@gaiventures/pilotfish-mcp-managed 0.1.33 → 0.1.35

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.
Files changed (3) hide show
  1. package/README.md +12 -3
  2. package/cli.js +1 -1
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -344,6 +344,8 @@ Everyone is in one organization, and its credits pay for every task its people a
344
344
  | `allocation_used` | You've used your (or this key's) allowance, naming the admins to ask | An admin raises the allowance |
345
345
  | `org_limit` | The organization has reached its monthly limit | An admin turns on overage or raises the limit |
346
346
  | `one_session` | You already have a task running | Wait for it to finish, or stop it with `cancel_job` |
347
+ | `queue_full` | Your organization has 50 tasks waiting to start already | Wait for some to start, or stop some with `cancel_job` |
348
+ | `start_rate` | Your organization is starting tasks faster than 60 a minute | Try again after the seconds it gives |
347
349
 
348
350
  `get_usage` shows where you stand: for an admin, the organization's balance and auto reload; for a member, their
349
351
  allowance and whether the organization's credits are fine, low or out; for everyone, this month's spending against
@@ -353,7 +355,7 @@ the monthly limit and spending by category and by model.
353
355
 
354
356
  | Tool | What it does |
355
357
  | --- | --- |
356
- | `browser_task` `{task, start_url?, region?, sites?, login?, accounts?, identity?, credentials?, stealth?, solve?, model?, quality?, max_steps?, pre_approved?, files?, wait?, wait_seconds?}` | Run a whole web task, however many sites and steps. Waits up to `wait_seconds` (default 120 when your client asks for progress updates, else 50) and returns the result with its cost by kind and its project and identity, or the job id if it is still running (it carries on; `get_job` waits again). A call that is cancelled or times out stops waiting and leaves the task running. `wait: false` returns the id at once. `model`: `gpt-6-luna` (the default), `auto` (Haiku does the task, Sonnet checks it), or one model for every step: `opus`, `sonnet`, `haiku`, `gpt-5-mini` or `gpt-5-nano`. `quality` (`auto`, `economy`, `accurate`) instead of one model; `model` wins. `region`: the country to browse from (`"us"`, `"in"`). `start_url`: the page to open first. `sites`: further sites whose saved logins the task may use. `login`: which of your accounts on those sites; `accounts` (`{"linkedin.com": "work"}`, `""` the main one): which account on each site. `identity` (`idn_…`, in a shared project): run as that end user; `credentials` (`["cred_…"]`): which of its saved logins. `stealth` and `solve`: on by default; `false` turns them off for this run. `max_steps`: browser actions across the run. `pre_approved` (`{actions: [pay, delete, send, transfer, cancel], max_amount?, currency?}`): only with the person's say-so, final steps that run without asking. `files`: up to 10 attachments (`{name, type?, data}` in base64, 25 MB each). |
358
+ | `browser_task` `{task, start_url?, region?, sites?, login?, accounts?, identity?, credentials?, stealth?, solve?, model?, max_steps?, pre_approved?, files?, wait?, wait_seconds?}` | Run a whole web task, however many sites and steps. Waits up to `wait_seconds` (default 120 when your client asks for progress updates, else 50) and returns the result with its cost by kind and its project and identity, or the job id if it is still running (it carries on; `get_job` waits again). A call that is cancelled or times out stops waiting and leaves the task running. `wait: false` returns the id at once. `model`: the OpenAI model every step runs on, `gpt-6-luna` (the default), `gpt-5-mini` or `gpt-5-nano`. `region`: the country to browse from (`"us"`, `"in"`). `start_url`: the page to open first. `sites`: further sites whose saved logins the task may use. `login`: which of your accounts on those sites; `accounts` (`{"linkedin.com": "work"}`, `""` the main one): which account on each site. `identity` (`idn_…`, in a shared project): run as that end user; `credentials` (`["cred_…"]`): which of its saved logins. `stealth` and `solve`: on by default; `false` turns them off for this run. `max_steps`: browser actions across the run. `pre_approved` (`{actions: [pay, delete, send, transfer, cancel], max_amount?, currency?}`): only with the person's say-so, final steps that run without asking. `files`: up to 10 attachments (`{name, type?, data}` in base64, 25 MB each). |
357
359
  | `get_job` `{id, wait_seconds?}` | A job's status, its open question with the link to answer it, the result, the cost so far, the live-view link while it runs, and the session's files. `wait_seconds` waits for it to finish or need you first, with progress updates while it waits. |
358
360
  | `get_file` `{id, file_id}` | One of the session's files, attached or downloaded. Up to 5 MB comes back in the result (an image as an image, text as text); larger files are linked in the app. |
359
361
  | `list_jobs` `{status?, limit?}` | Your recent jobs, newest first, with their cost; `[replay]` marks recorded ones. `status`: `queued`, `running`, `needs_input`, `done`, `failed` or `cancelled`. |
@@ -363,10 +365,10 @@ the monthly limit and spending by category and by model.
363
365
  | `message_job` `{id, text}` | Pass on what the person says while a job runs ("take the cheaper one", a detail it asked for), in their words. It reads the message before its next step, and the person's newest words win over the task; sent while the job waits on a question, it answers it. |
364
366
  | `take_control` `{id}` / `hand_back` `{id}` | Pause a running job and get a link to drive its browser yourself, then let it carry on from where you left it. |
365
367
  | `cancel_job` `{id}` | Stop a queued, running or waiting job for good: it can't be resumed, and what it spent stays charged. It is the only way to stop one: a tool call that is cancelled or times out stops waiting, and the job carries on. |
366
- | `get_replay` `{id}` | The job's steps with timings and what got in the way, and a link to its replay video (valid for an hour) when one was recorded. |
368
+ | `get_replay` `{id}` | The job's steps with timings and what got in the way, and a link to its replay video (valid for an hour) when one was recorded. Replay videos are kept 7 days by default (your org's admins can choose 1–30); after that it says the video expired, and the steps are still there. |
367
369
  | `list_saved_tasks` | Your saved tasks: id, name, settings, how often and when they last ran, and what their last run needed. |
368
370
  | `run_saved_task` `{id, extra_instructions?, start_url?, region?, sites?, stealth?, solve?, wait?, wait_seconds?}` | Run a saved task with its saved settings, with optional changes for this run only. |
369
- | `save_task` `{name, task? \| from_job?, start_url?, region?, sites?, login?, accounts?, stealth?, solve?, model?, quality?}` | Save a task to run again here or in the app: give the task and settings, or `from_job` to save a job's task with the settings it ran with. |
371
+ | `save_task` `{name, task? \| from_job?, start_url?, region?, sites?, login?, accounts?, stealth?, solve?, model?}` | Save a task to run again here or in the app: give the task and settings, or `from_job` to save a job's task with the settings it ran with. |
370
372
  | `update_saved_task` `{id, name?, task?, …settings}` | Rename a saved task, change its task, or change only the settings given. |
371
373
  | `delete_saved_task` `{id}` | Delete a saved task. Its past runs stay in your history. |
372
374
  | `delete_session` `{id}` | Delete a session from your history: it no longer shows or opens anywhere; its record and cost are kept for billing. Logins, saved tasks and spending stay. Only with the person's say-so. |
@@ -388,6 +390,13 @@ updates), and your agent waits again with `get_job`. A tool call that is cancell
388
390
  too: `get_job` (or `list_jobs`, for its id) gets it, and only `cancel_job` stops it. A job that needs a person shows the question,
389
391
  a `Question <id>` line saying how to answer it, and the answer link.
390
392
 
393
+ When every browser is busy, a job says `QUEUED`: it starts by itself as one frees up, each organization taking its turn
394
+ (at most 5 tasks running at once per organization while others wait). One that cannot start within 15 minutes ends
395
+ `NOT DONE` with `fleet_busy`: nothing ran and nothing was charged, so send it again. A job interrupted because the
396
+ machine running it stopped or was replaced says `PAUSED` (`machine_lost`, `machine_reclaimed`), as a spend check-in
397
+ does: `follow_up` with the text "Continue" picks it up from where it left off, in a new browser. A job whose machine
398
+ stopped before it did anything on a site starts again by itself, once.
399
+
391
400
  ## Whole tasks or steps?
392
401
 
393
402
  Send the whole web task in one `browser_task`, however many sites and steps it has: "find the cheapest return flight
package/cli.js CHANGED
@@ -15,7 +15,7 @@ import { Client } from "@modelcontextprotocol/sdk/client/index.js";
15
15
  import { isJSONRPCRequest, isJSONRPCResultResponse } from "@modelcontextprotocol/sdk/types.js";
16
16
 
17
17
  // packages/mcp-managed/dist/version.js
18
- var VERSION = true ? "0.1.33" : "0.0.0-dev";
18
+ var VERSION = true ? "0.1.35" : "0.0.0-dev";
19
19
 
20
20
  // packages/mcp-managed/dist/bridge.js
21
21
  var DEFAULT_URL = "https://pilotfish-be.gai.ventures";
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@gaiventures/pilotfish-mcp-managed",
3
- "version": "0.1.33",
3
+ "version": "0.1.35",
4
4
  "description": "Whole browser tasks done in pilotfish's cloud for any MCP agent, signed in with your saved logins. mcprush.com-37c48d491684ec6011385ea5",
5
5
  "license": "MIT",
6
6
  "type": "module",