fix(rag): scope lazy-load catches so model failures aren't mislabeled 'not installed' (#118)

CHANGELOG.md

@@ -25,6 +25,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+- **Lazy-loaded embedding providers no longer mislabel model/runtime failures as "not installed" ([#118](https://github.com/jdutton/vibe-agent-toolkit/issues/118)).** `loadPipeline` in `transformers-embedding-provider.ts` wrapped both the dynamic `import('@xenova/transformers')` and the model download/inference in a single `catch` that always rethrew a fixed `@xenova/transformers is not installed` message, swallowing the real error (not even as `cause`) — so a model-download or `onnxruntime-node` native-backend failure on an installed package was reported as a missing dependency. The two failure modes are now separated: an import failure keeps the actionable install hint (now with the original error attached as `cause`), while a model/inference failure throws `Failed to load transformers model '<model>'` preserving `cause`. The sibling `onnx-embedding-provider.ts` was audited: its install-hint `catch` was already correctly scoped to the import alone, but its model download (`ensureModelFiles`) and session creation (`InferenceSession.create`) previously bubbled raw errors with no provider/model context, so they now throw `Failed to download ONNX model '<model>'` / `Failed to load ONNX model '<model>'` with `cause` preserved.
 - **Transformers.js integration tests now skip on Windows CI instead of flaking.** `transformers-embedding-provider.integration.test.ts` and the Transformers.js block of `comparison.integration.test.ts` skip on Windows (in addition to skipping when the optional `@xenova/transformers` dependency is absent), matching the existing `onnx-embedding-provider` test. These tests download a model over the network and load the `onnxruntime-node` native backend — both flaky in Windows CI. Such a failure was previously mislabeled `@xenova/transformers is not installed` by an over-broad `catch` in the provider's `loadPipeline` (the package was installed; the model download/inference is what failed), which is also why an availability-only guard did not prevent it.
 - **Config-first skill discovery now honors `..` in `skills.include` patterns.** `vat build`, `vat verify`, and `vat skills validate` all funnel through `discoverSkillsFromConfig`, which previously passed every include pattern to a single downward-only crawl rooted at `projectRoot` — so an include like `"../../docs/skills/*/SKILL.md"` (common in monorepos where SKILL.md sources live alongside, not inside, the package) silently matched zero skills. `vat audit` accepted the same config only because it has a separate filesystem-first walker. Each include pattern is now split into a literal base + glob remainder via `picomatch.scan`, patterns are grouped by their resolved absolute base, and the crawler runs once per base — making config-first discovery agree with audit. User-supplied excludes stay anchored to `projectRoot` so patterns like `docs/private/**` keep their original meaning, and a pattern resolving to a nonexistent base now silently produces zero matches.
 

packages/rag/src/embedding-providers/onnx-embedding-provider.ts

@@ -202,19 +202,31 @@ export class OnnxEmbeddingProvider implements EmbeddingProvider {
       modelPath = safePath.join(this.configModelPath, 'model.onnx');
       vocabPath = safePath.join(this.configModelPath, 'vocab.txt');
     } else {
-      const files = await ensureModelFiles(this.model, this.cacheDir);
-      modelPath = files.modelPath;
-      vocabPath = files.vocabPath;
+      try {
+        const files = await ensureModelFiles(this.model, this.cacheDir);
+        modelPath = files.modelPath;
+        vocabPath = files.vocabPath;
+      } catch (cause) {
+        throw new Error(`Failed to download ONNX model '${this.model}': ${String(cause)}`, {
+          cause,
+        });
+      }
     }
 
     const sessionOptions = this.executionProviders
       ? { executionProviders: this.executionProviders }
       : undefined;
 
-    const session = await ort.InferenceSession.create(modelPath, sessionOptions);
-    const tokenizer = await BertTokenizer.fromVocabFile(vocabPath);
+    try {
+      const session = await ort.InferenceSession.create(modelPath, sessionOptions);
+      const tokenizer = await BertTokenizer.fromVocabFile(vocabPath);
 
-    return { session, tokenizer };
+      return { session, tokenizer };
+    } catch (cause) {
+      throw new Error(`Failed to load ONNX model '${this.model}': ${String(cause)}`, {
+        cause,
+      });
+    }
   }
 
   /**

packages/rag/src/embedding-providers/transformers-embedding-provider.ts

@@ -7,6 +7,8 @@
  * Requires optional dependency: npm install @xenova/transformers
  */
 
+import type { pipeline as PipelineFactory } from '@xenova/transformers';
+
 import type { EmbeddingProvider } from '../interfaces/embedding.js';
 
 /**
@@ -31,16 +33,25 @@ type PipelineFunction = (
 async function loadPipeline(
   model: string,
 ): Promise<PipelineFunction> {
+  let pipeline: typeof PipelineFactory;
   try {
-    const { pipeline } = await import('@xenova/transformers');
-    return (await pipeline('feature-extraction', model, {
-      quantized: true,
-    })) as PipelineFunction;
-  } catch {
+    ({ pipeline } = await import('@xenova/transformers'));
+  } catch (cause) {
     throw new Error(
       '@xenova/transformers is not installed. Install with: npm install @xenova/transformers',
+      { cause },
     );
   }
+
+  try {
+    return (await pipeline('feature-extraction', model, {
+      quantized: true,
+    })) as PipelineFunction;
+  } catch (cause) {
+    throw new Error(`Failed to load transformers model '${model}': ${String(cause)}`, {
+      cause,
+    });
+  }
 }
 
 /**