--- name: pp-walmart description: "Printing Press CLI for Walmart. Reads via orchestra GraphQL. Cart changes are link-only: cart link prints one affil.walmart.com add-to-cart URL for the user to open. CLI never mutates the cart; never checkout." author: "DashLabsDev" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - walmart-pp-cli install: - kind: go bins: [walmart-pp-cli] module: github.com/mvanhorn/printing-press-library/library/commerce/walmart/cmd/walmart-pp-cli --- # Walmart — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `walmart-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install walmart --cli-only ``` 2. Verify: `walmart-pp-cli --version` 3. Ensure the reported install directory is on `$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 `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/commerce/walmart/cmd/walmart-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. Purchase history, grocery search, product and store lookups, cart view and slot listing, plus a cart link builder that prints one Walmart add-to-cart URL for you to open. The CLI never mutates the cart or checks out. ## When Not to Use This CLI Do not activate this CLI for checkout, ordering, purchasing, order changes, cart mutations, slot reservations, or switching between Pickup and Delivery; it cannot do them. To add items, run `cart link` and give the user the URL to open in their own browser. ## Unique Capabilities These capabilities aren't available in any other tool for this API. - **`orders list`** — PurchaseHistoryV3 persisted query with --type in-store/online, --status completed/in-progress, --search and cursor paging; read-only. - **`orders get`** — getOrder line items (name, item id, quantity, line price) plus subtotal, tax, fees and total; customer, address and payment fields are never emitted. - **`search`** — Parses the server-rendered search page for price, unit price, aisle, availability and pickup/delivery fulfillment at the session's store. - **`orders list`** — Client refuses non-GET requests and denylisted cart/checkout/slot/order mutations, and stops (no retry) on PerimeterX 412/418/429/456 or /blocked. - **`product get`** — ItemById persisted query: price, unit price, stock, pickup/delivery/shipping status and seller; shopper location fields are never emitted. - **`store list`** — nearByNodes query for a ZIP: store id, distance, address, pickup types and hours; view only, never sets a store. - **`cart view`** — getCart GET with a supplied cart id: items, mode, store and slot-reserved flag; MergeAndGetCart and every cart mutation stay blocked. - **`search`** — --filter type:value (e.g. brand:Great Value), --sort and --list-filters from the page's sort/filter facets. ## HTTP Transport This CLI uses standard HTTP transport with HTTP/2 disabled for browser-facing endpoints. It does not require a resident browser process for normal API calls. ## Recipes ### Build a grocery add-to-cart link ```bash walmart-pp-cli cart link 51259338:1 44391152:1 14584700257:1 ``` ### Check session health ```bash walmart-pp-cli doctor ``` ## Command Reference **account** — Account landing data used to verify the session, read only - `walmart-pp-cli account` — Account landing page (accountLandingPage persisted query) **orders** — Walmart purchase history (online and in-store), read only - `walmart-pp-cli orders detail` — One order with line items and price details (getOrder persisted query) - `walmart-pp-cli orders history` — Purchase history page (PurchaseHistoryV3 persisted query) - `walmart-pp-cli orders items` — Recently purchased items across orders (ItemHistory persisted query) **Shopping commands** (hand-built; customer names, addresses, phones and payment data are never emitted) Link-only writes: reads call orchestra GraphQL. **`cart link …`** builds `https://affil.walmart.com/cart/addToCart?items=id|qty,…` and prints it (optional `--open` / `--launch` opens the user's default browser). The link ADDS/increments qty on the existing browser cart. It also works signed out: items go into a guest cart and carry over into the account cart when you sign in. There is no cart update/remove, no slots reserve, and no CDP/browser driver. Never checkout or switch Pickup/Delivery. Read only: `orders list|get`, `search`, `product get`, `store list`, `cart view`, `slots list [--available]`. Cart link (mcp:read-only; prints a URL; does not call the cart API): - `cart link …` / `cart add …` — print one affiliate add-to-cart URL (ADDS to the existing browser cart; works signed out as a guest cart that carries over on sign-in, or signed in); `--open` / `--launch` opens the default browser; extra items can go in one comma-separated `--items` value (the MCP tool's multi-item field) - User opens the URL, picks a time, and checks out themselves. No update/remove/reserve commands. Cart id: `--cart-id` once, then remembered. On bot challenge / dropped connection: stop; ask user to clear walmart.com and `auth login --chrome`. ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash walmart-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 Import a signed-in walmart.com browser session with auth login --chrome (or --cookies-file with Playwright storage-state JSON, a browser-extension cookie export, a Netscape cookies.txt file or a raw Cookie header), then run doctor. auth status shows whether the session is active and when the short-lived auth cookie expires. Run `walmart-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 walmart-pp-cli account --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 - **Link-only cart** — `cart link` prints an affiliate add-to-cart URL; CLI never mutates the cart; never checkout or place an order ### 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 `WALMART_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `WALMART_CONFIG_DIR`, `WALMART_DATA_DIR`, `WALMART_STATE_DIR`, `WALMART_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `WALMART_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 `walmart-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": { "walmart": { "command": "walmart-pp-mcp", "env": { "WALMART_HOME": "/srv/walmart" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `WALMART_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 `WALMART_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 walmart-pp-cli recall "" --agent ``` 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": ["", "walmart-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 `walmart-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; `walmart-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 candidates branch in Step 2 before anything else. - Top-level `no_learnings_for_query_family`: the table had no rows above the Jaccard floor. Pure cold start. ### Step 4: `teach &` after finalizing your response - always Teaching is unconditional. After resolving a query the store could not answer, background-teach the final resource mapping - no call-count threshold, no judging whether it was "worth" learning. The teach is the anchor of the loop: it triggers playbook synthesis for a family without a playbook, and same-referent phrasings fold into one family so near-duplicate teaches do not fragment the store. Fire it after assembling your user-facing response but BEFORE emitting it, with a shell `&` so the call returns immediately: ```bash walmart-pp-cli teach --query "" --resource-type --resource --resource # (append shell `&` to background it) ``` Silent on success. Errors only land in `teach.log` under the resolved state dir. Teach the **most specific** resource - if the user asked a broad question and you walked through parent records to find the specific answer, teach the leaf id, not the parent. The CLI uses seeded `entity_lookups` for cross-alias resolution at recall time, so a teach under one alias (e.g., "Niners") satisfies future queries under another alias (e.g., "49ers", "San Francisco") automatically. PII rule: teach the structural question with identifiers stripped - never include names, emails, phone numbers, account ids, or other personal identifiers in taught queries or notes. The CLI scans teach queries for obvious email/phone shapes and warns, but does not block; strip before teaching rather than relying on the warning. ### Step 5: playbooks - optional flags, automatic synthesis You do not need to decide whether a session "deserves" a playbook: a teach on a family without one auto-synthesizes a `playbook_candidate` from the session's journal, and the next session judges it via confirm/reject. Attach explicit playbook flags only when you already hold choreography worth recording verbatim - workarounds the CLI didn't surface (silently-dropped flags, undocumented params, pagination tricks, payload gotchas). Prefer the **integrated one-call form** - record the resource learning and the playbook in the same `teach` invocation: ```bash # Common case: record both the resource learning AND the playbook in one call. walmart-pp-cli teach \ --query "" \ --resource \ --playbook-file ~/playbooks/.json \ --playbook-notes-file ~/playbooks/-notes.md # (append shell `&` to background it) # Alternate: playbook-only (no resource to record alongside). walmart-pp-cli teach-playbook \ --query "" \ --playbook-file ~/playbooks/<