longitudinallisted

When the user types /longitudinal, run the multi-year correlation pass and surface only the strongest signals across years of health-mcp + journal data. ## Language Generate the report in the language the user writes in. If Spanish, all sections including the panel commentary are in Spanish. ## Scope resolution Parse the argument for window: - `all` -> earliest record in DB to today - `Ny` -> last N years (e.g. 5y, 3y) - `Nm` -> last N months (e.g. 18m) - blank -> 365 days If `all`, query the DB for the earliest record date first: ```python SELECT MIN(start_date) FROM records WHERE value IS NOT NULL ``` ## Step 1: top_signals first (the noise filter) Always call `health_top_signals(vault_root=..., lookback_days=N, min_strength="moderate")` first. This is Lara Briden's dissent codified: most correlations are noise. The substrate has already filtered. Start with what's left. If `signal_count == 0`, report "no signals above noise threshold for this window" and stop — do not invent. Surface what IS there: the deltas and r-values that didn't quite clear the threshold, in case the user wants to relax it. ## Step 2: Floor x body fingerprints for the user's top 3 Floors Load the journal index, count Floors in the window, take the top 3 by occurrence. For each Floor, call: ```python health_floor_body_fingerprint(floor=<name>, vault_root=..., lookback_days=N) ``` Report the body fingerprint deltas (HRV, RHR, sleep efficiency, cycle phase distribution). If `delta_pct` exceed