Economy organ spec review: data flow corrections, toolchain decisions, typo fix

- M3 hub: predictions publish continuously to Marketplace via M2 (not trader-queried)
- M3 BoundedPrediction: three quality metrics (confidence, correctness, certainty)
- M5 traders: read predictions from Marketplace, mixed roster (LLM + bots)
- M7 SAE: monitors at Marketplace level (the only trader interface)
- M6 Conductor: clarified as LLM, not rule-based
- M4 wallets: one multi-chain wallet per trader, strictly 1:1
- M1 Marketplace: added query_predictions interface for traders
- M3d/M3e: Fortran 2018, gfortran, fpm, OpenBLAS, hand-rolled numerics
- M3b typo: "literao" -> "literal"
- SessionStart hook: added gfortran, fpm, Tcl, ECLiPSe Prolog, Zig, Foundry
- Stub fpm.toml for M3d (mev sims)

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

core/docs/plans/M6-conductor.md

@@ -57,7 +57,8 @@ inference wrapper sits alongside the Marketplace.
   fields, same signatures. The Conductor processes them the same way the Brain would.
 
 ## 8. Build steps
-1. Define the Conductor's decision model (rule-based for v1? fine-tuned LLM for v2?).
+1. Define the Conductor's LLM decision model (specialist-trained; rules are enforced by the
+   Marketplace law script and wallet spending limits — the Conductor applies judgment).
 2. Wire SAE alert intake (M7 → M6).
 3. Wire Marketplace veto check (M1 → M6 → approve/veto).
 4. Implement trader pause/investigate/resume flow.