notdiamond 2.0.0-rc1 → 2.0.0-rc10

package/CHANGELOG.md

@@ -1,5 +1,94 @@
 # Changelog
 
+## 2.0.0-rc10 (2025-11-10)
+
+Full Changelog: [v2.0.0-rc9...v2.0.0-rc10](https://github.com/Not-Diamond/not-diamond-typescript/compare/v2.0.0-rc9...v2.0.0-rc10)
+
+### Features
+
+* **api:** manual updates ([b19bcb6](https://github.com/Not-Diamond/not-diamond-typescript/commit/b19bcb6965272f127345ef26b044fb74ac5a9f2a))
+
+## 2.0.0-rc9 (2025-11-10)
+
+Full Changelog: [v2.0.0-rc9...v2.0.0-rc9](https://github.com/Not-Diamond/not-diamond-typescript/compare/v2.0.0-rc9...v2.0.0-rc9)
+
+### Features
+
+* **api:** manual updates ([33b1872](https://github.com/Not-Diamond/not-diamond-typescript/commit/33b1872a28439049fe06472bdb7502ae9dd0d260))
+
+## 2.0.0-rc9 (2025-11-10)
+
+Full Changelog: [v2.0.0-rc8...v2.0.0-rc9](https://github.com/Not-Diamond/not-diamond-typescript/compare/v2.0.0-rc8...v2.0.0-rc9)
+
+## 2.0.0-rc8 (2025-11-10)
+
+Full Changelog: [v2.0.0-rc6...v2.0.0-rc8](https://github.com/Not-Diamond/not-diamond-typescript/compare/v2.0.0-rc6...v2.0.0-rc8)
+
+### Features
+
+* **api:** manual updates ([46892a1](https://github.com/Not-Diamond/not-diamond-typescript/commit/46892a160ca21dedd68512bbc0f31dd26ab67586))
+
+## 2.0.0-rc6 (2025-11-07)
+
+Full Changelog: [v2.0.0-rc5...v2.0.0-rc6](https://github.com/Not-Diamond/not-diamond-typescript/compare/v2.0.0-rc5...v2.0.0-rc6)
+
+### Features
+
+* **api:** api update ([1d08dd1](https://github.com/Not-Diamond/not-diamond-typescript/commit/1d08dd1ee83a2f4f6147152c044858ad5c113247))
+
+## 2.0.0-rc5 (2025-11-06)
+
+Full Changelog: [v2.0.0-rc4...v2.0.0-rc5](https://github.com/Not-Diamond/not-diamond-typescript/compare/v2.0.0-rc4...v2.0.0-rc5)
+
+### Features
+
+* **api:** manual updates ([92ec1c6](https://github.com/Not-Diamond/not-diamond-typescript/commit/92ec1c69f2c5de881cdc36790aa84bcf568eae70))
+
+## 2.0.0-rc4 (2025-11-05)
+
+Full Changelog: [v2.0.0-rc3...v2.0.0-rc4](https://github.com/Not-Diamond/not-diamond-typescript/compare/v2.0.0-rc3...v2.0.0-rc4)
+
+### Features
+
+* **api:** manual updates ([dd4e78c](https://github.com/Not-Diamond/not-diamond-typescript/commit/dd4e78c59a3b8d07613b72e33cf0e414b62d7e30))
+
+
+### Chores
+
+* update SDK settings ([42a98d0](https://github.com/Not-Diamond/not-diamond-typescript/commit/42a98d0699147509d025e232ad05ed97e6fa9ed3))
+
+## 2.0.0-rc3 (2025-11-05)
+
+Full Changelog: [v2.0.0-rc2...v2.0.0-rc3](https://github.com/Not-Diamond/not-diamond-typescript/compare/v2.0.0-rc2...v2.0.0-rc3)
+
+### Features
+
+* **api:** api update ([d087c64](https://github.com/Not-Diamond/not-diamond-typescript/commit/d087c6421949701acada35f89a1a8d009b581194))
+* **api:** api update ([e431f34](https://github.com/Not-Diamond/not-diamond-typescript/commit/e431f343b558579f7940eacaef5d4f4b3656398f))
+* **api:** api update ([8e6ad30](https://github.com/Not-Diamond/not-diamond-typescript/commit/8e6ad303485025b04622fcaf8d92686581fcc2a7))
+* **api:** enable tests ([d94af20](https://github.com/Not-Diamond/not-diamond-typescript/commit/d94af20e2963644a0034fe1b60a7febf140b204f))
+* **api:** manual updates ([20adad9](https://github.com/Not-Diamond/not-diamond-typescript/commit/20adad9ab8f778b3a8599c41cd91734b2c556614))
+* **api:** regen docs ([ba39a05](https://github.com/Not-Diamond/not-diamond-typescript/commit/ba39a05f842dac7d5eb5153192ec08c3d87bf79f))
+* **api:** verify mock tests enabled ([dcfbb6b](https://github.com/Not-Diamond/not-diamond-typescript/commit/dcfbb6b47900690ea531c510387b7e0392e23abb))
+
+
+### Bug Fixes
+
+* **env:** handle empty environment variable values ([8360f59](https://github.com/Not-Diamond/not-diamond-typescript/commit/8360f59232e1887a1c6560a6195846c1c45f66e9))
+
+
+### Chores
+
+* update SDK settings ([259c1ab](https://github.com/Not-Diamond/not-diamond-typescript/commit/259c1ab15d0c4d8bb1700ffa79fc24481ac4a4ae))
+
+## 2.0.0-rc2 (2025-10-31)
+
+Full Changelog: [v2.0.0-rc1...v2.0.0-rc2](https://github.com/Not-Diamond/not-diamond-typescript/compare/v2.0.0-rc1...v2.0.0-rc2)
+
+### Features
+
+* **api:** api update ([137fd6a](https://github.com/Not-Diamond/not-diamond-typescript/commit/137fd6ae915e6394e13e8d4416bf8d7441246606))
+
 ## 2.0.0-rc1 (2025-10-31)
 
 Full Changelog: [v0.3.0...v2.0.0-rc1](https://github.com/Not-Diamond/not-diamond-typescript/compare/v0.3.0...v2.0.0-rc1)

package/README.md

@@ -4,10 +4,27 @@
 
 This library provides convenient access to the Not Diamond REST API from server-side TypeScript or JavaScript.
 
-The REST API documentation can be found on [docs.notdiamond.ai](https://docs.notdiamond.ai). The full API of this library can be found in [api.md](api.md).
+The library includes type definitions for all request params and response fields.
 
 It is generated with [Stainless](https://www.stainless.com/).
 
+## What is Prompt Adaptation?
+
+Not Diamond specializes in **Prompt Adaptation** - automatically optimizing your prompts to work optimally across different LLMs. Each language model has unique characteristics, instruction-following patterns, and preferred prompt formats. A prompt that works perfectly for GPT-4 might perform poorly on Claude or Gemini.
+
+**The Problem**: Manually rewriting prompts for each model is time-consuming and requires deep expertise in each model's quirks.
+
+**The Solution**: Not Diamond automatically adapts your prompts through:
+
+- Systematic optimization using your evaluation dataset
+- Automated testing across target models
+- Performance metrics to validate improvements
+- Both system prompt and user message template optimization
+
+## Documentation
+
+The REST API documentation can be found on [docs.notdiamond.ai](https://docs.notdiamond.ai). The full API of this library can be found in [api.md](api.md).
+
 ## Installation
 
 ```sh
@@ -16,22 +33,126 @@ npm install notdiamond
 
 ## Usage
 
-The full API of this library can be found in [api.md](api.md).
+### Prompt Adaptation
+
+Automatically optimize your prompts to work better across different language models. Each model has unique characteristics and preferences - what works well for GPT-4 might not work as well for Claude or Gemini. Prompt Adaptation helps you get optimal performance from each model.
+
+#### Quick Start
 
 <!-- prettier-ignore -->
-```js
+```ts
 import NotDiamond from 'notdiamond';
 
 const client = new NotDiamond({
   apiKey: process.env['NOT_DIAMOND_API_KEY'], // This is the default and can be omitted
-  environment: 'staging', // defaults to 'production'
 });
 
-const response = await client.routing.selectModel({
+// Step 1: Start a prompt adaptation job
+const adaptation = await client.prompt.adapt.create({
+  fields: ['question'],
+  system_prompt: 'You are a helpful assistant that answers questions accurately.',
+  target_models: [
+    {
+      model: 'claude-sonnet-4-5-20250929',
+      provider: 'anthropic',
+    },
+    {
+      model: 'gemini-2.5-flash',
+      provider: 'google',
+    },
+  ],
+  template: 'Question: {question}\nAnswer:',
+  train_goldens: [
+    { fields: { question: 'What is 2+2?' }, answer: '4' },
+    { fields: { question: 'What is the capital of France?' }, answer: 'Paris' },
+    { fields: { question: 'Who wrote Romeo and Juliet?' }, answer: 'William Shakespeare' },
+    // Add at least 25 training examples for best results
+    // More examples = better adaptation quality
+  ],
+  test_goldens: [
+    { fields: { question: 'What is 3*3?' }, answer: '9' },
+    { fields: { question: 'What is the largest ocean?' }, answer: 'Pacific Ocean' },
+    // Add test examples to validate performance
+  ],
+  evaluation_metric: 'LLMaaJ:Sem_Sim_1', // Or use custom evaluation
+});
+
+console.log(`Adaptation started: ${adaptation.adaptation_run_id}`);
+
+// Step 2: Poll for completion (typically takes 10-30 minutes)
+let status;
+while (true) {
+  status = await client.prompt.getAdaptStatus(adaptation.adaptation_run_id);
+  console.log(`Status: ${status.status}`);
+  
+  if (status.status === 'queued') {
+    console.log(`Queue position: ${status.queue_position}`);
+  }
+  
+  if (status.status === 'completed' || status.status === 'failed') {
+    break;
+  }
+  
+  await new Promise(resolve => setTimeout(resolve, 30000)); // Poll every 30 seconds
+}
+
+// Step 3: Get the optimized prompts
+if (status.status === 'completed') {
+  const results = await client.prompt.getAdaptResults(adaptation.adaptation_run_id);
+  
+  console.log(`\nOrigin model baseline: ${results.origin_model.score.toFixed(2)}`);
+  
+  for (const target of results.target_models) {
+    console.log('\n' + '='.repeat(50));
+    console.log(`Model: ${target.model.model} (${target.model.provider})`);
+    console.log(`Optimized System Prompt:\n${target.system_prompt}`);
+    console.log(`Optimized Template:\n${target.user_message_template}`);
+    console.log(`Pre-optimization score: ${target.pre_optimization_score.toFixed(2)}`);
+    console.log(`Post-optimization score: ${target.post_optimization_score.toFixed(2)}`);
+    console.log(`Improvement: ${((target.post_optimization_score / target.pre_optimization_score - 1) * 100).toFixed(1)}%`);
+    console.log(`Cost: $${target.cost.toFixed(4)}`);
+  }
+}
+```
+
+#### Key Features
+
+- **Automatic Optimization**: Adapts both system prompts and user message templates
+- **Evaluation Metrics**: Choose from standard metrics (semantic similarity, JSON matching, SQL) or provide custom evaluation
+- **Dataset Requirements**: Minimum 25 training examples (more examples = better results)
+- **Processing Time**: Typically 10-30 minutes depending on dataset size and number of target models
+- **Subscription Tiers**: Support for 1-10 target models depending on your plan
+
+#### Evaluation Metrics
+
+Choose from standard metrics:
+
+- `LLMaaJ:Sem_Sim_1`, `LLMaaJ:Sem_Sim_3`, `LLMaaJ:Sem_Sim_10` - Semantic similarity
+- `LLMaaJ:SQL` - SQL query validation
+- `JSON_Match` - JSON structure matching
+
+Or provide custom evaluation configuration with your own LLM judge.
+
+#### Best Practices
+
+1. **Use Representative Examples**: Include diverse examples from your production workload
+2. **Sufficient Dataset Size**: Use at least 25 training examples (50+ recommended)
+3. **Train/Test Split**: Separate train_goldens and test_goldens for proper validation
+4. **A/B Test Results**: Validate optimized prompts in production before full deployment
+
+For more details, see the [Prompt Adaptation documentation](https://docs.notdiamond.ai/docs/adapting-prompts-to-new-models).
+
+### Model Routing
+
+Not Diamond also provides intelligent model routing to select the best model for your query:
+
+<!-- prettier-ignore -->
+```ts
+const response = await client.modelRouter.selectModel({
   llm_providers: [
     { model: 'gpt-4o', provider: 'openai' },
-    { model: 'claude-3-5-sonnet-20241022', provider: 'anthropic' },
-    { model: 'gemini-1.5-pro', provider: 'google' },
+    { model: 'claude-sonnet-4-5-20250929', provider: 'anthropic' },
+    { model: 'gemini-2.5-flash', provider: 'google' },
   ],
   messages: [
     { role: 'system', content: 'You are a helpful assistant.' },
@@ -52,21 +173,40 @@ import NotDiamond from 'notdiamond';
 
 const client = new NotDiamond({
   apiKey: process.env['NOT_DIAMOND_API_KEY'], // This is the default and can be omitted
-  environment: 'staging', // defaults to 'production'
 });
 
-const params: NotDiamond.RoutingSelectModelParams = {
-  llm_providers: [
-    { model: 'gpt-4o', provider: 'openai' },
-    { model: 'claude-3-5-sonnet-20241022', provider: 'anthropic' },
-    { model: 'gemini-1.5-pro', provider: 'google' },
+const params: NotDiamond.PromptAdaptCreateParams = {
+  fields: ['question', 'context'],
+  system_prompt: 'You are a helpful assistant.',
+  target_models: [
+    {
+      model: 'claude-sonnet-4-5-20250929',
+      provider: 'anthropic',
+    },
   ],
-  messages: [
-    { role: 'system', content: 'You are a helpful assistant.' },
-    { role: 'user', content: 'Explain quantum computing in simple terms' },
+  template: 'Context: {context}\nQuestion: {question}\nAnswer:',
+  train_goldens: [
+    {
+      fields: {
+        question: 'What is 2+2?',
+        context: 'Basic arithmetic',
+      },
+      answer: '4',
+    },
+    // Add at least 25 examples for best results
+  ],
+  test_goldens: [
+    {
+      fields: {
+        question: 'What is 3*3?',
+        context: 'Basic arithmetic',
+      },
+      answer: '9',
+    },
   ],
 };
-const response: NotDiamond.RoutingSelectModelResponse = await client.routing.selectModel(params);
+const response: NotDiamond.PromptAdaptCreateResponse = await client.prompt.adapt.create(params);
+console.log(response.adaptation_run_id);
 ```
 
 Documentation for each method, request param, and response field are available in docstrings and will appear on hover in most modern editors.
@@ -87,56 +227,51 @@ import NotDiamond, { toFile } from 'notdiamond';
 const client = new NotDiamond();
 
 // If you have access to Node `fs` we recommend using `fs.createReadStream()`:
-await client.routing.createSurveyResponse({
-  constraint_priorities: 'constraint_priorities',
-  email: 'email',
-  llm_providers: 'llm_providers',
-  use_case_desc: 'use_case_desc',
-  user_id: 'user_id',
-  'x-token': 'x-token',
+await client.customRouter.trainCustomRouter({
   dataset_file: fs.createReadStream('/path/to/file'),
+  language: 'english',
+  llm_providers:
+    '[{"provider": "openai", "model": "gpt-4o"}, {"provider": "anthropic", "model": "claude-sonnet-4-5-20250929"}]',
+  maximize: true,
+  prompt_column: 'prompt',
 });
 
 // Or if you have the web `File` API you can pass a `File` instance:
-await client.routing.createSurveyResponse({
-  constraint_priorities: 'constraint_priorities',
-  email: 'email',
-  llm_providers: 'llm_providers',
-  use_case_desc: 'use_case_desc',
-  user_id: 'user_id',
-  'x-token': 'x-token',
+await client.customRouter.trainCustomRouter({
   dataset_file: new File(['my bytes'], 'file'),
+  language: 'english',
+  llm_providers:
+    '[{"provider": "openai", "model": "gpt-4o"}, {"provider": "anthropic", "model": "claude-sonnet-4-5-20250929"}]',
+  maximize: true,
+  prompt_column: 'prompt',
 });
 
 // You can also pass a `fetch` `Response`:
-await client.routing.createSurveyResponse({
-  constraint_priorities: 'constraint_priorities',
-  email: 'email',
-  llm_providers: 'llm_providers',
-  use_case_desc: 'use_case_desc',
-  user_id: 'user_id',
-  'x-token': 'x-token',
+await client.customRouter.trainCustomRouter({
   dataset_file: await fetch('https://somesite/file'),
+  language: 'english',
+  llm_providers:
+    '[{"provider": "openai", "model": "gpt-4o"}, {"provider": "anthropic", "model": "claude-sonnet-4-5-20250929"}]',
+  maximize: true,
+  prompt_column: 'prompt',
 });
 
 // Finally, if none of the above are convenient, you can use our `toFile` helper:
-await client.routing.createSurveyResponse({
-  constraint_priorities: 'constraint_priorities',
-  email: 'email',
-  llm_providers: 'llm_providers',
-  use_case_desc: 'use_case_desc',
-  user_id: 'user_id',
-  'x-token': 'x-token',
+await client.customRouter.trainCustomRouter({
   dataset_file: await toFile(Buffer.from('my bytes'), 'file'),
+  language: 'english',
+  llm_providers:
+    '[{"provider": "openai", "model": "gpt-4o"}, {"provider": "anthropic", "model": "claude-sonnet-4-5-20250929"}]',
+  maximize: true,
+  prompt_column: 'prompt',
 });
-await client.routing.createSurveyResponse({
-  constraint_priorities: 'constraint_priorities',
-  email: 'email',
-  llm_providers: 'llm_providers',
-  use_case_desc: 'use_case_desc',
-  user_id: 'user_id',
-  'x-token': 'x-token',
+await client.customRouter.trainCustomRouter({
   dataset_file: await toFile(new Uint8Array([0, 1, 2]), 'file'),
+  language: 'english',
+  llm_providers:
+    '[{"provider": "openai", "model": "gpt-4o"}, {"provider": "anthropic", "model": "claude-sonnet-4-5-20250929"}]',
+  maximize: true,
+  prompt_column: 'prompt',
 });
 ```
 
@@ -148,27 +283,47 @@ a subclass of `APIError` will be thrown:
 
 <!-- prettier-ignore -->
 ```ts
-const response = await client.routing
-  .selectModel({
-    llm_providers: [
-      { model: 'gpt-4o', provider: 'openai' },
-      { model: 'claude-3-5-sonnet-20241022', provider: 'anthropic' },
-      { model: 'gemini-1.5-pro', provider: 'google' },
+import NotDiamond from 'notdiamond';
+
+const client = new NotDiamond();
+
+try {
+  await client.prompt.adapt.create({
+    fields: ['question'],
+    system_prompt: 'You are a helpful assistant.',
+    target_models: [
+      {
+        model: 'claude-sonnet-4-5-20250929',
+        provider: 'anthropic',
+      },
+      {
+        model: 'gemini-2.5-flash',
+        provider: 'google',
+      },
     ],
-    messages: [
-      { role: 'system', content: 'You are a helpful assistant.' },
-      { role: 'user', content: 'Explain quantum computing in simple terms' },
+    template: 'Question: {question}\nAnswer:',
+    train_goldens: [
+      { fields: { question: 'What is 2+2?' }, answer: '4' },
+      // Add at least 25 examples...
+    ],
+    test_goldens: [
+      { fields: { question: 'What is 3*3?' }, answer: '9' },
     ],
-  })
-  .catch(async (err) => {
-    if (err instanceof NotDiamond.APIError) {
-      console.log(err.status); // 400
-      console.log(err.name); // BadRequestError
-      console.log(err.headers); // {server: 'nginx', ...}
-    } else {
-      throw err;
-    }
   });
+} catch (err) {
+  if (err instanceof NotDiamond.APIConnectionError) {
+    console.log('The server could not be reached');
+    console.log(err.cause); // an underlying Error, likely from fetch()
+  } else if (err instanceof NotDiamond.RateLimitError) {
+    console.log('A 429 status code was received; we should back off a bit.');
+  } else if (err instanceof NotDiamond.APIError) {
+    console.log(err.status); // 400
+    console.log(err.name); // BadRequestError
+    console.log(err.headers); // {server: 'nginx', ...}
+  } else {
+    throw err;
+  }
+}
 ```
 
 Error codes are as follows:
@@ -200,7 +355,28 @@ const client = new NotDiamond({
 });
 
 // Or, configure per-request:
-await client.routing.selectModel({ llm_providers: [{ model: 'gpt-4o', provider: 'openai' }, { model: 'claude-3-5-sonnet-20241022', provider: 'anthropic' }, { model: 'gemini-1.5-pro', provider: 'google' }], messages: [{ role: 'system', content: 'You are a helpful assistant.' }, { role: 'user', content: 'Explain quantum computing in simple terms' }] }, {
+await client.prompt.adapt.create({
+  fields: ['question'],
+  system_prompt: 'You are a helpful assistant.',
+  target_models: [
+    {
+      model: 'claude-sonnet-4-5-20250929',
+      provider: 'anthropic',
+    },
+    {
+      model: 'gemini-2.5-flash',
+      provider: 'google',
+    },
+  ],
+  template: 'Question: {question}\nAnswer:',
+  train_goldens: [
+    { fields: { question: 'What is 2+2?' }, answer: '4' },
+    // Add at least 25 examples...
+  ],
+  test_goldens: [
+    { fields: { question: 'What is 3*3?' }, answer: '9' },
+  ],
+}, {
   maxRetries: 5,
 });
 ```
@@ -216,9 +392,9 @@ const client = new NotDiamond({
   timeout: 20 * 1000, // 20 seconds (default is 1 minute)
 });
 
-// Override per-request:
-await client.routing.selectModel({ llm_providers: [{ model: 'gpt-4o', provider: 'openai' }, { model: 'claude-3-5-sonnet-20241022', provider: 'anthropic' }, { model: 'gemini-1.5-pro', provider: 'google' }], messages: [{ role: 'system', content: 'You are a helpful assistant.' }, { role: 'user', content: 'Explain quantum computing in simple terms' }] }, {
-  timeout: 5 * 1000,
+// Override per-request (note: prompt adaptation may take 10-30 minutes, so increase timeout accordingly):
+await client.prompt.getAdaptStatus('your-adaptation-run-id', {
+  timeout: 120 * 1000, // 2 minutes
 });
 ```
 
@@ -240,37 +416,59 @@ Unlike `.asResponse()` this method consumes the body, returning once it is parse
 ```ts
 const client = new NotDiamond();
 
-const response = await client.routing
-  .selectModel({
-    llm_providers: [
-      { model: 'gpt-4o', provider: 'openai' },
-      { model: 'claude-3-5-sonnet-20241022', provider: 'anthropic' },
-      { model: 'gemini-1.5-pro', provider: 'google' },
+const response = await client.prompt.adapt
+  .create({
+    fields: ['question'],
+    system_prompt: 'You are a helpful assistant.',
+    target_models: [
+      {
+        model: 'claude-sonnet-4-5-20250929',
+        provider: 'anthropic',
+      },
+      {
+        model: 'gemini-2.5-flash',
+        provider: 'google',
+      },
     ],
-    messages: [
-      { role: 'system', content: 'You are a helpful assistant.' },
-      { role: 'user', content: 'Explain quantum computing in simple terms' },
+    template: 'Question: {question}\nAnswer:',
+    train_goldens: [
+      { fields: { question: 'What is 2+2?' }, answer: '4' },
+      // Add at least 25 examples...
+    ],
+    test_goldens: [
+      { fields: { question: 'What is 3*3?' }, answer: '9' },
     ],
   })
   .asResponse();
 console.log(response.headers.get('X-My-Header'));
 console.log(response.statusText); // access the underlying Response object
 
-const { data: response, response: raw } = await client.routing
-  .selectModel({
-    llm_providers: [
-      { model: 'gpt-4o', provider: 'openai' },
-      { model: 'claude-3-5-sonnet-20241022', provider: 'anthropic' },
-      { model: 'gemini-1.5-pro', provider: 'google' },
+const { data: adaptResponse, response: raw } = await client.prompt.adapt
+  .create({
+    fields: ['question'],
+    system_prompt: 'You are a helpful assistant.',
+    target_models: [
+      {
+        model: 'claude-sonnet-4-5-20250929',
+        provider: 'anthropic',
+      },
+      {
+        model: 'gemini-2.5-flash',
+        provider: 'google',
+      },
+    ],
+    template: 'Question: {question}\nAnswer:',
+    train_goldens: [
+      { fields: { question: 'What is 2+2?' }, answer: '4' },
+      // Add at least 25 examples...
     ],
-    messages: [
-      { role: 'system', content: 'You are a helpful assistant.' },
-      { role: 'user', content: 'Explain quantum computing in simple terms' },
+    test_goldens: [
+      { fields: { question: 'What is 3*3?' }, answer: '9' },
     ],
   })
   .withResponse();
 console.log(raw.headers.get('X-My-Header'));
-console.log(response.providers);
+console.log(adaptResponse.adaptation_run_id);
 ```
 
 ### Logging
@@ -350,10 +548,14 @@ parameter. This library doesn't validate at runtime that the request matches the
 send will be sent as-is.
 
 ```ts
-client.routing.selectModel({
-  // ...
-  // @ts-expect-error baz is not yet public
-  baz: 'undocumented option',
+client.prompt.adapt.create({
+  fields: ['question'],
+  system_prompt: 'You are a helpful assistant.',
+  target_models: [{ model: 'claude-sonnet-4-5-20250929', provider: 'anthropic' }],
+  template: 'Question: {question}\nAnswer:',
+  train_goldens: [{ fields: { question: 'What is 2+2?' }, answer: '4' }],
+  // @ts-expect-error experimental_feature is not yet public
+  experimental_feature: true,
 });
 ```