@everworker/oneringai 0.4.4 → 0.4.6

package/README.md

@@ -92,7 +92,7 @@ Showcasing another amazing "built with oneringai": ["no saas" agentic business t
 - 🔌 **Tool Execution Plugins** - NEW: Pluggable pipeline for logging, analytics, UI updates, custom behavior
 - 💾 **Session Persistence** - Save and resume conversations with full state restoration
 - 👤 **Multi-User Support** - Set `userId` once, flows automatically to all tool executions and session metadata
-- 🔒 **Connector Allowlist** - Restrict agents to a named subset of connectors, composable with access policies
+- 🔒 **Auth Identities** - Restrict agents to specific connectors (and accounts), composable with access policies
 - 🤖 **Universal Agent** - ⚠️ *Deprecated* - Use `Agent` with plugins instead
 - 🤖 **Task Agents** - ⚠️ *Deprecated* - Use `Agent` with `WorkingMemoryPluginNextGen`
 - 🔬 **Research Agent** - ⚠️ *Deprecated* - Use `Agent` with search tools
@@ -120,7 +120,7 @@ Showcasing another amazing "built with oneringai": ["no saas" agentic business t
 - 🔄 **Streaming** - Real-time responses with event streams
 - 📝 **TypeScript** - Full type safety and IntelliSense support
 
-> **v0.2.0 — Multi-User Support:** Set `userId` once on an agent and it automatically flows to all tool executions, OAuth token retrieval, session metadata, and connector scoping. Combine with `connectors` allowlist and access policies for complete multi-tenant isolation. See [Multi-User Support](#multi-user-support-userid) and [Connector Allowlist](#connector-allowlist-connectors) in the User Guide.
+> **v0.2.0 — Multi-User Support:** Set `userId` once on an agent and it automatically flows to all tool executions, OAuth token retrieval, session metadata, and connector scoping. Combine with `identities` and access policies for complete multi-tenant isolation. See [Multi-User Support](#multi-user-support-userid) and [Auth Identities](#auth-identities-identities) in the User Guide.
 
 ## Quick Start
 
@@ -454,7 +454,10 @@ const agent = Agent.create({
   connector: 'openai',
   model: 'gpt-4',
   userId: 'user-123',            // Flows to all tool executions automatically
-  connectors: ['github', 'slack'], // Only these connectors visible to tools
+  identities: [                   // Only these connectors visible to tools
+    { connector: 'github' },
+    { connector: 'slack' },
+  ],
   tools: [weatherTool, emailTool],
   context: {
     features: {
@@ -685,7 +688,7 @@ const agent = Agent.create({
   },
 });
 
-// Agent now has memory_store, memory_retrieve, memory_delete, memory_list tools
+// Agent now has memory_store, memory_retrieve, memory_delete, memory_query tools
 await agent.run('Check weather for SF and remember the result');
 ```
 
@@ -793,7 +796,7 @@ const agent = Agent.create({
 **Available Features:**
 | Feature | Default | Plugin | Associated Tools |
 |---------|---------|--------|------------------|
-| `workingMemory` | `true` | WorkingMemoryPluginNextGen | `memory_store/retrieve/delete/list` |
+| `workingMemory` | `true` | WorkingMemoryPluginNextGen | `memory_store/retrieve/delete/query/cleanup_raw` |
 | `inContextMemory` | `false` | InContextMemoryPluginNextGen | `context_set/delete/list` |
 | `persistentInstructions` | `false` | PersistentInstructionsPluginNextGen | `instructions_set/remove/list/clear` |
 | `userInfo` | `false` | UserInfoPluginNextGen | `user_info_set/get/remove/clear`, `todo_add/update/remove` |
@@ -971,7 +974,7 @@ for await (const event of agent.streamDirect('Tell me a story')) {
 
 **Comparison:**
 
-| Aspect | `run()` / `chat()` | `runDirect()` |
+| Aspect | `run()` | `runDirect()` |
 |--------|-------------------|---------------|
 | History tracking | ✅ | ❌ |
 | Memory/Cache | ✅ | ❌ |
@@ -1639,7 +1642,7 @@ await agent.run('Find available meeting slots for alice and bob this week');
 
 Supports both **delegated** (`/me` — user signs in) and **application** (`/users/{id}` — app-only) permission modes. See the [User Guide](./USER_GUIDE.md#microsoft-graph-connector-tools) for full parameter reference.
 
-### 23. Tool Catalog (NEW)
+### 23. Tool Catalog
 
 When agents have 100+ available tools, sending all definitions to the LLM wastes tokens and degrades performance. The Tool Catalog lets agents discover and load only the categories they need:
 
@@ -1656,14 +1659,22 @@ ToolCatalogRegistry.registerTools('knowledge', [
   { name: 'entity_search', displayName: 'Entity Search', description: 'Search entities', tool: entitySearchTool, safeByDefault: true },
 ]);
 
-// Enable tool catalog on an agent
+// Enable tool catalog with scoping
 const agent = Agent.create({
   connector: 'openai',
   model: 'gpt-4',
+  // Identities control which connector categories are visible
+  identities: [{ connector: 'github' }, { connector: 'slack' }],
   context: {
     features: { toolCatalog: true },
+    toolCategories: ['filesystem', 'knowledge'],  // scope for built-in categories
+    plugins: {
+      toolCatalog: {
+        pinned: ['filesystem'],       // always loaded, LLM can't unload
+        autoLoadCategories: ['knowledge'],  // pre-loaded, LLM can unload
+      },
+    },
   },
-  toolCategories: ['filesystem', 'knowledge'],  // optional scope
 });
 
 // Agent gets 3 metatools: tool_catalog_search, tool_catalog_load, tool_catalog_unload
@@ -1673,8 +1684,10 @@ await agent.run('Search for information about quantum computing');
 
 **Key Features:**
 - **Dynamic loading** — Agent loads only needed categories, saving token budget
-- **Category scoping** — Restrict visible categories per agent (allowlist/blocklist)
-- **Connector discovery** — Connector tools auto-discovered as categories
+- **Pinned categories** — Always-loaded categories that the LLM cannot unload
+- **Dual scoping** — `toolCategories` scopes built-in categories, `identities` scopes connector categories
+- **Dynamic instructions** — LLM sees exactly which categories are available, with `[PINNED]` markers
+- **Connector discovery** — Connector tools auto-discovered as categories, filtered by `identities`
 - **Registry API** — `ToolCatalogRegistry.resolveTools()` for app-level tool resolution
 
 See the [User Guide](./USER_GUIDE.md#tool-catalog) for full documentation.
@@ -1827,4 +1840,4 @@ MIT License - See [LICENSE](./LICENSE) file.
 
 ---
 
-**Version:** 0.4.4 | **Last Updated:** 2026-02-26 | **[User Guide](./USER_GUIDE.md)** | **[API Reference](./API_REFERENCE.md)** | **[Changelog](./CHANGELOG.md)**
+**Version:** 0.4.6 | **Last Updated:** 2026-03-04 | **[User Guide](./USER_GUIDE.md)** | **[API Reference](./API_REFERENCE.md)** | **[Changelog](./CHANGELOG.md)**

package/dist/{ImageModel-OWbA277F.d.ts → ImageModel-1uP-2vk7.d.ts}

@@ -230,11 +230,11 @@ declare class ImageGeneration {
 /**
  * Supported image sizes by model
  */
-type ImageSize = '256x256' | '512x512' | '1024x1024' | '1024x1536' | '1536x1024' | '1792x1024' | '1024x1792' | 'auto';
+type ImageSize = '256x256' | '512x512' | '1024x1024' | '1024x1536' | '1536x1024' | '1792x1024' | '1024x1792' | '1536x1536' | 'auto';
 /**
  * Supported aspect ratios
  */
-type AspectRatio = '1:1' | '3:4' | '4:3' | '9:16' | '16:9' | '3:2' | '2:3';
+type AspectRatio = '1:1' | '3:4' | '4:3' | '9:16' | '16:9' | '3:2' | '2:3' | '1:4' | '4:1' | '1:8' | '8:1' | '2:1' | '1:2';
 /**
  * Image model capabilities
  */
@@ -309,6 +309,12 @@ declare const IMAGE_MODELS: {
         readonly IMAGEN_4_ULTRA: "imagen-4.0-ultra-generate-001";
         /** Imagen 4.0 Fast: Optimized for speed */
         readonly IMAGEN_4_FAST: "imagen-4.0-fast-generate-001";
+        /** Nano Banana 2: Gemini 3.1 Flash native image gen with 4K support */
+        readonly GEMINI_3_1_FLASH_IMAGE: "gemini-3.1-flash-image-preview";
+        /** Nano Banana Pro: Gemini 3 Pro professional design engine with reasoning */
+        readonly GEMINI_3_PRO_IMAGE: "gemini-3-pro-image-preview";
+        /** Nano Banana: Gemini 2.5 Flash native image gen/editing */
+        readonly GEMINI_2_5_FLASH_IMAGE: "gemini-2.5-flash-image";
     };
     readonly grok: {
         /** Grok Imagine Image: xAI image generation with editing support */

package/dist/{ImageModel-Ds5_6sf7.d.cts → ImageModel-BDI37OED.d.cts}

@@ -230,11 +230,11 @@ declare class ImageGeneration {
 /**
  * Supported image sizes by model
  */
-type ImageSize = '256x256' | '512x512' | '1024x1024' | '1024x1536' | '1536x1024' | '1792x1024' | '1024x1792' | 'auto';
+type ImageSize = '256x256' | '512x512' | '1024x1024' | '1024x1536' | '1536x1024' | '1792x1024' | '1024x1792' | '1536x1536' | 'auto';
 /**
  * Supported aspect ratios
  */
-type AspectRatio = '1:1' | '3:4' | '4:3' | '9:16' | '16:9' | '3:2' | '2:3';
+type AspectRatio = '1:1' | '3:4' | '4:3' | '9:16' | '16:9' | '3:2' | '2:3' | '1:4' | '4:1' | '1:8' | '8:1' | '2:1' | '1:2';
 /**
  * Image model capabilities
  */
@@ -309,6 +309,12 @@ declare const IMAGE_MODELS: {
         readonly IMAGEN_4_ULTRA: "imagen-4.0-ultra-generate-001";
         /** Imagen 4.0 Fast: Optimized for speed */
         readonly IMAGEN_4_FAST: "imagen-4.0-fast-generate-001";
+        /** Nano Banana 2: Gemini 3.1 Flash native image gen with 4K support */
+        readonly GEMINI_3_1_FLASH_IMAGE: "gemini-3.1-flash-image-preview";
+        /** Nano Banana Pro: Gemini 3 Pro professional design engine with reasoning */
+        readonly GEMINI_3_PRO_IMAGE: "gemini-3-pro-image-preview";
+        /** Nano Banana: Gemini 2.5 Flash native image gen/editing */
+        readonly GEMINI_2_5_FLASH_IMAGE: "gemini-2.5-flash-image";
     };
     readonly grok: {
         /** Grok Imagine Image: xAI image generation with editing support */

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

@@ -1,4 +1,4 @@
-export { a3 as AfterToolContext, a4 as AgentEventName, w as AgentEvents, a5 as AgenticLoopEventName, a6 as AgenticLoopEvents, a7 as ApprovalResult, a8 as ApproveToolContext, z as AuditEntry, a9 as BeforeToolContext, be as ExecutionCompleteEvent, al as ExecutionConfig, E as ExecutionContext, y as ExecutionMetrics, bf as ExecutionStartEvent, v as HistoryMode, am as Hook, H as HookConfig, an as HookManager, D as HookName, bg as LLMRequestEvent, bh as LLMResponseEvent, aw as ModifyingHook, bi as ToolCompleteEvent, aU as ToolModification, bj as ToolStartEvent } from '../../index-DmYrHH7d.cjs';
+export { a3 as AfterToolContext, a4 as AgentEventName, w as AgentEvents, a5 as AgenticLoopEventName, a6 as AgenticLoopEvents, a7 as ApprovalResult, a8 as ApproveToolContext, z as AuditEntry, a9 as BeforeToolContext, be as ExecutionCompleteEvent, al as ExecutionConfig, E as ExecutionContext, y as ExecutionMetrics, bf as ExecutionStartEvent, v as HistoryMode, am as Hook, H as HookConfig, an as HookManager, D as HookName, bg as LLMRequestEvent, bh as LLMResponseEvent, aw as ModifyingHook, bi as ToolCompleteEvent, aU as ToolModification, bj as ToolStartEvent } from '../../index-DJ-qAK15.cjs';
 import '../../IProvider-B8sqUzJG.cjs';
 import '../../Vendor-DYh_bzwo.cjs';
 import 'eventemitter3';

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

@@ -1,4 +1,4 @@
-export { a3 as AfterToolContext, a4 as AgentEventName, w as AgentEvents, a5 as AgenticLoopEventName, a6 as AgenticLoopEvents, a7 as ApprovalResult, a8 as ApproveToolContext, z as AuditEntry, a9 as BeforeToolContext, be as ExecutionCompleteEvent, al as ExecutionConfig, E as ExecutionContext, y as ExecutionMetrics, bf as ExecutionStartEvent, v as HistoryMode, am as Hook, H as HookConfig, an as HookManager, D as HookName, bg as LLMRequestEvent, bh as LLMResponseEvent, aw as ModifyingHook, bi as ToolCompleteEvent, aU as ToolModification, bj as ToolStartEvent } from '../../index-Dyl6pHfq.js';
+export { a3 as AfterToolContext, a4 as AgentEventName, w as AgentEvents, a5 as AgenticLoopEventName, a6 as AgenticLoopEvents, a7 as ApprovalResult, a8 as ApproveToolContext, z as AuditEntry, a9 as BeforeToolContext, be as ExecutionCompleteEvent, al as ExecutionConfig, E as ExecutionContext, y as ExecutionMetrics, bf as ExecutionStartEvent, v as HistoryMode, am as Hook, H as HookConfig, an as HookManager, D as HookName, bg as LLMRequestEvent, bh as LLMResponseEvent, aw as ModifyingHook, bi as ToolCompleteEvent, aU as ToolModification, bj as ToolStartEvent } from '../../index-oBtp-8Qn.js';
 import '../../IProvider-CxDUGl6n.js';
 import '../../Vendor-DYh_bzwo.js';
 import 'eventemitter3';

package/dist/capabilities/images/index.cjs

@@ -3228,7 +3228,13 @@ var IMAGE_MODELS = {
     /** Imagen 4.0 Ultra: Highest quality */
     IMAGEN_4_ULTRA: "imagen-4.0-ultra-generate-001",
     /** Imagen 4.0 Fast: Optimized for speed */
-    IMAGEN_4_FAST: "imagen-4.0-fast-generate-001"
+    IMAGEN_4_FAST: "imagen-4.0-fast-generate-001",
+    /** Nano Banana 2: Gemini 3.1 Flash native image gen with 4K support */
+    GEMINI_3_1_FLASH_IMAGE: "gemini-3.1-flash-image-preview",
+    /** Nano Banana Pro: Gemini 3 Pro professional design engine with reasoning */
+    GEMINI_3_PRO_IMAGE: "gemini-3-pro-image-preview",
+    /** Nano Banana: Gemini 2.5 Flash native image gen/editing */
+    GEMINI_2_5_FLASH_IMAGE: "gemini-2.5-flash-image"
   },
   [Vendor.Grok]: {
     /** Grok Imagine Image: xAI image generation with editing support */
@@ -3412,7 +3418,7 @@ var IMAGE_MODEL_REGISTRY = {
     sources: {
       documentation: "https://ai.google.dev/gemini-api/docs/imagen",
       pricing: "https://ai.google.dev/pricing",
-      lastVerified: "2026-01-25"
+      lastVerified: "2026-03-04"
     },
     capabilities: {
       sizes: ["1024x1024"],
@@ -3523,7 +3529,7 @@ var IMAGE_MODEL_REGISTRY = {
     sources: {
       documentation: "https://ai.google.dev/gemini-api/docs/imagen",
       pricing: "https://ai.google.dev/pricing",
-      lastVerified: "2026-01-25"
+      lastVerified: "2026-03-04"
     },
     capabilities: {
       sizes: ["1024x1024"],
@@ -3620,7 +3626,8 @@ var IMAGE_MODEL_REGISTRY = {
       }
     },
     pricing: {
-      perImage: 0.08,
+      perImage: 0.06,
+      // Updated per official pricing page (was $0.08)
       currency: "USD"
     }
   },
@@ -3634,7 +3641,7 @@ var IMAGE_MODEL_REGISTRY = {
     sources: {
       documentation: "https://ai.google.dev/gemini-api/docs/imagen",
       pricing: "https://ai.google.dev/pricing",
-      lastVerified: "2026-01-25"
+      lastVerified: "2026-03-04"
     },
     capabilities: {
       sizes: ["1024x1024"],
@@ -3735,6 +3742,141 @@ var IMAGE_MODEL_REGISTRY = {
       currency: "USD"
     }
   },
+  // ======================== Google Nano Banana (Gemini Native Image) ========================
+  "gemini-3.1-flash-image-preview": {
+    name: "gemini-3.1-flash-image-preview",
+    displayName: "Nano Banana 2 (Gemini 3.1 Flash Image)",
+    provider: Vendor.Google,
+    description: "High-efficiency native image generation and editing with 4K support and thinking capabilities",
+    isActive: true,
+    releaseDate: "2026-02-01",
+    sources: {
+      documentation: "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image-preview",
+      pricing: "https://ai.google.dev/pricing",
+      lastVerified: "2026-03-04"
+    },
+    capabilities: {
+      sizes: ["512x512", "1024x1024", "1536x1536", "auto"],
+      aspectRatios: ["1:1", "1:4", "4:1", "1:8", "8:1"],
+      maxImagesPerRequest: 4,
+      outputFormats: ["png", "jpeg"],
+      features: {
+        generation: true,
+        editing: true,
+        variations: false,
+        styleControl: false,
+        qualityControl: true,
+        // Multiple resolution tiers: 0.5K, 1K, 2K, 4K
+        transparency: false,
+        promptRevision: false
+      },
+      limits: { maxPromptLength: 131072 },
+      // 131K input tokens
+      vendorOptions: {
+        outputImageResolution: {
+          type: "enum",
+          label: "Resolution",
+          description: "Output image resolution tier",
+          enum: ["0.5K", "1K", "2K", "4K"],
+          default: "1K",
+          controlType: "select"
+        }
+      }
+    },
+    pricing: {
+      // Per-image, varies by resolution: $0.045 (512px), $0.067 (1K), $0.101 (2K), $0.151 (4K)
+      perImageStandard: 0.067,
+      // 1K default
+      perImageHD: 0.151,
+      // 4K
+      currency: "USD"
+    }
+  },
+  "gemini-3-pro-image-preview": {
+    name: "gemini-3-pro-image-preview",
+    displayName: "Nano Banana Pro (Gemini 3 Pro Image)",
+    provider: Vendor.Google,
+    description: "Professional design engine with reasoning for studio-quality 4K visuals, complex layouts, and precise text rendering",
+    isActive: true,
+    releaseDate: "2025-11-01",
+    sources: {
+      documentation: "https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image-preview",
+      pricing: "https://ai.google.dev/pricing",
+      lastVerified: "2026-03-04"
+    },
+    capabilities: {
+      sizes: ["1024x1024", "auto"],
+      aspectRatios: ["1:1", "3:4", "4:3", "9:16", "16:9"],
+      maxImagesPerRequest: 4,
+      outputFormats: ["png", "jpeg"],
+      features: {
+        generation: true,
+        editing: true,
+        variations: false,
+        styleControl: true,
+        // Reasoning-driven design
+        qualityControl: true,
+        // 1K, 2K, 4K tiers
+        transparency: false,
+        promptRevision: false
+      },
+      limits: { maxPromptLength: 65536 },
+      // 65K input tokens
+      vendorOptions: {
+        outputImageResolution: {
+          type: "enum",
+          label: "Resolution",
+          description: "Output image resolution tier",
+          enum: ["1K", "2K", "4K"],
+          default: "1K",
+          controlType: "select"
+        }
+      }
+    },
+    pricing: {
+      // $0.134 per 1K/2K image, $0.24 per 4K image
+      perImageStandard: 0.134,
+      // 1K/2K
+      perImageHD: 0.24,
+      // 4K
+      currency: "USD"
+    }
+  },
+  "gemini-2.5-flash-image": {
+    name: "gemini-2.5-flash-image",
+    displayName: "Nano Banana (Gemini 2.5 Flash Image)",
+    provider: Vendor.Google,
+    description: "Native image generation and editing designed for fast, creative workflows",
+    isActive: true,
+    releaseDate: "2025-10-01",
+    sources: {
+      documentation: "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-image",
+      pricing: "https://ai.google.dev/pricing",
+      lastVerified: "2026-03-04"
+    },
+    capabilities: {
+      sizes: ["1024x1024", "auto"],
+      aspectRatios: ["1:1", "3:4", "4:3", "9:16", "16:9"],
+      maxImagesPerRequest: 4,
+      outputFormats: ["png", "jpeg"],
+      features: {
+        generation: true,
+        editing: true,
+        variations: false,
+        styleControl: false,
+        qualityControl: false,
+        transparency: false,
+        promptRevision: false
+      },
+      limits: { maxPromptLength: 65536 }
+      // 65K input tokens
+    },
+    pricing: {
+      perImage: 0.039,
+      // $0.039 per image
+      currency: "USD"
+    }
+  },
   // ======================== xAI Grok ========================
   "grok-imagine-image": {
     name: "grok-imagine-image",
@@ -3746,11 +3888,11 @@ var IMAGE_MODEL_REGISTRY = {
     sources: {
       documentation: "https://docs.x.ai/docs/guides/image-generation",
       pricing: "https://docs.x.ai/docs/models",
-      lastVerified: "2026-02-01"
+      lastVerified: "2026-03-04"
     },
     capabilities: {
       sizes: ["1024x1024"],
-      aspectRatios: ["1:1", "4:3", "3:4", "16:9", "9:16", "3:2", "2:3"],
+      aspectRatios: ["1:1", "4:3", "3:4", "16:9", "9:16", "3:2", "2:3", "2:1", "1:2"],
       maxImagesPerRequest: 10,
       outputFormats: ["png", "jpeg"],
       features: {