compact-is-deterministic-pure-and-bounded
OUT derived (depth 1)
The compact module produces output that is simultaneously deterministic (pure function with fixed priority ordering), bounded (guaranteed to never exceed the token budget), and self-describing (includes its own token count for auditability).
Summary
The compact module was claimed to combine three guarantees: it always produces the same output for the same input with a fixed priority ordering, it never exceeds its token budget, and it includes its own token count in the output so you can verify the budget was respected. This matters because together these properties would make compaction fully predictable and auditable. However, this combined claim is currently marked as not holding, meaning at least one of those three underlying guarantees has been retracted or is in question.
Justifications
SL — Three independent compact properties unify into a single reliability guarantee for downstream consumers
Antecedents (all must be IN):
- compact-is-pure-function — `compact()` performs no I/O, no database access, no mutations, and no side effects; it is a pure transformation from `Network` to `str`.
- compact-never-exceeds-budget — `compact()` guarantees the returned string's estimated token count (chars/4) does not exceed the `budget` parameter, enforced by pre-checking every line addition against remaining space.
- compact-self-reports-tokens — When given a budget, the `compact` output includes a `Token count: N / B budget` line for auditability.
Dependents
These beliefs depend on this one:
- compact-is-efficient-deterministic-and-bounded — The compact module simultaneously achieves computational efficiency (O(1) per-line budget tracking via running character count with chars/4 token estimation), mathematical determinism (pure function with no side effects), and guaranteed output bounds (never exceeds the budget parameter) — all three desirable output properties without trade-offs.
- compact-is-predictable-bounded-distillation — The compact module is a fully predictable information distillation: a pure function with deterministic priority ordering that reliably constrains output within token budgets, self-reports resource usage, and structurally important nodes are prioritized through dependent-count sorting