Conversation
…escription Story 25.1: AI-generated blockquote descriptions (> description) are now recognized as the highest-priority strategy for module descriptions. This enables the upcoming AI-enhanced mode to inject semantic descriptions that parent-level README_AI.md files will automatically pick up. Refs #31 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…ions Story 25.2: New enricher module provides: - extract_symbol_summary(): compact symbol+file name extraction for AI prompt - build_enrich_prompt(): minimal prompt (~200-400 tokens) for one-line description - inject_blockquote(): inject/replace description in README_AI.md header - should_enrich(): only enrich overview/navigation levels, skip detailed/leaf This replaces the old AI-takeover approach with targeted micro-enhancement. Refs #31 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Updated by post-commit hook based on code changes. Update level: full Co-Authored-By: Claude <noreply@anthropic.com>
Story 25.3: Redefines --ai behavior for scan-all: - Phase 1 (unchanged): SmartWriter generates structural README_AI.md - Phase 2 (new): AI enrichment generates one-line functional descriptions for overview/navigation directories and injects as blockquote The new --ai mode: - Only enriches non-leaf directories (overview + navigation levels) - Uses minimal prompts (~200-400 tokens vs 2-5KB previously) - Validates ai_command is configured before starting - Falls back gracefully if AI fails for individual directories - Preserves all structural content from Phase 1 Refs #31 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Updated by post-commit hook based on code changes. Update level: full Co-Authored-By: Claude <noreply@anthropic.com>
- Use extract_summary_from_readme() instead of re-scanning directories - Shorten symbol names (strip ClassName:: prefix) to reduce prompt size - Add parent_name context to build_enrich_prompt() - Add anti-hallucination instruction and bilingual examples - Increase char limit from 20 to 30 for better descriptions - Fix test assertion to match updated prompt wording Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Updated by post-commit hook based on code changes. Update level: affected Co-Authored-By: Claude <noreply@anthropic.com>
scan-all now auto-detects ai_command in config and enables Phase 2 AI enrichment by default. Use --no-ai to opt out. Also refactors post-commit hook to thin wrapper pattern: - Shell script only handles loop guard and venv activation - All logic delegates to `codeindex hooks run post-commit` (Python) - Removes custom AI prompt and git diff injection (fixes #30) - pip upgrade automatically updates hook behavior Refs #31 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Updated by post-commit hook. Update level: full
- Rewrite post-commit hook section with thin wrapper architecture - Add hook upgrade path: pip upgrade auto-updates Python logic - Update SKILL.md with upgrade and troubleshooting guidance - Update CLAUDE.md template best practices with hooks + auto-AI Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Epic 25 (AI-Enhanced Module Descriptions) complete: - Story 25.1: blockquote description support - Story 25.2: AI enrichment module + prompt design - Story 25.3: scan-all auto-AI + --no-ai opt-out - Issue #30: post-commit hook thin wrapper (no more changelog noise) Closes #30, Closes #31 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Epic 25: AI-Enhanced Module Descriptions (v0.23.0) - Blockquote description support in extract_module_description() - AI enrichment module for one-line module descriptions - scan-all auto-detects ai_command, enables Phase 2 automatically - Post-commit hook thin wrapper (fixes #30) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
--aimode from full AI takeover to structural + AI micro-enhancementextract_module_description()blockquote support (Strategy 0, highest priority)enricher.pygenerates one-line functional descriptions per module (~200-400 tokens, 10-20x cheaper)scan-allauto-detectsai_command→ enables Phase 2 automatically;--no-aito opt outcodeindex hooks run post-commit(Python, upgradeable via pip)Test plan
Closes #30, Closes #31
🤖 Generated with Claude Code