The calendar already said which individual days went over budget, but not
whether the week as a whole did. A run of small overages reads as four
harmless yellow squares; averaged, it is the thing that actually moves the
needle.
Three rules are load-bearing, and are documented in CLAUDE.md because getting
any of them wrong silently changes what "under budget" means:
- The denominator is logged days, not elapsed days. An unlogged day is not a
zero-kcal day, and averaging gaps in as zeros would make a badly-tracked
week look like the best week of the year.
- The yardstick is the mean of the per-day budgets over those same days,
resolved through BudgetSchedule -- never today's budget, which would
retroactively reclassify past weeks on every budget edit.
- Today is excluded. A half-logged today drags the mean far enough to flip
the band, so every period ends at yesterday.
Band boundaries reuse the calendar's own OVER_BUDGET_YELLOW_CEILING by
import rather than by copy, so a period and its days can never disagree
about what "over" means; that constant loses its underscore to say so.
The MCP get_averages tool returns the average and the band but drops the
average budget, keeping the module's existing invariant that the budget
number never leaves this machine. The CLI, the gate and the phone all show
both, since it is hidden from the network, not from the user.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DjJqpcEsaV5WRhPXyxCThd
Expose diet_guard's read surface and one gated write action as typed MCP
tools (diet_guard._mcp) so Claude Code and its subagents can query today's
intake and -- with explicit confirmation -- log a meal without shelling out
to the interactive gate CLI.
- _mcp.py: FastMCP stdio server. Read tools get_status, list_today,
get_slots expose today's CONSUMED kcal/macros and the qualitative
consumption band only -- never the raw daily budget, remaining number,
body weight, or protein target (those would back out the deliberately
hidden budget). Gated write log_meal previews unless confirm=True and
degrades gracefully on write failure. Nutrition is grouped into a Macros
model (kcal + optional protein/carbs/fat) to keep the tool under the
arg-count limits with no lint suppression, mirroring the CLI's grouping.
Logs to stderr; no secret (HMAC key / sync token) is ever returned.
- .mcp.json + scripts/setup_mcp.sh: registration via a dedicated
~/.venvs/diet-guard-mcp interpreter; mcp is an optional-dep, kept out of
the systemd/CLI system-python path.
- 100% coverage of the new module; verified end-to-end over stdio.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LQGQj8Ne6TriBExv91nG8v
Rewrites python_pkg.diet_guard imports to diet_guard, vendors the
shared as_float coercion helper, drops the monorepo PYTHONPATH from
install.sh and the systemd unit (package is now pip-installed), and
scaffolds standalone lint/test config matching testsAndMisc's real
enforced bar (pylint --fail-under=10 with tests excluded and the
use-implicit-booleaness/consider-using-with disables, mypy's actual
disabled-error-code set, ruff ALL, bandit, 100% branch coverage).
