converse-mcp-server 4.2.1 → 4.3.0

package/README.md

@@ -274,7 +274,8 @@ SUMMARIZATION_MODEL=gpt-5-nano        # Default: gpt-5-nano
 - **claude-opus-5** (alias: `opus-5`): Previous Opus generation (1M context, 128K output)
 - **claude-opus-4-8** / **claude-opus-4-7** / **claude-opus-4-6**: Earlier Opus generations with adaptive thinking (200K context, 1M via beta, 128K output)
 - **claude-opus-4-5** / **claude-opus-4-1**: Legacy Opus models with extended thinking (64K / 32K output)
-- **claude-sonnet-4-6** (alias: `sonnet`): Best combination of speed and intelligence with adaptive thinking (64K output)
+- **claude-sonnet-5-5** (aliases: `sonnet`, `sonnet-5.5`): Current Sonnet with adaptive thinking and effort (1M context, 128K output)
+- **claude-sonnet-4-6** (alias: `sonnet-4.6`): Previous Sonnet generation with adaptive thinking (64K output)
 - **claude-haiku-4-5** (alias: `haiku`): Fast and intelligent for simple queries (64K output)
 
 ### Mistral Models
@@ -321,6 +322,7 @@ Claude via the Claude Agent SDK. `claude` uses its default model (Opus 5.5, or `
 
 - **claude-opus-5-5** (default; aliases: `opus`, `claude-opus`, `opus-5.5`), **claude-opus-5** (`opus-5`)
 - **claude-fable-5-1** (aliases: `fable`, `claude-fable`, `fable-5.1`), **claude-fable-5** (`fable-5`)
+- **claude-sonnet-5-5** (aliases: `sonnet`, `claude-sonnet`, `sonnet-5.5`)
 - Uses Claude Code CLI authentication (`claude login`) - no API key needed
 - Direct filesystem access from working directory
 
@@ -329,7 +331,7 @@ Claude via the Claude Agent SDK. `claude` uses its default model (Opus 5.5, or `
 Reach these only with the `copilot:` namespace (e.g. `copilot:gpt-6-sol`) — Copilot never serves bare model names. `copilot` alone uses GPT-6 Sol, or `COPILOT_DEFAULT_MODEL`. Uses your GitHub Copilot subscription (`gh auth login`) - no API key needed:
 
 - **OpenAI**: `gpt-6-sol` (aliases: `gpt-6`, `gpt-5`, `sol`), `gpt-6-luna` (alias: `luna`), `gpt-5.6-sol` (alias: `gpt-5.6`), `gpt-5.6-terra`, `gpt-5.6-luna` (all support `reasoning_effort`)
-- **Anthropic**: `claude-opus-5.5` (aliases: `opus`, `claude`), `claude-fable-5` (alias: `fable`), `claude-sonnet-5` (alias: `sonnet`), `claude-opus-5`, `claude-opus-4.8`
+- **Anthropic**: `claude-opus-5.5` (aliases: `opus`, `claude`), `claude-fable-5` (alias: `fable`), `claude-sonnet-5.5` (alias: `sonnet`), `claude-sonnet-5`, `claude-opus-5`, `claude-opus-4.8`
 - **Google**: `gemini-3.1-pro-preview` (aliases: `gemini`, `gemini-3.1-pro`), `gemini-3.8-flash` (aliases: `gemini-3.8`, `flash-3.8`), `gemini-3.5-flash` (alias: `gemini-flash`)
 
 ## 📚 Help & Documentation
@@ -469,7 +471,7 @@ Every entry in `models` takes one of four forms:
 "openai:gpt-6-astra"; // -> OpenAI API, even when Codex is available
 "gemini:pro"; // -> Antigravity CLI (Gemini 3.1 Pro)
 "google:gemini-3.1-pro-preview"; // -> Google API
-"copilot:sonnet"; // -> GitHub Copilot (Claude Sonnet 5)
+"copilot:sonnet"; // -> GitHub Copilot (Claude Sonnet 5.5)
 "openrouter:z-ai/glm-5.2:online"; // -> OpenRouter with web search opt-in
 
 // A bare model ID or alias — the first configured provider that offers it

package/docs/API.md

@@ -524,10 +524,11 @@ Provide models as plain name strings in the `models` array. Each entry is `auto`
 | `claude-opus-5` | `opus-5` | 1M | 128K | Previous Opus, adaptive thinking + effort, compaction |
 | `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6` | `opus-4.8`, `opus-4.7`, `opus-4.6` | 200K (1M beta) | 128K | Previous Opus generations |
 | `claude-opus-4-5-20251101`, `claude-opus-4-1-20250805` | `opus-4.5`, `opus-4.1` | 200K | 64K / 32K | Earlier Opus tiers |
-| `claude-sonnet-4-6` | `sonnet`, `sonnet-4.6` | 200K (1M beta) | 64K | Best speed/intelligence balance, adaptive thinking |
+| `claude-sonnet-5-5` | `sonnet`, `sonnet-5.5`, `claude-sonnet` | 1M | 128K | Current Sonnet, adaptive thinking + effort, compaction |
+| `claude-sonnet-4-6` | `sonnet-4.6` | 200K (1M beta) | 64K | Previous Sonnet, adaptive thinking |
 | `claude-haiku-4-5-20251001` | `haiku`, `haiku-4.5` | 200K | 64K | Fast and intelligent |
 
-Models with adaptive thinking control depth via `reasoning_effort`, which is passed by name to Anthropic's `effort` parameter and clamped to what each model accepts: Opus 5.5, Fable 5, Opus 5, Opus 4.8, and Opus 4.7 take `low`–`max`; Opus 4.6 and Sonnet 4.6 lack `xhigh` (it becomes `max`); Opus 4.5 tops out at `high`. `none` and `minimal` become `low` everywhere. System prompts are automatically cached for 1 hour; cache stats appear in response metadata as `cache_creation_input_tokens` / `cache_read_input_tokens`.
+Models with adaptive thinking control depth via `reasoning_effort`, which is passed by name to Anthropic's `effort` parameter and clamped to what each model accepts: Opus 5.5, Sonnet 5.5, Fable 5, Opus 5, Opus 4.8, and Opus 4.7 take `low`–`max`; Opus 4.6 and Sonnet 4.6 lack `xhigh` (it becomes `max`); Opus 4.5 tops out at `high`. `none` and `minimal` become `low` everywhere. System prompts are automatically cached for 1 hour; cache stats appear in response metadata as `cache_creation_input_tokens` / `cache_read_input_tokens`.
 
 ### Mistral Models
 
@@ -580,7 +581,7 @@ Any other model works via its full `provider/model` slug (e.g. `anthropic/claude
 **Claude** is available through the Claude Agent SDK, using Claude Code CLI authentication instead of an API key:
 
 - **Model**: `claude` (namespaces: `claude`, `claude-code`, `claude-sdk`) — defaults to Claude Opus 5.5 (`claude-opus-5-5`), or `CLAUDE_DEFAULT_MODEL`
-- **Model selection**: `claude-opus-5-5` (`opus`, `claude-opus`, `opus-5.5`), `claude-opus-5` (`opus-5`), `claude-fable-5-1` (`fable`, `claude-fable`, `fable-5.1`), `claude-fable-5` (`fable-5`), e.g. `claude:opus`, `claude:fable`. Other names are rejected with suggestions.
+- **Model selection**: `claude-opus-5-5` (`opus`, `claude-opus`, `opus-5.5`), `claude-opus-5` (`opus-5`), `claude-fable-5-1` (`fable`, `claude-fable`, `fable-5.1`), `claude-fable-5` (`fable-5`), `claude-sonnet-5-5` (`sonnet`, `claude-sonnet`, `sonnet-5.5`), e.g. `claude:opus`, `claude:fable`, `claude:sonnet`. Other names are rejected with suggestions.
 - **Authentication**: `claude login` — no `ANTHROPIC_API_KEY` needed
 - **Availability**: the Claude Agent SDK is installed and `~/.claude/.credentials.json` exists (`$CLAUDE_CONFIG_DIR` when set), or `CLAUDE_CODE_OAUTH_TOKEN`/`ANTHROPIC_API_KEY` is in the environment; on macOS the Keychain login is assumed. An expired login is caught at call time and bare-name/`auto` routing fails over.
 - **Permissions**: runs with `bypassPermissions`
@@ -621,7 +622,7 @@ agy
 Reach these only with the `copilot:` namespace (also `github-copilot:`, `copilot-sdk:`; e.g. `copilot:gpt-6-sol`) — Copilot never serves bare model names. `copilot` alone uses GPT-6 Sol, or `COPILOT_DEFAULT_MODEL`. Available when the Copilot SDK is installed; uses your GitHub Copilot subscription (`gh auth login`) — no API key needed:
 
 - **OpenAI**: `gpt-6-sol` (aliases: `gpt-6`, `gpt-5`, `sol`), `gpt-6-luna` (alias: `luna`), `gpt-5.6-sol` (alias: `gpt-5.6`), `gpt-5.6-terra`, `gpt-5.6-luna` (all accept `reasoning_effort`)
-- **Anthropic**: `claude-opus-5.5` (aliases: `opus`, `claude`), `claude-fable-5` (alias: `fable`), `claude-sonnet-5` (alias: `sonnet`), `claude-opus-5`, `claude-opus-4.8`
+- **Anthropic**: `claude-opus-5.5` (aliases: `opus`, `claude`), `claude-fable-5` (alias: `fable`), `claude-sonnet-5.5` (alias: `sonnet`), `claude-sonnet-5`, `claude-opus-5`, `claude-opus-4.8`
 - **Google**: `gemini-3.1-pro-preview` (aliases: `gemini`, `gemini-3.1-pro`), `gemini-3.8-flash` (aliases: `gemini-3.8`, `flash-3.8`), `gemini-3.5-flash` (alias: `gemini-flash`)
 - Any other `copilot:<id>` is rejected with suggestions
 

package/docs/PROVIDERS.md

@@ -53,7 +53,8 @@ This guide documents all supported AI providers in the Converse MCP Server and t
   - `claude-opus-5` (alias `opus-5`) - Previous Opus generation (1M context, 128K output)
   - `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6` - Earlier Opus generations with adaptive thinking (128K output)
   - `claude-opus-4-5-20251101`, `claude-opus-4-1-20250805` - Legacy Opus models (64K / 32K output)
-  - `claude-sonnet-4-6` (alias `sonnet`) - Best combination of speed and intelligence with adaptive thinking (64K output)
+  - `claude-sonnet-5-5` (aliases `sonnet`, `sonnet-5.5`, `claude-sonnet`) - Current Sonnet: speed and capability for everyday coding and agentic work; adaptive thinking, effort `low`–`max` (1M context, 128K output)
+  - `claude-sonnet-4-6` (alias `sonnet-4.6`) - Previous Sonnet generation with adaptive thinking (64K output)
   - `claude-sonnet-4-5-20250929` - Legacy Sonnet (64K output)
   - `claude-haiku-4-5-20251001` (alias `haiku`) - Fast and intelligent with extended thinking (64K output)
 
@@ -215,7 +216,8 @@ agy
   - `claude-opus-5` (alias: `opus-5`) - Claude Opus 5
   - `claude-fable-5-1` (aliases: `fable`, `claude-fable`, `fable-5.1`) - Claude Fable 5.1 (`claude:fable`)
   - `claude-fable-5` (alias: `fable-5`) - Claude Fable 5.0
-  - Names outside this catalog are rejected with suggestions (e.g. `claude:sonnet` suggests `copilot:sonnet` and `anthropic:sonnet`)
+  - `claude-sonnet-5-5` (aliases: `sonnet`, `claude-sonnet`, `sonnet-5.5`) - Claude Sonnet 5.5 (`claude:sonnet`)
+  - Names outside this catalog are rejected with suggestions (e.g. `claude:haiku` suggests `anthropic:haiku`)
 
 **Key Features:**
 - **Subscription Access**: Uses your Claude subscription instead of API credits
@@ -228,7 +230,7 @@ agy
 **Differences from Anthropic API Provider:**
 - **Authentication**: Claude Code login vs `ANTHROPIC_API_KEY`
 - **Billing**: Claude subscription vs pay-per-use API
-- **Model Routing**: `claude` and `claude:<model>` → SDK provider; `anthropic:<model>` → API provider; bare names both serve as the same model (`opus`, `claude-opus-5-5`, `claude-opus-5`, `claude-fable-5`) → SDK first, then the API on authentication/availability failure; bare names only the API serves (e.g., `sonnet`, `haiku`) → API provider. Bare `fable` is Fable 5.1 on the SDK but Fable 5 on the API, so it does not fail over between them.
+- **Model Routing**: `claude` and `claude:<model>` → SDK provider; `anthropic:<model>` → API provider; bare names both serve as the same model (`opus`, `sonnet`, `claude-opus-5-5`, `claude-opus-5`, `claude-sonnet-5-5`, `claude-fable-5`) → SDK first, then the API on authentication/availability failure; bare names only the API serves (e.g., `haiku`, `sonnet-4.6`) → API provider. Bare `fable` is Fable 5.1 on the SDK but Fable 5 on the API, so it does not fail over between them.
 - **Permissions**: The SDK runs with `bypassPermissions`, and bare names and `auto` reach it whenever it is available. Use `anthropic:<model>` to keep a request on the plain API.
 
 ### GitHub Copilot SDK
@@ -240,7 +242,7 @@ agy
 - **Supported Models** (namespace-only: reach them with `copilot:`, `github-copilot:` or `copilot-sdk:`, e.g. `copilot:gpt-6-sol`; Copilot never serves bare model names):
   - `copilot` - GPT-6 Sol, or `COPILOT_DEFAULT_MODEL`
   - OpenAI: `gpt-6-sol` (aliases: `gpt-6`, `gpt-5`, `sol`), `gpt-6-luna` (alias: `luna`), `gpt-5.6-sol` (alias: `gpt-5.6`), `gpt-5.6-terra`, `gpt-5.6-luna`
-  - Anthropic: `claude-opus-5.5` (aliases: `opus`, `claude`; Copilot Pro+/Max/Business/Enterprise), `claude-fable-5` (alias: `fable`), `claude-sonnet-5` (alias: `sonnet`), `claude-opus-5`, `claude-opus-4.8`
+  - Anthropic: `claude-opus-5.5` (aliases: `opus`, `claude`; Copilot Pro+/Max/Business/Enterprise), `claude-fable-5` (alias: `fable`), `claude-sonnet-5.5` (alias: `sonnet`), `claude-sonnet-5`, `claude-opus-5`, `claude-opus-4.8`
   - Google: `gemini-3.1-pro-preview` (aliases: `gemini`, `gemini-3.1-pro`), `gemini-3.8-flash` (aliases: `gemini-3.8`, `flash-3.8`), `gemini-3.5-flash` (alias: `gemini-flash`)
 - **Reasoning**: The GPT-6 and GPT-5.6 tiers accept `reasoning_effort` (clamped onto Copilot's `low`–`xhigh`).
 - **Unknown IDs**: Any other `copilot:<id>` is rejected with suggestions; only the IDs and aliases above are accepted.
@@ -333,7 +335,7 @@ All providers support streaming responses for real-time output.
 - **Google**:
   - Gemini 3.0 Pro: Thinking levels (low/high) via `reasoning_effort` - always enabled
   - Gemini 2.5 Pro/Flash: Thinking budget (token-based) via `reasoning_effort`
-- **Anthropic**: Claude Fable 5, Opus 4.6+, and Sonnet 4.6 use adaptive thinking (depth controlled by `reasoning_effort` via Anthropic's `effort` parameter); older Claude 4 models use budget-based extended thinking
+- **Anthropic**: Claude Fable 5, Opus 4.6+, and Sonnet 4.6+ use adaptive thinking (depth controlled by `reasoning_effort` via Anthropic's `effort` parameter); older Claude 4 models use budget-based extended thinking
 - **X.AI**: Grok 4.5 maps `reasoning_effort` to `low`/`medium`/`high` and always reasons (cannot be disabled)
 - **Mistral**: `mistral-medium-3-5` and `mistral-small-2603` map `reasoning_effort` to `high` (enabled) or `none` (disabled); `mistral-large-2512` has no adjustable reasoning
 - **DeepSeek**: V4 models use thinking mode via `reasoning_effort` (`none` disables; enabled levels use `high`, `max` uses `max`)
@@ -384,7 +386,7 @@ Examples:
 "fable"                    // Claude Agent SDK (claude-fable-5-1) when set up, otherwise Anthropic API (claude-fable-5)
 "opus"                     // Claude Agent SDK (claude-opus-5-5), else Anthropic API
 "anthropic:opus"           // Anthropic API only
-"sonnet"                   // Anthropic API (claude-sonnet-4-6)
+"sonnet"                   // Claude Agent SDK (claude-sonnet-5-5), else Anthropic API
 "claude"                   // Claude Agent SDK (defaults to Claude Opus 5.5)
 "claude:fable"             // Claude Agent SDK (Claude Fable 5.1)
 "pro"                      // Antigravity CLI (gemini-3.1-pro-preview), else Google API

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "converse-mcp-server",
-  "version": "4.2.1",
+  "version": "4.3.0",
   "description": "Converse MCP Server - Converse with other LLMs with chat and consensus tools",
   "type": "module",
   "main": "src/index.js",
@@ -93,16 +93,16 @@
     ".env.example"
   ],
   "dependencies": {
-    "@anthropic-ai/claude-agent-sdk": "^0.3.282",
-    "@anthropic-ai/sdk": "^0.128.0",
+    "@anthropic-ai/claude-agent-sdk": "^0.3.284",
+    "@anthropic-ai/sdk": "^0.129.0",
     "@github/copilot-sdk": "^1.0.14",
     "@google/genai": "^2.24.0",
     "@lydell/node-pty": "1.2.0-beta.15",
     "@mistralai/mistralai": "^2.7.0",
-    "@modelcontextprotocol/sdk": "^1.30.1",
-    "@openai/codex-sdk": "^0.157.0",
+    "@modelcontextprotocol/sdk": "^1.31.0",
+    "@openai/codex-sdk": "^0.158.0",
     "cors": "^2.8.6",
-    "dotenv": "^18.0.3",
+    "dotenv": "^18.0.4",
     "express": "^5.2.1",
     "lru-cache": "^11.5.3",
     "nanoid": "^6.0.1",
@@ -111,10 +111,10 @@
     "vite": "^8.3.1"
   },
   "devDependencies": {
-    "@vitest/coverage-v8": "^5.0.1",
+    "@vitest/coverage-v8": "^5.0.2",
     "cross-env": "^10.1.0",
     "eslint": "^10.11.0",
     "rimraf": "^6.1.3",
-    "vitest": "^5.0.1"
+    "vitest": "^5.0.2"
   }
 }

package/src/providers/anthropic.js

@@ -37,6 +37,7 @@ const SUPPORTED_MODELS = {
     effortTiers: EFFORT_TIERS_FULL,
     // Absent from Anthropic's compaction compatibility list, unlike Opus 5
     supportsCompaction: false,
+    supportsDefaultFallback: true,
     description:
       'Claude Opus 5.5 - Flagship Opus for complex agentic coding and deep reasoning; matches Fable 5.1 on most work at Opus pricing',
     aliases: [
@@ -93,6 +94,7 @@ const SUPPORTED_MODELS = {
     effortGA: true,
     effortTiers: EFFORT_TIERS_FULL,
     supportsCompaction: true,
+    supportsDefaultFallback: true,
     description:
       'Claude Opus 5 - Previous Opus generation for complex agentic coding and deep reasoning',
     aliases: [
@@ -103,6 +105,37 @@ const SUPPORTED_MODELS = {
       'claude-opus-5.0',
     ],
   },
+  'claude-sonnet-5-5': {
+    modelName: 'claude-sonnet-5-5',
+    friendlyName: 'Claude Sonnet 5.5',
+    contextWindow: 1000000, // 1M context by default - no beta header required
+    maxOutputTokens: 128000,
+    supportsStreaming: true,
+    supportsImages: true,
+    supportsWebSearch: false,
+    supportsThinking: true,
+    supportsAdaptiveThinking: true, // {type: "disabled"} is rejected; adaptive is the only on-mode
+    timeout: 1800000,
+    supportsEffort: true,
+    effortGA: true,
+    effortTiers: EFFORT_TIERS_FULL,
+    supportsCompaction: true,
+    supportsDefaultFallback: true,
+    description:
+      'Claude Sonnet 5.5 - Current Sonnet: speed and capability for everyday coding and agentic work',
+    aliases: [
+      'claude-sonnet-5-5',
+      'claude-sonnet-5.5',
+      'claude-5.5-sonnet',
+      'claude-5-5-sonnet',
+      'sonnet-5.5',
+      'sonnet-5-5',
+      'sonnet5.5',
+      'sonnet5-5',
+      'sonnet',
+      'claude-sonnet',
+    ],
+  },
   'claude-opus-4-8': {
     modelName: 'claude-opus-4-8',
     friendlyName: 'Claude Opus 4.8',
@@ -270,7 +303,7 @@ const SUPPORTED_MODELS = {
     supports1MContext: true, // Beta 1M context support
     supportsCompaction: true, // Beta server-side context compaction
     description:
-      'Claude Sonnet 4.6 - Best combination of speed and intelligence with adaptive thinking',
+      'Claude Sonnet 4.6 - Previous Sonnet generation with adaptive thinking',
     aliases: [
       'claude-sonnet-4-6',
       'claude-4.6-sonnet',
@@ -280,8 +313,6 @@ const SUPPORTED_MODELS = {
       'sonnet4.6',
       'sonnet4-6',
       'claude-sonnet-4.6',
-      'sonnet',
-      'claude-sonnet',
     ],
   },
   'claude-sonnet-4-5-20250929': {
@@ -369,6 +400,24 @@ class AnthropicProviderError extends ProviderError {
   }
 }
 
+/**
+ * A refusal arrives as a successful response whose text is empty or cut off
+ * mid-answer, so it must not be passed on as a (partial) answer. The category
+ * tells the caller whether rephrasing or another model is the way forward.
+ */
+function refusalError(stopDetails) {
+  const category = stopDetails?.category
+    ? ` (category: ${stopDetails.category})`
+    : '';
+  const explanation = stopDetails?.explanation
+    ? `: ${stopDetails.explanation}`
+    : '';
+  return new AnthropicProviderError(
+    `Anthropic declined the request${category}${explanation}`,
+    ErrorCodes.REFUSED,
+  );
+}
+
 /**
  * Resolve model name to canonical form, including aliases
  */
@@ -661,6 +710,13 @@ export const anthropicProvider = {
       );
     }
 
+    // A safety-classifier decline is retried server-side on the model Anthropic
+    // recommends for that refusal category; only a decline by the whole chain
+    // comes back as a refusal.
+    if (modelConfig.supportsDefaultFallback) {
+      betas.push('server-side-fallback-2026-07-01');
+    }
+
     // Add effort beta feature for models that need it (not GA yet)
     if (modelConfig.supportsEffort && reasoning_effort && !modelConfig.effortGA) {
       betas.push('effort-2025-11-24');
@@ -690,6 +746,10 @@ export const anthropicProvider = {
       requestPayload.system = systemPrompt;
     }
 
+    if (modelConfig.supportsDefaultFallback) {
+      requestPayload.fallbacks = 'default';
+    }
+
     // Set max tokens - API requires this field
     if (maxTokens) {
       requestPayload.max_tokens = Math.min(
@@ -823,6 +883,10 @@ export const anthropicProvider = {
       const responseTime = Date.now() - startTime;
       debugLog(`[Anthropic] Response received in ${responseTime}ms`);
 
+      if (response.stop_reason === 'refusal') {
+        throw refusalError(response.stop_details);
+      }
+
       // Extract response content
       let content = '';
 
@@ -965,6 +1029,7 @@ export const anthropicProvider = {
     let thinkingContent = '';
     let lastUsage = null;
     let finishReason = null;
+    let stopDetails = null;
 
     try {
       // Yield start event
@@ -1040,6 +1105,7 @@ export const anthropicProvider = {
             // Message-level updates (usage, stop_reason)
             if (event.delta?.stop_reason) {
               finishReason = event.delta.stop_reason;
+              stopDetails = event.delta.stop_details ?? null;
             }
             if (event.usage) {
               lastUsage = event.usage;
@@ -1083,6 +1149,10 @@ export const anthropicProvider = {
         }
       }
 
+      if (finishReason === 'refusal') {
+        throw refusalError(stopDetails);
+      }
+
       const responseTime = Date.now() - startTime;
       debugLog(`[Anthropic] Streaming completed in ${responseTime}ms`);
 

package/src/providers/claude.js

@@ -93,6 +93,25 @@ const SUPPORTED_MODELS = {
       'Claude Fable 5 via Agent SDK - requires claude login authentication',
     aliases: ['fable-5', 'fable5'],
   },
+  'claude-sonnet-5-5': {
+    modelName: 'claude-sonnet-5-5',
+    friendlyName: 'Claude Sonnet 5.5 (via Agent SDK)',
+    contextWindow: 1000000,
+    maxOutputTokens: 128000,
+    supportsStreaming: true,
+    supportsImages: true,
+    supportsWebSearch: false,
+    timeout: 1800000,
+    description:
+      'Claude Sonnet 5.5 via Agent SDK - requires claude login authentication',
+    aliases: [
+      'sonnet',
+      'claude-sonnet',
+      'claude-sonnet-5.5',
+      'sonnet-5-5',
+      'sonnet-5.5',
+    ],
+  },
 };
 
 /**

package/src/providers/copilot.js

@@ -123,6 +123,18 @@ const SUPPORTED_MODELS = {
     description: 'Anthropic Claude Fable 5 via Copilot subscription',
     aliases: ['fable'],
   },
+  'claude-sonnet-5.5': {
+    modelName: 'claude-sonnet-5.5',
+    friendlyName: 'Claude Sonnet 5.5 (via Copilot)',
+    contextWindow: 200000,
+    maxOutputTokens: 32768,
+    supportsStreaming: true,
+    supportsImages: false,
+    supportsWebSearch: false,
+    timeout: 1800000,
+    description: 'Anthropic Claude Sonnet 5.5 via Copilot subscription',
+    aliases: ['sonnet', 'claude-sonnet-5-5'],
+  },
   'claude-sonnet-5': {
     modelName: 'claude-sonnet-5',
     friendlyName: 'Claude Sonnet 5 (via Copilot)',
@@ -133,7 +145,7 @@ const SUPPORTED_MODELS = {
     supportsWebSearch: false,
     timeout: 1800000,
     description: 'Anthropic Claude Sonnet 5 via Copilot subscription',
-    aliases: ['sonnet'],
+    aliases: [],
   },
   'claude-opus-5': {
     modelName: 'claude-opus-5',

package/src/providers/interface.js

@@ -168,6 +168,7 @@ export const ErrorCodes = {
   // Response errors
   NO_RESPONSE_CONTENT: 'NO_RESPONSE_CONTENT',
   NO_RESPONSE_CHOICE: 'NO_RESPONSE_CHOICE',
+  REFUSED: 'REFUSED',
 
   // Rate limiting and quota
   RATE_LIMIT_EXCEEDED: 'RATE_LIMIT_EXCEEDED',