Commit Graph
22 Commits
Author SHA1 Message Date
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 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 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 4bdbab2976 Pump: say why a day yields no image (none in base, never reached S3, not returned by S3); LENZSPITZE has no DIFF images
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 14:23:54 +01:00
maximeandClaude Opus 5.5 052e72c682 Support: rejected measures are still delivered to the client, not removed by the camera
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 11:42:37 +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 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 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 57dab8e47a Rework the Diagnosis tab: curves in mm, AI request, link with View; drop the grid (D-054)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16 17:29:28 +02:00
maximeandClaude Opus 5.5 36a42a342a Add the View tab: image browser, ±24 h comparison, target close-up, rejection band (D-053)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16 16:48:38 +02:00
maximeandClaude Opus 5.5 6890ae28b6 Document the Barcelona incident (C-004) and the platform image times
- docs/displacement/domaine/incident-de-barcelone.md: the AIMsight
  regression case is data/CLARIDEN/ (case C-004); what the data show,
  the documentation's reading (reference/compensation instability)
  against the expert's (real movement of the structure, confirmed by
  other instruments, amplitude likely overestimated), open questions.
- nouveau-cas: platform zips date images in UTC, exports cover local
  days; keep every image of the range, even at 10 min.
- colonnes-des-deplacements: native cadence is 15 or 10 min.
- CLAUDE.md: four cases in the base, displacement data of NORDEND,
  WILDSTRUBEL and CLARIDEN.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 16:07:21 +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 1e80ee0acb Add PS des Coudres optical exports as the displacement working set (D-045)
Exports go to data/<STATION>/displacement/, out of reach of the system
metrics loader. The 15-min "advanced" export (UTC) is the analysis source;
the hourly export is kept for the corr_x/corr_y conversion factors.
Document both formats and record the open questions in the framing doc.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 12:15:34 +02:00
maximeandClaude Opus 5.5 276c34ea38 Add the temperature domain on the GPU manufacturer limit
DAILY_GPU_TEMPERATURE_LIMIT: red when an hourly GPU mean reached 97.5 °C
(T.gpu, Jetson Nano Thermal Design Guide) in the last 24 hours, green
otherwise, gray without measurement. Working sets WEISSHORN and NORDEND;
all measured days are green. D-040 replaces D-036; the exploration note
moves to docs/temperature/domaine/point-de-depart.md.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 16:07:36 +02:00
maximeandClaude Opus 5.5 1a18ddd059 Document the temperature exploration and defer the domain
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 12:42:54 +02:00
maximeandClaude Opus 5.5 67fbc39e11 Document the paused cellular domain and the collector versions
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 11:52:04 +02:00
maximeandClaude Opus 5.5 75619e8f1c Remove the raw expert notes and the archived stations
Point the docs to the summaries that remain and record D-033.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 11:51:03 +02:00
maximeandClaude Opus 5.5 28cbec408e Note that WEISSHORN exports the collector battery fields
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 10:48:34 +02:00
maximeandClaude Opus 5.5 8a32f4d418 Organize the project by domain and name analyses by their rule
Energy code moves to src/energy/ and its docs to docs/energy/; shared code
(CSV loading, venv switch, browser, zoom script) goes to src/common/, and the
AIMsight originals to docs/aimsight/. Analyses are no longer numbered: two
Energy scripts remain, daily.py (delivered state and trend) and
all_analyses.py (comparison of the four). Calculations and pages unchanged (D-026).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 17:12:37 +02:00
maximeandClaude Opus 5.5 129d4ff59b Plot daily analysis points at noon of their day
Analyses 03 and 04 now place each day's point and bar at 12:00 UTC
instead of 23:00, where they read as the next day. Computations are
unchanged. D-019 records the choice and the rejected one-day shift of
the night-end voltage (tried in 03, then in 04 only); sheet 04 gains
limit 6 (night end of J reflects J-1), and the data-pitfalls note
explains why.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 12:11:45 +02:00
maximeandClaude Opus 5.5 e77d3e4b82 Spec analysis 03 DAILY_BATTERY_STATE, battery voltage report
- docs/analyses/analyse_03.md: design of the daily battery state
  analysis (phase C, state only): FULL_CHARGE / BELOW_PLATEAU /
  NO_CHARGE / PARTIAL_CHARGE per UTC day, hardware thresholds
  (14.0 V end of charge, 12.8 V LiFePO4 knee), status "en conception".
- D-018: next analyses give a day-by-day state with hardware
  thresholds, usable from installation day; phase C then phase B.
- docs/domaine: voltage report per battery state (charging, full,
  discharging) with sources; Power dispersion on VERMONT.
- CLAUDE.md: analyses table, state and next step, domain map.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 10:43:36 +02:00
maximeandClaude Opus 5.5 8992bda17e Document the project: decisions log, analysis sheet, domain notes
- CLAUDE.md becomes a short map: status and next step, analyses index,
  documentation map, working rules.
- docs/decisions.md: ADR-style project decision log (D-001..D-014).
- docs/analyses/: living sheet per analysis (analyse_01) and template.
- docs/domaine/: domain knowledge, one note per question.
- .claude/rules/analyses.md: path-scoped rule loaded on src/ and
  docs/analyses/; .claude/skills/nouvelle-analyse: new-analysis workflow.
- README.md: human entry point.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 23:29:42 +02:00