14 Commits
Author SHA1 Message Date
maximeandClaude Opus 5.5 7fb176cf0a Events-learner: the analyst writes its own tools, a tool-builder brings them into agent-tools; /aiguiser retired (D-097)
- inventaire.py: what each source contains on the window (filled or empty columns, metric names, images), names and counts only
- analyser-lot: step 0 on the data, own scripts in <lot>/outils/, section 3 "Outils"
- tool-builder (the optimiser, rewritten): after the analyst, optimises or adds reading tools, never removes; no control yet
- /aiguiser skill, reader, corrector and voir.py removed; its sessions and spec stay as history
- docs: D-097, specs, CLAUDE.md, run.md, README, plan point 56; the shared files also carry another session's pending edits (D-096 entry, plan points 57 to 67)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 17:10:17 +01:00
maximeandClaude Opus 5.5 3b732adc52 Loop renamed events-learner; end benchmark on the same events; spec reduced to the why (D-092)
- /boucle becomes /events-learner: skill and scripts in
  .claude/skills/events-learner/, sessions in events-learner/, spec
  vues-deplacements/contexte/events-learner.md, end page
  out/events-learner_<session>.html, commits "Learn <STATION> ...";
  history keeps /boucle, the review page reads both.
- No benchmark-fin.txt: the end benchmark is the last kept
  modification's, on the same events as the start.
- The spec keeps only the why; the how lives in the skill and agents.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 10:27:05 +01:00
maximeandClaude Opus 5.5 79d83be3ff Loop: the builder becomes the event-builder, called every batch (D-091)
- event-builder: called at every batch, reads the whole analysis and
  decides on its own, against the event base, what is new; an event
  keeps the bounds of the event, not of the batch (plus 6 h).
- the "Nouveautés" section leaves the analysis and the upgrader's
  output; the summary lists contradictions with the base.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 10:17:54 +01:00
maximeandClaude Opus 5.5 c763cda5c3 Loop: the analyst analyses, a new detectors-critic critiques (D-090)
- analyste: the most precise analysis of the batch, detectors allowed as
  a tool; reading, labels, known events, novelties in analyse.md; skill
  critiquer-lot renamed analyser-lot.
- detectors-critic: compares the detectors to the analysis event by
  event, without looking at the data; verdict and at most two
  suggestions in critique.md, read by the detectors-upgrader.
- /boucle step 2, builder, review page, /new-event and score.py import
  follow.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 09:58:48 +01:00
maximeandClaude Opus 5.5 21f8cd1db6 Loop: upgrader and validator become detectors-upgrader and detectors-control (D-089)
- detectors-upgrader: makes the detectors better on the batch from the
  analyst's critique; adds, removes or modifies, removing first; targets
  the significant events missed or badly bounded, not a perfect match.
- detectors-control: the guard against overfitting; never looks at the
  batch, judges the diff and the benchmark on the event base, decides,
  and sends its remarks back to the upgrader.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 08:45:57 +01:00
maximeandClaude Opus 5.5 4d99585474 Detectors, loop and sharpening sessions moved to the repo root (D-084)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 17:19:51 +01:00
maximeandClaude Opus 5.5 0df340231a Diagnostic agent: agents/diagnostic/ renamed agent-diagnostic/ (D-082)
The diagnostic agent is kept in case it is needed again, under a name that
says what it is; entry point still .claude/agents/diagnostic.md; paths updated
in skills, agents, spec, contexts, the living plan and CLAUDE.md; reports and
history keep old paths. Also: two stale tool paths in the living plan.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 16:45:02 +01:00
maximeandClaude Opus 5.5 56b93e9b82 Agent tools: reading tools moved to agent-tools/ (D-081)
The reading tools leave agents/diagnostic/outils/ for a root folder of their
own; paths updated in skills, agents, detectors, scripts, case fiches,
support/, contexts and CLAUDE.md; graphique, vignettes and gif find the repo
root one level up; history keeps old paths.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 16:36:45 +01:00
maximeandClaude Opus 5.5 cb98818712 Events: cases, event map and eventualities graph moved to events/ (D-080)
The case base leaves agents/diagnostic/cas/ for a root folder of its own,
with the event map and its graph; paths updated in skills, agents, scripts,
case fiches, contexts, the living plan and CLAUDE.md; history keeps old paths.
Also: plan point 51, an analyst that improves from session to session.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 16:32:06 +01:00
maximeandClaude Opus 5.5 d5bae7a696 Add the loop's end-of-session page and a detector benchmark on the case base
- 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>
2026-10-26 16:48:13 +01:00
maximeandClaude Opus 5.5 add165dc38 Let every agent inherit the session model and effort (D-063)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 12:09:12 +01:00
maximeandClaude Opus 5.5 7714a55cfa Score the detectors against every label of the station at each loop batch (D-062, point 45)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-25 11:25:12 +01:00
maximeandClaude Opus 5.5 02ed7a4a60 Record the analyst's labels at every loop batch (D-061, point 44)
Each batch now leaves etiquettes.json next to the critique: the analyst's
own reading, written before the detectors' output, one entry per moment,
checked by critiquer-lot/etiquettes.py against the event map and the
station's sensors. Groundwork for a future learned model.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-25 09:39:34 +01:00
maximeandClaude Opus 5.5 da34d16d06 Add draw.io diagrams of the AI pipelines: overview, /boucle, /aiguiser, diagnostic agent
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-24 19:20:25 +02:00