feat(providers): add Claude Sonnet 5.5 and make it the default model

apps/docs/content/docs/agents/index.mdx

@@ -17,7 +17,7 @@ The example throughout is an agent that scores inbound sales leads.
 
 ## The Agent block
 
-You set up the reasoning step by giving the Agent block a **model** and a **prompt**. The model is the LLM that powers it; you pick one from the available providers, and the default is `claude-sonnet-5`. The prompt is a system message that defines who the agent is and how it should behave, plus a user message that carries the input, usually a reference like `<start.input>`.
+You set up the reasoning step by giving the Agent block a **model** and a **prompt**. The model is the LLM that powers it; you pick one from the available providers, and the default is `claude-sonnet-5-5`. The prompt is a system message that defines who the agent is and how it should behave, plus a user message that carries the input, usually a reference like `<start.input>`.
 
 When it runs, the Agent block reasons, calls any tools it needs, and stores its result under its own name. By default that result is free text in `content`, read by a later block as `<agent.content>`, alongside run details like the model used, token counts, tool calls, and cost. Every setting and output field is in the [Agent block reference](/workflows/blocks/agent).
 

apps/docs/content/docs/getting-started/index.mdx

@@ -28,7 +28,7 @@ Build a people research agent in 10 minutes. It takes a name through a chat inte
     - **System**: "You are a people research agent. When given a person's name, use your search tools to find their location, profession, educational background, and other relevant details."
     - **User**: insert `<start.input>` so the agent reads whatever the chat receives.
 
-    Leave the **Model** on the default (`claude-sonnet-5`), or pick any other.
+    Leave the **Model** on the default (`claude-sonnet-5-5`), or pick any other.
 
     <div className="mx-auto w-full overflow-hidden rounded-lg">
       <Video src="getting-started/started-2.mp4" width={700} height={450} />

apps/docs/content/docs/workflows/blocks/agent.mdx

@@ -25,7 +25,7 @@ Answer in two sentences, cite the doc you used, and never guess a price.
 
 ### Model
 
-The model that runs the step. Defaults to `claude-sonnet-5`. Type or pick any model from OpenAI, Anthropic, Google, xAI, Groq, Cerebras, DeepSeek, Azure, AWS Bedrock, Google Vertex, or OpenRouter, or a local model through Ollama or VLLM.
+The model that runs the step. Defaults to `claude-sonnet-5-5`. Type or pick any model from OpenAI, Anthropic, Google, xAI, Groq, Cerebras, DeepSeek, Azure, AWS Bedrock, Google Vertex, or OpenRouter, or a local model through Ollama or VLLM.
 
 For a custom cloud deployment, enter its provider prefix and model ID: `azure/my-deployment`, `azure-anthropic/my-deployment`, `bedrock/my-inference-profile`, or `vertex/my-gemini-model`. The prefix selects the provider and shows its credential fields even when the ID is absent from the catalog. Bedrock accepts full inference profile ARNs after `bedrock/`; Vertex uses the Gemini API and accepts Google model resource names. The deployment must support the selected provider's API. Custom IDs have no catalog pricing or token limits.
 
@@ -159,7 +159,7 @@ Live tool-call chips stream for **OpenAI, Anthropic, Azure Anthropic, Google, Ve
 | Provider | Streamed thinking | Models |
 |----------|-------------------|--------|
 | OpenAI | Summaries only — Requires OpenAI organization verification; falls back to no summaries. | `gpt-6-astra`, `gpt-6-sol`, `gpt-6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-pro`, `gpt-5.5`, `gpt-5.4-pro`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.3-codex`, `gpt-5.2-pro`, `gpt-5.2`, `gpt-5.1`, `gpt-5-pro`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `o4-mini`, `o3`, `o3-mini`, `o1` |
-| Anthropic | Summaries only — These generations omit full thinking; Sim requests summarized thinking on streaming runs. | `claude-fable-5-1`, `claude-fable-5`, `claude-sonnet-5`, `claude-opus-5-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-4-6`, `claude-opus-4-5`, `claude-sonnet-4-5`, `claude-haiku-4-5` |
+| Anthropic | Summaries only — These generations omit full thinking; Sim requests summarized thinking on streaming runs. | `claude-fable-5-1`, `claude-fable-5`, `claude-sonnet-5-5`, `claude-sonnet-5`, `claude-opus-5-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-4-6`, `claude-opus-4-5`, `claude-sonnet-4-5`, `claude-haiku-4-5` |
 | Azure OpenAI | Summaries only — Requires OpenAI organization verification; falls back to no summaries. | `azure/gpt-6-astra`, `azure/gpt-5.6-sol`, `azure/gpt-5.6-terra`, `azure/gpt-5.6-luna`, `azure/gpt-5.5`, `azure/gpt-5.4-pro`, `azure/gpt-5.4`, `azure/gpt-5.4-mini`, `azure/gpt-5.4-nano`, `azure/gpt-5.2`, `azure/gpt-5.1`, `azure/gpt-5.1-codex`, `azure/gpt-5`, `azure/gpt-5-mini`, `azure/gpt-5-nano`, `azure/o3`, `azure/o4-mini` |
 | Azure Anthropic | Summaries only — These generations omit full thinking; Sim requests summarized thinking on streaming runs. | `azure-anthropic/claude-fable-5-1`, `azure-anthropic/claude-opus-5`, `azure-anthropic/claude-opus-4-8`, `azure-anthropic/claude-opus-4-7`, `azure-anthropic/claude-opus-4-6`, `azure-anthropic/claude-opus-4-5`, `azure-anthropic/claude-sonnet-5`, `azure-anthropic/claude-sonnet-4-6`, `azure-anthropic/claude-sonnet-4-5`, `azure-anthropic/claude-opus-4-1`, `azure-anthropic/claude-haiku-4-5` |
 | Google | Summaries only | `gemini-3.8-flash`, `gemini-3.7-flash`, `gemini-3.6-flash`, `gemini-3.5-flash-lite`, `gemini-3.5-flash`, `gemini-3.1-pro-preview`, `gemini-3.1-flash-lite`, `gemini-3-flash-preview`, `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.5-flash-lite` |

apps/docs/content/docs/workflows/blocks/evaluator.mdx

@@ -30,7 +30,7 @@ The content to score. Usually an earlier output like `<agent.content>`. Structur
 
 ### Model
 
-The model that does the scoring, defaulting to `claude-sonnet-5`. Stronger reasoning models give more consistent scores. Type or pick any supported model. **Temperature** and a **System Prompt** are available under advanced, and on hosted Sim the API key is supplied for you.
+The model that does the scoring, defaulting to `claude-sonnet-5-5`. Stronger reasoning models give more consistent scores. Type or pick any supported model. **Temperature** and a **System Prompt** are available under advanced, and on hosted Sim the API key is supplied for you.
 
 ### Fallback models
 

apps/docs/content/docs/workflows/blocks/router.mdx

@@ -33,7 +33,7 @@ Each route is a **title** and a **description** of when to choose it ("Route her
 
 ### Model
 
-The model that makes the decision, defaulting to `claude-sonnet-5`. Stronger reasoning models route more accurately; a faster, cheaper model is fine when the routes are clearly distinct. Type or pick any supported model, or a local one through Ollama or VLLM. On hosted Sim the API key is supplied for you.
+The model that makes the decision, defaulting to `claude-sonnet-5-5`. Stronger reasoning models route more accurately; a faster, cheaper model is fine when the routes are clearly distinct. Type or pick any supported model, or a local one through Ollama or VLLM. On hosted Sim the API key is supplied for you.
 
 ### Fallback models
 

apps/sim/app/(landing)/components/hero/components/hero-visual/workflow-data.ts

@@ -162,7 +162,7 @@ export const BLOCKS: BlockDef[] = [
     bgColor: 'var(--text-primary)',
     sentence: {
       segments: ['Prompt', { subBlockId: 'model', noun: 'a model' }],
-      values: { model: 'claude-sonnet-5' },
+      values: { model: 'claude-sonnet-5-5' },
     },
     rows: [],
     x: 300,

apps/sim/app/(landing)/components/product-demo/components/composer-loop/demo-workflow-data.ts

@@ -98,7 +98,7 @@ export const DEMO_BLOCKS: BlockDef[] = [
     bgColor: 'var(--text-primary)',
     sentence: {
       segments: ['Prompt', { subBlockId: 'model', noun: 'a model' }],
-      values: { model: 'claude-sonnet-5' },
+      values: { model: 'claude-sonnet-5-5' },
     },
     rows: [],
     x: col(2),
@@ -127,7 +127,7 @@ export const DEMO_BLOCKS: BlockDef[] = [
     bgColor: 'var(--text-primary)',
     sentence: {
       segments: ['Prompt', { subBlockId: 'model', noun: 'a model' }],
-      values: { model: 'claude-sonnet-5' },
+      values: { model: 'claude-sonnet-5-5' },
     },
     rows: [],
     x: col(4),

apps/sim/app/workspace/[workspaceId]/w/[workflowId]/components/panel/components/editor/components/sub-block/components/combobox/combobox.tsx

@@ -25,7 +25,7 @@ import { useSubBlockStore } from '@/stores/workflows/subblock/store'
 /**
  * Constants for ComboBox component behavior
  */
-const DEFAULT_MODEL = 'claude-sonnet-5'
+const DEFAULT_MODEL = 'claude-sonnet-5-5'
 const ZOOM_FACTOR_BASE = 0.96
 const MIN_ZOOM = 0.1
 const MAX_ZOOM = 1
@@ -296,7 +296,7 @@ export const ComboBox = memo(function ComboBox({
 
   /**
    * Determines the default option value to use.
-   * Priority: explicit defaultValue > claude-sonnet-5 for model field > first option
+   * Priority: explicit defaultValue > DEFAULT_MODEL for model field > first option
    */
   const defaultOptionValue = useMemo(() => {
     if (defaultValue !== undefined) {
@@ -308,7 +308,6 @@ export const ComboBox = memo(function ComboBox({
       // Default not available (e.g. provider disabled) — fall through to other fallbacks
     }
 
-    // For model field, default to claude-sonnet-5 if available
     if (subBlockId === 'model') {
       const defaultModelOption = evaluatedOptions.find(
         (opt) => getOptionValue(opt) === DEFAULT_MODEL

apps/sim/blocks/blocks/agent.ts

@@ -34,7 +34,7 @@ import type { ToolResponse } from '@/tools/types'
 const logger = createLogger('AgentBlock')
 
 /** Model the agent block falls back to when `model` is unset or the auto pseudo-model. */
-const AGENT_FALLBACK_MODEL = 'claude-sonnet-5'
+const AGENT_FALLBACK_MODEL = 'claude-sonnet-5-5'
 
 const MODELS_WITH_REASONING_EFFORT = getModelsWithReasoningEffort()
 const MODELS_WITH_VERBOSITY = getModelsWithVerbosity()
@@ -154,7 +154,7 @@ Return ONLY the JSON array.`,
       type: 'combobox',
       placeholder: 'Type or select a model...',
       required: true,
-      defaultValue: 'claude-sonnet-5',
+      defaultValue: 'claude-sonnet-5-5',
       options: getAgentModelOptions,
       commandSearchable: true,
     },

apps/sim/blocks/blocks/evaluator.ts

@@ -186,7 +186,7 @@ export const EvaluatorBlock: BlockConfig<EvaluatorResponse> = {
       type: 'combobox',
       placeholder: 'Type or select a model...',
       required: true,
-      defaultValue: 'claude-sonnet-5',
+      defaultValue: 'claude-sonnet-5-5',
       options: getModelOptions,
     },
     ...getProviderCredentialSubBlocks(),

apps/sim/blocks/blocks/router.ts

@@ -183,7 +183,7 @@ export const RouterBlock: BlockConfig<RouterResponse> = {
       type: 'combobox',
       placeholder: 'Type or select a model...',
       required: true,
-      defaultValue: 'claude-sonnet-5',
+      defaultValue: 'claude-sonnet-5-5',
       options: getModelOptions,
     },
     ...getProviderCredentialSubBlocks(),
@@ -302,7 +302,7 @@ export const RouterV2Block: BlockConfig<RouterV2Response> = {
       type: 'combobox',
       placeholder: 'Type or select a model...',
       required: true,
-      defaultValue: 'claude-sonnet-5',
+      defaultValue: 'claude-sonnet-5-5',
       options: getModelOptions,
     },
     ...getProviderCredentialSubBlocks(),

apps/sim/executor/constants.ts

@@ -228,7 +228,7 @@ export const HTTP = {
 } as const
 
 export const AGENT = {
-  DEFAULT_MODEL: 'claude-sonnet-5',
+  DEFAULT_MODEL: 'claude-sonnet-5-5',
   get DEFAULT_FUNCTION_TIMEOUT() {
     return getMaxExecutionTimeout()
   },
@@ -243,13 +243,13 @@ export const MCP = {
 } as const
 
 export const ROUTER = {
-  DEFAULT_MODEL: 'claude-sonnet-5',
+  DEFAULT_MODEL: 'claude-sonnet-5-5',
   DEFAULT_TEMPERATURE: 0,
   INFERENCE_TEMPERATURE: 0.1,
 } as const
 
 export const EVALUATOR = {
-  DEFAULT_MODEL: 'claude-sonnet-5',
+  DEFAULT_MODEL: 'claude-sonnet-5-5',
   DEFAULT_TEMPERATURE: 0.1,
   RESPONSE_SCHEMA_NAME: 'evaluation_response',
   JSON_INDENT: 2,

apps/sim/providers/anthropic/core.test.ts

@@ -293,7 +293,7 @@ describe('executeAnthropicProviderRequest forced tool use', () => {
     expect(payload.tool_choice).toEqual({ type: 'tool', name: 'publish' })
   })
 
-  it.each(['claude-fable-5-1', 'claude-opus-5-5'])(
+  it.each(['claude-fable-5-1', 'claude-opus-5-5', 'claude-sonnet-5-5'])(
     'drops forced tool_choice when the catalog model disables Force (%s)',
     async (model) => {
       const { payload, warn } = await runWithForcedTool(model)
@@ -745,6 +745,87 @@ describe('streaming', () => {
       }
     })
   })
+
+  /**
+   * Both tool loops rebuild the request for every turn after a tool call, so
+   * the `none` mapping must hold past the first request. Claude Sonnet 5.5
+   * rejects `thinking.type: "disabled"` and names `between_tools` (which takes
+   * no effort or display field) as its lowest setting; a later turn without it
+   * would silently run adaptive thinking. Every other model keeps `none` as
+   * "send no thinking config".
+   */
+  describe('executeAnthropicProviderRequest none thinking level across tool turns', () => {
+    const lookupTool = {
+      id: 'lookup',
+      name: 'lookup',
+      description: 'Lookup',
+      params: {},
+      parameters: { type: 'object', properties: {}, required: [] },
+    }
+    const turns = [
+      message([{ type: 'tool_use', id: 'tool-1', name: 'lookup', input: {} }], 'tool_use'),
+      message([{ type: 'text', text: 'done' }], 'end_turn'),
+    ]
+
+    /** Runs a tool exchange and returns every request body sent over the SDK boundary. */
+    async function runToolExchange(model: string, streaming: boolean) {
+      mockExecuteTool.mockResolvedValue({ success: true, output: { value: 'tool result' } })
+      const sent: Anthropic.Messages.MessageCreateParams[] = []
+      const nextTurn = (payload: Anthropic.Messages.MessageCreateParams) => {
+        sent.push(payload)
+        return turns[sent.length - 1]
+      }
+      const result = await executeAnthropicProviderRequest(
+        {
+          model,
+          apiKey: 'test-key',
+          stream: streaming,
+          maxTokens: 1024,
+          thinkingLevel: 'none',
+          agentEvents: true,
+          messages: [{ role: 'user', content: 'Look this up' }],
+          tools: [lookupTool],
+        },
+        {
+          providerId: 'anthropic',
+          providerLabel: 'Anthropic',
+          createClient: () =>
+            ({
+              messages: streaming
+                ? {
+                    stream: (payload: never) =>
+                      stream([{ type: 'message_stop' }], nextTurn(payload)),
+                  }
+                : { create: async (payload: never) => nextTurn(payload) },
+            }) as never,
+          logger: { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() },
+        }
+      )
+      if (streaming) await collectEvents(result as StreamingExecution)
+      return sent
+    }
+
+    it.each([false, true])(
+      'sends bare between_tools on every turn (streaming: %s)',
+      async (streaming) => {
+        const sent = await runToolExchange('claude-sonnet-5-5', streaming)
+        expect(sent).toHaveLength(2)
+        for (const payload of sent) {
+          expect(payload.thinking).toEqual({ type: 'between_tools' })
+          expect(payload.output_config).toBeUndefined()
+        }
+      }
+    )
+
+    it.each(['claude-sonnet-5', 'claude-opus-5-5'])(
+      'sends no thinking config on %s',
+      async (model) => {
+        const sent = await runToolExchange(model, false)
+        expect(sent).toHaveLength(2)
+        for (const payload of sent) expect(payload.thinking).toBeUndefined()
+      }
+    )
+  })
 })
 
 /**
@@ -758,6 +839,7 @@ describe('buildThinkingConfig', () => {
     for (const model of [
       'claude-fable-5-1',
       'claude-fable-5',
+      'claude-sonnet-5-5',
       'claude-sonnet-5',
       'claude-opus-5-5',
       'claude-opus-5',

apps/sim/providers/anthropic/core.ts

@@ -144,6 +144,7 @@ const ANTHROPIC_THINKING_OUTPUT_HEADROOM = 4096
 /**
  * Checks if a model supports adaptive thinking (thinking.type: "adaptive").
  * Fable 5, Fable 5.1, and Opus 5.5 support ONLY adaptive thinking (always on; type: "disabled" is rejected).
+ * Sonnet 5.5 is adaptive by default and rejects type: "disabled"; its lowest setting is "between_tools".
  * Sonnet 5 supports ONLY adaptive thinking (manual budget_tokens returns a 400 error).
  * Opus 5, Opus 4.8, and Opus 4.7 support ONLY adaptive thinking (no extended thinking / budget_tokens).
  * Opus 4.6 and Sonnet 4.6 support both extended and adaptive thinking — use adaptive.
@@ -169,10 +170,15 @@ function supportsAdaptiveThinking(modelId: string): boolean {
 /**
  * Builds the thinking configuration for the Anthropic API based on model capabilities and level.
  *
- * - Fable 5.1, Fable 5, Sonnet 5, Opus 5.5, Opus 5, Opus 4.8, Opus 4.7: Uses adaptive thinking only (no extended thinking support)
+ * - Fable 5.1, Fable 5, Sonnet 5.5, Sonnet 5, Opus 5.5, Opus 5, Opus 4.8, Opus 4.7: Uses adaptive thinking only (no extended thinking support)
  * - Opus 4.6, Sonnet 4.6: Uses adaptive thinking with effort parameter
  * - Other models: Uses budget_tokens-based extended thinking
  *
+ * The `none` level returns null (send no thinking config) unless the model
+ * declares `capabilities.thinking.noneMode`: Sonnet 5.5 rejects
+ * `type: "disabled"`, so `none` becomes `type: "between_tools"`, which turns
+ * off up-front thinking and takes no effort or display field.
+ *
  * The newest Claude generations default `thinking.display` to `omitted`
  * (empty thinking blocks, no thinking deltas). Their registry entries mark
  * `capabilities.thinking.streamed: 'summary'`, and for those models Sim opts
@@ -190,7 +196,19 @@ export function buildThinkingConfig(
   outputConfig?: Anthropic.Messages.OutputConfig
 } | null {
   const capability = getThinkingCapability(modelId)
-  if (!capability || !capability.levels.includes(thinkingLevel)) {
+  if (!capability) {
+    return null
+  }
+
+  if (thinkingLevel === 'none') {
+    if (capability.noneMode !== 'between_tools') return null
+    return {
+      // double-cast-allowed: @anthropic-ai/sdk 0.115 predates the between_tools thinking type (typed from 0.129)
+      thinking: { type: 'between_tools' } as unknown as Anthropic.Messages.ThinkingConfigParam,
+    }
+  }
+
+  if (!capability.levels.includes(thinkingLevel)) {
     return null
   }
 
@@ -358,9 +376,8 @@ export async function executeAnthropicProviderRequest(
     }
   }
 
-  // Add extended thinking configuration if supported and requested
-  // The 'none' sentinel means "disable thinking" — skip configuration entirely.
-  if (request.thinkingLevel && request.thinkingLevel !== 'none') {
+  // The 'none' sentinel means "disable thinking": no config, unless the model declares a noneMode.
+  if (request.thinkingLevel) {
     const thinkingConfig = buildThinkingConfig(
       request.model,
       request.thinkingLevel,
@@ -405,11 +422,15 @@ export async function executeAnthropicProviderRequest(
       // Per Anthropic docs: thinking is not compatible with temperature or top_k modifications.
       payload.temperature = undefined
 
-      const isAdaptive = thinkingConfig.thinking.type === 'adaptive'
-      logger.info(
-        `Using ${isAdaptive ? 'adaptive' : 'extended'} thinking for model: ${modelId} with ${isAdaptive ? `effort: ${request.thinkingLevel}` : `budget: ${(thinkingConfig.thinking as { budget_tokens: number }).budget_tokens}`}`
-      )
-    } else {
+      if (request.thinkingLevel === 'none') {
+        logger.info(`Using between_tools thinking for model: ${modelId}`)
+      } else {
+        const isAdaptive = thinkingConfig.thinking.type === 'adaptive'
+        logger.info(
+          `Using ${isAdaptive ? 'adaptive' : 'extended'} thinking for model: ${modelId} with ${isAdaptive ? `effort: ${request.thinkingLevel}` : `budget: ${(thinkingConfig.thinking as { budget_tokens: number }).budget_tokens}`}`
+        )
+      }
+    } else if (request.thinkingLevel !== 'none') {
       logger.warn(
         `Thinking level "${describeModelLevel(request.thinkingLevel)}" not supported for model: ${modelId}, ignoring`
       )