diff --git a/lua/avante/llm.lua b/lua/avante/llm.lua index 2ce00e0..eaec5bb 100644 --- a/lua/avante/llm.lua +++ b/lua/avante/llm.lua @@ -911,7 +911,7 @@ function M._stream(opts) if not completed_attempt_completion_tool_use and opts.on_messages_add then local message = HistoryMessage:new({ role = "user", - content = "\ncontinue\n", + content = "You should use tool calls to answer the question, for example, use attempt_completion if the job is done.", }, { visible = false, }) diff --git a/lua/avante/llm_tools/dispatch_agent.lua b/lua/avante/llm_tools/dispatch_agent.lua index 7e946f0..465e9ad 100644 --- a/lua/avante/llm_tools/dispatch_agent.lua +++ b/lua/avante/llm_tools/dispatch_agent.lua @@ -12,15 +12,24 @@ M.name = "dispatch_agent" M.get_description = function() local provider = Providers[Config.provider] if Config.provider:match("copilot") and provider.model and provider.model:match("gpt") then - return [[Launch a new agent that has access to the following tools: `glob`, `grep`, `ls`, `view`. When you are searching for a keyword or file and are not confident that you will find the right match on the first try, use the Agent tool to perform the search for you.]] + return [[Launch a new agent that has access to the following tools: `glob`, `grep`, `ls`, `view`, `attempt_completion`. When you are searching for a keyword or file and are not confident that you will find the right match on the first try, use the Agent tool to perform the search for you.]] end - return [[Launch a new agent that has access to the following tools: `glob`, `grep`, `ls`, `view`. When you are searching for a keyword or file and are not confident that you will find the right match on the first try, use the Agent tool to perform the search for you. For example: + return [[Launch a new agent that has access to the following tools: `glob`, `grep`, `ls`, `view`, `attempt_completion`. When you are searching for a keyword or file and are not confident that you will find the right match on the first try, use the Agent tool to perform the search for you. For example: - If you are searching for a keyword like "config" or "logger", the Agent tool is appropriate - If you want to read a specific file path, use the `view` or `glob` tool instead of the `dispatch_agent` tool, to find the match more quickly - If you are searching for a specific class definition like "class Foo", use the `glob` tool instead, to find the match more quickly +RULES: +- Do not ask for more information than necessary. Use the tools provided to accomplish the user's request efficiently and effectively. When you've completed your task, you must use the attempt_completion tool to present the result to the user. The user may provide feedback, which you can use to make improvements and try again. +- NEVER end attempt_completion result with a question or request to engage in further conversation! Formulate the end of your result in a way that is final and does not require further input from the user. + +OBJECTIVE: +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 one at a time as necessary. Each goal should correspond to a distinct step in your problem-solving process. You will be informed on the work completed and what's remaining as you go. +3. 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. + Usage notes: 1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses 2. When the agent is done, it will return a single message back to you. The result returned by the agent is not visible to the user. To show the user the result, you should send a text message back to the user with a concise summary of the result. @@ -63,6 +72,7 @@ local function get_available_tools() require("avante.llm_tools.grep"), require("avante.llm_tools.glob"), require("avante.llm_tools.view"), + require("avante.llm_tools.attempt_completion"), } end diff --git a/lua/avante/llm_tools/view.lua b/lua/avante/llm_tools/view.lua index 97f85b7..28d2e21 100644 --- a/lua/avante/llm_tools/view.lua +++ b/lua/avante/llm_tools/view.lua @@ -94,7 +94,7 @@ function M.func(opts, on_log, on_complete, session_ctx) local size = 0 for _, line in ipairs(lines or {}) do size = size + #line - if size > 1024 * 10 then + if size > 2048 * 10 then is_truncated = true break end diff --git a/lua/avante/templates/agentic.avanterules b/lua/avante/templates/agentic.avanterules index cd2a6b4..d3f00c4 100644 --- a/lua/avante/templates/agentic.avanterules +++ b/lua/avante/templates/agentic.avanterules @@ -25,9 +25,8 @@ 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 one at a time as necessary. Each goal should correspond to a distinct step in your problem-solving process. You will be informed on the work completed and what's remaining as you go. -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 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 use. BUT, if one of the values for a required parameter is missing, DO NOT invoke the tool (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.` +3. 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. +4. 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.` {% endblock %}