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>
- 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>
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>
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>
- /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>
- 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>
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>
- 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>
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>