Commit Graph
51 Commits
Author SHA1 Message Date
maximeandClaude Opus 5.5 1057aadd2b Sharpen WILDSTRUBEL lot 01: modification 2
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 10:19:05 +01:00
maximeandClaude Opus 5.5 a55280056d Sharpen WILDSTRUBEL lot 01: modification 1
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 10:02:44 +01:00
maximeandClaude Opus 5.5 1424c7f56b Loop WILDSTRUBEL lot 01: cas C-012
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 09:52:40 +01:00
maximeandClaude Opus 5.5 d6e011bff4 Sharpen CLARIDEN lot 01: modification 2
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 19:07:50 +01:00
maximeandClaude Opus 5.5 3e8b16aff4 Sharpen CLARIDEN lot 01: modification 1
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 18:50:25 +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 34ce43fbdb Loop FLORIDA lot 01: cas C-011
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 18:22:37 +01:00
maximeandClaude Opus 5.5 037accd26e Loop CLARIDEN lot 01: cas C-009, C-010
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 18:01:18 +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 97a632cea2 Loop NORDEND lot 01: cas C-006, C-007, C-008
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 15:50:06 +01:00
maximeandClaude Opus 5.5 09cd4638a5 Sharpen NORDEND lot 01: modification 2
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 14:55:46 +01:00
maximeandClaude Opus 5.5 174088da02 Sharpen NORDEND lot 01: modification 1
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 14:47:00 +01:00
maximeandClaude Sonnet 5.5 839fe663cb Shorten inventaire.py: first and last file past 5 per type, --fichiers for the full list
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-26 14:30:32 +01:00
maximeandClaude Opus 5.5 48a64fc5c4 Sharpen NORDEND lot 01: modification 3
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 13:15:46 +01:00
maximeandClaude Opus 5.5 53eaf45e9d Sharpen NORDEND lot 01: modification 2
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 13:09:24 +01:00
maximeandClaude Opus 5.5 4424ea1cbe Sharpen NORDEND lot 01: modification 1
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-26 13:02:03 +01:00
maximeandClaude Opus 5.5 a0550869aa Move the reading method into a shared lire-les-donnees skill
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-24 16:16:03 +02:00
maximeandClaude Opus 5.5 4d14f5ea5d Open the diagnostic agent to project knowledge and the journal detectors (D-058)
The agent now serves one precise case, reads the project's displacement
knowledge and the whole case base, starts from the detectors' events
without judging them, and no longer has conclusions imposed on it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-24 15:46:30 +02:00
maximeandClaude Opus 5.5 955566d86f Clean the journal curves, unfold its timeline and sort it in batches (D-056)
Plan points 18 to 26, 30, 39, 40 and the point 37 housekeeping:
- greyed zones per target, vertical scale without the zones to ignore, Fit all,
  mm by default with a px switch, Support view, Expand (one row per category);
- cleaned curves: cut in the zones to ignore, raw data kept there in thin grey;
- target02 to target05 count as targets; smoothing questions answered;
- categories.py sorts in slices with 3 days of history by default;
- the pumping script points to ~/monitoring-dashboard and skips diff images;
- CLAUDE.md back under 200 lines; a case page is named after its case.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-24 14:31:42 +02:00
maximeandClaude Opus 5.5 0aed4af56b Add the PR17 diagnostic report and the expert's path on the NORDEND October case
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16 13:23:46 +02:00
maximeandClaude Opus 5.5 0dae00d6c4 Add case C-005 to the diagnostic case base
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 18:01:28 +02:00
maximeandClaude Opus 5.5 c86faa2ac6 Fix repeated isolated points in the diagnostic instructions
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 17:56:43 +02:00
maximeandClaude Opus 5.5 f8f236aacc Remove misplaced copies of the CLARIDEN export
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 17:36:19 +02:00
maximeandClaude Opus 5.5 b6ec01c1e5 Strip sensor names in the diagnostic tools
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 17:36:19 +02:00
maxime c0dc68a5c3 cases 2026-10-15 17:17:53 +02:00
maximeandClaude Opus 5.5 e1431b76d3 Review case C-004 with the user
Card checked against the case data and images:
- signature: corrected ranges (corr_y plateau up to +1.2, 18 to 126
  MAD; error_value of the local group 3 to 7 times the previous day),
  the local group moves far more than the other sensors, not alone;
- new criterion 4: at night the references move between themselves
  (not R1), sigma0 rises tenfold and corr_x of most targets drops
  without their raw position moving, a plateau that lasts to the end
  of the measurements; images become criterion 5;
- event now starts on 18.09 at 23:20 (header, summary, symptom, index);
- diagnosis: night then morning in the mechanism; C24 sits in the
  local group and its error_value rises from 05:50;
- figure 1 redone with a corr_x panel, captions corrected.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 17:10:31 +02:00
maximeandClaude Opus 5.5 bcbf61b20e Record the C-004 match test
Second run on the same question, case in the index: C-004, complete
match (criteria 1 to 4 verified); monitored-object motion with a
camera/reference compensation event, consistent with; consequence:
real movement; action: intervention. The card needed no change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 16:07:21 +02:00
maximeandClaude Opus 5.5 ea4954807c Add case C-004 to the diagnostic case base
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 16:02:19 +02:00
maximeandClaude Opus 5.5 4d19abba2b Add case C-003 to the diagnostic case base
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 15:44:30 +02:00
maximeandClaude Opus 5.5 27cebbb4f0 Fix day/night cycle case lookup and cause meanings in the diagnostic instructions
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 15:34:03 +02:00
maximeandClaude Opus 5.5 7a86d25eb1 Review case C-002 with the user
Card checked section by section against the case data and images:
- header: "end of measurements" (images run to 23:00);
- summary, symptom: duration, most targets, uneven jumps;
- signature: corrected ratios and ranges, remaining references at 0,
  jumps only at some switches (setting R2 aside alone moves nothing),
  web visible by day too; C1 is a local reference, outside the
  compensation;
- diagnosis: mechanism with one or two references set aside, inflated
  MAD for several targets, "masked movement" line removed;
- proofs: three captions corrected; index line aligned.

Domain note: pattern_type `ref` is a local reference (station manual).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 14:28:45 +02:00
maximeandClaude Opus 5.5 4424037665 Add case C-002 to the diagnostic case base
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 11:42:49 +02:00
maximeandClaude Opus 5.5 2ae91930de Fix the diagnostic instructions: show the full camera image when the cause is visible on it
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 11:42:20 +02:00
maximeandClaude Opus 5.5 46bc89b8ad Review case C-001: data in the case, shorter human-first case file
Copy the station's displacement export and images into the case folder,
with coded sensor names; the station takes the case number instead of
S01, and graphique.py / vignettes.py drop --alias (D-050).

Rewrite C-001 as the expert's diagnosis of this event only: summary,
symptom, verdict, signature with commands, diagnosis, evidence. Drop
exclusions, expected output, unknowns and test history; matching no
longer uses exclusions (D-051). The corr_x jumps at the reference
switches are judged negligible.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 10:52:58 +02:00
maximeandClaude Opus 5.5 43a1438550 Record the C-001 match test with coded names
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 17:49:05 +02:00
maximeandClaude Opus 5.5 a684349501 Code station and sensor names in the diagnostic case base (D-049)
Add the anonymiser-cas skill: a growing registry gives stable codes
(S01, R1, C1), a stdlib script rewrites a case and renames its files,
and graphique.py / vignettes.py take --alias to plot with codes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 17:45:40 +02:00
maximeandClaude Opus 5.5 3478d77f1d Record the C-001 match test
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 17:39:16 +02:00
maximeandClaude Opus 5.5 5a99acec28 Add case C-001 to the diagnostic case base
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 17:35:42 +02:00
maximeandClaude Opus 5.5 2aa15a5df0 Add the /nouveau-cas skill to add expert-validated cases to the diagnostic case base
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 17:00:13 +02:00
maximeandClaude Opus 5.5 3662851f06 Tighten case matching after review: exclusions, asymmetry, two-case rule
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 16:45:45 +02:00
maximeandClaude Opus 5.5 d4514008fc Run the diagnostic agent blind with an empty case base and record the results
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 16:38:41 +02:00
maximeandClaude Opus 5.5 ee61d62d79 Document the diagnostic agent case base: spec, D-048, README and CLAUDE.md
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 16:34:45 +02:00
maximeandClaude Opus 5.5 f056da2875 Add the empty case base and the known-cases step to the diagnostic agent (D-048)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 16:34:06 +02:00
maximeandClaude Opus 5.5 2a39335fb5 Make diagnostic reports short, evidence-backed and anomaly-only (D-047)
Reports become a folder with rapport.md and its figures: a verdict, one
short section per anomaly (series plot with shaded window, full-resolution
image crops around the sensors), constant behaviour in one line each.
graphique.py gains --zone and --sortie; new vignettes.py crops images at
the sensors' raw x/y. Old reports removed; the blind rescan of PS des
Coudres finds the single anomaly flagged by the specialist (REF_G/REF_D).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 16:00:40 +02:00
maximeandClaude Opus 5.5 4b937da95b Fix review findings in the diagnostic agent tools and instructions
Inclusive --fin at the displayed minute, UTC for naive time_utc, neutral examples,
5-significant-digit values, 'vide' vs '-' cells, no empty or gap-bridging plots,
timestamped report names, and an up-to-date CLAUDE.md next step.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 15:35:44 +02:00
maximeandClaude Opus 5.5 fcc01d2d68 Run the diagnostic agent blind on PS des Coudres and record the results
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 15:25:09 +02:00
maximeandClaude Opus 5.5 94670c2c92 Add the diagnostic subagent: entry point, instructions and README (D-046)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 15:14:35 +02:00
maximeandClaude Opus 5.5 77fda7103d Add the diagnostic agent's plot tool and matplotlib (D-046)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 15:14:11 +02:00
maximeandClaude Opus 5.5 f33f09dbf6 Add the diagnostic agent's numeric summary tool (D-046)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 15:13:20 +02:00