What's New in Proxima 5.5.0

Proxima 5.5.0 (October 2026) changes how you pick models, how you control reasoning, and how clients find the local gateway. This page lists what is new, what changed under the hood, and what to check when you upgrade from 5.0.0. It is based on the project's CHANGELOG and migration notes, and on reading the 5.5.0 source for the details below.

Short version: your editors, aliases such as claude or chatgpt, and the privacy model are unchanged. What you should do after upgrading is stop hard-coding model names, let scripts find the REST port automatically, and re-check your editor's tool list (41 tools now).

Highlights

Live model discovery

In 5.0.0, clients relied on fixed model aliases. Which models you could actually use depends on your account (a free ChatGPT login and a Team workspace expose different models), so a hard-coded name could fail in confusing ways or end up answered by a different model than you asked for.

5.5.0 asks the accounts you are logged into, and your BYOK configuration, what is available right now:

  • ChatGPT: models are discovered from the logged-in account, so what you see follows your plan (Free, Plus, Team or Enterprise).
  • Gemini: routes to engines such as gemini:flash, gemini:pro, gemini:argon and gemini:latest, and keeps memory separate per account.
  • Each model is reported with its availability, capability tags (Fast, Reasoning, Pro) and instructions for using it.

Where to get the list

MCP tool list_available_models (refresh: true forces a live re-check) MCP resource proxima://models REST GET /v1/models CLI proxima models JavaScript await ai.getModels() Python ai.get_models()

No more silent substitution

If you explicitly ask for a model your account does not have, Proxima now returns an error that tells you to call list_available_models. It does not quietly answer with a different model. The core aliases auto, claude, chatgpt, gemini and perplexity keep working exactly as before.

Thinking-depth controls

You can now choose how much reasoning a model spends on a request. Two parameters are accepted:

thinking_level default | low | medium | high reasoning_effort none | default | auto | low | medium | high (OpenAI-compatible name)

They work in the MCP tools ask_gemini and ask_model, in the REST API and WebSocket, in the Python and JavaScript SDKs, in the CLI as --thinking, and in the Agent web UI and desktop chat widget.

curl http://localhost:3210/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{"model": "gemini", "message": "Check the complexity of this algorithm", "thinking_level": "high"}' proxima ask gemini "Check the complexity of this algorithm" --thinking high

The REST API validates the values. If you send thinking_level and reasoning_effort together with contradictory meanings, or ask for an option the model does not support, the reply is HTTP 400 rather than a guess.

Cancelling a request

Before 5.5.0, a request you abandoned kept running and held up the next request to the same provider. Now you can stop it:

curl -X POST http://localhost:3210/v1/cancel \ -H "Content-Type: application/json" \ -d '{"provider": "gemini"}'

The provider field is optional. The reply is {"success": true, "cancelled": true}. Cancellation is handled across MCP, REST and WebSocket, and a client that disconnects mid-request on a single-provider call also cancels it.

Automatic port discovery

The REST and WebSocket gateway still starts on port 3210. In 5.0.0, if another program already used that port, the gateway failed to start and clients could not connect. In 5.5.0 Proxima tries the following ports (up to 20 attempts) and writes the port it actually bound to a small file, rest-port.json:

Windows %APPDATA%\Proxima\rest-port.json macOS ~/Library/Application Support/Proxima/rest-port.json Linux ~/.config/Proxima/rest-port.json (or $XDG_CONFIG_HOME/Proxima/rest-port.json)

The official Python SDK, JavaScript SDK, CLI and Agent read this file on their own. For curl scripts and third-party OpenAI-compatible clients, keep using http://localhost:3210, or read the live port from GET /api/status. You can also start from another port by setting PROXIMA_REST_PORT.

The MCP bridge to the desktop app (default 19222) follows the same idea: it scans a small range of nearby ports, and AGENT_HUB_PORT overrides the starting value. The REST API is still switched on from Settings; discovery only changes which port it uses.

Battle Mode and the chat widget

The interactive documentation served at http://localhost:3210 includes a live chat widget. It now fills its model list from your active sessions, shows capability badges, and shows a thinking-depth selector when you pick a reasoning model. Battle Mode sends the same prompt to two or more models and shows their answers side by side, with a status and timing for each cell, so you can compare providers on your own prompts.

JavaScript SDK as an ES module

The JavaScript SDK used to be a single CommonJS file. It now has its own package.json and a native ES module entry (proxima.mjs), so both styles work:

// ES module import { Proxima } from 'proxima-sdk'; // CommonJS const { Proxima } = require('proxima-sdk'); const ai = new Proxima(); // finds the port via rest-port.json const res = await ai.chat("Hello", { model: "gemini", thinking_level: "low" }); console.log(res.text, await ai.getModels());

Other changes and fixes

  • Gemini multi-turn: fixed follow-up conversations that stalled or were cut off early across Gemini engines.
  • Conversation isolation: new_conversation now clears both the active and the MCP session context, so one turn no longer bleeds into the next.
  • DuckDuckGo search: ddg_search was refactored into a reusable utility that detects rate limits and bot challenges.
  • Python check: the app now validates the Python version and the required agent modules before launching the agent, instead of only finding an interpreter.
  • Agent retries: terminal provider failures are treated as non-retryable, which avoids pointless retry loops.
  • CLI and SDKs: consistent ESM and CommonJS imports, normalized /v1 endpoint handling, and better handling of piped standard input.
  • Platforms: application data paths are resolved the same way on every OS, and the startup health check is more tolerant.

Upgrade checklist (5.0.0 to 5.5.0)

AreaWhat changedDo you need to act?
Core aliasesclaude, chatgpt, gemini, perplexity, autoNo. They still work.
Explicit model namesHard-coded names such as gemini:3.5-flash are replaced by discovered slugs such as gemini:flash or gemini:argonYes, if you pinned one. Run list_available_models and update the name.
Port3210 by default, with automatic fallbackOnly if a script hard-codes a non-standard port. Official clients need nothing.
MCP tool list41 tools (list_available_models added) and a proxima://models resourceRe-open your editor's MCP tool list in Cursor, Windsurf or Claude Desktop so it picks up the new tool.
JavaScript SDKESM entry and package.json addedNo. Existing require calls keep working.
Agent web consoleFastAPI server on port 8500No. Open it from the Agent tab or run proxima-agent web.

Steps

1 Install 5.5.0 from the releases page, or pull the repository and run npm install.
2 Start Proxima and confirm the version: proxima status prints it, and so does the proxima://status MCP resource.
3 Restart your editor, or reload its MCP servers, then check that 41 tools are listed.
4 Run proxima models (or call list_available_models) and replace any pinned model names in your scripts and prompts.
5 If you call the REST API from your own code, either use an official client or read the port from GET /api/status.

If something does not behave as described here, the troubleshooting guide covers the common cases, and the documentation and CLI and SDK reference describe each interface in full.