345 Commits

• Merge pull request #419 from chengyongru/feat/nanobot-support

  feat(install): add Nanobot platform support

  Yuxiang Lin · 2026-06-11 16:28:17 +08:00
  09ede1917f
• sync egonex organization metadata
  chienvon · 2026-06-09 14:26:48 -07:00
  7254852f4a
• feat(install): add Nanobot platform support
  chengyongru · 2026-06-09 16:52:35 +08:00
  8de0b3b11d
• Merge pull request #347 from tirth8205/feat/kotlin-extractor

  feat(core): add Kotlin structural analysis via tree-sitter

  Yuxiang Lin · 2026-06-09 13:25:10 +08:00
  ef7adac58e
• Merge pull request #359 from tirth8205/fix/import-resolver-nodenext-rewrite

  fix(extract-import-map): apply NodeNext .js→.ts rewrite (#294)

  Yuxiang Lin · 2026-06-09 13:23:21 +08:00
  13a39c01cb
• Merge pull request #387 from tirth8205/fix/phase7-cleanup-mv-trash

  fix(skill): use mv-to-trash + delayed purge for Phase 7 cleanup (#301)

  ZebangCheng · 2026-06-06 18:47:00 +08:00
  5c1e35f90b
• Merge pull request #346 from tirth8205/perf/understand-pipeline

  perf(understand): parallelise file I/O in compute-batches + extract-import-map (#76)

  ZebangCheng · 2026-06-06 16:25:49 +08:00
  3281fd15e0
• fix(skill): use mv-to-trash + delayed purge for Phase 7 cleanup (#301)

  Phase 7's `rm -rf` of the just-created `intermediate/` and `tmp/` dirs
  trips destructive-action gates on hardened hosts (e.g. freshness-window
  checks that flag deleting paths created moments earlier). Move them into
  a timestamped `.trash-<epoch>/` instead; Phase 0 reclaims the space once
  the trash is older than 7 days, well past any freshness window. Behavior
  on normal hosts is unchanged — disk usage is identical after the next
  run's purge.
  
  Closes #301
  
  Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

  Tirth Kanani · 2026-06-05 16:56:42 +01:00
  b3da919223
• fix(extract-import-map): preserve deterministic stderr order across concurrent loaders

  Addresses the regression flagged by ZebangCheng on #346: under the
  parallelised `buildResolutionContext`, `loadTsConfigs` /
  `loadGoModules` / `loadPhpAutoloads` ran concurrently but each wrote
  warnings to stderr inline as it iterated read results, so a fixture
  with both a malformed `tsconfig.json` and a malformed `composer.json`
  could emit `composer, tsconfig` instead of the pre-PR `tsconfig,
  composer` depending on I/O timing.
  
  Each loader now buffers its warnings into a returned array and the
  caller drains them in canonical order (tsconfig → go → php) after
  `Promise.all`, restoring byte-identical stderr output. Added a
  regression test that fixtures both malformed configs and asserts the
  tsconfig warning precedes the composer warning in stderr.
  
  Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

  Tirth Kanani · 2026-06-05 16:19:31 +01:00
  1f8d165f86
• feat(understand): auto-detect conversation language on first run

  When /understand runs with no --language flag and no stored outputLanguage,
  step 3.6 now infers the conversation language and — only when it is non-English
  — confirms once before generating, then persists the choice to config.json.
  English conversations keep the exact same silent `en` path; --language flag and
  stored config still take priority. README documents the behavior; version
  bumped 2.7.5 -> 2.7.6 across all five manifests (user-visible behavior change).
  
  Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

  Bozheng Long · 2026-06-03 21:19:52 +08:00
  92e76190aa
• Merge branch 'main' into fix/import-resolver-nodenext-rewrite

  Resolve conflict in tests/skill/understand/test_extract_import_map.test.mjs
  by keeping both new test groups — they cover independent fixes that should
  coexist:
    - upstream #214: tsconfig path-alias targets with leading "./"
    - this PR  #294: NodeNext .js → .ts rewrite for ESM TypeScript imports
  
  The extract-import-map.mjs script auto-merged cleanly; both fixes are
  already present in the merged source.
  
  Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

  Tirth Kanani · 2026-06-01 10:25:37 +01:00
  143b4e492f
• fix(extract-import-map): apply NodeNext .js→.ts rewrite (#294)

  Fixes the silent near-edgeless-graph regression on any modern ESM
  TypeScript project. Reported in #294 with full repro + root-cause
  analysis.
  
  ### Why this matters
  
  Under `moduleResolution: NodeNext` (or `Node16` / `Bundler` with
  explicit extensions — the default for new TS-ESM projects since 2023),
  TypeScript does NOT rewrite import specifiers during compilation:
  
    // src/index.ts — real, idiomatic NodeNext source
    import { x } from './config.js';   // on disk: config.ts
  
  Before this fix, `probeWithExtensions` only tried APPENDING extensions
  to the import specifier:
  
    './config.js' → not in fileSet
    './config.js.ts', './config.js.tsx', './config.js.js', ... → all miss
    → returns null → edge dropped at merge as dangling
  
  Net result on the reporter's repro: a knowledge graph with hundreds of
  file nodes and almost no `imports` edges between them — silently
  removing exactly the dependency structure the graph is meant to show.
  
  ### Fix
  
  New `NODENEXT_REWRITES` table maps each compiled-output extension to
  the TypeScript source extensions that could have produced it:
  
    .js   → [.ts, .tsx, .js, .jsx]
    .jsx  → [.tsx, .jsx]
    .mjs  → [.mts, .mjs, .ts]
    .cjs  → [.cts, .cjs, .ts]
  
  `probeWithExtensions` now applies the rewrite when the import already
  ends with one of these extensions and no such file exists on disk. The
  rewrite runs BEFORE the legacy append-extensions loop — otherwise
  `./foo.js` would generate the nonsense candidate `foo.js.ts` and the
  append loop would never reach the actual `foo.ts`.
  
  ### Disambiguation
  
  If both `config.ts` and `config.js` exist on disk (rare, but possible
  during a partial migration), `import './config.js'` still resolves to
  the .js — that's an exact-disk match and what NodeNext compilation
  actually does. The rewrite only kicks in when the .js doesn't exist.
  
  ### Tests
  
  6 new tests in `test_extract_import_map.test.mjs`:
  - The main #294 case (`.js → .ts`)
  - `.jsx → .tsx` and `.mjs → .mts` rewrites
  - Disambiguation when both `.ts` and `.js` exist on disk
  - Pure-JS projects still work (real `.js → .js` imports)
  - Historical no-extension probes unaffected
  - Missing files still return null (rewrite can't invent targets)
  
  Total: 202 tests passing (was 196).
  
  Closes #294

  Tirth Kanani · 2026-05-31 22:31:23 +01:00
  a6c653e36b
• feat(core): add Kotlin structural analysis via tree-sitter

  Wires Kotlin into the existing tree-sitter pipeline so .kt and .kts
  files now produce functions, classes, data classes, sealed classes,
  interfaces, objects, imports, exports, and call-graph edges — matching
  the behavior of the other language extractors.
  
  ## Why @tree-sitter-grammars/tree-sitter-kotlin
  
  The standard `tree-sitter-kotlin` (v0.3.8) ships only native bindings.
  The new `@tree-sitter-grammars/tree-sitter-kotlin@1.1.0` ships a
  prebuilt `.wasm` (loads cleanly with `web-tree-sitter@^0.26.6`,
  nodeTypeCount=289, parses class_declaration / function_declaration as
  expected). Same shape that PR1 used for Swift, just a different
  publisher because the repomix WASM bundle does not include Kotlin.
  
  `@tree-sitter-grammars` is the official tree-sitter org's GitHub
  account, so this is the canonical upstream WASM source for Kotlin.
  
  ## Notes for reviewers
  
  - `kotlinConfig` already existed as a stub (no `treeSitter` field), so
    Android / JVM / Gradle codebases currently produce no structural
    edges between `.kt` files. This PR adds the `treeSitter` field; the
    existing plugin loader picks it up unchanged.
  - **Visibility rule differs from Swift**: Kotlin's default visibility
    is `public`, so the extractor treats *every* declaration with no
    modifier as exported. Only an explicit `private` opts out. `internal`
    and `protected` remain exported in the project-graph sense because
    they are still resolvable from other files (within the module / via
    inheritance).
  - `class_declaration` in tree-sitter-kotlin is overloaded for class,
    data class, sealed class, and interface (distinguished by the keyword
    child and `modifiers > class_modifier`). The extractor handles all
    four uniformly.
  - `object_declaration` is a separate node type (Kotlin singletons) —
    treated as a class-like entry with its own `name` and members.
  - Primary-constructor parameters marked `val` / `var` are surfaced as
    class properties; plain `parameter`s without `val/var` are
    constructor-only and are NOT counted as properties (matching Kotlin
    semantics).
  - Import handling distinguishes the three forms: plain dotted
    (`import a.b.C`), wildcard (`import a.b.*` → specifier `"*"`), and
    aliased (`import a.b.C as Foo` → specifier `"Foo"`).
  
  ## Verification
  
  - `pnpm lint` clean
  - `pnpm --filter @understand-anything/core build` clean
  - `pnpm --filter @understand-anything/skill build` clean
  - `pnpm --filter @understand-anything/core test`: **692/692** (+22 new
    Kotlin tests, matching the bar set by go-extractor.test.ts /
    swift-extractor.test.ts)
  - `pnpm test`: 196/196 (no regressions)
  
  Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

  Tirth Kanani · 2026-05-31 20:42:12 +01:00
  235f2fafc8
• perf(understand): parallelise file I/O in compute-batches + extract-import-map (#76)

  The /understand pipeline reads every code file twice during analysis:
  once in compute-batches (`extractExports` for the cross-batch neighbour
  map) and once again in extract-import-map (per-language config loaders).
  Both sites used sequential `readFileSync` loops, so on the iOS repo in
  issue #226 (~15k files) the disk-read time was effectively serialised
  behind a single libuv thread while the rest of the pool sat idle.
  
  ## Changes
  
  - `extractExports` now batches files into `IO_PARALLELISM = 64` slices
    and issues all `readFile` calls in each slice through `Promise.all`,
    letting libuv's worker-thread pool overlap disk reads. The
    tree-sitter parse stays on the main thread because `web-tree-sitter`
    is single-threaded WASM — pipelining the I/O while parses run is
    where the wall-time savings come from.
  - `loadTsConfigs`, `loadGoModules`, `loadPhpAutoloads` and
    `buildResolutionContext` switch to async / `Promise.all` for the
    same reason. `buildResolutionContext` also runs the three loader
    passes concurrently (`Promise.all([...])`) since they're independent.
  - A small `readFilesParallel(paths)` helper is added at the top of
    `extract-import-map.mjs` so the three loaders share the same
    error-preserving shape.
  
  ## Why behavior stays identical
  
  - Each loader collects its candidate paths in `files[]` order *before*
    issuing reads, then iterates `reads` in the same order to emit
    warnings + populate output maps. So stderr order and the final map
    contents are byte-identical to the previous sequential loops.
  - `extractExports` collects per-file errors in-place in the
    `Promise.all` callbacks and emits warnings during the post-read
    serial loop, again in chunk order — so warning text and order match
    the previous implementation.
  - Tree-sitter parsing is unchanged: parses still run serially on the
    main thread, just with reads pipelined alongside.
  
  ## What's NOT in this PR
  
  - `buildFingerprintStore` and `analyzeChanges` in `core/fingerprint.ts`
    have the same sequential pattern. They're left alone here because
    they're part of the public `@understand-anything/core` API; making
    them async would be a breaking change worth its own discussion.
    Internal-only `.mjs` scripts are safe to refactor without API churn.
  - No change to scan-project: most of its sync I/O is `statSync`
    (metadata, not content) plus a handful of small `.gitignore` /
    `.understandignore` reads. The parallelism win is marginal there.
  
  ## Verification
  
  - `pnpm lint` clean
  - `pnpm --filter @understand-anything/core build` clean
  - `pnpm --filter @understand-anything/skill build` clean
  - `pnpm test`: 196/196 — including
    `test_compute_batches.test.mjs` (19 tests) and
    `test_extract_import_map.test.mjs` (40 tests), which exercise both
    changed pipelines end-to-end with fixture projects. No output
    diff vs main.
  
  Refs #76
  
  Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

  Tirth Kanani · 2026-05-31 20:25:39 +01:00
  eea73b656d
• fix(skill): preserve scan-result.json across Phase 7 cleanup for incremental runs (#293)
  Zebang Cheng · 2026-05-29 15:33:31 +00:00
  928b997c57
• Merge pull request #227 from ZebangCheng/fix/tsconfig-path-leading-dot-slash

  fix(extract-import-map): normalize tsconfig path-alias candidates with leading "./" (#214)

  ZebangCheng · 2026-05-26 13:09:25 +08:00
  d40d6b6204
• fix(scan-project): preserve non-ASCII path bytes via git ls-files -z

  `enumerateViaGit` ran `git ls-files -co --exclude-standard` (newline-separated
  output) and then `split('\n').map(trim)` on the result. Without `-z`,
  `git ls-files` C-escapes any byte outside the locale's "safe" set and wraps
  the path in double quotes — for example, a directory named `30. 🏗️ docs/`
  comes back as `"30. \360\237\217\227\357\270\217 docs/"`. Downstream
  consumers then can't round-trip those octal-quoted strings to real disk
  paths, so every file under such directories is silently dropped from the
  scan.
  
  This is particularly biting on Windows (where the issue surfaces even with
  UTF-8 locale settings) and for any project that uses emoji, accented
  characters, or CJK codepoints in directory names — which is increasingly
  common in design/spec/journal trees.
  
  The fix is to use `-z` (NUL-terminated output), the same approach git
  itself documents for downstream consumers (e.g. `xargs -0`). NUL-separated
  chunks are raw bytes, so every codepoint round-trips back to its real disk
  path on every platform. Split on `\0` instead of `\n`; drop the now-
  unnecessary `.trim()`.
  
  Verified on a real project with emoji-prefixed directory names:
  
    bare `git ls-files`:
      "30. \360\237\217\227\357\270\217\360\237\247\231\342\200\215..."
  
    `git ls-files -z`:
      30. 🏗️🧙‍♂️🔮 BD-CCSP/01. Demo's/DEMO--...
  
  Discovered during a multi-agent scan of an Atlas Intelligence spoke repo;
  ~33 design-intent files in `30. 🏗️ BD-{app}/` directories were silently
  dropped per scan. Full report: atlas-intelligence-io/fleet-feedback#491.
  
  Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

  Adam Herring · 2026-05-25 11:09:20 -07:00
  b4d856d3b8
• fix(extract-import-map): normalize tsconfig path-alias candidates with leading "./" (#214)
  Zebang Cheng · 2026-05-25 14:02:01 +00:00
  d9ae3c290c
• Merge pull request #200 from AsimRaza10/fix/agent-model-omit-inherit

  fix(agents): omit `model: inherit` so non-Claude tools don't see a bad model id

  Yuxiang Lin · 2026-05-24 21:12:57 +08:00
  470cc01dc5
• Merge pull request #204 from Lum1104/feat/semantic-batching-and-output-chunking

  fix(#159): semantic batching + bundled importMap + Phase 1 speedup

  Yuxiang Lin · 2026-05-24 20:12:14 +08:00
  a59a573a1d
• fix(agents): omit model: inherit so non-Claude tools don't see a bad model id

  `model: inherit` is a Claude Code-specific keyword that means "use the
  parent session's model." Other tools that read the same agent frontmatter
  (opencode, codex, etc.) don't understand it and instead try to use
  `inherit` as a literal model id, which the configured provider rejects.
  
  Reproduction (from #167): opencode + deepseek runs `/understand`, the
  project-scanner subagent dispatches with `model: inherit`, deepseek
  returns `ProviderModelNotFoundError`, and the pipeline halts on every
  subagent dispatch.
  
  With the field omitted, each platform falls back to its own configured
  default:
  - Claude Code: user's default subagent model
  - opencode / codex / etc.: globally configured model
  
  Note for Claude Code Opus users: subagents will no longer auto-inherit
  the Opus session model. If you want the previous behavior, set your
  default subagent model globally — that single setting now controls all
  nine agents.
  
  Closes #167

  Asim Raza · 2026-05-24 10:50:26 +05:00
  0566ea8b6b
• Merge pull request #186 from AsimRaza10/fix/tailwind-source-detection

  fix(dashboard): explicit @source for Tailwind v4 (fixes #179)

  Yuxiang Lin · 2026-05-24 10:10:58 +08:00
  42d70c3f9c
• fix(ux): add progress reporting to /understand pipeline

  Adds phase status lines, batch progress with total count, and phase
  completion confirmations to the skill definition. Users now see
  [Phase N/7] headers and Batch X/N during analysis instead of
  unnumbered batch lines with no context.
  
  Fixes #182

  devangpratap · 2026-05-23 14:18:26 -04:00
  31ae12b65c
• fix(dashboard): add explicit @source for Tailwind v4 detection

  Tailwind v4's default source detection walks the nearest .git and
  collects tracked files via git ls-files. When the dashboard sources
  sit inside a gitignored subtree of an ancestor repo (e.g. the default
  marketplace install path ~/.claude/plugins/cache/, which is ignored by
  ~/.claude/.gitignore), detection returns 0 files and the Oxide engine
  skips all utility generation — the dashboard renders unstyled.
  
  Adding explicit @source directives is the supported Tailwind v4 escape
  hatch and is a no-op for installs where automatic detection works.
  
  Verified: built CSS bundle jumps from ~9 KB to ~55 KB and utility
  classes (.flex, .grid, .absolute, .w-full, .h-full) are present.
  
  Fixes #179

  Asim Raza · 2026-05-23 18:23:17 +05:00
  96c412bcc1
• Merge pull request #171 from Derrick-xn/docs/update-skill-graph-reference

  docs(skills): update graph structure references

  Yuxiang Lin · 2026-05-23 16:10:55 +08:00
  35699dd82b
• chore(dependencies): update astro and vite versions in package.json and pnpm-lock.yaml

  Bumps astro to version 6.3.7 and vite to version 6.4.2 across relevant package files to ensure compatibility and access to the latest features.

  Ved Prakash · 2026-05-23 15:58:37 +08:00
  4ef12f39a6
• Merge pull request #161 from okwn/contrib/understand-anything/eslint-tooling

  chore: add ESLint tooling with TypeScript support

  Yuxiang Lin · 2026-05-23 15:47:52 +08:00
  4bd6f78dff
• chore(lint): switch to recommended baseline, fix errors, wire into CI

  - typescript-eslint preset: strict -> recommended for a usable first-pass
    baseline (per PR discussion); ratchet up in a follow-up.
  - Drop the projectService/parserOptions block. Neither `recommended` nor
    `strict` is type-aware, so it was unused; removing it also avoids the
    pnpm-workspace tsconfig-resolution failure mode flagged in review.
  - Add Node + browser globals via the `globals` package so .mjs scripts and
    the dashboard stop hitting `no-undef`.
  - Expand ignores: built bundles (**/public/**), Astro generated (.astro/),
    and .private/ (eval scratch). Cuts 2400+ errors in vendored output.
  - Allow `_`-prefixed unused vars/args/caught errors; skip irregular
    whitespace inside comments (json-parser intentionally embeds ZWSP-escaped
    block-comment examples in JSDoc).
  - Fix the residual 13 genuine errors: drop dead imports/vars, replace
    two `as any[]` in schema.ts with `Array<Record<string, unknown>>`,
    drop unused destructure in change-classifier, drop unused catch binding
    in extract-structure.mjs.
  - Add EOF newline to eslint.config.mjs.
  - Refresh pnpm-lock.yaml.
  - Add `pnpm lint` step to .github/workflows/ci.yml so the tooling
    actually enforces something.
  
  pnpm lint now exits 0 locally; 33+13 test files / 1445 tests still pass.

  Lum1104 · 2026-05-23 15:26:39 +08:00
  a1261b4883
• fix: correct GitHub URL in onboarding guide footer

  The generated onboarding markdown linked to a nonexistent repository
  (anthropics/understand-anything) instead of the actual project URL
  (Lum1104/Understand-Anything).

  Ubuntu · 2026-05-22 20:23:21 +08:00
  11c5123d61
• docs(skills): update graph structure references
  初晨 · 2026-05-22 12:08:44 +08:00
  a30c226bf4
• chore(release): bump version to 2.7.4
  Lum1104 · 2026-05-21 19:36:17 +08:00
  d14d6f8f96
• fix(skills/understand): canonicalize isCli paths so symlinked SKILL_DIR runs main()

  import.meta.url resolves through symlinks but pathToFileURL(process.argv[1])
  preserves them, so extract-structure.mjs silently exited 0 without writing
  output when invoked via the plugin's symlinked install path — the documented
  Claude Code / Copilot CLI layout. Compare both sides via realpathSync and add
  a post-write existence assertion plus caller-side guidance in the agent.
  
  Closes #162

  Lum1104 · 2026-05-21 19:36:14 +08:00
  8a78c94fc6
• refactor(onboarding): theme tokens, lifted state, a11y

  - Replace hardcoded hex with var(--color-*) and CJK font stacks with
    var(--font-sans) / var(--font-heading) so the overlay tracks the theme
    picker and uses the project's typography (DM Serif Display).
  - Lift dismiss/visibility state to Dashboard (shouldShowOnboarding +
    showOnboarding useState + dismissOnboarding callback). Gate the
    Suspense mount with a boolean so the lazy chunk is only fetched on
    first visit, matching the PathFinderModal / KeyboardShortcutsHelp
    mount pattern.
  - Add capture-phase Escape handler (stopPropagation prevents the global
    shortcut chain from also firing) and role="dialog" / aria-modal /
    aria-labelledby on the card for screen readers.

  Lum1104 · 2026-05-21 11:07:02 +08:00
  9dfcce73a5
• fix(onboarding): include class/function in node-type description

  Schema (packages/core/src/schema.ts) defines node types: file, function,
  class, module, concept, config, document, ... The welcome step body only
  listed "file, concept, entity, claim", missing the most common code-side
  types. Updated all 6 locales (en / zh / zh-TW / ja / ko / ru) to mention
  file / class / function from code plus concept / entity / claim from the
  knowledge wiki.

  Lum1104 · 2026-05-21 11:06:54 +08:00
  a29585874e
• fix(onboarding): wire to i18n + add missing ua-fade-in keyframes

  - Replace hardcoded Chinese strings with t.onboarding.* via useI18n
  - Add `onboarding` namespace to en / zh / zh-TW / ja / ko / ru locales
  - Inject @keyframes ua-fade-in (was referenced in inline style but
    never defined, so the overlay popped in instead of fading)

  Lum1104 · 2026-05-21 10:56:10 +08:00
  8f85b85679
• Merge branch 'main' into feat/onboarding-overlay
  Lum1104 · 2026-05-21 10:33:16 +08:00
  cd09d4fe09
• feat(i18n): add Russian language support
  Lum1104 · 2026-05-19 15:01:43 +08:00
  9d1318a0e7
• chore(release): bump version to 2.7.3

  Ships the fingerprints baseline fix (e7af9ae): every install since
  2.7.0 had a broken Phase 7 step 2.5 that threw TypeError on the first
  /understand run and left fingerprints.json empty/missing, which made
  every subsequent auto-update escalate to FULL_UPDATE. This release
  replaces the LLM-written script with a bundled build-fingerprints.mjs
  and reorders Phase 7 to write fingerprints before meta.json.
  
  Anyone upgrading from 2.7.0–2.7.2 should re-run /understand --full
  to regenerate a valid baseline.

  Lum1104 · 2026-05-18 10:13:22 +08:00
  0e39f227a4
• fix(skills/understand): bundle build-fingerprints.mjs and reorder Phase 7

  The Phase 7 step 2.5 code example in SKILL.md called
  buildFingerprintStore() with 2 arguments, but the real signature
  requires 4 (projectDir, filePaths, registry: PluginRegistry,
  gitCommitHash: string). It also omitted the required
  `await TreeSitterPlugin.init()`. Any LLM following the example
  threw TypeError on `registry.analyzeFile()` and never produced a
  baseline — which is why fingerprints.json never existed in a usable
  form after a fresh /understand, and is the root cause behind
  issue #152's "every auto-update escalates to FULL_UPDATE" cascade.
  
  Replace the LLM-written script with a bundled `build-fingerprints.mjs`
  that mirrors `extract-structure.mjs`: resolves @understand-anything/core
  via createRequire, initializes TreeSitterPlugin + PluginRegistry
  correctly, calls buildFingerprintStore with all four arguments, and
  persists via saveFingerprints. Smoke-tested on this repo (3 files,
  correct functions/classes/imports extracted).
  
  Reorder Phase 7 so fingerprints are written BEFORE meta.json. If
  fingerprint generation fails, the new step explicitly says to abort
  Phase 7 — meta.json must not advance without a valid baseline, or
  the next auto-update sees a fresh commit hash with no fingerprints
  and classifies every file as STRUCTURAL.
  
  Affects every install since 2.7.0 (when the broken example was
  introduced). Users running /understand --full on 2.7.3+ will get
  a usable fingerprints.json on the first try.

  Lum1104 · 2026-05-18 10:13:02 +08:00
  e7af9ae35e
• chore(release): bump version to 2.7.2

  Ships two auto-update fixes:
  - #153 (5304ff0): apply .understandignore in Phase 0 so user-excluded
    paths don't inflate the structural-change count.
  - #152 (dd8b724): LOAD-PATCH-SAVE template for Phase 3d fingerprints
    merge, with guard against silent load failure.

  Lum1104 · 2026-05-18 09:59:05 +08:00
  97fa2f3cab
• fix(hooks/auto-update): make fingerprints merge unambiguous in Phase 3d

  Fixes #152. Phase 3d step 3 instructed the LLM to "merge with existing
  fingerprints (keep unchanged files as-is)" but the prose was vague
  enough that the LLM-written script frequently wrote only the freshly
  re-analyzed batch entries to fingerprints.json, discarding every other
  file's fingerprint. The next auto-update saw N-batch_size files with
  no stored fingerprint → classified as STRUCTURAL → exceeded the 30-file
  threshold → FULL_UPDATE permanently, burning hundreds of thousands of
  tokens on every subsequent commit.
  
  Replace the four-bullet description with an explicit LOAD-PATCH-SAVE
  script template:
  
    1. LOAD ALL existing entries from fingerprints.json (never skip).
    2. PATCH or REMOVE each path in filesToReanalyze (inline deletion
       handling so the spec doesn't need a separate deletedFiles list).
    3. GUARD: if the file existed and was non-empty but loaded as {},
       abort the write — silent load failure would otherwise clobber
       every fingerprint.
    4. SAVE the full dict back.
  
  The reporter's dry-run showed this restores 81/97 files to COSMETIC
  classification on their project (zero LLM tokens) instead of all 97
  incorrectly forced into STRUCTURAL.
  
  Note: a related ordering bug exists in skills/understand/SKILL.md
  Phase 7 (meta.json written before fingerprints.json — silent failure
  in step 2.5 leaves stale fingerprints). That's a separate fix in a
  different file and is intentionally not bundled here.

  Lum1104 · 2026-05-18 09:58:45 +08:00
  dd8b724c99
• fix(hooks/auto-update): apply .understandignore exclusions in Phase 0

  Fixes #153. Phase 0 step 7 filters changed files to source extensions
  only and never reads `.understandignore`, so files in user-excluded
  paths (migrations, vendored code, tests) count as structural changes
  and can spuriously escalate the action to FULL_UPDATE. The reporter
  saw 50 → 38 structural files after applying their ignore patterns
  (below the 30-file FULL_UPDATE threshold, ARCHITECTURE_UPDATE would
  have sufficed).
  
  Add step 9 that delegates to `createIgnoreFilter` from
  `@understand-anything/core` via $CLAUDE_PLUGIN_ROOT. Same code path
  as /understand's project-scanner Step 2.5, so the auto-update honors
  the exact same patterns (hardcoded defaults + user .understandignore
  files at both standard locations + `!` negation semantics).
  
  If $CLAUDE_PLUGIN_ROOT can't be resolved, fail loud rather than
  silently skipping — a silent skip reproduces the original bug.

  Lum1104 · 2026-05-18 09:58:11 +08:00
  5304ff06f3
• chore(release): bump version to 2.7.1

  Ships the fixes that landed on main after the 2.7.0 cut:
  
  - #139 (f3ea1a3): understand-knowledge — Windows path separators in
    wikilink resolution + omit empty `category` so KnowledgeMetaSchema's
    `z.string().optional()` no longer drops every article node. Closes #151.
  - #147 (fafb888): understand-domain — resolve $PLUGIN_ROOT at runtime
    for symlink installs.
  - f71bad5: understand — persist canonical edge direction during merge,
    fixing the 153k auto-correction cascade. Closes #140.

  Lum1104 · 2026-05-18 09:48:44 +08:00
  2da74848e5
• fix(skills/understand): persist canonical edge direction during merge

  Fixes #140. merge-batch-graphs.py already defaulted missing `direction`
  to "forward" when building the dedup key, but the value was never written
  back onto the edge — so the generated knowledge-graph.json shipped without
  the field and the dashboard validator emitted one auto-correction per
  edge (153k on the reporter's Go codebase).
  
  Mirror the dashboard schema validator at packages/core/src/schema.ts:
  lowercase the value, map "both"/"mutual" → "bidirectional", fall back to
  "forward" for missing or invalid values, and persist the result onto the
  edge before it enters edges_by_key. This also closes a latent dedup leak
  where "Forward" and "forward" (or "both" and "bidirectional") would have
  produced separate dedup keys.

  Lum1104 · 2026-05-18 09:27:06 +08:00
  f71bad5267
• Merge pull request #139 from nieao/fix/windows-compat

  fix(understand-knowledge): Windows path + zod schema null compatibility

  Yuxiang Lin · 2026-05-17 22:07:38 +08:00
  a5644ca3b0
• Merge pull request #147 from rustanacexd/fix/understand-domain-plugin-root

  fix(skills/understand-domain): resolve plugin root for agent prompt loading (#146)

  Yuxiang Lin · 2026-05-13 10:20:33 +08:00
  cde871990c
• fix(skills/understand-domain): resolve plugin root at runtime for symlink installs

  Fixes #146. Ports the $PLUGIN_ROOT resolution pattern from understand/SKILL.md
  to understand-domain/SKILL.md, including:
  - Symlink resolution for ~/.agents/skills/understand-domain
  - Copilot fallback for ~/.copilot/skills/understand-domain
  - Detailed error diagnostics listing all checked paths
  - Phase 4 agent prompt path now uses $PLUGIN_ROOT/agents/domain-analyzer.md

  Rustan Corpuz · 2026-05-12 15:00:55 +08:00
  fafb888422
• chore(release): bump version to 2.7.0

  Includes since 2.6.3: Hermes (#91), Cline (#116), KIMI CLI (#134)
  platform support; dashboard ACCESS_TOKEN env override; README cleanup
  (slogan rewrite, drop outdated overview gifs, move thanks to footer).
  
  Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

  Lum1104 · 2026-05-12 14:27:12 +08:00
  04c84ab4a4
• Merge pull request #142 from zhushen12580/feature/language-parameter

  feat: Add --language parameter for localized content generation

  Yuxiang Lin · 2026-05-12 11:07:14 +08:00
  4c6f7c3e0b
• fix: Address code review feedback for PR #142

  - Remove invalid allowBuilds from pnpm-workspace.yaml (use onlyBuiltDependencies in root package.json)
  - Use data-testid for search input selector (fixes / keyboard shortcut for non-English locales)

  zhushen · 2026-05-12 11:02:13 +08:00
  2083342199