Duplicate Executions in Kimi K2 Model via Cortecs or Nebius Directly #2284

New Issue

Open

opened 2026-02-16 17:34:58 -05:00 by yindo · 9 comments

yindo commented 2026-02-16 17:34:58 -05:00

Owner

Copy Link

Copy Source

Originally created by @ASMAE20 on GitHub (Oct 26, 2025).

Originally assigned to: @rekram1-node on GitHub.

Description

I encountered an issue while using the Kimi K2 model where the model executes the same request multiple times (typically three), even though the input prompt is sent only once.

I first used OpenCode and sent the request through Cortecs, and observed this issue. Then, I tried sending the same request directly to Nebius (without using Cortecs) and experienced the same behavior. This suggests that the issue is not related to Cortecs. Nebius also confirmed that the problem is not on their side.

Could this be related to the OpenCode setup, the Kimi K2 model itself, or am I missing something 🤔

?

Originally created by @ASMAE20 on GitHub (Oct 26, 2025). Originally assigned to: @rekram1-node on GitHub. ### Description I encountered an issue while using the Kimi K2 model where the model executes the same request multiple times (typically three), even though the input prompt is sent only once. I first used OpenCode and sent the request through Cortecs, and observed this issue. Then, I tried sending the same request directly to Nebius (without using Cortecs) and experienced the same behavior. This suggests that the issue is not related to Cortecs. Nebius also confirmed that the problem is not on their side. Could this be related to the OpenCode setup, the Kimi K2 model itself, or am I missing something 🤔 <img width="1678" height="492" alt="Image" src="https://github.com/user-attachments/assets/294a3aa8-4ae0-4bfd-9410-579640ce78f0" /> ?

yindo added the bug label 2026-02-16 17:34:58 -05:00

yindo commented 2026-02-16 17:34:58 -05:00

Author

Owner

Copy Link

Copy Source

@github-actions[bot] commented on GitHub (Oct 26, 2025):

This issue might be a duplicate of existing issues. Please check:

• #3444: GLM-4.6 model gets stuck in infinite loop, repeating same actions - Similar issue where a model repeats the same actions/executions, though with GLM-4.6 instead of Kimi K2

Feel free to ignore if none of these address your specific case.

@github-actions[bot] commented on GitHub (Oct 26, 2025): This issue might be a duplicate of existing issues. Please check: - #3444: GLM-4.6 model gets stuck in infinite loop, repeating same actions - Similar issue where a model repeats the same actions/executions, though with GLM-4.6 instead of Kimi K2 Feel free to ignore if none of these address your specific case.

yindo commented 2026-02-16 17:34:58 -05:00

Author

Owner

Copy Link

Copy Source

@rekram1-node commented on GitHub (Oct 26, 2025):

It can be hard to tell without seeing the session (if u could share that'd be awesome) but kimi k2 does sometimes enter doom loops. That could be what happened

@rekram1-node commented on GitHub (Oct 26, 2025): It can be hard to tell without seeing the session (if u could share that'd be awesome) but kimi k2 does sometimes enter doom loops. That could be what happened

yindo commented 2026-02-16 17:34:58 -05:00

Author

Owner

Copy Link

Copy Source

@ASMAE20 commented on GitHub (Oct 26, 2025):

@rekram1-node Could you please clarify what additional information I need to share?

@ASMAE20 commented on GitHub (Oct 26, 2025): @rekram1-node Could you please clarify what additional information I need to share?

yindo commented 2026-02-16 17:34:58 -05:00

Author

Owner

Copy Link

Copy Source

@rekram1-node commented on GitHub (Oct 26, 2025):

@ASMAE20 if you can open the session and do a /share it will make a share link that is viewable on the web it will give me some clarity to look into it

Alternatively you can run opencode export and select the session that had this, and give me the json dump of it

@rekram1-node commented on GitHub (Oct 26, 2025): @ASMAE20 if you can open the session and do a /share it will make a share link that is viewable on the web it will give me some clarity to look into it Alternatively you can run `opencode export` and select the session that had this, and give me the json dump of it

yindo commented 2026-02-16 17:34:58 -05:00

Author

Owner

Copy Link

Copy Source

@ASMAE20 commented on GitHub (Oct 26, 2025):

@rekram1-node This one

@ASMAE20 commented on GitHub (Oct 26, 2025): @rekram1-node [This one ](https://opencode.ai/s/1XV4twn9)

yindo commented 2026-02-16 17:34:58 -05:00

Author

Owner

Copy Link

Copy Source

@rekram1-node commented on GitHub (Oct 26, 2025):

Hm now that is pretty strange I haven't seen this with other providers

@rekram1-node commented on GitHub (Oct 26, 2025): Hm now that is pretty strange I haven't seen this with other providers

yindo commented 2026-02-16 17:34:58 -05:00

Author

Owner

Copy Link

Copy Source

@ASMAE20 commented on GitHub (Oct 27, 2025):

@rekram1-node So what could be a possible assumption here?

@ASMAE20 commented on GitHub (Oct 27, 2025): @rekram1-node So what could be a possible assumption here?

yindo commented 2026-02-16 17:34:59 -05:00

Author

Owner

Copy Link

Copy Source

@rekram1-node commented on GitHub (Oct 28, 2025):

The duplication appears to be coming from their apis, I noticed that there are 2 messages with the same parent id msg_a2195fb1a001eW0gGxvTDdC6HC, all our messages & parts are built from the ai sdk primitives, I haven't seen this behavior with other providers so it seems like they are double sending a message perhaps? I may need to setup an account to help debug further

Raw json:

{
  "info": {
    "id": "ses_5de6af0bdffefjog7L1XV4twn9",
    "version": "0.15.18",
    "projectID": "global",
    "directory": "/home/asmae-elazrak",
    "title": "Greeting",
    "time": {
      "created": 1761500008259,
      "updated": 1761500082087
    },
    "summary": {
      "diffs": []
    },
    "share": {
      "url": "https://opencode.ai/s/1XV4twn9"
    }
  },
  "messages": {
    "msg_a21950f4b0012gfFA09gQMrXfW": {
      "parts": [
        {
          "id": "prt_a21950f4b002Owh01ksI7vuWhS",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a21950f4b0012gfFA09gQMrXfW",
          "type": "text",
          "text": "hi",
          "synthetic": false,
          "time": {
            "start": 0,
            "end": 0
          }
        }
      ],
      "id": "msg_a21950f4b0012gfFA09gQMrXfW",
      "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
      "role": "user",
      "time": {
        "created": 1761500008305
      },
      "summary": {
        "diffs": []
      }
    },
    "msg_a219510950018hEvPas3Cbtoxx": {
      "parts": [
        {
          "id": "prt_a219517aa001Xxn3Gq30DzygbE",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a219510950018hEvPas3Cbtoxx",
          "type": "step-start"
        },
        {
          "id": "prt_a219517b4001ZTTUl8aJPcd2hN",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a219510950018hEvPas3Cbtoxx",
          "type": "text",
          "text": "Hello! How can I help you today?",
          "time": {
            "start": 1761500010481,
            "end": 1761500010481
          }
        },
        {
          "id": "prt_a219517fb001fyTigf2fZTuIup",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a219510950018hEvPas3Cbtoxx",
          "type": "step-finish",
          "reason": "stop",
          "cost": 0.00538218,
          "tokens": {
            "input": 9720,
            "output": 10,
            "reasoning": 0,
            "cache": {
              "read": 0,
              "write": 0
            }
          }
        }
      ],
      "id": "msg_a219510950018hEvPas3Cbtoxx",
      "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
      "role": "assistant",
      "time": {
        "created": 1761500008597,
        "completed": 1761500010522
      },
      "system": [
        "You are opencode, an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\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- /help: Get help with using opencode\n- To give feedback, users should report the issue at https://github.com/sst/opencode/issues\n\nWhen the user directly asks about opencode (eg 'can opencode do...', 'does opencode have...') or asks in second person (eg 'are you able...', 'can you do...'), first use the WebFetch tool to gather information to answer the question from opencode docs at https://opencode.ai\n\n# Tone and style\nYou should be concise, direct, and to the point. When you run a non-trivial bash command, you should explain what the command does and why you are running it, to make sure the user understands what you are doing (this is especially important when you are running a command that will make changes to the user's system).\nRemember that your output will be displayed on a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\nOutput text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.\nIf you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.\nOnly use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.\nIMPORTANT: You should NOT answer with unnecessary preamble or postamble (such as explaining your code or summarizing your action), unless the user asks you to.\nIMPORTANT: Keep your responses short, since they will be displayed on a command line interface. You MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail. Answer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text before/after your response, such as \"The answer is <answer>.\", \"Here is the content of the file...\" or \"Based on the information provided, the answer is...\" or \"Here is what I will do next...\". Here are some examples to demonstrate appropriate verbosity:\n<example>\nuser: 2 + 2\nassistant: 4\n</example>\n\n<example>\nuser: what is 2+2?\nassistant: 4\n</example>\n\n<example>\nuser: is 11 a prime number?\nassistant: Yes\n</example>\n\n<example>\nuser: what command should I run to list files in the current directory?\nassistant: ls\n</example>\n\n<example>\nuser: what command should I run to watch files in the current directory?\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\nnpm run dev\n</example>\n\n<example>\nuser: How many golf balls fit inside a jetta?\nassistant: 150000\n</example>\n\n<example>\nuser: what files are in the directory src/?\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\nuser: which file contains the implementation of foo?\nassistant: src/foo.c\n</example>\n\n<example>\nuser: write tests for new feature\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\n</example>\n\n# Proactiveness\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\n1. Doing the right thing when asked, including taking actions and follow-up actions\n2. Not surprising the user with actions you take without asking\nFor example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\n3. Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\n\n# Following conventions\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Code style\n- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked\n\n# Doing tasks\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\n- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.\n- Implement the solution using all tools available to you\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\n- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to AGENTS.md so that you will know to run it next time.\nNEVER 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\n- Tool results and 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.\n\n# Tool usage policy\n- When doing file search, prefer to use the Task tool in order to reduce context usage.\n- You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run \"git status\" and \"git diff\", send a single message with two tool calls to run the calls in parallel.\n\nYou MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\n\n# Code References\n\nWhen referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.\n\n<example>\nuser: Where are errors from the client handled?\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.ts:712.\n</example>\n\n",
        "Here is some useful information about the environment you are running in:\n<env>\n  Working directory: /home/asmae-elazrak\n  Is directory a git repo: no\n  Platform: linux\n  Today's date: Sun Oct 26 2025\n</env>\n<project>\n  \n</project>"
      ],
      "parentID": "msg_a21950f4b0012gfFA09gQMrXfW",
      "modelID": "kimi-k2-instruct",
      "providerID": "cortecs",
      "mode": "build",
      "path": {
        "cwd": "/home/asmae-elazrak",
        "root": "/"
      },
      "cost": 0.00538218,
      "tokens": {
        "input": 9720,
        "output": 10,
        "reasoning": 0,
        "cache": {
          "read": 0,
          "write": 0
        }
      }
    },
    "msg_a2195fb1a001eW0gGxvTDdC6HC": {
      "parts": [
        {
          "id": "prt_a2195fb1a002hdpcJCH2ktX50B",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a2195fb1a001eW0gGxvTDdC6HC",
          "type": "text",
          "text": "Creat a python file to calculate prime numbers < 100",
          "synthetic": false,
          "time": {
            "start": 0,
            "end": 0
          }
        }
      ],
      "id": "msg_a2195fb1a001eW0gGxvTDdC6HC",
      "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
      "role": "user",
      "time": {
        "created": 1761500068637
      },
      "summary": {
        "diffs": []
      }
    },
    "msg_a2195fb82001cUXT0hQCC2bhXI": {
      "parts": [
        {
          "id": "prt_a219600e4001pO7iXlLQIySX0w",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a2195fb82001cUXT0hQCC2bhXI",
          "type": "step-start"
        },
        {
          "id": "prt_a219601dc001EV6NlOBJT3WjWq",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a2195fb82001cUXT0hQCC2bhXI",
          "type": "tool",
          "callID": "functions.write:0",
          "tool": "write",
          "state": {
            "status": "completed",
            "input": {
              "filePath": "/home/asmae-elazrak/primes.py",
              "content": "def is_prime(n):\n    if n < 2:\n        return False\n    for i in range(2, int(n ** 0.5) + 1):\n        if n % i == 0:\n            return False\n    return True\n\nprimes = [n for n in range(2, 100) if is_prime(n)]\nprint(f\"Prime numbers less than 100: {primes}\")\nprint(f\"Count: {len(primes)}\")"
            },
            "output": "",
            "title": "home/asmae-elazrak/primes.py",
            "metadata": {
              "diagnostics": {
                "/home/asmae-elazrak/primes.py": []
              },
              "filepath": "/home/asmae-elazrak/primes.py",
              "exists": false
            },
            "time": {
              "start": 1761500072983,
              "end": 1761500077058
            }
          }
        },
        {
          "id": "prt_a21961c09001E3UqXHjyQrNBZb",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a2195fb82001cUXT0hQCC2bhXI",
          "type": "step-finish",
          "reason": "tool-calls",
          "cost": 0.005736296,
          "tokens": {
            "input": 9748,
            "output": 138,
            "reasoning": 0,
            "cache": {
              "read": 0,
              "write": 0
            }
          }
        }
      ],
      "id": "msg_a2195fb82001cUXT0hQCC2bhXI",
      "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
      "role": "assistant",
      "time": {
        "created": 1761500068738,
        "completed": 1761500077088
      },
      "system": [
        "You are opencode, an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\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- /help: Get help with using opencode\n- To give feedback, users should report the issue at https://github.com/sst/opencode/issues\n\nWhen the user directly asks about opencode (eg 'can opencode do...', 'does opencode have...') or asks in second person (eg 'are you able...', 'can you do...'), first use the WebFetch tool to gather information to answer the question from opencode docs at https://opencode.ai\n\n# Tone and style\nYou should be concise, direct, and to the point. When you run a non-trivial bash command, you should explain what the command does and why you are running it, to make sure the user understands what you are doing (this is especially important when you are running a command that will make changes to the user's system).\nRemember that your output will be displayed on a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\nOutput text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.\nIf you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.\nOnly use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.\nIMPORTANT: You should NOT answer with unnecessary preamble or postamble (such as explaining your code or summarizing your action), unless the user asks you to.\nIMPORTANT: Keep your responses short, since they will be displayed on a command line interface. You MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail. Answer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text before/after your response, such as \"The answer is <answer>.\", \"Here is the content of the file...\" or \"Based on the information provided, the answer is...\" or \"Here is what I will do next...\". Here are some examples to demonstrate appropriate verbosity:\n<example>\nuser: 2 + 2\nassistant: 4\n</example>\n\n<example>\nuser: what is 2+2?\nassistant: 4\n</example>\n\n<example>\nuser: is 11 a prime number?\nassistant: Yes\n</example>\n\n<example>\nuser: what command should I run to list files in the current directory?\nassistant: ls\n</example>\n\n<example>\nuser: what command should I run to watch files in the current directory?\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\nnpm run dev\n</example>\n\n<example>\nuser: How many golf balls fit inside a jetta?\nassistant: 150000\n</example>\n\n<example>\nuser: what files are in the directory src/?\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\nuser: which file contains the implementation of foo?\nassistant: src/foo.c\n</example>\n\n<example>\nuser: write tests for new feature\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\n</example>\n\n# Proactiveness\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\n1. Doing the right thing when asked, including taking actions and follow-up actions\n2. Not surprising the user with actions you take without asking\nFor example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\n3. Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\n\n# Following conventions\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Code style\n- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked\n\n# Doing tasks\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\n- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.\n- Implement the solution using all tools available to you\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\n- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to AGENTS.md so that you will know to run it next time.\nNEVER 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\n- Tool results and 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.\n\n# Tool usage policy\n- When doing file search, prefer to use the Task tool in order to reduce context usage.\n- You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run \"git status\" and \"git diff\", send a single message with two tool calls to run the calls in parallel.\n\nYou MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\n\n# Code References\n\nWhen referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.\n\n<example>\nuser: Where are errors from the client handled?\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.ts:712.\n</example>\n\n",
        "Here is some useful information about the environment you are running in:\n<env>\n  Working directory: /home/asmae-elazrak\n  Is directory a git repo: no\n  Platform: linux\n  Today's date: Sun Oct 26 2025\n</env>\n<project>\n  \n</project>"
      ],
      "parentID": "msg_a2195fb1a001eW0gGxvTDdC6HC",
      "modelID": "kimi-k2-instruct",
      "providerID": "cortecs",
      "mode": "build",
      "path": {
        "cwd": "/home/asmae-elazrak",
        "root": "/"
      },
      "cost": 0.005736296,
      "tokens": {
        "input": 9748,
        "output": 138,
        "reasoning": 0,
        "cache": {
          "read": 0,
          "write": 0
        }
      }
    },
    "msg_a21961c340017jF1p6mXM8I446": {
      "parts": [
        {
          "id": "prt_a21961f2d001Ec9dVvZreeFxzj",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a21961c340017jF1p6mXM8I446",
          "type": "step-start"
        },
        {
          "id": "prt_a21961f990010VBK0W0eSQmHqD",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a21961c340017jF1p6mXM8I446",
          "type": "tool",
          "callID": "functions.write:0",
          "tool": "write",
          "state": {
            "status": "completed",
            "input": {
              "filePath": "/home/asmae-elazrak/primes.py",
              "content": "def is_prime(n):\n    if n < 2:\n        return False\n    for i in range(2, int(n ** 0.5) + 1):\n        if n % i == 0:\n            return False\n    return True\n\nprimes = [n for n in range(2, 100) if is_prime(n)]\nprint(f\"Prime numbers less than 100: {primes}\")\nprint(f\"Count: {len(primes)}\")"
            },
            "output": "",
            "title": "home/asmae-elazrak/primes.py",
            "metadata": {
              "diagnostics": {
                "/home/asmae-elazrak/primes.py": []
              },
              "filepath": "/home/asmae-elazrak/primes.py",
              "exists": true
            },
            "time": {
              "start": 1761500080339,
              "end": 1761500080810
            }
          }
        },
        {
          "id": "prt_a21962aad001J7nLjJQbNbcGhx",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a21961c340017jF1p6mXM8I446",
          "type": "step-finish",
          "reason": "tool-calls",
          "cost": 0.005740704,
          "tokens": {
            "input": 9756,
            "output": 138,
            "reasoning": 0,
            "cache": {
              "read": 0,
              "write": 0
            }
          }
        }
      ],
      "id": "msg_a21961c340017jF1p6mXM8I446",
      "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
      "role": "assistant",
      "time": {
        "created": 1761500077108,
        "completed": 1761500080833
      },
      "system": [
        "You are opencode, an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\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- /help: Get help with using opencode\n- To give feedback, users should report the issue at https://github.com/sst/opencode/issues\n\nWhen the user directly asks about opencode (eg 'can opencode do...', 'does opencode have...') or asks in second person (eg 'are you able...', 'can you do...'), first use the WebFetch tool to gather information to answer the question from opencode docs at https://opencode.ai\n\n# Tone and style\nYou should be concise, direct, and to the point. When you run a non-trivial bash command, you should explain what the command does and why you are running it, to make sure the user understands what you are doing (this is especially important when you are running a command that will make changes to the user's system).\nRemember that your output will be displayed on a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\nOutput text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.\nIf you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.\nOnly use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.\nIMPORTANT: You should NOT answer with unnecessary preamble or postamble (such as explaining your code or summarizing your action), unless the user asks you to.\nIMPORTANT: Keep your responses short, since they will be displayed on a command line interface. You MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail. Answer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text before/after your response, such as \"The answer is <answer>.\", \"Here is the content of the file...\" or \"Based on the information provided, the answer is...\" or \"Here is what I will do next...\". Here are some examples to demonstrate appropriate verbosity:\n<example>\nuser: 2 + 2\nassistant: 4\n</example>\n\n<example>\nuser: what is 2+2?\nassistant: 4\n</example>\n\n<example>\nuser: is 11 a prime number?\nassistant: Yes\n</example>\n\n<example>\nuser: what command should I run to list files in the current directory?\nassistant: ls\n</example>\n\n<example>\nuser: what command should I run to watch files in the current directory?\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\nnpm run dev\n</example>\n\n<example>\nuser: How many golf balls fit inside a jetta?\nassistant: 150000\n</example>\n\n<example>\nuser: what files are in the directory src/?\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\nuser: which file contains the implementation of foo?\nassistant: src/foo.c\n</example>\n\n<example>\nuser: write tests for new feature\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\n</example>\n\n# Proactiveness\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\n1. Doing the right thing when asked, including taking actions and follow-up actions\n2. Not surprising the user with actions you take without asking\nFor example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\n3. Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\n\n# Following conventions\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Code style\n- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked\n\n# Doing tasks\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\n- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.\n- Implement the solution using all tools available to you\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\n- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to AGENTS.md so that you will know to run it next time.\nNEVER 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\n- Tool results and 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.\n\n# Tool usage policy\n- When doing file search, prefer to use the Task tool in order to reduce context usage.\n- You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run \"git status\" and \"git diff\", send a single message with two tool calls to run the calls in parallel.\n\nYou MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\n\n# Code References\n\nWhen referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.\n\n<example>\nuser: Where are errors from the client handled?\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.ts:712.\n</example>\n\n",
        "Here is some useful information about the environment you are running in:\n<env>\n  Working directory: /home/asmae-elazrak\n  Is directory a git repo: no\n  Platform: linux\n  Today's date: Sun Oct 26 2025\n</env>\n<project>\n  \n</project>"
      ],
      "parentID": "msg_a2195fb1a001eW0gGxvTDdC6HC",
      "modelID": "kimi-k2-instruct",
      "providerID": "cortecs",
      "mode": "build",
      "path": {
        "cwd": "/home/asmae-elazrak",
        "root": "/"
      },
      "cost": 0.005740704,
      "tokens": {
        "input": 9756,
        "output": 138,
        "reasoning": 0,
        "cache": {
          "read": 0,
          "write": 0
        }
      }
    },
    "msg_a21962ae2001Q9hQQ7nIpLqDwo": {
      "parts": [
        {
          "id": "prt_a21962e01001uBfRYSLOfs2q5X",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a21962ae2001Q9hQQ7nIpLqDwo",
          "type": "step-start"
        },
        {
          "id": "prt_a21962e03001RxJDyi1nI5hjWY",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a21962ae2001Q9hQQ7nIpLqDwo",
          "type": "text",
          "text": "Created `primes.py` with a function to calculate all prime numbers less than 100.",
          "time": {
            "start": 1761500082007,
            "end": 1761500082007
          }
        },
        {
          "id": "prt_a21962f580019P7edkwd2P3Nr0",
          "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
          "messageID": "msg_a21962ae2001Q9hQQ7nIpLqDwo",
          "type": "step-finish",
          "reason": "stop",
          "cost": 0.005432884,
          "tokens": {
            "input": 9764,
            "output": 20,
            "reasoning": 0,
            "cache": {
              "read": 0,
              "write": 0
            }
          }
        }
      ],
      "id": "msg_a21962ae2001Q9hQQ7nIpLqDwo",
      "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9",
      "role": "assistant",
      "time": {
        "created": 1761500080866,
        "completed": 1761500082035
      },
      "system": [
        "You are opencode, an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\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- /help: Get help with using opencode\n- To give feedback, users should report the issue at https://github.com/sst/opencode/issues\n\nWhen the user directly asks about opencode (eg 'can opencode do...', 'does opencode have...') or asks in second person (eg 'are you able...', 'can you do...'), first use the WebFetch tool to gather information to answer the question from opencode docs at https://opencode.ai\n\n# Tone and style\nYou should be concise, direct, and to the point. When you run a non-trivial bash command, you should explain what the command does and why you are running it, to make sure the user understands what you are doing (this is especially important when you are running a command that will make changes to the user's system).\nRemember that your output will be displayed on a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\nOutput text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.\nIf you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.\nOnly use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.\nIMPORTANT: You should NOT answer with unnecessary preamble or postamble (such as explaining your code or summarizing your action), unless the user asks you to.\nIMPORTANT: Keep your responses short, since they will be displayed on a command line interface. You MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail. Answer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text before/after your response, such as \"The answer is <answer>.\", \"Here is the content of the file...\" or \"Based on the information provided, the answer is...\" or \"Here is what I will do next...\". Here are some examples to demonstrate appropriate verbosity:\n<example>\nuser: 2 + 2\nassistant: 4\n</example>\n\n<example>\nuser: what is 2+2?\nassistant: 4\n</example>\n\n<example>\nuser: is 11 a prime number?\nassistant: Yes\n</example>\n\n<example>\nuser: what command should I run to list files in the current directory?\nassistant: ls\n</example>\n\n<example>\nuser: what command should I run to watch files in the current directory?\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\nnpm run dev\n</example>\n\n<example>\nuser: How many golf balls fit inside a jetta?\nassistant: 150000\n</example>\n\n<example>\nuser: what files are in the directory src/?\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\nuser: which file contains the implementation of foo?\nassistant: src/foo.c\n</example>\n\n<example>\nuser: write tests for new feature\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\n</example>\n\n# Proactiveness\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\n1. Doing the right thing when asked, including taking actions and follow-up actions\n2. Not surprising the user with actions you take without asking\nFor example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\n3. Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\n\n# Following conventions\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Code style\n- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked\n\n# Doing tasks\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\n- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.\n- Implement the solution using all tools available to you\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\n- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to AGENTS.md so that you will know to run it next time.\nNEVER 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\n- Tool results and 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.\n\n# Tool usage policy\n- When doing file search, prefer to use the Task tool in order to reduce context usage.\n- You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run \"git status\" and \"git diff\", send a single message with two tool calls to run the calls in parallel.\n\nYou MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\n\n# Code References\n\nWhen referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.\n\n<example>\nuser: Where are errors from the client handled?\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.ts:712.\n</example>\n\n",
        "Here is some useful information about the environment you are running in:\n<env>\n  Working directory: /home/asmae-elazrak\n  Is directory a git repo: no\n  Platform: linux\n  Today's date: Sun Oct 26 2025\n</env>\n<project>\n  \n</project>"
      ],
      "parentID": "msg_a2195fb1a001eW0gGxvTDdC6HC",
      "modelID": "kimi-k2-instruct",
      "providerID": "cortecs",
      "mode": "build",
      "path": {
        "cwd": "/home/asmae-elazrak",
        "root": "/"
      },
      "cost": 0.005432884,
      "tokens": {
        "input": 9764,
        "output": 20,
        "reasoning": 0,
        "cache": {
          "read": 0,
          "write": 0
        }
      }
    }
  }
}

@rekram1-node commented on GitHub (Oct 28, 2025): The duplication appears to be coming from their apis, I noticed that there are 2 messages with the same parent id `msg_a2195fb1a001eW0gGxvTDdC6HC`, all our messages & parts are built from the ai sdk primitives, I haven't seen this behavior with other providers so it seems like they are double sending a message perhaps? I may need to setup an account to help debug further Raw json: ``` { "info": { "id": "ses_5de6af0bdffefjog7L1XV4twn9", "version": "0.15.18", "projectID": "global", "directory": "/home/asmae-elazrak", "title": "Greeting", "time": { "created": 1761500008259, "updated": 1761500082087 }, "summary": { "diffs": [] }, "share": { "url": "https://opencode.ai/s/1XV4twn9" } }, "messages": { "msg_a21950f4b0012gfFA09gQMrXfW": { "parts": [ { "id": "prt_a21950f4b002Owh01ksI7vuWhS", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a21950f4b0012gfFA09gQMrXfW", "type": "text", "text": "hi", "synthetic": false, "time": { "start": 0, "end": 0 } } ], "id": "msg_a21950f4b0012gfFA09gQMrXfW", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "role": "user", "time": { "created": 1761500008305 }, "summary": { "diffs": [] } }, "msg_a219510950018hEvPas3Cbtoxx": { "parts": [ { "id": "prt_a219517aa001Xxn3Gq30DzygbE", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a219510950018hEvPas3Cbtoxx", "type": "step-start" }, { "id": "prt_a219517b4001ZTTUl8aJPcd2hN", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a219510950018hEvPas3Cbtoxx", "type": "text", "text": "Hello! How can I help you today?", "time": { "start": 1761500010481, "end": 1761500010481 } }, { "id": "prt_a219517fb001fyTigf2fZTuIup", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a219510950018hEvPas3Cbtoxx", "type": "step-finish", "reason": "stop", "cost": 0.00538218, "tokens": { "input": 9720, "output": 10, "reasoning": 0, "cache": { "read": 0, "write": 0 } } } ], "id": "msg_a219510950018hEvPas3Cbtoxx", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "role": "assistant", "time": { "created": 1761500008597, "completed": 1761500010522 }, "system": [ "You are opencode, an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\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- /help: Get help with using opencode\n- To give feedback, users should report the issue at https://github.com/sst/opencode/issues\n\nWhen the user directly asks about opencode (eg 'can opencode do...', 'does opencode have...') or asks in second person (eg 'are you able...', 'can you do...'), first use the WebFetch tool to gather information to answer the question from opencode docs at https://opencode.ai\n\n# Tone and style\nYou should be concise, direct, and to the point. When you run a non-trivial bash command, you should explain what the command does and why you are running it, to make sure the user understands what you are doing (this is especially important when you are running a command that will make changes to the user's system).\nRemember that your output will be displayed on a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\nOutput text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.\nIf you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.\nOnly use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.\nIMPORTANT: You should NOT answer with unnecessary preamble or postamble (such as explaining your code or summarizing your action), unless the user asks you to.\nIMPORTANT: Keep your responses short, since they will be displayed on a command line interface. You MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail. Answer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text before/after your response, such as \"The answer is <answer>.\", \"Here is the content of the file...\" or \"Based on the information provided, the answer is...\" or \"Here is what I will do next...\". Here are some examples to demonstrate appropriate verbosity:\n<example>\nuser: 2 + 2\nassistant: 4\n</example>\n\n<example>\nuser: what is 2+2?\nassistant: 4\n</example>\n\n<example>\nuser: is 11 a prime number?\nassistant: Yes\n</example>\n\n<example>\nuser: what command should I run to list files in the current directory?\nassistant: ls\n</example>\n\n<example>\nuser: what command should I run to watch files in the current directory?\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\nnpm run dev\n</example>\n\n<example>\nuser: How many golf balls fit inside a jetta?\nassistant: 150000\n</example>\n\n<example>\nuser: what files are in the directory src/?\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\nuser: which file contains the implementation of foo?\nassistant: src/foo.c\n</example>\n\n<example>\nuser: write tests for new feature\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\n</example>\n\n# Proactiveness\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\n1. Doing the right thing when asked, including taking actions and follow-up actions\n2. Not surprising the user with actions you take without asking\nFor example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\n3. Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\n\n# Following conventions\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Code style\n- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked\n\n# Doing tasks\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\n- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.\n- Implement the solution using all tools available to you\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\n- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to AGENTS.md so that you will know to run it next time.\nNEVER 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\n- Tool results and 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.\n\n# Tool usage policy\n- When doing file search, prefer to use the Task tool in order to reduce context usage.\n- You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run \"git status\" and \"git diff\", send a single message with two tool calls to run the calls in parallel.\n\nYou MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\n\n# Code References\n\nWhen referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.\n\n<example>\nuser: Where are errors from the client handled?\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.ts:712.\n</example>\n\n", "Here is some useful information about the environment you are running in:\n<env>\n Working directory: /home/asmae-elazrak\n Is directory a git repo: no\n Platform: linux\n Today's date: Sun Oct 26 2025\n</env>\n<project>\n \n</project>" ], "parentID": "msg_a21950f4b0012gfFA09gQMrXfW", "modelID": "kimi-k2-instruct", "providerID": "cortecs", "mode": "build", "path": { "cwd": "/home/asmae-elazrak", "root": "/" }, "cost": 0.00538218, "tokens": { "input": 9720, "output": 10, "reasoning": 0, "cache": { "read": 0, "write": 0 } } }, "msg_a2195fb1a001eW0gGxvTDdC6HC": { "parts": [ { "id": "prt_a2195fb1a002hdpcJCH2ktX50B", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a2195fb1a001eW0gGxvTDdC6HC", "type": "text", "text": "Creat a python file to calculate prime numbers < 100", "synthetic": false, "time": { "start": 0, "end": 0 } } ], "id": "msg_a2195fb1a001eW0gGxvTDdC6HC", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "role": "user", "time": { "created": 1761500068637 }, "summary": { "diffs": [] } }, "msg_a2195fb82001cUXT0hQCC2bhXI": { "parts": [ { "id": "prt_a219600e4001pO7iXlLQIySX0w", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a2195fb82001cUXT0hQCC2bhXI", "type": "step-start" }, { "id": "prt_a219601dc001EV6NlOBJT3WjWq", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a2195fb82001cUXT0hQCC2bhXI", "type": "tool", "callID": "functions.write:0", "tool": "write", "state": { "status": "completed", "input": { "filePath": "/home/asmae-elazrak/primes.py", "content": "def is_prime(n):\n if n < 2:\n return False\n for i in range(2, int(n ** 0.5) + 1):\n if n % i == 0:\n return False\n return True\n\nprimes = [n for n in range(2, 100) if is_prime(n)]\nprint(f\"Prime numbers less than 100: {primes}\")\nprint(f\"Count: {len(primes)}\")" }, "output": "", "title": "home/asmae-elazrak/primes.py", "metadata": { "diagnostics": { "/home/asmae-elazrak/primes.py": [] }, "filepath": "/home/asmae-elazrak/primes.py", "exists": false }, "time": { "start": 1761500072983, "end": 1761500077058 } } }, { "id": "prt_a21961c09001E3UqXHjyQrNBZb", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a2195fb82001cUXT0hQCC2bhXI", "type": "step-finish", "reason": "tool-calls", "cost": 0.005736296, "tokens": { "input": 9748, "output": 138, "reasoning": 0, "cache": { "read": 0, "write": 0 } } } ], "id": "msg_a2195fb82001cUXT0hQCC2bhXI", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "role": "assistant", "time": { "created": 1761500068738, "completed": 1761500077088 }, "system": [ "You are opencode, an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\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- /help: Get help with using opencode\n- To give feedback, users should report the issue at https://github.com/sst/opencode/issues\n\nWhen the user directly asks about opencode (eg 'can opencode do...', 'does opencode have...') or asks in second person (eg 'are you able...', 'can you do...'), first use the WebFetch tool to gather information to answer the question from opencode docs at https://opencode.ai\n\n# Tone and style\nYou should be concise, direct, and to the point. When you run a non-trivial bash command, you should explain what the command does and why you are running it, to make sure the user understands what you are doing (this is especially important when you are running a command that will make changes to the user's system).\nRemember that your output will be displayed on a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\nOutput text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.\nIf you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.\nOnly use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.\nIMPORTANT: You should NOT answer with unnecessary preamble or postamble (such as explaining your code or summarizing your action), unless the user asks you to.\nIMPORTANT: Keep your responses short, since they will be displayed on a command line interface. You MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail. Answer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text before/after your response, such as \"The answer is <answer>.\", \"Here is the content of the file...\" or \"Based on the information provided, the answer is...\" or \"Here is what I will do next...\". Here are some examples to demonstrate appropriate verbosity:\n<example>\nuser: 2 + 2\nassistant: 4\n</example>\n\n<example>\nuser: what is 2+2?\nassistant: 4\n</example>\n\n<example>\nuser: is 11 a prime number?\nassistant: Yes\n</example>\n\n<example>\nuser: what command should I run to list files in the current directory?\nassistant: ls\n</example>\n\n<example>\nuser: what command should I run to watch files in the current directory?\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\nnpm run dev\n</example>\n\n<example>\nuser: How many golf balls fit inside a jetta?\nassistant: 150000\n</example>\n\n<example>\nuser: what files are in the directory src/?\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\nuser: which file contains the implementation of foo?\nassistant: src/foo.c\n</example>\n\n<example>\nuser: write tests for new feature\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\n</example>\n\n# Proactiveness\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\n1. Doing the right thing when asked, including taking actions and follow-up actions\n2. Not surprising the user with actions you take without asking\nFor example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\n3. Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\n\n# Following conventions\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Code style\n- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked\n\n# Doing tasks\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\n- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.\n- Implement the solution using all tools available to you\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\n- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to AGENTS.md so that you will know to run it next time.\nNEVER 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\n- Tool results and 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.\n\n# Tool usage policy\n- When doing file search, prefer to use the Task tool in order to reduce context usage.\n- You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run \"git status\" and \"git diff\", send a single message with two tool calls to run the calls in parallel.\n\nYou MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\n\n# Code References\n\nWhen referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.\n\n<example>\nuser: Where are errors from the client handled?\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.ts:712.\n</example>\n\n", "Here is some useful information about the environment you are running in:\n<env>\n Working directory: /home/asmae-elazrak\n Is directory a git repo: no\n Platform: linux\n Today's date: Sun Oct 26 2025\n</env>\n<project>\n \n</project>" ], "parentID": "msg_a2195fb1a001eW0gGxvTDdC6HC", "modelID": "kimi-k2-instruct", "providerID": "cortecs", "mode": "build", "path": { "cwd": "/home/asmae-elazrak", "root": "/" }, "cost": 0.005736296, "tokens": { "input": 9748, "output": 138, "reasoning": 0, "cache": { "read": 0, "write": 0 } } }, "msg_a21961c340017jF1p6mXM8I446": { "parts": [ { "id": "prt_a21961f2d001Ec9dVvZreeFxzj", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a21961c340017jF1p6mXM8I446", "type": "step-start" }, { "id": "prt_a21961f990010VBK0W0eSQmHqD", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a21961c340017jF1p6mXM8I446", "type": "tool", "callID": "functions.write:0", "tool": "write", "state": { "status": "completed", "input": { "filePath": "/home/asmae-elazrak/primes.py", "content": "def is_prime(n):\n if n < 2:\n return False\n for i in range(2, int(n ** 0.5) + 1):\n if n % i == 0:\n return False\n return True\n\nprimes = [n for n in range(2, 100) if is_prime(n)]\nprint(f\"Prime numbers less than 100: {primes}\")\nprint(f\"Count: {len(primes)}\")" }, "output": "", "title": "home/asmae-elazrak/primes.py", "metadata": { "diagnostics": { "/home/asmae-elazrak/primes.py": [] }, "filepath": "/home/asmae-elazrak/primes.py", "exists": true }, "time": { "start": 1761500080339, "end": 1761500080810 } } }, { "id": "prt_a21962aad001J7nLjJQbNbcGhx", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a21961c340017jF1p6mXM8I446", "type": "step-finish", "reason": "tool-calls", "cost": 0.005740704, "tokens": { "input": 9756, "output": 138, "reasoning": 0, "cache": { "read": 0, "write": 0 } } } ], "id": "msg_a21961c340017jF1p6mXM8I446", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "role": "assistant", "time": { "created": 1761500077108, "completed": 1761500080833 }, "system": [ "You are opencode, an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\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- /help: Get help with using opencode\n- To give feedback, users should report the issue at https://github.com/sst/opencode/issues\n\nWhen the user directly asks about opencode (eg 'can opencode do...', 'does opencode have...') or asks in second person (eg 'are you able...', 'can you do...'), first use the WebFetch tool to gather information to answer the question from opencode docs at https://opencode.ai\n\n# Tone and style\nYou should be concise, direct, and to the point. When you run a non-trivial bash command, you should explain what the command does and why you are running it, to make sure the user understands what you are doing (this is especially important when you are running a command that will make changes to the user's system).\nRemember that your output will be displayed on a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\nOutput text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.\nIf you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.\nOnly use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.\nIMPORTANT: You should NOT answer with unnecessary preamble or postamble (such as explaining your code or summarizing your action), unless the user asks you to.\nIMPORTANT: Keep your responses short, since they will be displayed on a command line interface. You MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail. Answer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text before/after your response, such as \"The answer is <answer>.\", \"Here is the content of the file...\" or \"Based on the information provided, the answer is...\" or \"Here is what I will do next...\". Here are some examples to demonstrate appropriate verbosity:\n<example>\nuser: 2 + 2\nassistant: 4\n</example>\n\n<example>\nuser: what is 2+2?\nassistant: 4\n</example>\n\n<example>\nuser: is 11 a prime number?\nassistant: Yes\n</example>\n\n<example>\nuser: what command should I run to list files in the current directory?\nassistant: ls\n</example>\n\n<example>\nuser: what command should I run to watch files in the current directory?\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\nnpm run dev\n</example>\n\n<example>\nuser: How many golf balls fit inside a jetta?\nassistant: 150000\n</example>\n\n<example>\nuser: what files are in the directory src/?\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\nuser: which file contains the implementation of foo?\nassistant: src/foo.c\n</example>\n\n<example>\nuser: write tests for new feature\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\n</example>\n\n# Proactiveness\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\n1. Doing the right thing when asked, including taking actions and follow-up actions\n2. Not surprising the user with actions you take without asking\nFor example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\n3. Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\n\n# Following conventions\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Code style\n- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked\n\n# Doing tasks\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\n- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.\n- Implement the solution using all tools available to you\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\n- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to AGENTS.md so that you will know to run it next time.\nNEVER 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\n- Tool results and 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.\n\n# Tool usage policy\n- When doing file search, prefer to use the Task tool in order to reduce context usage.\n- You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run \"git status\" and \"git diff\", send a single message with two tool calls to run the calls in parallel.\n\nYou MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\n\n# Code References\n\nWhen referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.\n\n<example>\nuser: Where are errors from the client handled?\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.ts:712.\n</example>\n\n", "Here is some useful information about the environment you are running in:\n<env>\n Working directory: /home/asmae-elazrak\n Is directory a git repo: no\n Platform: linux\n Today's date: Sun Oct 26 2025\n</env>\n<project>\n \n</project>" ], "parentID": "msg_a2195fb1a001eW0gGxvTDdC6HC", "modelID": "kimi-k2-instruct", "providerID": "cortecs", "mode": "build", "path": { "cwd": "/home/asmae-elazrak", "root": "/" }, "cost": 0.005740704, "tokens": { "input": 9756, "output": 138, "reasoning": 0, "cache": { "read": 0, "write": 0 } } }, "msg_a21962ae2001Q9hQQ7nIpLqDwo": { "parts": [ { "id": "prt_a21962e01001uBfRYSLOfs2q5X", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a21962ae2001Q9hQQ7nIpLqDwo", "type": "step-start" }, { "id": "prt_a21962e03001RxJDyi1nI5hjWY", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a21962ae2001Q9hQQ7nIpLqDwo", "type": "text", "text": "Created `primes.py` with a function to calculate all prime numbers less than 100.", "time": { "start": 1761500082007, "end": 1761500082007 } }, { "id": "prt_a21962f580019P7edkwd2P3Nr0", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "messageID": "msg_a21962ae2001Q9hQQ7nIpLqDwo", "type": "step-finish", "reason": "stop", "cost": 0.005432884, "tokens": { "input": 9764, "output": 20, "reasoning": 0, "cache": { "read": 0, "write": 0 } } } ], "id": "msg_a21962ae2001Q9hQQ7nIpLqDwo", "sessionID": "ses_5de6af0bdffefjog7L1XV4twn9", "role": "assistant", "time": { "created": 1761500080866, "completed": 1761500082035 }, "system": [ "You are opencode, an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\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- /help: Get help with using opencode\n- To give feedback, users should report the issue at https://github.com/sst/opencode/issues\n\nWhen the user directly asks about opencode (eg 'can opencode do...', 'does opencode have...') or asks in second person (eg 'are you able...', 'can you do...'), first use the WebFetch tool to gather information to answer the question from opencode docs at https://opencode.ai\n\n# Tone and style\nYou should be concise, direct, and to the point. When you run a non-trivial bash command, you should explain what the command does and why you are running it, to make sure the user understands what you are doing (this is especially important when you are running a command that will make changes to the user's system).\nRemember that your output will be displayed on a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\nOutput text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.\nIf you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.\nOnly use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.\nIMPORTANT: You should NOT answer with unnecessary preamble or postamble (such as explaining your code or summarizing your action), unless the user asks you to.\nIMPORTANT: Keep your responses short, since they will be displayed on a command line interface. You MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail. Answer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text before/after your response, such as \"The answer is <answer>.\", \"Here is the content of the file...\" or \"Based on the information provided, the answer is...\" or \"Here is what I will do next...\". Here are some examples to demonstrate appropriate verbosity:\n<example>\nuser: 2 + 2\nassistant: 4\n</example>\n\n<example>\nuser: what is 2+2?\nassistant: 4\n</example>\n\n<example>\nuser: is 11 a prime number?\nassistant: Yes\n</example>\n\n<example>\nuser: what command should I run to list files in the current directory?\nassistant: ls\n</example>\n\n<example>\nuser: what command should I run to watch files in the current directory?\nassistant: [use the ls tool to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\nnpm run dev\n</example>\n\n<example>\nuser: How many golf balls fit inside a jetta?\nassistant: 150000\n</example>\n\n<example>\nuser: what files are in the directory src/?\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\nuser: which file contains the implementation of foo?\nassistant: src/foo.c\n</example>\n\n<example>\nuser: write tests for new feature\nassistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]\n</example>\n\n# Proactiveness\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\n1. Doing the right thing when asked, including taking actions and follow-up actions\n2. Not surprising the user with actions you take without asking\nFor example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\n3. Do not add additional code explanation summary unless requested by the user. After working on a file, just stop, rather than providing an explanation of what you did.\n\n# Following conventions\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Code style\n- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked\n\n# Doing tasks\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\n- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.\n- Implement the solution using all tools available to you\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\n- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to AGENTS.md so that you will know to run it next time.\nNEVER 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\n- Tool results and 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.\n\n# Tool usage policy\n- When doing file search, prefer to use the Task tool in order to reduce context usage.\n- You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run \"git status\" and \"git diff\", send a single message with two tool calls to run the calls in parallel.\n\nYou MUST answer concisely with fewer than 4 lines of text (not including tool use or code generation), unless user asks for detail.\n\nIMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse.\nIMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).\n\n# Code References\n\nWhen referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.\n\n<example>\nuser: Where are errors from the client handled?\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.ts:712.\n</example>\n\n", "Here is some useful information about the environment you are running in:\n<env>\n Working directory: /home/asmae-elazrak\n Is directory a git repo: no\n Platform: linux\n Today's date: Sun Oct 26 2025\n</env>\n<project>\n \n</project>" ], "parentID": "msg_a2195fb1a001eW0gGxvTDdC6HC", "modelID": "kimi-k2-instruct", "providerID": "cortecs", "mode": "build", "path": { "cwd": "/home/asmae-elazrak", "root": "/" }, "cost": 0.005432884, "tokens": { "input": 9764, "output": 20, "reasoning": 0, "cache": { "read": 0, "write": 0 } } } } } ```

yindo commented 2026-02-16 17:34:59 -05:00

Author

Owner

Copy Link

Copy Source

@LePao1 commented on GitHub (Oct 28, 2025):

@ASMAE20 If possible, please use the official Moonshot K2 API (e.g., kimi-k2-turbo-preview ,the high-speed K2 release that is both extremely fast and near 100 % accurate on tool-calling) instead of third-party open-source K2 inference endpoints. Some providers deploy quantized versions or impose their own technical constraints that can drastically degrade model performance. If you must use one of these external APIs, consult Moonshot’s official guidance: https://github.com/MoonshotAI/K2-Vendor-Verifier.

@LePao1 commented on GitHub (Oct 28, 2025): @ASMAE20 If possible, please use the official Moonshot K2 API (e.g., kimi-k2-turbo-preview ,the high-speed K2 release that is both extremely fast and near 100 % accurate on tool-calling) instead of third-party open-source K2 inference endpoints. Some providers deploy quantized versions or impose their own technical constraints that can drastically degrade model performance. If you must use one of these external APIs, consult Moonshot’s official guidance: https://github.com/MoonshotAI/K2-Vendor-Verifier.

yindo referenced this issue 2026-02-16 18:14:52 -05:00

[PR #2284] chore: add star history to README #10255

Sign in to join this conversation.

No Branch/Tag Specified

Branches Tags

dev

simplify-token-rows

text-phase-state

v2

beta

ling-free-docs

meta-placeholders

app-state

discovery-compat

pty-compat

review-data

session-requests

session-timeline

desktop-v2-compat

ai-msg-phases

mistral-reasoning

raw-finish-reasons

project-metadata

session-archival

vcs-branch-metadata

pty-connect-tokens

command-sources

server-location-paths

canonical-tool-output

v2-theme-registry

openai-text-phase

tooltip-delay

service-test-timeout

patch-error-messages

figma-plugin

production

snapshot-repository

codemode-catalog-diffs

base-ui-theme

nxl-acp-delete

nxl-acp-lifecycle

css-design-system

nxl-acp-v1

nxl-acp-sdk

nxl-acp-elicitation

alibaba-images

item-reference-investigation

wsl-shell-env

wsl-env-load

stream-eof-finish

nvidia-minimax-thinking

pr-38231-assets

pr-38224-assets

model-flicker

default-background

terminal-queries

event-batching

port-plugins

gemini-thinking-level

patch-symlink-policy

session-version-sentinel

client-service

service-channel-config

webfetch-images

search-integration

billing-details

shell-exit-grace

desktop-image-backgrounds

copilot-endpoint

bound-tool-output

workspace-model-block

remove-promo

collapse-model-providers

review-sidebar-hydration

collapse-questions

location-startup-timing

remove-output-paths

shell-output-preview

quark-timeline

raw-tool-recovery

dialog-hover-fix

server-profiles

server-switcher

kimi-mfjs-schema

session-options-hook

interleaved-fields

remote-workspaces-plan

fix-initial-message

undo-git-guard

pr-37575-assets

opentui-binary-repro

startup-lock-release

system-theme-v2

llm-error-types

tui-plugin-load

external-defaults

productionclear

pr-37513-assets

console-auth-refresh

v2-app-api

backend-adapter-v2

oc-clipboard-and-paste

test/hot-reload-regressions

provider-benchmark

shell-progress-tail

model-cycle-palette

theme-toggle-copy

flaky-provider-tests

permission-modal-keyboard

shell-output-alignment

session-http-hook

permission-highlight

activity-panel

workspace-copy

interrupt-not-found

device-org-select

v2-subagent-limit

vertex-xai-default

reasoning-replay

agent-picker-custom

effect-dynamic-tools

patch-empty-hang

fix/empty-assistant-output

favorites-cli-config

simulated-tools

console-analytics-logger

simulation-terminal-frame-capture

feature-defaults

free-model-logo

service-restart

interrupt-stop-race

xai-oauth

background-indicator-inline

home-shortcut-align

compaction-model-marker

provider-config-shape

interface-toggle

install-layout-eligibility

tools-menu

mcp-location-refresh

session-picker-crash

optimistic-submit

dialog-action-focus

llm-terminal-contract

llm-remove-provider-error

remove-subtle-syntax

title-small-model

dialog-empty-states

permission-panel

api-dsl-cleanup

app-backend-v2

free-model-badge

compaction-percent

thought-toggle

home-session-scroll

llm-error-redesign

luna-oauth-fix

tool-flat-draft

v2-shell-utf8

remove-starptech

effort-values-none

config-dialog

update-tsgo

bounded-compaction-prod

stale-form-submit

dismiss-stale-form

bounded-compaction

agent-picker-variants

config-dir-repro

shell-tail-output

v2-integrations

quick-undo

startup-error-cause

subagent-panel-ui

lazy-fff

optimistic-input

zsh-positional

v2-diff-route

plugin-session-rename

gpt56-max

shortcut-screenshots

service-status

context-overflow

random-tool-catalog

review-nav-spacing

architecture-review

duplicate-event-logs

fix-shell-tab

v2-agent-env

plugin-watch-fix

compaction-cleanup

fix-compaction

genai-observability

agent-permission-order

tui-pending

catalog-repros

catalog-cold-start

console-login-logs

fix/tui-fresh-session-prompt

review-terminal

model-reset-repro

reasoning-variants

improve-caching

team-members

promise-chaining

tabs-launch-screenshots

compaction-steer

agent-env-markers

daemon-election

retry-layout

bash-streaming-fix

bash-tool-crash

restore-session-paging

provider-entrypoints

model-input-defaults

fix-initial-message-page-size

background-return

model-capability-defaults

runner-scenario-dsl

location-watch-guard

fix-shell-count

session-model-sync

new-session-commands

interrupt-tool-hang

codemode-service

mcp-attachments

stdlib-gaps

codemode-object-delete

json-callbacks

code-mode-opencode

drive-manifest

firecrawl-search

persisted-suspense

mcp-resource-app

mcp-resource-ui

mcp-resource-api

media-attachment

instruction-rename

destructuring-assign

codemode-audit

schema-reexports

event-subscribe

nxl/vcs-plugin-api

global-forms

revert-prompt

fix-stale-tools

service-version-guard

partial-refund-ledger

sdk-js-imports

jlongster/simulation-improvements

promise-named-types

tool-output

execute-code-mode-v2

compaction-indicator

subagent-command

catalog-readiness

pending-tool-error

zen-body-limit

form-tui

step-settlement

settlement-ledger

provider-packages

elicitation-timeout

codemode-opencode-adapter

optimize-hooks

models-log-leak

zen-accounting-latency

form-elicitation

codemode-opencode-wiring

codemode-opencode-integration

models-refresh-daemon

v2-model-refresh

filesystem-simulation

context-checkpoint

system-context

subagent-notify

subagent-resume

simulation-spec-v2

directory-attachment-expansion

zen-headers-timeout

config-effect-v2

embedded-config-seam

config-ownership

shell-background-notice

compaction-idle-status

session-tab-remount

publish-server

directory-attachments

content-filter-notice

settings-model-clipping

home-autocomplete-location

tabs-restore

plugin-runtime-bridge

simulation-spec

optimistic-prompt

reasoning-model-api

tool-result-api

beta-badge

prompt-submit-clear

prompt-attachments

mcp-prompts

background-shortcut

debug-windows-opentui-standalone-repro-release

fix-empty-sessions-list

core-node-consumers

model-selection

snapshot-otui

pty-env-route

status-frame-fix

daxbox-servers

shell-output-flush

shell-tool-test

auth-list

remove-default-layers

jlongster/opencode-all-tests-more

native-provider-clean

context-tooltip-v2

native-provider-core

native-provider-stack

deferred-tools

delete-email-action

poll-updates

jlongster/test-batch

session-forking

plugin-patterns

anthropic-thinking-variants

merge-dev-into-v2

fix-windows-abbreviate-home

project-edit-update

streaming-prd

zen-refund-accounting

fish-completion

cache-code-highlights

review-session-pane

sdk-generation-dev-check

clean-desktop-deps

clean-http-recorder-deps

clean-opencode-deps

clean-session-ui-deps

clean-stats-app-deps

clean-ui-deps

clean-web-deps

clean-app-deps

clean-cli-deps

clean-console-app-deps

clean-console-core-deps

clean-console-function-deps

clean-console-mail-deps

clean-console-support-deps

clean-core-deps

clean-root-deps

tui-child-picker

core-project-relocation

complete-client

open-auth-url

desktop-relocated

child-session-picker

fix-event-type

typecheck-28263387070

refresh-singleflight

jlongster/location-nodes

home-active-indicator

session-step-interrupted

interrupt-loading

fix/tui-preserve-renderer-error

fix/provider-session-failures

frank-production-validation-20260626

embedded-live-tail

fix/openai-stateless-reasoning-continuation

session-event-stream

responses-stream-retry

mcp-core-skeleton

server-auto-approve

opentui-retry

timeline-scroll-state

protocol-events

published-events

native-provider-config

native-provider-packages

oc-1.17.10-hotfix

new-session-model

tab-custom-color

feat/tui-render-state-dump

fix/tui-palette-question-mode

otui-native-yoga

feature/expand-paste-summary

todo-dock-motion

mcp-search-tool

tab-shrink

session-provider-errors

isolate-oauth-headers

verify-mcp-auth

secure-oauth-api

mcp-reconnect

restrict-mcp-env

redact-config-secrets

atomic-oauth-callback

native-provider-schema

add-model-comparison-pages

question-paste

simplify-target-layouts

fix-mention-mime

tagged-error-lint

websocket-auth

headless-console-login

mobile-utility-ui

ios-pwa-shell

mobile-bottom-nav

mobile-session-layout

mobile-home-layout

plugin-internal

fix/v2-queue-after-terminal-failure

http-recorder-release

custom-image-defaults

consolidate-todo-event

normalize-step-event-versions

fix-session-subpath

simplify/v2-runner-transitions

run-core-tests

feat/v2-terminal-run-failures-dev

filesystem-errors

hide-read-arguments

layer-node-permit

layer-node-projector

layer-node-repocache

layer-node-sprompt

layer-node-projcopy

layer-node-location

layer-node-movesess

layer-node-locfs

layer-node-models

layer-node-locmut

layer-node-instruct

layer-node-cconfig

layer-node-watcher

layer-node-fmutation

layer-node-integrate

layer-node-cevent

layer-node-cspawn

layer-node-cagent

layer-node-cproject

layer-node-command

yolo-flag

layer-node-extdir

layer-node-cprocess

layer-node-cgit

layer-node-cripgrep

layer-node-csearch

figma-mcp-client

stabilize-ci-tests

core-tests-ci

project-copy-migration

mcp-prompt-refresh

mcp-oauth-refresh

workerd

share-listener-runtime

v2-global-nodes

server-node-graph

mcp-resource-content

fix/command-double-file

background-model-refresh

jlongster/project-copy-config

demo/pr-31617-session-location

feat/tui-copy-session-location

reasoning-options

reasoning-options-support

fix/opencode-bundle-fff

refactor/mcp-connection-results

refactor/reference-directory-parts

feat/mcp-resource-updated

fix/mcp-prompts-list-changed

feat/mcp-resource-list-changed

docs-go-pricing-explanation

refactor/tui-http-sdk

fix/v2-read-validation-failure

refactor/v2-session-run-coordinator

refactor/core-provider-turn

feat/v2-terminal-run-failures

fix/v2-session-wake-retry-dev

feat/core-v2-background-agent

fix/http-recorder-release

fix/v2-session-wake-retry

fix/bash-tool-settlement

fix/v2-headless-permission-policy

fix/v2-binary-detection

fix/v2-read-images

fix/v2-read-errors

feat/core-v2-overflow-recovery

feat/jsonl-log-file

feat/core-v2-session-context-epoch

fix-bedrock-1

fix/session-metadata-migration-repair

pr-30929-demo-video

nexxeln-copy-git-worktree-path

fix/tui-worker-rpc-errors

refactor/core-v2-message-identity

fix/core-v2-sequence-index-invariants

refactor/core-account-file-agents

feat/core-command-registry

fix/tui-rpc-errors

fix/openai-codex-route-timeouts

fix/openai-websocket-header-timeout

refactor/remove-aisdk-option-fields

dustin/improve-memory-usage

feat/sdk-oagen-effect-emitter

nxl/consolidate-project-references

fix/prompt-loop-shutdown

feat/stripe-lake-ingest

kit/tui-scenario-frames

test/core-location-filesystem-canonical-paths

fix/zen-provider-sse-errors

dustin/clickable-titles

fix/free-tier-limit-cta

fix-model-selection

kit/pr-30051-screenshots

fix/xai-provider-upstream-pdf-support

chore/opencode-ai-provider-updates

feat/mcp-add-inline-args

refactor/provider-inline-local-helpers

fix/tui-syntax-builtins

fix/tui-question-keybindings

nxl/session-status-parent-id

feat/core-config-service

fix/free-model-sort

jlongster/workspace-v2

server-discovery

nxl/tui-message-keyboard-nav

fix-github-links-and-star

kit/tui-pending-tool-spinner

fix/task-running-continuation-feedback

fix-leader-none

fix/google-vertex-anthropic-auth-message

worktree-fork-toast

feat/request-aware-provider-fetch

fix/session-project-migration-time

kit/tui-optimistic-prompt-render

issue-13770-tool-output-docs

fix/google-vertex-metadata-warning

brendan/fix-e2e

question-endpoint

test/config-effect-dsl

fix-native-llm-options

compaction-adjustments

fix/app-v2-channel-gate

feat/core-database-schema-sync

fix/mcp-oauth-scope-and-callback-port

dustin/fix-structured-output-fields

kit/repro-zod-schema-leak

worktree-dead-exports

worktree-dead-files

nxl/fix-permission-specificity

jlongster/diff-viewer

nxl/v2-deferred-prompt

fix-retries

nxl/compaction-args

dustin/tool-choice-capability-support

cooper/opencode-codex-refresh-dedupe

refactor/native-runtime-prepared-request

storage-v2-service

drop-app-runtime-instance

worktree-test-port-audit

worktree-cli-effect-harness-2

worktree-cli-prewarm

refactor/session-prompt-parts

image-paths

test/config-instance-opencode-files

fix-env-json-parse-guards

test/config-instance-save-update

extract-part-text-helper

test/config-instance-template-loads

test/config-instance-first-slice

test/config-instance-agent-command

test/provider-instance-custom-models

test/provider-instance-model-lookup

worktree-global-bus-unify

test/provider-instance-first-slice

oc-issue-question-stuck

oc-snapshot-subdir

nxl/fix-auto-compaction-progress

fix/edit-project-dialog

brendan/message-timeline-scroll-virtualiser

jlongster/simulation-rebase

thdxr/auth-well-known-service

models-dev-global-snapshot

tui-markdown-h3-muted

debug-windows-opentui-bun-1.3.14

debug-windows-opentui-crash

serve-socket-mode

fix-event-sync

kit/delete-instance-local-context

upgrade-otui-0212

snapshot-npm-native-binary-install

emdash/27458-h7lu6

session-next-delta-events

new-colors

fix/event-stream-context-capture

fix/event-stream-context-27391

effect/session-transport-service

effect/config-paths-service

adjust-perm-array-logic

nxl/remove-http-notfound-fallback

nxl/render-config-json-diagnostics

nxl/render-tagged-config-errors

effect-test-permission-next

fix/desktop-session-status-tui-20260513090340

opencode/storage-engine-repository

effect/define-service-helper

disable-image-resizing-default

effect/util-process-effect-returning

effect-test-plugin-auth-override

effect/kill-tuiconfig-installation-facades

effect/unwrap-run-runtime-facades

effect-test-project-project

jlongster/fuzz-backend

fix-aws-issue

llm-native-inject-client

llm-native-runtime-openai

llm-native-prepare-tests

llm-native-request-adapter

llm-native-event-adapter

effect-test-provider-cluster1

brendan/lazy-init-plugins

kit/drop-project-sandboxes

claude/learn-new-skill-Ji0dn

fix/windows-instance-fixture-cleanup

worktree-draft+llm-usage-additive

styled-skill-errors

cleanup/effectify-remaining-compaction-tests

draft/session-timeline-rewind

worktree-http-recorder-cassette-seam

claude/review-recent-issues-Ck5UO

opencode/happy-cabin

cleanup/localize-id-prefixes

cleanup/openapi-workspace-path-pattern

llm-service-event-seam

kit/config-field-tolerant

kit/migrate-drift-tests-into-exerciser

kit/httpapi-exercise-via-sdk

kit/mcp-tolerate-bad-output-schemas

refactor-provider-model-status-schema

fix/httpapi-query-schema-drift

kit/fix-26435-legacy-session-model

kit/plugin-mutation-reproducers

kit/fix-workspace-time-used-migration

kit/revert-26550-fallback

kit/restore-hono-temporary

kit/fix-empty-bad-request-normalization

nxl/reference-file-mentions

fix/composer-image-preview-click

kit/httpapi-project-skill-repro

kit/httpapi-total-coverage

kit/httpapi-auth-cleanup-base

jlongster/workspace-external

fix-reasoning-efforts

fix/session-negative-output-tokens

make-review-normal

nxl/fix-anthropic-provider-tools

brendan/desktop-electron-refactor

fix/workspace-warp-typecheck

jlongster/warp

nxl/background-subagents

kit/pty-no-auth-parity

thdxr/v2-message-model-failures

kit/server-listen-native

kit/httpapi-listener-proxy-ws

kit/typed-session-not-found-sketch

fix-wellknown-down

kit/httpapi-not-found-shape

effect-drizzle-sqlite

question-lifecycle-effect-tests

kit/instance-loader-service

kit/effect-workspace-adapters

docs-sdk

kit/llm-approval-instance-ref

kit/session-llm-instance-state

effect-sync-event-service

jlongster/pin-session

azure-cognitive-improvements

adapter-rename

nxl/runtime-aware-search-service

deflake-test

moonshot-mfjs

nxl/small-model-subagents

brendan/new-composer-design

kit/httpapi-sdk-smoke-test

simon-reject-failure

kit/httpapi-json-shape-parity

kit/fix-httpapi-session-list-main

kit/httpapi-route-parity

fix-deepseek-reasoner

kit/httpapi-experimental-tools

deepseek-anthropic

fix/usage-chart-local-time

fix-shell-test

fix-config-ordering-issue

fix/beta-lazy-assistant-error

fix/session-event-typecheck-ci-shell

kit/httpapi-route-inventory-current

shell-test

simon-thread-network-defaults

fix-hover-selected

kit/schema-native-cleanup-ts

adjust-retry-logic

kit/session-schema-events

kit/config-permission-effect

Cramer/2026-03-25/bare-repo-bug

opencode-remote-voice

core

fix-zen-2

kit/multiedit-schema-fix-ts

kit/fix-release-publish-effect

kit/file-instance-context

kit/lsp-effect-refactor

kit/tui-terminal-notifications

tui-favorite-sort-on-query

openai-compaction

fix-copilot

opencode/swift-nebula

fix/project-worktree-external-directory-default

kit/tui-go-upsell-shimmer

kit/httpapi-workspace-schema-migration

kit/ns-plugin-loader-redo

kit/ns-plugin-loader

kit/ns-file-watcher

kit/repro-write-lsp-hang

kit/collapse-session

kit/collapse-patch

kit/retrofit-plugin-main

kit/retrofit-skill-main

kit/retrofit-permission-main

kit/retrofit-mcp-main

kit/retrofit-config-main

kit/unwrap-plugin-siblings

kit/unwrap-small-standalone

kit/unwrap-mcp-siblings

kit/unwrap-config-siblings

kit/self-reexport-migration-tooling

claude/verify-pr-comment-UuyAZ

claude/debug-e2e-tests-Hkgdb

kit/ns-heap

kit/ns-bus-event

kit/ns-standalone

kit/config-httpapi

kit/ns-file-3

kit/ns-session-3

kit/project-httpapi-reads

kit/ns-session

kit/ns-share

kit/ns-project

kit/ns-util-color

kit/ns-lsp

kit/ns-util-local-context

jlongster/sync-fenc

anthropic-fixes

feat/request-route-spans

kit/fs-search

kit/fs-tui-state

example-tui-plugin

cli-perf/tui-config

kit/fs-cli-io

kit/fs-plugin-npm

kit/llm-facade-cleanup

fix/snapshot-gitignored-index

kit/tui-facade-cleanup

kit/config-providers-httpapi-spike

kit/file-httpapi-spike

kit/workspace-httpapi-reads

nxl/mount-question-server

fix/session-prompt-permission-draft

fix-effect-context-bridges

followup-question-reply-inline

kit/fix-session-prompt-logger-interop

kit/question-httpapi-spike

kit/httpapi-route-inventory

kit/facade-session-prompt

jlongster/wip

nxl/fff-search-service

brendan/effect-env

kit/facade-project-20260413

kit/ripgrep-schema-source

kit/shell-job-service

fix/lsp-dead-root-prune

2.0

foo

facade/config

facade/lsp

facade/file

facade/provider

kit/ai-sdk-motel-bridge

oc-run

kit/e2e-seed-runtime-scope

brendan/electron-window-state

go-hero-banner-glm51-promo

snapshot-node-shim-stuff

fix/tui-session-diff-summary

oc-release-0.1.98

fix/snapshot-gitignore-respect

oc-basecode

worktree-agent-ab6ff98a

layered-deferred-comp

oc-startup

feat/tui-logo-radial-pulse

claude/effect-migration-review-Qyu6m

fix-anthropic-transform

kit/effect-sync-event

kit/effect-workspace

kit/eliminate-message-v2-roundtrips

worktree-agent-ab5855c0

kit/motel-session-telemetry

kit/tool-effect-multiedit

task-spec-executor-split

kit/tool-effect-invalid

worktree-feat+otel-bridge

kit/effect-native-tool-interrupt

jlongster/tui-workspaces-ux

kit/permission-flow-ux

nxl/deflake-webfetch-memory-test

npmcli-config

brendan/node-server-types

pr-21017

app/startup-splash

no-diff-virtualization

opencode/shiny-cactus

nxl/fix-diffs-header-sticky

nxl/shell-mode-tray

message-v3

opencode/gentle-pixel

oc-run-pinned

kit/prompt-abort-cleanup

opencode-suggest

rankings

copilot/research-opencode-server-plugin-api

kit/console-org-switcher

kit/ci-unit-reporting

figma-tokens

copilot/fix-spawn-error-windows

kit/dev-memory-observe

kit/remove-e2e-url-repro

effect-sync-event

effect/summary

pr-18308

worktree-audit-effect-services

test/processor-mock-server

fix/session-tool-metadata

opencode/glowing-tiger

claude/variant-popover-number-keys-gc6Bo

kit/format-child-process-spawner

jlongster/flaky-plugin-test

timeline-spacing-cleanup

feat/fff-search-tools

pr-18335

refactor/server-route-organization

jlongster/remove-workspace-server

kit/zen-stream-diagnostics

worktree-agent-a682f34a

spinner-concepts

openai-websocket

brendan-cli-codesign

brendan/cli-codesign

kit/windows-session-restore

opencode/cosmic-mountain

opencode/quick-orchid

perf/tool-memory

input-cleanup

opencode/sunny-comet

log-worktree-error-details

remove-context-tooltip-from-tab

tui-experimental-design

kit/effectify-command-review

brendan/better-session-id-handling

fix/lazy-facades

fix/insufferable-cycle-cyclone

kit/effectify-worktree

kit/effectify-tool-registry

kit/effectify-plugin

kit/effectify-pty

kit/effectify-command

kit/effectify-session-status

feat/auto-accept-permissions

kit/skill-lazy-init

fix-plugin-provider-behavior

fix/stale-running-session-ui

opencode-2-0

opencode/quiet-pixel

enterprise-lead-tracking

fix-e2e

kit/effect-bus

gitlab-version

add-model-reconciliation

jlongster/effectify-event-route

fix/zen-openai-response-usage

refactor/effect-pattern-migration

no-projects-empty-state

nexxeln/readme-small-tweak

test-branch

refactor/delete-scheduler

fix/shell-tab-shell-mode

effectify-skill

rhys/fast-mode-toggle

fix/flaky-question-dock-e2e

no-project-empty-state

fix/webkit-diff-viewer-crash

repro/watcher-als-bug

kit/repro-interrupted-text

startup

revert-17354-opencode/mighty-garden

move-status

perf/tui-session-history-cursor

effect-auth-foundation

console-subcommands

title-bar-cleanup

effect-log-compat

node-pty

fix/interrupt-idle-reason-poc

fix/interrupt-double-sound

opencode/proud-rocket

jlongster/automatic-session-routing

refactor/node-server-adapter

add-api-shape

node-build

jlongster/revert-sighup

fix/memory-tui-cache-listeners

auto-accept-permissions

pr-16286

default-explore-models

kit-pr

kit-pr-ahhhh

fix/16323-keyed-show-callbacks

feat/hashline-edit-experimental-v2

fix/git-fsmonitor-cleanup

snapshot-spawn-server-logs

implement-background-agents

opencode/happy-planet

fix/subagent-navigation-inline-click

go-page

fix/daytona-plugin-link-15976

opencode/hidden-orchid

tweaks

sidebar-fade-scroll

migrate-enterprise-to-nextjs

migrate-web-to-nextjs

migrate-app-to-nextjs

migrate-console-app-to-nextjs

fix/beta-stack-aware-sync

feature/tui-assistant-tokens-per-second

opencode/misty-falcon

snapshot-node-pty

update-stats

legal-req

commit-history

mhart/fix-cloning-slowness

chore/duplicate-issues-agent-dev

chore/duplicate-issues-agent

migrate-skill-discovery

migrate-mcp

migrate-config

optimize-apply-patch

temp

test-fields

brendan/nsis-vc-redistributables

chore-cleanup

feat/reference-agent

fix/attach-default-cwd

clean-modified-files

feat/discord-bot

v5-v6

feat/fff-file-search

snapshot-windows-desktop

fix-read-tool-for-webfetch

K-Mistele/dev

provider-optional-fields

feature/session-handoff

models-endpoint

opencode/sunny-harbor

utilize-family-in-dialog

review

tui-claude-style

rm-footer

fix/shiki-highlight-engine

fix/plugin-install-config

fix/plugin-install-location

feat/update-to-include-discord

git-slop-v2

docs-export

app/open-button

feature/workspace-domain

redesign-run-command

git-slop

opencode/clever-falcon

ripgrep-tree-paths

adjust-instructions-logic

fix-tool-ordering

workflow/publish-updates

chore-update-deps

feat/turborepo-caching

trigger-publish-on-beta

add-beta-branch-trigger

remove/nix-desktop-workflow

ci

fix-markdown-parsing

remove-highlights-template

update-to-add-learn-script

release-highlights-template

fixing-changelog-spacing

fixing-changelog-ui

fix-changelog-json

changelog-swr-caching

add-dynamic-agents-resolving

release-notes

fix/claude-pro-max-docs-warning

web-fixing-download-buton-on-changelog

fix/google-vertex-anthropic-thinking

sqlite

fix-azure-issue

desktop-poilsh-styles-ui-ux

desktop-shortcuts-panel

scheduler-module

apply-patch

cleanup-server-routes

fix-tool-outputs

fix-ai-message-issue

updated-black-page-performance

fix-black-page-view-transition-safari

update-design-subscriptions

fix-markdown-parser

fix/mcp-timeout

fix-id-issue

upgrade-bun

black-page-transitions-design-updates

official-copilot-plugin

plan-mode

read-plurals

cli-run-improvements

style-new-tips-layout

codex-auth

disable-auto-server

fix-model-dialog

fix-plugin-hook

feat/question-multiselect

new-toolbar-layout

feature/tui-sidebar-overlay

ui-improvements-some-animations

ask-question-tool

truncate-to-file

update-perms

truncation

snaphot-style-multiple-commands-input

experimental-mentions

queue-on-track

add-ignored

rename-repo-sst-to-anomalyco

permission-rework

ripgrep-tests

variants-docs

fix-custom-model-variants

read-global-claude-skills

changelog-updates

thinking-toggle-wip

style-current-todo

tui-shortcuts-panel

update-toggle-and-model-selection

small-screens

feature/skill-tool

feature/agent-skills

add-tests

llm-centralization

interleaved-fixes

interleaved-thinking

docs

sdk

bash-tweaks

provider-cleanup

fix-issue

blacksmith-migration-0ddfdb5

fix/cli-clean-exit-on-model-errors

pr-38252-videos

pr-37967-screenshots-final

pr-37967-screenshots-v2

pr-37967-screenshots

v1.18.4

v1.18.3

v1.18.2

v1.18.1

v1.18.0

v1.17.20

v1.17.19

pr-36567-inline-evidence

pr-36567-evidence

pr-36516-evidence

v1.17.18

v1.17.17

v1.17.16

v1.17.15

v1.17.14

v1.17.13

v1.17.12

v1.17.11

v1.17.10

pr-33649-assets

v1.17.9

v1.17.8

v1.17.7

v1.17.6

v1.17.5

v1.17.4

v1.17.3

v1.17.2

v1.17.1

v1.17.0

v1.16.2

v1.16.0

github-v1.2.25

v1.15.13

pr-29948-screenshots

v1.15.12

github-v1.2.24

github-v1.2.23

v1.15.11

v1.15.10

v1.15.9

v1.15.7

v1.15.6

v1.15.5

v1.15.4

v1.15.3

v1.15.2

v1.15.1

v1.15.0

v1.14.51

v1.14.50

v1.14.49

v1.14.48

v1.14.47

v1.14.46

v1.14.45

v1.14.44

v1.14.43

v1.14.42

v1.14.41

v1.14.40

v1.14.39

v1.14.38

v1.14.37

v1.14.35

v1.14.34

v1.14.33

v1.14.32

v1.14.31

v1.14.30

v1.14.29

v1.14.28

v1.14.27

v1.14.26

v1.14.25

v1.14.24

v1.14.23

v1.14.22

v1.14.21

v1.14.20

v1.14.19

v1.14.18

v1.14.17

v1.4.14

v1.4.12

v1.4.11

v1.4.10

v1.4.9

v1.4.8

v1.4.7

github-v1.2.22

github-v1.2.21

github-v1.2.20

v1.4.6

v1.4.5

v1.4.4

v1.4.3

v1.4.2

v1.4.1

v1.4.0

latest

v1.3.17

v1.3.16

v1.3.15

v1.3.14

v1.3.13

v1.3.12

v1.3.11

v1.3.10

v1.3.9

v1.3.8

v1.3.7

v1.3.6

v1.3.5

v1.3.4

v1.3.3

github-v1.2.19

v1.3.2

v1.3.1

v1.3.0

v1.2.27

v1.2.26

v1.2.25

v1.2.24

v1.2.23

v1.2.22

v1.2.21

v1.2.20

v1.2.19

github-v1.2.18

v1.2.18

v1.2.17

v1.2.16

v1.2.15

v1.2.14

v1.2.13

v1.2.12

v1.2.11

github-v1.2.17

v1.2.10

v1.2.9

v1.2.8

v1.2.7

github-v1.2.16

v1.2.6

v1.2.5

v1.2.4

v1.2.3

v1.2.2

v1.2.1

v1.2.0

v1.1.65

v1.1.64

v1.1.63

v1.1.62

v1.1.61

v1.1.60

v1.1.59

v1.1.58

v1.1.57

v1.1.56

v1.1.55

v1.1.54

github-v1.2.15

v1.1.53

v1.1.52

v1.1.51

v1.1.50

v1.1.49

v1.1.48

v1.1.47

v1.1.46

v1.1.45

v1.1.44

github-v1.2.14

v1.1.43

v0.0.0-ci-202601291718

v0.0.0-ci-202601291635

v0.0.0-ci-202601291626

v1.1.42

v1.1.41

v1.1.40

v1.1.39

v1.1.38

v1.1.37

v1.1.36

v1.1.35

v1.1.34

v1.1.33

v1.1.32

v1.1.31

v1.1.30

v1.1.29

v1.1.28

v1.1.27

v1.1.26

github-v1.2.13

v1.1.25

v1.1.24

v1.1.23

v1.1.21

v1.1.20

v1.1.19

v1.1.18

github-v1.2.12

v1.1.17

v1.1.16

v1.1.15

v1.1.14

v1.1.13

v1.1.12

v1.1.11

v1.1.10

v1.1.8

v1.1.7

v1.1.6

v1.1.5

v1.1.4

v1.1.3

github-v1.2.11

v1.1.2

v1.1.1

github-v1.2.10

github-v1.2.9

github-v1.2.8

github-v1.2.7

v1.0.224

v1.0.223

v1.0.222

v1.0.221

v1.0.220

v1.0.219

v1.0.218

v1.0.217

v1.0.216

v1.0.215

v1.0.214

v1.0.213

v1.0.212

v1.0.211

v1.0.210

v1.0.209

v1.0.208

v1.0.207

v1.0.206

vscode-v0.0.13

v1.0.205

v1.0.204

v1.0.203

v1.0.202

v1.0.201

v1.0.200

v1.0.199

v1.0.198

v1.0.197

v1.0.196

v1.0.195

v1.0.194

v1.0.193

v1.0.192

v1.0.191

v1.0.190

v1.0.189

v1.0.188

v1.0.187

v1.0.186

v1.0.185

github-v1.2.6

v1.0.184

v1.0.183

v1.0.182

v1.0.181

github-v1.2.5

github-v1.2.4

v1.0.180

v1.0.179

v1.0.178

v1.0.177

v1.0.176

v1.0.175

v1.0.174

v1.0.173

v1.0.172

v1.0.171

v1.0.170

v1.0.169

v1.0.168

github-v1.2.3

github-v1.2.2

v1.0.167

v1.0.166

v1.0.165

v1.0.164

github-v1.2.1

v1.0.163

v1.0.162

v1.0.161

v1.0.160

v1.0.159

v1.0.158

v1.0.157

v1.0.156

v1.0.155

v1.0.154

v1.0.153

v1.0.152

v1.0.151

v1.0.150

v1.0.149

v1.0.148

v1.0.147

v1.0.146

v1.0.145

v1.0.144

github-v1.2.0

github-v1.1.0

v1.0.143

v1.0.142

v1.0.141

v1.0.138

v1.0.137

v1.0.134

v1.0.133

v1.0.132

v1.0.131

v1.0.130

v1.0.129

v1.0.128

v1.0.127

v1.0.126

v1.0.125

v1.0.124

v1.0.123

v1.0.122

v1.0.121

v1.0.120

v1.0.119

v1.0.118

v1.0.117

v1.0.116

v1.0.115

v1.0.114

v1.0.113

v1.0.112

v1.0.111

v1.0.110

v1.0.109

v1.0.108

v1.0.107

v1.0.106

v1.0.105

v1.0.104

v1.0.103

v1.0.102

v1.0.101

v1.0.100

v1.0.99

v1.0.98

v1.0.97

v1.0.96

v1.0.95

v1.0.93

v1.0.94

v1.0.92

v1.0.91

v1.0.90

v1.0.89

v1.0.88

v1.0.87

v1.0.86

v1.0.85

v1.0.84

v1.0.83

v1.0.82

v1.0.81

v1.0.80

v1.0.79

v1.0.78

v1.0.77

v1.0.76

v1.0.75

v1.0.74

v1.0.73

v1.0.72

v1.0.71

v1.0.70

v1.0.69

v1.0.68

v1.0.67

v1.0.66

v1.0.65

v1.0.64

v0.0.2-feature-bench

v1.0.63

v0.0.1-feature-bench

v1.0.62

v1.0.61

v1.0.60

v1.0.59

v1.0.58

v1.0.57

v1.0.56

v1.0.55

v1.0.54

v1.0.53

v1.0.52

v1.0.51

v1.0.50

v1.0.49

v1.0.48

v1.0.47

v1.0.46

v1.0.45

v1.0.44

v1.0.43

v1.0.41

v1.0.40

v1.0.39

v1.0.38

v1.0.37

v1.0.36

v1.0.35

v1.0.34

v1.0.33

v1.0.32

v1.0.31

v1.0.30

v1.0.29

v1.0.28

v1.0.27

v1.0.26

v1.0.25

v1.0.24

v1.0.23

v1.0.22

v1.0.21

v1.0.20

v1.0.19

v1.0.18

v1.0.17

v1.0.16

v1.0.15

v1.0.14

v1.0.13

v1.0.12

v1.0.11

github-v1.0.10

v1.0.10

v1.0.9

v1.0.8

v1.0.7

v1.0.6

v1.0.5

v1.0.4

v1.0.3

v1.0.2

v1.0.1

v1.0.0

v0.15.31

v0.15.30

v0.15.29

v0.15.28

v0.15.27

v0.15.26

v0.15.25

v0.15.24

v0.15.23

v0.15.21

v0.15.22

v0.15.20

v0.15.19

v0.15.18

v0.15.17

v0.15.16

v0.15.15

v0.15.14

vscode-v0.0.12

vscode-v0.0.11

vscode-v0.0.10

v0.15.13

v0.15.12

v0.15.11

v0.15.10

v0.15.9

v0.15.8

v0.15.7

v0.15.6

github-v1.0.9

github-v1.0.8

github-v1.0.7

v0.15.5

v0.15.4

v0.15.3

v0.15.2

v0.15.1

v0.15.0

v0.14.7

v0.14.6

v0.14.5

v0.14.4

v0.14.3

v0.14.1

v0.14.0

v0.13.9

v0.13.8

v0.13.7

v0.13.6

v0.13.5

v0.13.4

v0.13.3

v0.13.2

v0.12.1

v0.12.0

v0.11.8

v0.11.7

v0.11.6

v0.11.5

v0.11.4

v0.11.3

v0.11.2

v0.11.1

v0.11.0

v0.0.0-202509210757

v0.10.4

v0.10.3

github-v1.0.6

v0.10.2

v0.10.1

v0.10.0

v0.9.11

v0.9.10

v0.9.9

v0.9.8

v0.9.7

v0.9.6

v0.9.5

v0.9.4

v0.9.3

v0.9.2

v0.9.1

v0.9.0

v0.8.0

v0.0.0-202509130959

v0.0.0-202509130953

v0.0.0-202509130949

v0.7.9

v0.7.8

v0.7.7

v0.7.6

v0.7.5

v0.7.4

v0.7.3

v0.7.2

v0.7.1

v0.7.0

v0.6.10

v0.6.9

v0.6.8

v0.6.7

v0.6.6

v0.6.5

v0.6.4

v0.6.3

v0.6.2

v0.6.1

v0.6.0

v0.0.0-202509010531

v0.0.0-202509010020

v0.5.29

v0.5.28

v0.5.27

v0.5.26

v0.5.25

v0.5.24

v0.5.23

v0.5.18

v0.5.15

v0.5.13

v0.5.12

v0.5.11

v0.5.10

v0.5.9

v0.5.8

v0.5.7

v0.5.6

github-v1.0.5

v0.5.5

v0.5.4

v0.5.3

v0.5.2

v0.5.1

v0.4.45

v0.4.44

v0.4.43

v0.4.42

v0.4.41

v0.4.40

v0.4.37

v0.4.36

v0.4.34

v0.4.29

v0.4.28

v0.4.27

v0.4.26

v0.4.25

v0.4.24

v0.4.23

v0.4.22

v0.4.21

v0.4.20

v0.4.19

v0.4.18

v0.4.17

v0.4.16

v0.4.15

v0.4.14

v0.4.13

v0.4.12

v0.4.11

v0.4.10

v0.4.6

v0.4.4

v0.4.5

v0.4.3

v0.4.2

v0.4.1

v0.4.0

v0.3.133

v0.3.132

v0.3.131

v0.3.130

v0.3.129

v0.3.128

v0.3.127

v0.3.126

v0.3.124

v0.3.123

v0.0.0-202508031658

v0.0.0-202508031655

v0.0.0-202508031652

v0.0.0-202508031649

v0.0.0-202508031638

v0.0.0-202508031634

v0.0.0-202508031629

v0.3.122

v0.3.121

v0.3.120

v0.3.119

v0.3.118

v0.3.117

v0.3.116

v0.3.115

v0.3.114

v0.0.0-202508022246

v0.0.0-202508022229

v0.0.0-202508022228

v0.0.0-202508022056

v0.0.0-202508022055

v0.0.0-202508022053

v0.3.113

v0.3.112

v0.3.111

v0.3.110

v0.3.109

v0.3.108

v0.3.107

v0.3.106

v0.3.105

v0.3.104

v0.3.103

vscode-v0.0.8

vscode-v0.0.9

v0.3.102

v0.3.101

v0.3.100

v0.3.93

v0.3.92

v0.3.90

v0.3.88

v0.0.0-202507310417

v0.3.87

v0.3.86

v0.3.85

v0.3.84

v0.3.83

v0.3.82

v0.3.81

v0.3.80

vscode-v0.0.7

v0.3.79

v0.3.78

v0.3.77

v0.3.76

v0.3.75

github-v1.0.4

github-v1.0.3

v0.3.74

v0.3.72

v0.3.73

v0.3.71

v0.3.70

v0.3.69

v0.3.68

v0.3.67

v0.3.66

v0.3.65

v0.3.64

v0.3.63

v0.3.62

v0.3.61

v0.3.60

v0.3.59

v0.3.58

v0.3.57

v0.3.56

vscode-v0.0.6

v0.3.55

vscode-v0.0.5

v0.3.54

v0.3.53

v0.3.52

v0.3.51

v0.3.50

v0.3.49

v0.3.48

v0.3.47

v0.3.46

v0.3.45

v0.3.44

vscode-v0.0.4

github-v1

vscode-v0.0.3

github-v1.0.2

github-v1.0.1

github-v1.0.0

vscode-v0.0.2

v0.3.43

v0.3.41

v0.3.42

v0.3.40

v0.3.39

v0.3.38

v0.3.37

v0.3.36

v0.3.35

v0.3.34

v0.3.33

v0.3.32

v0.3.31

v0.3.30

v0.3.29

v0.3.28

v0.3.27

v0.3.26

v0.3.25

v0.3.24

v0.3.23

v0.3.22

v0.3.21

v0.3.20

v0.3.19

vscode-v0.0.1

v0.3.18

v0.3.17

v0.3.16

v0.3.15

v0.3.14

v0.3.13

v0.3.12

v0.3.10

v0.3.11

v0.3.9

v0.3.8

v0.3.7

v0.3.5

v0.3.6

v0.3.4

v0.3.3

v0.3.2

v0.3.1

v0.2.35

v0.3.0

v0.2.34

v0.2.33

v0.2.31

v0.2.32

v0.2.30

v0.2.28

v0.2.29

v0.2.27

v0.2.26

v0.2.25

v0.2.24

v0.2.23

v0.2.22

v0.2.21

v0.2.20

v0.2.19

v0.2.18

v0.2.17

v0.2.16

v0.2.15

v0.2.14

v0.2.13

v0.2.12

v0.2.11

v0.2.10

v0.2.9

v0.2.7

v0.2.8

v0.2.6

v0.2.5

v0.2.4

v0.2.3

v0.2.2

v0.2.1

v0.2.0

v0.1.195

v0.1.196

v0.1.194

v0.1.193

v0.1.192

v0.1.190

v0.1.191

v0.1.189

v0.1.188

v0.1.187

v0.1.186

v0.1.185

v0.1.184

v0.1.183

v0.1.182

v0.1.181

v0.1.180

v0.1.179

v0.1.178

v0.1.177

v0.1.176

v0.1.175

v0.1.174

v0.1.173

v0.1.172

v0.1.171

v0.1.170

v0.1.169

v0.1.168

v0.1.167

v0.1.166

v0.1.165

v0.1.164

v0.1.163

v0.1.162

v0.1.161

v0.1.160

v0.1.159

v0.1.158

v0.1.157

v0.1.156

v0.1.155

v0.1.154

v0.1.153

v0.1.152

v0.1.151

v0.1.150

v0.1.149

v0.1.148

v0.1.147

v0.1.146

v0.1.145

v0.1.144

v0.1.143

v0.1.142

v0.1.141

v0.1.140

v0.1.139

v0.1.138

v0.1.137

v0.1.136

v0.1.135

v0.1.133

v0.1.134

v0.1.132

v0.1.131

v0.1.130

v0.1.129

v0.1.128

v0.1.127

v0.1.126

v0.1.125

v0.1.124

v0.1.123

v0.1.122

v0.1.121

v0.1.120

v0.1.119

v0.1.118

v0.1.117

v0.1.116

v0.1.115

v0.1.114

v0.1.113

v0.1.112

v0.1.111

v0.1.110

v0.1.109

v0.1.108

v0.1.107

v0.1.106

v0.1.105

v0.1.104

v0.1.103

v0.1.101

v0.1.102

v0.1.100

v0.1.99

v0.1.98

v0.1.97

v0.1.96

v0.1.95

v0.1.94

v0.1.93

v0.1.92

v0.1.91

v0.1.90

v0.1.89

v0.1.88

v0.1.87

v0.1.86

v0.1.85

v0.1.84

v0.1.83

v0.1.82

v0.1.81

v0.1.80

v0.1.79

v0.1.78

v0.1.77

v0.1.76

v0.1.75

v0.1.74

v0.1.73

v0.1.72

v0.1.71

v0.1.70

v0.1.69

v0.1.68

v0.1.67

v0.1.66

v0.1.65

v0.1.64

v0.1.63

v0.1.62

v0.1.61

v0.1.60

v0.1.59

v0.1.58

v0.1.57

v0.1.56

v0.1.55

v0.1.54

v0.1.53

v0.1.52

v0.1.51

v0.1.50

v0.1.49

v0.1.48

v0.1.47

v0.1.46

v0.1.45

v0.1.44

v0.1.43

v0.1.42

v0.1.41

v0.1.40

v0.1.39

v0.1.38

v0.1.37

v0.1.36

v0.1.35

v0.1.34

v0.1.33

v0.1.32

v0.1.31

v0.1.30

v0.1.29

v0.1.28

v0.1.27

v0.1.26

v0.1.24

v0.1.25

v0.1.23

v0.1.22

v0.1.21

v0.1.20

v0.1.19

v0.1.18

v0.1.17

v0.1.16

v0.1.15

v0.1.14

v0.1.13

v0.1.12

v0.1.11

v0.1.10

v0.1.9

v0.1.6

v0.1.7

v0.1.8

v0.1.5

v0.1.4

v0.1.3

v0.1.2

v0.1.1

v0.1.0-beta3

v0.1.0-beta2

v0.1.0-beta1

v0.1.0

v0.0.55

v0.0.54

v0.0.53

v0.0.52

v0.0.51

v0.0.50

v0.0.49

v0.0.48

v0.0.46

v0.0.45

v0.0.47

0.0.47

0.0.46

0.0.45

v0.0.44

v0.0.43

v0.0.42

v0.0.41

v0.0.40

v0.0.39

v0.0.38

v0.0.37

v0.0.36

v0.0.35

v0.0.34

v0.0.33

v0.0.32

v0.0.31

v0.0.30

v0.0.29

v0.0.28

v0.0.27

v0.0.26

v0.0.25

v0.0.24

v0.0.22

v0.0.21

v0.0.20

v0.0.19

v0.0.18

v0.0.17

v0.0.16

v0.0.15

v0.0.14

v0.0.13

v0.0.10

v0.0.9

v0.0.8

v0.0.7

v0.0.6

v0.0.3

v0.0.4

v0.0.5

v0.0.2

v0.0.1

Labels

Clear labels

acp

bad

bug

discussion

docs

documentation

enhancement

extension

good first issue

growth

help-wanted

mcp

model-problem

needs:compliance

nix

opentui

perf

pull-request

Mirrored from GitHub Pull Request

tui

web

windows

zen

No Label bug

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

yindo

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: anomalyco/opencode#2284