Commit Graph
67 Commits
Author SHA1 Message Date
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 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 a0467e4c82 Measurement chain note for the analyst (draft, point 67)
docs/displacement/domaine/chaine-de-mesure.md: how a measurement is made and where each cause enters the chain (view, obstacle, target, lens, camera support, references, structure), the three thermal effects, the displacement reading rules; sources marked, Claude's hypotheses flagged. Draft, not yet read by the analyst. Plan: pipelines status at point 57, draft noted at point 67.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 17:16:39 +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 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 ba2e9da3ab Analyst: consults the event base whenever it wants (D-088)
The event base is the analyst's knowledge base, read before or during
its reading; a known event is a lead to check on the data, not a
conclusion. No measurement of the analyst's progress.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 08:02:25 +01:00
maximeandClaude Opus 5.5 c481323dc5 Event map: learns from each validated event, shown with the fiche (D-087)
- Catch-up: E-004, E-006, E-007, E-008, E-010, E-011 in the map; new
  section 5 "Faux amis"; rejected E-009 no longer cited.
- /review-event and /new-event: what the event teaches goes into the
  map at validation, shown to the expert with the fiche.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 07:44:26 +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
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 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 02f2bf5369 Support-agent: /support skill answers a client's question, GIF tool, first case LENZSPITZE (draft)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 11:12:28 +01:00
maximeandClaude Opus 5.5 425acbbad4 Detectors page: a click on an event bar acts like a click on a Status block
It zooms on the event, shows its details and its timelapse under the figure,
and keeps only its sensors on the curves (no second click). Bar dates are
given without the trailing Z, which Plotly does not parse.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 09:17:48 +01:00
maximeandClaude Opus 5.5 75e7963ca2 Detectors page: GIF without red border, date and time bottom right, up to 150 frames
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 08:54:46 +01:00
maximeandClaude Opus 5.5 55fbe2bf77 Detectors page: ⤓ GIF button exports the timelapse to the browser's downloads
The GIF is the timelapse as shown (focused or global, sensors circled and
labelled), 1000 px wide at most, red border during the event, time at the
bottom. In file:// the browser cannot read the images' pixels, so the
detectors, end-of-session and case-review pages now open through a local
server (open_served, 127.0.0.1:8765, started in the background, serving
out/ and data/ only).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 08:49:51 +01:00
maximeandClaude Opus 5.5 1ad8e74e8e detecteurs.py: the timelapse circles the event's sensors at their median position (targets yellow, references blue), when x, y are positions in the image
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 13:27:42 +01:00
maximeandClaude Opus 5.5 040b69e3f3 detecteurs.py: Details in two columns, the block's events on the left, its timelapse on the right, started by the click on the block
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 12:31:53 +01:00
maximeandClaude Opus 5.5 367bc5d563 detecteurs.py: a click on a Status block fills a Details section under the figure (its events, sensors, sentences) with a ▶ Images button, the block's timelapse with a margin before and after
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 12:23:18 +01:00
maximeandClaude Opus 5.5 03b5d3fd59 detecteurs.py: a click on a Status block zooms the page on its range
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 12:14:20 +01:00
maximeandClaude Opus 5.5 d7fb8e41d0 detecteurs.py: the Status row right under the curves, the categories below it in a fold (click on ▾ Status), open by default, without their title
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 12:10:43 +01:00
maximeandClaude Opus 5.5 2659c465aa detecteurs.py: no y rescaling on zoom; the timelapse shows the whole image when x, y are not positions in it (LENZSPITZE)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 12:02:05 +01:00
maximeandClaude Opus 5.5 6bfcf22e14 detecteurs.py: the Status row says what is happening, light blue nothing, dark blue a block named by the event that covers most of it (plan point 50, user's revision)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 11:52:17 +01:00
maximeandClaude Opus 5.5 0c778b4b4f detecteurs.py: a Status row compiles the detectors (can the data be trusted?), the strongest level over all sensors (plan point 50)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 10:56:52 +01:00
maximeandClaude Opus 5.5 876572b0fc Give every journal category a detector: slow drift, faulty target, large shift, camera thermal (D-074)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 09:28:29 +01:00
maximeandClaude Opus 5.5 ae5bfdc688 Map field events to the morning journal categories (D-074)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 09:17:00 +01:00
maximeandClaude Opus 5.5 b30b781b3b Lecture : la pose de la caméra se lit avant les capteurs (D-073)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 18:30:03 +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 5ff342a7f2 Keep each case's labeling record in its own folder
- etiquetage.md sits next to etiquettes.json in every case: C-001..C-005
  moved from vues-deplacements/benchmark/etiquetage/, C-006..C-008 written
  from lot 01 (source and table of moments, coded names)
- anonymiser.py --etiquettes now writes etiquetage.md too (with its test);
  builder, /nouveau-cas, anonymiser-cas, agent spec and D-069 follow
- vues-deplacements/benchmark/ keeps only the history

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 16:54:37 +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 6b3d058a67 Pompage : métriques système dans metrics/, images absentes de S3 sautées
pomper.py écrit les métriques dans data/<SERIE>/metrics/ ; load_stations les y lit
aussi. Les images dont measurement_uuid est vide (jamais arrivées sur S3) sont
écartées de la requête : plus d'erreur de l'appli, la tranche prend l'image suivante.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 16:47:47 +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 0372a20da9 Plan the NORDEND September sessions: /aiguiser before /boucle (points 31, 42)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 12:08:58 +01:00
maximeandClaude Opus 5.5 3ec6261b5a Pump the camera movements and add run.md with the generic pump command (point 43)
Camera pan, tilt, scale, rotation and sigma0, one row per camera measurement,
read like the platform viewer (cam_movements aggregate), one CSV per day in
camera/. Tried on NORDEND 30/07: 70 poses out of 95 instants, sigma0 on the
same 7 as the advanced export. run.md holds the command to copy into the
app's dev container.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 11:27:06 +01:00
maximeandClaude Opus 5.5 2d2d50a8b3 Run the first pump on NORDEND: identical to the received exports (point 27)
Two days (29-30/07) pumped by the user in the app's dev container: system
metrics, displacements and camera images match the received exports, and
the journal gives the same events. The container mounts ~ on /workspaces,
so the script now writes straight into Support-Agent's data/ (no copies).
Add --delai for days that exceed the 60 s query timeout, and report the
root database error instead of pandas' wrapper.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 11:13:57 +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 a81cc4c380 Pump system metrics and resume day by day (point 43)
pomper.py now also pumps every system metric of a station, in the format of
the System page download (hourly mean, text lists, empty hour), one CSV per
metric and per day; displacements are written one file per day, today is
never pumped, and a rerun only fetches missing days. Fix image resume: an
image already on disk now counts for its time slot. load_stations merges
several files of the same metric instead of failing on a duplicate.

Not run against the database: first run by the user, with point 27.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-24 19:14:59 +02:00
maximeandClaude Opus 5.5 6ed1264ec8 Add point 43 to the living plan: a complete, incremental local database
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-24 16:35:30 +02:00
maximeandClaude Opus 5.5 e5c03b1d4a Record the reading sharpening decision (D-059)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-24 16:33:19 +02:00
maximeandClaude Opus 5.5 54d1c6a142 Document the automatic loop as validated, run lot by lot by the user (D-057)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-24 15:26:36 +02:00
maximeandClaude Opus 5.5 6be683819e Record the automatic loop decision (D-057)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-24 15:14:14 +02:00