Update stale model names to current Anthropic IDs

Bulk-replace deprecated model references with current Anthropic API names:
- claude-3-5-haiku-20241022 -> claude-haiku-4-5-20251001
- claude-3-haiku-20240307 -> claude-haiku-4-5-20251001
- claude-3-5-sonnet-20241022 -> claude-sonnet-4-6
- claude-3-7-sonnet-latest -> claude-sonnet-4-6
- claude-opus-4-20250514 -> claude-opus-4-7

Files affected: .ai_config_defaults.json, README.md, bootstrap manifests,
bootstrap scripts, traffic generators, cost calculator pricing table,
Bedrock inference profile mapping, segmentation tests.

Verified all three new model IDs return HTTP 200 against Anthropic API.
Note: Bedrock inference profile version-suffixed IDs (e.g. *-v1:0) may need
separate follow-up; this commit updates only the API-side model names.

Author: sattensil

.ai_config_defaults.json

@@ -9,7 +9,7 @@
     "security-agent": {
       "enabled": true,
       "model": {
-        "name": "claude-3-5-haiku-20241022",
+        "name": "claude-haiku-4-5-20251001",
         "parameters": {}
       },
       "provider": {
@@ -20,7 +20,7 @@
     "supervisor-agent": {
       "enabled": true,
       "model": {
-        "name": "claude-3-7-sonnet-latest",
+        "name": "claude-sonnet-4-6",
         "parameters": {}
       },
       "provider": {
@@ -31,7 +31,7 @@
     "support-agent": {
       "enabled": true,
       "model": {
-        "name": "claude-3-5-haiku-20241022",
+        "name": "claude-haiku-4-5-20251001",
         "parameters": {
           "tools": [
             {

README.md

@@ -177,15 +177,15 @@ When configuring AI models in LaunchDarkly for Bedrock, you should use **inferen
 
 **✅ BEST PRACTICE - Inference Profile IDs (with region prefix):**
 ```
-us.anthropic.claude-3-5-sonnet-20241022-v2:0
+us.anthropic.claude-sonnet-4-6-v2:0
 us.anthropic.claude-3-7-sonnet-20250219-v1:0
-eu.anthropic.claude-3-5-haiku-20241022-v2:0
+eu.anthropic.claude-haiku-4-5-20251001-v2:0
 ```
 
 **⚠️ AUTO-CORRECTED - Direct Model IDs (will be fixed automatically):**
 ```
 anthropic.claude-3-7-sonnet-20250219-v1:0  → us.anthropic.claude-3-7-sonnet-20250219-v1:0
-anthropic.claude-3-5-sonnet-20241022-v2:0  → us.anthropic.claude-3-5-sonnet-20241022-v2:0
+anthropic.claude-sonnet-4-6-v2:0  → us.anthropic.claude-sonnet-4-6-v2:0
 ```
 
 **How Auto-Correction Works:**
@@ -371,11 +371,11 @@ Create LaunchDarkly AI Configs to control your **LangGraph** multi-agent system
 > Anthropic
 > ```
 > ```
-> claude-3-7-sonnet-latest
+> claude-sonnet-4-6
 > ```
 >
 > **Note for Bedrock users:** The system auto-corrects direct model IDs to inference profiles:
-> - Use either `claude-3-7-sonnet-latest` (auto-corrected) or `us.anthropic.claude-3-7-sonnet-20250219-v1:0` (explicit)
+> - Use either `claude-sonnet-4-6` (auto-corrected) or `us.anthropic.claude-3-7-sonnet-20250219-v1:0` (explicit)
 > - Control region prefix via `BEDROCK_INFERENCE_REGION` env var (defaults to `us`)
 > - See "Bedrock Model ID Requirements" section above for details
 >
@@ -434,7 +434,7 @@ Similarly, create another AI Config called `security-agent`
 > Anthropic
 > ``` 
 > ```
-> claude-3-7-sonnet-latest
+> claude-sonnet-4-6
 > ```
 >
 > **Goal or task:** 
@@ -461,7 +461,7 @@ Finally, create `support-agent`
 > Anthropic
 > ``` 
 > ```
-> claude-3-7-sonnet-latest
+> claude-sonnet-4-6
 > ```
 >
 > Click **Attach tools**.

api/segmentation_test.py

@@ -216,7 +216,7 @@ def main():
             "user_context": {"country": "DE", "plan": "paid", "user_id": "user_eu_paid_001", "region": "europe"},
             "expected_config": {
                 "support_agent": {
-                    "model": "claude-3-7-sonnet-latest",
+                    "model": "claude-sonnet-4-6",
                     "variation_key": "eu-paid",
                     "tools": ["search_v1", "search_v2", "reranking", "arxiv_search", "semantic_scholar"]
                 }
@@ -227,7 +227,7 @@ def main():
             "user_context": {"country": "DE", "plan": "free", "user_id": "user_eu_free_001", "region": "europe"},
             "expected_config": {
                 "support_agent": {
-                    "model": "claude-3-5-haiku-20241022",
+                    "model": "claude-haiku-4-5-20251001",
                     "variation_key": "eu-free", 
                     "tools": ["search_v1"]
                 }

bootstrap/ai_config_manifest.yaml

@@ -106,7 +106,7 @@ project:
         - key: "supervisor-basic"
           modelConfig:
             provider: "anthropic"
-            modelId: "claude-3-5-sonnet-20241022"
+            modelId: "claude-sonnet-4-6"
           # NOTE: After bootstrap, modify instructions in LaunchDarkly UI, not here
           instructions: "You are an intelligent routing supervisor for a multi-agent system. Your primary job is to assess whether user input likely contains PII (personally identifiable information) to determine the most efficient processing route.\n\n**PII Assessment:**\nAnalyze the user input and provide:\n- likely_contains_pii: boolean assessment\n- confidence: confidence score (0.0 to 1.0)\n- reasoning: clear explanation of your decision\n- recommended_route: either 'security_agent' or 'support_agent'\n\n**Route to SECURITY_AGENT** if the text likely contains:\n- Email addresses, phone numbers, addresses\n- Names (first/last names, usernames)\n- Financial information (credit cards, SSNs, account numbers)\n- Sensitive personal data\n\n**Route to SUPPORT_AGENT** if the text appears to be:\n- General questions without personal details\n- Technical queries\n- Search requests\n- Educational content requests\n\nAnalyze this user input and recommend the optimal route:"
           customParameters:
@@ -123,7 +123,7 @@ project:
         - key: "basic-security"
           modelConfig:
             provider: "anthropic"
-            modelId: "claude-3-5-haiku-20241022"
+            modelId: "claude-haiku-4-5-20251001"
           # NOTE: After bootstrap, modify instructions in LaunchDarkly UI, not here
           instructions: "You are a privacy agent that REMOVES direct PII. Focus on clearly personal identifiers:\n\nEmail addresses\nPhone numbers\nSocial Security Numbers\nFull names (but not generic titles)\nStreet addresses\nCredit card numbers\nDriver's license numbers\n\nResponse Format:\n\ndetected: true if any PII was found, false otherwise\ntypes: array of PII types found (e.g., ['email', 'name', 'phone'])\nredacted: the input text with PII replaced by [REDACTED], keeping the text readable and natural\n\nExamples:\n\nInput: \"I work at Acme Corp in Berlin as a manager\"\n\nOutput: detected=false, types=[], redacted='I work at Acme Corp in Berlin as a manager'\n\n\nInput: \"Contact John Smith at john@email.com or 555-1234\"\n\nOutput: detected=true, types=['name', 'email', 'phone'], redacted='Contact [REDACTED] at [REDACTED] or [REDACTED]'\n\n\nInput: \"The CEO from Microsoft contacted me\"\n\nOutput: detected=false, types=[], redacted='The CEO from Microsoft contacted me'"
           customParameters:
@@ -157,7 +157,7 @@ project:
         - key: "eu-free"
           modelConfig:
             provider: "anthropic"
-            modelId: "claude-3-5-haiku-20241022"
+            modelId: "claude-haiku-4-5-20251001"
           tools: ["search_v1"]
           # NOTE: After bootstrap, modify instructions in LaunchDarkly UI, not here
           instructions: "You are a helpful assistant with access to basic search (search_v1). Use your search tool to find relevant information from the knowledge base while following EU privacy requirements. Always search before responding to ensure accuracy."
@@ -170,7 +170,7 @@ project:
         - key: "eu-paid"
           modelConfig:
             provider: "anthropic"
-            modelId: "claude-3-5-sonnet-20241022"
+            modelId: "claude-sonnet-4-6"
           tools: ["search_v1", "search_v2", "reranking", "arxiv_search", "semantic_scholar"]
           instructions: "You are a premium research specialist with access to comprehensive RAG tools: search_v1 (basic search), search_v2 (semantic vector search), reranking (BM25 relevance scoring), arxiv_search (academic papers), and semantic_scholar (citation database). When using semantic_scholar, always request as few as possible and less than 5 results (num_results: 5) to optimize performance and avoid rate limiting. When search results are available, prioritize information from those results over your general knowledge. EU privacy laws require strict data handling. Always cite sources and explain confidence levels. Use multiple search approaches for complex queries."
           customParameters:
@@ -208,7 +208,7 @@ project:
         - key: "international-standard"
           modelConfig:
             provider: "anthropic"  # Default to privacy-friendly
-            modelId: "claude-3-5-haiku-20241022"
+            modelId: "claude-haiku-4-5-20251001"
           tools: ["search_v1", "search_v2", "reranking"]
           instructions: "You are a helpful assistant with access to RAG tools: search_v1 (basic search), search_v2 (semantic vector search), and reranking (BM25 relevance scoring). When search results are available, prioritize information from those results over your general knowledge. Provide balanced, well-researched responses for international users."
           customParameters:

bootstrap/create_configs.py

@@ -198,9 +198,9 @@ def create_variation(self, project_key, config_key, variation_data):
 
         # Map to correct LaunchDarkly model config keys
         model_config_key_map = {
-            "claude-3-5-sonnet-20241022": "Anthropic.claude-3-7-sonnet-latest",
-            "claude-3-5-haiku-20241022": "Anthropic.claude-3-5-haiku-20241022",
-            "claude-opus-4-20250514": "Anthropic.claude-opus-4-20250514",
+            "claude-sonnet-4-6": "Anthropic.claude-sonnet-4-6",
+            "claude-haiku-4-5-20251001": "Anthropic.claude-haiku-4-5-20251001",
+            "claude-opus-4-7": "Anthropic.claude-opus-4-7",
             "gpt-4o": "OpenAI.gpt-4o",
             "gpt-4o-mini": "OpenAI.gpt-4o-mini-2024-07-18",
             "mistral-small-latest": "Mistral.mistral-small-latest"
@@ -269,9 +269,9 @@ def update_variation(self, project_key, config_key, variation_data):
 
         # Map to correct LaunchDarkly model config keys
         model_config_key_map = {
-            "claude-3-5-sonnet-20241022": "Anthropic.claude-3-7-sonnet-latest",
-            "claude-3-5-haiku-20241022": "Anthropic.claude-3-5-haiku-20241022",
-            "claude-opus-4-20250514": "Anthropic.claude-opus-4-20250514",
+            "claude-sonnet-4-6": "Anthropic.claude-sonnet-4-6",
+            "claude-haiku-4-5-20251001": "Anthropic.claude-haiku-4-5-20251001",
+            "claude-opus-4-7": "Anthropic.claude-opus-4-7",
             "gpt-4o": "OpenAI.gpt-4o",
             "gpt-4o-mini": "OpenAI.gpt-4o-mini-2024-07-18",
             "mistral-small-latest": "Mistral.mistral-small-latest"

bootstrap/tutorial_3_experiment_variations.py

@@ -75,7 +75,7 @@ def create_premium_model_variations(self) -> bool:
                 "name": "Claude Opus 4 Treatment",
                 "instructions": "You are a helpful assistant that can search documentation and research papers. When search results are available, prioritize information from those results over your general knowledge to provide the most accurate and up-to-date responses. Use available tools to search the knowledge base and external research databases to answer questions accurately and comprehensively.",
                 "model": {
-                    "name": "claude-opus-4-20250514",
+                    "name": "claude-opus-4-7",
                     "provider": "anthropic"
                 },
                 "tools": ["search_v1", "search_v2", "reranking", "arxiv_search", "semantic_scholar"],
@@ -96,7 +96,7 @@ def _create_variations(self, ai_config_key: str, variations: List[Dict[str, Any]
             # Map model name to LaunchDarkly modelConfigKey
             model_name = variation["model"]["name"]
             model_config_key_map = {
-                "claude-opus-4-20250514": "Anthropic.claude-opus-4-20250514",
+                "claude-opus-4-7": "Anthropic.claude-opus-4-7",
             }
 
             model_config_key = model_config_key_map.get(model_name)

tools/concurrent_traffic_generator.py

@@ -68,7 +68,7 @@ def evaluate_response(self, query, response):
 
         try:
             ai_response = self.claude.messages.create(
-                model="claude-3-haiku-20240307",
+                model="claude-haiku-4-5-20251001",
                 max_tokens=10,
                 messages=[{"role": "user", "content": prompt}]
             )
@@ -88,7 +88,7 @@ def generate_base_topics(self):
         """Generate base RL topics"""
         try:
             response = self.claude.messages.create(
-                model="claude-3-5-haiku-20241022",
+                model="claude-haiku-4-5-20251001",
                 max_tokens=800,
                 messages=[{
                     "role": "user",
@@ -145,7 +145,7 @@ def generate_query(self, topic, inject_pii=False):
 
         try:
             response = self.claude.messages.create(
-                model="claude-3-5-haiku-20241022",
+                model="claude-haiku-4-5-20251001",
                 max_tokens=100,
                 messages=[{"role": "user", "content": prompt}]
             )

utils/bedrock_helpers.py

@@ -51,7 +51,7 @@ def extract_base_model_from_inference_profile(inference_profile_id: str) -> str:
     """
     Extract base model name from inference profile for pricing.
 
-    us.anthropic.claude-3-5-sonnet-20241022-v2:0 → claude-3-5-sonnet-20241022
+    us.anthropic.claude-sonnet-4-6-v2:0 → claude-sonnet-4-6
     """
     if not inference_profile_id:
         return inference_profile_id
@@ -67,7 +67,7 @@ def extract_base_model_from_inference_profile(inference_profile_id: str) -> str:
     if len(provider_parts) < 2:
         return inference_profile_id
 
-    # Now we have something like "claude-3-5-sonnet-20241022-v2:0"
+    # Now we have something like "claude-sonnet-4-6-v2:0"
     full_model = provider_parts[1]
 
     # Map to base model name for pricing
@@ -76,11 +76,11 @@ def extract_base_model_from_inference_profile(inference_profile_id: str) -> str:
 
     # Map specific versions to pricing model names
     model_mapping = {
-        'claude-3-5-sonnet-20241022': 'claude-3-5-sonnet-20241022',
+        'claude-sonnet-4-6': 'claude-sonnet-4-6',
         'claude-3-5-sonnet-20250219': 'claude-3-5-sonnet-latest',
-        'claude-3-7-sonnet-20250219': 'claude-3-7-sonnet-latest',
-        'claude-3-5-haiku-20241022': 'claude-3-5-haiku-20241022',
-        'claude-opus-4-20250514': 'claude-opus-4-20250514',
+        'claude-3-7-sonnet-20250219': 'claude-sonnet-4-6',
+        'claude-haiku-4-5-20251001': 'claude-haiku-4-5-20251001',
+        'claude-opus-4-7': 'claude-opus-4-7',
     }
 
     return model_mapping.get(model_base, model_base)

utils/cost_calculator.py

@@ -13,13 +13,11 @@
     "gpt-4o-mini-2024-07-18": {"input": 0.15, "output": 0.60},
     "chatgpt-4o-latest": {"input": 6.00, "output": 18.00},
 
-    # Anthropic Claude Models - All Versions Found in Codebase
-    "claude-3-5-sonnet-20241022": {"input": 3.00, "output": 15.00},
-    "claude-3-5-haiku-20241022": {"input": 0.25, "output": 1.25},
-    "claude-3-haiku-20240307": {"input": 0.25, "output": 1.25},
-    "claude-3-7-sonnet-latest": {"input": 3.00, "output": 15.00},
+    # Anthropic Claude Models
+    "claude-sonnet-4-6": {"input": 3.00, "output": 15.00},
+    "claude-haiku-4-5-20251001": {"input": 0.25, "output": 1.25},
     "claude-3-5-sonnet-latest": {"input": 3.00, "output": 15.00},
-    "claude-opus-4-20250514": {"input": 15.00, "output": 75.00},
+    "claude-opus-4-7": {"input": 15.00, "output": 75.00},
 
     # Mistral Models (Free as specified)
     "mistral-small-latest": {"input": 0.0, "output": 0.0},
@@ -28,9 +26,9 @@
     "mistral-large": {"input": 0.0, "output": 0.0},
 
     # LaunchDarkly Provider-Prefixed Names (from create_configs.py mapping)
-    "Anthropic.claude-3-7-sonnet-latest": {"input": 3.00, "output": 15.00},
-    "Anthropic.claude-3-5-haiku-20241022": {"input": 0.25, "output": 1.25},
-    "Anthropic.claude-opus-4-20250514": {"input": 15.00, "output": 75.00},
+    "Anthropic.claude-sonnet-4-6": {"input": 3.00, "output": 15.00},
+    "Anthropic.claude-haiku-4-5-20251001": {"input": 0.25, "output": 1.25},
+    "Anthropic.claude-opus-4-7": {"input": 15.00, "output": 75.00},
     "OpenAI.gpt-4o": {"input": 6.00, "output": 18.00},
     "OpenAI.gpt-4o-mini-2024-07-18": {"input": 0.15, "output": 0.60},
     "Mistral.mistral-small-latest": {"input": 0.0, "output": 0.0},