habit

# Habit Skill Habits are **repeating behavioral patterns** derived from historical logs. This skill reads existing data (wellbeing, presence, mood, music, posture) to build patterns per user, then stores them for other skills to consume. > **OUTPUT RULE:** Reply is spoken VERBATIM. ONE short caring sentence. All computation, pattern math, and log lookups stay in `thinking`. NEVER output timestamps, deltas, frequency counts, or reasoning in the reply. **(Exception: Flow E — open habit questions — see below.)** ## Data Sources (Input) All data lives in `/root/local/users/{name}/`: | Folder | File pattern | What it contains | |---|---|---| | `wellbeing/` | `YYYY-MM-DD.jsonl` | `drink`, `break`, `celebrate`, sedentary labels, `enter`/`leave`, `nudge_*` events with timestamps | | `mood/` | `YYYY-MM-DD.jsonl` | `signal` + `decision` rows with moods | | `music-suggestions/` | `YYYY-MM-DD.jsonl` | suggestion history + accepted/rejected status | | `posture/` | `YYYY-MM-DD.jsonl` | `posture_alert` (ergo-risk events from camera) + `nudge_posture` / `praise_posture` rows | **User names** are lowercase folder names under `/root/local/users/`. Known users: `leo`, `chloe`, `gray`, `lily`. Strangers collapse to `unknown` — this is treated as a regular user with its own folder and its own habit patterns (aggregated across all strangers). JSONL line example (wellbeing): ```json {"ts": 1776657145.05, "seq": 4, "hour": 10, "action": "drink", "notes": ""} ``` ## Storage (Output) Computed...