fix(6477): a body uses a canon by name only when the name can resolve to it
CI & Build / Python lint (push) Successful in 2s
CI & Build / Plugin hooks (push) Successful in 13s
CI & Build / TypeScript typecheck (push) Successful in 43s
CI & Build / integration (push) Successful in 1m36s
CI & Build / Python tests (push) Successful in 2m7s
CI & Build / Build & push image (push) Successful in 42s

The proposer's reference basis, and every uses edge it writes, counted any
word-bounded mention of a canon's symbol. Three holes made that wrong at
scale (snippet #5448, symbol `file`, held 2,161 uses edges):

- Go, Rust, Kotlin, Swift, Dart, C, C#, Ruby and PHP were outside the
  language-family maps, so their canons read as "unknown, no gate" and were
  matched in every Python, TS and CSS body.
- Canons in other projects were matched by name, though one repo never
  calls a function defined in another's.
- A plain word (`file`, `seen`) or a module's own helper (`_run`) matched
  wherever it appeared.

names_canon is now the one by-name test, used by match_canon,
reference_canons and the write-path hint: same project, not a name the file
defines itself (unless the canon is recorded there), no generic verb with or
without a leading underscore, and a bare lowercase word only where it is
called. The write path keeps the payload's own names in play, since a
redefinition of a pulled canon is the copy it exists to flag.

Repair: record_uses only adds, so replace_reference_uses now makes a row's
machine-written reference edges exactly what the current rule finds,
leaving judged and hook edges alone. _PROPOSER_VERSION 7 re-reads every row
on its project's next refresh. Migration 0125 deletes the cross-project
reference edges already stored.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-26 17:41:21 -04:00
co-authored by Claude Opus 5.5
parent 0b98a3a5cd
commit cdb71e64c4
4 changed files with 229 additions and 23 deletions
@@ -0,0 +1,35 @@
"""drop machine-written uses edges that cross projects
Revision ID: 0125
Revises: 0124
Create Date: 2026-10-26
A `uses` edge with basis `reference` is the proposer's by-name reading: the
shape's body names a canon's symbol. A body never calls a function defined in
another project's repository, so such an edge across projects is a common
word matched, not a call. The proposer no longer writes them, and this removes
the ones it wrote before. Edges a person or an audit judged keep their own
basis and are left alone. Rows within one project are re-read on the next
coverage refresh, which replaces their reference edges under the same rule.
Downgrade restores nothing: the removed edges were never facts.
"""
from alembic import op
revision = "0125"
down_revision = "0124"
branch_labels = None
depends_on = None
def upgrade() -> None:
op.execute(
"DELETE FROM code_shape_uses u USING code_shapes s, notes n "
"WHERE u.shape_id = s.id AND u.snippet_id = n.id "
"AND u.basis = 'reference' "
"AND n.project_id IS NOT NULL AND n.project_id <> s.project_id"
)
def downgrade() -> None:
pass