--- name: pp-respondio description: "Every Respond.io feature, plus an offline mirror and SQL that answers inbox questions no single API call can. Trigger phrases: `check my respondio inbox`, `who talks to us on whatsapp`, `find contacts missing orderId`, `respondio workload by agent`, `send a message to this contact`, `use respondio`, `run respondio`." author: "bobe" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - respondio-pp-cli install: - kind: go bins: [respondio-pp-cli] module: github.com/mvanhorn/printing-press-library/library/social-and-messaging/respondio/cmd/respondio-pp-cli --- # Respond.io — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `respondio-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install respondio --cli-only ``` 2. Verify: `respondio-pp-cli --version` 3. Ensure the reported install directory is on `$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 `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/social-and-messaging/respondio/cmd/respondio-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. respondio-pp-cli wraps the full Respond.io Unification API v2 - contacts, messaging, conversations, comments, and workspace - then syncs contacts, users, and channels into a local SQLite store. Offline you can segment by tag, find custom-field gaps, check channel mix, and gauge workload by agent with --json output built for agents. ## When to Use This CLI Use respondio-pp-cli for Respond.io support/sales operations: looking up contacts, sending messages, routing and assigning conversations, and answering inbox questions offline (channel mix, tag cohorts, custom-field gaps, workload by agent). It is the right choice when you want agent-native --json output and a local mirror instead of one-off API calls. ## Anti-triggers Do not use this CLI for: - Do not use this CLI for deep Respond.io analytics that need historical message-by-message mining (the mirror is a snapshot). - Do not use it to configure Respond.io workspace settings outside the exposed endpoints. - Do not use it as a replacement for the Respond.io web product for manual conversation handling. ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Local state that compounds - **`overview`** — One-command summary of open conversations, unassigned contacts, per-agent distribution, and recent activity. _Use instead of a dozen API calls when you need the current inbox load at a glance._ ```bash respondio-pp-cli overview --json ``` - **`report workload`** — Per-agent message and conversation handling volume from the synced workspace. _Balance the team and spot overloaded agents without manual tallying._ ```bash respondio-pp-cli report workload --json ``` ### Segment & find - **`report channel-mix`** — See which messaging channels (WhatsApp, Instagram, email...) your contacts actually use. _Answer 'where do our customers talk to us' instantly from local data._ ```bash respondio-pp-cli report channel-mix --json ``` - **`contact by-tag`** — List every contact that carries a given tag (VIP, unpaid, in-trial). _Pull a whole segment for campaigns or support outreach in one command._ ```bash respondio-pp-cli contact by-tag VIP --json ``` - **`contact field-gaps`** — Find contacts missing a custom field value (e.g. no orderId or region). _Spot data quality gaps to drive clean-up or re-enrichment._ ```bash respondio-pp-cli contact field-gaps --name orderId --json ``` - **`contact idle`** — Find unassigned contacts with no recent activity worth working. _Route idle work before it goes cold._ ```bash respondio-pp-cli contact idle --days 7 --json ``` ### Agent-native plumbing - **`contact search`** — Free-text search across synced contacts without hitting the API. _Find a customer by name/email offline, fast, without api.respond.io._ ```bash respondio-pp-cli contact search --query acme --json ``` ## Command Reference **comment** — Add internal comments to contacts - `respondio-pp-cli comment ` — Create an internal comment on a contact **contact** — Manage Respond.io contacts and contact-level actions - `respondio-pp-cli contact add-tags` — Add tags to a contact - `respondio-pp-cli contact create` — Create a new contact (identifier must be email: or phone:) - `respondio-pp-cli contact delete` — Delete a contact - `respondio-pp-cli contact get` — Get a contact by identifier (id:123, email:user@example.com, phone:+1234567890) - `respondio-pp-cli contact list` — List contacts with optional search and filters - `respondio-pp-cli contact list-channels` — List all channels connected to a contact - `respondio-pp-cli contact merge` — Merge two contacts into one - `respondio-pp-cli contact remove-tags` — Remove tags from a contact - `respondio-pp-cli contact update` — Update an existing contact - `respondio-pp-cli contact update-lifecycle` — Update a contact's lifecycle stage - `respondio-pp-cli contact upsert` — Create or update a contact keyed by email/phone identifier **conversation** — Manage conversation assignment and status - `respondio-pp-cli conversation assign` — Assign or unassign a conversation - `respondio-pp-cli conversation update-status` — Open or close a conversation **message** — Send and retrieve messages for a contact - `respondio-pp-cli message get` — Get a message by ID - `respondio-pp-cli message list` — List messages for a contact - `respondio-pp-cli message send` — Send a message to a contact **space** — Respond.io workspace-level operations - `respondio-pp-cli space create-custom-field` — Create a custom field definition - `respondio-pp-cli space create-tag` — Create a workspace tag - `respondio-pp-cli space delete-tag` — Delete a workspace tag - `respondio-pp-cli space get-custom-field` — Get a custom field by ID - `respondio-pp-cli space get-user` — Get a user by ID - `respondio-pp-cli space list-channels` — List all channels in the workspace - `respondio-pp-cli space list-closing-notes` — List closing note categories - `respondio-pp-cli space list-custom-fields` — List all custom field definitions - `respondio-pp-cli space list-templates` — List message templates for a channel - `respondio-pp-cli space list-users` — List users in the workspace - `respondio-pp-cli space update-tag` — Update a workspace tag ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash respondio-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. ## Recipes ### Inbox load at a glance ```bash respondio-pp-cli overview --json ``` Summarize open conversations, unassigned contacts, and activity. ### Narrow a contact payload ```bash respondio-pp-cli contact get id:123 --agent --select firstName,email,lifecycle ``` Keep context small by selecting only the fields you need. ### Find data-quality gaps ```bash respondio-pp-cli contact field-gaps --name orderId --json ``` List contacts missing a custom field to drive enrichment. ### Where customers talk to you ```bash respondio-pp-cli report channel-mix --json ``` Show the channel-source distribution across synced contacts. ### Team workload ```bash respondio-pp-cli report workload --json ``` Per-agent handling volume from synced assignments. ## Auth Setup Auth uses a Respond.io API access token (Settings > Integrations > Developer API). Set RESPOND_IO_API_TOKEN and run respondio-pp-cli auth login. All commands are read-mostly; mutations support --dry-run. Run `respondio-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 respondio-pp-cli contact list --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 - **Explicit retries** — use `--idempotent` only when an already-existing create should count as success, and use `--ignore-missing` only when a missing delete target 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 `RESPONDIO_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `RESPONDIO_CONFIG_DIR`, `RESPONDIO_DATA_DIR`, `RESPONDIO_STATE_DIR`, `RESPONDIO_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `RESPONDIO_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 `respondio-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": { "respondio": { "command": "respondio-pp-mcp", "env": { "RESPONDIO_HOME": "/srv/respondio" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `RESPONDIO_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 `RESPONDIO_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 respondio-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": ["", "respondio-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 `respondio-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; `respondio-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 `respondio-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 respondio-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 a