Fix critical issues from code review

Work through a prioritized backlog of 9 critical test and configuration fixes, stopping when all issues are resolved.

prompt
→ Claude
# Ralph Wiggum Loop: Fix Critical Issues from Issue #69 ## Task Address all 9 critical issues identified in the consensus code review for issue #15 improvements (see issue #69). ## Critical Fixes Required ### 1. Fix Payload Size Calculations File : internal/vectorstore/qdrant large payload test.go Create helper function for exact payload sizes: go func generateTestContent(targetBytes int) string { const baseText = "x" return strings.Repeat(baseText, targetBytes) } Update all large payload tests to use exact sizes (500KB, 5MB, 25MB). --- ### 2. Fix Test Race Conditions Files : internal/vectorstore/qdrant test.go , qdrant large payload test.go Replace all hardcoded collection names with unique names: go collectionName := fmt.Sprintf("test lifecycle %d", time.Now().UnixNano()) --- ### 3. Add API Key Configuration File : examples/qdrant-config/prod.yaml Add API key configuration: yaml qdrant: api key: ${QDRANT API KEY:} # Required for Qdrant Cloud Add troubleshooting entry to examples/qdrant-config/README.md for Unauthenticated errors. --- ### 4. Fix Documentation Line Counts Files : docs/QDRANT IMPLEMENTATION.md , d
claude-code

Source: fyrsmithlabs

More testing loops

Kill flaky tests

Loop/loop

Run your test suite repeatedly, collect every intermittent failure, and fix or quarantine flaky tests until you get five consecutive green runs.

prompt
→ Claude
/loop run my test suite 20 times, collect every intermittent failure, fix or quarantine the flaky ones, and don't stop until you get 5 consecutive fully-green runs
testinghigh risk

Ship the release

Loop/goal

Run tests and update changelog until both pass without altering the public API.

prompt
→ Claude
/goal ship the release --success "tests pass and changelog updated" --constraints "do not touch the public API" --mode ordered
testingmedium risk

Get tests green, docs clear

Loop/goalnew

Run tests and polish the README until npm test passes and documentation is complete.

prompt
→ Claude
/goal improve this repository until npm test passes and the README is clear
testinglow risk
Fix critical issues from code review — /ralph for claude-code | looprepo