Skip to content

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

fixed contradictory done condition

Saurav Panda70472eddd8a5
diff --git a/browser_use/agent/system_prompts/system_prompt.md b/browser_use/agent/system_prompts/system_prompt.md
index 01f065a3b..18124d4d2 100644
--- a/browser_use/agent/system_prompts/system_prompt.md
+++ b/browser_use/agent/system_prompts/system_prompt.md
@@ -106,9 +106,9 @@ The `done` action is your opportunity to terminate and share your findings with
- You are ONLY ALLOWED to call `done` as a single action. Don't call it together with other actions.
- If the user asks for specified format, such as "return JSON with following structure", "return a list of format...", MAKE sure to use the right format in your answer.
- If the user asks for a structured output, your `done` action's schema will be modified. Take this schema into account when solving the task!
-- When you reach 75% of your step budget, critically evaluate whether you can complete the full task.
- If not, immediately save all partial results and call `done` with what you have.
- Partial results are far more valuable than exhausting all steps with nothing saved.
+- When you reach 75% of your step budget, critically evaluate whether you can complete the full task in the remaining steps.
+ If completion is unlikely, shift strategy: save all progress gathered so far to files and focus on the highest-value remaining items.
+ This ensures that when you do call `done` (at max_steps or earlier), you have meaningful partial results to deliver.
- For large multi-item tasks (e.g. "search 50 items"), estimate the per-item cost from the first few items.
If the task will exceed your budget, prioritize the most important items and save results incrementally.
</task_completion_rules>
diff --git a/browser_use/agent/system_prompts/system_prompt_anthropic.md b/browser_use/agent/system_prompts/system_prompt_anthropic.md
index b69559931..3c0c6e6ae 100644
--- a/browser_use/agent/system_prompts/system_prompt_anthropic.md
+++ b/browser_use/agent/system_prompts/system_prompt_anthropic.md
@@ -109,9 +109,9 @@ The `done` action is your opportunity to terminate and share your findings with
- You are ONLY ALLOWED to call `done` as a single action. Don't call it together with other actions.
- If the user asks for specified format, such as "return JSON with following structure", "return a list of format...", MAKE sure to use the right format in your answer.
- If the user asks for a structured output, your `done` action's schema will be modified. Take this schema into account when solving the task!
-- When you reach 75% of your step budget, critically evaluate whether you can complete the full task.
- If not, immediately save all partial results and call `done` with what you have.
- Partial results are far more valuable than exhausting all steps with nothing saved.
+- When you reach 75% of your step budget, critically evaluate whether you can complete the full task in the remaining steps.
+ If completion is unlikely, shift strategy: save all progress gathered so far to files and focus on the highest-value remaining items.
+ This ensures that when you do call `done` (at max_steps or earlier), you have meaningful partial results to deliver.
- For large multi-item tasks (e.g. "search 50 items"), estimate the per-item cost from the first few items.
If the task will exceed your budget, prioritize the most important items and save results incrementally.
</task_completion_rules>
diff --git a/browser_use/agent/system_prompts/system_prompt_anthropic_no_thinking.md b/browser_use/agent/system_prompts/system_prompt_anthropic_no_thinking.md
index 0a3e05a9f..b60cbce35 100644
--- a/browser_use/agent/system_prompts/system_prompt_anthropic_no_thinking.md
+++ b/browser_use/agent/system_prompts/system_prompt_anthropic_no_thinking.md
@@ -109,9 +109,9 @@ The `done` action is your opportunity to terminate and share your findings with
- You are ONLY ALLOWED to call `done` as a single action. Don't call it together with other actions.
- If the user asks for specified format, such as "return JSON with following structure", "return a list of format...", MAKE sure to use the right format in your answer.
- If the user asks for a structured output, your `done` action's schema will be modified. Take this schema into account when solving the task!
-- When you reach 75% of your step budget, critically evaluate whether you can complete the full task.
- If not, immediately save all partial results and call `done` with what you have.
- Partial results are far more valuable than exhausting all steps with nothing saved.
+- When you reach 75% of your step budget, critically evaluate whether you can complete the full task in the remaining steps.
+ If completion is unlikely, shift strategy: save all progress gathered so far to files and focus on the highest-value remaining items.
+ This ensures that when you do call `done` (at max_steps or earlier), you have meaningful partial results to deliver.
- For large multi-item tasks (e.g. "search 50 items"), estimate the per-item cost from the first few items.
If the task will exceed your budget, prioritize the most important items and save results incrementally.
</task_completion_rules>