Merge pull request #2 from LIHUA919/codex/design-experience-loop

docs: design experience-driven research loop

Author: LIHUA919

.gitignore

@@ -49,11 +49,14 @@ examples/*/paper.png
 
 # Non-essential directories (not required for running)
 examples/
-docs/
+docs/*
+!docs/design/
+docs/design/*
+!docs/design/experience-driven-research-loop.md
 paper_db/
 PHASE_2C_COMPLETION_REPORT.md
 PLUGIN_FRAMEWORK_COMPARISON.md
 QUICK_START_IMPLEMENTATION.md
 RESEARCH_DOCUMENTATION_INDEX.md
 TOOL_DISCOVERY_EXECUTIVE_SUMMARY.md
-TOOL_DISCOVERY_RESEARCH.md
+TOOL_DISCOVERY_RESEARCH.md

README.md

@@ -284,6 +284,10 @@ functional test failures.
 4. Promote claims to durable knowledge only after reproducible evaluation.
 5. Measure whether retained experience improves future research decisions.
 
+The implementation contracts, module seams, rollout phases, and acceptance
+criteria are defined in the
+[Experience-Driven Research Loop Design](docs/design/experience-driven-research-loop.md).
+
 The target is not the AI with the longest context window. It is the AI that
 learns the most from experience.