Datasets:

DrVon
/

hermes-tool-selector

+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Got it, that makes a lot of sense.\n\nOkay cool. Earlier we had a chat about getting you set up with Github. I think that's relevant.\n\nAlso when we do that I want to specify some guidelines and rules before you get access to it because I can imagine that there is a lot of malicious code on Github as well. If you just jump into a repo willy-nilly and install it then you might get in trouble with malware. We need to figure out a structure for the agent or whoever the Github agent is. They need to cross-reference, maybe do a search, find a few different options that are interesting, somehow verify if there is a way to verify in Github if it's been authorized or approved by somebody. The code has been checked and made sure it is free from malware then they can have a look at it, evaluate the code if it's if the repo is good enough just to install and run or if there is a part of the code in the repo that is useful, it can be implemented. It doesn't have to use the repo exactly how it is. Maybe it can usually get inspiration and some code for its own application to improve. Basically use GitHub as a reference and inspiration place. If it finds one good repo that will work, install it. If it finds parts or IDs in a repo that are interesting, then you can use those parts to code its own skill or program or whatever the project is about."}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: session_search\nTOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] is there any regular reviue of what is in the memory at the moment. if not could it be a corn job to check the relevans of the stored memorys?"}, {"role": "assistant", "content": "TOOL: skill_manage\nTOOL: cronjob"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[System note: Your previous turn was interrupted before you could process the last tool result(s). The conversation history contains tool outputs you haven't responded to yet. Please finish processing those results and summarize what was accomplished, then address the user's new message below.]\n\n[DrVon Dobermann] ok we can remove all the apple mac-related skills we can remove the pokémon and the minecraft we can remove touch designer and comfy ui we can disable but let's put them in a list somewhere that we know we can evoke them if needed we can disable the memory architecture one and only use the obsidian but perhaps we don't delete it. we just keep it dormant research paper writing: maybe we don't need it to get injected every time but we can keep it as a skill that we can evoke.\n- hermes agent: don't know if we need to do anything with that. we can leave that for now.\n- claude code: we can leave dormant.\n- humanizer: we can leave for now.\n- p5js: we can leave.\n- confi ui: maybe we can make it dormant or we can reference it if we need it.\n- llm vicky is: we can leave that and we leave god mode."}, {"role": "assistant", "content": "TOOL: terminal\nTOOL: read_file\nTOOL: patch\nTOOL: write_file\nTOOL: todo"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "what model are you running now?"}, {"role": "assistant", "content": "TOOL: read_file\nTOOL: search_files\nTOOL: patch"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "is this in the correct path now because it should be in the wiki second brain file i think? double check that"}, {"role": "assistant", "content": "TOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[Recent channel messages]\n[DrVon Dobermann] Check your Gmail inbox and give me an update on what is going on. If there is anything relevant that needs to be updated in the calendar, do so\n[DrVon Dobermann] God morgon\n\n[New message]\n[DrVon Dobermann] good morning"}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: terminal\nTOOL: execute_code"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] can you check out the latest research on using LoRa to fine tune and make tasks for agents? I'm thinking perhaps this could be a valuable addition to the workflow."}, {"role": "assistant", "content": "TOOL: web_search\nTOOL: web_extract\nTOOL: terminal\nTOOL: clarify"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Yes please go ahead with all those suggestions and can you also add the road association appointment to the family wall calendar?"}, {"role": "assistant", "content": "TOOL: terminal\nTOOL: skill_view\nTOOL: execute_code\nTOOL: vision_analyze"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Yes start prepping searxng"}, {"role": "assistant", "content": "TOOL: todo\nTOOL: terminal\nTOOL: write_file\nTOOL: process\nTOOL: execute_code\nTOOL: read_file\nTOOL: patch"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] yes go ahead with the doctor and chromium"}, {"role": "assistant", "content": "TOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[The user sent a document: '2603.16021v2_1.pdf'. The file is saved at: /home/wiki/.hermes/cache/documents/doc_00156b4a113d_2603.16021v2_1.pdf. Ask the user what they'd like you to do with it.]\n\n[DrVon Dobermann] Before we carry on doing any changes, I would like you to review the following document. Make an analysis and determine if this method is valuable for updating your work procedures"}, {"role": "assistant", "content": "TOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Can you give me a structural run down of how the agentic workflow is organized that you use?"}, {"role": "assistant", "content": "TOOL: skill_view"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] When I checked the log in open router, it seems like you're only using one agent. There are only IPA calls from deepseek v4. Before we discuss that you should use more agents and that you should spawn agents, can you check your procedure there and get back to me about the structure?"}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: search_files\nTOOL: read_file"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Try to add something to the grocery list. Add corn"}, {"role": "assistant", "content": "TOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] That was a painful process. I need you to have a good look at what you did to be able to create that. I need you to have a good look at the procedure that you have to do to get that family wall thing working. I need you to either make it into a skill or a procedure or whatever because I want to make a cron job. I want a morning report every morning and it needs to be ready at 5:30 in the morning. When I wake up I want to be able to get an overview of what is going on during the day so I know how to plan. I need you to make sure that that process is smooth on your side, minimize tokens, and make it efficient."}, {"role": "assistant", "content": "TOOL: skill_manage\nTOOL: terminal\nTOOL: cronjob\nTOOL: todo"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] I have invited you to a family app. The link is in the inbox. Check and se off you can use it. Try to send me a dm"}, {"role": "assistant", "content": "TOOL: terminal\nTOOL: web_extract"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Can you? You can't. Isn't there a web application for Family Wall as well that you can log into? I gave you the invite and you have a phone number. Perhaps you can make a phone emulator or something like that."}, {"role": "assistant", "content": "TOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Just go for it. I want you to be more proactive. You don't have to ask, just try and when you failed then you can let me know. Just keep on trying."}, {"role": "assistant", "content": "TOOL: terminal\nTOOL: todo\nTOOL: execute_code\nTOOL: memory"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[Recent channel messages]\n[DrVon Dobermann] Check your Email inbox\n\n[New message]\n[DrVon Dobermann] check your email inbox"}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] ok let's do one at a time so it doesn't get too complicated or overwhelming and risk any hallucination"}, {"role": "assistant", "content": "TOOL: skill_manage\nTOOL: terminal\nTOOL: read_file\nTOOL: patch"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] let's do the sub-agent now. is it possible to have different llms for different agents? i'm thinking that you wanted to choose the smallest agents for the job necessary so we don't go with cloud opus 4.7 for every task if it's really simple. in that case you might want to use a cheaper model for the easier tasks and then if you need a reasoning model then perhaps you need to use a more capable one. is this possible to do?"}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Let's try your new web browser skilles. Can you find out when Ahlsells in Täby closes today"}, {"role": "assistant", "content": "TOOL: web_search\nTOOL: web_extract"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] I sent you an invite link in Gmail. You should be able to just go through that one and access the family wall through that"}, {"role": "assistant", "content": "TOOL: read_file\nTOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "okay check now. i did some changes and you should be good to go"}, {"role": "assistant", "content": "TOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] good morning milly thank you for the morning brief. can you check your obsidian inbox?"}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: search_files\nTOOL: read_file\nTOOL: todo\nTOOL: execute_code\nTOOL: terminal\nTOOL: vision_analyze\nTOOL: write_file\nTOOL: patch"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] I want you to change your orchestrator model to deep seek v4 Pro"}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: terminal\nTOOL: search_files\nTOOL: read_file"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Windows Luminous Scouts stop today"}, {"role": "assistant", "content": "TOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] You need to update your memory because you know that you have a Google account. I don't want to have to remind you all the time"}, {"role": "assistant", "content": "TOOL: session_search\nTOOL: execute_code\nTOOL: memory\nTOOL: terminal\nTOOL: vision_analyze"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Let's tackle no 6"}, {"role": "assistant", "content": "TOOL: patch"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Why is this the only channel where you respond? I've checked all the other ones that I have but I don't get any response in those channels"}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: terminal\nTOOL: search_files"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] OK I think we got your setup going pretty well now. Now I want to start getting you to do some stuff for me. Somehow I need you to help me with this. Somehow I want you to see my emails. I'm using Outlook at the moment but somehow I want to be able to create or share folders from my email with you. I want you to be able to read the emails, help me keep track of appointments, dates, and conversations. Can you ponder a little bit on that and then come back with a plan?"}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] what is 202? what is the next step?"}, {"role": "assistant", "content": "TOOL: search_files\nTOOL: read_file\nTOOL: patch\nTOOL: write_file\nTOOL: memory"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] For point 6, the one with the clarification, I think we're going to go for option B. If there is a task or if we start with a project that is a little bit more advanced or substantial, we really need to make a specification or dig down into what needs to be done and what the expected outcome is before we start coding or doing research"}, {"role": "assistant", "content": "TOOL: session_search\nTOOL: patch"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Let's go with your recommendations for the llms"}, {"role": "assistant", "content": "TOOL: terminal\nTOOL: patch"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Can you see the calendar in Family Wall?"}, {"role": "assistant", "content": "TOOL: web_search"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Good morning Milly! Can you check when ICA in Arninge and Vallentuna opens today?"}, {"role": "assistant", "content": "TOOL: web_search\nTOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Now this is just for tasks in Google. Let's leave family wall for now. It seems like it is not suitable for agents to work with. But what you can do is make it different colors. At the moment there should be work tasks or company tasks. We have a project building a wooden deck so that's one different. There is another project. If it's unclear what project the tasks should go to, you can ask but I'll try to categorize them when I add it when I tell you. But make them different color codes so it is easy to separate visually."}, {"role": "assistant", "content": "TOOL: execute_code\nTOOL: clarify"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "did you also update the obsidian vault with these memories?"}, {"role": "assistant", "content": "TOOL: read_file"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] can we get all of them so that we can use all the credits? then you start with one and when you run out of credits, you do the next one and then the next one and then we can have a searxng as a fallback."}, {"role": "assistant", "content": "TOOL: execute_code\nTOOL: search_files\nTOOL: read_file"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Can you add the task today that:\n- for the company I need to go through the pricing and the offer for the new unit\n- we need to reschedule with Terese\n- we need to make plans for the Altaan extension and the railing\n- have a look at what stones to use for the new garden path\n\n\nThis is for the home project and"}, {"role": "assistant", "content": "TOOL: todo"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "i just forwarded an email to you. can you check it for me?"}, {"role": "assistant", "content": "TOOL: execute_code"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] I want you to put in your way of working, basically your procedures that if you need to get a feature or update, when you are looking to solve problems. I want you to be able to check in GitHub to see if there are any repos there that you can use or are similar, or you can implement stuff that other people have already done and tried. Basically just give you another tool in your tool chest to improve and get better."}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: todo\nTOOL: terminal\nTOOL: execute_code"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] how are the moonshot kimmy k 2.6 compared to these ones that you suggested?"}, {"role": "assistant", "content": "TOOL: delegate_task"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] I've already done the full OAuth setup in the CLI so you should have all the information that you need"}, {"role": "assistant", "content": "TOOL: terminal\nTOOL: session_search\nTOOL: read_file"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "did you see the attachments as well?"}, {"role": "assistant", "content": "TOOL: execute_code\nTOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "Can you create a Google Docs just as a test? I just wanted to see how it works if I talk to you in Discord and give you instructions. You should be able to create a Google Docs and maybe write a little short story about spring time."}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Share the Google Drive project with me in my Gmail"}, {"role": "assistant", "content": "TOOL: execute_code"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] nice one! let's have a look at your capability of web browsing and web scraping. do you have any skills for that?"}, {"role": "assistant", "content": "TOOL: terminal\nTOOL: skill_view"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] There is one text document in the project files. It looks like it's in markdown format. All documents should be formatted for human reading."}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: execute_code"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] You did it. The family wall is updated correctly. One thing: when you add a schedule appointment or event like that, I want a reminder one day before. Could you please update it for me please?"}, {"role": "assistant", "content": "TOOL: execute_code"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Can you check your email that I've given to you? I sent you an email"}, {"role": "assistant", "content": "TOOL: session_search"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Okay let's do number seven. Before you start just do some thinking and planning so we get a strategy so we don't start implementing hooks and guard rails that are just going to slow you down. We really need to focus on you getting the freedom you need without being able to irreversibly delete something or change something that it's not going to be able to fix or that makes your performance slower over time."}, {"role": "assistant", "content": "TOOL: todo\nTOOL: terminal\nTOOL: search_files\nTOOL: read_file\nTOOL: write_file\nTOOL: clarify"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] I will get the keys later. Let's try out searxng and see what it is good for"}, {"role": "assistant", "content": "TOOL: execute_code\nTOOL: terminal\nTOOL: web_search\nTOOL: web_extract"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Yes absolutely if you are going to be my reshercher you need to have full internet access"}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: read_file\nTOOL: search_files"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Do you have access to github?"}, {"role": "assistant", "content": "TOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "can you make a draft in gmail without sending it? just the draft?"}, {"role": "assistant", "content": "TOOL: execute_code"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] Yeah my idea was never to replace the main engine. I think using Loras as tools for different tasks is the way to go. How about we could set up a separate sort of research department that we can call upon that develops the Loras in parallel with the way we're working now? Then we can do an evaluation of the benefit of using Loras and the original way that we are working."}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: terminal\nTOOL: write_file"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "I just went through the whole Google Workspace OAuth setup yesterday so we also tested it earlier today and it should be working yeah we definitely tested it today and it was working fine from the CLI"}, {"role": "assistant", "content": "TOOL: terminal"}]}
+{"messages": [{"role": "system", "content": "You are a tool selection router for Hermes Agent. \nGiven a user's task, identify which tools should be used to accomplish it.\nOutput ONLY the tool names, one per line, prefixed with TOOL:.\nAvailable tools: web_search, web_extract, terminal, read_file, write_file, search_files, \npatch, execute_code, skill_view, skill_manage, skills_list, memory, session_search, \nsend_message, clarify, cronjob, delegate_task, todo, vision_analyze, text_to_speech, \nprocess, webhook, github_pr, github_issues, git, nvidia_smi"}, {"role": "user", "content": "[DrVon Dobermann] yeah let's go for it. we need to get your web browsing and searching"}, {"role": "assistant", "content": "TOOL: skill_view\nTOOL: terminal\nTOOL: read_file\nTOOL: search_files"}]}