@gaiventures/pilotfish-mcp-managed 0.1.18 → 0.1.19
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/README.md +11 -4
- package/cli.js +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -80,8 +80,8 @@ In `~/.codex/config.toml`, through this package:
|
|
|
80
80
|
command = "npx"
|
|
81
81
|
args = ["-y", "@gaiventures/pilotfish-mcp-managed"]
|
|
82
82
|
env = { PILOTFISH_KEY = "pf_YOUR_KEY" }
|
|
83
|
-
# browser_task waits up to
|
|
84
|
-
tool_timeout_sec =
|
|
83
|
+
# browser_task waits up to 120 s for a result (the task carries on); Codex stops a call after 60 s by default.
|
|
84
|
+
tool_timeout_sec = 180
|
|
85
85
|
```
|
|
86
86
|
|
|
87
87
|
### Any client that starts a local server
|
|
@@ -118,14 +118,14 @@ organization. Clients that sign in with OAuth (Claude.ai, Claude Desktop, Claude
|
|
|
118
118
|
|
|
119
119
|
| Tool | What it does |
|
|
120
120
|
| --- | --- |
|
|
121
|
-
| `browser_task` `{task, start_url?, region?, sites?, login?, stealth?, solve?, model?, quality?, max_steps?, pre_approved?, files?, wait?, wait_seconds?}` | Run a whole task as you. Waits for the result (up to `wait_seconds`, default
|
|
121
|
+
| `browser_task` `{task, start_url?, region?, sites?, login?, stealth?, solve?, model?, quality?, max_steps?, pre_approved?, files?, wait?, wait_seconds?}` | Run a whole task as you. Waits for the result (up to `wait_seconds`, default 120; the task carries on after that, and `get_job` waits again), or with `wait: false` returns the job id at once. `model`: `auto` (Haiku does the task, Sonnet checks it), or one model for every step: `opus`, `sonnet`, `haiku`, `gpt-6-luna`, `gpt-5-mini` or `gpt-5-nano`. `region`: the country to browse from. `files`: up to 10 attachments (`{name, type?, data}` in base64, 25 MB each). |
|
|
122
122
|
| `get_job` `{id, wait_seconds?}` | A job's status, open question and its answer link, result, cost so far, live-view link and files. Can wait for the job to finish or need you. A finished job reads `SUCCESS`, `PARTLY DONE` or `NOT DONE`; one that did not pass lists what of the task is done, what is not (with the evidence for each) and why it stopped. |
|
|
123
123
|
| `get_file` `{id, file_id}` | One of the session's files, attached or downloaded. Up to 5 MB comes back in the result; larger files are linked. |
|
|
124
124
|
| `list_jobs` `{status?, limit?}` | Your recent jobs with their cost; `[replay]` marks recorded ones. |
|
|
125
125
|
| `follow_up` `{id, text, model?, files?, wait?}` | Carry on in the same session: same browser while it is kept, same sign-ins, what earlier turns found. |
|
|
126
126
|
| `rerun_job` `{id, wait?}` | Run the same task with the same settings again. |
|
|
127
127
|
| `answer_job` `{id, question_id, answer}` | Answer a job's question: yes, no, done, cancel or text. The id is in the job's `Question …` line, which also says what answer it takes. Codes and passwords go on the answer page, never here. |
|
|
128
|
-
| `message_job` `{id, text}` |
|
|
128
|
+
| `message_job` `{id, text}` | Pass on what the person says while a job runs ("take the cheaper one", a detail it asked for). It reads the message before its next step; the person's newest words win over the task; sent while the job waits on a question, it answers it. |
|
|
129
129
|
| `take_control` `{id}` / `hand_back` `{id}` | Pause a job and get a link to drive its browser yourself, then let it carry on from there. |
|
|
130
130
|
| `cancel_job` `{id}` | Stop a job. Cancelling a tool call that is waiting on a job stops the job too. |
|
|
131
131
|
| `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). |
|
|
@@ -146,6 +146,13 @@ pilotfish searches the web first and answers from what it read, every fact linke
|
|
|
146
146
|
no browser. When the answer needs a site (a fare for a date, a table to book, your own account), the browser starts
|
|
147
147
|
on the site the search found, and a price or availability for particular dates is always read on the site itself.
|
|
148
148
|
|
|
149
|
+
## When the person says more mid-task
|
|
150
|
+
|
|
151
|
+
Your agent reads what the person types only between tool calls, so `browser_task`, `follow_up` and `get_job` return
|
|
152
|
+
within two minutes by default while the task carries on. Anything the person says meanwhile (a correction, a detail,
|
|
153
|
+
the answer to the task's question) goes to the task with `message_job`, in their words, and the agent keeps waiting
|
|
154
|
+
with `get_job`. The task reads it before its next step; sent while it waits on a question, it answers that question.
|
|
155
|
+
|
|
149
156
|
## Whole tasks or steps?
|
|
150
157
|
|
|
151
158
|
Send the whole web task in one `browser_task`, however many sites and steps it has: "find the cheapest return
|
package/cli.js
CHANGED
|
@@ -10,7 +10,7 @@ import { Client } from "@modelcontextprotocol/sdk/client/index.js";
|
|
|
10
10
|
import { isJSONRPCRequest, isJSONRPCResultResponse } from "@modelcontextprotocol/sdk/types.js";
|
|
11
11
|
|
|
12
12
|
// packages/mcp-managed/dist/version.js
|
|
13
|
-
var VERSION = true ? "0.1.
|
|
13
|
+
var VERSION = true ? "0.1.19" : "0.0.0-dev";
|
|
14
14
|
|
|
15
15
|
// packages/mcp-managed/dist/bridge.js
|
|
16
16
|
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.
|
|
3
|
+
"version": "0.1.19",
|
|
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",
|