src/energy/final.py is daily.py unchanged; the comparison script, the
day focus and the client mockup now import energy.final. References in
the README, the analysis rule, the nouvelle-analyse skill, the two
delivered analysis sheets and the guide follow. Output files keep
their names (out/<STATION>_daily.html and .json).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Record decision D-027: a server-side LLM agent layer next to the
unchanged deterministic rules, aimed at unknown anomalies and rule
edge cases. The agent annotates and never rewrites the day color.
Home-made harness (Messages API + Tool Runner), staged start with a
manual Energy pilot on VERMONT history. D-003 is partly replaced.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
D-025: the support side gets the site's home page (one tile per
station: name, last voltage, curve) with a Status section on top. It
holds one notification per station whose last day of the window is
Orange or Red (src/day_color.py), the most serious first; Green
notifies nothing. Each notification, like the station tile, links to
the station's client view (out/maquette_user_energy.html).
maquettes/support/home.py writes out/maquette_support_home.html with
the standard library only (inline SVG, no plotly). Only VERMONT has
data; the other tiles keep the site's names and stay empty.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
CLAUDE.md records D-022/D-023 in the project state and the next mockup
steps (client Energy step by step, then the support side). D-022 lists
the open points of the Energy mockup: the guide is still in French,
the battery scale has no IR compensation, the energy save button is
for the site team to build, and a day in progress is not yet flagged
as provisional on the client side.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
D-024: to explain a day's color, show only that day and the day before,
the only days analyses 03 and 04 read for it. day_color.focus() selects
the data (standard library); src/focus_jour.py prints a traceable fact
summary and writes a 48 h BusVoltage figure (out/<STATION>_focus_<date>
.html and .json). Analysis 03 gains the night_end_h fact; the other
facts are unchanged. The client Energy mockup does not use this figure:
the user prefers numeric facts there.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
D-022: page mockups are HTML built from real data, in maquettes/user/
(client) and maquettes/support/; Figma only on request.
maquettes/user/energy.py renders the System Summary page with a
Diagnostic section: an Energy box with the day's color, a one-line
headline, a battery scale (zones from the collector's LiFePO4 OCV
table, no percentage shown), the trend against the day before, an
"Activate energy save mode" button on orange and red days (mockup
only, sends nothing), and two collapsibles: the full history (D-021
figure) and the guide (part 1 of the manual, rendered from Markdown).
D-023: everything meant for the monitoring site is in English,
including the titles, legends, axes and hovers of the 03/04 panels.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
D-020: the delivered energy diagnostic keeps analyses 03 and 04 only,
combined by the state x trend matrix of cas-d-usage-03-04.drawio into
one color per day (green / orange / red, grey when unknown), coded in
src/day_color.py (standard library). docs/guide/diagnostic-energetique.md
explains it: part 1 for the client, part 2 for support.
D-021: energy_plot.daily_figure builds the figure for the monitoring
site (panel 03 above panel 04, shared time axis), written by
analyse_01.py as out/<STATION>_daily.html and .json. battery_state no
longer imports energy_check, so analyses 03 and 04 ship on their own.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
src/analyse_04.py launches the common page; sheet 04 moves to
"prototype en place" with VERMONT results; CLAUDE.md, the analyses
rule, README and sheet 01 list the fourth panel and extend the
"no verdict" contract exception to analysis 04.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The night end and rise were anchored on the first daily maximum,
which can be the 00:00 tail of the previous evening: 2026-05-05 was
read NO_CHARGE despite a +0.079 V rise, 2026-09-30 showed a wrong
night end, and 2026-09-26 stayed unknown from 04:00 to 11:00 when
evaluated mid-day. The rise now starts from an earlier minimum and
the knee is tested on the daily minimum (min_v). VERMONT: 139 / 31 /
14 / 0.
Docs: sheet 02 page order, battery_state.py in the CLAUDE.md map,
phase C exception to "anomaly = None means UNKNOWN".
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
src/analyse_03.py launches the common page; sheet 03 moves to
"prototype en place" with VERMONT results; CLAUDE.md, README and
sheet 01 list the third panel.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
One state per UTC day from BusVoltage: FULL_CHARGE, BELOW_PLATEAU,
NO_CHARGE, PARTIAL_CHARGE or unknown, with hardware thresholds
(14.0 V end of charge, 12.8 V LiFePO4 knee). No verdict yet.
Includes the implementation plan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Background bands for discharge (12.0-13.2 V), charging (13.1-13.8 V)
and full charge (14.0-14.4 V), from the battery voltage report.
Display only, no effect on the analyses.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- 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>
- Analysis 02 MOVING_AVERAGE_7_DAYS_MIDNIGHT_UTC_DROP: same rule as
analysis 01 on the 00:00 UTC BusVoltage sample only, one point per
day. Shared computation in energy_check._ma_drop(); analysis 01
results unchanged on VERMONT.
- Common page: one panel per analysis (02 under 01), then the time
series (D-016); src/analyse_02.py launches that page.
- Analysis panel reduced to two curves on one volt axis: 7-day mean
and threshold; gap and reference moved to hover (D-015).
- Date tick labels under every subplot.
- Rule IDs spelled out: MA7D_DROP -> MOVING_AVERAGE_7_DAYS_DROP,
MA7D_MIDNIGHT_DROP -> MOVING_AVERAGE_7_DAYS_MIDNIGHT_UTC_DROP (D-017).
- Docs: analysis sheet 02, sheet 01, CLAUDE.md, README, decisions
D-015..D-017, analysis rule and nouvelle-analyse skill.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- 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>
Four TDD tasks: CSV loading, causal analysis, periods/summary/CLI,
plotly report. Code validated against real data in a prototype.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
First analysis of the station energy-health use case: 7-day moving
average of BusVoltage compared to its own 30-day maximum, evaluated
causally at each hourly point, with a plotly visualisation.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>