@everworker/oneringai 0.2.0 → 0.2.2

package/README.md

@@ -27,7 +27,8 @@
   - [13. Streaming](#13-streaming)
   - [14. OAuth for External APIs](#14-oauth-for-external-apis)
   - [15. Developer Tools](#15-developer-tools)
-  - [16. External API Integration](#16-external-api-integration) — Scoped Registry, Vendor Templates, Tool Discovery
+  - [16. Document Reader](#16-document-reader-new) — PDF, DOCX, XLSX, PPTX, CSV, HTML, images
+  - [17. External API Integration](#17-external-api-integration) — Scoped Registry, Vendor Templates, Tool Discovery
 - [MCP Integration](#mcp-model-context-protocol-integration)
 - [Documentation](#documentation)
 - [Examples](#examples)
@@ -54,6 +55,15 @@
 
 ---
 
+## HOSEA APP
+We realize that library alone in these times is not enough to get you excited, so we built a FREE FOREVER desktop app on top of this library to showcase its power! It's as easy to start using as cloning this library's repo, and then `cd apps/hosea` and then `npm install` and then `npm run dev`. Or watch the video first:
+
+![Watch the demo](https://img.youtube.com/vi/_LzDiuOQD8Y/maxresdefault.jpg)](https://www.youtube.com/watch?v=_LzDiuOQD8Y)
+
+Or read the more detailed installation / setup instructions [here](https://github.com/Integrail/oneringai/blob/main/apps/hosea/README.md)
+
+Better to see once and then dig in the code! :)
+
 ## Features
 
 - ✨ **Unified API** - One interface for 10+ AI providers (OpenAI, Anthropic, Google, Groq, DeepSeek, and more)
@@ -77,6 +87,8 @@
 - 📝 **Persistent Instructions** - NEW: Agent-level custom instructions that persist across sessions on disk
 - 🛠️ **Agentic Workflows** - Built-in tool calling and multi-turn conversations
 - 🔧 **Developer Tools** - NEW: Filesystem and shell tools for coding assistants (read, write, edit, grep, glob, bash)
+- 🖥️ **Desktop Automation** - NEW: OS-level computer use — screenshot, mouse, keyboard, and window control for vision-driven agent loops
+- 📄 **Document Reader** - NEW: Universal file-to-text converter — PDF, DOCX, XLSX, PPTX, CSV, HTML, images auto-converted to markdown
 - 🔌 **MCP Integration** - NEW: Model Context Protocol client for seamless tool discovery from local and remote servers
 - 👁️ **Vision Support** - Analyze images with AI across all providers
 - 📋 **Clipboard Integration** - Paste screenshots directly (like Claude Code!)
@@ -254,6 +266,55 @@ const veoJob = await googleVideo.generate({
 });
 ```
 
+### Document Reader (NEW)
+
+Read any document format — agents automatically get markdown text from PDFs, Word docs, spreadsheets, and more:
+
+```typescript
+import { Agent, developerTools } from '@everworker/oneringai';
+
+const agent = Agent.create({
+  connector: 'openai',
+  model: 'gpt-4',
+  tools: developerTools,
+});
+
+// read_file auto-converts binary documents to markdown
+await agent.run('Read /path/to/report.pdf and summarize the key findings');
+await agent.run('Read /path/to/data.xlsx and describe the trends');
+await agent.run('Read /path/to/presentation.pptx and list all slides');
+```
+
+**Programmatic usage:**
+
+```typescript
+import { DocumentReader, readDocumentAsContent } from '@everworker/oneringai';
+
+// Read any file to markdown pieces
+const reader = DocumentReader.create();
+const result = await reader.read('/path/to/report.pdf');
+console.log(result.pieces); // DocumentPiece[] (text + images)
+
+// One-call conversion to LLM Content[] (for multimodal input)
+const content = await readDocumentAsContent('/path/to/slides.pptx', {
+  imageFilter: { minWidth: 100, minHeight: 100 },
+  imageDetail: 'auto',
+});
+
+const response = await agent.run([
+  { type: 'input_text', text: 'Analyze this document:' },
+  ...content,
+]);
+```
+
+**Supported Formats:**
+- **Office**: DOCX, PPTX, ODT, ODP, ODS, RTF (via `officeparser`)
+- **Spreadsheets**: XLSX, CSV (via `exceljs`)
+- **PDF** (via `unpdf`)
+- **HTML** (via Readability + Turndown)
+- **Text**: TXT, MD, JSON, XML, YAML
+- **Images**: PNG, JPG, GIF, WEBP, SVG (pass-through as base64)
+
 ### Web Search
 
 Connector-based web search with multiple providers:
@@ -963,7 +1024,108 @@ await agent.run('Run npm test and report any failures');
 - Timeout protection (default 2 min)
 - Output truncation for large outputs
 
-### 16. External API Integration
+### 16. Desktop Automation Tools (NEW)
+
+OS-level desktop automation for building "computer use" agents — screenshot the screen, send to a vision model, receive tool calls (click, type, etc.), execute them, repeat:
+
+```typescript
+import { desktopTools } from '@everworker/oneringai';
+
+const agent = Agent.create({
+  connector: 'openai',
+  model: 'gpt-4',
+  tools: desktopTools, // All 11 desktop tools
+});
+
+// Agent can now see and interact with the desktop:
+await agent.run('Take a screenshot and describe what you see');
+await agent.run('Open Safari and search for "weather forecast"');
+```
+
+**Available Tools:**
+- **desktop_screenshot** - Capture full screen or region (returns image to vision model)
+- **desktop_mouse_move** - Move cursor to position
+- **desktop_mouse_click** - Click (left/right/middle, single/double/triple)
+- **desktop_mouse_drag** - Drag from one position to another
+- **desktop_mouse_scroll** - Scroll wheel (vertical and horizontal)
+- **desktop_get_cursor** - Get current cursor position
+- **desktop_keyboard_type** - Type text
+- **desktop_keyboard_key** - Press shortcuts (e.g., `ctrl+c`, `cmd+shift+s`, `enter`)
+- **desktop_get_screen_size** - Get screen dimensions and scale factor
+- **desktop_window_list** - List visible windows
+- **desktop_window_focus** - Bring a window to the foreground
+
+**Key Design:**
+- All coordinates are in **physical pixel space** (same as screenshot pixels) — no manual Retina scaling needed
+- Screenshots use the `__images` convention for automatic multimodal handling across all providers (Anthropic, OpenAI, Google)
+- Requires `@nut-tree-fork/nut-js` as an optional peer dependency: `npm install @nut-tree-fork/nut-js`
+
+### 17. Document Reader (NEW)
+
+Universal file-to-LLM-content converter. Reads arbitrary document formats and produces clean markdown text with optional image extraction:
+
+```typescript
+import { DocumentReader, mergeTextPieces } from '@everworker/oneringai';
+
+const reader = DocumentReader.create({
+  defaults: {
+    maxTokens: 50_000,
+    extractImages: true,
+    imageFilter: { minWidth: 100, minHeight: 100 },
+  },
+});
+
+// Read from file path, URL, Buffer, or Blob
+const result = await reader.read('/path/to/report.pdf');
+const result = await reader.read('https://example.com/doc.xlsx');
+const result = await reader.read({ type: 'buffer', buffer: myBuffer, filename: 'doc.docx' });
+
+// Get merged markdown text
+const markdown = mergeTextPieces(result.pieces);
+
+// Metadata
+console.log(result.metadata.format);          // 'pdf'
+console.log(result.metadata.estimatedTokens); // 12500
+console.log(result.metadata.processingTimeMs); // 234
+```
+
+**Automatic Integration — No Code Changes Needed:**
+- **`read_file` tool** — Agents calling `read_file` on a PDF, DOCX, or XLSX get markdown text automatically
+- **`web_fetch` tool** — Documents downloaded from URLs are auto-converted to markdown
+
+**Content Bridge for Multimodal Input:**
+
+```typescript
+import { readDocumentAsContent } from '@everworker/oneringai';
+
+// Convert document directly to Content[] for LLM input
+const content = await readDocumentAsContent('/path/to/slides.pptx', {
+  extractImages: true,
+  imageDetail: 'auto',
+  maxImages: 20,
+});
+
+// Use in agent.run() with text + images
+await agent.run([
+  { type: 'input_text', text: 'Analyze this presentation:' },
+  ...content,
+]);
+```
+
+**Pluggable Architecture:**
+- 6 built-in format handlers (Office, Excel, PDF, HTML, Text, Image)
+- 3 default transformers (header, table formatting, truncation)
+- Custom handlers and transformers via `DocumentReader.create({ handlers, ... })`
+- All heavy dependencies lazy-loaded (officeparser, exceljs, unpdf)
+
+**Image Filtering:**
+- Configurable min dimensions, min size, max count, pattern exclusions
+- Automatically removes junk images (logos, icons, tiny backgrounds)
+- Applied both at extraction time and at content conversion time
+
+See the [User Guide](./USER_GUIDE.md#document-reader) for complete API reference and configuration options.
+
+### 18. External API Integration
 
 Connect your AI agents to 35+ external services with enterprise-grade resilience:
 
@@ -1315,4 +1477,4 @@ MIT License - See [LICENSE](./LICENSE) file.
 
 ---
 
-**Version:** 0.2.0 | **Last Updated:** 2026-02-09 | **[User Guide](./USER_GUIDE.md)** | **[API Reference](./API_REFERENCE.md)** | **[Changelog](./CHANGELOG.md)**
+**Version:** 0.2.1 | **Last Updated:** 2026-02-11 | **[User Guide](./USER_GUIDE.md)** | **[API Reference](./API_REFERENCE.md)** | **[Changelog](./CHANGELOG.md)**

package/dist/capabilities/agents/index.d.cts

@@ -1,4 +1,4 @@
-export { aD as AfterToolContext, av as AgentEventName, A as AgentEvents, ay as AgenticLoopEventName, ax as AgenticLoopEvents, aG as ApprovalResult, aE as ApproveToolContext, m as AuditEntry, aC as BeforeToolContext, aI as ExecutionCompleteEvent, aw as ExecutionConfig, E as ExecutionContext, l as ExecutionMetrics, aH as ExecutionStartEvent, j as HistoryMode, aA as Hook, H as HookConfig, au as HookManager, az as HookName, aL as LLMRequestEvent, aM as LLMResponseEvent, aB as ModifyingHook, aK as ToolCompleteEvent, aF as ToolModification, aJ as ToolStartEvent } from '../../index-MJ14lkui.cjs';
+export { aD as AfterToolContext, av as AgentEventName, A as AgentEvents, ay as AgenticLoopEventName, ax as AgenticLoopEvents, aG as ApprovalResult, aE as ApproveToolContext, m as AuditEntry, aC as BeforeToolContext, aI as ExecutionCompleteEvent, aw as ExecutionConfig, E as ExecutionContext, l as ExecutionMetrics, aH as ExecutionStartEvent, j as HistoryMode, aA as Hook, H as HookConfig, au as HookManager, az as HookName, aL as LLMRequestEvent, aM as LLMResponseEvent, aB as ModifyingHook, aK as ToolCompleteEvent, aF as ToolModification, aJ as ToolStartEvent } from '../../index-D62LXWdW.cjs';
 import '../../IProvider-c4QCbPjn.cjs';
 import '../../Vendor-DYh_bzwo.cjs';
 import 'eventemitter3';

package/dist/capabilities/agents/index.d.ts

@@ -1,4 +1,4 @@
-export { aD as AfterToolContext, av as AgentEventName, A as AgentEvents, ay as AgenticLoopEventName, ax as AgenticLoopEvents, aG as ApprovalResult, aE as ApproveToolContext, m as AuditEntry, aC as BeforeToolContext, aI as ExecutionCompleteEvent, aw as ExecutionConfig, E as ExecutionContext, l as ExecutionMetrics, aH as ExecutionStartEvent, j as HistoryMode, aA as Hook, H as HookConfig, au as HookManager, az as HookName, aL as LLMRequestEvent, aM as LLMResponseEvent, aB as ModifyingHook, aK as ToolCompleteEvent, aF as ToolModification, aJ as ToolStartEvent } from '../../index-B5UaeEvK.js';
+export { aD as AfterToolContext, av as AgentEventName, A as AgentEvents, ay as AgenticLoopEventName, ax as AgenticLoopEvents, aG as ApprovalResult, aE as ApproveToolContext, m as AuditEntry, aC as BeforeToolContext, aI as ExecutionCompleteEvent, aw as ExecutionConfig, E as ExecutionContext, l as ExecutionMetrics, aH as ExecutionStartEvent, j as HistoryMode, aA as Hook, H as HookConfig, au as HookManager, az as HookName, aL as LLMRequestEvent, aM as LLMResponseEvent, aB as ModifyingHook, aK as ToolCompleteEvent, aF as ToolModification, aJ as ToolStartEvent } from '../../index-DVb6vfA3.js';
 import '../../IProvider-DcYJ3YE-.js';
 import '../../Vendor-DYh_bzwo.js';
 import 'eventemitter3';

package/dist/capabilities/images/index.cjs

@@ -342,14 +342,32 @@ var AuthCodePKCEFlow = class {
     if (this.config.usePKCE !== false && verifierData) {
       params.append("code_verifier", verifierData.verifier);
     }
-    const response = await fetch(this.config.tokenUrl, {
+    let response = await fetch(this.config.tokenUrl, {
       method: "POST",
       headers: {
         "Content-Type": "application/x-www-form-urlencoded"
       },
       body: params
     });
-    if (!response.ok) {
+    if (!response.ok && this.config.clientSecret) {
+      const errorText = await response.text();
+      if (isPublicClientError(errorText)) {
+        params.delete("client_secret");
+        response = await fetch(this.config.tokenUrl, {
+          method: "POST",
+          headers: {
+            "Content-Type": "application/x-www-form-urlencoded"
+          },
+          body: params
+        });
+        if (!response.ok) {
+          const retryError = await response.text();
+          throw new Error(`Token exchange failed: ${response.status} ${response.statusText} - ${retryError}`);
+        }
+      } else {
+        throw new Error(`Token exchange failed: ${response.status} ${response.statusText} - ${errorText}`);
+      }
+    } else if (!response.ok) {
       const error = await response.text();
       throw new Error(`Token exchange failed: ${response.status} ${response.statusText} - ${error}`);
     }
@@ -395,14 +413,32 @@ var AuthCodePKCEFlow = class {
     if (this.config.clientSecret) {
       params.append("client_secret", this.config.clientSecret);
     }
-    const response = await fetch(this.config.tokenUrl, {
+    let response = await fetch(this.config.tokenUrl, {
       method: "POST",
       headers: {
         "Content-Type": "application/x-www-form-urlencoded"
       },
       body: params
     });
-    if (!response.ok) {
+    if (!response.ok && this.config.clientSecret) {
+      const errorText = await response.text();
+      if (isPublicClientError(errorText)) {
+        params.delete("client_secret");
+        response = await fetch(this.config.tokenUrl, {
+          method: "POST",
+          headers: {
+            "Content-Type": "application/x-www-form-urlencoded"
+          },
+          body: params
+        });
+        if (!response.ok) {
+          const retryError = await response.text();
+          throw new Error(`Token refresh failed: ${response.status} ${response.statusText} - ${retryError}`);
+        }
+      } else {
+        throw new Error(`Token refresh failed: ${response.status} ${response.statusText} - ${errorText}`);
+      }
+    } else if (!response.ok) {
       const error = await response.text();
       throw new Error(`Token refresh failed: ${response.status} ${response.statusText} - ${error}`);
     }
@@ -457,6 +493,10 @@ var AuthCodePKCEFlow = class {
     }
   }
 };
+function isPublicClientError(responseBody) {
+  const lower = responseBody.toLowerCase();
+  return lower.includes("aadsts700025") || lower.includes("invalid_client") && lower.includes("public");
+}
 
 // src/connectors/oauth/flows/ClientCredentials.ts
 var ClientCredentialsFlow = class {