Skip to content
View nancy6547's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report nancy6547

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
nancy6547/README.md

Nancy Singh

I work on browser testing tools and LLM reliability (open to work). 2026 CS graduate, Delhi.

Open source

10 PRs merged: 8 into Google's Puppeteer and Chrome DevTools MCP, 1 into Hugging Face, 1 into Confident AI's DeepEval, plus bugs I found in Microsoft Playwright, Twenty and Documenso that their teams fixed.

  • Puppeteer · #15587 WebSocket handshake timeout · #15590 setGeolocation(null) clears the override · #15595 respond() skips undefined headers on CDP · #15697 BiDi respond()/abort() no longer reject for gone requests
  • Chrome DevTools MCP · #3144 · #3148 · #3198 · #3199 console, network and Lighthouse fixes
  • sentence-transformers · #4204 PListMLE custom rank discount received a mask instead of ranks
  • DeepEval · #3470 JSON dataset loader crashed on null tools_called/expected_tools (reported as #3469)
  • Playwright · reported #43459, a codegen escaping bug, fixed in #43472
  • Documenso · reported #3445, ~26 redundant waitForTimeout calls (~27.5 s of fixed sleep) found by parsing the E2E suite with the TypeScript Compiler API, fixed in #3536
  • XERJ Corpus Hub · my #3199 fix is indexed as a contributor corpus, a reference library AI coding agents search before writing code
  • Twenty · reported #28342, Links field dropping slashes in query/hash, fixed in #28421

Projects

Junban Finds the API response order that breaks a flaky Playwright test. Caught 6/6 rare races by run 5; 3,000 plain reruns caught only 2/6.
Zeitaku Replaces hard-coded sleeps in Playwright tests with network-aware waits over CDP. Built after the Documenso #3445 analysis.
HalluGuard Flags RAG answer sentences their sources don't support, using an NLI cross-encoder.
Kensa Metamorphic testing for RAG apps.
DocMind Question answering over PDFs, scanned ones included, with hybrid search.
Attention-Guard Learns your personal "drifting" pattern from activity and 20-minute check-ins, and nudges you when focus slips. Runs fully on-device.

TypeScript · Python · Playwright · Chrome DevTools Protocol · PyTorch

Writing: I keep building tools that catch software lying about whether it works

nancy6547.github.io · LinkedIn · X · Medium · singhnancy2004@gmail.com

Pinned Loading

  1. zeitaku zeitaku Public

    Finds hard-coded sleeps in Playwright tests and replaces them with network-aware waits, automatically (TypeScript Compiler API + CDP).

    TypeScript 1

  2. docmind docmind Public

    Ask questions about any PDF, including scanned ones. Hybrid retrieval, answers only from the document, every sentence verified with HalluGuard.

    Python

  3. junban junban Public

    Finds the network response order that breaks a flaky Playwright test and writes a repro that fails every time (CDP Fetch + delta debugging).

    TypeScript

  4. puppeteer/puppeteer puppeteer/puppeteer Public

    JavaScript API for Chrome and Firefox

    TypeScript 95.8k 9.6k

  5. halluguard halluguard Public

    Flags sentences in a RAG answer that its sources don't support, using sentence-level NLI with the backing passage. Evaluated on RAGTruth.

    Python

  6. attention-guard attention-guard Public

    Python 2