refactor(cli): port deterministic actions to V4 - #2526
Draft
shrey150 wants to merge 7 commits into
Draft
Conversation
|
# Conflicts: # packages/cli/src/lib/driver/commands/elements.ts
# Conflicts: # packages/sdk-go/internal/extensionassets/stagehand-extension.zip
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Actionto run deterministically without an LLM while preserving the existing model requirement for natural-language instructionsStagehand.act(Action)so they exercise the V4performUnderstudyMethodpathThis is the next draft in the CLI migration stack and is based on #2525.
CLI contract changes
click/fillsyntax and success JSONclick/fillStagehand.act(Action)without a modelStagehand.act("instruction")without a modelselectupload,cursor,network onnetwork off,network path,network clearE2E Test Matrix
pnpm exec turbo run build --filter=browsepnpm checkbrowse:typecheckpnpm --filter @browserbasehq/stagehand-server test:unitpnpm --filter @browserbasehq/stagehand test:unitBROWSE_DAEMON_DIR=<temp> pnpm --filter browse test:unitgo -C packages/sdk-go run ./internal/extensionpack --check<local fixture>with--local --headless, then click, fill, drag, scroll, evaluate results, and stopmanaged-localmode; click changed the page toclicked, fill returnedhello-v4, drag returneddragged, scroll reached600, and stop succeeded--local --headedclicked,hello-v4-headed,dragged, and600; stop succeededBrowserbase remote smoke coverage and the eval adapter update are intentionally left for the next stacked draft.