Add Claude 4.6 prompt optimization A/B test configurations (#4316)

* Add Claude 4.6 prompt optimization A/B test configurations

Implement three-way prompt optimization experiment for Claude 4.6 models:
- Control: existing Claude46DefaultPrompt (no change)
- Combined: single optimized prompt for both Opus and Sonnet with moderate exploration guidance
- Split: separate Opus-specific (bounded exploration) and Sonnet-specific (full persistence) prompts

* Optimize Claude 4.6 prompt configurations with type adjustments and conditional rendering for tool instructions

Author: bhavyaus

package.json

@@ -3681,6 +3681,20 @@
 							"clear-both"
 						]
 					},
+					"github.copilot.chat.anthropic.promptOptimization": {
+						"type": "string",
+						"default": "control",
+						"markdownDescription": "%github.copilot.config.anthropic.promptOptimization%",
+						"tags": [
+							"experimental",
+							"onExp"
+						],
+						"enum": [
+							"control",
+							"combined",
+							"split"
+						]
+					},
 					"github.copilot.chat.responsesApiReasoningEffort": {
 						"type": "string",
 						"default": "default",

package.nls.json

@@ -333,6 +333,7 @@
 	"copilot.toolSet.web.description": "Fetch information from the web",
 	"github.copilot.config.useMessagesApi": "Use the Messages API instead of the Chat Completions API when supported.",
 	"github.copilot.config.anthropic.contextEditing.mode": "Select the context editing mode for Anthropic models. Automatically manages conversation context as it grows, helping optimize costs and stay within context window limits.\n\n- `off`: Context editing is disabled.\n- `clear-thinking`: Clears thinking blocks while preserving tool uses.\n- `clear-tooluse`: Clears tool uses while preserving thinking blocks.\n- `clear-both`: Clears both thinking blocks and tool uses.\n\n**Note**: This is an experimental feature. Context editing may cause additional cache rewrites. Enable with caution.",
+	"github.copilot.config.anthropic.promptOptimization": "Prompt optimization mode for Claude 4.6 models.\n\n- `control`: Uses the current default prompt (no changes).\n- `combined`: Uses a single optimized prompt for both Opus and Sonnet.\n- `split`: Uses separate optimized prompts for Opus (bounded exploration) and Sonnet (full persistence).\n\n**Note**: This is an experimental feature for A/B testing prompt configurations.",
 	"github.copilot.config.anthropic.toolSearchTool.enabled": "Enable tool search tool for Anthropic models. When enabled, tools are dynamically discovered and loaded on-demand using natural language search, reducing context window usage when many tools are available.",
 	"github.copilot.config.anthropic.toolSearchTool.mode": "Controls how tool search works for Anthropic models. 'server' uses Anthropic's built-in regex-based tool search. 'client' uses local embeddings-based semantic search for more accurate tool discovery.",
 	"github.copilot.config.useResponsesApi": "Use the Responses API instead of the Chat Completions API when supported. Enables reasoning and reasoning summaries.\n\n**Note**: This is an experimental feature that is not yet activated for all users.\n\n**Important**: URL API path resolution for custom OpenAI-compatible and Azure models is independent of this setting and fully determined by `url` property of `#github.copilot.chat.customOAIModels#` or `#github.copilot.chat.azureModels#` respectively.",