feat(azure): added azure anthropic, added backwards compat support for chat completions API, added opus 4.6 (#3145)

* feat(azure): added azure anthropic, added backwards compat support for chat completions API, added opus 4.6

* added max thinking level

* update tests

* ack comments

* update cql validation

Author: waleedlatif1

apps/sim/app/api/tools/confluence/search-in-space/route.ts

@@ -53,7 +53,7 @@ export async function POST(request: NextRequest) {
       return NextResponse.json({ error: cloudIdValidation.error }, { status: 400 })
     }
 
-    const escapeCqlValue = (value: string) => value.replace(/"/g, '\\"')
+    const escapeCqlValue = (value: string) => value.replace(/\\/g, '\\\\').replace(/"/g, '\\"')
 
     let cql = `space = "${escapeCqlValue(spaceKey)}"`
 

apps/sim/app/api/tools/confluence/search/route.ts

@@ -42,7 +42,7 @@ export async function POST(request: NextRequest) {
       return NextResponse.json({ error: cloudIdValidation.error }, { status: 400 })
     }
 
-    const escapeCqlValue = (value: string) => value.replace(/"/g, '\\"')
+    const escapeCqlValue = (value: string) => value.replace(/\\/g, '\\\\').replace(/"/g, '\\"')
 
     const searchParams = new URLSearchParams({
       cql: `text ~ "${escapeCqlValue(query)}"`,

apps/sim/app/llms-full.txt/route.ts

@@ -56,7 +56,7 @@ An execution is a single run of a workflow. It includes:
 ### LLM Orchestration
 Sim supports all major LLM providers:
 - OpenAI (GPT-5.2, GPT-5.1, GPT-5, GPT-4o, GPT-4.1)
-- Anthropic (Claude Opus 4.5, Claude Opus 4.1, Claude Sonnet 4.5, Claude Haiku 4.5)
+- Anthropic (Claude Opus 4.6, Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5)
 - Google (Gemini Pro 3, Gemini Pro 3 Preview, Gemini 2.5 Pro, Gemini 2.5 Flash)
 - Mistral (Mistral Large, Mistral Medium)
 - xAI (Grok)

apps/sim/blocks/blocks/agent.ts

@@ -274,6 +274,7 @@ Return ONLY the JSON array.`,
         { label: 'low', id: 'low' },
         { label: 'medium', id: 'medium' },
         { label: 'high', id: 'high' },
+        { label: 'max', id: 'max' },
       ],
       dependsOn: ['model'],
       fetchOptions: async (blockId: string) => {
@@ -318,14 +319,14 @@ Return ONLY the JSON array.`,
 
     {
       id: 'azureEndpoint',
-      title: 'Azure OpenAI Endpoint',
+      title: 'Azure Endpoint',
       type: 'short-input',
       password: true,
-      placeholder: 'https://your-resource.openai.azure.com',
+      placeholder: 'https://your-resource.services.ai.azure.com',
       connectionDroppable: false,
       condition: {
         field: 'model',
-        value: providers['azure-openai'].models,
+        value: [...providers['azure-openai'].models, ...providers['azure-anthropic'].models],
       },
     },
     {
@@ -763,7 +764,10 @@ Example 3 (Array Input):
     maxTokens: { type: 'number', description: 'Maximum number of tokens in the response' },
     reasoningEffort: { type: 'string', description: 'Reasoning effort level for GPT-5 models' },
     verbosity: { type: 'string', description: 'Verbosity level for GPT-5 models' },
-    thinkingLevel: { type: 'string', description: 'Thinking level for Gemini 3 models' },
+    thinkingLevel: {
+      type: 'string',
+      description: 'Thinking level for models with extended thinking (Anthropic Claude, Gemini 3)',
+    },
     tools: { type: 'json', description: 'Available tools configuration' },
   },
   outputs: {