-`manual/<STATION>.jsonl`: the expert's labels, for him alone: no process and no agent uses them; `auto/<STATION>.jsonl`: those of the Support-Agent `etiqueteur` and those submitted by the aimsight-app `analyst`; `review` is the date the user validated a label in aimsight-app (quality over quantity: only the analyses discussed and validated there), and any change removes it; the agents' reviews of 2026-11-04 and 2026-11-05 were removed on 2026-11-17 (in the history); one label per line, `{"id", "start", "end", "family", "description", ...}`, UTC times, `family` = the family.
-`scripts/`: `validate.py` (the labels against the rules; `check` for one label), `ids.py` (the stable id of each), `client.py` (what the client is told of a detectors' event).
-`scripts/precedents.py`: the RAG of the labels. The labels of `auto/` closest in meaning to a text, with their provenance (validated by the user or not); `--exclude STATION START END` leaves out the analyzed range. bge-m3 model of the Ollama container `ollama-bge-m3` (started by the script itself if it does not answer; port 11435); the `.index/` index, outside git, updates itself at every call (only new or modified labels go through the model; ~8 min to redo everything on CPU).
aimsight-app and Optimizer reach it through a link `labeling -> ~/aimsight-labeling`, ignored by git: aimsight-app reads and writes there (labels, analyses), Optimizer only reads; commits are made here. The scripts run from here (`python3 scripts/validate.py`) or through the link (`python3 labeling/scripts/validate.py`). Descriptions are written in English from now on.
History taken from Support-Agent (the `labeling/` folder, up to commit 48a3092), then the state of aimsight-app on 2026-11-13 (462ba9e): the archives of the etiqueteur and of the reviews (`auto/etiqueteur/`, `auto/revue/`, `auto/revue-croisee/`) and the old `labeling.py` tool remain in the history.