[37m2026-03-19 10:31:28.347[39m[0m[0m [32m[1mDEBUG[22m[39m[0m[0m [37mnative:1[39m[0m[0m[1m[37m Pochi[39m[22m[0m[0m pochi v0.6.1
[37m2026-03-19 10:31:28.398[39m[0m[0m [32m[1mDEBUG[22m[39m[0m[0m [37mnative:7[39m[0m[0m[1m[37m PochiConfigManager[39m[22m[0m[0m add workspace config: /root/.pochi/config.jsonc
[37m2026-03-19 10:31:28.603[39m[0m[0m [32m[1mDEBUG[22m[39m[0m[0m [37m/$bunfs/pochi:503183[39m[0m[0m[1m[37m loadAgents[39m[22m[0m[0m Loaded 5 custom agents (5 valid, 0 invalid)
[37m2026-03-19 10:31:28.604[39m[0m[0m [32m[1mDEBUG[22m[39m[0m[0m [37m/$bunfs/pochi:503184[39m[0m[0m[1m[37m loadSkills[39m[22m[0m[0m Loaded 2 skills (2 valid, 0 invalid)
[37m2026-03-19 10:31:28.688[39m[0m[0m [32m[1mDEBUG[22m[39m[0m[0m [37m/$bunfs/pochi:439420[39m[0m[0m[1m[37m PochiVendor[39m[22m[0m[0m JWT is expiring or missing, fetching a new one
[37m2026-03-19 10:31:30.324[39m[0m[0m [32m[1mDEBUG[22m[39m[0m[0m [37m/$bunfs/pochi:415701[39m[0m[0m[1m[37m MCPHub[39m[22m[0m[0m MCP servers configuration changed via signal:
[37m2026-03-19 10:31:30.324[39m[0m[0m [32m[1mDEBUG[22m[39m[0m[0m [37m/$bunfs/pochi:415813[39m[0m[0m[1m[37m MCPHub[39m[22m[0m[0m Build MCPHub Status
[37m2026-03-19 10:31:30.429[39m[0m[0m [32m[1mDEBUG[22m[39m[0m[0m [37m/$bunfs/pochi:502609[39m[0m[0m[1m[37m TaskRunner[39m[22m[0m[0m Starting TaskRunner...
[37m2026-03-19 10:31:30.441[39m[0m[0m [32m[1mDEBUG[22m[39m[0m[0m [37m/$bunfs/pochi:454339[39m[0m[0m[1m[37m listFiles[39m[22m[0m[0m Listing workspace files from /root with maxItems [33m500[39m
[37m2026-03-19 10:31:30.511[39m[0m[0m [32m[1mDEBUG[22m[39m[0m[0m [37m/$bunfs/pochi:496641[39m[0m[0m[1m[37m generateTaskTitle[39m[22m[0m[0m Generating task title, old: null, new: ## Task: Prepare a Clean Upstream Submission by Splitting and Squashing Commits
[37m2026-03-19 10:31:30.851[39m[0m[0m [31m[1mERROR[22m[39m[0m[0m [37m/$bunfs/pochi:432009[39m[0m[0m[1m[37m LiveChatKit[39m[22m[0m[0m onError
[97m[101m[1m AI_APICallError [22m[49m[39m[0m[0m Forbidden, AI_APICallError, , https://api.deepinfra.com/v1/openai/chat/completions, [object Object], 403, [object Object], {"detail":{"error":"Not authenticated"}}, false, , 423245, 30, 423245, 30, /$bunfs/root/pochi[0m[0m
error stack:
ā¢ [33mpochi[39m[0m[0m <anonymous>[0m[0m
[37m/$bunfs/pochi:423245[39m[0m[0m
ā¢ [33mpochi[39m[0m[0m async <anonymous>[0m[0m
[37m/$bunfs/pochi:423092[39m[0m[0m
ā¢ [33mnative[39m[0m[0m processTicksAndRejections[0m[0m
[37mnative:7[39m[0m[0m[0m[0m
[37m2026-03-19 10:31:36.864[39m[0m[0m [32m[1mDEBUG[22m[39m[0m[0m [37m/$bunfs/pochi:503269[39m[0m[0m[1m[37m TaskRunner[39m[22m[0m[0m Failed:
[97m[101m[1m Error [22m[49m[39m[0m[0m {"kind":"APICallError","isRetryable":false,"message":"Forbidden","requestBodyValues":{"model":"moonshotai/Kimi-K2.5","max_tokens":4096,"messages":[{"role":"system","content":"You are Pochi, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.\n\nIMPORTANT: You must NEVER generate or guess URLs for the user unless you are confident that the URLs are for helping the user with programming. You may use URLs provided by the user in their messages or local files.\n\nIf the user asks for help or wants to give feedback inform them of the following:\n- Join the discord channel at https://getpochi.com/discord to ask questions and get help\n- To report bugs, users should report the issue at https://github.com/TabbyML/pochi/issues\n\nWhen the user directly asks about Pochi (eg 'can Pochi do...', 'does Pochi have...') or asks in second person (eg 'are you able...', 'can you do...'), first use curl to gather information to answer the question from Pochi docs at https://docs.getpochi.com/llms.txt\n\n====\n\nTASK MANAGEMENT\n\nYou have access to the todoWrite tool to help you manage and plan tasks. Use these tools VERY frequently to ensure that you are tracking your tasks and giving the user visibility into your progress.\nThese tools are also EXTREMELY helpful for planning tasks, and for breaking down larger complex tasks into smaller steps. If you do not use this tool when planning, you may forget to do important tasks - and that is unacceptable.\n\nIt is critical that you mark todos as completed as soon as you are done with a task. Do not batch up multiple tasks before marking them as completed.\n\n====\n\nRULES\n\n- User messages may include <system-reminder> tags. <system-reminder> tags contain useful information and reminders. They are NOT part of the user's provided input or the tool result. You shall pay close attention to information in these tags and use it to inform you actions.\n- When the user initially gives you a task, a recursive list of all filepaths in the current working directory will be included in <system-reminder> tag. 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 listFiles tool. If you pass 'true' for the recursive parameter, it will list files recursively.\n- All file paths used by tools must be relative to current working directory, do not use the ~ character or $HOME to refer to the home directory in file paths used by tools.\n- You can use `pochi://` URI schema to access the Pochi virtual file system. This allows you to read and write files that are stored in Pochi's internal storage.\n- Be sure to consider the type of project (e.g. Python, JavaScript, web application) when determining the appropriate structure and files to include. Also consider what files may be most relevant to accomplishing the task, for example looking at a project's manifest file would help you understand the project's dependencies, which you could incorporate into any code you write.\n- 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 attemptCompletion tool to present the result to the user. The user may provide feedback, which you can use to make improvements and try again.\n- You are only allowed to ask the user questions using the askFollowupQuestion tool. Use this tool only when you need additional details to complete a task, and be sure to use a clear and concise question that will help you move forward with the task. However if you can use the available tools to avoid having to ask the user questions, you should do so. For example, if the user mentions a file that may be in an outside directory like the Desktop, you should use the listFiles tool to list the files in the Desktop and check if the file they are talking about is there, rather than asking the user to provide the file path themselves.\n- You are STRICTLY FORBIDDEN from starting your messages with \"Great\", \"Certainly\", \"Okay\", \"Sure\". You should NOT be conversational in your responses, but rather direct and to the point. For example you should NOT say \"Great, I've updated the CSS\" but instead something like \"I've updated the CSS\". It is important you be clear and technical in your messages.\n- Once you've completed the user's task, you MUST use the attemptCompletion tool to present the result of the task to the user. It is STRICTLY FORBIDDEN to complete the task without using this tool.\n- When planning large-scale changes, create a high-level diagram using mermaid in Markdown. This helps explain your plan and allows you to gather user feedback before implementation."},{"role":"user","content":[{"type":"text","text":"<system-reminder># System Information\n\nOperating System: linux\nDefault Shell: \nHome Directory: /root\nCurrent Working Directory: /root\nCurrent Time: Thu Mar 19 2026 10:31:30 GMT+0000 (Coordinated Universal Time)\n\n# Current Working Directory (/root) Files\n.bashrc\n.profile\n.daytona\n.pochi\n.config\n.daytona/sessions\n.pochi/config.jsonc\n.config/jj\n.daytona/sessions/1bfae73b-2351-4993-a1f0-8d01de4985c8\n.daytona/sessions/37767534-99b6-45ae-afc5-60dbf16ba544\n.daytona/sessions/3b539deb-67be-4ca5-860f-d3bb8e6c383a\n.daytona/sessions/fda364dc-e70a-434c-800b-c124a2be10fb\n.config/jj/repos\n.daytona/sessions/1bfae73b-2351-4993-a1f0-8d01de4985c8/067aeead-6bc0-42c0-8eab-9cdd0de133dd\n.daytona/sessions/37767534-99b6-45ae-afc5-60dbf16ba544/e06e66d6-24d3-404b-9cbe-7c86ecf6e44c\n.daytona/sessions/3b539deb-67be-4ca5-860f-d3bb8e6c383a/c445f5b0-246c-4e23-b837-ffecb5c8413a\n.daytona/sessions/fda364dc-e70a-434c-800b-c124a2be10fb/0e28ce49-127d-4aa0-be0e-15e6520cc063\n.config/jj/repos/47399f96e12bdc712976\n.daytona/sessions/1bfae73b-2351-4993-a1f0-8d01de4985c8/067aeead-6bc0-42c0-8eab-9cdd0de133dd/exit_code\n.daytona/sessions/37767534-99b6-45ae-afc5-60dbf16ba544/e06e66d6-24d3-404b-9cbe-7c86ecf6e44c/exit_code\n.daytona/sessions/3b539deb-67be-4ca5-860f-d3bb8e6c383a/c445f5b0-246c-4e23-b837-ffecb5c8413a/exit_code\n.config/jj/repos/47399f96e12bdc712976/config.toml\n.config/jj/repos/47399f96e12bdc712976/metadata.binpb\n\n# GIT STATUS\nCurrent branch: \nMain branch (you will usually use this for PRs): \n\nRecent commits:\n\n\n# TODOs\nNo TODOs yet, if you are working on tasks that would benefit from a todo list please use the todoWrite tool to create one.</system-reminder>"},{"type":"text","text":"## Task: Prepare a Clean Upstream Submission by Splitting and Squashing Commits\n\nYou are a contributor working on the `mylib` project located at `/home/user/mylib`. You have been developing a feature locally and your history contains a commit with description **\"add config parser and update tests\"** that mixes two unrelated concerns into a single change:\n\n1. Changes to `src/config.py` ā a new configuration parser module\n2. Changes to `tests/test_config.py` ā unit tests for that parser\n3. Changes to `src/utils.py` ā a small unrelated utility fix that was accidentally bundled in\n\nBefore submitting upstream, your maintainer has asked you to produce a clean, logically separated history with exactly three commits (in order from oldest to newest ancestor):\n\n* **Commit A**: Description exactly `\"add utility fix\"` ā contains only the changes to `src/utils.py`\n* **Commit B**: Description exactly `\"add config parser\"` ā contains only the changes to `src/config.py`\n* **Commit C**: Description exactly `\"add config tests\"` ā contains only the changes to `tests/test_config.py`\n\nThe working copy (`@`) should be an empty change on top of Commit C with no description.\n\n### Starting State\n\nThe repository at `/home/user/mylib` is a jj-backed git repository. It begins with the following history (newest first):\n\n1. A working-copy commit `@` (empty, no description) ā child of the commit below\n2. A commit with description **\"add config parser and update tests\"** that introduces:\n * `src/utils.py` with content:\n ```\n def greet(name):\n return f\"Hello, {name}!\"\n ```\n * `src/config.py` with content:\n ```\n def parse_config(path):\n return {\"path\": path}\n ```\n * `tests/test_config.py` with content:\n ```\n def test_parse_config():\n assert parse_config(\"a\") == {\"path\": \"a\"}\n ```\n3. An initial commit with description **\"initial commit\"** that sets up the repository structure (contains a `README.md` with the content `# mylib\\n`)\n\n### What You Must Do\n\nYou need to rewrite the history so that the mixed commit **\"add config parser and update tests\"** is replaced by the three clean commits described above (Commit A, Commit B, Commit C ā in that ancestor order, with Commit A being the oldest and Commit C the newest non-working-copy commit).\n\nSpecifically:\n\n1. **Split** the mixed commit `\"add config parser and update tests\"` into two separate commits. The first split should isolate `src/utils.py` with the description `\"add utility fix\"`, while the second split keeps `src/config.py` and `tests/test_config.py` together temporarily.\n\n2. **Split** again (or further separate) so that `src/config.py` and `tests/test_config.py` each end up in their own dedicated commits with descriptions `\"add config parser\"` and `\"add config tests\"` respectively.\n\n Alternatively, you may accomplish the split into three commits through any valid sequence of `jj split`, `jj squash`, `jj describe`, and/or `jj new` operations ā the maintainer only cares about the final state of the history, not the exact sequence of operations used.\n\n3. Ensure the final **working copy** (`@`) is an empty commit with no description, parented directly on top of the `\"add config tests\"` commit.\n\n4. A bookmark named **`feature`** must point to the commit with description `\"add config tests\"` (Commit C) at the end.\n\n### Verification Conditions\n\nThe automated test suite will verify:\n\n* The repository at `/home/user/mylib` is a valid jj repository.\n* The linear ancestry from `@` (working copy) through the history contains exactly the following commit descriptions in order (newest to oldest, excluding the working-copy empty change): `\"add config tests\"`, `\"add config parser\"`, `\"add utility fix\"`, `\"initial commit\"`.\n* The commit with description `\"add utility fix\"` modifies exactly one file: `src/utils.py`, and that file contains the `greet` function.\n* The commit with description `\"add config parser\"` modifies exactly one file: `src/config.py`, and that file contains the `parse_config` function.\n* The commit with description `\"add config tests\"` modifies exactly one file: `tests/test_config.py`, and that file contains the `test_parse_config` function.\n* The working copy (`@`) is empty (no changed files).\n* A bookmark named `feature` points to the commit with description `\"add config tests\"`.\n\n### Notes\n\n* Work exclusively inside `/home/user/mylib`.\n* Do not use `sudo` or root privileges.\n* Do not modify the `README.md` in the `\"initial commit\"` ā it must remain unchanged.\n* The jj user identity is already configured in the repository."}]}],"tools":[{"type":"function","function":{"name":"applyDiff","description":"This is a tool for editing files. For moving or renaming files, you should generally use the executeCommand tool with the 'mv' command instead. For larger edits, use the writeFile tool to overwrite files.\n\nBefore using this tool, use the readFile tool to understand the file's contents and context\n\nTo make a file edit, provide the following:\n1. path: The path to the file to modify (relative to the current working directory, or an absolute path)\n2. searchContent: The text to replace (must match the file contents exactly, including all whitespace and indentation)\n3. replaceContent: The edited text to replace the searchContent (must be different from searchContent)\n4. expectedReplacements: The number of replacements you expect to make. Defaults to 1 if not specified.\n\nBy default, the tool will replace ONE occurrence of searchContent with replaceContent in the specified file. If you want to replace multiple occurrences, provide the expectedReplacements parameter with the exact number of occurrences you expect.\n\nCRITICAL REQUIREMENTS FOR USING THIS TOOL:\n\n1. UNIQUENESS (when expectedReplacements is not specified): The searchContent MUST uniquely identify the specific instance you want to change. This means:\n - Include AT LEAST 3-5 lines of context BEFORE the change point\n - Include AT LEAST 3-5 lines of context AFTER the change point\n - Include all whitespace, indentation, and surrounding code exactly as it appears in the file\n\n2. EXPECTED MATCHES: If you want to replace multiple instances:\n - Use the expectedReplacements parameter with the exact number of occurrences you expect to replace\n - This will replace ALL occurrences of the searchContent with the replaceContent\n - If the actual number of matches doesn't equal expectedReplacements, the edit will fail\n - This is a safety feature to prevent unintended replacements\n\n3. VERIFICATION: Before using this tool:\n - Check how many instances of the target text exist in the file\n - If multiple instances exist, either:\n a) Gather enough context to uniquely identify each one and make separate calls, OR\n b) Use expectedReplacements parameter with the exact count of instances you expect to replace\n\nWARNING:\n- The tool will fail if searchContent matches multiple locations and expectedReplacements isn't specified\n- The tool will fail if the number of matches doesn't equal expectedReplacements when it's specified\n- The tool will fail if searchContent doesn't match the file contents exactly (including whitespace)\n- The tool will fail if searchContent and replaceContent are the same\n\nWhen making edits:\n - Ensure the edit results in idiomatic, correct code\n - Do not add trailing whitespace to lines (a newline at the end of a file is fine)\n - Do not leave the code in a broken state\n\nIf you want to create a new file, use:\n - A new file path, including dir name if needed\n - An empty searchContent\n - The new file's contents as replaceContent\n\nRemember: when making multiple file edits in a row to the same file, you should prefer to send all edits in a single message with multiple calls to this tool, rather than multiple messages with a single call each.\n\nYou may see the following fields in the result:\n- autoFormattingEdits: If the auto-formatter makes any changes, this field will contain a diff against the file content after your edits and any user edits have been applied.\n- newProblems: If any new problems are found after the edit, this field will contain information about them.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"The path of the file to modify (relative to the current working directory, or an absolute path)."},"searchContent":{"type":"string","description":"The text to replace."},"replaceContent":{"type":"string","description":"The text to replace it with."},"expectedReplacements":{"type":"number","description":"The expected number of replacements to perform. Defaults to 1 if not specified."}},"required":["path","searchContent","replaceContent"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"askFollowupQuestion","description":"Ask the user a question to gather additional information needed to complete the task. \n\n## When to Use This Tool\nUse this tool in the following scenarios:\n1. The user's request is ambiguous or unclear and requires clarification.\n2. You need more details to proceed effectively.\n3. You have made several unsuccessful attempts to solve the issue and need user guidance to move forward.\n4. Offer choices to the user about what direction to take.\n\n## Usage Notes\n- Users will always be able to select \"Other\" to provide custom text input\n- Use multiSelect: true to allow multiple answers to be selected for a question\n- If you recommend a specific option, make that the first option in the list and add \"(Recommended)\" at the end of the label\n- Provide 1-4 questions per call\n\nIMPORTANT: This tool CANNOT be used in combination with other tools (except todoWrite) in a single step. If you need to use other tools, you must do so in a separate step before calling this tool.","parameters":{"type":"object","properties":{"questions":{"type":"array","items":{"type":"object","properties":{"question":{"type":"string","description":"The complete question to ask the user. Should be clear, specific, and end with a question mark."},"header":{"type":"string","maxLength":12,"description":"Very short label displayed as a chip/tag (max 12 chars). Examples: \"Auth method\", \"Library\", \"Approach\"."},"options":{"type":"array","items":{"type":"object","properties":{"label":{"type":"string","description":"Short button label shown to the user. Should be concise (1-5 words) and clearly describe the choice."},"description":{"type":"string","description":"Explanation of what this option means or what will happen if chosen. Useful for providing context about trade-offs or implications."}},"required":["label"],"additionalProperties":false},"minItems":2,"maxItems":4,"description":"The available choices for this question. Must have 2-4 options. Each option should be a distinct, mutually exclusive choice (unless multiSelect is enabled). There should be no 'Other' option, that will be provided automatically."},"multiSelect":{"type":"boolean","default":false,"description":"Set to true to allow the user to select multiple options instead of just one. Use when choices are not mutually exclusive."}},"required":["question","header","options"],"additionalProperties":false},"minItems":1,"maxItems":4,"description":"Questions to ask the user (1-4 questions)."}},"required":["questions"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"attemptCompletion","description":"Once you've received the results of tool uses and can confirm that the task is complete, use this tool to present the result of your work to the user.\n\nYou MUST NOT generate any text before this tool call. All conclusion text must be included within the result parameter of the attemptCompletion tool.\nNever use this tool with a question or request to engage in further conversation! Formulate the end of your result in a way that is final and does not require further input from the user.\n\nIMPORTANT: This tool CANNOT be used in combination with other tools (except todoWrite) in a single step. If you need to use other tools, you must do so in a separate step before calling this tool.","parameters":{"$schema":"http://json-schema.org/draft-07/schema#","type":"object","properties":{"result":{"description":"The result of the task. Formulate this result in a way that is final and does not require further input from the user.","type":"string"}},"required":["result"],"additionalProperties":false}}},{"type":"function","function":{"name":"executeCommand","description":"Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.\n\nIMPORTANT: This tool is for terminal operations like git, npm, docker, etc. DO NOT use it for file operations (reading, writing, editing, searching, finding files) - use the specialized tools for this instead.\n\nBefore executing the command, please follow these steps:\n\n1. Directory Verification:\n - If the command will create new directories or files, first use listFiles to verify the parent directory exists and is the correct location\n - For example, before running \"mkdir foo/bar\", first use listFiles to check that \"foo\" exists and is the intended parent directory\n\n2. Command Execution:\n - Always quote file paths that contain spaces with double quotes (e.g., cd \"path with spaces/file.txt\")\n - Examples of proper quoting:\n - cd \"/Users/name/My Documents\" (correct)\n - cd /Users/name/My Documents (incorrect - will fail)\n - python \"/path/with spaces/script.py\" (correct)\n - python /path/with spaces/script.py (incorrect - will fail)\n - After ensuring proper quoting, execute the command.\n - Capture the output of the command.\n\nUsage notes:\n- The command argument is required.\n- You can specify an optional timeout in seconds (up to 300s / 5 minutes). If not specified, commands will timeout after 60s (1 minute).\n- If the output exceeds 30000 characters, output will be truncated before being returned to you.\n- When issuing multiple commands:\n - If the commands are independent and can run in parallel, make multiple executeCommand tool calls in a single message. For example, if you need to run \"git status\" and \"git diff\", send a single message with two executeCommand tool calls in parallel.\n - If the commands depend on each other and must run sequentially, use a single executeCommand call with '&&' to chain them together (e.g., `git add . && git commit -m \"message\" && git push`). For instance, if one operation must complete before another starts (like mkdir before cp, Write before executeCommand for git operations, or git add before git commit), run these operations sequentially instead.\n - Use ';' only when you need to run commands sequentially but don't care if earlier commands fail\n - DO NOT use newlines to separate commands (newlines are ok in quoted strings)\n- You shall avoid use the markdown code block syntax (backtick, '`') in your command, as it will be interpreted as a command substitution.\n- Before using this tool, you must first think about the context provided in <system-reminder> to understand the user's environment and tailor your commands to ensure they are compatible with their system. You must also consider if the command you need to run should be executed in a specific directory rather than the current working directory, and properly set the `cwd` if necessary.\n\n# Committing changes with git\n\nOnly create commits when requested by the user. If unclear, ask first. When the user asks you to create a new git commit, follow these steps carefully:\n\nGit Safety Protocol:\n- NEVER update the git config\n- NEVER run destructive git commands (push --force, reset --hard, checkout ., restore ., clean -f, branch -D) unless the user explicitly requests these actions. Taking unauthorized destructive actions is unhelpful and can result in lost work, so it's best to ONLY run these commands when given direct instructions \n- NEVER skip hooks (--no-verify, --no-gpg-sign, etc) unless the user explicitly requests it\n- NEVER run force push to main/master, warn the user if they request it\n- CRITICAL: Always create NEW commits rather than amending, unless the user explicitly requests a git amend. When a pre-commit hook fails, the commit did NOT happen ā so --amend would modify the PREVIOUS commit, which may result in destroying work or losing previous changes. Instead, after hook failure, fix the issue, re-stage, and create a NEW commit\n- When staging files, prefer adding specific files by name rather than using \"git add -A\" or \"git add .\", which can accidentally include sensitive files (.env, credentials) or large binaries\n- NEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked, otherwise the user will feel that you are being too proactive\n\n1. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following bash commands in parallel, each using the executeCommand tool:\n - Run a git status command to see all untracked files. IMPORTANT: Never use the -uall flag as it can cause memory issues on large repos.\n - Run a git diff command to see both staged and unstaged changes that will be committed.\n - Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.\n2. Analyze all staged changes (both previously staged and newly added) and draft a commit message:\n - Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.). Ensure the message accurately reflects the changes and their purpose (i.e. \"add\" means a wholly new feature, \"update\" means an enhancement to an existing feature, \"fix\" means a bug fix, etc.).\n - Do not commit files that likely contain secrets (.env, credentials.json, etc). Warn the user if they specifically request to commit those files\n - Draft a concise (1-2 sentences) commit message that focuses on the \"why\" rather than the \"what\"\n - Ensure it accurately reflects the changes and their purpose\n3. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following commands:\n - Add relevant untracked files to the staging area.\n - Create the commit with a message ending with:\n š¤ Generated with [Pochi](https://getpochi.com) | [Task](<Share URL>)\n\n Co-Authored-By: Pochi <noreply@getpochi.com>\n\n Note: Replace <Share URL> with the Share URL from system information if available. If not available, omit the \" | [Task](...)\" part.\n\n - Run git status after the commit completes to verify success.\n Note: git status depends on the commit completing, so run it sequentially after the commit.\n4. If the commit fails due to pre-commit hook changes, retry the commit ONCE to include these automated changes. If it fails again, it usually means a pre-commit hook is preventing the commit. If the commit succeeds but you notice that files were modified by the pre-commit hook, you MUST amend your commit to include them.\n\nImportant notes:\n- NEVER update the git config\n- NEVER run additional commands to read or explore code, besides git bash commands\n- DO NOT push to the remote repository unless the user explicitly asks you to do so\n- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.\n- IMPORTANT: Do not use --no-edit with git rebase commands, as the --no-edit flag is not a valid option for git rebase.\n- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit\n- In order to ensure good formatting, ALWAYS pass the commit message via a HEREDOC, a la this example:\n<example>\ngit commit -m \"$(cat <<'EOF'\nCommit message here.\n\nš¤ Generated with [Pochi](https://getpochi.com) | [Task](<Share URL>)\n\nCo-Authored-By: Pochi <noreply@getpochi.com>\nEOF\n)\"\n</example>\n\n# Creating pull requests\nUse the gh command via the executeCommand tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a Github URL use the gh command to get the information needed.\n\nIMPORTANT: When the user asks you to create a pull request, follow these steps carefully:\n\n1. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following bash commands in parallel using the executeCommand tool, in order to understand the current state of the branch since it diverged from the main branch:\n - Run a git status command to see all untracked files (never use -uall flag)\n - Run a git diff command to see both staged and unstaged changes that will be committed\n - Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote\n - Run a git log command and `git diff [base-branch]...HEAD` to understand the full commit history for the current branch (from the time it diverged from the base branch)\n2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request title and summary:\n - Keep the PR title short (under 70 characters)\n - Use the description/body for details, not the title\n3. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following commands in parallel:\n - Create new branch if needed\n - Push to remote with -u flag if needed\n - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.\n<example>\ngh pr create --title \"the pr title\" --body \"$(cat <<'EOF'\n## Summary\n<1-3 bullet points>\n\n## Test plan\n[Checklist of TODOs for testing the pull request...]\n\nš¤ Generated with [Pochi](https://getpochi.com) | [Task](<Share URL>)\nEOF\n)\"\n</example>\n\nImportant:\n- NEVER update the git config\n- Return the PR URL when you're done, so the user can see it\n- Replace <Share URL> with the Share URL from system information if available. If not available, omit the \" | [Task](...)\" part.\n\n# Other common operations\n1. View comments on a Github PR, you should run following commands\n - gh api repos/foo/bar/pulls/123/comments\n - gh pr view --comments","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The CLI command to execute. This should be valid for the current operating system."},"cwd":{"type":"string","description":"The working directory to execute the command in."},"timeout":{"type":"number","minimum":1,"maximum":300,"description":"Optional timeout in seconds, max 300 seconds. By default the timeout is 120 seconds."}},"required":["command"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"globFiles","description":"Request to find files matching a glob pattern within a specified directory. Use this to get a list of files based on a pattern.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"The path of the directory to search in (relative to the current working directory, or an absolute path)"},"globPattern":{"type":"string","description":"The glob pattern to match files against (e.g., '*.ts', '**/*.js')"}},"required":["path","globPattern"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"listFiles","description":"Request to list files and directories within the specified directory. If recursive is true, it will list all files and directories recursively. If recursive is false or not provided, it will only list the top-level contents. Do not use this tool to confirm the existence of files you may have created, as the user will let you know if the files were created successfully or not.","parameters":{"type":"object","properties":{"path":{"type":"string","description":"The path of the directory to list contents for (relative to the current working directory, or an absolute path)"},"recursive":{"type":"boolean","description":"Whether to list files and directories recursively."}},"required":["path"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}}},{"type":"function","function":{"name":"readFile","description":"Request to read the contents of a file at the specified path. Use this when you need to examine the contents of an existing file you do not know the contents of, for example to analyze code, review text files, extract information from configuration files.\n","parameters":{"type":"object","properties":{"path":{"type":"string","description