omp packages

@tduyng/pi-cursor0.0.4

Cursor models in Pi through the official Cursor SDK: one warm agent per session, Pi's own prompt and tools, resumed instead of replayed.

tienduy-nguyen Published 4 hours ago Apache-2.0 ~383 downloads/mo

Untested on omp

This is a pi package. No one has reported whether it works on omp yet. If you try it, add your result below.

Did it work for you?

Result

One report per person. A new report replaces your old one.

Reports 0

No reports yet.

Readme

@tduyng/pi-cursor

Cursor models inside pi, through the official Cursor SDK. The SDK runs the agent loop, and everything above the transport stays pi's: system prompt, tools, approvals, compaction and session tree.

Tools are callbacks, not a server

LocalAgentOptions.customTools registers one in-process callback per tool, and a tool call does not end the Cursor run. The callback waits, pi executes the named tool through its normal pipeline, and the next streamSimple call resolves the callback with the result. The same run continues, so the model sees the result in the same conversation.

The extension switches Cursor's own harness off: AgentOptions.tools: ['mcp'] leaves only pi's custom tools, and local.settingSources: [] drops Cursor's rules, skills and MCP servers. No HTTP MCP server, no Hono server, no tool-name rewriting.

A restart resumes the agent

At the end of every clean turn the extension records the agent id with the working folder, prompt and tool hashes, the pi message count and its own hash of that prefix, in ~/.pi/agent/pi-cursor-agents.json. The next process calls Agent.resume when all of those still match and the pending turn is a single new user message. A stale id, a diverged fork, or a turn killed mid tool round falls back to the replay. The ledger keeps the last 20 sessions.

A message typed while a tool runs goes out with Run.steer, so the model reads it before its next step. Images attached to such a message become a one-line note, because steering carries only text.

Use

/model cursor/gpt-5.5

The provider id is cursor and model ids are Cursor's own. The list comes from Cursor.models.list(), cached after the last successful read in ~/.pi/agent/pi-cursor-models.json at mode 0600 and keyed by the credential. Startup registers the cache with no network call, session start refreshes it, and a small built-in list is the fallback.

A model that offers several context windows is registered once per window: the plain id uses the smallest, and cursor/gpt-5.5@1m asks for 1M. Cursor bills the larger windows as Max Mode, so the small default is the cheap one.

Command Effect
/cursor status Account, fast mode, prompt path, models
/cursor login The SDK browser flow
/cursor logout Removes the stored key and the resume ledger
/cursor models Every registered id, per context window
/cursor fast on|off Cursor's fast parameter on every model that exposes it
/cursor clear Drops the resume ledger

/cursor fast is a billing choice, so it stays off until asked.

Thinking levels map to Cursor model parameters from the live catalog: thinking and effort for Claude models, reasoning for GPT, effort for Grok.

Wire cost

Measured on the account this extension was built on, gpt-5.5 with auto-smart and thinking off:

Call Input tokens Wall time
First call of an agent 11.9k fresh plus 2.6k cached 4.8 to 5.5s
Plain follow-up turn 12.9k fresh plus 12.7k cached 2.2s
Call after a tool round 36.9k fresh plus 36.0k cached 4.4 to 13s

The tool-round number is Cursor's, not the tool result. The SDK re-prefills its own context around the custom tool callback, so one tool call costs about three plain calls. The same 32k fresh appears with an empty working directory, so it is not workspace scanning. Fewer, wider tool calls per turn is the lever that exists.

The extension adds no tool, no prompt block and no schema. What it saves on the wire is the replay: a normal turn sends only the new user message, a tool round sends nothing, and a restarted pi process resumes the same agent.

Install

  • Pi 1.4 or newer.
  • Node 24 or newer.
  • A Cursor account.
  • @cursor/sdk 1.0.40, installed by the workspace as a 25 MB dependency with optional platform packages.
pi install npm:@tduyng/pi-cursor

Local checkout: pi install /path/to/dotfiles/pi/agent/extensions/pi-cursor

No Cursor CLI is installed or called. Login is the SDK browser flow, which mints a stored Cursor key under ~/.cursor/sdk/auth.json:

/cursor login

If the browser does not open, the command prints the URL. CURSOR_API_KEY overrides the stored login, and the key is read by the SDK rather than copied into pi's auth.json.

Cursor bills SDK traffic under its own terms, and this extension cannot tell whether a run is plan-included. Check the Cursor dashboard for the account's SDK usage.

~/.pi/agent/pi-cursor.json holds the two preferences: fast, from /cursor fast, and noSystemPrompt, once Cursor has refused pi's prompt for this account.

Limits

  • Cursor owns the agent loop and its context management, so pi's compaction does not reach inside a live agent.

  • AgentOptions.systemPrompt is server-gated. A rejected prompt comes back as a failed run about 20 seconds in, not from Agent.create, so that turn is retried with the prompt prepended to the first message.

  • The rejection is recorded as noSystemPrompt, and every later agent skips the doomed attempt. The fallback works but spends more tokens, because the Cursor harness prompt remains.

  • A failed run reaches pi as an error message, so an empty answer means a broken transport rather than a silent backend rejection.

  • Usage tokens come from Cursor's turn-ended events plus the run's own total. A message that ends in a tool call shows zero, because that step has not ended server side, and the next message carries both. Pi shows zero money cost because Cursor bills outside pi.

  • A replay replaces earlier images with an [image: mime] placeholder and keeps only the pending message's images, so reattach one to ask about it again after a restart.

  • A model id Cursor no longer serves fails at send, not at selection.

  • A long pi tool run is held open by the Cursor local runtime, and the SDK documents no timeout for custom tools.