--- name: pp-repark description: "Find Repark parking with live source vacancy, declared vehicle limits, and verified price estimates. Trigger phrases: `find Repark parking near Tokyo Station`, `check Repark vehicle height limits`, `estimate Repark parking cost`, `use repark`, `run repark`." author: "Jet Sng" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - repark-pp-cli install: - kind: go bins: [repark-pp-cli] module: github.com/mvanhorn/printing-press-library/library/travel/repark/cmd/repark-pp-cli --- # 三井のリパーク (Repark) — Printing Press CLI ## Local build status This checkout is built and tested locally. Public installer/release commands below apply after separate publication. In this checkout, use `go build -o repark-pp-cli ./cmd/repark-pp-cli` and invoke `./repark-pp-cli`. ## Prerequisites: Install the CLI This skill drives the `repark-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install repark --cli-only ``` 2. Verify: `repark-pp-cli --version` 3. Ensure the reported install directory is on `$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 `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/travel/repark/cmd/repark-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. Search named places or explicit coordinates, inspect source day and night rules, and compare chosen lots. Vacancy and declared vehicle fit remain separate; quotes come from the provider calculator. ## When to Use This CLI Use for Repark time parking discovery by place or explicit coordinates, lot comparison, declared vehicle limits and provider fee estimates. Include exact JST entry/exit times and bay for a quote. ## Anti-triggers Do not use this CLI for: - Reservations or payments - Guaranteed availability or remaining-bay fit - Other parking providers or personal live location ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Parking planning - **`parking compare`** — Compare source rates, maximum rules, opening hours and vehicle limits across chosen lot IDs. _Compare source rates, maximum rules, opening hours and vehicle limits across chosen lot IDs._ ```bash repark-pp-cli parking compare REP0022209 REP0029431 --agent ``` - **`parking nearby`** — Assess supplied dimensions independently from remaining bay suitability. _Assess supplied dimensions independently from remaining bay suitability._ ```bash repark-pp-cli parking nearby --lat 34.663534 --lon 135.516310 --height 2.1 --agent ``` - **`parking nearby`** — Filter source vacancy categories within an explicit search radius. _Filter source vacancy categories within an explicit search radius._ ```bash repark-pp-cli parking nearby --park REP0022209 --available-only --agent ``` - **`parking detail`** — Read day type, rate windows and maximum rules alongside exact source conditions. _Read day type, rate windows and maximum rules alongside exact source conditions._ ```bash repark-pp-cli parking detail REP0022209 --agent ``` - **`parking capabilities`** — Inspect source support, measurement unknowns and bounded request policy. _Inspect source support, measurement unknowns and bounded request policy._ ```bash repark-pp-cli parking capabilities --agent ``` ## Discovery Signals This CLI was generated with browser-observed traffic context. - Capture coverage: 0 API entries from 1 total network entries - Protocols: ssr_embedded_data (85% confidence) ## Parking decision procedure 1. Choose `parking search` for a supplied named place/area, or `parking nearby` for supplied coordinates or a known lot. A `needs_refinement` search requires a more precise query or explicit anchor; never substitute current driver location. 2. Use `parking detail` to inspect a canonical REP lot. Preserve Japanese day types, overnight windows, maximum conditions and explicit repeating/one-time wording. 3. Supply known vehicle dimensions to detail/nearby/compare. Treat published-limit conflicts separately from vacancy. Remaining-bay suitability and exact available-space counts remain unknown, including when the lot is available/crowded. 4. Use `parking quote` only with an actual marked bay and exact JST entry/exit timestamps. The CLI calls the source simulator and performs no local total arithmetic. Use current-rate estimates with their source cautions; discounts and final billed amounts are not guaranteed. 5. Parse `.results`, inspect `.meta.requests` and truncation flags, and retain `.observed_at`. Source import/update strings are raw metadata with unverified measurement semantics. Tax inclusion/exclusion is known only when the source says so; retain displayed JPY amounts without adding tax. Manual `sync` snapshots require a supplied bounded `--param range=...` or `REPARK_SYNC_RANGE` environment value (flags take precedence; no location is preset) and do not replace live parking facts. Discovery output is `.results.lots`, with a source-resolved/supplied anchor, 50..2000 m radius, independent 1..1000 row matching cap, and 1..50 output cap. Comparison reports `fetch_failures` and successful-lot count. Runtime has no credentials/browser, no automatic retries, 2 MiB response bounds and 60-second whole-command bounds (or a shorter `--timeout`). Prices, vacancy and coverage can change. See `parking capabilities --json` for current bounds and unknowns. ## Command Reference **site** — Source interfaces for maintainers; prefer parking commands for planning facts - `repark-pp-cli site calculator-form` — Inspect whether the source calculator form is present - `repark-pp-cli site detail-page` — Fetch the source lot detail document - `repark-pp-cli site markers` — Fetch source markers for an explicit bounded map window ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash repark-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. ## Recipes ### Source facts ```bash repark-pp-cli parking detail REP0022209 --agent --select id,name,occupancy,rates,maximum_charges ``` Narrow detailed output to source identity and tariff facts. ### Vehicle fit ```bash repark-pp-cli parking nearby --park REP0022209 --height 2.1 --limit 3 --agent ``` See declared limit conflicts separately from vacancy. ### Source quote ```bash repark-pp-cli parking quote REP0022209 --bay 1 --start 2026-10-03T08:00 --end 2026-10-03T12:00 --agent ``` Get a provider estimate for a future exact JST interval. ## Auth Setup Public discovery and calculator simulation use no account, token or browser at runtime. Run `repark-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 repark-pp-cli parking nearby --park REP0022209 --limit 3 --agent --select lots.id,lots.name,lots.occupancy ``` - **Previewable** — `--dry-run` shows the request without sending - **Live parking facts** — parking commands read the public provider on every invocation; framework learning/state commands do not provide an offline parking inventory - **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": } ``` 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 `REPARK_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `REPARK_CONFIG_DIR`, `REPARK_DATA_DIR`, `REPARK_STATE_DIR`, `REPARK_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `REPARK_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 `repark-pp-cli doctor --fail-on warn` to surface path 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": { "repark": { "command": "repark-pp-mcp", "env": { "REPARK_HOME": "/srv/repark" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `REPARK_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 `REPARK_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=$(cat /path/to/question.txt) repark-pp-cli recall "$QUERY" --agent ``` Prefer MCP: pass the question as the tool's query argument. `"$QUERY"` after a file read is argv-safe; putting the question itself in the command text is not. The response envelope: ```json { "query": "...", "normalized": "", "query_entities": ["..."], "found": true | false, "match_score": 0.0, "results": [ { "resource_id": "...", "resource_type": "...", "venue": "...", "confidence": 2, "entity_match": "exact|partial|unknown", "source": "taught|preseed|pattern", "warnings": ["..."] } ], "mismatches": [ /* only when --debug-mismatches */ ], "warnings": [ /* top-level */ ], "candidates": [ { "id": 12, "class": "flag_alias | playbook_candidate", "summary": "...", "sightings": 3, "last_seen": "...", "rationale": "...", "next_action": ["", "repark-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "", "purpose": "..." } ], "entity_slots": ["$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 `repark-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; `repark-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. - `lookup_refresh_available` (top-level): an entity in the query has no lookup row yet, but synced data could provide one. Run `repark-pp-cli sync --resources site --param "range=C34.663534,135.516310N34.664W135.515S34.663E135.517" --max-pages 1` to refresh entity lookups. - 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