Skip to content

Commit 922dd7e

Browse files
committed
docs(D5.1c): add explicit revisit trigger + tracking issue for the deferred exclusivity axis
The decline of transitive borrow_mut propagation through MOS wrapper summaries was already recorded as D5.1c, but without a concrete reactivation condition or a live tracker. Add both: the revisit trigger (land the borrow-kind axis alongside the first interprocedural exclusivity consumer — an OWN006/011/012/013-class conflict checked across the call boundary), the cheap-to-reverse rationale (the skeleton already preserves the forward edges, so the future work is additive), and a link to the tracking issue #122. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01KkpSWNx7ARLpQeAs13kkyA
1 parent c1dfb2e commit 922dd7e

1 file changed

Lines changed: 8 additions & 2 deletions

File tree

‎docs/notes/d5-ownership-transfer.md‎

Lines changed: 8 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -276,8 +276,14 @@ escape-without-transfer and all `unknown`/`may` lower to **silence** in the defa
276276
behaviour unchanged, `$borrow_mut` wrapper tests, and mixed-path regressions proving ambiguous
277277
flows degrade to silence (not shared borrow). Prior art: Rust `&`/`&mut`, RustBelt exclusivity,
278278
Oxide's `shrd|uniq`, Polonius's per-loan invalidation — exclusivity is a distinct semantic
279-
axis, not coarser metadata. Tracked here so the deferral is recorded, not buried (Codex P2 /
280-
CodeRabbit Major on #113).
279+
axis, not coarser metadata. **Revisit trigger:** land the axis alongside the first
280+
*interprocedural exclusivity consumer* — i.e. when an OWN006/011/012/013-class conflict is
281+
checked *across* the call boundary (today exclusivity is enforced only intraprocedurally and at
282+
the *direct* `$borrow_mut` call). Until that reader exists the summary axis has no consumer, so
283+
the decline costs no observable soundness and stays cheap to reverse: the forward edges are
284+
already preserved in the skeleton (`PathAction(kind="forward", …)`), so the future work is
285+
additive (leaf borrow-kind + a join), not a solver rebuild. Tracked here so the deferral is
286+
recorded, not buried (Codex P2 / CodeRabbit Major on #113); live tracker: **#122**.
281287
- **D5.2 — T1 return-value door (shipped).** A `fresh`-returning call becomes an **acquire
282288
site**. `_build_skeletons` now infers the return kind (`_infer_return_skeleton`): a body that
283289
`acquire`s a local and returns it is `fresh` (a factory), and a single returned local that is

0 commit comments

Comments
 (0)