window (window 2, opened 2026-08-03; window 1 ran at d4)"
added = "2026-07-30"
review_by = "2026-11-30"
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-0017: d4=4 — second override in twelve, and the first to roll UP (structural S → M). It bought ADR-0010: the script's widening from 'it does one thing' to holding a drag, following the pointer and marking other elements would otherwise have landed under a tier-S provenance paragraph, silently outgrowing ADR-0007 D5. The ADR's own finding is that the permitted and forbidden designs are indistinguishable from outside, which demoted the vocabulary grep to a cheap first line and produced the two behavioural controls that replaced it",
  "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 = "an override changes nothing twice running (window 2 condition, CB-WP-0018 T04). Window 1's condition — no override changing the outcome — was NOT met: both did, so the mechanism was kept and the rate dropped d4 → d8 instead"
# VERDICT, CB-EV-0015 §5 (window closed 2026-08-02, 12 declarations, 2 overrides).
# Not retired: both overrides changed the outcome. CB-WP-0011 (L→S) bought a
# defect in the existing renderer that the deleted survey would have walked
# past, at 0.099 $/response against 0.123. CB-WP-0017 (S→M) bought the
# restatement of control 5 — at tier S the script would have outgrown
# ADR-0007 D5 under a one-paragraph commit note.
# RECOMMENDED, and owed to the next declaration as tier-M work: drop the rate
# d4 → d8 and open a second window of 12. Both overrides were informative
# BECAUSE they were rare; a mechanism firing on a quarter of declarations
# stops being a calibration and becomes the tier system.
# New retirement condition proposed: retire if an override changes nothing
# twice running.

[[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 = [
  "CB-WP-0013: forced SH-3's re-justification and then its retirement. `make gate-review` had reported SH-3 as a standing breach for seven passes with zero actions taken, which is this registry's own ritual test (ADR-0006 D4); asking what it had ever caught is what exposed that the metric could not read above ~0% in the window it was gated on (ADR-0008 D1)",
]
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"