session 2026-07-23: CORRECT the wake-frame — verified against the plans; two parallel tracks (corpus + engine), not a linear four-movement arc; verifier-next not pattern-finder (stale-memory error caught)

claude/memory/session-2026-07-23-reviewed69-70-v2.4-v2.5-character-as-image-glyph-mapping.md

@@ -4,7 +4,7 @@ description: "A very long single session that ran the whole PENDING-69/70 arc to
 metadata: 
   node_type: memory
   type: project
-  modified: 2026-07-23T19:34:45.497Z
+  modified: 2026-07-23T19:39:14.378Z
   originSessionId: d6f7ee32-e448-465c-967f-54c1d9f9c8a2
 ---
 
@@ -51,6 +51,9 @@ This was a LONG session — far past "one concentrated bite." It stayed coherent
 
 **LITERAL QUESTION for next-Claude:** When the Levi pilot runs — 14 works, ~18 mutilation sites now repaired by glyph-mapping, converter-better divergences to adjudicate against the source — does the JUDGMENT COST stay tractable (the jurist's actual worry: does one-door's cost explode when the easy mechanical patterns run out?), or does the per-work source-adjudication blow the budget? And the paired sub-question: do the 14 witness brackets interior-verify cleanly against the source spine, or does one resist (the La Chute lesson at omnibus scale)?
 
-**THE FRAME WE WAKE INTO (the altitude, steward-affirmed at session close — "we wake to this tomorrow morning"):** Read the telos (`project-studium-engine-telos-chamber-of-voices.md`) FIRST, because this session's finding is a telos-level event, not a corpus chore. The charter's hinge: *"a counsel surfaced from a corrupted source is not counsel; it is the simulacrum v1 already was."* Today proved the extant corpus is NOT yet the trustworthy substrate — a graduated canonical said `Wstawa` where Levi wrote `Wstawać`, and the whole body was converted pre-constitution/pre-fleet. So the one-door re-verification is **not plumbing before the real work — it is the condition of the real work** (a mutilated Levi surfaced as counsel *is* the v1 simulacrum reappearing one level down). Four movements: (1) **prove the door scales — the Levi pilot, tomorrow, the hinge**; (2) restore the body (turn *converted* → *verified*, per-source, human-in-the-loop); (3) the engine over the trusted set (L2 pattern-finder next, then L3 the chamber of conversing voices, the frontier); (4) the chamber of voices — the destination. **The strategic discipline the pilot forces: order the restoration by TELOS, not by census** — verify the sources the FIRST conversations need (The Making sequence, then the violin treatise), in the order the voices need them; NOT a blind sweep of the 47-file / character-as-image classes. That keeps the restoration finite and proportionate. **And the pilot itself is a genuine fork, not a formality:** hold its judgment-cost number as a real measurement willing to be surprised — if it's tractable, the trusted-corpus path opens as a paced telos-ordered march; if it explodes, that's learned before hundreds of hours, and the verification strategy for the legacy body must change. Let the substrate answer, not the hope.
+**THE FRAME WE WAKE INTO (the altitude, steward-affirmed at close — "we wake to this"; VERIFIED against the plans 2026-07-23, an earlier draft's sequencing drift CORRECTED):** Read the telos (`project-studium-engine-telos-chamber-of-voices.md`) + the engine charter-update (`studium-engine/docs/the-studium-engine-charter-update-after-the-substrate-2026-07-04.md` Part V) FIRST. **The telos is the measure** — the charter's hinge, *"a counsel surfaced from a corrupted source is not counsel; it is the simulacrum v1 already was,"* is why today's char-as-image finding is telos-level, not a chore. **BUT the shape is TWO PARALLEL TRACKS advancing together, NOT a linear four-movement arc** (that was my drift; the plans correct it):
+- **Corpus track:** grow the VERIFIED tier via one-door (the fence — converted/verified/fenced — already handles tiered trust; the engine reasons only over *verified*, which grows one source at a time). The char-as-image finding TIGHTENS the graduation gate (glyph-check now part of what makes a file *verified*) — it does NOT invalidate the corpus. **The Levi pilot gates whether the tier can grow AT SCALE** (`scale_application`). Order restoration by TELOS (the Making sources the engine grounds first) — a steward-PACING call that slots alongside the plan's other open-corpus tracks (Loeb apparatus recovery, source-match remediation), NOT a re-ordering the plan already fixes.
+- **Engine track (already underway, in parallel — "the engine cannot outrun the corpus" = paced-together, NOT corpus-first-then-engine):** verifier-first. V0 ratified, **V1 verify-quote BUILT + `fidelity_equivalence@2` GOVERNING**; **NEXT = N1 (navigation-tree builder) → V2**, NOT the pattern-finder (`pattern_finder.py` was built AHEAD of sequence, pass-1 PASS-BUT-FALSELY — the standing reason the verifier leads; the "L2 pattern-finder next" in my first draft + the 35-day-old telos memory is STALE). The **voices (L3, the chamber-of-voices telos) are the FRONTIER, behind the verifier track** (Steps 8–9) — correctly last.
+**The pilot is still tomorrow's right work and still a hinge — but the hinge on the CORPUS track's ability to SCALE, running parallel to an engine track already several organs in.** And it is a genuine fork, not a formality: hold its judgment-cost number as a measurement willing to surprise — tractable → the verified tier grows as a paced telos-ordered march; explodes → learned before hundreds of hours, and the legacy-body verification strategy changes. Let the substrate answer, not the hope.
 
 **State at wrap:** chamber-library main @ `3852d46` (github current; **origin 2 behind — Gitea down**) · spec **v2.5.0 OPERATIVE** · fleet 222/222 · glyph-mapping Q3 precondition MET for Levi · REVIEWED-69/70 placed, PENDING-69 closed / PENDING-70 ruling received (step 1+2 done, step 3 held). Governance dotfiles state committed+pushed at this wrap (§6.5). Ledger: `session-ledger-2026-07-23.md`.