3.0 KiB
3.0 KiB
CLAUDE.md
aimsight-app: the control station of the AIMsight diagnostic (README.md): the web app, and the launching of processes whose code lives elsewhere. A camera follows targets on a structure; the detectors read the displacement series of the stations and flag the moments when the curves must not be trusted (rain, fog, spider web, turbulence…) or a real movement. The architecture of the repositories: docs/architecture.drawio.
- The processes: the Analysis tab launches
agents:analyst(pluginagents/) on a range, withinstructions/analyst.mdandDETECTORS: no(labels and report inlabeling/auto/analyses/<STATION>_<start>_<end>/, submitted tolabeling/auto/<STATION>.jsonl); "Optimize the detectors" launches/optimizeinoptimizer/on the analysis (its request inapp/server/analysis.py, its summary inoptimizer/sessions/<analysis>_<time>/summary.md), which commits the detectors indetectors/and the reading tools intools/. - The links (ignored by git, one copy of each repository on the workstation):
data/,labeling/,detectors/,tools/,agents/,optimizer/,models/(the pilot of learned detectors); each thing is committed in its own repository, never here. This repository carries no agent, no reading tool, no workflow. - The truth: the labels of
labeling/auto/; the labeling knowledge is inlabeling/. - The contracts: with the detectors,
detectors/CLAUDE.md(categories.events,bench/score.py); with the agents,agents/README.md(the request of the analyst); with Optimizer,optimizer/README.md(the request of/optimize). A renaming over there requires the change here. The Data page passes to the detectors the measurements read bytools/scripts/data.py, whereas the benchmark and Optimizer read throughdetectors/scripts/data.py: a reading fix in one is carried over to the other. - The benchmark:
python3 detectors/bench/regression.py --labels labeling/auto --data data(~3 min); the score of a range:python3 detectors/bench/score.py data/<STATION> --labels labeling/auto/<STATION>.jsonl --from YYYY-MM-DD --to YYYY-MM-DD(--toexcluded). - The pumping: in
~/aimsight-data(extraction/pump.sh, VS Code tasks pump, pump a range), read-only on the platform; user guide~/aimsight-data/extraction/README.md. Claude may launch it on small ranges; a long range or a history, outside busy hours. - Check a change of the app:
.venv/bin/python app/server/check.py, thencd app/web && npm run buildand launch the server. The labels:python3 labeling/validate.py.
Rules:
- Every time is in UTC.
- No rule specific to a station, a target or a date.
- Read-only on
data/, except the pumping; never copy the identifiers of the metrics (SIM_CCID,ip*). - Never read
.env(the credentials of the platform). - The agents run on the Claude subscription, never on an API key.
- Commits by path, never
git add -A: another session may be working in this repository. - Language: the repository (documents, code, UI) in English; conversations with the user in French.