docs(research): add LLM instruction architecture entries 24-27#62
Merged
docs(research): add LLM instruction architecture entries 24-27#62
Conversation
…le: blocks - Replace folder-per-feature with one .feature file per feature - User stories are now Rule: blocks; ACs are Example: blocks under each Rule - Discovery content embedded in feature description free text - Test layout: tests/features/<feature-name>/<rule-slug>_test.py - Function naming: test_<rule_slug>_<id_hex>() - Rewrite gen_test_stubs.py to parse Rule: blocks (one test file per Rule) - Update gen_todo.py to find .feature files directly in in-progress/ - Update all skills: scope, tdd, implementation, verify, session-workflow - Add mandatory Self-Declaration block in TODO.md at SELF-DECLARE phase - Enforce Hypothesis @given + @pytest.mark.slow on all tests/unit/ tests - Migrate completed/display-version to new single-file format - Clarify OC-8: fix must produce a new named class, no workarounds
…s, fix gen_test_stubs duplicate detection - Rewrite developer.md, product-owner.md, reviewer.md as thin routing scripts (~60 lines each, down from ~150) - Remove duplicated workflow details, principle lists, and path specs from agent files - Fix stale folder-based paths in developer.md and product-owner.md (v4.1 restructure) - Fix product-owner.md Phase 3 description (one .feature file with Rule: blocks, not one per story) - Fix reviewer.md report template using <story> instead of <rule_slug> - Consolidate Self-Declaration checklist in session-workflow/SKILL.md to reference implementation/SKILL.md - Fix gen_test_stubs.py find_duplicate_ids() false positives: use set instead of list so the same feature in multiple stage dirs (completed + in-progress) does not trigger spurious warnings
Replace the hard rule that tests/unit/ must use @given with guidance: use Hypothesis for properties spanning many inputs, plain pytest for specific behaviors or single edge cases. @pytest.mark.slow remains mandatory on all @given-decorated tests. Affected files: AGENTS.md, tdd/SKILL.md, implementation/SKILL.md, verify/SKILL.md
…ntries Add entries 24-27 covering instruction conflict resolution failure, positional attention degradation, modular prompt de-duplication, and the three-file agent architecture split. Amend entry 23 status to reflect RAG extrapolation caveat. Add bibliography entries 27-31.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
docs/academic_research.mdcovering the empirical and inferred foundations of the three-file agent architecture split