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

Github Actions Bot SOMETIMES failing #1986

New Issue
Closed
opened 2026-02-16 17:33:34 -05:00 by yindo · 5 comments
yindo commented 2026-02-16 17:33:34 -05:00
Owner
Copy Link
Copy Source

Originally created by @notlousybook on GitHub (Oct 7, 2025).

Originally assigned to: @fwang on GitHub.

shows "Unknown Error:" with no error message buttt in logs :

Run sst/opencode/github@latest
Run curl -fsSL https://opencode.ai/install | bash
Downloading opencode version: 0.5.5 ...
#=#=#                                                                          
##O#-#                                                                         

                                                                           0.0%
################                                                          22.4%
####################################                                      50.1%
################################################                          67.3%
######################################################################## 100.0%
Successfully added opencode to $PATH in /home/runner/.bashrc
Added /home/runner/.opencode/bin to $GITHUB_PATH
Run opencode github run
Images []
Configuring git...
AUTHORIZATION: basic ***
Asserting permissions for user LousyBook94...
  permission: admin
Creating comment...
opencode session ses_640df8088ffeF33LaPQzsLboM2
Fetching prompt data for PR...
Checking out local branch...
From https://github.com/LousyBook94/ZtoApi-Deno
 * branch            opencode/issue4-20251007115646 -> FETCH_HEAD
 * [new branch]      opencode/issue4-20251007115646 -> origin/opencode/issue4-20251007115646
Switched to a new branch 'opencode/issue4-20251007115646'
branch 'opencode/issue4-20251007115646' set up to track 'origin/opencode/issue4-20251007115646'.
Sending message to opencode...
{
  id: "msg_9bf209022001RwQiLtY1SV27lk",
  role: "assistant",
  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](https://github.com/sst/opencode/issues/n/nWhen?q=sort%3Aupdated-desc+is%3Aissue+is%3Aopen) 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#](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/runner/work/ZtoApi-Deno/ZtoApi-Deno\n  Is directory a git repo: yes\n  Platform: linux\n  Today's date: Tue Oct 07 2025\n</env>\n<project>\n  .github/\n\tworkflows/\n\t\topencode.yml\nui/\n\tdashboard/\n\t\tdashboard.css\n\t\tdashboard.html\n\t\tdashboard.js\n\tdocs/\n\t\tdocs.css\n\t\tdocs.html\n\t\tdocs.js\n\tindex.css\n\tindex.html\n\tindex.js\nvisual_tester/\n\tcapture.py\nLICENSE\nmain_test.ts\nmain.ts\nREADME.md\nresponse_test.js\nserver.log\nthing.json\nthink_tags_mode_example.md\n</project>"
  ],
  mode: "build",
  path: {
    cwd: "/home/runner/work/ZtoApi-Deno/ZtoApi-Deno",
    root: "/home/runner/work/ZtoApi-Deno/ZtoApi-Deno",
  },
  cost: 0,
  tokens: {
    input: 0,
    output: 0,
    reasoning: 0,
    cache: {
      read: 0,
      write: 0,
    },
  },
  modelID: "zai-org/GLM-4.5-Air",
  providerID: "chutes",
  time: {
    created: 1759848206370,
    completed: 1759848214397,
  },
  sessionID: "ses_640df8088ffeF33LaPQzsLboM2",
  error: {
    name: "UnknownError",
    data: {
      message: "AI_InvalidResponseDataError: Expected 'id' to be a string.",
    },
  },
}
124243 |               }
124244 |             ])
124245 |           ]
124246 |         });
124247 |         if (result.info.error) {
124248 |           throw new Error(`${result.info.error.name}: ${"message" in result.info.error ? result.info.error.message : ""}`);
                         ^
error: UnknownError: 
      at chat (/$bunfs/root/opencode:124248:17)

Updating comment...
Error: UnknownError: 
Error: Process completed with exit code 1.

reference : https://github.com/LousyBook94/ZtoApi-Deno/actions/runs/18316472751/job/52157973387

Originally created by @notlousybook on GitHub (Oct 7, 2025). Originally assigned to: @fwang on GitHub. shows "Unknown Error:" with no error message buttt in logs : ``` Run sst/opencode/github@latest Run curl -fsSL https://opencode.ai/install | bash Downloading opencode version: 0.5.5 ... #=#=# ##O#-# 0.0% ################ 22.4% #################################### 50.1% ################################################ 67.3% ######################################################################## 100.0% Successfully added opencode to $PATH in /home/runner/.bashrc Added /home/runner/.opencode/bin to $GITHUB_PATH Run opencode github run Images [] Configuring git... AUTHORIZATION: basic *** Asserting permissions for user LousyBook94... permission: admin Creating comment... opencode session ses_640df8088ffeF33LaPQzsLboM2 Fetching prompt data for PR... Checking out local branch... From https://github.com/LousyBook94/ZtoApi-Deno * branch opencode/issue4-20251007115646 -> FETCH_HEAD * [new branch] opencode/issue4-20251007115646 -> origin/opencode/issue4-20251007115646 Switched to a new branch 'opencode/issue4-20251007115646' branch 'opencode/issue4-20251007115646' set up to track 'origin/opencode/issue4-20251007115646'. Sending message to opencode... { id: "msg_9bf209022001RwQiLtY1SV27lk", role: "assistant", 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](https://github.com/sst/opencode/issues/n/nWhen?q=sort%3Aupdated-desc+is%3Aissue+is%3Aopen) 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#](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/runner/work/ZtoApi-Deno/ZtoApi-Deno\n Is directory a git repo: yes\n Platform: linux\n Today's date: Tue Oct 07 2025\n</env>\n<project>\n .github/\n\tworkflows/\n\t\topencode.yml\nui/\n\tdashboard/\n\t\tdashboard.css\n\t\tdashboard.html\n\t\tdashboard.js\n\tdocs/\n\t\tdocs.css\n\t\tdocs.html\n\t\tdocs.js\n\tindex.css\n\tindex.html\n\tindex.js\nvisual_tester/\n\tcapture.py\nLICENSE\nmain_test.ts\nmain.ts\nREADME.md\nresponse_test.js\nserver.log\nthing.json\nthink_tags_mode_example.md\n</project>" ], mode: "build", path: { cwd: "/home/runner/work/ZtoApi-Deno/ZtoApi-Deno", root: "/home/runner/work/ZtoApi-Deno/ZtoApi-Deno", }, cost: 0, tokens: { input: 0, output: 0, reasoning: 0, cache: { read: 0, write: 0, }, }, modelID: "zai-org/GLM-4.5-Air", providerID: "chutes", time: { created: 1759848206370, completed: 1759848214397, }, sessionID: "ses_640df8088ffeF33LaPQzsLboM2", error: { name: "UnknownError", data: { message: "AI_InvalidResponseDataError: Expected 'id' to be a string.", }, }, } 124243 | } 124244 | ]) 124245 | ] 124246 | }); 124247 | if (result.info.error) { 124248 | throw new Error(`${result.info.error.name}: ${"message" in result.info.error ? result.info.error.message : ""}`); ^ error: UnknownError: at chat (/$bunfs/root/opencode:124248:17) Updating comment... Error: UnknownError: Error: Process completed with exit code 1. ``` reference : https://github.com/LousyBook94/ZtoApi-Deno/actions/runs/18316472751/job/52157973387
yindo closed this issue 2026-02-16 17:33:34 -05:00
yindo commented 2026-02-16 17:33:35 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Oct 7, 2025):

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

  • #1880: Opencode with GLM 4.5 String issue - This issue reports the exact same error message 'AI_InvalidResponseDataError: Expected "id" to be a string.' when using GLM 4.5 model

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

@github-actions[bot] commented on GitHub (Oct 7, 2025): This issue might be a duplicate of existing issues. Please check: - #1880: Opencode with GLM 4.5 String issue - This issue reports the exact same error message 'AI_InvalidResponseDataError: Expected "id" to be a string.' when using GLM 4.5 model Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 17:33:35 -05:00
Author
Owner
Copy Link
Copy Source

@notlousybook commented on GitHub (Oct 7, 2025):

ohh yeah related 100%

@notlousybook commented on GitHub (Oct 7, 2025): ohh yeah related 100%
yindo commented 2026-02-16 17:33:35 -05:00
Author
Owner
Copy Link
Copy Source

@notlousybook commented on GitHub (Oct 7, 2025):

mine has more info idk

@notlousybook commented on GitHub (Oct 7, 2025): mine has more info idk
yindo commented 2026-02-16 17:33:35 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 7, 2025):

thx for raising we will investigate

@rekram1-node commented on GitHub (Oct 7, 2025): thx for raising we will investigate
yindo commented 2026-02-16 17:33:35 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 20, 2025):

This is a glm issue so I am going to close in favor of #1880

@rekram1-node commented on GitHub (Oct 20, 2025): This is a glm issue so I am going to close in favor of #1880
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#1986
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?