fix(browser): add full_page parameter to browser_vision for viewport-only screenshots - #19647
Open
liuhao1024 wants to merge 3 commits into
Open
liuhao1024 wants to merge 3 commits into
liuhao1024 wants to merge 3 commits into
Conversation
…INSTALL_TIMEOUT Increase the default npm install timeout for WhatsApp bridge from 60s to 300s (5 minutes) to accommodate slower systems like Unraid NAS. Make it configurable via WHATSAPP_NPM_INSTALL_TIMEOUT environment variable for users who need even longer timeouts. Closes NousResearch#14980
- Add 'path', 'old_string', 'new_string', and 'patch' to required list - Update description to clarify mode-specific parameter requirements - This addresses issue where LLMs would omit these parameters because they were not marked as required in the schema, even though they are required depending on the mode Fixes NousResearch#15524
…only screenshots browser_vision unconditionally passed --full to the screenshot command, capturing the entire scrollable page. On long pages (e.g. 10,000+ px), this produces enormous PNGs that vision APIs downscale to unreadable smears. Add a full_page parameter (default True for backward compatibility) that controls whether --full is passed. Setting full_page=False captures only the current viewport, producing crisp, manageable screenshots. Fixes NousResearch#19620
liuhao1024
force-pushed
the
fix/issue-19620-browser-vision-full-page
branch
from
May 4, 2026 10:13
75fc362 to
481e8b3
Compare
23 tasks
Collaborator
|
Thanks for isolating a real browser-vision failure: current Problems
Suggested changes
Automated hermes-sweeper review. |
This was referenced Aug 3, 2026
Open
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Adds a
full_pageparameter tobrowser_visionthat controls whether the screenshot captures the full scrollable page or just the current viewport.Root Cause
browser_visionunconditionally appended--fullto theagent-browser screenshotcommand (line 2167 oftools/browser_tool.py). On long pages (e.g.bodyHeight ≈ 10,000 px), this produces enormous PNGs (~41k px height) that vision APIs downscale to unreadable smears. The model then reports "highly compressed, low-resolution, corrupted image" and refuses to extract data.Related Issue
N/A
Type of Change
Changes Made
How to Test
pytest tests/ -q— all tests should passChecklist
Code
fix(scope):,feat(scope):, etc.)pytest tests/ -qand all tests passDocumentation & Housekeeping
docs/, docstrings) — or N/Acli-config.yaml.exampleif I added/changed config keys — or N/ACONTRIBUTING.mdorAGENTS.mdif I changed architecture and workflows — or N/A