could not parse response

TL;DR

What works: If browser-use throws 'could not parse response' against a local model, upgrade browser-use to 0.1.30 and update Ollama.

Steps

1. What was reported:

Issue browser-use/browser-use#349 (closed, 19 comments): ### Bug Description Here , Most of the time it failed sometime at 4 step and sometimes at 15 or 20, but never generated full test script that is executable Can you Please tell me why the most of time it failed. ### Reproduction Steps Just run this python file. ### Code Sample ```python import asyncio import os from dotenv import loaddotenv from langchainaws import ChatBedrock from browseruse import Agent, Controller from browseruse.browser.context import BrowserContext # Load environment variables load_dotenv() response = "" # Initialize Controller and Browser controller = Controller() #...

2. What works:

If browser-use throws 'could not parse response' against a local model, upgrade browser-use to 0.1.30 and update Ollama. The old response handling mis-parsed output from local Qwen models, which one reporter confirmed was the cause.

When to use

You are seeing this: The old response handling mis-parsed output from local Qwen models, which one reporter confirmed was the cause. Use this skill when you run into "could not parse response".

When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

Versions

Versions mentioned in the source: 0.1.30. If you are on something much newer or older, the details may have shifted.

Why this happens

The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.

In the GitHub issue, the reporter asked: could not parse response. The working answer that came out of the thread: If browser-use throws 'could not parse response' against a local model, upgrade browser-use to 0.1.30 and update Ollama. The old response handling mis-parsed output from local Qwen models, which one reporter confirmed was the cause. Source: https://github.com/browser-use/browser-use/issues/349