sheldon/loop-loop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
62 Commits 2 Branches 0 Tags
e4df81fdac841d470900edd05dff3ac766841258
Commit Graph

4 Commits

Author SHA1 Message Date
Sheldon Finlay
60ce0fef54 fix: tighten vague language across all prompt files 
- Remove blanket "write tests" instructions; tests only when
  acceptance criteria require them
- Replace arbitrary "30-50% rejection rate" with clear directive
- Replace "4/5 threshold" with "majority of claims" rule
- List concrete quality gate commands instead of "whatever project uses"
- Remove "learnings" from progress summary (too vague)
- Make error-leak pattern generic (not HTTP-specific)
- Align fix evaluator with updated test expectations
 2026-03-28 11:58:13 -04:00
Sheldon Finlay
80b0f0f4c1 feat: add regression patterns to evaluator implement prompt 
Three new failure patterns: missing imports after refactoring,
orphaned resource instances, and error detail leakage. These were
observed in a real loop run where the evaluator missed them.
 2026-03-28 10:57:44 -04:00
Sheldon Finlay
f3cbfd258c refactor: remove domain-specific language from prompts — fully universal 2026-03-27 14:50:52 -04:00
Sheldon Finlay
17e5eb707f feat: agent loop harness with Claude Code plugin support 
Generator-evaluator architecture with iterative context-reset for
long-running coding tasks. Ships as a Claude Code plugin — install
with /plugin and use /agent-loop:init, /agent-loop:plan, /agent-loop:run.
 2026-03-27 08:03:18 -04:00