6.8 KiB
Agent Instructions
This project uses bd (beads) for issue tracking. Run bd prime for full workflow context.
Build & Test
cargo build --release # Build binary
cargo test # Run unit tests
./target/release/nutrition-mcp # Run server (needs env vars)
Smoke Test
# Start server
NUTRITION_MCP_BIND=127.0.0.1:9432 NUTRITION_MCP_API_KEY=test \
NUTRITION_MCP_DB_PATH=/tmp/test.db ./target/release/nutrition-mcp &
# Health check
curl http://127.0.0.1:9432/health
# MCP initialize
curl -X POST http://127.0.0.1:9432/mcp \
-H "Authorization: Bearer test" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"test","version":"0.1"}},"id":1}'
Architecture Overview
MCP server exposing 13 tools for personal nutrition tracking. Streamable HTTP transport with Bearer token auth.
Module Map
src/
├── main.rs — Entry point: axum server, auth middleware, /health endpoint
├── config.rs — Config struct from env vars (bind, api_key, db_path, user_agent)
├── db.rs — SQLite schema, migrations, DbPool type, TRACKED_NUTRIENTS const, DEFAULT_GOALS_JSON
├── api.rs — OffClient: Search-a-licious + v3 barcode + SQLite cache (FTS5)
└── tools.rs — NutritionServer: 13 MCP tools via #[tool_router] + ServerHandler impl
SQLite Schema
- products — OFF cache: code (PK), product_name, brands, nutriments (JSON), serving_quantity, serving_size, image_url
- products_fts — FTS5 virtual table on product_name (synced via triggers)
- entries — Food log: id, date, meal, product_code, food_name, grams, servings, nutriments (JSON, scaled to portion)
- daily_goal — Single row (id=1), goals JSON with 14 nutrient targets
- weight_log — id, date, weight_kg
Nutrient Storage
All nutrients stored as JSON blob in nutriments TEXT column (verbatim from OFF API). Daily summaries use json_extract() or Rust-side parsing to aggregate the 14 tracked nutrients.
Portion Scaling
Nutrients are stored per-100g in OFF data. When logging, scale_nutriments() multiplies each value by grams / 100.0. For servings, grams = servings * serving_quantity.
Meal Auto-Detection
- breakfast: before 11:00
- lunch: 11:00–15:00
- dinner: 15:00–21:00
- snack: after 21:00
Conventions & Patterns
- JSON nutriments — Never hardcode nutrient columns. Store OFF nutriments verbatim as JSON, query at runtime.
- "no data" vs 0 — Micronutrients (potassium, calcium, magnesium) are sparse in OFF. Summary shows
"no data"when no entries have the nutrient, not 0. - Env vars only — No config files. All settings via environment variables.
- API-first — Always check SQLite cache first, fall back to OFF API, cache results.
- User-Agent — Always send custom User-Agent to OFF API (good citizenship).
Tracked Nutrients (14)
energy_kcal → energy-kcal_100g
protein → proteins_100g
carbohydrates → carbohydrates_100g
fat → fat_100g
fiber → fiber_100g
sugars → sugars_100g
saturated_fat → saturated-fat_100g
salt → salt_100g
fructose → fructose_100g (gout)
alcohol → alcohol_100g (gout)
potassium → potassium_100g (hypertension)
calcium → calcium_100g (hypertension)
magnesium → magnesium_100g (hypertension)
cholesterol → cholesterol_100g (hypertension)
Non-Interactive Shell Commands
ALWAYS use non-interactive flags to avoid hanging on confirmation prompts.
cp -f source dest # NOT: cp source dest
rm -f file # NOT: rm file
Session Completion
- File issues for remaining work -
bd createfor follow-up items - Run quality gates -
cargo build --release && cargo test - Close completed issues -
bd close <id1> <id2> ... - PUSH -
git add -A && git commit -m "..." && git push - Verify -
git statusmust show clean working tree
Beads Issue Tracker
This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands.
Quick Reference
bd ready # Find available work
bd show <id> # View issue details
bd update <id> --claim # Claim work
bd close <id> # Complete work
Rules
- Use
bdfor ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists - Run
bd primefor detailed command reference and session close protocol - Use
bd rememberfor persistent knowledge — do NOT use MEMORY.md files
Architecture in one line: issues live in a local Dolt DB; sync uses refs/dolt/data on your git remote; .beads/issues.jsonl is a passive export. See https://github.com/gastownhall/beads/blob/main/docs/SYNC_CONCEPTS.md for details and anti-patterns.
Agent Context Profiles
The managed Beads block is task-tracking guidance, not permission to override repository, user, or orchestrator instructions.
- Conservative (default): Use
bdfor task tracking. Do not run git commits, git pushes, or Dolt remote sync unless explicitly asked. At handoff, report changed files, validation, and suggested next commands. - Minimal: Keep tool instruction files as pointers to
bd prime; use the same conservative git policy unless active instructions say otherwise. - Team-maintainer: Only when the repository explicitly opts in, agents may close beads, run quality gates, commit, and push as part of session close. A current "do not commit" or "do not push" instruction still wins.
Session Completion
This protocol applies when ending a Beads implementation workflow. It is subordinate to explicit user, repository, and orchestrator instructions.
- File issues for remaining work - Create beads for anything that needs follow-up
- Run quality gates (if code changed) - Tests, linters, builds
- Update issue status - Close finished work, update in-progress items
- Handle git/sync by active profile:
# Conservative/minimal/default: report status and proposed commands; wait for approval. git status # Team-maintainer opt-in only, unless current instructions forbid it: git pull --rebase git push git status - Hand off - Summarize changes, validation, issue status, and any blocked sync/commit/push step
Critical rules:
- Explicit user or orchestrator instructions override this Beads block.
- Do not commit or push without clear authority from the active profile or the current user request.
- If a required sync or push is blocked, stop and report the exact command and error.