Commit Graph
51 Commits
Author SHA1 Message Date
maximeandClaude Opus 5.5 be147e92df Detector-learner per family, on all stations, launched by Claude (D-132)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-05 09:13:48 +01:00
maximeandClaude Opus 5.5 d55de98746 Labeling processes: lessons from the auto-label reviews (D-130)
- 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>
2026-11-05 08:31:53 +01:00
maximeandClaude Opus 5.5 85e590762b Presentations for the client: Sandouville, no data-gap slide, settlements in corr_y (D-127)
The three October decks (BREITHORN, MICHIGAN, NEBRASKA) no longer criticise
the system: facts and their external cause only. Figures redrawn in corr_y
(figure-y.py), BREITHORN parallax kept. Sources and PDFs named after the
station; the charter's draft stamp reads "Sandouville".

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 17:36:25 +01:00
maximeandClaude Opus 5.5 6fbd7510b7 Etiqueteur: October labels for 8 stations; its folder moves to labeling/auto/etiqueteur/, analyses and scripts versioned (D-126)
Labels for CLARIDEN, FLORIDA, JUNGFRAU (gaps 06-20.10, 26.10-01.11), LENZSPITZE,
NIEDERHORN, NORDEND, SNCF01, WILDSTRUBEL. Figures and tool outputs stay out of git.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 16:33:41 +01:00
maximeandClaude Opus 5.5 98c3308ca7 Detector-learner: one benchmark, scripts moved, critic with realistic suggestions (D-120)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 15:12:24 +01:00
maximeandClaude Opus 5.5 9df0cde364 Detector-learner NEBRASKA: process fixes
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 14:07:37 +01:00
maximeandClaude Opus 5.5 2a8d3da49d Detector-learner: --ameliorer, the improver after the releveur as in /events-learner (D-071); the improver covers both processes
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 13:47:44 +01:00
maximeandClaude Opus 5.5 0537f4ddeb Detector-learner (D-116): the detectors learn from the labeler's labels alone, without events; critic, upgrader and control, the control guarded by the score on the other labeled stations (regression.py); NEBRASKA and NORDEND labels
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 13:46:36 +01:00
maximeandClaude Opus 5.5 9724ea5c3b Presentations: MICHIGAN and NEBRASKA say the redundancy is lost with two references and the correction no longer compensates "correctement"; MICHIGAN's two targets too close since the data start, jump on 5 Oct; sources compile in place in VS Code (brand/ link, Tinymist export on save)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 12:29:37 +01:00
maximeandClaude Opus 5.5 3211c9ce30 Presentations: their sources live next to each report (support/<dossier>/presentation.typ) and compile with .claude/skills/presentation/compiler.sh
The script copies the source and the folder's images into the AIMsight Typst factory, builds, puts the PDF back as presentation.pdf and reports overflowing slides. run.md: how the user edits and compiles a presentation. Skill /presentation, D-114 and CLAUDE.md updated.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 12:03:03 +01:00
maximeandClaude Opus 5.5 bc984a86d3 Events-learner on the labeler's labels: the session reads the lot's labels in labeling/auto/ instead of having the analyst read the lot; the detectors-critic judges the detectors against them, family by family (correspondence of labeling/familles.md); score.py --du --au scores by family and by instant, the session page shows labels and detectors on one row per family; analyst, tool-builder and event-builder leave the session (D-112, point 72)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 16:25:44 +01:00
maximeandClaude Opus 5.5 5adb711ce0 Label families: five families for labels, documented in labeling/familles.md and read by the labeler (Visibility, Obstruction, Thermal displacement, Displacement, Faulty target; turbulence merged into Visibility) (D-109, D-110); the labeler keeps only its labels, its work folder goes to out/ (D-106); third trial on WILDSTRUBEL 01-06.09, 30 labels; the labeling tool shows one-measurement labels
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 15:40:35 +01:00
maximeandClaude Opus 5.5 8266293ed3 Labeler agent: an analyst that only produces labels (etiqueteur, D-106), one category per label (D-107), anomalies only and one Thermal displacement category (D-108); second trial on JUNGFRAU 30.09-05.10, 15 labels; the labeling tool gets a Category box above the text, to add and to edit
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 14:44:08 +01:00
maximeandClaude Opus 5.5 fe025612cc Automatic labels, first trial: the analyst labels JUNGFRAU 20-25.10 alone with the labels map (7 labels in labeling/auto/, analysis beside them); the labeling tool shows manual or auto labels from a Labels menu (D-105)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 13:40:29 +01:00
maximeandClaude Opus 5.5 7ca701e502 Label review as the /review-labels skill, one label at a time with the expert, a qualitative text proposed for each, no review file (D-103); NIEDERHORN reviewed: 5 labels kept, 3 train passages removed
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 11:26:34 +01:00
maximeandClaude Opus 5.5 c72ef6fdf1 Labeling tool: the open label's bounds are edited in two UTC date fields and saved with its text; plan point 71, an integrator for the labels
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 10:40:24 +01:00
maximeandClaude Opus 5.5 3a07d45ffe Labels in two folders: manual/ (by hand, checked with the label-reviewer, the tool's) and auto/ (what the analyst will find alone, empty) (D-102)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 10:27:32 +01:00
maximeandClaude Opus 5.5 96f4bb58aa Labeling tool: Delete removes a label (red button, right of Save and Close), hover shows sensor, value and UTC time, text boxes 10 lines high
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 09:56:04 +01:00
maximeandClaude Opus 5.5 63c9f9e625 Labels: the validated events' diagnoses become labels in their stations' files, real sensor names, same format as the expert's (D-100)
30 labels written by an agent from E-001 to E-011, decoded with the anonymization registry and appended to labeling/<STATION>.jsonl, so the labeling tool shows them with the others; no source field. The tool accepts only data/ stations again.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 09:42:08 +01:00
maximeandClaude Opus 5.5 713bb80aa3 Label-reviewer: an agent checks the expert's labels against the data and asks before any change (D-101); labels as the knowledge base, validated events get theirs (D-100)
The labeling tool now accepts event folders (Add, Save), and a Save of a label's text drops its "revue" mark.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 09:35:28 +01:00
maximeandClaude Opus 5.5 d1fd7f6bdd Labels-learner: the analyst measures the expert's labels and asks until it understands, a documentaliste writes its conclusions into the docs (D-099, point 69)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 09:12:53 +01:00
maximeandClaude Opus 5.5 010798d992 Labeling tool: a click on a label shows it, its text is edited and saved (point 68)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 08:56:16 +01:00
maximeandClaude Opus 5.5 83f7f7be7f Labeling tool: system metrics in the plot menu, identifiers left out; point 69: how the analyst learns from labels, still open
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-30 11:23:31 +01:00
maximeandClaude Opus 5.5 fcd9191a95 Labeling tool: the expert labels ranges in plain text, one plot at a time (D-098, point 68)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-30 08:59:38 +01:00
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 e3150cf96c Reading tools: quality/ files are no longer read as displacement exports; run-detectors.sh runs the detectors page on every station
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 10:42:21 +01:00
maximeandClaude Opus 5.5 10e122067a Detectors page moves to detectors-view/ with its display helpers (D-093)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 10:37:37 +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 446fde3192 Events: read-event skill to consult the base (D-085), cases renamed events E-xxx (D-086)
- read-event: map and index first, then the card of close events only,
  then their data with the reading tools; never all cards at once.
  Diagnostic agent, critiquer-lot and builder point to it; the index
  header too. Signature length: about 250 characters, a guideline.
- "Cas" becomes "event": events/E-xxx/event.md, skills new-event,
  review-event, anonymize-event.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 07:25:29 +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
maxime be8897e38e clean-up 2026-10-28 17:02:17 +01:00
maxime b7f489b539 changes 2026-10-27 10:32:46 +01:00
maximeandClaude Opus 5.5 eca278279d comparaison.py: the end-of-session page of /boucle is now the detecteurs.py page, with the analyst's bars above the detectors'
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 10:30:18 +01:00
maximeandClaude Opus 5.5 ea4936e4b9 Commit /aiguiser sessions directly on master, like /boucle (D-077)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 09:47:11 +01:00
maximeandClaude Opus 5.5 2d89c21df1 Add --ameliorer to /aiguiser, like /boucle (D-076)
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>
2026-10-27 09:46:11 +01:00
maximeandClaude Opus 5.5 3d9e9d3a26 Add a page of the journal detectors alone on a station and a date range
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 08:28:19 +01:00
maximeandClaude Opus 5.5 432530a554 Boucle: one batch per session, the --du/--au range (D-072)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 18:05:01 +01:00
maximeandClaude Opus 5.5 925497e320 run.md: /boucle command copyable as is, --ameliorer without brackets
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 17:36:39 +01:00
maximeandClaude Opus 5.5 6ea82ca918 Loop CLARIDEN: process fixes
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 17:32:31 +01:00
maximeandClaude Opus 5.5 55519e53b3 Loop: --ameliorer runs an improver after the releveur (D-071)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 17:11:31 +01:00
maximeandClaude Opus 5.5 a614010292 Loop: commit sessions directly on master (D-070)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 17:05:28 +01:00
maximeandClaude Opus 5.5 9ff04eb28f run.md: end-of-session page and benchmark of the loop
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 16:48:37 +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 c68d47b10c Drop the case control from /aiguiser (D-064)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 14:14:38 +01:00
maximeandClaude Opus 5.5 0c8c90d1d5 Note what DIFF and IRON camera images are, keep --diff optional (point 28)
The station manual says the DIFF image is the contrast-enhanced view of the
reflectors that the displacement algorithm measures, not a difference between
two instants. The reading tools only look at IRON images, so run.md describes
--diff as an option instead of putting it in the pump command.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 12:27:20 +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 b1d2e2f531 Add the generic /aiguiser command to run.md
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 12:09:07 +01:00