feat(agent): add provider options passthrough, tool call records, and completion validation retries

readme.md

@@ -91,11 +91,15 @@ The single entry point. Options:
 | `prompt` | `string` | *required* | The user's task/question |
 | `system` | `string` | `undefined` | System prompt |
 | `tools` | `ToolSet` | `{}` | Tools the agent can call |
+| `providerOptions` | `ProviderOptions` | `undefined` | Provider-specific AI SDK request options passed through to `streamText()` |
 | `maxSteps` | `number` | `20` | Max agentic steps before stopping |
 | `messages` | `ModelMessage[]` | `[]` | Conversation history (for multi-turn) |
 | `maxRetries` | `number` | `5` | Max retries on rate-limit/server errors |
 | `onToken` | `(delta: string) => void` | — | Streaming token callback |
 | `onToolCall` | `(name: string) => void` | — | Called when a tool is invoked |
+| `onToolResult` | `(name: string, result: unknown) => void` | — | Called when a tool finishes |
+| `validateCompletion` | `(result) => string \| void` | — | Return a string to reject and reprompt an incomplete run |
+| `maxValidationRetries` | `number` | `0` | Number of validation-triggered reprompts allowed |
 | `onContextOverflow` | `(messages) => messages` | — | Handle context overflow (e.g., compact messages) |
 
 ### `IAgentRunResult`
@@ -107,13 +111,75 @@ interface IAgentRunResult {
   steps: number;             // Number of agentic steps taken
   messages: ModelMessage[];  // Full conversation for multi-turn
   usage: {
-    promptTokens: number;
-    completionTokens: number;
+    inputTokens: number;
+    outputTokens: number;
     totalTokens: number;
   };
+  toolCalls: Array<{
+    toolName: string;
+    input: unknown;
+    output?: unknown;
+    error?: string;
+  }>;
 }
 ```
 
+### OpenAI Provider Options
+
+Use `providerOptions` for provider-specific request settings such as GPT reasoning effort. SmartAgent forwards the object unchanged to AI SDK `streamText()`.
+
+```typescript
+import { getModelSetup } from '@push.rocks/smartai';
+import { runAgent } from '@push.rocks/smartagent';
+
+const setup = getModelSetup({
+  provider: 'openai',
+  model: 'gpt-5.5',
+  apiKey: process.env.OPENAI_API_KEY,
+  providerOptions: {
+    openai: {
+      reasoningEffort: 'xhigh',
+    },
+  },
+});
+
+const result = await runAgent({
+  model: setup.model,
+  system: 'You handle financial documents carefully.',
+  prompt: 'Process this inbox document.',
+  tools,
+  maxSteps: 20,
+  providerOptions: setup.providerOptions,
+});
+
+const saved = result.toolCalls.some((call) =>
+  call.toolName === 'saveVoucher' || call.toolName === 'saveBankStatement',
+);
+```
+
+### Completion Validation
+
+Use `validateCompletion` when a workflow must not finish unless a required side-effect happened. Return `void` to accept the run, or return a string to append that string as a new user message and continue. If retries are exhausted, `runAgent()` throws.
+
+```typescript
+const result = await runAgent({
+  model,
+  prompt: 'Process this inbox document.',
+  tools,
+  maxSteps: 20,
+  maxValidationRetries: 1,
+  validateCompletion: (result) => {
+    const saved = result.toolCalls.some((call) =>
+      call.toolName === 'saveVoucher' || call.toolName === 'saveBankStatement',
+    );
+
+    if (!saved) {
+      return 'You must call saveVoucher or saveBankStatement before finalizing.';
+    }
+  },
+});
+```
+
 ## Defining Tools 🛠️
 
 Tools use Vercel AI SDK's `tool()` helper with Zod schemas: