Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
28 commits
Select commit Hold shift + click to select a range
938a791
benchmakrs added
rishabhraj36 Aug 10, 2026
b7e4d5e
fix: removed missing refs from readme
rishabhraj36 Aug 10, 2026
bfa4d4b
feat(benchmarks): support OpenAI as judge provider
rishabhraj36 Aug 10, 2026
2c5c778
fix: screenshot upload
rishabhraj36 Aug 10, 2026
c861319
Merge branch 'main' into feat/evals
rishabhraj36 Aug 13, 2026
134c8a0
feat: added cost support
rishabhraj36 Aug 13, 2026
712bc99
docs: design benchmark-specific judge prompts
beubax Aug 13, 2026
332db0f
feat(benchmarks): split general and stealth judge prompts
beubax Aug 13, 2026
57fb122
Delete docs/superpowers/specs directory
beubax Aug 13, 2026
c69011f
chore: bump version metadata for 0.7.0 release
beubax Aug 13, 2026
ac8d5fa
Revert "chore: bump version metadata for 0.7.0 release"
beubax Aug 13, 2026
dce482c
feat(benchmarks): expose full Webcmd skill pack to Codex evals
rishabhraj36 Aug 14, 2026
4234b94
Merge remote-tracking branch 'origin/main' into feat/evals
beubax Aug 14, 2026
d7549e7
feat(benchmarks): clarify stealth captcha handling
beubax Aug 14, 2026
0cb090c
Merge remote-tracking branch 'origin/feat/evals' into feat/evals
beubax Aug 14, 2026
317e66c
fix: added support for webcmd browser skills only
rishabhraj36 Aug 14, 2026
268d8b8
feat(benchmarks): run eval attempts in parallel
beubax Aug 14, 2026
9af8437
fix(benchmarks): isolate parallel webcmd sessions
beubax Aug 14, 2026
251f4ef
test(benchmarks): cover parallel webcmd sessions
beubax Aug 14, 2026
3f50d78
pi support (#313)
rishabhraj36 Aug 14, 2026
6cdf4f2
chore(benchmarks): pin webcmd 0.7.1
beubax Aug 14, 2026
59581e0
refactor: disable concurrency in benchmark evaluation and remove inte…
beubax Aug 14, 2026
8d99e67
feat(benchmarks): support Codex subscription evals
beubax Aug 14, 2026
637e4ba
docs(skills): improve browser diff and form guidance
rishabhraj36 Aug 18, 2026
50ad60e
Merge branch 'main' into feat/evals
rishabhraj36 Aug 18, 2026
d63dac2
docs(skills): sync browser skill sources
rishabhraj36 Aug 18, 2026
1667413
Merge branch 'main' into feat/evals
rishabhraj36 Aug 18, 2026
bef4722
docs(skills): refine snapshot diff and QuickJS guidance
rishabhraj36 Aug 18, 2026
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions skill-src/webcmd-browser/SKILL.src.md
Original file line number Diff line number Diff line change
Expand Up @@ -184,13 +184,13 @@ For CAPTCHA or raw user takeover, stop automation, give the user any viewer URL

For native controls, inspect structure first, then use Playwright's normal form APIs inside `run`. Do not guess date formats, option labels, or file constraints from memory; read them from the DOM.

`browser run` uses QuickJS, not Node.js: `Buffer` and `TextEncoder` are unavailable. For an in-memory upload, pass bytes directly:
`browser run` uses QuickJS, not Node.js: `Buffer` is unavailable. For an in-memory upload, pass a `Uint8Array`; encode text with the supported `TextEncoder`:

```js
await page.locator('input[type="file"]').setInputFiles({
name: 'evidence.txt',
mimeType: 'text/plain',
buffer: new Uint8Array([102, 105, 108, 101]),
buffer: new TextEncoder().encode('file'),
});
```

Expand Down
4 changes: 2 additions & 2 deletions skills/webcmd-browser/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -184,13 +184,13 @@ For CAPTCHA or raw user takeover, stop automation, give the user any viewer URL

For native controls, inspect structure first, then use Playwright's normal form APIs inside `run`. Do not guess date formats, option labels, or file constraints from memory; read them from the DOM.

`browser run` uses QuickJS, not Node.js: `Buffer` and `TextEncoder` are unavailable. For an in-memory upload, pass bytes directly:
`browser run` uses QuickJS, not Node.js: `Buffer` is unavailable. For an in-memory upload, pass a `Uint8Array`; encode text with the supported `TextEncoder`:

```js
await page.locator('input[type="file"]').setInputFiles({
name: 'evidence.txt',
mimeType: 'text/plain',
buffer: new Uint8Array([102, 105, 108, 101]),
buffer: new TextEncoder().encode('file'),
});
```

Expand Down
1 change: 1 addition & 0 deletions src/browser/run/runner.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,8 @@
type Page,
} from 'playwright-core';
import { LocalBrowserRunArtifactSink } from './artifacts.js';
import { MemorySnapshotBaselineStore } from '../snapshot/index.js';

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (windows-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (windows-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (macos-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (macos-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (ubuntu-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (ubuntu-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (ubuntu-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (ubuntu-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (windows-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (windows-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (macos-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (macos-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 22 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / audit

Duplicate identifier 'MemorySnapshotBaselineStore'.
import { MemorySnapshotBaselineStore } from '../snapshot/index.js';

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (windows-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (windows-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (macos-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (macos-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (ubuntu-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (ubuntu-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (ubuntu-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (ubuntu-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (windows-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (windows-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (macos-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / Build (macos-latest)

Duplicate identifier 'MemorySnapshotBaselineStore'.

Check failure on line 23 in src/browser/run/runner.test.ts

View workflow job for this annotation

GitHub Actions / audit

Duplicate identifier 'MemorySnapshotBaselineStore'.
import { unsupportedApiMessage } from './playwright-transport.js';
import { QuickJSHost } from './quickjs-host.js';
import { runBrowserProgram } from './runner.js';
Expand Down
Loading