111 Commits

This Branch

This Branch

All Branches

• Merge pull request #13 from Lum1104/feat/language-agnostic-support

  feat: language-agnostic support for 12 languages

  Yuxiang Lin · 2026-03-23 20:43:55 +08:00
  9805f9fcb3
• Merge pull request #26 from Lum1104/refactor/unify-skills-install

  refactor: unify skills install method across all platforms

  Yuxiang Lin · 2026-03-23 20:30:20 +08:00
  b3af2c97b7
• refactor: unify skills install method across all platforms

  Replace platform-specific install approaches with a consistent
  per-skill symlink pattern for OpenCode and Codex (both share
  ~/.agents/skills/), matching the OpenCode docs requirement of
  <name>/SKILL.md discovery.
  
  Changes:
  - OpenCode: migrate from opencode.json plugin config to direct
    skill symlinks in ~/.agents/skills/<name>/
  - Codex: replace broken bundle symlink (understand-anything/ had
    no SKILL.md at root) with individual per-skill symlinks, matching
    OpenCode exactly
  - All platforms: add universal ~/.understand-anything-plugin symlink
    so understand-dashboard SKILL.md can reliably find packages/dashboard/
  - All platforms: use idempotent [ -e ] || [ -L ] || ln -s guard to
    handle multi-platform installs on the same machine
  - All platforms: use ln -sf and rm -f for robust re-installs and
    partial uninstalls
  - understand-dashboard/SKILL.md: replace fragile dirname-based path
    resolution with a prioritized candidate loop with explicit error
    guard
  - Remove orphaned .opencode/plugins/understand-anything.js and its
    build scaffolding
  - Update all three README variants (en, zh-CN, ja-JP) to reflect
    new OpenCode AI-driven install method
  
  Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-23 16:41:29 +08:00
  c8d92444e2
• Merge pull request #24 from eltociear/add-ja-doc

  docs: add Japanese README

  Yuxiang Lin · 2026-03-23 11:38:54 +08:00
  d539fd45ba
• docs: add Japanese README
  Ikko Ashimine · 2026-03-23 12:33:59 +09:00
  1aa29897b2
• Merge pull request #17 from Lum1104/fix/opencode-plugin-discovery

  fix: OpenCode plugin not discovering skills

  Yuxiang Lin · 2026-03-23 08:15:43 +08:00
  d8e95e1b82
• fix: OpenCode plugin not discovering skills (#16)

  OpenCode installs the repo via git and looks at the root for the plugin
  entry point. Our skills/agents live inside understand-anything-plugin/,
  so OpenCode couldn't find them.
  
  - Add .opencode/plugins/understand-anything.js that uses the config hook
    to inject understand-anything-plugin/skills/ into skills.paths
  - Add "main" field to root package.json pointing to the plugin entry
  - Update INSTALL.md with version pinning and troubleshooting sections
  
  Closes #16
  
  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-22 23:10:23 +08:00
  c7f564a60e
• docs: add language-agnostic implementation plan

  15-task TDD plan covering LanguageConfig types, LanguageRegistry,
  12 language configs, GenericTreeSitterPlugin, prompt snippets,
  and migration from TS-only TreeSitterPlugin.
  
  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-21 23:38:40 +08:00
  87c07a61d8
• docs: add language-agnostic support design document

  Design for making Understand-Anything language-agnostic instead of
  TypeScript-heavy. Covers LanguageConfig registry, GenericTreeSitterPlugin,
  language-aware prompts, and support for 12 languages.
  
  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-21 23:38:40 +08:00
  d7d3925463
• chore: bump version to 1.1.1

  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-21 23:08:56 +08:00
  8134bb95ca
• fix: add zoom limits and auto-center for large graphs

  - Set minZoom to 0.01 so fit-view works on graphs with hundreds of nodes
  - Add TourFitView to pan/zoom to highlighted nodes during guided tours
  - Add SelectedNodeFitView to center graph on node selected via search
  - Wrap GraphView in ReactFlowProvider to enable useReactFlow() hooks
  
  Thanks to @blackboxaicode for the insight on these improvements.
  
  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-21 23:07:58 +08:00
  7c638603c0
• fix: consolidate triple normalization into ordered Phase 4/5 steps

  The original commit 9fe003a introduced normalization logic in three
  separate places (Phase 4 inline, Phase 5 inline, Phase 5.5), creating
  an ordering conflict where "do not use field X" rules appeared before
  "convert field X to field Y" rules. An LLM following instructions
  sequentially could drop legacy fields before converting them.
  
  - Consolidate all layer normalization into Phase 4 as ordered steps
  - Consolidate all tour normalization into Phase 5 as ordered steps
  - Remove redundant Phase 5.5 entirely
  - Fix misleading "from current prompt" comments about envelope format
  - Add defensive handling for nodes-as-objects edge case
  - Wrap JSON examples in arrays for visual consistency with prompts
  
  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-21 22:59:36 +08:00
  b8e605eafb
• fix: ensure core is built before launching dashboard in /understand-dashboard

  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-21 22:25:21 +08:00
  de66bb7d76
• docs: improve CLAUDE.md with prerequisites, lint command, and gotchas

  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-21 22:23:48 +08:00
  922cc32a13
• fix: update Antigravity skills install path to ~/.gemini/antigravity/skills/
  Lum1104 · 2026-03-21 22:15:39 +08:00
  54fc8d44c2
• Merge pull request #12 from longvv/main

  feat: add Antigravity installation guide and update README with compa…

  Yuxiang Lin · 2026-03-21 20:49:37 +08:00
  dfac994497
• feat: add Antigravity installation guide and update README with compatibility information.
  longvv · 2026-03-21 16:33:07 +07:00
  18c0fcd9eb
• docs: thanks
  Lum1104 · 2026-03-20 19:16:47 +08:00
  9866fccae9
• Merge pull request #9 from Jamie-HM/docs/add-zh-cn-readme

  Add Chinese language support

  Yuxiang Lin · 2026-03-20 12:58:29 +08:00
  17d796309d
• Add Chinese language support V1.1
  Jamie-HM · 2026-03-20 12:49:03 +08:00
  366c0b9403
• Add Chinese language support
  Jamie-HM · 2026-03-20 12:23:51 +08:00
  a38843d57e
• Merge pull request #6 from Lum1104/feature/multi-platform-simple

  feat: add multi-platform support for Understand-Anything

  Yuxiang Lin · 2026-03-20 00:14:51 +08:00
  f0264e6ec2
• feat: Align understand skill outputs with dashboard graph schema better
  Lum1104 · 2026-03-20 00:14:23 +08:00
  9fe003a977
• docs: add star history and bump version to 1.1.0
  Lum1104 · 2026-03-19 23:48:26 +08:00
  54259f3b86
• docs: add Windows PowerShell instructions to OpenClaw INSTALL.md

  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-19 23:30:43 +08:00
  e237eba20c
• docs: update multi-platform URLs after moving configs to root

  Update raw GitHub URLs in README to remove understand-anything-plugin/
  prefix for Codex and OpenClaw INSTALL.md paths. Replace Cursor section
  with auto-discovery via .cursor-plugin/plugin.json.
  
  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-19 23:18:42 +08:00
  fb46373cef
• feat: add Cursor and Claude plugin descriptors for auto-discovery

  Add .cursor-plugin/plugin.json with skills/agents paths pointing into
  understand-anything-plugin/. Add .claude-plugin/plugin.json alongside
  existing marketplace.json.
  
  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-19 23:16:43 +08:00
  8b5499e8db
• refactor: move platform config directories to repo root for discovery

  Move .codex/, .opencode/, .openclaw/ from understand-anything-plugin/ to
  repo root so each AI coding platform discovers its config at the standard
  location. Delete .cursor/ (replaced by .cursor-plugin/plugin.json in next
  commit). Plugin source code stays inside understand-anything-plugin/.
  
  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-19 23:15:00 +08:00
  0f2b710992
• docs: revise implementation plan — minimal restructure, move platform configs to root

  Replace full flatten approach with minimal restructure: only move platform
  config directories (.codex, .opencode, .openclaw) to repo root for discovery.
  Add Cursor/Claude plugin descriptors. Remove Gemini extension. Keep all
  plugin source code inside understand-anything-plugin/.
  
  Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

  Lum1104 · 2026-03-19 23:10:23 +08:00
  2779408569
• fix: address code review feedback — terminology consistency and URL path

  - Replace "agent" with "subagent" in SKILL.md dispatch references (5 locations)
  - Add node_modules/.git/dist exclusions to Phase 0 find command
  - Fix design doc URL to include understand-anything-plugin/ prefix
  
  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-19 11:18:39 +08:00
  4ea55cd6fc
• feat: add per-platform INSTALL.md for AI-driven installation

  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-19 10:51:43 +08:00
  aa4df6e987
• docs: add multi-platform installation instructions to README

  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-19 10:51:25 +08:00
  8e3c0660c9
• refactor: update SKILL.md to dispatch subagents with context injection

  Replace all named agent dispatches (project-scanner, file-analyzer,
  architecture-analyzer, tour-builder, graph-reviewer) with subagent
  dispatches using prompt template files. Add context injection for each
  phase including README content, package manifest, directory tree,
  framework-specific guidance, and cross-validation data.
  
  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-19 10:35:38 +08:00
  2a01d3cc77
• feat: add knowledge-graph-guide agent for graph navigation and querying

  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-19 10:32:03 +08:00
  84d0462e20
• refactor: move pipeline agents into skills/understand/ as prompt templates

  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-19 10:31:22 +08:00
  5e85a23aa2
• docs: add context injection to implementation plan

  Each subagent dispatch now injects relevant context from the main session:
  - Scanner: README + package manifest
  - File Analyzer: framework info + project description from Phase 1
  - Architecture Analyzer: framework layer hints + directory tree
  - Tour Builder: README + entry point
  - Graph Reviewer: scan inventory for cross-validation + phase warnings
  
  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-18 22:55:18 +08:00
  4ff36e3dae
• docs: add simplified multi-platform implementation plan

  6 tasks: move agents to prompt templates, update SKILL.md dispatch,
  create knowledge-graph-guide agent, add platform INSTALL.md files,
  update README, verify.
  
  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-18 22:49:49 +08:00
  6346972ee5
• docs: add simplified multi-platform skill support design

  Follows superpowers pattern: same files everywhere, model: inherit,
  AI-driven installation via INSTALL.md, self-contained skills.
  
  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-18 22:47:52 +08:00
  64d901836d
• Add MIT license
  Lum1104 · 2026-03-17 14:54:57 +08:00
  e1c3b901c9
• Merge pull request #3 from Lum1104/feature/diff-mode

  perf(dashboard): skip diff overlay computation when diffMode is off

  Yuxiang Lin · 2026-03-17 11:59:15 +08:00
  6c38510acb
• Merge pull request #2 from KyleWMiller/feature/diff-mode

  Diff Mode

  Yuxiang Lin · 2026-03-17 11:55:10 +08:00
  988e73f249
• perf(dashboard): skip diff overlay computation when diffMode is off

  Guard diffNodeIds construction and per-edge lookups behind diffMode
  check to avoid unnecessary Set spreads and has() calls on every
  graph recompute when diff mode is inactive.
  
  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-17 11:53:08 +08:00
  4161d3eba3
• Merge pull request #1 from Lum1104/feat/script-augmented-agents

  feat(agents): script-augmented two-phase architecture

  Yuxiang Lin · 2026-03-17 11:29:39 +08:00
  449a4f01cb
• fix(graph-reviewer): remove duplicated critical checks from warning section

  Edge weights, node ID prefix conventions, and tag formatting were listed
  in both Check 1 (Schema Validation — Critical) and Check 7 (Quality —
  Warning). A deterministic script following check headings would classify
  these as warnings, potentially approving invalid graphs. Remove the
  duplicates from Check 7 since Check 1 already covers them as critical.
  
  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-17 11:28:29 +08:00
  70b4e6fe0a
• fix(agents): define .sh as supported source extension in project-scanner

  The exclusion rule conditionally kept .sh files for bash-first projects,
  but the source-file whitelist and language mapping table had no .sh entry,
  causing retained shell files to be dropped or untyped. Add .sh/.bash to
  the whitelist and language table (mapped to 'bash'), and remove the
  conditional exclusion rule.
  
  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-17 11:13:18 +08:00
  3715552875
• fix(graph-reviewer): align duplicate-ID classification as critical

  Duplicate node IDs were listed under Check 6 (Warning) but classified as
  critical in the Severity Classification section. A script following check
  headings would classify duplicates as warnings, letting invalid graphs
  pass review. Move duplicate-ID check to its own Check 5 (Critical) and
  renumber subsequent checks.
  
  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-17 11:12:29 +08:00
  f5b9eb7d61
• chore: bump version to 1.0.5

  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-17 11:10:14 +08:00
  b9b48466c3
• feat: diff mode added
  Kyle Miller · 2026-03-16 16:40:19 -07:00
  da8509e2b1
• feat(agents): add script-augmented two-phase architecture to all agents

  Redesign all 5 agent prompts with a "Phase 1 — Script" + "Phase 2 — LLM
  Reasoning" structure. Agents now write and execute scripts for deterministic
  work (validation, file discovery, structure extraction, graph analysis)
  before applying LLM judgment for semantic tasks (summaries, tags, pedagogy).
  
  Key changes per agent:
  - graph-reviewer: script performs all 6 validation checks deterministically
  - project-scanner: script handles file discovery, language detection, line counting
  - file-analyzer: script extracts functions/classes/imports via regex patterns
  - architecture-analyzer: script computes import adjacency, inter-group frequency
  - tour-builder: script calculates fan-in, BFS traversal, cluster detection
  
  Design safeguards:
  - scriptCompleted sentinel field guards against partial script output
  - Batch-indexed temp paths prevent collision in concurrent file-analyzer agents
  - Explicit "trust the script" directives prevent LLM from re-reading raw data
  - Up to 2 script retries on failure
  - Explicit instructions to strip intermediate fields from final output
  - Bash tool added to all agent tool lists
  
  Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-03-16 18:17:02 +08:00
  6af00c5f85
• fix(dashboard): enable click and expand for all node types (function, class, etc.)

  Previously only FILE nodes responded to clicks with the code viewer overlay.
  Now all node types open the detail viewer on click. Also added a direct click
  handler on CustomNode to fix click events not firing for child nodes inside
  group layers on Windows.
  
  Bump version to 1.0.4.

  Lum1104 · 2026-03-16 14:34:11 +08:00
  b82efea88e