Skip to content

Commit 571669e

Browse files
committed
P-037 B1: pre-register the guarded shadow read (contract only, no code)
docs/notes/p037-phase-b1-shadow.md freezes the B1 contract before any Rust: - §0: the owner's fixed frame; - the question; - N1-N6: architecture guard, zero semantic cut, the 16 B0 obligations as acceptance controls, required-read, difference classification, and the A14 / R gate metrics; - falsifiers G1-G13; - the hard KILL / PASS rule; - the first shadow population; - the budget and stop point. The §0 frame, from the owner: - shadow-only, with own-bridge untouched; - a new crate own-guarded as the only p037-kernel dependent, enforced by an executable guard; - own-shadow may consume own-guarded; - own-bridge -> own-guarded is phase C; - A14 is measured, never solved or assumed away; - every ambiguity degrades to NO_GUARDED_EVIDENCE. N2 records a consequence found while writing the contract. rust/ is an A2 evidence instrument path, so the snapshot differential correctly refuses across B1. Zero-cut evidence is therefore: - a source-path guard; - identical own-cli binaries, base vs head; - a declared fallback, or a STOP (case 4). Stopped for owner review. No implementation. Refs #304 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01KmiyfrkaG9sJruTcshM2oq
1 parent 0e2c01a commit 571669e

1 file changed

Lines changed: 239 additions & 0 deletions

File tree

‎docs/notes/p037-phase-b1-shadow.md‎

Lines changed: 239 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,239 @@
1+
# P-037 Phase B1: the guarded shadow read (pre-registered)
2+
3+
> Status: **PRE-REGISTERED. No Rust code written; stopped for owner review.**
4+
>
5+
> This contract is committed before any implementation, so the result is
6+
> judged against it rather than an impression afterwards.
7+
>
8+
> - Governance: `docs/notes/p037-formal-kernel.md` §10.1 (finding classes),
9+
> §10.4 (proof boundary), §10.6 (R), §10.7 (B0 accepted, A14 gate).
10+
> - Entry state: B0 PASS, `docs/notes/p037-phase-b-proof-boundary.md` and
11+
> `formal/p037-kernel/proof-boundary.json`.
12+
> - Base: `0e2c01a`, the head of #372. Branch:
13+
> `research/p037-phase-b1-shadow`.
14+
>
15+
> Evidence tags as elsewhere: `REPOSITORY FACT`, `MEASURED OBSERVATION`,
16+
> `INFERENCE`, `OWNER RULING`.
17+
18+
## 0. Fixed by the owner (OWNER RULING, 2026-09-28, recorded verbatim in meaning)
19+
20+
These are the frame of the contract, not choices it makes.
21+
22+
1. B1 is shadow-only. It changes no MOS, verdict or diagnostic, no
23+
`ConsumesParam`, and no `own-bridge` behavior.
24+
2. `own-bridge` is untouched in B1.
25+
3. The home is a new crate, `own-guarded`.
26+
- It is the only Rust crate allowed to depend on `p037-kernel`.
27+
- An executable architecture guard enforces this, because
28+
`own-diagnostics/tests/dag.rs` sees only workspace-internal edges.
29+
4. `own-shadow` may depend on `own-guarded` to produce guarded-vs-legacy
30+
reports.
31+
5. `own-bridge → own-guarded` is **not** pre-authorized; that edge is phase C.
32+
6. All 16 B0 entry obligations are B1 acceptance conditions.
33+
7. A14 remains conditional static-dispatch debt. B1 may **measure** it; B1 may
34+
not solve it or assume it away.
35+
8. The first shadow population collects the A14 exposure metrics and the R
36+
record-absence metrics that the later kill-gates need.
37+
9. These all degrade to **`NO_GUARDED_EVIDENCE`**, never to a positive
38+
conclusion:
39+
- an ambiguous body⋈sidecar join;
40+
- a missing record or sidecar;
41+
- an unresolved positive fact;
42+
- a solver bound failure;
43+
- unsupported placement.
44+
45+
## A. Question
46+
47+
Can a guarded summary be computed for the real fact surface in shadow, with
48+
the existing kernel reused rather than re-implemented and every B0 obligation
49+
discharged by an executable control? That is, reading only A2's sidecar, the
50+
legacy body and the `functions[]` records. Two things must also hold:
51+
52+
- every place where the facts do not support a guarded conclusion yields
53+
`NO_GUARDED_EVIDENCE` rather than a guess;
54+
- every difference against the legacy summary is either one of the three
55+
declared P-037 classes or explicitly degraded.
56+
57+
If not, **STOP** before phase C. The finding is classified under §10.1, and
58+
case 5 goes back to the owner.
59+
60+
## B. Necessary conditions (all must hold for PASS)
61+
62+
**N1 — architecture, executable.**
63+
- `own-guarded` is a workspace member. Its workspace dependencies are
64+
exactly `own-ir`, and its only non-workspace path dependency is
65+
`formal/p037-kernel`.
66+
- `own-shadow` gains `own-guarded`. No other crate gains either.
67+
- A new guard (a `dag.rs` test reading every `Cargo.toml` under `rust/`,
68+
mirrored by `scripts/p037_proof_boundary.py`) fails when:
69+
- any crate other than `own-guarded` names `p037-kernel`;
70+
- any crate other than `own-shadow` names `own-guarded`;
71+
- `own-bridge` / `own-cli` / any core crate reaches either, directly or
72+
transitively.
73+
- `own-bridge → own-guarded` is absent and asserted absent.
74+
75+
**N2 — zero semantic cut.** `rust/` is an A2 evidence instrument path
76+
(`scripts/p037_evidence.py`), so adding a crate moves the instrument by
77+
definition. The A2 snapshot differential therefore refuses to compare across
78+
B1, and that refusal is correct. The pre-registered evidence instead:
79+
- **Source-level:** `git diff base..head` touches nothing under `ownlang/`,
80+
`rust/crates/{own-bridge,own-cli,own-ir,own-lowered,own-analysis,own-cfg,own-syntax,own-diagnostics}/src`,
81+
`scripts/own-check.sh` or `spec/`. The exceptions are the `dag.rs` guard
82+
test and `Cargo.toml` / `Cargo.lock` workspace membership. The checker
83+
enforces the path set.
84+
- **Binary-level:** the release `own-cli` built at the base and at the head
85+
with the same toolchain has the **same sha256**. If it does not, the
86+
fallback is a full MOS/verdict before/after take with the instrument move
87+
declared. If the harness cannot express that, **STOP**: an
88+
evidence-infrastructure addition (case 4) comes before B1 can pass.
89+
- **Extractor-level** (only if the A14 side report of N6 lands in the
90+
extractor): with the flag absent, the census is byte-identical on both
91+
engines, and the facts of the 137-file corpus and the repo tree are
92+
byte-identical to the base.
93+
94+
**N3 — the 16 B0 obligations, each with an executable control in
95+
`own-guarded`'s tests (or in `own-shadow` for report properties).**
96+
97+
| B0 id | B1 acceptance control |
98+
|---|---|
99+
| WF / EWF | a system or coordinate that fails the ported well-formedness predicates is `NO_GUARDED_EVIDENCE`; it is never solved |
100+
| A2 | Id/Neg only for a resolved callee, at the callee's elected guard ordinal, from `param{source_param}`; an unresolved callee with a param at that position is Opaque |
101+
| A3 | Uncond seeds only via `Cells::diag`; apply(Uncond) lowers the collapse |
102+
| A4 / A15 | seeds and masks only through the fail-closed join. The B0 probe shapes (`docs/evidence/p037-b0-probes`) plus `ctor-initializer` are fixtures, each with the pre-registered outcome from B0 §E.6: placeable, or `NO_GUARDED_EVIDENCE` with its reason |
103+
| A5 | the transform table: `bool_const`/`null_literal`/`object_creation` → ConstPos/ConstNeg (canonical orientation); `param` → Id/Neg under A2; `call_result`/`opaque` → Opaque in the solver |
104+
| A6 | the driver's step composes `p037_kernel::{read, contribute, Cells::join, import}` (checked: `own-guarded` defines none of the kernel's types or algebra) |
105+
| A7 | a full sweep by construction, with no schedule parameter; F8 extended to scan `own-guarded` |
106+
| A8 | application only through `p037_kernel::apply`; F9 scans `own-guarded`; **the K7 witness ported onto the adapter**: a `(must, ⊥)` unselected coordinate built from real facts lowers to plain |
107+
| A9 / A10 / A11 | a missing record, missing sidecar, unresolved callee or ambiguous join reads as Unknown / `NO_GUARDED_EVIDENCE`, never ⊥. `record-absence-boundary` is a required control: a mutant that reads absence positively turns it red |
108+
| A12 | the pass bound is `n·HEIGHT+1` per SCC; exceeding it (fault-injected) is `NO_GUARDED_EVIDENCE` for the SCC, never a partial value or a panic |
109+
| A13 | only `fin()` cells cross an SCC boundary; a two-SCC fixture whose callee has a residual ⊥ cell must not yield `must` at the caller |
110+
| A14 | every report carries `static_dispatch_conditional: true`; nothing in `own-guarded` reads, upgrades or degrades on dispatch |
111+
112+
**N4 — required-read.** The contradictory-sidecar fixture of A2 flips role
113+
(§10.3):
114+
- in B1 it must **change** the guarded shadow result, which proves the
115+
sidecar is actually read;
116+
- it must still leave MOS and verdicts unchanged (the inertness script, with a
117+
guarded layer added).
118+
119+
**N5 — every guarded-vs-legacy difference is classified.** Legacy is
120+
`own-bridge`'s MOS, read through `own-shadow`. Every coordinate lands in
121+
exactly one of:
122+
- `EQUAL`;
123+
- `SUMMARY_REFINEMENT` (guarded ⊑ legacy after finalization, G-T2a);
124+
- `LEGACY_HONESTY` (guarded unknown vs legacy may, G-T2b class 3);
125+
- `APPLICATION_REFINEMENT` (call-site selection differs; the collapse agrees);
126+
- `NO_GUARDED_EVIDENCE(reason)`;
127+
- `UNEXPLAINED`.
128+
129+
`UNEXPLAINED > 0` is a KILL (§D).
130+
131+
**N6 — the first shadow population collects the gate metrics.**
132+
- **A14 exposure** (measurement only; OwnIR is not amended, per §10.7):
133+
- relevant calls, total;
134+
- exact calls (static, non-virtual, or a sealed/struct target);
135+
- virtual / abstract / interface / override dispatch candidates;
136+
- candidates in a guarded summary chain;
137+
- candidates whose admissible first-party implementations (in the
138+
compilation) have **different** guarded summary classes;
139+
- the subset where the static target yields MUST and some admissible target
140+
does not (the A14 hard-KILL witness count).
141+
142+
Dispatch class is not in the facts. The measurement therefore comes from a
143+
**side report** of the extractor: an opt-in flag that writes a separate JSON
144+
keyed by call site. It is not OwnIR, not read by either engine, and facts
145+
are byte-identical when it is off (N2). It is an instrument, not a fact, and
146+
it is reported, not acted upon.
147+
- **R record-absence:** first-party resolved callees with no `functions[]`
148+
record, how many guarded paths end there, and the share of otherwise-eligible
149+
guarded chains that break on R.
150+
- **Degradation census:** `NO_GUARDED_EVIDENCE` counts by reason (join
151+
ambiguity per rule clause, missing record, missing sidecar, unresolved,
152+
bound, malformed, expression form, no body op).
153+
154+
## C. Cheap falsifiers (each demonstrated to fire before the result)
155+
156+
| id | mutation | must happen |
157+
|---|---|---|
158+
| G1 | `own-bridge` (or `own-cli`, `own-ir`) gains `own-guarded` or `p037-kernel` | the architecture guard fails |
159+
| G2 | a second crate gains `p037-kernel` | the architecture guard fails |
160+
| G3 | `own-guarded` defines its own `join` / `Transfer` / `apply`-like lowering | the reuse guard fails (A6/A8) |
161+
| G4 | the driver takes a schedule, or `own-guarded` calls `solve_with` / `elect_with` / `lfp_chaotic` | F8 fails |
162+
| G5 | `own-guarded` lowers/collapses outside `apply` | F9 fails |
163+
| G6 | the join resolves an ambiguous line (e.g. `Probe.TwoIfs`, `c && F(s)`) to a placement instead of `NO_GUARDED_EVIDENCE` | the A15 fixture test fails |
164+
| G7 | absence (R, missing sidecar) or an unresolved callee read as ⊥ / no / must | the A9–A11 tests fail, and `record-absence-boundary` goes red |
165+
| G8 | the ported K7 witness mutated so that application skips `fin` | the adapter-level K7 test fails |
166+
| G9 | a raw cell exported across an SCC | the A13 two-SCC test fails |
167+
| G10 | the contradictory sidecar no longer changes the shadow | the N4 required-read test fails |
168+
| G11 | the report drops `static_dispatch_conditional` or acts on dispatch | the A14 report test fails |
169+
| G12 | an own-bridge / own-cli source change sneaks in | the N2 path guard fails |
170+
| G13 | a synthetic guarded-vs-legacy pair outside the three classes | the classifier reports `UNEXPLAINED` (it is not silently bucketed) |
171+
172+
## D. Hard KILL / PASS
173+
174+
**KILL** gives `RESULT: FAIL — B1 BLOCKED`, lists the blockers, fixes no
175+
semantics here, and triggers when:
176+
177+
1. any MOS, verdict or diagnostic moves (N2 fails);
178+
2. the architecture guard can be satisfied only by an edge the owner did not
179+
authorize;
180+
3. any obligation of N3 has no executable control, or its control is only a
181+
comment;
182+
4. any positive guarded conclusion (a selected MUST / NO, or borrow) is
183+
produced where §0.9 requires `NO_GUARDED_EVIDENCE`;
184+
5. `UNEXPLAINED > 0` on the population. Each such difference is classified
185+
under §10.1 before anything else happens; case 5 goes to the owner;
186+
6. the fail-closed join (A15) cannot be implemented from the A2 facts without
187+
a sidecar/OwnIR change. That is a case-5 STOP, as B0 §E.3 item 3 foresaw;
188+
7. A14 is assumed away or acted on;
189+
8. the kernel is re-implemented rather than reused;
190+
9. the budget below is exceeded.
191+
192+
**PASS** gives `RESULT: PASS — GUARDED SHADOW READ ESTABLISHED`, and requires
193+
all of:
194+
- N1–N6 hold;
195+
- G1–G13 fire;
196+
- the first shadow report is committed as evidence (population, commit,
197+
toolchain), together with the A14 and R metrics;
198+
- the degradation census, and the classification counts with
199+
`UNEXPLAINED = 0`.
200+
201+
A PASS authorizes nothing further by itself. The A14 gate and the R value
202+
gate are separate steps that consume this report. Phase C
203+
(`own-bridge → own-guarded`, authoritative guarded summaries) needs its own
204+
authorization.
205+
206+
## E. Population (the first shadow run)
207+
208+
All of it is at one commit and one toolchain. The legacy side is `own-bridge`'s MOS (the Rust production core); Python/Rust parity is already gated by P-022, and B1 does not re-measure it. The population:
209+
- the repository C# tree (`frontend/`, `audit/`);
210+
- the committed corpus (the 137 files of `corpus/real-world`, `wpf`, `di`,
211+
`fixtures`, `p036-bakeoff`);
212+
- `corpus/p037-shapes` (23 shapes);
213+
- the P-037 controls `corpus/p036-bakeoff/{guarded-consume-*, gv4-control-*,
214+
legacy-honesty-*}`;
215+
- the B0 probes `docs/evidence/p037-b0-probes`.
216+
217+
The report's own schema is versioned (`p037-guarded-shadow/1`). It is
218+
evidence, not a gate on verdicts.
219+
220+
## F. Budget and stop point
221+
222+
Budget:
223+
- `own-guarded`: at most ~900 lines of non-test Rust. That covers the join,
224+
the fact-to-system builder, the dynamic full-sweep driver, application
225+
through `apply`, and the classifier.
226+
- `own-shadow`: one report entry point, at most ~200 lines, following owner
227+
decision R-1: stdin is the facts document, stdout is the report, and it
228+
takes no path arguments.
229+
- The extractor side report (A14): at most ~150 lines of C#, opt-in.
230+
- The architecture and reuse guards, plus fixture tests.
231+
- No new framework.
232+
233+
Twice the budget is a STOP and a re-plan, not a quiet overrun (the #369 lesson).
234+
235+
Stop point: the PASS/FAIL result, the committed first shadow report, and the
236+
metrics for the A14 and R gates. **No phase-C wiring, no A14 solution, no R
237+
experiment, no #368 fix.**
238+
239+
Implementation starts only after the owner has reviewed this contract.

0 commit comments

Comments
 (0)