Load a Samsung Health export (.zip or extracted folder) into the local database, replacing the old one. Takes about 10 seconds. Re-run whenever the user downloads a fresh export.

Save the periods to compare, e.g. [{"name": "Before", "start": "2025-01-01", "end": "2025-06-30"}, {"name": "After", "start": "2025-07-01"}]. end empty means today. Optional tz_offsets (["+01:00"]) overrides automatic travel detection for that period. Pass [] to go back to the 90-day default.

Date range, data coverage per metric, available metrics and the periods being compared.

Monthly averages per metric with month-over-month % change (mom_pct). Dates are YYYY-MM-DD. home_only=True drops travel days. Metrics default to the core set; see overview() for all keys.

Compare two periods. Either names from set_periods (defaults: the first two), or ad hoc ranges a_range/b_range like "2025-03-01..2025-03-31" (period_a/period_b then become their labels). Returns mean/median/n per period, delta %, Cohen's d and a plain verdict per metric. Travel days excluded by default.

Trips detected from the phone's timezone (no location data needed), each compared with the 30 home days before it, plus the overall travel effect on steps, sleep and heart rate.

Average steps for each hour of the day (0-23), per period. Shows when you move.

Average of a metric per weekday (Mon..Sun), per period. Useful for weekend effects (Sat/Sun vs Fri/Sat).

Bedtime, wake time, sleep hours, split nights and bedtime consistency (std dev in minutes) per period.

Each day's value against your own trailing baseline, with a z-score. |z| > 2 is unusual for you.

Timeline of contiguous UTC-offset runs: homes and trips. Use it to suggest periods (e.g. a move).

Recorded exercise sessions grouped by month, period and type.

Tables and columns available to run_sql.

Run a read-only DuckDB query. Main table: daily. Others: hourly_steps, exercise, sleep_sessions, weight, day_tz, day_home.

Everything the dashboard renders, including precomputed signals and trips. Read this before writing the story.

Render the single-file dashboard with the story you wrote from the payload. actions: 3 items of {title, detail, metric, target}, each grounded in a payload number. headline: one sentence, the most important finding. subtitle: one line of context. callouts: labels on the 24h clock, e.g. [{"hour": 6, "text": "Morning run"}], only for causes the user confirmed. travel_note: one or two sentences about the user's travel, from trips. trip_labels: [{"start": "2025-08-02", "label": "Lisbon"}] keyed by trip start date; only labels the user confirmed or that the timezone makes unambiguous. Returns the file path; set return_html=True when the client cannot read local files (e.g. Claude Desktop).