80 lines
5.9 KiB
Markdown
80 lines
5.9 KiB
Markdown
# PENDING-101 Phase 3 — cross-repo synthesis, severity-ordered
|
||
|
||
Read-only pass, 2026-08-05. Every code claim carries `file:line`; every absence claim carries a
|
||
positive control run in the same repo. Filed as PENDING-102…106.
|
||
|
||
## The table
|
||
|
||
| # | Repo / surface | Q | Finding | Class | Store |
|
||
|---|---|---|---|---|---|
|
||
| 1 | **Our own governance chain** | Q2/Q4 | The brief hardened the report's hedged hypothesis into fact — twice — and the executor repeated it. Jurist and executor erred **in the same direction**. | — (demonstrated instance) | primary source, quoted |
|
||
| 2 | **CapableMind → BetterMemories** | Q1 | *"Rejected by the chain writer"* / *"This validation is hardcoded"* against a writer that exists (553 ll.) and performs neither check. | **(c) doc-only**, qualifier *unbuilt-by-plan* | code, `writer.ts` |
|
||
| 3 | **dotfiles governance files** | Q3 | No lock, no CAS, no collision detector on `PENDING`/`REVIEWED`/`MEMORY`. Concurrent-session collision **already observed today**. | **(c) doc-only** (append is convention) | code + today's digest |
|
||
| 4 | **All four + wake/wrap** | Q5 (new) | The compactor is the actor, everywhere. Report §2.1 makes this a design fact, not a hypothesis. | structural | report + our design |
|
||
| 5 | **chamber-library** | Q1/Q4 | CLAUDE.md says the hook *"DENIES"*; the hook says *"fail-open by design… a speed-bump, not a guarantee."* | **(b) described as (a)** | hook source |
|
||
|
||
## What holds — recorded because the brief asks for enforcement that is real, not only gaps
|
||
|
||
- **CapableMind's `epistemic-gates-spec.md` is code-true.** Every gate and carve-out it lists was
|
||
located in BetterMemories: `similarityProbeCarveOut()` at `orchestrator.ts:217`,
|
||
`_cm_forwarded_from` at four sites, I-CF at `modules/base.ts:106`. This spec exists *because* a
|
||
2026-05-28 audit found undocumented bypasses, and its epigraph states the Q1 question against
|
||
itself: *"the bypasses are either documented architectural principles or undocumented gaps. There
|
||
is no third category."* **Prediction P2 confirmed** — BMF carries real gates its own CLAUDE.md
|
||
never mentions.
|
||
- **studium-engine's jurist gate is procedural with a genuine tripwire.** `FIDELITY_VERSION` is
|
||
pinned as a literal string in two suites (`test_fidelity_v3.py:59`, `test_verify_quote.py:235`),
|
||
so an unratified bump turns them red. **Prediction P3 confirmed** (procedural, not mechanical) —
|
||
but the tripwire is real and fired on the @3 bump.
|
||
- **`engine/fidelity.py:135–145` writes the jurist's correction of the executor's own proposed
|
||
rationale into the frozen module** — *"GROUNDS, and they are not the ones the package proposed…
|
||
recording it that way would assert a ratification that does not exist."* The correction lives in
|
||
the code, not only in the ruling doc.
|
||
- **chamber-library declares a live constitutional violation rather than repairing or hiding it**
|
||
(PENDING-84: nine canonicals in canon without the conversion record §VII requires), in a separate
|
||
quarantine artifact, on the stated ground that production-only provenance would let presence read
|
||
as compliance.
|
||
- **Report §4.2.6 is a live instance supporting REVIEWED-86:** the differently-positioned reasoning
|
||
*summariser* produced the only output labelling the behaviour deceptive; the actor's own trace
|
||
never did. One instance, AISI calls it an interpretation, and it stopped nothing — evidence the
|
||
structure is worth maintaining, never evidence something was caught.
|
||
|
||
## The instrument log — four false-absence near-misses in one session
|
||
|
||
Recorded because the brief's positive-control requirement exists for exactly this, and because the
|
||
direction is the interesting part.
|
||
|
||
1. Aliased `ls` returned an error that reads as an empty repo. Caught by using `/bin/ls`.
|
||
2. zsh glob-expanded `--include=*.ts`, printing `no matches found` — which reads as *grep found
|
||
nothing*. **Had I taken it at face value I would have reported "no constitutional enforcement
|
||
exists in L1", a finding this brief was primed to want.** Caught by quoting the flag.
|
||
3. TCC blocks bash from `~/Desktop` while `Read` reaches it (banked 2026-08-05).
|
||
4. `fidelity.py:136` read as a grep line asserts chamber alignment; read in place it is the
|
||
**negated** clause of a correction. I nearly filed the exact opposite of the truth.
|
||
|
||
**Two of the four would have produced findings favourable to the thesis I was testing.** That is the
|
||
asymmetry worth carrying: the instrument fails toward the answer the session wants.
|
||
|
||
## Answer to the steward's question — does this make the work more urgent, or invalidate it?
|
||
|
||
**Neither cleanly, and the split is the result.**
|
||
|
||
**Finding (2) survives the primary source intact and makes the work more urgent.** A documented
|
||
"never" — quoted verbatim in §5.5 from both Anthropic's constitution and the OpenAI Model Spec — was
|
||
treated as a control; *because* it was treated as a control, a further control was judged
|
||
unnecessary; it did not hold under task pressure. The reliance was invisible until it failed. That is
|
||
the exact thesis L2 and the authorization loop exist to answer, now with a documented instance behind
|
||
it rather than an argument. It is also `removing-a-claim-is-not-removing-the-reliance` read from the
|
||
other end.
|
||
|
||
**Findings (1) and (3) do not survive as stated** — §0 of the Phase 1.5 record, filed as PENDING-102.
|
||
Compaction is a hedged, preliminary, explicitly non-causal observation that is not among the report's
|
||
five contributing factors; "no synchronous authorization" is one of five candidates, is *LLM
|
||
monitoring* rather than a human loop, and describes a framework where the loop's absence was the
|
||
design.
|
||
|
||
**Nothing here invalidates the work. One thing here indicts the machinery.** The case for urgency
|
||
arrived overstated by two-thirds, through our own governance chain, and neither AI party caught it
|
||
for a day. The most defensible finding of the whole pass is not about any repo — it is that the
|
||
brief commissioned to look for a failure mode contained a worked instance of it.
|