Reuse history objects before querying the LLM, with LLM fallbackReuse existing history objects whenever they contain the information needed for the current task, instead of querying the LLM again. The history should be checked first and used when a suitable object is available. If no relevant history object exists, or the history does not contain sufficient information, fall back to querying the LLM as it does today. This would reduce redundant LLM calls while preserving the existing behavior as a fallback.

What is the problem that your feature request solves?

Currently, the system may query the LLM again even when the required information is already available in previously generated history objects. This results in unnecessary LLM calls, increasing latency and cost, and potentially producing different results for information that could have been reused directly.

What is your proposed solution?

Reuse existing history objects whenever they contain the information needed for the current task, instead of querying the LLM again. The history should be checked first and used when a suitable object is available. If no relevant history object exists, or the history does not contain sufficient information, fall back to querying the LLM as it does today. This would reduce redundant LLM calls while preserving the existing behavior as a fallback.

What hacks or alternative solutions have you tried to solve the problem?

No response

What version of browser-use are you currently using?

0.11.9

How badly do you want this new feature?

• It's an urgent deal-breaker, I can't live without it
• It's important to add it in the near-mid term future
• It would be nice to add it sometime in the next 2 years
• I'm willing to start a PR to work on this myself
• My company would spend >$5k on Browser-Use Cloud if it solved this reliably for us