Same features as the local page; agents, tools, prompts and knowledge unchanged.
- API/web/: React (Vite) with Mantine components: collapsible sidebar, mobile drawer,
cards, notifications, dark mode
- API/support/serveur.py: FastAPI serves the built page and /api; agent events pushed
by server-sent events (/api/flux) instead of polling
- data, cases folder and port set by AIMSIGHT_DATA, AIMSIGHT_CASES, AIMSIGHT_PORT
- check.py: server check (host guard, analyse, stream, PDF) with a fake client
- old page.html removed
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Self-contained sub-project API/: a local support page where Marc pastes a
client's mail; a support agent and an analyst agent stay alive for the session
and produce a slide PDF that answers the client's question. Tools, detectors,
knowledge and Typst brand are copied (API/PROVENANCE.md). First real case:
Crissier (LENZSPITZE), workflow validated.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Every auto label carries an id (<STATION>-<n>, labeling/ids.py), kept on edit, given to
new labels by labeling.py and by the reviews; controle.py requires it, unique. The
cross-review matches labels by id, and an applied review is locked (applique.md).
- The label map starts with a summary (labels-map/sommaire.py): readers take the summary and
sections 2-4 in full, then only the cards of the phenomena they meet.
- Tool-builder session on the reviewers' difficulties: jours.py --lissage/--fraction,
ensemble.py --suivre and rejected measures left out of --rigide, --residus non, zero noise
after a lost reference, new agent-tools/stations.py (several stations on one timeline),
long outputs convention in lire-les-donnees.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- 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>
- Every station's auto labels reviewed by an analyst (/review-auto-labels), then a
cross-review per family across all stations (new skill /cross-review-labels),
a finishing pass, and descriptions rewritten in words (no numeric values).
- The three never-labeled ranges (WILDSTRUBEL 07/09-01/10, NORDEND 16/08-01/10)
labeled and reviewed: 991 auto labels on 11 stations, labeling/controle.py at 0 errors.
- Labeling knowledge gathered in labeling/: regles-d-etiquetage.md (new), familles.md
(settled boundaries), connaissances/ (notes moved from docs/, links updated),
the label map rebuilt from reviewed labels, events and cases; events tied to their
stations (PS_DES_COUDRES is JUNGFRAU). The labeler and reviewers read only labeling/.
- labels-map reads auto labels and events; decision D-130; living plan points 73-75.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The analyst reviews labeling/auto/ labels on a range chosen by the user (bounds, one event, family, description, missed ones) and proposes corrected labels; the expert answers its questions, then the range is replaced. First run on BREITHORN October: 10 corrected, 25 and 26 merged, one missed night added; the expert confirms the camera's cold-night deviations are thermal (housing temperature, not air). Labels the expert settled carry "revue", read by /labels-map.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
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>
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>
Reports: all October labels (data from 03.10), the expert's diagnosis kept; new findings before 20.10 (night without measurements 15-16.10 on all three; BREITHORN references hidden on 04, 07, 10.10; MICHIGAN curves agitated 17-18.10; NEBRASKA camera stepping back 13-17.10); figures redone for the month.
Presentations (presentation.pdf in each report folder), built with the AIMsight Typst factory ~/docfactory-presentation, in the structure set by the user: "Point de situation" title with station and period, a numbered chronological summary, one self-sufficient slide per event with its diagnosis and picture (BREITHORN: the vehicle in front of COLI24), a conclusion (why it is less reliable, what to do), closing slide. A diagnosis, never an instruction ("to ignore"); the camera's movement is real, its cause (fixing, wall or other) not known.
Skill .claude/skills/presentation/: structure, the user's rules, what failed, model deck (BREITHORN) and image-de-la-cause.py (brightened crops around a target).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
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>
- 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>
A form at the top of the Status page: station dropdown (folders of data/), start and end dates
(end excluded, as --au), and an Analyse button that builds the page for that selection and opens it.
The code is in detectors-view/data-loader/chargeur.py: the form, and its local server (port 8766)
that serves out/ and data/ like the common one, plus /analyse, which runs status.py each time.
python3 detectors-view/status.py without arguments, or detectors-view/status.sh, opens the form
alone; with a station folder it builds the page as before, now opened through the loader server.
common.page.open_served takes another port and server script.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A click on a status label shows, below the figure, its details (name, times, sensors, sentence,
then References and Targets per sensor) and, on the right, the timelapse of its camera images,
as in detecteurs.py. Clicks in the details keep the selection; a click elsewhere clears them.
detecteurs.py shares its pieces instead of status.py copying them: the timelapse JavaScript
(TIMELAPSE_JS, the image slider stays in IMAGES_JS), the player HTML and CSS, camera() for the
images and sensor positions, and groupes() with French or English texts. The player's few
messages are now in English (before / DURING / after, no image, GIF export error).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The click keeps only the status's sensors and highlights its bands; the time range, including a
zoom made by hand, stays as it is.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Merging the two thermal phases into Thermal movements only holds for phases on the same targets;
the user has not decided yet. hierarchie-des-status.md keeps the merge; status.py, CLAUDE.md and
D-095 say it is suspended. Occultation and the target filter are unchanged.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
detectors-view/hierarchie-des-status.md, validated by the user: No visibility hides Reduced
visibility, Faulty target hides Target hidden, No data hides everything, No visibility hides Target
hidden; the two thermal phases form one status, Thermal movements. A hidden status is cut, not
removed, and only when the stronger one covers all its sensors. status.py transcribes it.
Hiding or isolating targets in the sensor legend keeps only the statuses that touch a visible
target, or all sensors. Discarded labels become transparent, without text, hover or click:
restyling x or base of the label row made Plotly retype its axis as linear.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
One label per detector event at its time, in its category colour, overlapping events on lower rows.
A click zooms on the event (half its duration on each side, 1 h to 6 h), keeps only its sensors and
highlights its band; a second click shows everything again. The range is set on every x axis: in
the same relayout as the band opacities, the axes matching the bottom one did not follow.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
detectors-view/status.py, a pseudo-final version of the site's Explore page: the curves with the
legend on the right, each detector event as a transparent band over them (one colour per category,
legend above), without Shift to check and Slow drift as in the Status line.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- /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>
- 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>
- 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>
- 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>