--- name: pp-juneoven description: "Control a June oven from the terminal — self-pair, preheat, adjust, watch live telemetry and camera frames, and cancel, over June's cloud with agent-native JSON. No HomeKit, no June app. Trigger phrases: `preheat my june oven to 350`, `what's my june oven doing`, `cancel the oven`, `set a timer on the june oven`, `watch the june oven`, `is the oven preheated`, `use juneoven`, `run juneoven`." author: "Matt Van Horn" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - juneoven-pp-cli install: - kind: go bins: [juneoven-pp-cli] module: github.com/mvanhorn/printing-press-library/library/devices/juneoven/cmd/juneoven-pp-cli --- # June Oven — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `juneoven-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install juneoven --cli-only ``` 2. Verify: `juneoven-pp-cli --version` 3. Ensure the reported install directory is on `$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 `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/devices/juneoven/cmd/juneoven-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. Direct pair/preheat/watch/cancel control with no HomeKit and no June app, plus local history (record, log, curve, preheat-stats), workflow primitives (ready, eta), and named repeatable cooks (repeat). All agent-native JSON. ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Cook workflow primitives - **`ready`** — Wait for the oven to reach its target temperature, then exit 0 (non-zero on timeout). _Lets an agent synchronously gate the next cook step on preheat completion instead of busy-waiting._ ```bash juneoven-pp-cli ready --timeout 20 --agent ``` - **`eta`** — Non-blocking estimate of time until the oven reaches target, from the live climb rate. _An agent can sequence the next action off a returned ETA without blocking._ ```bash juneoven-pp-cli eta --agent ``` - **`repeat`** — Save a named mode+temp(+timer) preset in local SQLite and replay it with one word. _Collapses a repeated weekly cook into a single memorable command._ ```bash juneoven-pp-cli repeat ``` ### Local history the cloud never keeps - **`record`** — Capture the current cook (session + telemetry/camera activity) into local SQLite. _Turns ephemeral live cooks into a queryable local dataset the cloud never stores._ ```bash juneoven-pp-cli record --label sourdough --agent ``` - **`log`** — List past cooks (mode, target, duration, outcome) from local history. _Answers historical questions about the oven that are impossible through June's API._ ```bash juneoven-pp-cli log --since 7d --agent ``` - **`curve`** — Export one recorded cook's temperature/progress samples as JSON or CSV. _Gives a plottable series for one cook, for analysis or piping._ ```bash juneoven-pp-cli curve 3 --format csv ``` - **`preheat-stats`** — Median/fastest/slowest time-to-target per cook over recorded cooks. _Shows how your specific oven performs over time and whether it is degrading._ ```bash juneoven-pp-cli preheat-stats --cook bake --agent ``` ## Recipes ### Preheat and record ```bash juneoven-pp-cli preheat --temp 450 && juneoven-pp-cli record --label pizza ``` Start a cook and capture its session to local history. ### Weekly cook by name ```bash juneoven-pp-cli repeat sunday-roast ``` Replay a saved mode+temp+timer preset in one command. ### Export a cook's curve ```bash juneoven-pp-cli curve 3 --format csv --agent --select ts,cavity_f ``` Pull one session's temperature series as CSV for plotting. ## Command Reference Control a June oven directly over June's cloud. No HomeKit, no June phone app. Temperatures are °F by default; add `--celsius` where a temperature is taken. - `juneoven-pp-cli pair` — Pair this CLI with your oven by typing an 8-digit code on its screen. Run once; credentials are stored at 0600 and control the oven. - `juneoven-pp-cli status` — Connection state, idle/active, and current target temperature. - `juneoven-pp-cli preheat --temp 350` — Start a cook (`--mode bake` or `roast`). Reports the oven's ack (`success`/`not-allowed`). - `juneoven-pp-cli temp --temp 375` — Change the target of the active cook (June may reject a live retarget with `not-allowed`). - `juneoven-pp-cli timer --minutes 10` — Set a cook timer. - `juneoven-pp-cli cancel` — Stop the active cook. `not-allowed` when already idle (reported as a normal result, not an error). - `juneoven-pp-cli watch --seconds 120` — Stream live telemetry and camera-frame events as JSON lines until the cook ends or the timeout elapses. - `juneoven-pp-cli cam --timeout 15` — Print the next interior camera frame's signed URL (frames are typically pushed only during an active cook). Every command supports `--json` / `--agent` for structured output. Command acks come back as `{"action","acked","status"}`; `status` is the oven's own verdict. ### Unique Capabilities June's cloud keeps only live state and no history. These commands add a durable local record (SQLite) and workflow primitives no other June tool offers: - `juneoven-pp-cli record --label sourdough` — Capture the current cook (session + activity) into local history. The only durable record; the cloud stores none. - `juneoven-pp-cli log --since 7d` — List past cooks (mode, target, duration, outcome). Impossible via June's API. - `juneoven-pp-cli repeat ` — Save (`--save --mode --temp --timer`) and replay named cooks in one word. `--list` shows saved presets. - `juneoven-pp-cli ready --timeout 20` — Block until the oven reaches target, typed exit (0 ready, 4 timeout). Gate an agent step on preheat completion. - `juneoven-pp-cli eta` — Non-blocking predicted time-to-ready from the live climb rate. - `juneoven-pp-cli curve --format csv` — Export one recorded cook's temperature curve. - `juneoven-pp-cli preheat-stats --cook bake` — Median/fastest/slowest time-to-target per cook over recorded cooks. **Firmware note (important):** `ready`, `eta`, `curve`, and `preheat-stats` need an oven that streams live cavity-temperature telemetry. Some firmware (e.g. the `penguin` model) streams only interior camera frames and no temperature; on those ovens these four commands return an honest empty/notice result rather than data, while `record`, `log`, and `repeat` work fully. `status`, `preheat`, `temp`, `timer`, `cancel`, `watch`, and `cam` work on all paired ovens. ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash juneoven-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. ## Auth Setup Auth is direct pairing: run `juneoven-pp-cli pair` once and type an 8-digit code on the oven. A signing key and access token are stored at ~/.config/juneoven-pp-cli/identity.json (0600). Run `juneoven-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 juneoven-pp-cli status --agent --select state,target_f ``` - **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 retries** — use `--idempotent` only when an already-existing create should count as success ### 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 `JUNEOVEN_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `JUNEOVEN_CONFIG_DIR`, `JUNEOVEN_DATA_DIR`, `JUNEOVEN_STATE_DIR`, `JUNEOVEN_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `JUNEOVEN_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 `juneoven-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": { "juneoven": { "command": "juneoven-pp-mcp", "env": { "JUNEOVEN_HOME": "/srv/juneoven" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `JUNEOVEN_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 `JUNEOVEN_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 juneoven-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": ["", "juneoven-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 `juneoven-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; `juneoven-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 `juneoven-pp-cli sync` 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 after assembling your user-facing response but BEFORE emitting it, with a shell `&` so the call returns immediately: ```bash juneoven-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). Prefe