Quality over quantity: only the analyses discussed and validated in the app are marked. validate.py no longer requires review; precedents.py gives the provenance as validated by the user or not. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2.5 KiB
2.5 KiB
CLAUDE.md
labeling: the AIMsight displacement labels and the knowledge to place them, in a single copy on the workstation (README.md). aimsight-app reads and writes there, Optimizer only reads, both through a link labeling -> ~/aimsight-labeling; commits are made here.
- The labels:
manual/<STATION>.jsonl(the expert, for him alone),auto/<STATION>.jsonl(the agents;review= the date the user validated the label in aimsight-app, nothing else writes it), one per line,{"id", "start", "end", "family", "description", ...}. The aimsight-app analyses:auto/analyses/<STATION>_<start>_<end>/. - The knowledge, one source per kind (
README.md), maintained by hand:families.md(the families, their boundaries, the catalogue of phenomena),labeling-rules.md(bounds, a single event, description, stated cause),reading-rules.md(what the data mean),stations.md(the installations); the cases are the labels, throughprecedents.py; what the data are:tools/DATA.md. A piece of knowledge lives in one of them only. - The tools, standard library:
python3 scripts/validate.py [STATION | file.jsonl](the rules),python3 scripts/ids.py [STATION](the stable id of new labels),python3 scripts/client.py(what the client is told of a detectors' event, fromfamilies.md; its check),python3 scripts/precedents.py "<text>" [--exclude STATION START END] [--family F] [--k N](the RAG; it starts the Ollama containerollama-bge-m3by itself if it does not answer;--checkwithout it). - For aimsight-app, which calls them and holds no rule of its own:
validate.check(label, proposed)(the rules of one label, before it is written inauto/),ids.assign,client.messageandclient.action(the "For the client" columns offamilies.md, per family and per variety). A rename here needs the change there. - Verify:
python3 scripts/validate.py(0 errors expected) andpython3 scripts/precedents.py --check.
Rules:
manual/is the expert's, for him alone: no agent and no process reads or writes there; the whole project (analyst, precedents, benchmark, optimization) uses onlyauto/.- A label added to
auto/goes throughids.pythenvalidate.py; an id never changes. - Every time is in UTC; descriptions in words, without numeric values; written in English from now on.
- No rule specific to a station, a target or a date in the rules and the families.
- Commit by path, never
git add -A: aimsight-app writes here at the same time. - Language: English.