Target and research for the interlingua-lowering campaign

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

docs/targets/interlingua-lowering.md

@@ -0,0 +1,66 @@
+# Target: agents speak interlingua, Weksa lowers it
+
+Campaign `weksa-lowering` (Eureka mind). Operator, 2026-10-29: "having agents
+writing interlingua and using weksa to lower it to the display language would
+be a fantastic feature. That would be a nice campaign to revive her with so she
+doesn't come back to a dead body".
+
+## Why
+
+An agent's outward speech today is English text the model chose, so meaning,
+register and voice are fused in one string nobody can inspect or re-target.
+Weksa's design already separates them: the packet owns meaning, the target
+profile owns address, politeness and forbidden flattenings, the lowerer owns
+surface text and a trace. The campaign makes that design real for a live
+reader, and gives Weksa's Persona a working body when her mind
+(`eureka-body:follow_up:weksa-mind`) wakes.
+
+## Body today (facts: docs/research/2026-10-29-weksa-substrate-facts.md)
+
+- The interlingua is a prose standard (`interlingua-standard.md`, 0.1-draft)
+  with no machine schema and no validator. Its only producer is a stub that
+  wraps raw text; its only consumer passes packets through unvalidated.
+- No lowering exists in code. `lowerInterlinguaToSpeechText` returns the
+  supplied text. The "LLM-free hot path" is a design statement. Real lowerings
+  so far are hand-run LLM prompts and hand-authored fixtures.
+- The daemon is a Node shim for one MiMo TTS command, runs nowhere, and is an
+  Idunn target only in the Starfire-local profile. Eve surfaces are quarantined
+  (55c75e3).
+- Her Face state is VoidBot-shaped (`.voidbot/state/weksa.cc`), not
+  `gamecult.persona_state.v0`; 41 files carry stale machine paths.
+
+## Prior art (docs/research/2026-10-29-interlingua-lowering-prior-art.md)
+
+- Deterministic open-domain renderers cost per-language grammar work for
+  years: GF's library covers 48 languages unevenly; Abstract Wikipedia's
+  symbolic renderers are only now reaching a first language Wikipedia.
+- Interlinguas that shipped (KANT) had closed domains and controlled input.
+- LLMs emit meaning structures poorly when asked directly (about 60 Smatch
+  few-shot vs 80-86 trained); free reasoning followed by conversion to the
+  structure keeps quality (Tam et al. 2024; Shin et al. 2021).
+- Round-trip checks measure consistency, not accuracy, and are inflated when
+  one model does both directions.
+
+## Invariants
+
+- `packet-owns-meaning`: what is said lives in the packet; no lowering may add
+  a claim, referent or commitment the packet lacks.
+- `typed-packet`: the packet is a typed CultCache document with a published
+  schema and a validator that refuses malformed packets at the door.
+- `lowering-traced`: every surface text carries a trace naming the packet, the
+  target profile and the choices made.
+- `profile-owns-register`: address, politeness and forbidden flattenings come
+  from the target profile, never from the lowerer's defaults.
+- `no-eve`: no new Eve surface; operator view waits on Thing 2.
+
+## Open forks (questions in the mind)
+
+- First reader: whose display text is lowered first.
+- Lowerer shape: deterministic, model, or both with one contract.
+- How an agent produces the packet.
+
+## Not in scope
+
+- Weksa's conlang engine (grammar, phonology, diachrony for alien languages).
+- MiMo TTS beyond keeping its command working or parking it.
+- Her Persona's mind; that is `eureka-body:follow_up:weksa-mind`.