What (One-liner)

Canvas LLM-in-the-loop strategy generation: regime + symbols → Fin-R1 generates Python pair-trading code + rationale → optional Python simulation. Tier 5 attestation track (not Tier 4 numerical tolerance).

How to use

macro_factor_v1 (regime=expansion) → casa_strategy_v1 (SPY+TLT)
                                      → strategy_code (momentum pair trade)
                                      → [run-sandbox Docker execution]
                                      → risk_management_v1

Core formulas

See frontmatter. Flow: generate-strategy LLM → extract Python code → optional dual-agent-simulate → combined return.

Assumptions & applicability

Assumptions: Fin-R1 / cloud LLM available + code block extraction works + Python sim tail already golden.

Applies to: macro-regime-driven auto-generated pair strategies, scenario analysis, LLM-finance demo.

Does not apply to: live trading, HFT, byte-deterministic regulator demos.

Known limitations

See frontmatter. Six items: LLM non-determinism / prompt drift / mock fallback / independent Python sim / LLM latency / sandbox independence.

References

• SUFE-AIFLM-Lab/Fin-R1 — local LLM
• Pangura Internal Prompt Library (2026-03) — prompt templates

Golden Test

Tier 5 attestation track. Python tail (simulate_dual_agent) covered by tests/golden/fixtures/tier4/casa_dual_agent/. LLM part requires: prompt_cid + model pin + ≥3 attestations (after Phase B framework lands).

Changelog

• 1.0.0 (2026-04-21) — First Active (Tier 5 attestation track)