anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 02:05:26 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

system message in 'assistant'? #1967

New Issue
Closed
opened 2026-02-16 17:33:28 -05:00 by yindo · 5 comments
yindo commented 2026-02-16 17:33:28 -05:00
Owner
Copy Link
Copy Source

Originally created by @patrafter1999 on GitHub (Oct 6, 2025).

Originally assigned to: @rekram1-node on GitHub.

Hi Folks,

Great job to pull this project together. I like the TUI a lot. Just quick questions out of curiosity.

I've found json files that look like containing system message in ~/.local/share/opencode/storage/message/. See below.

My questions:

  1. If these system messages are logged for each assistant's turn in a multi-turn conversation, why do you log multiple times? It's a system message after all.
  2. Does this mean, this message gets inserted for each model generation? If so, that would be a waste of tokens, wouldn't it?
  3. I use custom provider. But the custom provider name is not properly set here ("providerID": "myprovider")
{
  "id": "msg_9b80955a0001hRmBR088KNM6F4",
  "role": "assistant",
  "system": [
    "You are 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: 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\n# Tone and style\nYou should be concise, direct, and to the point.\nYou should be concise, direct, and to the point, while providing complete information and matching the level of detail you provide in your response with the level of complexity of the user's query or the work you have completed.\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.\nDo 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.\nAnswer 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>\nWhen 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: Keep your responses short, since they will be displayed on a command line interface.\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:\n- Doing the right thing when asked, including taking actions and follow-up actions\n- 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.\n\n# Professional objectivity\nPrioritize technical accuracy and truthfulness over validating the user's beliefs. Focus on facts and problem-solving, providing direct, objective technical info without any unnecessary superlatives, praise, or emotional validation. It is best for the user if Claude honestly applies the same rigorous standards to all ideas and disagrees when necessary, even if it may not be what the user wants to hear. Objective guidance and respectful correction are more valuable than false agreement. Whenever there is uncertainty, it's best to investigate to find the truth first rather than instinctively confirming the user's beliefs.\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\n# Task Management\nYou have access to the TodoWrite tools to help you manage and plan tasks. Use these tools VERY frequently to ensure that you are tracking your tasks and giving the user visibility into your progress.\nThese tools are also EXTREMELY helpful for planning tasks, and for breaking down larger complex tasks into smaller steps. If you do not use this tool when planning, you may forget to do important tasks - and that is unacceptable.\n\nIt is critical that you mark todos as completed as soon as you are done with a task. Do not batch up multiple tasks before marking them as completed.\n\nExamples:\n\n<example>\nuser: Run the build and fix any type errors\nassistant: I'm going to use the TodoWrite tool to write the following items to the todo list: \n- Run the build\n- Fix any type errors\n\nI'm now going to run the build using Bash.\n\nLooks like I found 10 type errors. I'm going to use the TodoWrite tool to write 10 items to the todo list.\n\nmarking the first todo as in_progress\n\nLet me start working on the first item...\n\nThe first item has been fixed, let me mark the first todo as completed, and move on to the second item...\n..\n..\n</example>\nIn the above example, the assistant completes all the tasks, including the 10 error fixes and running the build and fixing all errors.\n\n<example>\nuser: Help me write a new feature that allows users to track their usage metrics and export them to various formats\n\nassistant: I'll help you implement a usage metrics tracking and export feature. Let me first use the TodoWrite tool to plan this task.\nAdding the following todos to the todo list:\n1. Research existing metrics tracking in the codebase\n2. Design the metrics collection system\n3. Implement core metrics tracking functionality\n4. Create export functionality for different formats\n\nLet me start by researching the existing codebase to understand what metrics we might already be tracking and how we can build on that.\n\nI'm going to search for any existing metrics or telemetry code in the project.\n\nI've found some existing telemetry code. Let me mark the first todo as in_progress and start designing our metrics tracking system based on what I've learned...\n\n[Assistant continues implementing the feature step by step, marking todos as in_progress and completed as they go]\n</example>\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 TodoWrite tool to plan the task if required\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 CLAUDE.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 should proactively use the Task tool with specialized agents when the task at hand matches the agent's description.\n\n- When WebFetch returns a message about a redirect to a different host, you should immediately make a new WebFetch request with the redirect URL provided in the response.\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\nIMPORTANT: Always use the TodoWrite tool to plan and track tasks throughout the conversation.\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",
    "Here is some useful information about the environment you are running in:\n<env>\n  Working directory: /Users/jsmith/Downloads/opencode-dev\n  Is directory a git repo: no\n  Platform: darwin\n  Today's date: Mon Oct 06 2025\n</env>\n<project>\n  \n</project>\n## IMPORTANT\n\n- Try to keep things in one function unless composable or reusable\n- DO NOT do unnecessary destructuring of variables\n- DO NOT use `else` statements unless necessary\n- DO NOT use `try`/`catch` if it can be avoided\n- AVOID `try`/`catch` where possible\n- AVOID `else` statements\n- AVOID using `any` type\n- AVOID `let` statements\n- PREFER single word variable names where possible\n- Use as many bun apis as possible like Bun.file()\n\n## Debugging\n\n- To test opencode in the `packages/opencode` directory you can run `bun dev`\n\n## Tool Calling\n\n- ALWAYS USE PARALLEL TOOLS WHEN APPLICABLE. Here is an example illustrating how to execute 3 parallel file reads in this chat environnement:\n\njson\n{\n    \"recipient_name\": \"multi_tool_use.parallel\",\n    \"parameters\": {\n        \"tool_uses\": [\n            {\n                \"recipient_name\": \"functions.read\",\n                \"parameters\": {\n                    \"filePath\": \"path/to/file.tsx\"\n                }\n            },\n            {\n                \"recipient_name\": \"functions.read\",\n                \"parameters\": {\n                    \"filePath\": \"path/to/file.ts\"\n                }\n            },\n            {\n                \"recipient_name\": \"functions.read\",\n                \"parameters\": {\n                    \"filePath\": \"path/to/file.md\"\n                }\n            }\n        ]\n    }\n}\n"
  ],
  "mode": "build",
  "path": {
    "cwd": "/Users/<user_profile>/Downloads/opencode-dev",
    "root": "/"
  },
  "cost": 0,
  "tokens": {
    "input": 15184,
    "output": 139,
    "reasoning": 0,
    "cache": {
      "write": 0,
      "read": 0
    }
  },
  "modelID": "claude-4.5-sonnet",
  "providerID": "myprovider",
  "time": {
    "created": 1759729243552,
    "completed": 1759729267463
  },
  "sessionID": "ses_647f9aed3ffeaRSMs3mFIqKzvS"
}
Originally created by @patrafter1999 on GitHub (Oct 6, 2025). Originally assigned to: @rekram1-node on GitHub. Hi Folks, Great job to pull this project together. I like the TUI a lot. Just quick questions out of curiosity. I've found json files that look like containing system message in ~/.local/share/opencode/storage/message/. See below. My questions: 1. If these system messages are logged for each assistant's turn in a multi-turn conversation, why do you log multiple times? It's a system message after all. 2. Does this mean, this message gets inserted for each model generation? If so, that would be a waste of tokens, wouldn't it? 3. I use custom provider. But the custom provider name is not properly set here ("providerID": "myprovider") ``` { "id": "msg_9b80955a0001hRmBR088KNM6F4", "role": "assistant", "system": [ "You are 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: 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\n# Tone and style\nYou should be concise, direct, and to the point.\nYou should be concise, direct, and to the point, while providing complete information and matching the level of detail you provide in your response with the level of complexity of the user's query or the work you have completed.\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.\nDo 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.\nAnswer 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>\nWhen 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: Keep your responses short, since they will be displayed on a command line interface.\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:\n- Doing the right thing when asked, including taking actions and follow-up actions\n- 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.\n\n# Professional objectivity\nPrioritize technical accuracy and truthfulness over validating the user's beliefs. Focus on facts and problem-solving, providing direct, objective technical info without any unnecessary superlatives, praise, or emotional validation. It is best for the user if Claude honestly applies the same rigorous standards to all ideas and disagrees when necessary, even if it may not be what the user wants to hear. Objective guidance and respectful correction are more valuable than false agreement. Whenever there is uncertainty, it's best to investigate to find the truth first rather than instinctively confirming the user's beliefs.\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\n# Task Management\nYou have access to the TodoWrite tools to help you manage and plan tasks. Use these tools VERY frequently to ensure that you are tracking your tasks and giving the user visibility into your progress.\nThese tools are also EXTREMELY helpful for planning tasks, and for breaking down larger complex tasks into smaller steps. If you do not use this tool when planning, you may forget to do important tasks - and that is unacceptable.\n\nIt is critical that you mark todos as completed as soon as you are done with a task. Do not batch up multiple tasks before marking them as completed.\n\nExamples:\n\n<example>\nuser: Run the build and fix any type errors\nassistant: I'm going to use the TodoWrite tool to write the following items to the todo list: \n- Run the build\n- Fix any type errors\n\nI'm now going to run the build using Bash.\n\nLooks like I found 10 type errors. I'm going to use the TodoWrite tool to write 10 items to the todo list.\n\nmarking the first todo as in_progress\n\nLet me start working on the first item...\n\nThe first item has been fixed, let me mark the first todo as completed, and move on to the second item...\n..\n..\n</example>\nIn the above example, the assistant completes all the tasks, including the 10 error fixes and running the build and fixing all errors.\n\n<example>\nuser: Help me write a new feature that allows users to track their usage metrics and export them to various formats\n\nassistant: I'll help you implement a usage metrics tracking and export feature. Let me first use the TodoWrite tool to plan this task.\nAdding the following todos to the todo list:\n1. Research existing metrics tracking in the codebase\n2. Design the metrics collection system\n3. Implement core metrics tracking functionality\n4. Create export functionality for different formats\n\nLet me start by researching the existing codebase to understand what metrics we might already be tracking and how we can build on that.\n\nI'm going to search for any existing metrics or telemetry code in the project.\n\nI've found some existing telemetry code. Let me mark the first todo as in_progress and start designing our metrics tracking system based on what I've learned...\n\n[Assistant continues implementing the feature step by step, marking todos as in_progress and completed as they go]\n</example>\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 TodoWrite tool to plan the task if required\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 CLAUDE.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 should proactively use the Task tool with specialized agents when the task at hand matches the agent's description.\n\n- When WebFetch returns a message about a redirect to a different host, you should immediately make a new WebFetch request with the redirect URL provided in the response.\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\nIMPORTANT: Always use the TodoWrite tool to plan and track tasks throughout the conversation.\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", "Here is some useful information about the environment you are running in:\n<env>\n Working directory: /Users/jsmith/Downloads/opencode-dev\n Is directory a git repo: no\n Platform: darwin\n Today's date: Mon Oct 06 2025\n</env>\n<project>\n \n</project>\n## IMPORTANT\n\n- Try to keep things in one function unless composable or reusable\n- DO NOT do unnecessary destructuring of variables\n- DO NOT use `else` statements unless necessary\n- DO NOT use `try`/`catch` if it can be avoided\n- AVOID `try`/`catch` where possible\n- AVOID `else` statements\n- AVOID using `any` type\n- AVOID `let` statements\n- PREFER single word variable names where possible\n- Use as many bun apis as possible like Bun.file()\n\n## Debugging\n\n- To test opencode in the `packages/opencode` directory you can run `bun dev`\n\n## Tool Calling\n\n- ALWAYS USE PARALLEL TOOLS WHEN APPLICABLE. Here is an example illustrating how to execute 3 parallel file reads in this chat environnement:\n\njson\n{\n \"recipient_name\": \"multi_tool_use.parallel\",\n \"parameters\": {\n \"tool_uses\": [\n {\n \"recipient_name\": \"functions.read\",\n \"parameters\": {\n \"filePath\": \"path/to/file.tsx\"\n }\n },\n {\n \"recipient_name\": \"functions.read\",\n \"parameters\": {\n \"filePath\": \"path/to/file.ts\"\n }\n },\n {\n \"recipient_name\": \"functions.read\",\n \"parameters\": {\n \"filePath\": \"path/to/file.md\"\n }\n }\n ]\n }\n}\n" ], "mode": "build", "path": { "cwd": "/Users/<user_profile>/Downloads/opencode-dev", "root": "/" }, "cost": 0, "tokens": { "input": 15184, "output": 139, "reasoning": 0, "cache": { "write": 0, "read": 0 } }, "modelID": "claude-4.5-sonnet", "providerID": "myprovider", "time": { "created": 1759729243552, "completed": 1759729267463 }, "sessionID": "ses_647f9aed3ffeaRSMs3mFIqKzvS" } ```
yindo closed this issue 2026-02-16 17:33:29 -05:00
yindo commented 2026-02-16 17:33:29 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Oct 6, 2025):

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

  • #2666: [Question] detailed per-interaction telemetry (token counts and input composition) for opencode-model communications - discusses similar concerns about detailed telemetry and token usage logging
  • #254: Ridiculously big usage of input tokens for simple tasks - related to concerns about excessive token usage
  • #971: Model options are not forwarded for openai-compatible providers unless provider.name option is given - addresses custom provider configuration issues similar to your point about provider name not being set properly

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

@github-actions[bot] commented on GitHub (Oct 6, 2025): This issue might be a duplicate of existing issues. Please check: - #2666: [Question] detailed per-interaction telemetry (token counts and input composition) for opencode-model communications - discusses similar concerns about detailed telemetry and token usage logging - #254: Ridiculously big usage of input tokens for simple tasks - related to concerns about excessive token usage - #971: Model options are not forwarded for openai-compatible providers unless provider.name option is given - addresses custom provider configuration issues similar to your point about provider name not being set properly Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 17:33:29 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 6, 2025):

@patrafter1999 for every chat message the system message is only being sent 1 time, we aren't duplicating it over and over.

What is the name of your provider?

Can you do:

opencode debug config and show me the output

@rekram1-node commented on GitHub (Oct 6, 2025): @patrafter1999 for every chat message the system message is only being sent 1 time, we aren't duplicating it over and over. What is the name of your provider? Can you do: `opencode debug config` and show me the output
yindo commented 2026-02-16 17:33:29 -05:00
Author
Owner
Copy Link
Copy Source

@patrafter1999 commented on GitHub (Oct 6, 2025):

I am using my custom provider which I named. Looking at opencode debug config output, I suppose I need to change "myprovider" to the name I chose.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "myprovider": {
      "name": "spark-provider",
      "npm": "@ai-sdk/openai-compatible",
      "models": {
        "deepseek-r1": {
          "name": "deepseek-r1"
        },
        "gpt-4.1": {
          "name": "gpt-4.1"
        },
        "gpt-4.1-mini": {
          "name": "gpt-4.1-mini"
        },
        "gpt-5-chat": {
          "name": "gpt-5-chat"
        },
        "gpt-5-codex": {
          "name": "gpt-5-codex"
        },
        "claude-4-sonnet": {
          "name": "claude-4-sonnet"
        },
        "claude-4.5-sonnet": {
          "name": "claude-4.5-sonnet"
        }
      },
      "options": {
        "apiKey": "<my_api_key>",
        "baseURL": "<my_endpoint>"
      }
    }
  },
  "agent": {
    "git-committer": {
      "prompt": "You commit and push to git\n\nCommit messages should be brief since they are used to generate release notes.\n\nMessages should say WHY the change was made and not WHAT was changed.",
      "description": "Use this agent when you are asked to commit and push code changes to a git repository.",
      "mode": "subagent",
      "name": "git-committer"
    },
    "docs": {
      "prompt": "You are an expert technical documentation writer\n\nYou are not verbose\n\nThe title of the page should be a word or a 2-3 word phrase\n\nThe description should be one short line, should not start with \"The\", should\navoid repeating the title of the page, should be 5-10 words long\n\nChunks of text should not be more than 2 sentences long\n\nEach section is spearated by a divider of 3 dashes\n\nThe section titles are short with only the first letter of the word capitalized\n\nThe section titles are in the imperative mood\n\nThe section titles should not repeat the term used in the page title, for\nexample, if the page title is \"Models\", avoid using a section title like \"Add\nnew models\". This might be unavoidable in some cases, but try to avoid it.\n\nCheck out the /packages/web/src/content/docs/docs/index.mdx as an example.\n\nFor JS or TS code snippets remove trailing semicolons and any trailing commas\nthat might not be needed.\n\nIf you are making a commit prefix the commit message with `docs:`",
      "description": "ALWAYS use this when writing docs",
      "name": "docs"
    }
  },
  "mode": {},
  "plugin": [],
  "command": {
    "hello": {
      "template": "hey there $ARGUMENTS\n\n!`ls`\ncheck out @README.md",
      "description": "hello world"
    },
    "commit": {
      "template": "commit and push\n\nmake sure it includes a prefix like\ndocs:\ntui:\ncore:\nci:\nignore:\nwip:\n\nprefer to explain WHY something was done from an end user perspective instead of\nWHAT was done."
    }
  },
  "username": "<user>"
}
@patrafter1999 commented on GitHub (Oct 6, 2025): I am using my custom provider which I named. Looking at `opencode debug config` output, I suppose I need to change "myprovider" to the name I chose. ``` { "$schema": "https://opencode.ai/config.json", "provider": { "myprovider": { "name": "spark-provider", "npm": "@ai-sdk/openai-compatible", "models": { "deepseek-r1": { "name": "deepseek-r1" }, "gpt-4.1": { "name": "gpt-4.1" }, "gpt-4.1-mini": { "name": "gpt-4.1-mini" }, "gpt-5-chat": { "name": "gpt-5-chat" }, "gpt-5-codex": { "name": "gpt-5-codex" }, "claude-4-sonnet": { "name": "claude-4-sonnet" }, "claude-4.5-sonnet": { "name": "claude-4.5-sonnet" } }, "options": { "apiKey": "<my_api_key>", "baseURL": "<my_endpoint>" } } }, "agent": { "git-committer": { "prompt": "You commit and push to git\n\nCommit messages should be brief since they are used to generate release notes.\n\nMessages should say WHY the change was made and not WHAT was changed.", "description": "Use this agent when you are asked to commit and push code changes to a git repository.", "mode": "subagent", "name": "git-committer" }, "docs": { "prompt": "You are an expert technical documentation writer\n\nYou are not verbose\n\nThe title of the page should be a word or a 2-3 word phrase\n\nThe description should be one short line, should not start with \"The\", should\navoid repeating the title of the page, should be 5-10 words long\n\nChunks of text should not be more than 2 sentences long\n\nEach section is spearated by a divider of 3 dashes\n\nThe section titles are short with only the first letter of the word capitalized\n\nThe section titles are in the imperative mood\n\nThe section titles should not repeat the term used in the page title, for\nexample, if the page title is \"Models\", avoid using a section title like \"Add\nnew models\". This might be unavoidable in some cases, but try to avoid it.\n\nCheck out the /packages/web/src/content/docs/docs/index.mdx as an example.\n\nFor JS or TS code snippets remove trailing semicolons and any trailing commas\nthat might not be needed.\n\nIf you are making a commit prefix the commit message with `docs:`", "description": "ALWAYS use this when writing docs", "name": "docs" } }, "mode": {}, "plugin": [], "command": { "hello": { "template": "hey there $ARGUMENTS\n\n!`ls`\ncheck out @README.md", "description": "hello world" }, "commit": { "template": "commit and push\n\nmake sure it includes a prefix like\ndocs:\ntui:\ncore:\nci:\nignore:\nwip:\n\nprefer to explain WHY something was done from an end user perspective instead of\nWHAT was done." } }, "username": "<user>" } ```
yindo commented 2026-02-16 17:33:29 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 6, 2025):

yeah @patrafter1999 the key is the provider id, so in this case the id is myprovider

@rekram1-node commented on GitHub (Oct 6, 2025): yeah @patrafter1999 the key is the provider id, so in this case the id is myprovider
yindo commented 2026-02-16 17:33:29 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 6, 2025):

think we resolved this right? ill reopen if not

@rekram1-node commented on GitHub (Oct 6, 2025): think we resolved this right? ill reopen if not
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
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
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#1967
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?