- cancel reverts only the run's commits (base..HEAD), never the caller's edits - validator diffs base..HEAD, not the working tree - fix commits carry their Co-Authored-By line; no redundant end benchmark - score.py: clear error on a missing labels file; docstring says end is not passed - usage lines; README and CLAUDE.md for the generic workflow Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2.3 KiB
2.3 KiB
detectors
AIMsight anomaly detectors (Python 3, standard library only) and the Claude Code plugin that improves them (/detectors:wf-improve). Everything is in English: code, identifiers, docs, outputs. Layout and usage: README.md.
Contract (do not break)
- One detector per family, in
scripts/:visibility.py,obstruction.py,target_issue.py,thermal_displacement.py,no_data.py,displacement.py(D-119).categories.pyloads everyscripts/*.pythat hasdetect: never put another script with adetectfunction, or with side effects at import, directly inscripts/; tools go inskills/wf-improve/scripts/. detect(measurements)returns episodes with the keysstart,end,kind(the family),label(the variety),text,ignore,sensors. A detector may also declaretemperature,camera,metrics(categories.CONTEXT) orend;categories.eventspasses them by introspection.- Label files are external data and keep their French keys:
debut,fin,categorie,description. - Diagnostic-app uses this repository as its
detectors/submodule:categories.events,categories.CATEGORIES(process:images,none,check), the--from/--toCLIs,/detectors:wf-improve. A rename here needs the matching change there.
The workflow stays generic
skills/wf-improve/SKILL.md and agents/ describe only the workflow (range + labels → upgrader → validator → summary). Everything specific to a caller (its paths, its files, its git rules, where the summary goes) is given in the request at launch, never written here. The tools take their paths as arguments.
Rules
- A constant added or changed updates
thresholds.mdin the same change; check withgrep -nE "^[A-Z_0-9]+ = " scripts/*.py. - No rule specific to a station, a sensor or a date.
- A change to a detector is checked with the benchmark:
python3 skills/wf-improve/scripts/regression.py --labels <labels folder> --data <data folder>(Diagnostic-app:labeling/auto,data; about 3 min). A refactoring must leave every figure unchanged. - History references in docstrings and
thresholds.md("wf-improve X, mod. 1, S2", "X, batch 01", D-xxx, E-xxx) point to past runs and to decisions recorded in Diagnostic-app/Support-Agent; keep them when editing a rule.