@ordis-dev/ordis 0.1.1 → 0.4.0

package/README.md

@@ -16,6 +16,7 @@ Ordis is a local-first tool and library that turns messy, unstructured text into
 - **Schema-first workflow**: Define your data structure upfront
 - **Deterministic output**: Returns validated records or structured failures
 - **Token budget awareness**: Automatic token counting with warnings and limits
+- **HTML preprocessing**: Strip noise from web pages before extraction
 - **Dual-purpose**: Use as a CLI or import as a library
 - **TypeScript support**: Full type definitions included
 
@@ -167,6 +168,30 @@ const result = await extract({
 });
 ```
 
+**Extracting from HTML:**
+
+```typescript
+import { extract, loadSchema } from '@ordis-dev/ordis';
+
+const schema = await loadSchema('./schema.json');
+
+// Strip HTML noise before extraction
+const result = await extract({
+  input: rawHtmlContent,
+  schema,
+  llmConfig: { baseURL: 'http://localhost:11434/v1', model: 'llama3.2:3b' },
+  preprocessing: {
+    stripHtml: true  // Removes scripts, styles, nav, ads, etc.
+    // Or with options:
+    // stripHtml: {
+    //   preserveStructure: true,  // Convert headings/lists to markdown
+    //   removeSelectors: ['.sidebar', '#comments'],
+    //   maxLength: 10000
+    // }
+  }
+});
+```
+
 ## What Works
 
 - ✅ Schema loader and validator
@@ -179,6 +204,7 @@ const result = await extract({
 - ✅ Field-level confidence tracking
 - ✅ TypeScript type definitions
 - ✅ Performance benchmarks
+- ✅ HTML preprocessing for noisy web content
 
 ## Performance
 
@@ -191,6 +217,26 @@ npm run benchmark
 
 ## Roadmap
 
+**Completed in v0.4.0:**
+- ✅ User-friendly error messages ([#63](https://github.com/ordis-dev/ordis/issues/63))
+  - Emoji indicators (❌, 💡, ℹ️) for quick scanning
+  - Expected vs. actual values for validation errors
+  - Actionable suggestions for common issues
+  - Service-specific troubleshooting (Ollama, LM Studio, OpenAI)
+  - File system error handling (ENOENT, EACCES)
+- ✅ Debug mode enhancements
+  - Full LLM request/response logging
+  - Token usage breakdown
+  - System and user prompt visibility
+  - Detailed error context
+
+**Completed in v0.2.0:**
+- ✅ HTML stripping/preprocessing before extraction ([#59](https://github.com/ordis-dev/ordis/issues/59))
+  - `stripHtml: true` removes HTML tags, keeps text content
+  - `preserveStructure: true` converts headings/lists to markdown-like format
+  - `removeSelectors` for custom element removal
+  - Automatic removal of scripts, styles, nav, footer, ads
+
 **Completed in v0.1.0:**
 - ✅ Core extraction pipeline with schema validation
 - ✅ Token budget awareness and management
@@ -201,6 +247,7 @@ npm run benchmark
 - ✅ Support for any OpenAI-compatible API
 
 **Upcoming:**
+- [ ] Schema validation error line numbers ([#64](https://github.com/ordis-dev/ordis/issues/64))
 - [ ] Smart input truncation ([#40](https://github.com/ordis-dev/ordis/issues/40))
 - [ ] Multi-pass extraction for large inputs ([#41](https://github.com/ordis-dev/ordis/issues/41))
 - [ ] Config file support ([#16](https://github.com/ordis-dev/ordis/issues/16))

package/dist/cli.js

@@ -8,6 +8,7 @@ import * as fs from 'node:fs/promises';
 import * as path from 'node:path';
 import { loadSchema } from './schemas/loader.js';
 import { extract } from './core/pipeline.js';
+import { formatError } from './core/error-formatter.js';
 import packageJson from '../package.json' with { type: 'json' };
 function parseArgs(args) {
     const parsed = {};
@@ -130,6 +131,7 @@ async function runExtraction(args) {
             baseURL: args.base,
             model: args.model,
             ...(args.apiKey && { apiKey: args.apiKey }),
+            debug: args.debug,
         };
         if (args.debug) {
             console.log('[DEBUG] LLM config:', {
@@ -171,10 +173,23 @@ async function runExtraction(args) {
             process.exit(0);
         }
         else {
-            // Output failure with errors
+            // Output failure with formatted errors
+            const formattedErrors = result.errors.map((err) => {
+                // If we have the original error in details, format that
+                const errorToFormat = err.details?.error || err;
+                const formatted = formatError(errorToFormat, {
+                    model: args.model,
+                    baseURL: args.base,
+                });
+                return {
+                    message: formatted,
+                    code: err.code,
+                    field: err.field,
+                };
+            });
             const output = {
                 success: false,
-                errors: result.errors,
+                errors: formattedErrors,
                 data: result.data, // May be partial
                 confidence: result.confidence,
                 meetsThreshold: result.meetsThreshold,
@@ -185,15 +200,16 @@ async function runExtraction(args) {
         }
     }
     catch (error) {
-        // Handle unexpected errors
+        // Handle unexpected errors with formatted messages
         if (args.debug && error instanceof Error) {
             console.error('[DEBUG] Stack trace:', error.stack);
         }
+        const formattedMessage = formatError(error);
         const errorOutput = {
             success: false,
             errors: [
                 {
-                    message: error instanceof Error ? error.message : String(error),
+                    message: formattedMessage,
                     code: error.code || 'UNKNOWN_ERROR',
                 },
             ],

package/dist/cli.js.map

@@ -1 +1 @@
-{"version":3,"file":"cli.js","sourceRoot":"","sources":["../src/cli.ts"],"names":[],"mappings":";AAEA;;;GAGG;AAEH,OAAO,OAAO,MAAM,cAAc,CAAC;AACnC,OAAO,KAAK,EAAE,MAAM,kBAAkB,CAAC;AACvC,OAAO,KAAK,IAAI,MAAM,WAAW,CAAC;AAClC,OAAO,EAAE,UAAU,EAAE,MAAM,qBAAqB,CAAC;AACjD,OAAO,EAAE,OAAO,EAAE,MAAM,oBAAoB,CAAC;AAE7C,OAAO,WAAW,MAAM,iBAAiB,CAAC,OAAO,IAAI,EAAE,MAAM,EAAE,CAAC;AAYhE,SAAS,SAAS,CAAC,IAAc;IAC7B,MAAM,MAAM,GAAY,EAAE,CAAC;IAE3B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACnC,MAAM,GAAG,GAAG,IAAI,CAAC,CAAC,CAAC,CAAC;QAEpB,IAAI,GAAG,KAAK,QAAQ,IAAI,GAAG,KAAK,IAAI,EAAE,CAAC;YACnC,QAAQ,EAAE,CAAC;YACX,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QACpB,CAAC;QAED,IAAI,GAAG,KAAK,WAAW,IAAI,GAAG,KAAK,IAAI,EAAE,CAAC;YACtC,WAAW,EAAE,CAAC;YACd,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QACpB,CAAC;QAED,IAAI,GAAG,KAAK,SAAS,EAAE,CAAC;YACpB,MAAM,CAAC,KAAK,GAAG,IAAI,CAAC;YACpB,SAAS;QACb,CAAC;QAED,IAAI,GAAG,KAAK,UAAU,IAAI,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;YACpC,MAAM,CAAC,MAAM,GAAG,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;QAC9B,CAAC;aAAM,IAAI,GAAG,KAAK,SAAS,IAAI,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;YAC1C,MAAM,CAAC,KAAK,GAAG,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;QAC7B,CAAC;aAAM,IAAI,GAAG,KAAK,QAAQ,IAAI,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;YACzC,MAAM,CAAC,IAAI,GAAG,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;QAC5B,CAAC;aAAM,IAAI,GAAG,KAAK,SAAS,IAAI,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;YAC1C,MAAM,CAAC,KAAK,GAAG,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;QAC7B,CAAC;aAAM,IAAI,GAAG,KAAK,WAAW,IAAI,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;YAC5C,MAAM,CAAC,MAAM,GAAG,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;QAC9B,CAAC;aAAM,IAAI,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,CAAC,EAAE,CAAC;YAC/B,MAAM,CAAC,OAAO,GAAG,GAAG,CAAC;QACzB,CAAC;IACL,CAAC;IAED,OAAO,MAAM,CAAC;AAClB,CAAC;AAED,SAAS,QAAQ;IACb,OAAO,CAAC,GAAG,CAAC;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA4Bf,CAAC,CAAC;AACH,CAAC;AAED,SAAS,WAAW;IAChB,OAAO,CAAC,GAAG,CAAC,UAAU,WAAW,CAAC,OAAO,EAAE,CAAC,CAAC;AACjD,CAAC;AAED,KAAK,UAAU,aAAa,CAAC,IAAa;IACtC,8BAA8B;IAC9B,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,CAAC;QACf,OAAO,CAAC,KAAK,CAAC,6BAA6B,CAAC,CAAC;QAC7C,OAAO,CAAC,KAAK,CAAC,iFAAiF,CAAC,CAAC;QACjG,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;IAED,IAAI,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC;QACd,OAAO,CAAC,KAAK,CAAC,4BAA4B,CAAC,CAAC;QAC5C,OAAO,CAAC,KAAK,CAAC,iFAAiF,CAAC,CAAC;QACjG,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;IAED,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC;QACb,OAAO,CAAC,KAAK,CAAC,2BAA2B,CAAC,CAAC;QAC3C,OAAO,CAAC,KAAK,CAAC,iFAAiF,CAAC,CAAC;QACjG,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;IAED,IAAI,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC;QACd,OAAO,CAAC,KAAK,CAAC,4BAA4B,CAAC,CAAC;QAC5C,OAAO,CAAC,KAAK,CAAC,iFAAiF,CAAC,CAAC;QACjG,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;IAED,IAAI,CAAC;QACD,sBAAsB;QACtB,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,gCAAgC,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC;QAC/D,CAAC;QAED,MAAM,UAAU,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QAC7C,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,UAAU,CAAC,CAAC;QAE5C,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,qCAAqC,EAAE;gBAC/C,IAAI,EAAE,MAAM,CAAC,QAAQ,EAAE,IAAI;gBAC3B,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC;gBAClC,mBAAmB,EAAE,MAAM,CAAC,UAAU,EAAE,SAAS;aACpD,CAAC,CAAC;QACP,CAAC;QAED,0BAA0B;QAC1B,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,+BAA+B,IAAI,CAAC,KAAK,EAAE,CAAC,CAAC;QAC7D,CAAC;QAED,MAAM,SAAS,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QAC3C,MAAM,SAAS,GAAG,MAAM,EAAE,CAAC,QAAQ,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC;QAExD,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,yBAAyB,SAAS,CAAC,MAAM,aAAa,CAAC,CAAC;QACxE,CAAC;QAED,4BAA4B;QAC5B,MAAM,SAAS,GAAc;YACzB,OAAO,EAAE,IAAI,CAAC,IAAI;YAClB,KAAK,EAAE,IAAI,CAAC,KAAK;YACjB,GAAG,CAAC,IAAI,CAAC,MAAM,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,MAAM,EAAE,CAAC;SAC9C,CAAC;QAEF,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,qBAAqB,EAAE;gBAC/B,OAAO,EAAE,SAAS,CAAC,OAAO;gBAC1B,KAAK,EAAE,SAAS,CAAC,KAAK;aACzB,CAAC,CAAC;QACP,CAAC;QAED,yBAAyB;QACzB,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,yCAAyC,CAAC,CAAC;QAC3D,CAAC;QAED,MAAM,MAAM,GAAG,MAAM,OAAO,CAAC;YACzB,KAAK,EAAE,SAAS;YAChB,MAAM;YACN,SAAS;YACT,KAAK,EAAE,IAAI,CAAC,KAAK;SACpB,CAAC,CAAC;QAEH,yBAAyB;QACzB,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,6BAA6B,CAAC,CAAC;YAC3C,OAAO,CAAC,GAAG,CAAC,iBAAiB,EAAE;gBAC3B,OAAO,EAAE,MAAM,CAAC,OAAO;gBACvB,UAAU,EAAE,MAAM,CAAC,UAAU;gBAC7B,cAAc,EAAE,MAAM,CAAC,cAAc;gBACrC,UAAU,EAAE,MAAM,CAAC,MAAM,CAAC,MAAM;aACnC,CAAC,CAAC;QACP,CAAC;QAED,IAAI,MAAM,CAAC,OAAO,EAAE,CAAC;YACjB,uCAAuC;YACvC,MAAM,MAAM,GAAG;gBACX,OAAO,EAAE,IAAI;gBACb,IAAI,EAAE,MAAM,CAAC,IAAI;gBACjB,UAAU,EAAE,MAAM,CAAC,UAAU;gBAC7B,iBAAiB,EAAE,MAAM,CAAC,iBAAiB;gBAC3C,cAAc,EAAE,MAAM,CAAC,cAAc;gBACrC,QAAQ,EAAE,MAAM,CAAC,QAAQ;aAC5B,CAAC;YAEF,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;YAC7C,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QACpB,CAAC;aAAM,CAAC;YACJ,6BAA6B;YAC7B,MAAM,MAAM,GAAG;gBACX,OAAO,EAAE,KAAK;gBACd,MAAM,EAAE,MAAM,CAAC,MAAM;gBACrB,IAAI,EAAE,MAAM,CAAC,IAAI,EAAE,iBAAiB;gBACpC,UAAU,EAAE,MAAM,CAAC,UAAU;gBAC7B,cAAc,EAAE,MAAM,CAAC,cAAc;gBACrC,QAAQ,EAAE,MAAM,CAAC,QAAQ;aAC5B,CAAC;YAEF,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;YAC/C,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QACpB,CAAC;IACL,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACb,2BAA2B;QAC3B,IAAI,IAAI,CAAC,KAAK,IAAI,KAAK,YAAY,KAAK,EAAE,CAAC;YACvC,OAAO,CAAC,KAAK,CAAC,sBAAsB,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC;QACvD,CAAC;QAED,MAAM,WAAW,GAAG;YAChB,OAAO,EAAE,KAAK;YACd,MAAM,EAAE;gBACJ;oBACI,OAAO,EAAE,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC;oBAC/D,IAAI,EAAG,KAAa,CAAC,IAAI,IAAI,eAAe;iBAC/C;aACJ;SACJ,CAAC;QAEF,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,WAAW,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;QACpD,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;AACL,CAAC;AAED,KAAK,UAAU,IAAI;IACf,MAAM,IAAI,GAAG,SAAS,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;IAErC,IAAI,CAAC,IAAI,CAAC,OAAO,EAAE,CAAC;QAChB,OAAO,CAAC,KAAK,CAAC,oEAAoE,CAAC,CAAC;QACpF,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;IAED,IAAI,IAAI,CAAC,OAAO,KAAK,SAAS,EAAE,CAAC;QAC7B,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,wCAAwC,EAAE;gBAClD,MAAM,EAAE,IAAI,CAAC,MAAM;gBACnB,KAAK,EAAE,IAAI,CAAC,KAAK;gBACjB,IAAI,EAAE,IAAI,CAAC,IAAI;gBACf,KAAK,EAAE,IAAI,CAAC,KAAK;aACpB,CAAC,CAAC;QACP,CAAC;QAED,MAAM,aAAa,CAAC,IAAI,CAAC,CAAC;IAC9B,CAAC;SAAM,CAAC;QACJ,OAAO,CAAC,KAAK,CAAC,2BAA2B,IAAI,CAAC,OAAO,kCAAkC,CAAC,CAAC;QACzF,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;AACL,CAAC;AAED,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,KAAK,EAAE,EAAE;IACnB,OAAO,CAAC,KAAK,CAAC,cAAc,EAAE,KAAK,CAAC,OAAO,CAAC,CAAC;IAC7C,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AACpB,CAAC,CAAC,CAAC"}
+{"version":3,"file":"cli.js","sourceRoot":"","sources":["../src/cli.ts"],"names":[],"mappings":";AAEA;;;GAGG;AAEH,OAAO,OAAO,MAAM,cAAc,CAAC;AACnC,OAAO,KAAK,EAAE,MAAM,kBAAkB,CAAC;AACvC,OAAO,KAAK,IAAI,MAAM,WAAW,CAAC;AAClC,OAAO,EAAE,UAAU,EAAE,MAAM,qBAAqB,CAAC;AACjD,OAAO,EAAE,OAAO,EAAE,MAAM,oBAAoB,CAAC;AAE7C,OAAO,EAAE,WAAW,EAA0B,MAAM,2BAA2B,CAAC;AAChF,OAAO,WAAW,MAAM,iBAAiB,CAAC,OAAO,IAAI,EAAE,MAAM,EAAE,CAAC;AAYhE,SAAS,SAAS,CAAC,IAAc;IAC7B,MAAM,MAAM,GAAY,EAAE,CAAC;IAE3B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACnC,MAAM,GAAG,GAAG,IAAI,CAAC,CAAC,CAAC,CAAC;QAEpB,IAAI,GAAG,KAAK,QAAQ,IAAI,GAAG,KAAK,IAAI,EAAE,CAAC;YACnC,QAAQ,EAAE,CAAC;YACX,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QACpB,CAAC;QAED,IAAI,GAAG,KAAK,WAAW,IAAI,GAAG,KAAK,IAAI,EAAE,CAAC;YACtC,WAAW,EAAE,CAAC;YACd,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QACpB,CAAC;QAED,IAAI,GAAG,KAAK,SAAS,EAAE,CAAC;YACpB,MAAM,CAAC,KAAK,GAAG,IAAI,CAAC;YACpB,SAAS;QACb,CAAC;QAED,IAAI,GAAG,KAAK,UAAU,IAAI,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;YACpC,MAAM,CAAC,MAAM,GAAG,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;QAC9B,CAAC;aAAM,IAAI,GAAG,KAAK,SAAS,IAAI,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;YAC1C,MAAM,CAAC,KAAK,GAAG,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;QAC7B,CAAC;aAAM,IAAI,GAAG,KAAK,QAAQ,IAAI,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;YACzC,MAAM,CAAC,IAAI,GAAG,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;QAC5B,CAAC;aAAM,IAAI,GAAG,KAAK,SAAS,IAAI,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;YAC1C,MAAM,CAAC,KAAK,GAAG,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;QAC7B,CAAC;aAAM,IAAI,GAAG,KAAK,WAAW,IAAI,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;YAC5C,MAAM,CAAC,MAAM,GAAG,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC;QAC9B,CAAC;aAAM,IAAI,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,CAAC,EAAE,CAAC;YAC/B,MAAM,CAAC,OAAO,GAAG,GAAG,CAAC;QACzB,CAAC;IACL,CAAC;IAED,OAAO,MAAM,CAAC;AAClB,CAAC;AAED,SAAS,QAAQ;IACb,OAAO,CAAC,GAAG,CAAC;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA4Bf,CAAC,CAAC;AACH,CAAC;AAED,SAAS,WAAW;IAChB,OAAO,CAAC,GAAG,CAAC,UAAU,WAAW,CAAC,OAAO,EAAE,CAAC,CAAC;AACjD,CAAC;AAED,KAAK,UAAU,aAAa,CAAC,IAAa;IACtC,8BAA8B;IAC9B,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,CAAC;QACf,OAAO,CAAC,KAAK,CAAC,6BAA6B,CAAC,CAAC;QAC7C,OAAO,CAAC,KAAK,CAAC,iFAAiF,CAAC,CAAC;QACjG,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;IAED,IAAI,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC;QACd,OAAO,CAAC,KAAK,CAAC,4BAA4B,CAAC,CAAC;QAC5C,OAAO,CAAC,KAAK,CAAC,iFAAiF,CAAC,CAAC;QACjG,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;IAED,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC;QACb,OAAO,CAAC,KAAK,CAAC,2BAA2B,CAAC,CAAC;QAC3C,OAAO,CAAC,KAAK,CAAC,iFAAiF,CAAC,CAAC;QACjG,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;IAED,IAAI,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC;QACd,OAAO,CAAC,KAAK,CAAC,4BAA4B,CAAC,CAAC;QAC5C,OAAO,CAAC,KAAK,CAAC,iFAAiF,CAAC,CAAC;QACjG,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;IAED,IAAI,CAAC;QACD,sBAAsB;QACtB,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,gCAAgC,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC;QAC/D,CAAC;QAED,MAAM,UAAU,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QAC7C,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,UAAU,CAAC,CAAC;QAE5C,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,qCAAqC,EAAE;gBAC/C,IAAI,EAAE,MAAM,CAAC,QAAQ,EAAE,IAAI;gBAC3B,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC;gBAClC,mBAAmB,EAAE,MAAM,CAAC,UAAU,EAAE,SAAS;aACpD,CAAC,CAAC;QACP,CAAC;QAED,0BAA0B;QAC1B,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,+BAA+B,IAAI,CAAC,KAAK,EAAE,CAAC,CAAC;QAC7D,CAAC;QAED,MAAM,SAAS,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QAC3C,MAAM,SAAS,GAAG,MAAM,EAAE,CAAC,QAAQ,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC;QAExD,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,yBAAyB,SAAS,CAAC,MAAM,aAAa,CAAC,CAAC;QACxE,CAAC;QAED,4BAA4B;QAC5B,MAAM,SAAS,GAAc;YACzB,OAAO,EAAE,IAAI,CAAC,IAAI;YAClB,KAAK,EAAE,IAAI,CAAC,KAAK;YACjB,GAAG,CAAC,IAAI,CAAC,MAAM,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,MAAM,EAAE,CAAC;YAC3C,KAAK,EAAE,IAAI,CAAC,KAAK;SACpB,CAAC;QAEF,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,qBAAqB,EAAE;gBAC/B,OAAO,EAAE,SAAS,CAAC,OAAO;gBAC1B,KAAK,EAAE,SAAS,CAAC,KAAK;aACzB,CAAC,CAAC;QACP,CAAC;QAED,yBAAyB;QACzB,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,yCAAyC,CAAC,CAAC;QAC3D,CAAC;QAED,MAAM,MAAM,GAAG,MAAM,OAAO,CAAC;YACzB,KAAK,EAAE,SAAS;YAChB,MAAM;YACN,SAAS;YACT,KAAK,EAAE,IAAI,CAAC,KAAK;SACpB,CAAC,CAAC;QAEH,yBAAyB;QACzB,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,6BAA6B,CAAC,CAAC;YAC3C,OAAO,CAAC,GAAG,CAAC,iBAAiB,EAAE;gBAC3B,OAAO,EAAE,MAAM,CAAC,OAAO;gBACvB,UAAU,EAAE,MAAM,CAAC,UAAU;gBAC7B,cAAc,EAAE,MAAM,CAAC,cAAc;gBACrC,UAAU,EAAE,MAAM,CAAC,MAAM,CAAC,MAAM;aACnC,CAAC,CAAC;QACP,CAAC;QAED,IAAI,MAAM,CAAC,OAAO,EAAE,CAAC;YACjB,uCAAuC;YACvC,MAAM,MAAM,GAAG;gBACX,OAAO,EAAE,IAAI;gBACb,IAAI,EAAE,MAAM,CAAC,IAAI;gBACjB,UAAU,EAAE,MAAM,CAAC,UAAU;gBAC7B,iBAAiB,EAAE,MAAM,CAAC,iBAAiB;gBAC3C,cAAc,EAAE,MAAM,CAAC,cAAc;gBACrC,QAAQ,EAAE,MAAM,CAAC,QAAQ;aAC5B,CAAC;YAEF,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;YAC7C,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QACpB,CAAC;aAAM,CAAC;YACJ,uCAAuC;YACvC,MAAM,eAAe,GAAG,MAAM,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,GAAQ,EAAE,EAAE;gBACnD,wDAAwD;gBACxD,MAAM,aAAa,GAAG,GAAG,CAAC,OAAO,EAAE,KAAK,IAAI,GAAG,CAAC;gBAChD,MAAM,SAAS,GAAG,WAAW,CAAC,aAAa,EAAE;oBACzC,KAAK,EAAE,IAAI,CAAC,KAAK;oBACjB,OAAO,EAAE,IAAI,CAAC,IAAI;iBACrB,CAAC,CAAC;gBAEH,OAAO;oBACH,OAAO,EAAE,SAAS;oBAClB,IAAI,EAAE,GAAG,CAAC,IAAI;oBACd,KAAK,EAAE,GAAG,CAAC,KAAK;iBACnB,CAAC;YACN,CAAC,CAAC,CAAC;YAEH,MAAM,MAAM,GAAG;gBACX,OAAO,EAAE,KAAK;gBACd,MAAM,EAAE,eAAe;gBACvB,IAAI,EAAE,MAAM,CAAC,IAAI,EAAE,iBAAiB;gBACpC,UAAU,EAAE,MAAM,CAAC,UAAU;gBAC7B,cAAc,EAAE,MAAM,CAAC,cAAc;gBACrC,QAAQ,EAAE,MAAM,CAAC,QAAQ;aAC5B,CAAC;YAEF,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;YAC/C,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QACpB,CAAC;IACL,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACb,mDAAmD;QACnD,IAAI,IAAI,CAAC,KAAK,IAAI,KAAK,YAAY,KAAK,EAAE,CAAC;YACvC,OAAO,CAAC,KAAK,CAAC,sBAAsB,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC;QACvD,CAAC;QAED,MAAM,gBAAgB,GAAG,WAAW,CAAC,KAAK,CAAC,CAAC;QAC5C,MAAM,WAAW,GAAG;YAChB,OAAO,EAAE,KAAK;YACd,MAAM,EAAE;gBACJ;oBACI,OAAO,EAAE,gBAAgB;oBACzB,IAAI,EAAG,KAAa,CAAC,IAAI,IAAI,eAAe;iBAC/C;aACJ;SACJ,CAAC;QAEF,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,WAAW,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;QACpD,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;AACL,CAAC;AAED,KAAK,UAAU,IAAI;IACf,MAAM,IAAI,GAAG,SAAS,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;IAErC,IAAI,CAAC,IAAI,CAAC,OAAO,EAAE,CAAC;QAChB,OAAO,CAAC,KAAK,CAAC,oEAAoE,CAAC,CAAC;QACpF,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;IAED,IAAI,IAAI,CAAC,OAAO,KAAK,SAAS,EAAE,CAAC;QAC7B,IAAI,IAAI,CAAC,KAAK,EAAE,CAAC;YACb,OAAO,CAAC,GAAG,CAAC,wCAAwC,EAAE;gBAClD,MAAM,EAAE,IAAI,CAAC,MAAM;gBACnB,KAAK,EAAE,IAAI,CAAC,KAAK;gBACjB,IAAI,EAAE,IAAI,CAAC,IAAI;gBACf,KAAK,EAAE,IAAI,CAAC,KAAK;aACpB,CAAC,CAAC;QACP,CAAC;QAED,MAAM,aAAa,CAAC,IAAI,CAAC,CAAC;IAC9B,CAAC;SAAM,CAAC;QACJ,OAAO,CAAC,KAAK,CAAC,2BAA2B,IAAI,CAAC,OAAO,kCAAkC,CAAC,CAAC;QACzF,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpB,CAAC;AACL,CAAC;AAED,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,KAAK,EAAE,EAAE;IACnB,OAAO,CAAC,KAAK,CAAC,cAAc,EAAE,KAAK,CAAC,OAAO,CAAC,CAAC;IAC7C,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AACpB,CAAC,CAAC,CAAC"}

package/dist/core/error-formatter.d.ts

@@ -0,0 +1,35 @@
+/**
+ * Error formatting utilities for user-friendly error messages
+ */
+import type { ValidationError } from './validator.js';
+import type { Schema } from '../schemas/types.js';
+import type { LLMError } from '../llm/errors.js';
+export interface FormattedError {
+    title: string;
+    message: string;
+    suggestion?: string;
+    details?: string[];
+}
+/**
+ * Format validation error with context and suggestions
+ * Returns a formatted string with title, message, and suggestions
+ */
+export declare function formatValidationError(error: ValidationError, schema?: Schema, value?: unknown): string;
+/**
+ * Format LLM error with context and recovery suggestions
+ * Returns a formatted string with title, message, suggestions, and details
+ */
+export declare function formatLLMError(error: LLMError, context?: {
+    model?: string;
+    baseURL?: string;
+    inputLength?: number;
+}): string;
+/**
+ * Format multiple validation errors into a readable message
+ */
+export declare function formatValidationErrors(errors: ValidationError[], schema?: Schema): string;
+/**
+ * Format any error into a user-friendly message
+ */
+export declare function formatError(error: unknown, context?: Record<string, unknown>): string;
+//# sourceMappingURL=error-formatter.d.ts.map

package/dist/core/error-formatter.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"error-formatter.d.ts","sourceRoot":"","sources":["../../src/core/error-formatter.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAC;AACtD,OAAO,KAAK,EAAE,MAAM,EAAmB,MAAM,qBAAqB,CAAC;AACnE,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAIjD,MAAM,WAAW,cAAc;IAC3B,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,MAAM,CAAC;IAChB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,OAAO,CAAC,EAAE,MAAM,EAAE,CAAC;CACtB;AAED;;;GAGG;AACH,wBAAgB,qBAAqB,CACjC,KAAK,EAAE,eAAe,EACtB,MAAM,CAAC,EAAE,MAAM,EACf,KAAK,CAAC,EAAE,OAAO,GAChB,MAAM,CAuGR;AAuBD;;;GAGG;AACH,wBAAgB,cAAc,CAAC,KAAK,EAAE,QAAQ,EAAE,OAAO,CAAC,EAAE;IACtD,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,WAAW,CAAC,EAAE,MAAM,CAAC;CACxB,GAAG,MAAM,CA4HT;AAED;;GAEG;AACH,wBAAgB,sBAAsB,CAClC,MAAM,EAAE,eAAe,EAAE,EACzB,MAAM,CAAC,EAAE,MAAM,GAChB,MAAM,CAcR;AAED;;GAEG;AACH,wBAAgB,WAAW,CACvB,KAAK,EAAE,OAAO,EACd,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAClC,MAAM,CAwDR"}

package/dist/core/error-formatter.js

@@ -0,0 +1,319 @@
+/**
+ * Error formatting utilities for user-friendly error messages
+ */
+import { LLMErrorCodes } from '../llm/errors.js';
+import { PipelineErrorCodes } from './errors.js';
+/**
+ * Format validation error with context and suggestions
+ * Returns a formatted string with title, message, and suggestions
+ */
+export function formatValidationError(error, schema, value) {
+    const field = error.field ? schema?.fields?.[error.field] : undefined;
+    const fieldDesc = field?.description ? ` (${field.description})` : '';
+    const formatted = {
+        title: 'Field Validation Error',
+        message: '',
+        details: [],
+    };
+    switch (error.code) {
+        case PipelineErrorCodes.FIELD_MISSING:
+            formatted.message = `Required field '${error.field}' is missing${fieldDesc}`;
+            formatted.suggestion = field?.optional
+                ? `This field was expected but not marked as optional in the schema.`
+                : `The LLM didn't extract this field. Try:\n` +
+                    `  • Make the field description more explicit\n` +
+                    `  • Ensure the input text contains this information\n` +
+                    `  • Mark the field as optional if it's not always present`;
+            break;
+        case PipelineErrorCodes.TYPE_MISMATCH:
+            // Use expected/actual from error if provided, otherwise infer from schema
+            const expectedType = error.expected || field?.type || 'unknown';
+            const actualType = error.actual || typeof error.value;
+            const gotValue = JSON.stringify(error.value);
+            formatted.message = `Field '${error.field}'${fieldDesc}\n` +
+                `  Expected: ${expectedType}\n` +
+                `  Got: ${gotValue} (${actualType})`;
+            // Type-specific suggestions
+            if (expectedType === 'number' && actualType === 'string') {
+                formatted.suggestion = `The LLM returned a string instead of a number.\n` +
+                    `  • Check if the value contains formatting (e.g., "$1,250.00")\n` +
+                    `  • Update schema description to request "raw number without formatting"\n` +
+                    `  • Example: "amount as a number (e.g., 1250, not $1,250.00)"`;
+            }
+            else if (expectedType === 'string' && actualType === 'number') {
+                formatted.suggestion = `The LLM returned a number instead of a string.\n` +
+                    `  • Update schema to use type: "number" if numeric data is expected\n` +
+                    `  • Or clarify in description that quotes are required`;
+            }
+            else if (expectedType === 'integer' && actualType === 'number') {
+                formatted.suggestion = `Got a decimal number but expected an integer.\n` +
+                    `  • Ask for "whole number" or "integer" in the field description`;
+            }
+            break;
+        case PipelineErrorCodes.FIELD_INVALID:
+            // Check if expected is an array (enum values) or string (pattern)
+            const expectedValue = error.expected;
+            if (Array.isArray(expectedValue)) {
+                // Enum validation error
+                formatted.message = `Field '${error.field}' has invalid value\n` +
+                    `  Allowed: ${expectedValue.join(', ')}\n` +
+                    `  Got: ${JSON.stringify(error.value)}`;
+                formatted.suggestion = `The LLM returned a value not in the allowed list.\n` +
+                    `  • Add the value to the enum list if it's valid\n` +
+                    `  • Provide examples in the field description\n` +
+                    `  • Use pattern matching if exact values aren't required`;
+            }
+            else if (typeof expectedValue === 'string' && expectedValue.startsWith('^')) {
+                // Pattern validation error
+                formatted.message = `Field '${error.field}' doesn't match required pattern\n` +
+                    `  Pattern: ${expectedValue}\n` +
+                    `  Got: ${JSON.stringify(error.value)}`;
+                formatted.suggestion = `The value doesn't match the regex pattern.\n` +
+                    `  • Provide an example in the field description\n` +
+                    `  • Simplify the pattern if it's too strict`;
+            }
+            else if (field?.enum) {
+                formatted.message = `Field '${error.field}' has invalid value\n` +
+                    `  Allowed: ${field.enum.join(', ')}\n` +
+                    `  Got: ${JSON.stringify(error.value)}`;
+                formatted.suggestion = `The LLM returned a value not in the allowed list.\n` +
+                    `  • Add the value to the enum list if it's valid\n` +
+                    `  • Provide examples in the field description\n` +
+                    `  • Use pattern matching if exact values aren't required`;
+            }
+            else if (field?.pattern) {
+                formatted.message = `Field '${error.field}' doesn't match required pattern\n` +
+                    `  Pattern: ${field.pattern}\n` +
+                    `  Got: ${JSON.stringify(error.value)}`;
+                formatted.suggestion = `The value doesn't match the regex pattern.\n` +
+                    `  • Provide an example in the field description\n` +
+                    `  • Simplify the pattern if it's too strict`;
+            }
+            else if (field?.min !== undefined || field?.max !== undefined) {
+                formatted.message = error.message;
+                formatted.suggestion = `Value is out of the allowed range.\n` +
+                    `  • Check if the constraint is correct\n` +
+                    `  • Mention the range in the field description`;
+            }
+            else {
+                // Generic field invalid error
+                formatted.message = error.message;
+            }
+            break;
+        default:
+            formatted.message = error.message;
+    }
+    // Add field location in schema
+    if (schema?.metadata?.name) {
+        formatted.details = [` Field: ${error.field}`, `Schema: ${schema.metadata.name}`];
+    }
+    return formatFormattedError(formatted);
+}
+/**
+ * Helper to format a FormattedError into a string
+ */
+function formatFormattedError(error) {
+    const lines = [`❌ ${error.title}`, `   ${error.message.replace(/\n/g, '\n   ')}`];
+    if (error.suggestion) {
+        lines.push('', `💡 Tip:`);
+        lines.push(`   ${error.suggestion.replace(/\n/g, '\n   ')}`);
+    }
+    if (error.details && error.details.length > 0) {
+        lines.push('', `ℹ️  Details:`);
+        for (const detail of error.details) {
+            lines.push(`   • ${detail}`);
+        }
+    }
+    return lines.join('\n');
+}
+/**
+ * Format LLM error with context and recovery suggestions
+ * Returns a formatted string with title, message, suggestions, and details
+ */
+export function formatLLMError(error, context) {
+    const formatted = {
+        title: 'LLM Service Error',
+        message: error.message,
+        details: [],
+    };
+    switch (error.code) {
+        case LLMErrorCodes.NETWORK_ERROR:
+            formatted.title = 'Network Connection Error';
+            formatted.suggestion = `Cannot reach the LLM service.\n` +
+                `  • Check if the service is running (${context?.baseURL || 'unknown URL'})\n` +
+                `  • For Ollama: run 'ollama serve'\n` +
+                `  • For LM Studio: ensure the server is started\n` +
+                `  • Check firewall settings`;
+            break;
+        case LLMErrorCodes.AUTHENTICATION_ERROR:
+            formatted.title = 'Authentication Failed';
+            formatted.suggestion = `Invalid or missing API key.\n` +
+                `  • Check your API key is correct\n` +
+                `  • Use --api-key option or set in config\n` +
+                `  • For local models (Ollama/LM Studio), API key is not needed`;
+            break;
+        case LLMErrorCodes.RATE_LIMIT:
+            formatted.title = 'Rate Limit Exceeded';
+            const retryAfter = error.details?.retryAfter;
+            formatted.suggestion = retryAfter
+                ? `Too many requests. Retry after ${retryAfter} seconds.`
+                : `Too many requests.\n` +
+                    `  • Wait a moment and try again\n` +
+                    `  • Reduce request frequency\n` +
+                    `  • Check your API plan limits`;
+            break;
+        case LLMErrorCodes.TIMEOUT:
+            formatted.title = 'Request Timeout';
+            formatted.suggestion = `The LLM service didn't respond in time.\n` +
+                `  • Local models: this is normal for long inputs or slower hardware\n` +
+                `  • Try a faster model (e.g., llama3.2:3b instead of 70b)\n` +
+                `  • Reduce input size\n` +
+                `  • Increase timeout in config`;
+            break;
+        case LLMErrorCodes.TOKEN_LIMIT_EXCEEDED:
+            formatted.title = 'Context Window Exceeded';
+            formatted.message = error.message;
+            formatted.suggestion = `The input is too large for this model's context window.\n` +
+                `  • Model: ${context?.model || 'unknown'}\n` +
+                `  • Input length: ~${context?.inputLength || 'unknown'} characters\n` +
+                `\n` +
+                `  Solutions:\n` +
+                `  • Reduce input size (extract relevant sections only)\n` +
+                `  • Use HTML preprocessing to strip noise: --strip-html\n` +
+                `  • Switch to a model with larger context window\n` +
+                `  • Split extraction into multiple passes (coming soon)`;
+            break;
+        case LLMErrorCodes.INVALID_RESPONSE:
+            formatted.title = 'Invalid LLM Response';
+            if (error.message.includes('JSON')) {
+                formatted.suggestion = `The LLM didn't return valid JSON.\n` +
+                    `  • This usually happens with smaller or undertrained models\n` +
+                    `  • Try a more capable model (e.g., llama3.1:8b instead of 3b)\n` +
+                    `  • Simplify your schema\n` +
+                    `  • Reduce input complexity`;
+            }
+            else if (error.message.includes('confidence')) {
+                formatted.suggestion = `The LLM response is missing the confidence score.\n` +
+                    `  • This is a model capability issue\n` +
+                    `  • Try a different model`;
+            }
+            break;
+        case LLMErrorCodes.API_ERROR:
+            // Check for common API error patterns
+            const msg = error.message.toLowerCase();
+            if (msg.includes('context') || msg.includes('token') || msg.includes('length')) {
+                formatted.title = 'Context Window Exceeded';
+                formatted.suggestion = `The input is too large for this model's context window.\n` +
+                    `  • Model: ${context?.model || 'unknown'}\n` +
+                    `  • Input length: ~${context?.inputLength || 'unknown'} characters\n` +
+                    `\n` +
+                    `  Solutions:\n` +
+                    `  • Reduce input size (extract relevant sections only)\n` +
+                    `  • Use HTML preprocessing to strip noise: --strip-html\n` +
+                    `  • Switch to a model with larger context window\n` +
+                    `  • Split extraction into multiple passes (coming soon)`;
+            }
+            else if (msg.includes('model') && msg.includes('not found')) {
+                formatted.title = 'Model Not Found';
+                formatted.suggestion = `The specified model is not available.\n` +
+                    `  • Model: ${context?.model || 'unknown'}\n` +
+                    `  • For Ollama: run 'ollama list' to see available models\n` +
+                    `  • Pull the model: 'ollama pull ${context?.model}'\n` +
+                    `  • For LM Studio: check loaded models in the UI`;
+            }
+            else if (error.statusCode === 404) {
+                formatted.title = 'Endpoint Not Found';
+                formatted.suggestion = `The API endpoint doesn't exist.\n` +
+                    `  • Check the base URL: ${context?.baseURL || 'unknown'}\n` +
+                    `  • Ensure /v1 suffix for Ollama/LM Studio\n` +
+                    `  • Verify the service supports OpenAI-compatible API`;
+            }
+            else if (error.statusCode && error.statusCode >= 500) {
+                formatted.title = 'Service Error';
+                formatted.suggestion = `The LLM service encountered an internal error.\n` +
+                    `  • Check service logs for details\n` +
+                    `  • Try again in a moment\n` +
+                    `  • Report to service provider if persistent`;
+            }
+            break;
+    }
+    // Add error details
+    if (error.statusCode) {
+        formatted.details?.push(`Status: ${error.statusCode}`);
+    }
+    if (context?.model) {
+        formatted.details?.push(`Model: ${context.model}`);
+    }
+    if (context?.baseURL) {
+        formatted.details?.push(`URL: ${context.baseURL}`);
+    }
+    return formatFormattedError(formatted);
+}
+/**
+ * Format multiple validation errors into a readable message
+ */
+export function formatValidationErrors(errors, schema) {
+    if (errors.length === 0) {
+        return 'Validation passed';
+    }
+    const lines = [`Found ${errors.length} validation error${errors.length > 1 ? 's' : ''}:\n`];
+    for (const error of errors) {
+        const formatted = formatValidationError(error, schema, error.value);
+        lines.push(formatted);
+        lines.push('');
+    }
+    return lines.join('\n');
+}
+/**
+ * Format any error into a user-friendly message
+ */
+export function formatError(error, context) {
+    // Handle null/undefined
+    if (error === null || error === undefined) {
+        return 'Unknown error occurred';
+    }
+    // Handle string
+    if (typeof error === 'string') {
+        return error;
+    }
+    // Handle non-object types
+    if (typeof error !== 'object') {
+        return `Unknown error: ${String(error)}`;
+    }
+    // Handle validation error plain objects from pipeline
+    if ('field' in error && 'code' in error && 'message' in error) {
+        const validationError = error;
+        return formatValidationError(validationError, undefined, validationError.value);
+    }
+    // Handle LLMError
+    if (error instanceof Error && 'code' in error && typeof error.code === 'string' && error.code in LLMErrorCodes) {
+        return formatLLMError(error, context);
+    }
+    // Handle SchemaValidationError  
+    if (error instanceof Error && 'errors' in error && Array.isArray(error.errors)) {
+        const schemaError = error;
+        return `Schema validation failed:\n\n${formatValidationErrors(schemaError.errors)}`;
+    }
+    // Handle FormattedError
+    if ('title' in error && 'message' in error) {
+        return formatFormattedError(error);
+    }
+    // Handle common Node.js errors
+    if (error instanceof Error && 'code' in error) {
+        const nodeError = error;
+        if (nodeError.code === 'ENOENT') {
+            const path = nodeError.path || 'file';
+            return `❌ File Not Found\n   Cannot find: ${path}\n\n💡 Tip:\n   • Check the file path is correct\n   • Verify the file exists\n   • Use absolute path or check current directory`;
+        }
+        else if (nodeError.code === 'EACCES' || nodeError.code === 'EPERM') {
+            return `❌ Permission Denied\n   ${error.message}\n\n💡 Tip:\n   • Check file permissions\n   • Make sure you have read access\n   • Try running with appropriate permissions`;
+        }
+    }
+    // Handle generic Error
+    if (error instanceof Error) {
+        return error.message;
+    }
+    // Fallback
+    return `Unknown error: ${JSON.stringify(error)}`;
+}
+//# sourceMappingURL=error-formatter.js.map

package/dist/core/error-formatter.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"error-formatter.js","sourceRoot":"","sources":["../../src/core/error-formatter.ts"],"names":[],"mappings":"AAAA;;GAEG;AAKH,OAAO,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAC;AACjD,OAAO,EAAE,kBAAkB,EAAE,MAAM,aAAa,CAAC;AASjD;;;GAGG;AACH,MAAM,UAAU,qBAAqB,CACjC,KAAsB,EACtB,MAAe,EACf,KAAe;IAEf,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,MAAM,EAAE,MAAM,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;IACtE,MAAM,SAAS,GAAG,KAAK,EAAE,WAAW,CAAC,CAAC,CAAC,KAAK,KAAK,CAAC,WAAW,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC;IAEtE,MAAM,SAAS,GAAmB;QAC9B,KAAK,EAAE,wBAAwB;QAC/B,OAAO,EAAE,EAAE;QACX,OAAO,EAAE,EAAE;KACd,CAAC;IAEF,QAAQ,KAAK,CAAC,IAAI,EAAE,CAAC;QACjB,KAAK,kBAAkB,CAAC,aAAa;YACjC,SAAS,CAAC,OAAO,GAAG,mBAAmB,KAAK,CAAC,KAAK,eAAe,SAAS,EAAE,CAAC;YAC7E,SAAS,CAAC,UAAU,GAAG,KAAK,EAAE,QAAQ;gBAClC,CAAC,CAAC,mEAAmE;gBACrE,CAAC,CAAC,2CAA2C;oBAC3C,gDAAgD;oBAChD,uDAAuD;oBACvD,2DAA2D,CAAC;YAClE,MAAM;QAEV,KAAK,kBAAkB,CAAC,aAAa;YACjC,0EAA0E;YAC1E,MAAM,YAAY,GAAI,KAAK,CAAC,QAAmB,IAAI,KAAK,EAAE,IAAI,IAAI,SAAS,CAAC;YAC5E,MAAM,UAAU,GAAI,KAAK,CAAC,MAAiB,IAAI,OAAO,KAAK,CAAC,KAAK,CAAC;YAClE,MAAM,QAAQ,GAAG,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;YAE7C,SAAS,CAAC,OAAO,GAAG,UAAU,KAAK,CAAC,KAAK,IAAI,SAAS,IAAI;gBACvC,eAAe,YAAY,IAAI;gBAC/B,UAAU,QAAQ,KAAK,UAAU,GAAG,CAAC;YAExD,4BAA4B;YAC5B,IAAI,YAAY,KAAK,QAAQ,IAAI,UAAU,KAAK,QAAQ,EAAE,CAAC;gBACvD,SAAS,CAAC,UAAU,GAAG,kDAAkD;oBACpD,kEAAkE;oBAClE,4EAA4E;oBAC5E,+DAA+D,CAAC;YACzF,CAAC;iBAAM,IAAI,YAAY,KAAK,QAAQ,IAAI,UAAU,KAAK,QAAQ,EAAE,CAAC;gBAC9D,SAAS,CAAC,UAAU,GAAG,kDAAkD;oBACpD,uEAAuE;oBACvE,wDAAwD,CAAC;YAClF,CAAC;iBAAM,IAAI,YAAY,KAAK,SAAS,IAAI,UAAU,KAAK,QAAQ,EAAE,CAAC;gBAC/D,SAAS,CAAC,UAAU,GAAG,iDAAiD;oBACnD,kEAAkE,CAAC;YAC5F,CAAC;YACD,MAAM;QAEV,KAAK,kBAAkB,CAAC,aAAa;YACjC,kEAAkE;YAClE,MAAM,aAAa,GAAG,KAAK,CAAC,QAAQ,CAAC;YACrC,IAAI,KAAK,CAAC,OAAO,CAAC,aAAa,CAAC,EAAE,CAAC;gBAC/B,wBAAwB;gBACxB,SAAS,CAAC,OAAO,GAAG,UAAU,KAAK,CAAC,KAAK,uBAAuB;oBAC7C,cAAc,aAAa,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI;oBAC1C,UAAU,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,EAAE,CAAC;gBAC3D,SAAS,CAAC,UAAU,GAAG,qDAAqD;oBACvD,oDAAoD;oBACpD,iDAAiD;oBACjD,0DAA0D,CAAC;YACpF,CAAC;iBAAM,IAAI,OAAO,aAAa,KAAK,QAAQ,IAAI,aAAa,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;gBAC5E,2BAA2B;gBAC3B,SAAS,CAAC,OAAO,GAAG,UAAU,KAAK,CAAC,KAAK,oCAAoC;oBAC1D,cAAc,aAAa,IAAI;oBAC/B,UAAU,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,EAAE,CAAC;gBAC3D,SAAS,CAAC,UAAU,GAAG,8CAA8C;oBAChD,mDAAmD;oBACnD,6CAA6C,CAAC;YACvE,CAAC;iBAAM,IAAI,KAAK,EAAE,IAAI,EAAE,CAAC;gBACrB,SAAS,CAAC,OAAO,GAAG,UAAU,KAAK,CAAC,KAAK,uBAAuB;oBAC7C,cAAc,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI;oBACvC,UAAU,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,EAAE,CAAC;gBAC3D,SAAS,CAAC,UAAU,GAAG,qDAAqD;oBACvD,oDAAoD;oBACpD,iDAAiD;oBACjD,0DAA0D,CAAC;YACpF,CAAC;iBAAM,IAAI,KAAK,EAAE,OAAO,EAAE,CAAC;gBACxB,SAAS,CAAC,OAAO,GAAG,UAAU,KAAK,CAAC,KAAK,oCAAoC;oBAC1D,cAAc,KAAK,CAAC,OAAO,IAAI;oBAC/B,UAAU,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,EAAE,CAAC;gBAC3D,SAAS,CAAC,UAAU,GAAG,8CAA8C;oBAChD,mDAAmD;oBACnD,6CAA6C,CAAC;YACvE,CAAC;iBAAM,IAAI,KAAK,EAAE,GAAG,KAAK,SAAS,IAAI,KAAK,EAAE,GAAG,KAAK,SAAS,EAAE,CAAC;gBAC9D,SAAS,CAAC,OAAO,GAAG,KAAK,CAAC,OAAO,CAAC;gBAClC,SAAS,CAAC,UAAU,GAAG,sCAAsC;oBACxC,0CAA0C;oBAC1C,gDAAgD,CAAC;YAC1E,CAAC;iBAAM,CAAC;gBACJ,8BAA8B;gBAC9B,SAAS,CAAC,OAAO,GAAG,KAAK,CAAC,OAAO,CAAC;YACtC,CAAC;YACD,MAAM;QAEV;YACI,SAAS,CAAC,OAAO,GAAG,KAAK,CAAC,OAAO,CAAC;IAC1C,CAAC;IAED,+BAA+B;IAC/B,IAAI,MAAM,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC;QACzB,SAAS,CAAC,OAAO,GAAG,CAAC,WAAW,KAAK,CAAC,KAAK,EAAE,EAAE,WAAW,MAAM,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAC;IACtF,CAAC;IAED,OAAO,oBAAoB,CAAC,SAAS,CAAC,CAAC;AAC3C,CAAC;AAED;;GAEG;AACH,SAAS,oBAAoB,CAAC,KAAqB;IAC/C,MAAM,KAAK,GAAa,CAAC,KAAK,KAAK,CAAC,KAAK,EAAE,EAAE,MAAM,KAAK,CAAC,OAAO,CAAC,OAAO,CAAC,KAAK,EAAE,OAAO,CAAC,EAAE,CAAC,CAAC;IAE5F,IAAI,KAAK,CAAC,UAAU,EAAE,CAAC;QACnB,KAAK,CAAC,IAAI,CAAC,EAAE,EAAE,SAAS,CAAC,CAAC;QAC1B,KAAK,CAAC,IAAI,CAAC,MAAM,KAAK,CAAC,UAAU,CAAC,OAAO,CAAC,KAAK,EAAE,OAAO,CAAC,EAAE,CAAC,CAAC;IACjE,CAAC;IAED,IAAI,KAAK,CAAC,OAAO,IAAI,KAAK,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC5C,KAAK,CAAC,IAAI,CAAC,EAAE,EAAE,cAAc,CAAC,CAAC;QAC/B,KAAK,MAAM,MAAM,IAAI,KAAK,CAAC,OAAO,EAAE,CAAC;YACjC,KAAK,CAAC,IAAI,CAAC,QAAQ,MAAM,EAAE,CAAC,CAAC;QACjC,CAAC;IACL,CAAC;IAED,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC5B,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,cAAc,CAAC,KAAe,EAAE,OAI/C;IACG,MAAM,SAAS,GAAmB;QAC9B,KAAK,EAAE,mBAAmB;QAC1B,OAAO,EAAE,KAAK,CAAC,OAAO;QACtB,OAAO,EAAE,EAAE;KACd,CAAC;IAEF,QAAQ,KAAK,CAAC,IAAI,EAAE,CAAC;QACjB,KAAK,aAAa,CAAC,aAAa;YAC5B,SAAS,CAAC,KAAK,GAAG,0BAA0B,CAAC;YAC7C,SAAS,CAAC,UAAU,GAAG,iCAAiC;gBACnC,wCAAwC,OAAO,EAAE,OAAO,IAAI,aAAa,KAAK;gBAC9E,sCAAsC;gBACtC,mDAAmD;gBACnD,6BAA6B,CAAC;YACnD,MAAM;QAEV,KAAK,aAAa,CAAC,oBAAoB;YACnC,SAAS,CAAC,KAAK,GAAG,uBAAuB,CAAC;YAC1C,SAAS,CAAC,UAAU,GAAG,+BAA+B;gBACjC,qCAAqC;gBACrC,6CAA6C;gBAC7C,gEAAgE,CAAC;YACtF,MAAM;QAEV,KAAK,aAAa,CAAC,UAAU;YACzB,SAAS,CAAC,KAAK,GAAG,qBAAqB,CAAC;YACxC,MAAM,UAAU,GAAG,KAAK,CAAC,OAAO,EAAE,UAAgC,CAAC;YACnE,SAAS,CAAC,UAAU,GAAG,UAAU;gBAC7B,CAAC,CAAC,kCAAkC,UAAU,WAAW;gBACzD,CAAC,CAAC,sBAAsB;oBACtB,mCAAmC;oBACnC,gCAAgC;oBAChC,gCAAgC,CAAC;YACvC,MAAM;QAEV,KAAK,aAAa,CAAC,OAAO;YACtB,SAAS,CAAC,KAAK,GAAG,iBAAiB,CAAC;YACpC,SAAS,CAAC,UAAU,GAAG,2CAA2C;gBAC7C,uEAAuE;gBACvE,6DAA6D;gBAC7D,yBAAyB;gBACzB,gCAAgC,CAAC;YACtD,MAAM;QAEV,KAAK,aAAa,CAAC,oBAAoB;YACnC,SAAS,CAAC,KAAK,GAAG,yBAAyB,CAAC;YAC5C,SAAS,CAAC,OAAO,GAAG,KAAK,CAAC,OAAO,CAAC;YAClC,SAAS,CAAC,UAAU,GAAG,2DAA2D;gBAC7D,cAAc,OAAO,EAAE,KAAK,IAAI,SAAS,IAAI;gBAC7C,sBAAsB,OAAO,EAAE,WAAW,IAAI,SAAS,eAAe;gBACtE,IAAI;gBACJ,gBAAgB;gBAChB,0DAA0D;gBAC1D,2DAA2D;gBAC3D,oDAAoD;gBACpD,yDAAyD,CAAC;YAC/E,MAAM;QAEV,KAAK,aAAa,CAAC,gBAAgB;YAC/B,SAAS,CAAC,KAAK,GAAG,sBAAsB,CAAC;YACzC,IAAI,KAAK,CAAC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC,EAAE,CAAC;gBACjC,SAAS,CAAC,UAAU,GAAG,qCAAqC;oBACvC,gEAAgE;oBAChE,kEAAkE;oBAClE,4BAA4B;oBAC5B,6BAA6B,CAAC;YACvD,CAAC;iBAAM,IAAI,KAAK,CAAC,OAAO,CAAC,QAAQ,CAAC,YAAY,CAAC,EAAE,CAAC;gBAC9C,SAAS,CAAC,UAAU,GAAG,qDAAqD;oBACvD,wCAAwC;oBACxC,2BAA2B,CAAC;YACrD,CAAC;YACD,MAAM;QAEV,KAAK,aAAa,CAAC,SAAS;YACxB,sCAAsC;YACtC,MAAM,GAAG,GAAG,KAAK,CAAC,OAAO,CAAC,WAAW,EAAE,CAAC;YAExC,IAAI,GAAG,CAAC,QAAQ,CAAC,SAAS,CAAC,IAAI,GAAG,CAAC,QAAQ,CAAC,OAAO,CAAC,IAAI,GAAG,CAAC,QAAQ,CAAC,QAAQ,CAAC,EAAE,CAAC;gBAC7E,SAAS,CAAC,KAAK,GAAG,yBAAyB,CAAC;gBAC5C,SAAS,CAAC,UAAU,GAAG,2DAA2D;oBAC7D,cAAc,OAAO,EAAE,KAAK,IAAI,SAAS,IAAI;oBAC7C,sBAAsB,OAAO,EAAE,WAAW,IAAI,SAAS,eAAe;oBACtE,IAAI;oBACJ,gBAAgB;oBAChB,0DAA0D;oBAC1D,2DAA2D;oBAC3D,oDAAoD;oBACpD,yDAAyD,CAAC;YACnF,CAAC;iBAAM,IAAI,GAAG,CAAC,QAAQ,CAAC,OAAO,CAAC,IAAI,GAAG,CAAC,QAAQ,CAAC,WAAW,CAAC,EAAE,CAAC;gBAC5D,SAAS,CAAC,KAAK,GAAG,iBAAiB,CAAC;gBACpC,SAAS,CAAC,UAAU,GAAG,yCAAyC;oBAC3C,cAAc,OAAO,EAAE,KAAK,IAAI,SAAS,IAAI;oBAC7C,6DAA6D;oBAC7D,oCAAoC,OAAO,EAAE,KAAK,KAAK;oBACvD,kDAAkD,CAAC;YAC5E,CAAC;iBAAM,IAAI,KAAK,CAAC,UAAU,KAAK,GAAG,EAAE,CAAC;gBAClC,SAAS,CAAC,KAAK,GAAG,oBAAoB,CAAC;gBACvC,SAAS,CAAC,UAAU,GAAG,mCAAmC;oBACrC,2BAA2B,OAAO,EAAE,OAAO,IAAI,SAAS,IAAI;oBAC5D,8CAA8C;oBAC9C,uDAAuD,CAAC;YACjF,CAAC;iBAAM,IAAI,KAAK,CAAC,UAAU,IAAI,KAAK,CAAC,UAAU,IAAI,GAAG,EAAE,CAAC;gBACrD,SAAS,CAAC,KAAK,GAAG,eAAe,CAAC;gBAClC,SAAS,CAAC,UAAU,GAAG,kDAAkD;oBACpD,sCAAsC;oBACtC,6BAA6B;oBAC7B,8CAA8C,CAAC;YACxE,CAAC;YACD,MAAM;IACd,CAAC;IAED,oBAAoB;IACpB,IAAI,KAAK,CAAC,UAAU,EAAE,CAAC;QACnB,SAAS,CAAC,OAAO,EAAE,IAAI,CAAC,WAAW,KAAK,CAAC,UAAU,EAAE,CAAC,CAAC;IAC3D,CAAC;IACD,IAAI,OAAO,EAAE,KAAK,EAAE,CAAC;QACjB,SAAS,CAAC,OAAO,EAAE,IAAI,CAAC,UAAU,OAAO,CAAC,KAAK,EAAE,CAAC,CAAC;IACvD,CAAC;IACD,IAAI,OAAO,EAAE,OAAO,EAAE,CAAC;QACnB,SAAS,CAAC,OAAO,EAAE,IAAI,CAAC,QAAQ,OAAO,CAAC,OAAO,EAAE,CAAC,CAAC;IACvD,CAAC;IAED,OAAO,oBAAoB,CAAC,SAAS,CAAC,CAAC;AAC3C,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,sBAAsB,CAClC,MAAyB,EACzB,MAAe;IAEf,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACtB,OAAO,mBAAmB,CAAC;IAC/B,CAAC;IAED,MAAM,KAAK,GAAa,CAAC,SAAS,MAAM,CAAC,MAAM,oBAAoB,MAAM,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC;IAEtG,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;QACzB,MAAM,SAAS,GAAG,qBAAqB,CAAC,KAAK,EAAE,MAAM,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC;QACpE,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;QACtB,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACnB,CAAC;IAED,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC5B,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,WAAW,CACvB,KAAc,EACd,OAAiC;IAEjC,wBAAwB;IACxB,IAAI,KAAK,KAAK,IAAI,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;QACxC,OAAO,wBAAwB,CAAC;IACpC,CAAC;IAED,gBAAgB;IAChB,IAAI,OAAO,KAAK,KAAK,QAAQ,EAAE,CAAC;QAC5B,OAAO,KAAK,CAAC;IACjB,CAAC;IAED,0BAA0B;IAC1B,IAAI,OAAO,KAAK,KAAK,QAAQ,EAAE,CAAC;QAC5B,OAAO,kBAAkB,MAAM,CAAC,KAAK,CAAC,EAAE,CAAC;IAC7C,CAAC;IAED,sDAAsD;IACtD,IAAI,OAAO,IAAI,KAAK,IAAI,MAAM,IAAI,KAAK,IAAI,SAAS,IAAI,KAAK,EAAE,CAAC;QAC5D,MAAM,eAAe,GAAG,KAAY,CAAC;QACrC,OAAO,qBAAqB,CAAC,eAAe,EAAE,SAAS,EAAE,eAAe,CAAC,KAAK,CAAC,CAAC;IACpF,CAAC;IAED,kBAAkB;IAClB,IAAI,KAAK,YAAY,KAAK,IAAI,MAAM,IAAI,KAAK,IAAI,OAAO,KAAK,CAAC,IAAI,KAAK,QAAQ,IAAI,KAAK,CAAC,IAAI,IAAI,aAAa,EAAE,CAAC;QAC7G,OAAO,cAAc,CAAC,KAAiB,EAAE,OAAO,CAAC,CAAC;IACtD,CAAC;IAED,iCAAiC;IACjC,IAAI,KAAK,YAAY,KAAK,IAAI,QAAQ,IAAI,KAAK,IAAI,KAAK,CAAC,OAAO,CAAE,KAAa,CAAC,MAAM,CAAC,EAAE,CAAC;QACtF,MAAM,WAAW,GAAG,KAAY,CAAC;QACjC,OAAO,gCAAgC,sBAAsB,CAAC,WAAW,CAAC,MAAM,CAAC,EAAE,CAAC;IACxF,CAAC;IAED,wBAAwB;IACxB,IAAI,OAAO,IAAI,KAAK,IAAI,SAAS,IAAI,KAAK,EAAE,CAAC;QACzC,OAAO,oBAAoB,CAAC,KAAuB,CAAC,CAAC;IACzD,CAAC;IAED,+BAA+B;IAC/B,IAAI,KAAK,YAAY,KAAK,IAAI,MAAM,IAAI,KAAK,EAAE,CAAC;QAC5C,MAAM,SAAS,GAAG,KAAY,CAAC;QAC/B,IAAI,SAAS,CAAC,IAAI,KAAK,QAAQ,EAAE,CAAC;YAC9B,MAAM,IAAI,GAAG,SAAS,CAAC,IAAI,IAAI,MAAM,CAAC;YACtC,OAAO,qCAAqC,IAAI,kIAAkI,CAAC;QACvL,CAAC;aAAM,IAAI,SAAS,CAAC,IAAI,KAAK,QAAQ,IAAI,SAAS,CAAC,IAAI,KAAK,OAAO,EAAE,CAAC;YACnE,OAAO,2BAA2B,KAAK,CAAC,OAAO,8HAA8H,CAAC;QAClL,CAAC;IACL,CAAC;IAED,uBAAuB;IACvB,IAAI,KAAK,YAAY,KAAK,EAAE,CAAC;QACzB,OAAO,KAAK,CAAC,OAAO,CAAC;IACzB,CAAC;IAED,WAAW;IACX,OAAO,kBAAkB,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,EAAE,CAAC;AACrD,CAAC"}

package/dist/core/index.d.ts

@@ -4,5 +4,7 @@
 export { ExtractionPipeline, extract } from './pipeline.js';
 export { validateExtractedData } from './validator.js';
 export { PipelineError, PipelineErrorCodes } from './errors.js';
-export type { PipelineConfig, ExtractionRequest, PipelineResult, StepResult, } from './types.js';
+export { stripHtml, preprocess, preprocessWithDetails, resolveHtmlStripOptions, } from './preprocessor.js';
+export type { PreprocessResult } from './preprocessor.js';
+export type { PipelineConfig, ExtractionRequest, PipelineResult, StepResult, HtmlStripOptions, PreprocessingConfig, } from './types.js';
 //# sourceMappingURL=index.d.ts.map

package/dist/core/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/core/index.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,OAAO,EAAE,kBAAkB,EAAE,OAAO,EAAE,MAAM,eAAe,CAAC;AAC5D,OAAO,EAAE,qBAAqB,EAAE,MAAM,gBAAgB,CAAC;AACvD,OAAO,EAAE,aAAa,EAAE,kBAAkB,EAAE,MAAM,aAAa,CAAC;AAChE,YAAY,EACR,cAAc,EACd,iBAAiB,EACjB,cAAc,EACd,UAAU,GACb,MAAM,YAAY,CAAC"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/core/index.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,OAAO,EAAE,kBAAkB,EAAE,OAAO,EAAE,MAAM,eAAe,CAAC;AAC5D,OAAO,EAAE,qBAAqB,EAAE,MAAM,gBAAgB,CAAC;AACvD,OAAO,EAAE,aAAa,EAAE,kBAAkB,EAAE,MAAM,aAAa,CAAC;AAChE,OAAO,EACH,SAAS,EACT,UAAU,EACV,qBAAqB,EACrB,uBAAuB,GAC1B,MAAM,mBAAmB,CAAC;AAC3B,YAAY,EAAE,gBAAgB,EAAE,MAAM,mBAAmB,CAAC;AAC1D,YAAY,EACR,cAAc,EACd,iBAAiB,EACjB,cAAc,EACd,UAAU,EACV,gBAAgB,EAChB,mBAAmB,GACtB,MAAM,YAAY,CAAC"}

package/dist/core/index.js

@@ -4,4 +4,5 @@
 export { ExtractionPipeline, extract } from './pipeline.js';
 export { validateExtractedData } from './validator.js';
 export { PipelineError, PipelineErrorCodes } from './errors.js';
+export { stripHtml, preprocess, preprocessWithDetails, resolveHtmlStripOptions, } from './preprocessor.js';
 //# sourceMappingURL=index.js.map

package/dist/core/index.js.map

@@ -1 +1 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/core/index.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,OAAO,EAAE,kBAAkB,EAAE,OAAO,EAAE,MAAM,eAAe,CAAC;AAC5D,OAAO,EAAE,qBAAqB,EAAE,MAAM,gBAAgB,CAAC;AACvD,OAAO,EAAE,aAAa,EAAE,kBAAkB,EAAE,MAAM,aAAa,CAAC"}
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/core/index.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,OAAO,EAAE,kBAAkB,EAAE,OAAO,EAAE,MAAM,eAAe,CAAC;AAC5D,OAAO,EAAE,qBAAqB,EAAE,MAAM,gBAAgB,CAAC;AACvD,OAAO,EAAE,aAAa,EAAE,kBAAkB,EAAE,MAAM,aAAa,CAAC;AAChE,OAAO,EACH,SAAS,EACT,UAAU,EACV,qBAAqB,EACrB,uBAAuB,GAC1B,MAAM,mBAAmB,CAAC"}

package/dist/core/pipeline.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"pipeline.d.ts","sourceRoot":"","sources":["../../src/core/pipeline.ts"],"names":[],"mappings":"AAAA;;GAEG;AAKH,OAAO,KAAK,EAAE,iBAAiB,EAAE,cAAc,EAAc,MAAM,YAAY,CAAC;AAEhF;;GAEG;AACH,qBAAa,kBAAkB;IAC3B,OAAO,CAAC,KAAK,CAAU;gBAEX,KAAK,GAAE,OAAe;IAIlC;;OAEG;IACG,OAAO,CAAC,OAAO,EAAE,iBAAiB,GAAG,OAAO,CAAC,cAAc,CAAC;IAsKlE;;OAEG;IACH,OAAO,CAAC,UAAU;IAsBlB;;OAEG;YACW,eAAe;CAqBhC;AAED;;GAEG;AACH,wBAAsB,OAAO,CAAC,OAAO,EAAE,iBAAiB,GAAG,OAAO,CAAC,cAAc,CAAC,CAGjF"}
+{"version":3,"file":"pipeline.d.ts","sourceRoot":"","sources":["../../src/core/pipeline.ts"],"names":[],"mappings":"AAAA;;GAEG;AAMH,OAAO,KAAK,EAAE,iBAAiB,EAAE,cAAc,EAAc,MAAM,YAAY,CAAC;AAEhF;;GAEG;AACH,qBAAa,kBAAkB;IAC3B,OAAO,CAAC,KAAK,CAAU;gBAEX,KAAK,GAAE,OAAe;IAIlC;;OAEG;IACG,OAAO,CAAC,OAAO,EAAE,iBAAiB,GAAG,OAAO,CAAC,cAAc,CAAC;IAqLlE;;OAEG;IACH,OAAO,CAAC,UAAU;IAsBlB;;OAEG;YACW,eAAe;CAqBhC;AAED;;GAEG;AACH,wBAAsB,OAAO,CAAC,OAAO,EAAE,iBAAiB,GAAG,OAAO,CAAC,cAAc,CAAC,CAGjF"}

package/dist/core/pipeline.js

@@ -4,6 +4,7 @@
 import { LLMClient } from '../llm/client.js';
 import { validateExtractedData } from './validator.js';
 import { PipelineError, PipelineErrorCodes } from './errors.js';
+import { preprocessWithDetails } from './preprocessor.js';
 /**
  * Main extraction pipeline
  */
@@ -19,6 +20,18 @@ export class ExtractionPipeline {
         const startTime = Date.now();
         const steps = [];
         try {
+            // Step 0: Preprocess input (if configured)
+            let processedInput = request.input;
+            if (request.preprocessing) {
+                const preprocessStep = this.recordStep('preprocess', () => {
+                    return preprocessWithDetails(request.input, request.preprocessing);
+                });
+                steps.push(preprocessStep);
+                if (preprocessStep.success && preprocessStep.data) {
+                    const result = preprocessStep.data;
+                    processedInput = result.text;
+                }
+            }
             // Step 1: Create LLM client
             const clientStep = this.recordStep('create_client', () => {
                 return new LLMClient(request.llmConfig);
@@ -32,7 +45,7 @@ export class ExtractionPipeline {
             const extractStep = await this.recordStepAsync('llm_extract', async () => {
                 return await client.extract({
                     schema: request.schema,
-                    input: request.input,
+                    input: processedInput,
                 });
             });
             steps.push(extractStep);
@@ -123,6 +136,7 @@ export class ExtractionPipeline {
                         {
                             message: error.message,
                             code: error.code,
+                            details: error.details, // Include original error details
                         },
                     ],
                     steps: this.debug ? steps : undefined,
@@ -171,7 +185,7 @@ export class ExtractionPipeline {
             return {
                 step: name,
                 success: false,
-                error: error.message,
+                error, // Preserve full error object for formatting
                 duration,
             };
         }
@@ -196,7 +210,7 @@ export class ExtractionPipeline {
             return {
                 step: name,
                 success: false,
-                error: error.message,
+                error, // Preserve full error object for formatting
                 duration,
             };
         }