agent/Understand-Anything
2
0
Fork 0
mirror of https://github.com/Egonex-AI/Understand-Anything.git synced 2026-06-22 10:58:03 +08:00
Code Issues Packages Projects Releases Wiki Activity
570 Commits 2 Branches 7 Tags
09ede1917ffd043e6d5bbc8a80b45760814c2d7f
Commit Graph
10 Commits
Author SHA1 Message Date
chienvon 7254852f4a sync egonex organization metadata 2026-06-09 14:26:48 -07:00
Bozheng LongandClaude Opus 4.8 55d0ab2336 docs: design + implementation plan for language auto-detection 
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-03 21:19:52 +08:00
Yuxiang LinandGitHub a59a573a1d Merge pull request #204 from Lum1104/feat/semantic-batching-and-output-chunking 
fix(#159): semantic batching + bundled importMap + Phase 1 speedup
 2026-05-24 20:12:14 +08:00
Lum1104andClaude Opus 4.7 5d11a6bfdc docs(spec+plan): fix-up — rename KnowledgeGraph* types, correct §2 thresholds 
Task 2 implementation surfaced inconsistencies between the spec/plan
and the actual codebase:
- The real type exports are GraphNode / GraphEdge, not KnowledgeGraph*
- Folder grouping uses bucket count (folders + rooted) not just folder
  count, with threshold < 2 instead of < 3
- Concentration threshold is > 70% (was > 60%) so 2/3 distributions
  stay in folder mode
- Single-child suppression is gated by layer total ≥ 3 to avoid
  emptying tiny layers
- Removed the "layer < 8 → flat" rule; the algorithm is now uniform
  and small layers fall through naturally via single-child suppression

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-03 15:51:28 +08:00
Lum1104andClaude Opus 4.7 fec05f6278 docs(plan): graph layout scaling — implementation tasks 
17-task plan for the dashboard layout migration: dependencies + vitest,
container derivation (folder + Louvain), edge aggregation, ELK repair
pipeline, store extensions, ContainerNode component, per-view migration,
Stage 2 lazy expansion, auto-expand triggers, visual overlays, size
deviation re-layout, banner integration, and perf benchmarks.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-03 10:37:18 +08:00
Lum1104andClaude Opus 4.7 92ee9e3dbb docs: point homepage links at understand-anything.com 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-19 12:33:42 +08:00
Lum1104andClaude Opus 4.6 b2fb97b884 docs: add implementation plan for multi-language tree-sitter extractor architecture 
Plan covers: LanguageExtractor interface, per-language extractors for 8 languages
(Python, Go, Rust, Java, Ruby, PHP, C/C++, C#), bundled extract-structure.mjs
script replacing LLM-generated regex in file-analyzer agent, and PluginRegistry
enhancements.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-15 18:01:57 +08:00
Lum1104andClaude Opus 4.6 c077623389 docs: add .understandignore implementation plan (7 tasks) 
TDD-driven plan covering IgnoreFilter module, IgnoreGenerator, core exports,
project-scanner agent update, and skill Phase 0.5 integration.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-10 11:27:47 +08:00
Lum1104andClaude Opus 4.6 b3acd5b1d2 docs: reorganize docs/ into superpowers/specs/ and superpowers/plans/ 
Move all design docs to docs/superpowers/specs/ and all implementation
plans to docs/superpowers/plans/ for consistent organization.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-09 23:11:44 +08:00
Lum1104andClaude Opus 4.6 7c999602bf docs: add /understand-knowledge implementation plan (14 tasks) 
Detailed step-by-step plan covering core type extensions, schema validation,
dashboard changes (CSS, store, sidebar, reading panel, edge styling, layout),
agent definitions, format guides, and skill definition.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-09 23:06:32 +08:00