docs(decisions): amend D-138 with Spike 1 findings

- Tell-variant caching: 6→length-gated (short=neutral only, medium=3,
  long=6). 2B model produces identical output across tell states on
  short lines — confirmed across two test rounds.
- Composition-engine occasional injections: oath vocabulary, faith
  expressions etc. controlled by prompt generator frequency, not model.
  Systemic pattern for any culture marker that should appear occasionally.
- NI-1/NI-5 culture-gated: religious language and Earth-origin markers
  are per-culture injector constraints, not universal bans. Cultural
  heritage from colonization history is intentional. Earth is not lost.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

decisions/content.md

@@ -416,10 +416,12 @@ How narrative, NPCs, and world content are created: content tiers, NPC generatio
   - **Content tiers:** Baked (hub zones, build-time, human-reviewed) → Pre-voiced (background queue, priority-ordered) → Base text fallback (always present).
   - **Tell treatment:** Passthrough always. Tell state flows into re-voicing prompts as universal tone injectors. Cultural flavor is conditional and additive — humans are humans first; micro-expressions and body language must remain universally recognizable. Per-culture tell-tone tables are optional enrichment, not a launch requirement.
   - **Determinism:** Cache-as-determinism. LLM generates once per seed; result cached. Cache lookup is deterministic.
-  - **Caching:** 6 variants per line (neutral + 5 TellCategory states). Key: `(npc_stable_id, line_id, tell_state, culture_id)`.
+  - **Caching:** Content-length-gated variants. Short lines (≤7 words): neutral only. Medium lines: 3 variants (neutral, high-affect, guarded). Long lines: up to 6 variants. Key: `(npc_stable_id, line_id, tell_state, culture_id)`. *(Amended 2026-03-07: Spike 1 confirmed 2B model cannot produce distinguishable tell-state variants on short lines — 5/5 states produced near-identical output for "Inspection's next week." Length-gated caching reduces wasted compute/storage.)*
   - **Hardware:** "AI-Enhanced Dialogue" toggle. Layered detection: RAM check → TPT benchmark → recommendation. No hard minimum spec floor. Player can always override.
   - **Distribution:** Model bundled in game install (~1.5GB).
   - **Protected categories (never re-voiced):** Tell behaviors, secret-tier dialogue (D-028 Layer 3), anchor lines (D-092), relationship-specific lines naming third parties.
+  - **Composition engine:** Occasional prompt injections (e.g. oath vocabulary, faith expressions) are controlled by the prompt generator at a configurable frequency (e.g. 1-in-4), not by the model. The model never decides injection frequency — it either receives the clause or doesn't. This is a systemic pattern applicable to any culture marker that should appear occasionally. *(Added 2026-03-07: Spike 1 proved 2B models treat vocabulary lists as required markers. Composition-engine gating eliminates both over-use and under-use.)*
+  - **Negative injectors:** NI-2 (no military ranks), NI-3 (technology vocabulary), NI-4 (no banter/wit) are universal. NI-1 (religious language) and NI-5 (Earth references) are culture-gated — cultures with religious or Earth-descended heritage use appropriate expressions. Earth is not lost; cultural heritage from colonization history is intentional and expected. *(Amended 2026-03-07: Jeroen's decision — "a planet colonized by a company from Dublin would show clear traces of Ireland." NI-1/NI-5 moved from universal bans to culture-specific constraints.)*
 - **Validation:** Two-spike strategy. Spike 1: Rust `sr-voice` CLI + manual prompt testing (Jeroen/Mellanie/Paula). Spike 2: full pipeline integration.
 - **Rationale:** D-122 (all NPCs generated) and D-128 (culture implicit in starting location) require NPC voice to scale across zones and cultures without O(R×Z×C) hand-authoring. The re-voicing model is the only architecture that scales while preserving content quality. Base-text fallback ensures the game is complete without the pipeline.
 - **Source:** LLM Voice Pipeline Workshop (2026-03-07)
@@ -432,4 +434,4 @@ How narrative, NPCs, and world content are created: content tiers, NPC generatio
 
 ---
 
-*38 decisions. Last updated: 2026-03-07 (D-138 added; D-123 amended; D-124 superseded — LLM Voice Pipeline Workshop)*
+*38 decisions. Last updated: 2026-03-07 (D-138 added and amended with Spike 1 findings; D-123 amended; D-124 superseded — LLM Voice Pipeline Workshop)*