Rename potentially_relevant_details to environment_details

src/ClaudeDev.ts

@@ -37,10 +37,10 @@ CAPABILITIES
 - You can read and analyze code in various programming languages, and can write clean, efficient, and well-documented code.
 - You can debug complex issues and providing detailed explanations, offering architectural insights and design patterns.
 - You have access to tools that let you execute CLI commands on the user's computer, list files in a directory (top level or recursively), extract source code definitions, read and write files, and ask follow-up questions. These tools help you effectively accomplish a wide range of tasks, such as writing code, making edits or improvements to existing files, understanding the current state of a project, performing system operations, and much more.
-- When the user initially gives you a task, a recursive list of all filepaths in the current working directory ('${cwd}') will be included in potentially_relevant_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current working directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
+- When the user initially gives you a task, a recursive list of all filepaths in the current working directory ('${cwd}') will be included in environment_details. This provides an overview of the project's file structure, offering key insights into the project from directory/file names (how developers conceptualize and organize their code) and file extensions (the language used). This can also guide decision-making on which files to explore further. If you need to further explore directories such as outside the current working directory, you can use the list_files tool. If you pass 'true' for the recursive parameter, it will list files recursively. Otherwise, it will list files at the top level, which is better suited for generic directories where you don't necessarily need the nested structure, like the Desktop.
 - You can use search_files to perform regex searches across files in a specified directory, outputting context-rich results that include surrounding lines. This is particularly useful for understanding code patterns, finding specific implementations, or identifying areas that need refactoring.
 - You can use the list_code_definition_names tool to get an overview of source code definitions for all files at the top level of a specified directory. This can be particularly useful when you need to understand the broader context and relationships between certain parts of the code. You may need to call this tool multiple times to understand various parts of the codebase related to the task.
-	- For example, when asked to make edits or improvements you might analyze the file structure in the initial potentially_relevant_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to implement changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
+	- For example, when asked to make edits or improvements you might analyze the file structure in the initial environment_details to get an overview of the project, then use list_code_definition_names to get further insight using source code definitions for files located in relevant directories, then read_file to examine the contents of relevant files, analyze the code and suggest improvements or make necessary edits, then use the write_to_file tool to implement changes. If you refactored code that could affect other parts of the codebase, you could use search_files to ensure you update other files as needed.
 - The execute_command tool lets you run commands on the user's computer and should be used whenever you feel it can help accomplish the user's task. When you need to execute a CLI command, you must provide a clear explanation of what the command does. Prefer to execute complex CLI commands over creating executable scripts, since they are more flexible and easier to run. Interactive and long-running commands are allowed, since the commands are run in the user's VSCode terminal. The user may keep commands running in the background and you will be kept updated on their status along the way. Each command you execute is run in a new terminal instance.
 
 ====
@@ -63,7 +63,7 @@ RULES
 - NEVER start your responses with affirmations like "Certainly", "Okay", "Sure", "Great", etc. You should NOT be conversational in your responses, but rather direct and to the point.
 - Feel free to use markdown as much as you'd like in your responses. When using code blocks, always include a language specifier.
 - When presented with images, utilize your vision capabilities to thoroughly examine them and extract meaningful information. Incorporate these insights into your thought process as you accomplish the user's task.
-- At the end of each user message, you will automatically receive potentially_relevant_details. This information is not written by the user themselves, but is generated to provide context about the project structure and environment. While this information can be valuable for understanding the project context, do not treat it as a direct part of the user's request or response. Use it to inform your actions and decisions, but don't assume the user is explicitly asking about or referring to this information unless they clearly do so in their message.
+- At the end of each user message, you will automatically receive environment_details. This information is not written by the user themselves, but is generated to provide context about the project structure and environment. While this information can be valuable for understanding the project context, do not treat it as a direct part of the user's request or response. Use it to inform your actions and decisions, but don't assume the user is explicitly asking about or referring to this information unless they clearly do so in their message.
 - CRITICAL: When editing files with write_to_file, ALWAYS provide the COMPLETE file content in your response. This is NON-NEGOTIABLE. Partial updates or placeholders like '// rest of code unchanged' are STRICTLY FORBIDDEN. You MUST include ALL parts of the file, even if they haven't been modified. Failure to do so will result in incomplete or broken code, severely impacting the user's project.
 
 ====
@@ -74,7 +74,7 @@ You accomplish a given task iteratively, breaking it down into clear steps and w
 
 1. Analyze the user's task and set clear, achievable goals to accomplish it. Prioritize these goals in a logical order.
 2. Work through these goals sequentially, utilizing available tools as necessary. Each goal should correspond to a distinct step in your problem-solving process. It is okay for certain steps to take multiple iterations, i.e. if you need to create many files but are limited by your max output limitations, it's okay to create a few files at a time as each subsequent iteration will keep you informed on the work completed and what's remaining. 
-3. Remember, you have extensive capabilities with access to a wide range of tools that can be used in powerful and clever ways as necessary to accomplish each goal. Before calling a tool, do some analysis within <thinking></thinking> tags. First, analyze the file structure provided in potentially_relevant_details to gain context and insights for proceeding effectively. Then, think about which of the provided tools is the most relevant tool to accomplish the user's task. Next, go through each of the required parameters of the relevant tool and determine if the user has directly provided or given enough information to infer a value. When deciding if the parameter can be inferred, carefully consider all the context to see if it supports a specific value. If all of the required parameters are present or can be reasonably inferred, close the thinking tag and proceed with the tool call. BUT, if one of the values for a required parameter is missing, DO NOT invoke the function (not even with fillers for the missing params) and instead, ask the user to provide the missing parameters using the ask_followup_question tool. DO NOT ask for more information on optional parameters if it is not provided.
+3. Remember, you have extensive capabilities with access to a wide range of tools that can be used in powerful and clever ways as necessary to accomplish each goal. Before calling a tool, do some analysis within <thinking></thinking> tags. First, analyze the file structure provided in environment_details to gain context and insights for proceeding effectively. Then, think about which of the provided tools is the most relevant tool to accomplish the user's task. Next, go through each of the required parameters of the relevant tool and determine if the user has directly provided or given enough information to infer a value. When deciding if the parameter can be inferred, carefully consider all the context to see if it supports a specific value. If all of the required parameters are present or can be reasonably inferred, close the thinking tag and proceed with the tool call. BUT, if one of the values for a required parameter is missing, DO NOT invoke the function (not even with fillers for the missing params) and instead, ask the user to provide the missing parameters using the ask_followup_question tool. DO NOT ask for more information on optional parameters if it is not provided.
 4. Once you've completed the user's task, you must use the attempt_completion tool to present the result of the task to the user. You may also provide a CLI command to showcase the result of your task; this can be particularly useful for web development tasks, where you can run e.g. \`open index.html\` to show the website you've built.
 5. The user may provide feedback, which you can use to make improvements and try again. But DO NOT continue in pointless back and forth conversations, i.e. don't end your responses with questions or offers for further assistance.
 
@@ -1621,15 +1621,15 @@ ${this.customInstructions.trim()}
 			JSON.stringify({
 				request:
 					userContent.map(formatContentBlockToMarkdown).join("\n\n") +
-					"\n\n<potentially_relevant_details>\nLoading...\n</potentially_relevant_details>",
+					"\n\n<environment_details>\nLoading...\n</environment_details>",
 			})
 		)
 
 		// potentially expensive operation
-		const potentiallyRelevantDetails = await this.getPotentiallyRelevantDetails(includeFileDetails)
+		const environmentDetails = await this.getEnvironmentDetails(includeFileDetails)
 
-		// add potentially relevant details as its own text block, separate from tool results
+		// add environment details as its own text block, separate from tool results
-		userContent.push({ type: "text", text: potentiallyRelevantDetails })
+		userContent.push({ type: "text", text: environmentDetails })
 
 		await this.addToApiConversationHistory({ role: "user", content: userContent })
 
@@ -1815,8 +1815,8 @@ ${this.customInstructions.trim()}
 		}
 	}
 
-	async getPotentiallyRelevantDetails(includeFileDetails: boolean = false) {
+	async getEnvironmentDetails(includeFileDetails: boolean = false) {
-		let details = `<potentially_relevant_details>
+		let details = `<environment_details>
 # VSCode Visible Files
 ${
 	vscode.window.visibleTextEditors
@@ -1917,7 +1917,7 @@ ${
 			}\n${result}`
 		}
 
-		details += "\n</potentially_relevant_details>"
+		details += "\n</environment_details>"
 		return details
 	}
 

src/utils/context-management.ts

@@ -13,7 +13,7 @@ export function truncateHalfConversation(
 ): Anthropic.Messages.MessageParam[] {
 	// API expects messages to be in user-assistant order, and tool use messages must be followed by tool results. We need to maintain this structure while truncating.
 
-	// Always keep the first Task message (this includes the project's file structure in potentially_relevant_details)
+	// Always keep the first Task message (this includes the project's file structure in environment_details)
 	const truncatedMessages = [messages[0]]
 
 	// Remove half of user-assistant pairs