@mcptoolshop/style-dataset-lab 3.3.0 → 3.5.0

package/lib/adapters/diffusers-lora.js

@@ -16,6 +16,8 @@ import { writeFile, mkdir, symlink, copyFile } from 'node:fs/promises';
 import { join, relative } from 'node:path';
 import { existsSync } from 'node:fs';
 import { groupRowsByPartition } from '../rows.js';
+import { assertSafeAssetPath, assertSafeId } from '../export.js';
+import { warn } from '../log.js';
 
 /**
  * Build training package in diffusers LoRA format from canonical rows.
@@ -33,6 +35,11 @@ export async function buildPackage({ packageDir, rows, profile, manifest, config
   const partitioned = groupRowsByPartition(rows || []);
 
   let imageCount = 0;
+  // SDL-C5: per-row failure accounting (export.js DB-002 shape) — see
+  // generic-image-caption.js for the full rationale. A caught copy/symlink
+  // error must not silently drop the image, caption sidecar, AND metadata
+  // row together with zero logging.
+  const imagesFailed = [];
 
   for (const [partition, partitionRows] of Object.entries(partitioned)) {
     const datasetDir = join(packageDir, 'dataset', partition);
@@ -43,10 +50,21 @@ export async function buildPackage({ packageDir, rows, profile, manifest, config
     const metadataRows = [];
 
     for (const row of partitionRows) {
-      if (!row.asset_path) continue;
+      if (!row.asset_path) {
+        imagesFailed.push({ record_id: row.entity_id, partition, reason: 'missing_asset_path' });
+        continue;
+      }
 
-      const sourcePath = join(projectRoot, row.asset_path);
-      if (!existsSync(sourcePath)) continue;
+      // SDL-H5 / SDL-H6: defense-in-depth — see generic-image-caption.js
+      // for the full rationale. Throws (hard fail) on traversal/unsafe id;
+      // that is a security boundary, not an operational hiccup.
+      assertSafeId(row.entity_id, `row.entity_id in diffusers-lora adapter (partition "${partition}")`);
+      const sourcePath = assertSafeAssetPath(row.asset_path, projectRoot, row.entity_id);
+
+      if (!existsSync(sourcePath)) {
+        imagesFailed.push({ record_id: row.entity_id, partition, reason: 'source_missing' });
+        continue;
+      }
 
       const sourceBasename = row.asset_path.split(/[\\/]/).pop();
       const extMatch = sourceBasename.match(/\.[^.]+$/);
@@ -62,7 +80,13 @@ export async function buildPackage({ packageDir, rows, profile, manifest, config
           await symlink(relative(datasetDir, sourcePath), destPath);
         }
         imageCount++;
-      } catch {
+      } catch (err) {
+        imagesFailed.push({
+          record_id: row.entity_id,
+          partition,
+          reason: copy ? 'copy_failed' : 'link_failed',
+          detail: err.message,
+        });
         continue;
       }
 
@@ -77,7 +101,15 @@ export async function buildPackage({ packageDir, rows, profile, manifest, config
     );
   }
 
-  return { imageCount };
+  if (imagesFailed.length > 0) {
+    const sample = imagesFailed.slice(0, 10).map(f => `${f.record_id} (${f.reason})`);
+    warn(
+      `diffusers-lora adapter: ${imagesFailed.length} of ${imageCount + imagesFailed.length} rows failed to place` +
+      (imagesFailed.length > 10 ? ` — first 10: ${sample.join(', ')}, ...` : ` — ${sample.join(', ')}`),
+    );
+  }
+
+  return { imageCount, imagesFailed };
 }
 
 function buildMetadataRow(row, partition, filename, stem) {

package/lib/adapters/generic-image-caption.js

@@ -14,11 +14,20 @@ import { writeFile, mkdir, symlink, copyFile } from 'node:fs/promises';
 import { join, relative } from 'node:path';
 import { existsSync } from 'node:fs';
 import { groupRowsByPartition } from '../rows.js';
+import { assertSafeAssetPath, assertSafeId } from '../export.js';
+import { warn } from '../log.js';
 
 export async function buildPackage({ packageDir, rows, profile, manifest, config, projectRoot, copy }) {
   const partitioned = groupRowsByPartition(rows || []);
 
   let imageCount = 0;
+  // SDL-C5: per-row failure accounting (export.js DB-002 shape). The old
+  // bare `catch { continue; }` silently dropped the image, the caption
+  // sidecar, AND the metadata row together with no logging — on Windows
+  // without Developer Mode this fired on every row, so imageCount stayed
+  // 0 and the build still reported success. Every drop is now accounted
+  // for and returned to the caller.
+  const imagesFailed = [];
 
   for (const [partition, partitionRows] of Object.entries(partitioned)) {
     const datasetDir = join(packageDir, 'dataset', partition);
@@ -29,10 +38,25 @@ export async function buildPackage({ packageDir, rows, profile, manifest, config
     const metadataRows = [];
 
     for (const row of partitionRows) {
-      if (!row.asset_path) continue;
+      if (!row.asset_path) {
+        imagesFailed.push({ record_id: row.entity_id, partition, reason: 'missing_asset_path' });
+        continue;
+      }
 
-      const sourcePath = join(projectRoot, row.asset_path);
-      if (!existsSync(sourcePath)) continue;
+      // SDL-H5 / SDL-H6: defense-in-depth. buildTrainingPackage validates
+      // every row before dispatching here, but this adapter is also
+      // unit-tested (and documented in lib/rows.js as a future direct
+      // canon-build target) independent of that caller, so the guard
+      // lives here too. A traversal / unsafe id is a security boundary,
+      // not an operational hiccup — it throws (hard fail) rather than
+      // joining the soft imagesFailed accounting below.
+      assertSafeId(row.entity_id, `row.entity_id in generic-image-caption adapter (partition "${partition}")`);
+      const sourcePath = assertSafeAssetPath(row.asset_path, projectRoot, row.entity_id);
+
+      if (!existsSync(sourcePath)) {
+        imagesFailed.push({ record_id: row.entity_id, partition, reason: 'source_missing' });
+        continue;
+      }
 
       const sourceBasename = row.asset_path.split(/[\\/]/).pop();
       const extMatch = sourceBasename.match(/\.[^.]+$/);
@@ -47,7 +71,13 @@ export async function buildPackage({ packageDir, rows, profile, manifest, config
           await symlink(relative(datasetDir, sourcePath), destPath);
         }
         imageCount++;
-      } catch {
+      } catch (err) {
+        imagesFailed.push({
+          record_id: row.entity_id,
+          partition,
+          reason: copy ? 'copy_failed' : 'link_failed',
+          detail: err.message,
+        });
         continue;
       }
 
@@ -67,5 +97,13 @@ export async function buildPackage({ packageDir, rows, profile, manifest, config
     );
   }
 
-  return { imageCount };
+  if (imagesFailed.length > 0) {
+    const sample = imagesFailed.slice(0, 10).map(f => `${f.record_id} (${f.reason})`);
+    warn(
+      `generic-image-caption adapter: ${imagesFailed.length} of ${imageCount + imagesFailed.length} rows failed to place` +
+      (imagesFailed.length > 10 ? ` — first 10: ${sample.join(', ')}, ...` : ` — ${sample.join(', ')}`),
+    );
+  }
+
+  return { imageCount, imagesFailed };
 }

package/lib/args.js

@@ -149,8 +149,23 @@ export function getProjectName(argv) {
   for (let i = 0; i < argv.length; i++) {
     const a = argv[i];
     if (a === '--project' || a === '--game') {
+      const flagName = a === '--game' ? 'game' : 'project';
       if (a === '--game') warnDeprecated('game', 'project');
-      explicit = argv[i + 1];
+      const next = argv[i + 1];
+      // SDL-L1: mirror takeFlagValue's guard below — without it, a missing
+      // value silently swallowed the NEXT flag as the project name (e.g.
+      // `--project --dry-run` yielded the project name "--dry-run").
+      if (next === undefined) {
+        throw inputError('INPUT_MISSING_VALUE', `Flag --${flagName} requires a value.`);
+      }
+      if (next.startsWith('--')) {
+        throw inputError(
+          'INPUT_MISSING_VALUE',
+          `Flag --${flagName} is missing its value (got another flag: ${next}).`,
+          `Pass a value after --${flagName}.`
+        );
+      }
+      explicit = next;
       break;
     }
     if (a.startsWith('--project=')) { explicit = a.slice('--project='.length); break; }