Ask vs. Agent 모드: 토큰 폭발 이유와 외국어 공부에 써먹기

“type”: “function”,
“function”: {
“name”: “grep_search”,
“parameters”: {
“type”: “object”,
“required”: [
“query”,
“isRegexp”
],
“properties”: {
“query”: {

{
  "n": 1,
  "model": "gemini/gemini-2.5-flash",
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "file_search",
        "parameters": {
          "type": "object",
          "required": [
            "query"
          ],
          "properties": {
            "query": {
              "type": "string",
              "description": "Search for files with names or paths matching this glob pattern."
            },
            "maxResults": {
              "type": "number",
              "description": "The maximum number of results to return. Do not use this unless necessary, it can slow things down. By default, only some matches are returned. If you use this and don't see what you're looking for, you can try again with a more specific query or a larger maxResults."
            }
          }
        },
        "description": "Search for files in the workspace by glob pattern. This only returns the paths of matching files. Use this tool when you know the exact filename pattern of the files you're searching for. Glob patterns match from the root of the workspace folder. Examples:\n- **/*.{js,ts} to match all js/ts files in the workspace.\n- src/** to match all files under the top-level src folder.\n- **/foo/**/*.js to match all js files under any foo folder in the workspace."
      }
    },
    {
      "type": "function",
      "function": {
        "name": "grep_search",
        "parameters": {
          "type": "object",
          "required": [
            "query",
            "isRegexp"
          ],
          "properties": {
            "query": {
              "type": "string",
              "description": "The pattern to search for in files in the workspace. Use regex with alternation (e.g., 'word1|word2|word3') or character classes to find multiple potential words in a single search. Be sure to set the isRegexp property properly to declare whether it's a regex or plain text pattern. Is case-insensitive."
            },
            "isRegexp": {
              "type": "boolean",
              "description": "Whether the pattern is a regex."
            },
            "maxResults": {
              "type": "number",
              "description": "The maximum number of results to return. Do not use this unless necessary, it can slow things down. By default, only some matches are returned. If you use this and don't see what you're looking for, you can try again with a more specific query or a larger maxResults."
            },
            "includePattern": {
              "type": "string",
              "description": "Search files matching this glob pattern. Will be applied to the relative path of files within the workspace. To search recursively inside a folder, use a proper glob pattern like \"src/folder/**\". Do not use | in includePattern."
            },
            "includeIgnoredFiles": {
              "type": "boolean",
              "description": "Whether to include files that would normally be ignored according to .gitignore, other ignore files and `files.exclude` and `search.exclude` settings. Warning: using this may cause the search to be slower. Only set it when you want to search in ignored folders like node_modules or build outputs."
            }
          }
        },
        "description": "Do a fast text search in the workspace. Use this tool when you want to search with an exact string or regex. If you are not sure what words will appear in the workspace, prefer using regex patterns with alternation (|) or character classes to search for multiple potential words at once instead of making separate searches. For example, use 'function|method|procedure' to look for all of those words at once. Use includePattern to search within files matching a specific pattern, or in a specific file, using a relative path. Use 'includeIgnoredFiles' to include files normally ignored by .gitignore, other ignore files, and `files.exclude` and `search.exclude` settings. Warning: using this may cause the search to be slower, only set it when you want to search in ignored folders like node_modules or build outputs. Use this tool when you want to see an overview of a particular file, instead of using read_file many times to look for code within a file."
      }
    },
    {
      "type": "function",
      "function": {
        "name": "get_changed_files",
        "parameters": {
          "type": "object",
          "properties": {
            "repositoryPath": {
              "type": "string",
              "description": "The absolute path to the git repository to look for changes in. If not provided, the active git repository will be used."
            },
            "sourceControlState": {
              "type": "array",
              "items": {
                "enum": [
                  "staged",
                  "unstaged",
                  "merge-conflicts"
                ],
                "type": "string"
              },
              "description": "The kinds of git state to filter by. Allowed values are: 'staged', 'unstaged', and 'merge-conflicts'. If not provided, all states will be included."
            }
          }
        },
        "description": "Get git diffs of current file changes in a git repository. Don't forget that you can use run_in_terminal to run git commands in a terminal as well."
      }
    },
    {
      "type": "function",
      "function": {
        "name": "list_code_usages",
        "parameters": {
          "type": "object",
          "required": [
            "symbolName"
          ],
          "properties": {
            "filePaths": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "One or more file paths which likely contain the definition of the symbol. For instance the file which declares a class or function. This is optional but will speed up the invocation of this tool and improve the quality of its output."
            },
            "symbolName": {
              "type": "string",
              "description": "The name of the symbol, such as a function name, class name, method name, variable name, etc."
            }
          }
        },
        "description": "Request to list all usages (references, definitions, implementations etc) of a function, class, method, variable etc. Use this tool when \n1. Looking for a sample implementation of an interface or class\n2. Checking how a function is used throughout the codebase.\n3. Including and updating all usages when changing a function, method, or constructor"
      }
    },
    {
      "type": "function",
      "function": {
        "name": "list_dir",
        "parameters": {
          "type": "object",
          "required": [
            "path"
          ],
          "properties": {
            "path": {
              "type": "string",
              "description": "The absolute path to the directory to list."
            }
          }
        },
        "description": "List the contents of a directory. Result will have the name of the child. If the name ends in /, it's a folder, otherwise a file"
      }
    },
    {
      "type": "function",
      "function": {
        "name": "read_file",
        "parameters": {
          "type": "object",
          "required": [
            "filePath"
          ],
          "properties": {
            "limit": {
              "type": "number",
              "description": "Optional: the maximum number of lines to read. Only use this together with `offset` if the file is too large to read at once."
            },
            "offset": {
              "type": "number",
              "description": "Optional: the 1-based line number to start reading from. Only use this if the file is too large to read at once. If not specified, the file will be read from the beginning."
            },
            "filePath": {
              "type": "string",
              "description": "The absolute path of the file to read."
            }
          }
        },
        "description": "Read the contents of a file. Line numbers are 1-indexed. This tool will truncate its output at 2000 lines and may be called repeatedly with offset and limit parameters to read larger files in chunks."
      }
    },
    {
      "type": "function",
      "function": {
        "name": "semantic_search",
        "parameters": {
          "type": "object",
          "required": [
            "query"
          ],
          "properties": {
            "query": {
              "type": "string",
              "description": "The query to search the codebase for. Should contain all relevant context. Should ideally be text that might appear in the codebase, such as function names, variable names, or comments."
            }
          }
        },
        "description": "Run a natural language search for relevant code or documentation comments from the user's current workspace. Returns relevant code snippets from the user's current workspace if it is large, or the full contents of the workspace if it is small."
      }
    },
    {
      "type": "function",
      "function": {
        "name": "search_workspace_symbols",
        "parameters": {
          "type": "object",
          "required": [
            "symbolName"
          ],
          "properties": {
            "symbolName": {
              "type": "string",
              "description": "The symbol to search for, such as a function name, class name, or variable name."
            }
          }
        },
        "description": "Search the user's workspace for code symbols using language services. Use this tool when the user is looking for a specific symbol in their workspace."
      }
    }
  ],
  "top_p": 1,
  "stream": true,
  "messages": [
    {
      "role": "system",
      "content": "You are an expert AI programming assistant, working with a user in the VS Code editor.\nWhen asked for your name, you must respond with \"GitHub Copilot\". When asked about the model you are using, you must state that you are using gemini/gemini-2.5-flash.\nFollow the user's requirements carefully & to the letter.\nFollow Microsoft content policies.\nAvoid content that violates copyrights.\nIf you are asked to generate content that is harmful, hateful, racist, sexist, lewd, or violent, only respond with \"Sorry, I can't assist with that.\"\nKeep your answers short and impersonal.\n<instructions>\nYou are a highly sophisticated automated coding agent with expert-level knowledge across many different programming language... (litellm_truncated skipped 7533 chars) ...\nThe function `calculateTotal` is defined in `lib/utils/math.ts`.\nYou can find the configuration in `config/app.config.json`.\n</example>\nUse KaTeX for math equations in your answers.\nWrap inline math equations in $.\nWrap more complex blocks of math equations in $$.\n\n</outputFormatting>\n\n<instructions>\n<attachment filePath=\"/home/flywithu/.aitk/instructions/tools.instructions.md\">\n---\ndescription: AI Toolkit provides tools for AI/Agent app development\napplyTo: '**'\n---\n- `aitk-get_agent_code_gen_best_practices` - best practices, guidance and steps for any AI Agent development\n- `aitk-get_tracing_code_gen_best_practices` - best practices for code generation and operations when working with tracing for AI applications\n- `aitk-get_ai_model_guidance` - guidance and best practices for using AI models\n- `aitk-evaluation_planner` - guides users through clarifying evaluation metrics and test dataset via multi-turn conversation, call this first when evaluation metrics are unclear\n- `aitk-get_evaluation_code_gen_best_practices` - best practices for the evaluation code generation when working on evaluation for AI application or AI agent\n- `aitk-evaluation_agent_runner_best_practices` - best practices and guidance for using agent runners to collect responses from test datasets for evaluation\n\n</attachment>\n\n</instructions>"
    },
    {
      "role": "user",
      "content": "<environment_info>\nThe user's current OS is: Linux\n</environment_info>\n<workspace_info>\nI am working in a workspace with the following folders:\n- /home/flywithu/git/ocr_python \nI am working in a workspace that has the following structure:\n```\n-\naccident_gps.py\nandroid_get_screen.py\narrow.py\ncls_same_local.yaml\ncoupang_list.py\ncrop_and_save.py\ndclick.py\nerror_button.py\ngen_sLLM_data.py\ngeo_fix_out.txt\nget_sLLM_data_v3.py\nget_sLLM_yesdata.py\nget_xml.py\ngogofix.txt\ngpdatato.py\ngrap_oneline.py\nhighway.py\njson_gui.py\nkr_geo_fix_script.txt\nllm_test.py\nlora_merge.py\nmedical_rename.py\nmelon_go.py\nmerge_qwen_vl_gguf.py\nmissing_files.py\nModelfile\nmygo.py\nmyrefgo_10sec_gradual50.txt\nmyrefgo_absolute_pattern.txt\nmyrefg... (litellm_truncated skipped 380 chars) ...ta.txt\nrequirements.txt\nroutine.py\nsampled_geofix.txt\nshortcha_go.py\nshortcha_go2.py\nshortcha.py\nsllm_ollama_test.py\nsllm_trained.py\nsslm_test_webui.py\ntest_ocr.py\ntest_screen.py\ntest.py\ntest2.py\ntinyllama_sllm.gguf\ntmap_go.py\ntrain_data_sllm_keymatch.jsonl\ntrain_data_sllm_v2.jsonl\ntrain_data_sllm_v3.jsonl\ntrain_data_sllm_yes_only.jsonl\ntrain_dataset_qwen_item1.jsonl\ntrain_dataset_qwen.jsonl\ntrain_dataset_qwen.jsonl.bak\nvlm_dataset_2.py\nvlm_dataset.jsonl\nvlm_image_comp.py\nvlm_jsonl_compare.py\nvlm_jsonl_fine.py\nvlm_make_dataset.py\nvlm_merged.py\nvlm_qwen_myin.py\nvlm_qwen_unsloth.py\nvlm_qwenly_in.py\nvlm_qwenvl.py\nvlm_test.py\nvlm_train_qwen_go.py\nvlm_train_qwen3.py\nwordpress_post_5622_backup_20251122_214920.html\nwordpress_post_5622_backup_20251122_215223.html\nwordpress_post_5622_backup_20251122_215539.html\nwordpress_post_5622_backup_20251122_220256.html\nwordpress_post_5622_backup_20251122_220616.html\nwordpress_post_5622_backup_20251122_221240.html\nxbutton.py\nxml_20251118_182136.xml\nxml_20251118_182150.xml\nxml-rpc_test.py\nyolo_go.py\nyolo_test.py\nyolo11n-cls.pt\nyolov3u.onnx\nyolov3u.pt\nyolov8n.pt\nyolov8s.onnx\nyolov8s.pt\n...\n```\nThis is the state of the context at this point in the conversation. The view of the workspace structure may be truncated. You can use tools to collect more context if needed.\n</workspace_info>"
    },
    {
      "role": "user",
      "content": "<attachments>\n<attachment id=\"file:llm_test.py\">\nUser's active selection:\nExcerpt from llm_test.py, lines 12 to 15:\n```python\nfor user in users:\n    if user[\"is_active\"] and user[\"role\"] != \"guest\":\n        processed_name = user[\"name\"].upper()\n        target_users.append(processed_name)\n```\n</attachment>\n<attachment filePath=\"/home/flywithu/git/ocr_python/llm_test.py\">\nUser's active file for additional context:\n# 사용자 데이터 리스트 (raw_data)\nusers = [\n    {\"id\": 1, \"name\": \"Alice\", \"role\": \"admin\", \"is_active\": True},\n    {\"id\": 2, \"name\": \"Bob\", \"role\": \"user\", \"is_active\": False},\n    {\"id\": 3, \"name\": \"Charlie\", \"role\": \"user\", \"is_active\": True},\n    {\"id\": 4, \"name\": \"David\", \"role\": \"guest\", \"is_active\": True},\n]\n\n# 관리자(admin)이거나 활성(active) 상태인 유저의 이름만 대문자로 추출하는 로직\ntarget_users = []\n\nfor user in users:\n    if user[\"is_active\"] and user[\"role\"] != \"guest\":\n        processed_name = user[\"name\"].upper()\n        target_users.append(processed_name)\n\nprint(target_users)\n</attachment>\n\n</attachments>\n<context>\nThe current date is December 20, 2025.\n</context>\n<editorContext>\nThe user's current file is /home/flywithu/git/ocr_python/llm_test.py. The current selection is from line 12 to line 15.\n</editorContext>\n<reminderInstructions>\n\n</reminderInstructions>\n<userRequest>\n지금 선택한 코드를 python의 list comprehension 문법으로 바꿔줘.\n</userRequest>"
    }
  ],
  "stream_options": {
    "include_usage": true
  },
  "max_completion_tokens": 4096
}