- Every auto label carries an id (<STATION>-<n>, labeling/ids.py), kept on edit, given to
new labels by labeling.py and by the reviews; controle.py requires it, unique. The
cross-review matches labels by id, and an applied review is locked (applique.md).
- The label map starts with a summary (labels-map/sommaire.py): readers take the summary and
sections 2-4 in full, then only the cards of the phenomena they meet.
- Tool-builder session on the reviewers' difficulties: jours.py --lissage/--fraction,
ensemble.py --suivre and rejected measures left out of --rigide, --residus non, zero noise
after a lost reference, new agent-tools/stations.py (several stations on one timeline),
long outputs convention in lire-les-donnees.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- The labeler writes to its own folder (etiquettes.jsonl); labeling/auto/ only holds
reviewed labels, merged by /review-auto-labels (new apply script: dated, sorted, checked).
- labeling/controle.py also checks a proposed file; the labeler and reviewers run it before
handing back. Reviewers keep their measurements in revue.md, never in the labels.
- Reviewer instructions explicitly add their scripts, .venv/bin/python and for loops to the
lire-les-donnees commands (the contradiction raised by 12 reviews).
- Expert validation optional in /review-auto-labels; an expert hint given to the labeler is
written in the labels it touches. Cross-review ends with the releveur.
- docs/ameliorations-processus.md: 17 entries from this review, by the releveur.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The same ameliorateur agent runs after the releveur; its scope now depends
on the process named in its request.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- etiquetage.md sits next to etiquettes.json in every case: C-001..C-005
moved from vues-deplacements/benchmark/etiquetage/, C-006..C-008 written
from lot 01 (source and table of moments, coded names)
- anonymiser.py --etiquettes now writes etiquetage.md too (with its test);
builder, /nouveau-cas, anonymiser-cas, agent spec and D-069 follow
- vues-deplacements/benchmark/ keeps only the history
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- End-of-session page for /boucle: the session's curves, the analyst's
labels against the detectors' events per category, a plain score table
and the benchmark (comparaison.py, D-066)
- Detectors moved to vues-deplacements/detectors/ (D-067)
- Detectors must detect everything; what the client sees is a separate
layer (D-068)
- Benchmark: each case keeps its labels from creation (etiquettes.json),
benchmark.py scores the detectors on every case, history in
vues-deplacements/benchmark/historique.csv; run by /boucle at each lot,
after each change and at the end, read by the upgrader and validator;
labels for C-001..C-005 from one analyst pass corrected by their files,
C-006..C-008 from lot 01 (D-069)
- Fixes from the releveur's notes: /boucle arguments and other sessions,
branch name in the spec, detector name in categories.py output, learned
case header, anonymiser.py (camera/, no empty CSVs, --etiquettes),
ensemble.py (clock-aligned steps, title), plages.py (same-sign merge),
labeling request written into /nouveau-cas
- Also carries the other session's uncommitted D-065 edits in the same
files; data/, .gitignore, pomper.py and stations.py are left out
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Each /boucle subagent now ends its output with a Difficultés section;
at the end of a session the orchestrator calls the releveur once, which
locates the instruction or file at fault and records it in
docs/ameliorations-processus.md, without fixing anything.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>