You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 77446cd
Browse filesBrowse the repository at this point in the historyBrowse files
Two review findings on the interprocedural layer, both reproduced before
fixing:
P2 (S2 / INF-S3): a body like 'if (c) return; Sink(x)' kept exactly one
top-level forward, so the shape counted as an unconditional handoff and
solved to must — leaking the callee's own parameter on the guard path
and charging the caller's defensive Dispose a false OWN002. The
unconditional test now also requires no return reachable before the
forward (_early_return_before_forward), the forward twin of D1's
partial-release rule. Recorded as TZ D7.
P1 (INF-A5): the optimistic untrack applied to the whole body, so a
local passed to a may/unknown position anywhere lost its PRE-call
verdicts too (acquire s; release s; use s; maybe(s) reported nothing
but OWN051). Split into two mechanisms (_kill_sites_for_unverified):
a top-level unverified call keeps the local fully tracked up to the
call, discharges it there with a $consume on the handle (sound: a
top-level call lies on every path to the exit), and unmaps it after —
so the checked region now matches OWN051's 'not checked past this
call'. In-branch calls keep the conservative whole-body untrack (a
branch-local discharge would fabricate OWN001/OWN009 on the other
path); the residual is recorded in TZ D6 and INF-A5b.
Spec: INF-S3 + INF-A5a/A5b updated, conformance list extended.
Tests: 3 new pins (pre-call OWN002 beside OWN051, post-call silence,
early-return forward), 248/248 bridge checks green.
0 commit comments