voyage/lib/util
Kjell Tore Guttormsen 32e20fc0dc fix(cap): move the enforcement boundary to a denial tombstone, not the turn count
allowTurn() appends BEFORE the turn runs, so during granted turn N the
ledger holds N records. The hook denied at `used >= budget`, which blocked
every tool call of the FINAL granted turn: the primitive granted B turns
and the harness permitted B-1. Worse, an exhausted run therefore always
terminated through an exit-2 tool denial instead of the graceful "cap
exhausted" exit at commands/trekresearch.md - and the prose says in as
many words that exit 2 is not exit 1, so the model was pushed out through
the one exit it is told NOT to treat as a cap.

The review recommended denying at `used > budget`. Taken alone that fixes
the count and breaks the hook: once the O_EXCL claim (previous commit)
makes a breached ledger impossible, `granted > budget` can no longer fire,
and the case this hook exists for - the loop consults the gate, is denied,
and issues the tool call anyway - would be allowed. A deny branch that
cannot be reached is a dead security claim, which is the same thing S82
removed two of rather than leave standing.

So the denial itself became a record. allowTurn() appends a tombstone
{runId, exhausted: true} when it denies for budget, and the hook denies on
the tombstone. Both properties now hold at once:

  granted == budget, no tombstone  -> turn B is in flight   -> ALLOW
  tombstone present                -> the gate already said no -> DENY
  granted  >  budget               -> breached, any cause   -> DENY

A tombstone is not a turn: readLedger reports {granted, exhausted}
separately so it can never consume budget. allowTurn short-circuits on an
existing tombstone, so a hammered gate neither re-walks every slot nor
grows the ledger. The tombstone write is best effort on purpose - the
denial is already the correct answer, so a ledger that cannot take the
record must not turn a denial into a grant.

The parallel-boundary test now asserts GRANTED turns rather than raw
ledger lines, because the denied callers legitimately add tombstones.

Review finding 8eb53458ac3efec778094f9f03b09e1cc1077a09 (MINOR).
Operator decision: tombstone over the literal recommended_action.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LuGhWAbWyRFBFeemfhxoVv
2026-08-12 22:56:55 +02:00
..
atomic-write.mjs refactor(ultraplan-local): extract atomicWriteJson to lib/util 2026-05-01 20:21:15 +02:00
autonomy-gate.mjs feat(voyage)!: bulk content rewrite ultra -> voyage/trek prose [skip-docs] 2026-05-05 15:08:20 +02:00
cleanup.mjs feat(voyage)!: bulk content rewrite ultra -> voyage/trek prose [skip-docs] 2026-05-05 15:08:20 +02:00
frontmatter.mjs feat(graceful-handoff): 2.0 — migrate to skills/ with disable-model-invocation [skip-docs] 2026-05-01 05:45:26 +02:00
research-loop-cap.mjs fix(cap): move the enforcement boundary to a denial tombstone, not the turn count 2026-08-12 22:56:55 +02:00
result.mjs feat(ultraplan-local): Spor 1 wave 1 — lib/parsers + 66 tests grønn 2026-05-01 05:35:28 +02:00
test-census.mjs feat(eval): SKAL-1·4b offline gold-scored output eval 2026-06-30 09:00:33 +02:00