pp-cookunity

<!-- GENERATED FILE — DO NOT EDIT. This file is a verbatim mirror of library/food-and-dining/cookunity/SKILL.md, regenerated post-merge by tools/generate-skills/. Hand-edits here are silently overwritten on the next regen. Edit the library/ source instead. See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". --> # CookUnity — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `cookunity-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install cookunity --cli-only ``` 2. Verify: `cookunity-pp-cli --version` 3. Ensure the reported install directory is on `$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 1.26.5 or newer). This installs into `$GOPATH/bin` (default `$HOME/go/bin`), so add that directory to `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/food-and-dining/cookunity/cmd/cookunity-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. CookUnity's chef-driven menu is only visible logged-in and online, paginated across hundreds of lazy-loaded cards, with shallow filters that reset on reload. This CLI syncs the entire menu — every meal's macros, chef, price, diet tags, allergens, and ratings — into a local SQLite store, then lets you query it offline: build a macro-constrained meal plan with `plan`, rank best value with `value`, see what changed with `drift`, and search everything with FTS. Every command speaks `--json` for agents. ## When to Use This CLI Use this CLI when you want CookUnity's menu as data: to plan meals against macro/diet/budget constraints offline, to compare or rank meals by nutrition and value, to search the menu, or to track how the menu changes week over week. It is ideal for macro-tracking eaters, allergy-constrained households, and anyone who wants to script or feed the menu to an agent. ## Anti-triggers Do not use this CLI for: - Do not use this CLI to place, modify, or cancel a CookUnity order — it is read-only over the menu and account. - Do not use it to manage billing, subscription plan changes, or delivery addresses. - Do not use it as a general recipe database; it only covers CookUnity's current prepared-meal menu. ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Local planning that compounds - **`plan`** — Auto-build a set of meals that collectively hit your protein, calorie, budget, and diet targets — offline, in one command. _Reach for this when the user wants a week's worth of meals meeting nutrition or budget constraints instead of hand-picking dishes._ ```bash cookunity-pp-cli plan --protein-min 40 --calories-max 600 --count 8 --diet gluten-free --agent ``` - **`drift`** — See exactly which meals were added, removed, or repriced between two weekly menus. _Use this to track what changed on the new menu without re-scanning 300+ dishes by hand._ ```bash cookunity-pp-cli drift --from 2026-07-28 --to 2026-08-04 --json ``` - **`value`** — Rank meals by nutritional value per dollar (protein-per-dollar, calories-per-dollar) computed from the local mirror. _Pick this when the user cares about maximizing protein or calories per dollar across the menu._ ```bash cookunity-pp-cli value --metric protein-per-dollar --limit 20 --agent ``` ### Agent-native menu queries - **`favorites`** — Show which of your favorited meals are actually on the current week's menu. _Use this first after a menu drop to see if the user's liked meals are back._ ```bash cookunity-pp-cli favorites --json ``` - **`compare`** — Side-by-side macro, price, chef, and allergen comparison of two or more meals. _Reach for this to decide between specific candidate meals the user already has in mind._ ```bash cookunity-pp-cli compare 3707 3210 --json ``` - **`chefs`** — Leaderboard of chefs by dish count, average rating, average price, and cuisines on the current menu. _Use this to explore the menu by chef or find highly-rated chefs._ ```bash cookunity-pp-cli chefs --json ``` ## Command Reference **meals** — Query the locally-synced CookUnity meal catalog offline - `cookunity-pp-cli meals` — List meals (hand-built to read the local store; this endpoint is the upstream source) **menu** — Fetch the CookUnity weekly menu (server-driven-UI) for a delivery date ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash cookunity-pp-cli which "<capability in your own words>" ``` `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. ## Recipes ### Plan a high-protein gluten-free week ```bash cookunity-pp-cli plan --protein-min 40 --calories-max 650 --count 8 --diet gluten-free --agent ``` Selects 8 meals from the synced menu that collectively fit the macro and diet constraints. ### Find the best protein-per-dollar meals ```bash cookunity-pp-cli value --metric protein-per-dollar --limit 15 --agent --select name,chefName,protein,finalPrice ``` Ranks meals by protein per dollar and returns only the fields an agent needs, keeping the payload small. ### See what changed on the new menu ```bash cookunity-pp-cli drift --from 2026-07-28 --to 2026-08-04 --json ``` Diffs two synced weekly snapshots to show added, removed, and repriced meals. ### Compare two meals head to head ```bash cookunity-pp-cli compare 3707 3210 --json ``` Prints a side-by-side macro/price/chef/allergen comparison of the two meal ids. ## Auth Setup CookUnity has no public API. Auth is the Auth0 access token your logged-in browser session already holds. Copy it from the browser (DevTools → Network → any subscription.cookunity.com request → the `authorization` header value, which is the raw token with no `Bearer ` prefix) and set `COOKUNITY_TOKEN`. The token lasts about 24 hours; re-copy it when `doctor` reports it expired. Run `cookunity-pp-cli doctor` to verify setup. ## Agent Mode Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color --yes`. - **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 cookunity-pp-cli meals --agent --select id,name,status ``` - **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 - **Read-only** — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests ### 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": <data> } ``` 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 <dir>` for one invocation, or set `COOKUNITY_HOME=<dir>` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `COOKUNITY_CONFIG_DIR`, `COOKUNITY_DATA_DIR`, `COOKUNITY_STATE_DIR`, `COOKUNITY_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `COOKUNITY_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 `cookunity-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": { "cookunity": { "command": "cookunity-pp-mcp", "env": { "COOKUNITY_HOME": "/srv/cookunity" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `COOKUNITY_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 `COOKUNITY_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, run: ```bash cookunity-pp-cli recall "<user's question>" --agent ``` The response envelope: ```json { "query": "...", "normalized": "<normalized form>", "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": ["<trial command>", "cookunity-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ], "entity_slots": ["$ENTITY"], "expected_tool_calls": 3 }, "slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } }, "notes": "<workarounds + gotchas for this query family>" }, "notes": "<duplicate surface for non-playbook callers>" } ``` 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 <id>` only after the trial verified the behavior. Reject a wrong candidate with `learnings reject <id>`. -> 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 `cookunity-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 <id>` prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. `learnings reject <id>` tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; `cookunity-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:<canonical>` (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.