Skip to content

Commit 3fc1246

Browse files
authored
Merge pull request #336 from PhysShell/claude/p-022-analysis-wiring-mwhqlw
feat(bridge): wire the lowered module through the core analyses (#259 cp4)
2 parents 76324fe + 43cb602 commit 3fc1246

116 files changed

Lines changed: 7295 additions & 230 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.
Lines changed: 253 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,253 @@
1+
# P-022 step 6b (#259) — checkpoint 4: analysis wiring
2+
3+
> Status: **checkpoint-4 deliverable** — the bridge feeds real `OwnIR` facts
4+
> through the ported analyses and maps their verdicts back to C# anchors, at
5+
> the checkpoint-4 comparison surface (identity, anchor, kind, tiering).
6+
> Checkpoint 5 (messages, evidence, rendered surfaces) is unblocked and
7+
> compares against the same goldens. Written from the tree at the commit that
8+
> landed it; the numbers below are the ones the suites assert.
9+
10+
## What landed
11+
12+
- **`own_bridge::check_facts(&OwnIr) -> Result<Vec<Finding>, BridgeError>`** —
13+
`ownlang/ownir.py::check_facts` as spec/Bridge.md §5 writes it, in order:
14+
lower (the cp2 `lower_full`, now also returning the Python-shaped handle
15+
records with `column`, the OWN051 tuples and the solve-failure reason) →
16+
the Layer 2 document rebuilt as the core AST (`ast.rs`) →
17+
`own_analysis::check_module` (buffer policy, lifetime, resolver, ownership)
18+
→ ERROR-only, the closed BR-V2 skip list, `subject` → handle or the
19+
reference's map-or-raise refusal (BR-V3) → anchors per BR-V5 (the record's
20+
line; OWN025 at the view site with `column: None`; DI004/DI005 at the
21+
finder-selected call/store site) → kind and tiering per BR-V4/V6 → DI
22+
(`services[]` through BR-P1's coercions into the five `own-analysis`
23+
finders, in the bridge's append order) → effects (`effects[]`, BR-P2
24+
skip-not-coerce, `find_effect_storms`) → OWN050 → OWN051 → OWN052 → dedup
25+
(BR-V7) → the stable `(file, line, column or 0, code)` sort (BR-V8).
26+
- **Layer 2 → core AST** rather than a second lowering: the projection
27+
`ownlang/lowered.py` drops only the declaration lines `to_module` fixes at
28+
`0`, so the AST built from the 27/27 byte-exact document is the reference's
29+
node for node, and a lowering defect stays visible at the Layer 2 seam
30+
instead of hiding behind a verdict.
31+
- **The one core change: the verdict `subject`.** `own-analysis` emitted
32+
`(code, line)` only; the bridge maps through `subject` (`name#line`) and
33+
nothing else, so `Emit::push_at` now stamps the symbol's `origin` exactly
34+
where `analysis.py` passes `subject=sym.origin` (state problems, OWN001 via
35+
the RID's minting symbol, release, overspan, the return path, the buffer
36+
escape codes) and `lifetimes.py` stamps `source#line` on OWN014 — and
37+
nowhere else (the loan/permission codes stay subject-less, as in Python).
38+
Pinned through `check_module` in `own-analysis/tests/subject.rs`.
39+
Not stamped, deliberately: `resource_kind`, messages and evidence on the
40+
`.own` path are the core's own later contract (own-cli), not this
41+
checkpoint's, and nothing here asserts them.
42+
- **Layer 3 fixture family** (spec/Bridge.md §6): `ownlang/verdicts.py`
43+
(`VERDICTS_VERSION = 1`, every `Finding` member in declaration order, a
44+
refusal as `{"error": …}`), `tests/test_verdict_fixtures.py` (verify /
45+
`--write`, ledger == swept corpora + synthetic == goldens, orphan/stale/
46+
missing red, determinism), `tests/fixtures/verdicts/manifest.json`, and the
47+
Rust replay `own-bridge/tests/verdicts.rs`. All cases go through the
48+
**tolerant door** (`check_facts` on the loaded document) on both sides.
49+
- DAG: `own-bridge` → `own-syntax`, `own-cfg`, `own-analysis`,
50+
`own-diagnostics` added to the allowed set; a named test now asserts no
51+
core crate depends on the bridge.
52+
53+
## Census
54+
55+
| | |
56+
|---|---|
57+
| goldens (Python's truth, complete) | **77** — 22 `ownir` + 27 `lowered` + 9 `summaries` swept, **19** synthetic |
58+
| replayed by Rust at the cp4 surface | **69** — 5 refusals, **127** findings |
59+
| declared exclusions (executable) | **8** — 2 protocol documents, 4 coordinate-boundary controls, 2 OD-1 door controls |
60+
| Python-only / Rust-only / Changed / Ordering-only / Unexplained, over the replayed set | **0 / 0 / 0 / 0 / 0** |
61+
62+
The **compared members** at cp4: `file, line, column, code, component, event,
63+
handler, kind, advisory, severity, ignore_reason`. Not compared yet:
64+
`message`, `related`, `flow` — the goldens carry them, cp5 compares them
65+
without regenerating a golden.
66+
67+
### The unmeasured set is named, not hidden
68+
69+
Each exclusion is an entry in `rust_replay_excluded` with a reason and an
70+
expectation the replay executes (`rust_refusal: bridge` + an error substring,
71+
or `door`); the set is also pinned by name, and an exclusion that stops
72+
holding is a red build demanding promotion.
73+
74+
1. **Obligation protocols (2).** `ownlang/obligations.py` has no
75+
`own-analysis` port. A document that declares a protocol is **refused**
76+
by `check_facts`, never given a verdict list with a family missing —
77+
`protocol_isloaded_clean` would otherwise have "matched" vacuously.
78+
#259's checkpoint list never names the protocol analysis; its final
79+
acceptance ("full test-family inventory from #258") does. Recorded as
80+
**its own checkpoint (P-022 row 4b)**, deliberately not folded into cp5:
81+
cp5 is messages, evidence and rendering, and a whole analysis family on
82+
top would make the last checkpoint a bag. 4b does not block cp5; #259's
83+
final acceptance needs it.
84+
2. **The `u32` coordinate domain (4).** The core's line is a `u32`; the
85+
strict door admits every signed 64-bit coordinate (`spec/OwnIR.md` §4.2)
86+
and the tolerant door anything `_as_int` passes. A coordinate outside
87+
`0..=u32::MAX` on a lowered node, a DI registration line or an effect line
88+
is **refused, never clamped** (`ast::core_line`); a site or binding line
89+
whose only reader guards on `>= 1` folds a negative value to `0`, which
90+
is exact on every path (`verdict_di_duplicate_sites_last_wins` pins it).
91+
The reference analyzes these documents (OWN001 at `B.cs:-1`, DI001 at
92+
`reg.cs:-5`, …). This is the cp1 pattern again: a divergence family
93+
outside the measured set, recorded so a decision can be taken — a
94+
Python-first bound in §4.2, or a wider core line type — rather than
95+
"closed by widening Rust" or reported as parity. The owner's stated
96+
direction on review: **Python-first tightening** — define the valid
97+
coordinate domain normatively (a negative source line is meaningless),
98+
teach the reference to reject it, then remove the exclusion; as its own
99+
contract change with parity evidence, never by declaring the reference
100+
wrong because the port is `u32`.
101+
3. **OD-1, measured (2).** The Rust tolerant entry is the typed `OwnIr`
102+
constructor, so BR-D2's skip-not-coerce (`deps: "a"`) and the finders'
103+
unknown-lifetime tolerance are unreachable through it: the reference
104+
reports the sibling finding, the constructor refuses the document. The
105+
bridge-side port of both rules exists and is pinned at the raw-document
106+
level (`verdict::tests`), because that is the only level the production
107+
surface can reach them from today.
108+
109+
One **comparison** boundary on refusals: the map-or-raise text interpolates
110+
the core diagnostic's `message`, and this core's messages are still titles
111+
(`undefined name` vs the reference's `undefined name 'loc_0'`), so the three
112+
`hoist_neg_*` refusals are compared up to their `message=` member — on both
113+
sides, by the same function. The lowering-time refusals are byte-exact.
114+
115+
### The `subject` tail
116+
117+
The core change adds data to a diagnostic; whether it changes any
118+
**serialized** surface was checked rather than assumed. On the Rust side
119+
`render.rs` states it does not consult `subject`, `sarif.rs` never reads it,
120+
and its only carrier is `LocatedDiagnostic`/`DiagIdentity` — an in-memory
121+
comparison key, not an output. On the reference, `subject` is read by the
122+
bridge and by `report.py` (the `.ownreport.json` buffer report, struck from
123+
the port in #256). No Rust output surface serializes it, so "behavior
124+
changes: none" holds; cp5 re-checks this when the bridge's render/SARIF
125+
paths land.
126+
127+
### The dedup key, minus `message`
128+
129+
BR-V7's key is `(file, line, column, code, component, event, handler,
130+
message, kind, advisory, severity, ignore_reason)`; cp4 carries every member
131+
but `message`. On the reference's own outputs that is exact: every message is
132+
a function of the handle record and the code (the flow-local wordings key on
133+
`code`/`pool`/`ever_released`, the token wordings on the record, and the
134+
same-handle same-code duplicates BR-V7 exists for are byte-identical), so two
135+
findings equal on the carried members are equal on the message. The corpus
136+
measures it (the two-exit and nested-throw leaks fold to one finding on both
137+
sides); cp5 adds the member.
138+
139+
## Mutation campaign
140+
141+
Per the P-022 discipline (rule 2: a test is evidence only once its mutation
142+
fails through the production surface; rule 3: no fail-fast — every catching
143+
layer is recorded). Each mutation is applied to a copy of the file and
144+
restored from that copy, never by `git checkout` (the lesson from cp1's
145+
third round); `M00` is the harness-honesty control (no mutation must report
146+
zero failures); a compile error is reported as such, never as "caught".
147+
148+
**Round 1 (24 mutations) surfaced three real gaps and one bad mutation**,
149+
all fixed before round 2:
150+
151+
- M01 survived — nothing in the corpus produced an OWN033/034/035/041, so
152+
the *closed* BR-V2 list had no control per member.
153+
→ `verdict_skip_list_artifacts` (partial return, bare return beside a
154+
value return, a borrow handed to a consume position, an arity mismatch;
155+
OWN040 is unreachable by construction).
156+
- M04/M06 survived — `column` and `event` were redundant in the dedup key on
157+
that corpus (`handler` and the distinct names kept the pairs apart).
158+
→ a same-name rebind on one line differing only in column; one record
159+
pair per key member (event, handler, component, kind, severity,
160+
ignore_reason) differing in exactly that member.
161+
- M10 was not a mutation: `owned_here.is_empty() && …` kept the gate for the
162+
empty case it was meant to drop. Rewritten as `false && …`.
163+
- The harness attributed catchers to the wrong target: cargo's `Running`
164+
lines are on stderr, test results on stdout, and capturing them
165+
separately loses the interleaving. Fixed by merging the streams.
166+
167+
**Round 2: 30 mutations, 29 caught, 1 declared survivor — closed on review
168+
(round 3): 30/30.** M19 survived because BR-V1's ERROR-only rule guards a
169+
state the corpus cannot produce (no facts producer reaches the one core
170+
pass that grades below ERROR). Leaving a normative rule permanently
171+
unprovable was the wrong resting place: the filter is now a pure predicate
172+
(`is_mapped`, BR-V1 + BR-V2 in one place) and a synthetic WARNING is driven
173+
through `map_core` itself — same diagnostic, same handle, ERROR → one
174+
finding, WARNING → none — so the mutation is caught at the unit level, with
175+
the corpus still unable to reach it (recorded as such below).
176+
177+
| id | mutation | caught by |
178+
|---|---|---|
179+
| M01 | BR-V2 skip list: OWN033 no longer skipped | verdict replay |
180+
| M02 | BR-V5 flow-local anchored at the core's line, not the acquire record | verdict replay |
181+
| M03 | BR-V5 OWN025 anchored at the acquire, not the view site | verdict replay |
182+
| M04 | BR-V7 dedup key drops `column` | verdict replay |
183+
| M05 | BR-V8 sort key drops `column` | verdict replay |
184+
| M06 | BR-V7 dedup key drops `event` | verdict replay |
185+
| M07 | DI004/DI005 duplicate site: last-wins → first-wins (`own-analysis`) | `fact_parity::di_fact_parity` **and** verdict replay |
186+
| M08 | BR-V6 DI001 graded `warning` | verdict replay |
187+
| M09 | BR-D2 effect `deps` coerced instead of skipped | `verdict::tests::malformed_effect_entries_are_skipped_not_coerced` (raw-document level — the only reachable one, see OD-1) |
188+
| M10 | BR-L8 OWN051 owned-local gate dropped | verdict replay |
189+
| M11 | BR-M1 OWN052 never minted | verdict replay |
190+
| M12 | BR-V3 OWN001 emitted without a subject (`own-analysis`) | `subject.rs` ×3 **and** verdict replay |
191+
| M13 | BR-V3 OWN014 emitted without a subject (`own-analysis`) | `subject.rs` **and** verdict replay |
192+
| M14 | protocol documents no longer refused | verdict replay (the executable exclusion ledger) |
193+
| M15 | `core_line` clamps instead of refusing | verdict replay (the executable exclusion ledger) |
194+
| M16 | BR-V6 source tiering inverted | verdict replay |
195+
| M17 | BR-V6 an empty `ignore_reason` suppresses | verdict replay |
196+
| M18 | BR-V7 dedup removed | verdict replay |
197+
| M19 | BR-V1 ERROR-only half of the mapping predicate removed | `verdict::tests::only_error_severity_core_verdicts_are_mapped` (synthetic WARNING through `map_core`; the corpus cannot reach it — no facts producer feeds a sub-error core verdict today) |
198+
| M20 | `_as_col` accepts `0` | verdict replay |
199+
| M21 | a negative DI site line folds to `1`, not `0` | verdict replay |
200+
| M22 | OWN050 never minted | verdict replay |
201+
| M23 | BR-V3 handle read from the wrong subject separator | verdict replay |
202+
| M24 | OWN051 anchored at `0`, not the call line | verdict replay |
203+
| M25 | BR-V7 dedup key drops `handler` | verdict replay |
204+
| M26 | BR-V7 dedup key drops `component` | verdict replay |
205+
| M27 | BR-V7 dedup key drops `kind` | verdict replay |
206+
| M28 | BR-V7 dedup key drops `severity` | verdict replay |
207+
| M29 | BR-V7 dedup key drops `ignore_reason` | verdict replay |
208+
| M30 | DI findings anchored at `0`, not the finder's anchor | `verdict::tests::di_coercions_match_the_reference` **and** verdict replay |
209+
210+
Two catching layers exist where the analysis owns the rule (M07, M12, M13,
211+
M30) and one where only the bridge does — the same shape as cp1's ledger:
212+
the bridge replay is the outer catcher, and a rule with a single catcher is a
213+
rule with a single control. Two rules (M09, M19) are catchable only at the
214+
unit level because the production entry cannot reach them; both say so in
215+
the test.
216+
217+
## What checkpoint 5 needs
218+
219+
The comparison matrix over the same frozen goldens — cp5 turns every
220+
"deferred" row into "prove" and keeps every "proven" row as a regression
221+
guard; **no golden is regenerated beside the cp5 implementation**, because
222+
"implementation disagreed with the golden → regenerate → agreement" is the
223+
one move this family exists to make impossible:
224+
225+
| `Finding` surface | cp4 | cp5 |
226+
|---|---|---|
227+
| identity (`file`, `code`, `component`, `event`, `handler`) | proven | regression |
228+
| anchor (`line`, `column`) | proven | regression |
229+
| `kind` | proven | regression |
230+
| tiering (`advisory`, `severity`, `ignore_reason`) | proven | regression |
231+
| ordering and dedup | proven | regression |
232+
| `message` | deferred (carried) | prove |
233+
| `related` | deferred (carried) | prove |
234+
| `flow` (evidence slices) | deferred (carried) | prove |
235+
| rendered diagnostic (`render*`) | deferred | prove |
236+
| SARIF projection (`build_sarif`, bridge path) | deferred | prove |
237+
238+
And the wording discipline that comes with it: what cp4 proved is
239+
"127 verdicts × the cp4 comparison projection", never "verdict parity
240+
complete" — the shortcut a roadmap status is made of.
241+
242+
Concretely:
243+
244+
- the message matrix (BR-V4) on the bridge findings, and the core diagnostic
245+
messages behind the map-or-raise text;
246+
- the `related`/`flow` evidence slices (DI paths via the registration map,
247+
the DI004/DI005 registration `related`, the effect re-run → mint slice,
248+
the flow-local origin → violation slice, the capture escape slice);
249+
- `render`/`render_github`/`render_msbuild`/`build_sarif` on the bridge path
250+
(BR-V9), reusing `own_diagnostics::sarif`;
251+
- tightening `verdicts.rs` to full equality on the existing goldens;
252+
- the two decisions this checkpoint owes: the protocol analysis, and the
253+
coordinate domain.

0 commit comments

Comments
 (0)