--- name: pp-fooda description: "Your Fooda office lunch history, subsidy and this week's popups in a terminal, with vendor and spend analytics the app does not offer." author: "Allen Lew" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - fooda-pp-cli install: - kind: go bins: [fooda-pp-cli] module: github.com/mvanhorn/printing-press-library/library/food-and-dining/fooda/cmd/fooda-pp-cli --- # Fooda — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `fooda-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first: 1. Install via the Printing Press installer. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install fooda --cli-only ``` 2. Verify: `fooda-pp-cli --version` 3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill. If the `npx` install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into `$GOPATH/bin` (default `$HOME/go/bin`), so add that directory to `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/food-and-dining/fooda/cmd/fooda-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. Fooda has no public API. This CLI reads the logged-in web app with your Chrome session, syncs your order history locally, and answers questions like what you ate, where you keep ordering, and how much subsidy you have left today. ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Local history that compounds - **`served-history`** — See every lunch you were actually served, with date, vendor, items and price. _Use when an agent needs a longitudinal record of what a person ate rather than today's menu._ ```bash fooda-pp-cli served-history --since 90d --agent ``` - **`venue-rotation`** — Rank vendors by how often and how recently you ordered from them. _Use to spot vendor fatigue or under-used favorites before choosing lunch._ ```bash fooda-pp-cli venue-rotation --since 120d --agent ``` - **`spend-trends`** — Spend per month or week, split into subsidy-covered and out-of-pocket. _Use for budget or subsidy-utilization reporting._ ```bash fooda-pp-cli spend-trends --since 6mo --group-by month --agent ``` ### Lunch planning - **`week-ahead`** — One-line-per-day digest of upcoming events and restaurants at your building. _Use for a quick morning check of what is being served this week._ ```bash fooda-pp-cli week-ahead --agent ``` - **`subsidy-status`** — Remaining dollars of today's subsidy and when it is valid. _Use before ordering to know how much of the meal is covered._ ```bash fooda-pp-cli subsidy-status --agent ``` - **`menu-search`** — Search menu items across all of today's events. _Use for dietary or craving lookups without opening each vendor page._ ```bash fooda-pp-cli menu-search vegan --agent ``` - **`delivery-status`** — Whether your order for a day (default today) was delivered, with delivery time, vendor and items. _Use to confirm lunch arrived; delivered events drop off events and week-ahead, so a missing event does not mean there was no order._ ```bash fooda-pp-cli delivery-status --agent ``` ## Anti-Triggers & Limitations - **Ordering Support**: Ordering is supported via `order add` and `order place` when using `--confirm`. Automated agents must never pass `--confirm` without explicit user intent. - **Cancellation Limitation**: The `order cancel` command is not supported (please cancel manually in the Fooda app). - **`whoami` Cloudflare Constraints**: The `whoami` command is heavily limited by Cloudflare challenges. It fallbacks to greeting pages; account and building IDs are extracted from the home page. - **Catering / Billing**: Do not use this CLI for Fooda Catering orders or billing. - **Delivered events disappear**: Once a day's delivery completes, Fooda drops that event from `events` and `week-ahead`, and the My Fooda page jumps to the next day with no status. A missing event for today does not mean there was no order. Run `delivery-status` instead, which reads order history (`Delivered on …` versus `Delivering on … between …`). Orders report the same `checkout_complete` status whether they were delivered or are still scheduled, so the delivery text is the only delivered-versus-scheduled signal. ## Cookbook / Recipes - **Budget-Optimized Lunch Planning**: Plan an add-on item, add both to cart, and place order: ```bash fooda-pp-cli order plan --event S609348 --budget 20 --anchor "Beef Bulgogi Bowl" fooda-pp-cli order add 589968 --event S609348 --confirm fooda-pp-cli order add 589973 --event S609348 --confirm fooda-pp-cli order place --event S609348 --confirm ``` - **Vendor Fatigue Check**: `fooda-pp-cli venue-rotation --since 120d --agent --select vendor,order_count,last_ordered` - **Monthly Subsidy Report**: `fooda-pp-cli spend-trends --since 6mo --group-by month` - **Vegan Options Today**: `fooda-pp-cli menu-search vegan` - **Did Today's Lunch Arrive?**: `fooda-pp-cli delivery-status --agent` (add `--date YYYY-MM-DD` for another day) ## Recipes ### Budget-optimized lunch planning ```bash fooda-pp-cli order plan --event S609348 --budget 20 --anchor "Beef Bulgogi Bowl" ``` Suggests a budget-optimized add-on item from the event menu. ### Vendor fatigue check ```bash fooda-pp-cli venue-rotation --since 120d --agent --select vendor,order_count,last_ordered ``` Shows only the fields needed to see repeat vendors. ### Monthly subsidy report ```bash fooda-pp-cli spend-trends --since 6mo --group-by month ``` Splits covered and out-of-pocket spend per month. ### Vegan options today ```bash fooda-pp-cli menu-search vegan ``` Searches every event menu for the term. ### Did today's lunch arrive? ```bash fooda-pp-cli delivery-status --agent ``` Reports each order on the date as `delivered`, `scheduled`, or `unknown`, with the delivery text, vendor and items. It reads order history because a delivered event no longer appears in `events` or `week-ahead`. ## Command Reference **cards** — - `fooda-pp-cli cards balances` — Outstanding Fooda Card balances. - `fooda-pp-cli cards list` — Saved payment cards for a user id (variables: {userId}). **events** — - `fooda-pp-cli events` — Search public events (popup, cafe, delivery, catering) for an account/building and date range. **recommendations** — - `fooda-pp-cli recommendations` — Personalized recommendations for a select event (variables.input.targetId). **subsidies** — - `fooda-pp-cli subsidies` — List your subsidies with coverage, validity, state, and remaining balance (qrInfo). **served-history** — - `fooda-pp-cli served-history` — Show food history based on synced orders. **venue-rotation** — - `fooda-pp-cli venue-rotation` — Analyze vendor order frequency and last ordered date. **spend-trends** — - `fooda-pp-cli spend-trends` — Generate time-series spend reports showing subsidy and out-of-pocket costs. **week-ahead** — - `fooda-pp-cli week-ahead` — View live events for the next 7 days in a daily one-line digest. **subsidy-status** — - `fooda-pp-cli subsidy-status` — Display today's remaining dollar subsidy and validity details. **menu-search** — - `fooda-pp-cli menu-search ` — Filter and search menu items across today's events. **delivery-status** — - `fooda-pp-cli delivery-status` — Check whether your order for a day (default today) was delivered. ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash fooda-pp-cli which "" ``` `which` resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code `0` means at least one match; exit code `2` means no confident match — fall back to `--help` or use a narrower query. `--json` (and other machine formats) keep that exit-2 contract and write `{"matches":[]}` on stdout so agents can inspect the envelope without treating a miss as success. ## Auth Setup Fooda sits behind Cloudflare and has no API key. Log in to app.fooda.com in Chrome, then run `auth login --chrome` to import your session cookies, or use `auth login --cookies-file ` to import cookies from a JSON file. The CLI never logs in itself. Run `fooda-pp-cli doctor` to verify setup. ## Agent Mode Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color`. Global format flags share one contract on promoted, novel, sync, and `--deliver` paths: - `--json` — one JSON document on stdout (sync progress events go to stderr) - `--compact` — keep identity/status/timestamp fields; does not change the document vs stream shape - `--csv` / `--plain` — tabular rows (collection envelopes unwrap to the row array) - `--quiet` — one identity value per row, no envelope - **Pipeable** — JSON on stdout, errors on stderr - **Filterable** — `--select` keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs: ```bash fooda-pp-cli card --agent ``` - **Previewable** — `--dry-run` shows the request without sending - **Offline-friendly** — sync/search commands can use the local SQLite store when available - **Non-interactive** — never prompts, every input is a flag - **Explicit confirmation** — `--agent` does not imply `--yes`; pass `--yes` separately only after the target, arguments, and side effects are clear ### Response envelope Commands that read from the local store or the API wrap output in a provenance envelope: ```json { "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."}, "results": } ``` Parse `.results` for data and `.meta.source` to know whether it's live or local. A human-readable `N results (live)` summary is printed to stderr only when stdout is a terminal AND no machine-format flag (`--json`, `--csv`, `--compact`, `--quiet`, `--plain`, `--select`) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout. ## Paths and state Agents should treat the CLI's path resolver as part of the runtime contract: - Use `--home ` for one invocation, or set `FOODA_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `FOODA_CONFIG_DIR`, `FOODA_DATA_DIR`, `FOODA_STATE_DIR`, `FOODA_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `FOODA_HOME`, XDG (`XDG_CONFIG_HOME`, `XDG_DATA_HOME`, `XDG_STATE_HOME`, `XDG_CACHE_HOME`), then platform defaults. - `config` contains settings like `config.toml` and profiles. `data` contains `credentials.toml`, `data.db`, cookies, and auth sidecars. `state` contains persisted queries, jobs, and `teach.log`. `cache` contains regenerable HTTP/cache files. - Stored secrets live in `credentials.toml` under the data dir. Existing legacy `config.toml` secrets are read for compatibility and leave `config.toml` on the first auth write. - Run `fooda-pp-cli doctor --fail-on warn` to surface path and credential-location warnings. `agent-context` exposes a schema v4 `paths` block for agents that need the resolved dirs. - For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags: ```json { "mcpServers": { "fooda": { "command": "fooda-pp-mcp", "env": { "FOODA_HOME": "/srv/fooda" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `FOODA_HOME` or per-kind vars as durable fleet levers, and use `--home` only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing `FOODA_HOME`, or `doctor` will not find credentials left under the former root. ## Automatic learning This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a `flag_alias` candidate, and a `teach` on a query family without a playbook auto-synthesizes a `playbook_candidate` from the session's journal. Your job is judgment only: `recall` first, act on surfaced candidates, `teach` the final answer, `playbook amend` when you observe a correction. You never record failures by hand. ### Step 1: `recall` before any discovery Before list/search/drill commands on a new user question, pass the question as an argv or MCP tool argument to `recall --agent`. Do not interpolate user-controlled text into a shell command line. Quoted `recall ""` breaks on an apostrophe, which is ordinary English. A quoted heredoc breaks when a body line equals the delimiter, and that delimiter is published in these docs. Write the question with a non-shell file-writing tool, then read it back as data: ```bash # Write the question verbatim with your file-writing tool (no shell involved). # Command substitution on a file only ever yields data — the shell never # parses the file's bytes as syntax. QUERY=$(cat /path/to/question.txt) fooda-pp-cli recall "$QUERY" --agent ``` Prefer MCP: pass the question as the tool's query argument. `"$QUERY"` after a file read is argv-safe; putting the question itself in the command text is not. The response envelope: ```json { "query": "...", "normalized": "", "query_entities": ["..."], "found": true | false, "match_score": 0.0, "results": [ { "resource_id": "...", "resource_type": "...", "venue": "...", "confidence": 2, "entity_match": "exact|partial|unknown", "source": "taught|preseed|pattern", "warnings": ["..."] } ], "mismatches": [ /* only when --debug-mismatches */ ], "warnings": [ /* top-level */ ], "candidates": [ { "id": 12, "class": "flag_alias | playbook_candidate", "summary": "...", "sightings": 3, "last_seen": "...", "rationale": "...", "next_action": ["", "fooda-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "", "purpose": "..." } ], "entity_slots": ["$ENTITY"], "expected_tool_calls": 3 }, "slots_resolved": { "$ENTITY": { "token": "", "canonical": "" } }, "notes": "" }, "notes": "" } ``` Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and `learnings list` and `learnings candidates` are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught. ### Step 2: decision tree Read `candidates`, `playbook`, `notes`, `results[0]`, and warnings in that order: ``` if Candidates present (warnings include "candidates_present"): -> candidates are try-then-confirm, never facts. Follow each candidate's two-step next_action verbatim: run the trial command first, then run `learnings confirm ` only after the trial verified the behavior. Reject a wrong candidate with `learnings reject `. -> NEVER re-teach something recall surfaced as a candidate; confirm or reject that candidate instead of teaching a duplicate. -> candidates ride alongside playbooks and resource hits, not instead of them; continue with the branches below after acting on them. if Playbook present: -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose) -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries for the entity slot tokens. If a step's slot is unresolved, fall back to discovery for that step only. -> the Playbook's expected_tool_calls is a budget; if you find yourself running materially more, record the divergence via `fooda-pp-cli playbook amend` at end-of-session. elif Notes present (no Playbook): -> read Notes verbatim before any discovery step; they carry known gotchas for this query family even when no structured choreography exists yet. elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2: -> skip discovery; fetch live data for Results[*].ResourceID in parallel elif Found AND Results[0].EntityMatch == "partial": -> candidate hint, NOT a hit; read the resource title to validate before trusting elif (any row in Mismatches[] when --debug-mismatches was passed): -> treat as cold start; the stored learning is for a different entity (different canonical resolved from query_entities) else: // Found == false, no playbook, no notes -> cold start; run discovery normally; teach the answer afterward (Step 4). If the family has no playbook yet, that teach auto-synthesizes a playbook candidate from this session's journal - you do not need to record one by hand. ``` Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a `Results[]` hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping `mismatches`; pass `--debug-mismatches` only when investigating cold-start surprises. Candidate judgment details: `learnings confirm ` prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. `learnings reject ` tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; `fooda-pp-cli learnings candidates` lists the full open set. Graceful degradation: if `learnings confirm` is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol. ### Step 3: always read `warnings` - `low_confidence`: row exists at `confidence<2`. Treat as a hint, not a skip-discovery hit. - `resource_not_in_store`: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate. - `cross_alias_match` (per-result): the row was taught under a different alias and matched the live query's canonical via `entity_lookups` (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id. - `similar_shape_different_entity:` (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results. - `ambiguous_alias` (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource. - `candidates_present` (top-level): the envelope carries a `candidates` section. Handle it via the can