@ataraxy-labs/sem 0.5.4 → 0.8.0

package/README.md

@@ -24,7 +24,7 @@
   <img src="https://img.shields.io/badge/rust-stable-orange" alt="Rust">
   <img src="https://img.shields.io/badge/tests-133_passing-brightgreen" alt="Tests">
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-yellow" alt="License"></a>
-  <img src="https://img.shields.io/badge/languages-26-blue" alt="Languages">
+  <img src="https://img.shields.io/badge/languages-28-blue" alt="Languages">
 </p>
 
 sem is a semantic version control tool that works on top of Git. It parses your code with tree-sitter, extracts every function, class, and method as an entity, and diffs at the entity level instead of lines. This means you see "function `blahh` was modified" instead of "lines x-y changed."
@@ -92,6 +92,8 @@ If you installed via npm/bun, the binary lives in `node_modules/.bin/sem` and is
 
 Works in any Git repo. No setup required. Also works outside Git for arbitrary file comparison.
 
+sem stores its SQLite entity cache outside the repository, under the OS cache directory by default. Set `SEM_CACHE_DIR=/path/to/cache` to override the cache root; repo-local overrides are ignored so cache files do not dirty the working tree.
+
 ### sem diff
 
 Entity-level diff with rename detection, structural hashing, and word-level inline highlights.
@@ -154,6 +156,9 @@ sem impact authenticateUser --json
 
 # Disambiguate by file
 sem impact authenticateUser --file src/auth.ts
+
+# Include generated/build directories that repo-wide scans skip by default
+sem impact authenticateUser --no-default-excludes
 ```
 
 ### sem blame
@@ -198,11 +203,15 @@ sem entities src/auth.ts
 # JSON output
 sem entities --json
 sem entities src/auth.ts --json
+
+# Include generated/build directories that repo-wide scans skip by default
+sem entities --no-default-excludes
 ```
 
 ### sem context
 
-Token-budgeted context for LLMs: the entity, its dependencies, and its dependents, fitted to a token budget.
+Token-budgeted context for LLMs: the entity, its dependencies, and its dependents, fitted to a strict content token budget.
+When the target signature itself does not fit, JSON output reports `target_omitted: true`.
 
 ```bash
 sem context authenticateUser
@@ -212,6 +221,9 @@ sem context authenticateUser --budget 4000
 
 # JSON output
 sem context authenticateUser --json
+
+# Include generated/build directories that repo-wide scans skip by default
+sem context authenticateUser --no-default-excludes
 ```
 
 ## Use as default Git diff
@@ -232,7 +244,7 @@ sem unsetup
 
 ## What it parses
 
-26 programming languages with full entity extraction via tree-sitter:
+28 programming languages with full entity extraction via tree-sitter:
 
 | Language | Extensions | Entities |
 |----------|-----------|----------|
@@ -261,6 +273,8 @@ sem unsetup
 | Dart | `.dart` | classes, mixins, extensions, enums, type aliases, functions |
 | OCaml | `.ml` `.mli` | values, modules, types, classes, externals |
 | Scala | `.scala` `.sc` `.sbt` | classes, objects, traits, enums, functions, vals, extensions |
+| Nix | `.nix` | bindings, inherit declarations |
+| Haskell | `.hs` | functions, signatures, data types, newtypes, classes, instances, type synonyms |
 | Zig | `.zig` | functions, tests, variables |
 
 Plus structured data formats:
@@ -333,6 +347,11 @@ sem diff --format json
     "added": 1,
     "modified": 1,
     "deleted": 1,
+    "moved": 0,
+    "renamed": 0,
+    "reordered": 0,
+    "binary": 0,
+    "orphan": 0,
     "total": 3
   },
   "changes": [
@@ -341,12 +360,19 @@ sem diff --format json
       "changeType": "added",
       "entityType": "function",
       "entityName": "validateToken",
+      "startLine": 12,
+      "endLine": 18,
+      "oldStartLine": null,
+      "oldEndLine": null,
       "filePath": "src/auth.ts"
     }
-  ]
+  ],
+  "binaryChanges": []
 }
 ```
 
+The named change-type buckets (`added`, `modified`, `deleted`, `moved`, `renamed`, `reordered`) always sum to `total`. `orphan` is a cross-cutting metadata count for module-level changes, and those changes are already included in the named change-type buckets.
+
 ## As a library
 
 sem-core can be used as a Rust library dependency:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ataraxy-labs/sem",
-  "version": "0.5.4",
+  "version": "0.8.0",
   "description": "npm wrapper for the sem CLI. Downloads the matching release binary and exposes the sem command in node_modules/.bin.",
   "license": "MIT OR Apache-2.0",
   "type": "module",
@@ -42,6 +42,6 @@
   "scripts": {
     "postinstall": "node ./scripts/postinstall.mjs",
     "prepack": "node ./scripts/sync-package-version.mjs",
-    "test": "node ./scripts/package-meta.test.mjs"
+    "test": "node --test"
   }
 }

package/scripts/postinstall.mjs

@@ -38,9 +38,21 @@ async function downloadFile(url, destinationPath) {
 }
 
 function extractArchive(archivePath, outputDirectory) {
-  const result = spawnSync('tar', ['-xzf', archivePath, '-C', outputDirectory], {
-    stdio: 'pipe',
-  });
+  const args = ['-xzf', archivePath, '-C', outputDirectory];
+  let result = spawnSync('tar', args, { stdio: 'pipe' });
+
+  // On Windows, GNU tar (from Git for Windows / MSYS2) interprets colons in
+  // paths as remote host separators (host:path). If extraction fails with a
+  // colon-related error, retry with --force-local which disables this behavior.
+  // We don't add it unconditionally because the Windows built-in bsdtar doesn't
+  // recognize the flag.
+  if (
+    process.platform === 'win32' &&
+    result.status !== 0 &&
+    result.stderr?.toString('utf8').includes('Cannot connect to')
+  ) {
+    result = spawnSync('tar', [...args, '--force-local'], { stdio: 'pipe' });
+  }
 
   if (result.error) {
     throw new Error(`Failed to extract archive: ${result.error.message}`);

package/scripts/verify-checksum.mjs

@@ -5,19 +5,36 @@ import fs from 'node:fs/promises';
  * Downloads checksums.txt from the release, verifies the archive matches.
  * Returns silently on success, throws on mismatch or missing checksum.
  */
-export async function verifyChecksum(archivePath, archiveName, releaseBaseUrl) {
+export async function verifyChecksum(
+  archivePath,
+  archiveName,
+  releaseBaseUrl,
+  { env = process.env, fetchFn = fetch } = {},
+) {
+  if (env.SEM_SKIP_CHECKSUM === '1') {
+    console.warn('Skipping checksum verification because SEM_SKIP_CHECKSUM=1.');
+    return;
+  }
+
   const checksumsUrl = `${releaseBaseUrl}/checksums.txt`;
 
-  const response = await fetch(checksumsUrl, {
-    headers: { 'user-agent': '@ataraxy-labs/sem npm installer' },
-    redirect: 'follow',
-  });
+  let response;
+  try {
+    response = await fetchFn(checksumsUrl, {
+      headers: { 'user-agent': '@ataraxy-labs/sem npm installer' },
+      redirect: 'follow',
+    });
+  } catch (error) {
+    throw new Error(
+      `Failed to fetch checksum metadata from ${checksumsUrl}: ${error.message}`,
+    );
+  }
 
   if (!response.ok) {
-    console.warn(
-      `Could not fetch checksums (${response.status}), skipping verification.`,
+    throw new Error(
+      `Failed to fetch checksum metadata from ${checksumsUrl}: ` +
+        `${response.status} ${response.statusText}`,
     );
-    return;
   }
 
   const checksumsText = await response.text();
@@ -33,10 +50,9 @@ export async function verifyChecksum(archivePath, archiveName, releaseBaseUrl) {
   }
 
   if (!expectedHash) {
-    console.warn(
-      `No checksum found for ${archiveName} in checksums.txt, skipping verification.`,
+    throw new Error(
+      `No checksum found for ${archiveName} in checksum metadata from ${checksumsUrl}.`,
     );
-    return;
   }
 
   const fileBuffer = await fs.readFile(archivePath);