home for all of the looping and chunking work#16
Merged
Conversation
miguelg719
pushed a commit
that referenced
this pull request
Jul 23, 2026
* make server graph service-worker compatible * separate CDP multiplexing from WebSocket transport --------- Co-authored-by: samfinton <samfinton@samfintons-MacBook-Pro.local>
shriyatheunicorn
added a commit
that referenced
this pull request
Jul 23, 2026
… routing + STAGEHAND_V4_SDK_PATH Encodes the nondeterministic-suite cadence as data and wires attribution end to end; makes the v4 SDK location explicit configuration. - benchmarks/: manifest schema and expansion with validity rules (invalid combinations reported with reasons, never dropped silently); v4-vs-playwright manifest; GENERAL_HARNESS design doc; grading- decision README (v3-carried rubric verifier kept deliberately) - framework/runner.ts: project routing - deterministic --sdk runs land in stagehand-v4-deterministic, external-harness and benchmark-matrix runs in stagehand-v4; experiment names and metadata carry the full (benchmark, harness, toolSurface) triple; sdk metadata inferred from the tool surface; v4Sha resolved from the configured checkout - v4SdkLoader.ts: STAGEHAND_V4_SDK_PATH is the sole source of the v4 SDK at runtime. The former link:../../v4-spike dependency (and its lockfile entry) is removed: it broke pnpm install on every fresh clone and CI runner lacking the nested checkout - .v4-sdk-types/: generated SDK declarations are committed so typecheck works without any v4 checkout; regenerated against the SDK's logger- injection (onLog) surface; regenerate when the checkout moves (#16) - initV4.ts: anthropic browser-CORS header via model config (no SDK patch needed); pure buildV4InitParams for browserless unit coverage; systemPrompt passthrough; SDK logs bridged into the eval logger via onLog so they land in Braintrust rows Part of STG-2671
shriyatheunicorn
added a commit
that referenced
this pull request
Jul 23, 2026
… routing + STAGEHAND_V4_SDK_PATH Encodes the nondeterministic-suite cadence as data and wires attribution end to end; makes the v4 SDK location explicit configuration. - benchmarks/: manifest schema and expansion with validity rules (invalid combinations reported with reasons, never dropped silently); v4-vs-playwright manifest; GENERAL_HARNESS design doc; grading- decision README (v3-carried rubric verifier kept deliberately) - framework/runner.ts: project routing - deterministic --sdk runs land in stagehand-v4-deterministic, external-harness and benchmark-matrix runs in stagehand-v4; experiment names and metadata carry the full (benchmark, harness, toolSurface) triple; sdk metadata inferred from the tool surface; v4Sha resolved from the configured checkout - v4SdkLoader.ts: STAGEHAND_V4_SDK_PATH is the sole source of the v4 SDK at runtime. The former link:../../v4-spike dependency (and its lockfile entry) is removed: it broke pnpm install on every fresh clone and CI runner lacking the nested checkout - .v4-sdk-types/: generated SDK declarations are committed so typecheck works without any v4 checkout; regenerated against the SDK's logger- injection (onLog) surface; regenerate when the checkout moves (#16) - initV4.ts: anthropic browser-CORS header via model config (no SDK patch needed); pure buildV4InitParams for browserless unit coverage; systemPrompt passthrough; SDK logs bridged into the eval logger via onLog so they land in Braintrust rows (feature-detected against the loaded SDK's schema - older checkouts without onLog keep working) Part of STG-2671
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.
Why
what changed