Deep-read the browser/computer-use subsystem, write up what's there - #24
Open
nishantkluhera wants to merge 1 commit into
Open
Conversation
Evidence-based coverage from full reads of all nine tools/computer_use files, browser_tool.py, the broker + artifacts pair, cdp tool, and extension router (~8.5k lines), with file:line cites throughout: - computer_use: real action surface (som/vision/ax capture, background- default input ladder, typed cua_browser_* route onto cua-driver's own MCP browser tools); cua-driver is an external Rust binary with a 0.20.0 runtime contract floor; platform gates match the darwin/ win32/linux claim, Linux alpha/X11 and macOS SkyLight caveats noted - broker guess confirmed-with-correction: identity-and-ownership broker over six-field scopes, not a session pool - ambiguity fails closed; artifacts are a one-shot 10MiB/5min SHA-256 byte pipe so payloads never ride the control WebSocket - the Instagram question answered honestly: no storage_state machinery anywhere, but three already-gated mechanisms for persistent authenticated contexts (extension lane / CDP override / camofox managed persistence / cua existing-profile vs isolated_named) Draft placed in mershlab/research/ pending fold-in to the private internal-docs repo. Honest depth ledger included. Closes #3
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Evidence-based coverage from full reads of all nine tools/computer_use files, browser_tool.py, the broker + artifacts pair, cdp tool, and extension router (~8.5k lines), with file:line cites and an honest depth ledger.
Key findings: cua-driver is an external Rust binary with a 0.20.0 runtime contract floor; the broker is an identity-and-ownership broker over six-field scopes (ambiguity fails closed), not a session pool; three already-gated mechanisms exist for persistent authenticated browser contexts - the substrate a social-posting skill would ride.
Draft placed in mershlab/research/ pending fold-in to the private internal-docs repo (no access yet).
Addresses #3
Merge order: merge #23 first, then this.