Boost in OptiQ Code

Boost lets a cloud model lead a task in OptiQ Code while your local model does the reading, searching and test runs as its helper.

Type /boost before a hard task. From the next task the cloud model leads and your local model is its local tool; /boost again turns it off. Boost runs on GLM 5.3 Flash unless you pick another model: /boost deepseek-v4.1-flash picks one and /boost off stops it.

/boost
add retry with backoff to the HTTP client and make the tests pass

To have it on from the start, set boost_mode to lead in your OptiQ Code config (or OPTIQ_BOOST_MODE=lead); boost_model picks the model.

The local tool runs your local model in a fresh context on the same repository. The cloud model sends it work it can describe in a sentence: read files and answer a question, run the tests and report the failures, make an edit it has specified. Only the short answer goes back to the cloud. If the cloud cannot answer, the task carries on with your local model. The run summary shows what it cost:

tokens: 61,240 in / 1,830 out  ·  48,112 cached (79% of in)  ·  OptiQ Cloud $0.0062 · $1.99 left
local tool (Qwen3.6-35B-A3B): 2 calls, 14 turns, 210,512 in / 4,230 out