ghosty-acp 0.0.66 → 0.0.68
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json
CHANGED
|
@@ -5,7 +5,7 @@ license: MIT
|
|
|
5
5
|
compatibility: Needs Node 22+ (for npx @ghostystudio/cli) or curl, and network access to https://www.ghosty.studio
|
|
6
6
|
metadata:
|
|
7
7
|
author: ghosty-studio
|
|
8
|
-
version: "1.
|
|
8
|
+
version: "1.99"
|
|
9
9
|
---
|
|
10
10
|
|
|
11
11
|
# Configure a Ghosty Studio agent
|
|
@@ -142,6 +142,7 @@ legacy and always `true`.)
|
|
|
142
142
|
| "which workspaces do I have / where is X's workspace" | `ghosty spaces ls [--user <email>] --json` (others: staff) |
|
|
143
143
|
| "no claude model fits / raise the model cap" (422 «caps at 0.25×») | staff: `ghosty spaces set <workspace> --model-cap 4 --dry-run`, then `--yes` (1 = up to Sonnet, none = its plan's) |
|
|
144
144
|
| "create a workspace" | `ghosty spaces create <slug> --dry-run`, then without `--dry-run` (yours, trial; same rules as the web: confirmed email, plan cap). `--combo` other than teams: staff |
|
|
145
|
+
| "the agent should only answer new people on my number / don't let it answer my mom" | `ghosty channels whatsapp contacts <id> --integration <id>` (state: new-only, known contacts, muted) · `--new-only on` (skips people the owner already talks to: WhatsApp contacts + history + people the owner wrote first) · `--mute <phone>` (agent never answers that number) · `--allow <phone>` (agent always answers it, even if known) · `--unmute <phone>` (back to the general rule) · `--signature 👾|off` (prefix on the agent's messages so customers tell it from the owner; new numbers start with 👾) · `--seed` (bring known contacts again) · `--list [--q mom]` (the phone contacts with names and each rule; find a contact by name before muting it). Numbers connected from Channels start not answering, with new-only on: turn the number on once the known contacts show up |
|
|
145
146
|
| "bring only the ad leads from this number" | `ghosty channels whatsapp history <id> --integration <formmy-id> --dry-run --list --only-ads` → show which, then without `--dry-run` (`--yes`); new numbers: `channels whatsapp link … --ads-only on` |
|
|
146
147
|
| "this agent answers two numbers, keep their boards separate" | `ghosty channels whatsapp link <id> --integration <formmy-id> --board "<board>" --dry-run` per number (`--board agent` = back to the agent's); `channels whatsapp ls <id>` shows each number's board |
|
|
147
148
|
| "why did it fail? / it didn't answer" | `ghosty turns ls <id> --errors --since 24h --json` → failed turns with their `error`; a WhatsApp customer got NO turn at all: `ghosty turns ls <id> --skipped --since 24h --json` → `reason` (manual_mode, records_only, paused, reaction, channel_off, no_quota, own_number) |
|
|
@@ -192,6 +193,7 @@ legacy and always `true`.)
|
|
|
192
193
|
| "answer in this WhatsApp group / make the group team or customer" | personal WhatsApp only: `ghosty channels wa groups ls <id> --json`, then confirm with the user and `ghosty channels wa groups enable <id> "<group>" --role equipo\|cliente --yes` (`--dry-run` first); a newly enabled group only answers when mentioned — `--wake all` to answer every message |
|
|
193
194
|
| "move / migrate this WhatsApp number from EasyBits or Formmy" | Business: find its Integration id and who answers it today with `ghosty channels whatsapp integrations <id> --json`, then `ghosty channels whatsapp link <id> --integration <formmy-id> --answer on\|off --dry-run --json` → show `plan`; confirm with the user (on = answers real customers), then without `--dry-run` and `--yes`; back: `unlink`. Its recent cards/messages/orders: `ghosty channels whatsapp history <id> --integration <formmy-id> --days 7 --dry-run` (works before linking), then without `--dry-run` (`--yes`; re-running never duplicates; it retries by itself during a deploy). It reports conversations that arrive paused by Formmy: list them with `ghosty cards ls <id> --paused --limit 200` and tell the user the agent won't answer those until they're resumed. Personal: `ghosty channels wa import <id> --from easybits:<agent-id> --own-number yes\|no --dry-run` (needs `EASYBITS_API_KEY`; prints whether the origin session is alive — if not, pair again instead), or `--from-file F` (EasyBits JSON) or `--from-dir DIR` (Baileys multi-file folder) `--own-number yes\|no --dry-run` (the user turns off EasyBits WITHOUT logout first), then `wa status` |
|
|
194
195
|
| "answer this WhatsApp number" | confirm with the user (real customers), then `ghosty channels whatsapp enable <id> <number> --yes`; `--dry-run` shows the plan |
|
|
196
|
+
| "is my Facebook page answering?", "turn the Messenger page on/off" | `ghosty channels messenger status <id>` (who answers each page, last webhook, token health from Meta); to switch: confirm with the user (real customers), then `ghosty channels messenger on <id> <page> --yes` (`--take` if another agent has it; `--dry-run` first); `off` keeps logging to the board |
|
|
195
197
|
| "save my ElevenLabs / MercadoPago key" | never put the key in a command: ask the user to run `ghosty credentials set <provider>` themselves (hidden prompt), or use `--from-env VAR` |
|
|
196
198
|
| "remove this skill" | `ghosty skills rm <id> <slug> --yes` keeps a local copy and returns `restore`; `ghosty skills get <id> <slug> --out DIR` to back one up first (without `--out` it only lists) |
|
|
197
199
|
| "how much have I used? / am I out of usage?" | `ghosty usage --json` → `plan.name`, `week.pct` / `month.pct` (0–1), `exhausted` |
|
|
@@ -200,7 +202,8 @@ legacy and always `true`.)
|
|
|
200
202
|
| "make the widget look like my site / change its name, avatar, colors, side, suggestions" | Same command, no re-paste needed (the bubble fetches its look): `--title T --subtitle T --avatar <https image>|none --icon chat|avatar|ghost --placeholder T --position right|left --offset X,Y --theme light|dark|auto --bubble-text T --auto-open S|off --starters "a|b"` (≤4 of THEIR suggestions; Ghosty's never show) and `--welcome T` = the first message. Fine style, no free CSS: `--style '{"fontFamily":"Barlow","radius":0,"headerBg":"#2d4a2e","titleUppercase":true,"statusDot":"#c8a96a","panelBg":"#fbf9f4","userBubbleBg":"#2d4a2e","agentBubbleBg":"#f3efe6","sendBg":"#f3efe6","sendArrow":"right","launcherBg":"#2d4a2e"}'` (keys: fontFamily from an allow-list, radius 0–24, headerBg/headerText, titleUppercase, statusDot, headerAvatar, panelBg, userBubbleBg/Text, agentBubbleBg/Text, inputBg, sendBg/sendIcon/sendArrow, launcherBg/launcherIcon, typing bounce|flow|flashing|shimmer + typingColor for the "typing" dots; colors `#rrggbb`; patch per key, null resets one, `--style none` all). "Make the typing dots my brand color" → `--typing-color #rrggbb` (and `--typing flow|flashing|shimmer` to change the animation). Take it from their brand: `--theme-source teams [--workspace SLUG]` or `--theme-source site --site-url <their site>` (imported as editable values). `ghosty agents embed <id> theme --json` exports it; `--style-file theme.json` applies it back. Errors come back as 400 with the reason |
|
|
201
203
|
| "change what the widget says while it thinks / «Me estoy poniendo los lentes» doesn't fit my business / waiting messages" | `ghosty agents embed <id> --copy '{"waking":"Un momento, por favor","connecting":"Abriendo su expediente","thinking":["Revisando su consulta…","Consultando el expediente…"],"stillWorking":"Seguimos revisando su caso","showDuration":false}'` (keys: waking, connecting, thinking = 1–8 that rotate every 4 s, stillWorking (after 90 s), cantStart, interrupted, retryLabel — plain text ≤ 80 chars, no `<>` —, showDuration, showCopyButton true/false). Patch per key, `null` = Ghosty's phrase, `--copy none` all; `--copy-file texts.json`. Also in the card (Channels → Web widget → Advanced → Texts) and `<GhostyWidget copy>` / `useGhostyChat().copy` in React. Match the business tone (a law firm: formal «usted») |
|
|
202
204
|
| "use the widget from React / Next.js / draw my own chat / my design is very custom" | Pick by need: plain site (WordPress/Shopify/HTML) → the `<script>` (`snippet`). React and the usual bubble → `npm i @ghostystudio/widget` + `<GhostyWidget token="emb_…" />` (`ghosty agents embed <id> --json` → `react.install`/`react.code`; props `position`, `offsetX/Y`, `bubbleText`, `open`/`onOpenChange`, `style` = same keys as `--style`). Own UI with the logic solved → `useGhostyChat({ token })` → `{messages, send, stop, status, error}`. Own UI with NO dependency, code they edit (shadcn style) → `ghosty agents embed <id> --out src/components/GhostyChat.tsx` (`.jsx` without types; token + current theme baked as constants; `--force` to overwrite). Headless and `--out` call Ghosty from THEIR page: only works on the widget's `--domains` over https (CORS by exact origin; localhost is rejected) |
|
|
203
|
-
| "what files are in my account?" | `ghosty me files ls [--kind document] --json`; `me files upload <path>`, `me files rm <file-id
|
|
205
|
+
| "what files are in my account?" | `ghosty me files ls [--kind document] --json`; `me files upload <path>`, `me files rm <file-id>[,<file-id>…] --yes` (or `--q <name> --dry-run` first) |
|
|
206
|
+
| "what did I attach / what is left in that conversation's box?" (pool agent) | `ghosty files ls <agent> adjuntos --session <conversation-id> --json`; `ghosty files rm <agent> <path> --session <conversation-id> --yes`. A paused box answers `paused` (it is never woken for this) |
|
|
204
207
|
| "download / export / back up my files", "I want my files like in EasyBits" | `ghosty me files export --dry-run` (how many files and MB per folder), then `ghosty me files export --out <folder>` → `documents/`, `conversations/`, `library/`; rerunning only brings what's new. One file: `ghosty me files get <file-id> --out <path>` |
|
|
205
208
|
| "download / export / back up this database", "give me the table in Excel" | `ghosty dbs export <id> <db>` → `<db>.sqlite` (whole database); one table as CSV: `ghosty dbs export <id> <db> --table <t>` (`--out` to choose the path). On the web: /app/datos?tab=dbs → the database → **.sqlite** / **table.csv** |
|
|
206
209
|
| "use my browser / do it in my Chrome" | install Ghosty for Chrome (https://www.ghosty.studio/chrome), stay signed in to ghosty.studio and open /c: it pairs alone. In personal chats and scheduled tasks the agent gets `browser_*` tools (never in customer channels); never types passwords. Guide: https://www.ghosty.studio/docs/navegador |
|
|
@@ -213,6 +216,7 @@ legacy and always `true`.)
|
|
|
213
216
|
| "who changed this?", "audit log", "what happened to this agent's channels?", "who logged in as whom" | `ghosty audit ls [--workspace slug] [--agent id] [--actor email] [--action agent\|channel\|card\|factory\|workspace] [--since 24h] --json` (staff see all; others only their workspaces/agents) |
|
|
214
217
|
| "why did this run take so long?", "what did run N cost?", "where did @build spend its time?" | `ghosty factory runs show <n> --timing --workspace <slug> --json` (each role's turns with minutes, model, USD; clock split working / waiting for a person / other; commands ≥ 60 s). Long commands without output usually mean a hung test or a missing service in the work box |
|
|
215
218
|
| "why did run N fail / get stuck?", "what should we change so it doesn't happen again?" | `ghosty factory runs why <n> --workspace <slug> --json` (category — `approved_unmet_criterion` first when a plan criterion like "in the preview" was approved without evidence, see `acceptance[]` —, impact, critical step with evidence, typed actions: role_rules → `.ghosty/factory.md`, repo_setup, skill, prompt; `--refresh` redoes it). Stuck patterns per step are in `runs show <n> --timing` |
|
|
219
|
+
| "the run is escalated, what do I pick?", "a or b", "merge it as it is" | `ghosty factory runs choose <n> --workspace <slug>` lists the 2–3 paths @check left (a/b/c with their action); `ghosty factory runs choose <n> <letter> --yes` applies one and the choice reaches the next role word for word. `merge_as_is` merges with red CI that the PR did not cause (logged as `merge_override`): confirm with the user first |
|
|
216
220
|
| "how is the factory doing?", "cost per merged PR", "merge rate" | `ghosty factory runs stats --since 30d [--repo owner/repo] --workspace <slug> --json` |
|
|
217
221
|
| "connect this repo to the factory", "create a factory room", "set up the factory for <repo>" | `ghosty factory rooms connect owner/repo --room <name> --create --workspace <slug> --json` (checks the GitHub App sees it; returns `readiness` = what's missing); `ghosty factory rooms ls --workspace <slug>`; `rooms disconnect … --yes` |
|
|
218
222
|
| "hand this to the factory", "let the factory build it", "delegate this PR", "send it to @plan" | `ghosty factory run "<goal, why, how we know it's done>" --repo owner/repo --wait --workspace <slug> --json` → it returns at `plan_review` with `next` (the commands). Show the user the plan (`runs show <n> --full`) and ask before `runs approve <n> --plan-version N --yes`; then `runs watch <n>` until `pr_review` and ask before `runs merge <n> --yes`. `runs changes <n> --note "…"` sends it back; `runs card <n>` brings the live card down. More in the `ghosty-factory` skill |
|
|
@@ -247,7 +251,7 @@ Read `references/api.md` for exact request/response shapes before calling.
|
|
|
247
251
|
- **Restart is not free**: it cuts a turn in progress. Batch changes, restart once at the end.
|
|
248
252
|
- Files go to the agent's working directory; tell the user the agent can `ls` them. Max 10 MB each.
|
|
249
253
|
- Never print the token back to the user or into logs.
|
|
250
|
-
- **Destructive commands need `--yes`** when you run them (no terminal): `agents rm`, `files rm`, `skills rm`, `credentials rm`, `board archive`, `dbs import` over existing rows, `channels whatsapp enable`, `channels wa groups enable`, `channels whatsapp link|unlink|history`, `channels wa import`, `agents unshare`, `boards move-cards`, `spaces members rm`, `cards reply`, `cards pending --reply`, `factory runs rename`, `factory runs approve|changes|merge`. Confirm with the user BEFORE adding it; prefer `--dry-run` first where it exists.
|
|
254
|
+
- **Destructive commands need `--yes`** when you run them (no terminal): `agents rm`, `files rm`, `skills rm`, `credentials rm`, `board archive`, `dbs import` over existing rows, `channels whatsapp enable`, `channels messenger on`, `channels wa groups enable`, `channels whatsapp link|unlink|history`, `channels wa import`, `agents unshare`, `boards move-cards`, `spaces members rm`, `cards reply`, `cards pending --reply`, `factory runs rename`, `factory runs approve|changes|merge|choose`. Confirm with the user BEFORE adding it; prefer `--dry-run` first where it exists.
|
|
251
255
|
|
|
252
256
|
## Verify
|
|
253
257
|
|