aljaz/opencode
1
0
Fork 0
mirror of https://github.com/aljazceru/opencode.git synced 2025-12-24 03:04:21 +01:00
Code Issues Packages Projects Releases Wiki Activity

tool updates

Browse Source
This commit is contained in:
Dax Raad
2025-06-04 13:12:13 -04:00
parent a890288900
commit d13822d26e
37 changed files with 1066 additions and 702 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
packages/opencode/.gitignore vendored
View File

@@ -1,4 +1,5 @@
node_modules
research
dist
gen
app.log

9
packages/opencode/AGENTS.md
View File

@@ -1,6 +1,7 @@
# OpenCode Agent Guidelines
## Build/Test Commands
- **Install**: `bun install`
- **Run**: `bun run index.ts`
- **Typecheck**: `bun run typecheck` (npm run typecheck)
@@ -8,16 +9,22 @@
- **Single test**: `bun test test/tool/tool.test.ts` (specific test file)
## Code Style
- **Runtime**: Bun with TypeScript ESM modules
- **Imports**: Use relative imports for local modules, named imports preferred
- **Types**: Zod schemas for validation, TypeScript interfaces for structure
- **Naming**: camelCase for variables/functions, PascalCase for classes/namespaces
- **Error handling**: Use Result patterns, avoid throwing exceptions in tools
- **File structure**: Namespace-based organization (e.g., `Tool.define()`, `Session.create()`)
- DO NOT do unnecessary destructuring of variables
- DO NOT use else statements unless necessary
- DO NOT use try catch if it can be avoided
## Architecture
- **Tools**: Implement `Tool.Info` interface with `execute()` method
- **Context**: Pass `sessionID` in tool context, use `App.provide()` for DI
- **Validation**: All inputs validated with Zod schemas
- **Logging**: Use `Log.create({ service: "name" })` pattern
- **Storage**: Use `Storage` namespace for persistence
- **Storage**: Use `Storage` namespace for persistence

1
packages/opencode/src/global/index.ts
View File

@@ -17,6 +17,7 @@ await Promise.all([
export namespace Global {
export const Path = {
data,
bin: path.join(data, "bin"),
cache,
config,
} as const

10
packages/opencode/src/provider/provider.ts
View File

@@ -9,14 +9,14 @@ import { Global } from "../global"
import { BunProc } from "../bun"
import { BashTool } from "../tool/bash"
import { EditTool } from "../tool/edit"
import { FetchTool } from "../tool/fetch"
import { WebFetchTool } from "../tool/webfetch"
import { GlobTool } from "../tool/glob"
import { GrepTool } from "../tool/grep"
import { ListTool } from "../tool/ls"
import { LspDiagnosticTool } from "../tool/lsp-diagnostics"
import { LspHoverTool } from "../tool/lsp-hover"
import { PatchTool } from "../tool/patch"
import { ViewTool } from "../tool/view"
import { ReadTool } from "../tool/read"
import type { Tool } from "../tool/tool"
export namespace Provider {
@@ -165,18 +165,18 @@ export namespace Provider {
const TOOLS = [
BashTool,
EditTool,
FetchTool,
WebFetchTool,
GlobTool,
GrepTool,
ListTool,
LspDiagnosticTool,
LspHoverTool,
PatchTool,
ViewTool,
ReadTool,
EditTool,
]
const TOOL_MAPPING: Record<string, Tool.Info[]> = {
anthropic: TOOLS,
anthropic: TOOLS.filter((t) => t.id !== "opencode.patch"),
openai: TOOLS,
google: TOOLS,
}

82
packages/opencode/src/ripgrep/index.ts Normal file
View File

@@ -0,0 +1,82 @@
import { App } from "../app/app"
import path from "path"
import { Global } from "../global"
import fs from "fs/promises"
export namespace Ripgrep {
const PLATFORM = {
darwin: { platform: "apple-darwin", extension: "tar.gz" },
linux: { platform: "unknown-linux-musl", extension: "tar.gz" },
win32: { platform: "pc-windows-msvc", extension: "zip" },
} as const
const state = App.state("ripgrep", async () => {
const filepath = path.join(
Global.Path.bin,
"rg" + (process.platform === "win32" ? ".exe" : ""),
)
const file = Bun.file(filepath)
if (!(await file.exists())) {
const archMap = { x64: "x86_64", arm64: "aarch64" } as const
const arch = archMap[process.arch as keyof typeof archMap] ?? process.arch
const config = PLATFORM[process.platform as keyof typeof PLATFORM]
if (!config) throw new Error(`Unsupported platform: ${process.platform}`)
const version = "14.1.1"
const filename = `ripgrep-${version}-${arch}-${config.platform}.${config.extension}`
const url = `https://github.com/BurntSushi/ripgrep/releases/download/${version}/${filename}`
const response = await fetch(url)
if (!response.ok)
throw new Error(`Failed to download ripgrep: ${response.statusText}`)
const buffer = await response.arrayBuffer()
const archivePath = path.join(Global.Path.bin, filename)
await Bun.write(archivePath, buffer)
if (config.extension === "tar.gz") {
const proc = Bun.spawn(
[
"tar",
"-xzf",
archivePath,
"--strip-components=1",
"--wildcards",
"*/rg",
],
{
cwd: Global.Path.bin,
stderr: "ignore",
stdout: "ignore",
},
)
await proc.exited
}
if (config.extension === "zip") {
const proc = Bun.spawn(
["unzip", "-j", archivePath, "*/rg.exe", "-d", Global.Path.bin],
{
cwd: Global.Path.bin,
stderr: "ignore",
stdout: "ignore",
},
)
await proc.exited
}
await fs.unlink(archivePath)
if (process.platform !== "win32") await fs.chmod(filepath, 0o755)
}
return {
filepath,
}
})
export async function filepath() {
const { filepath } = await state()
return filepath
}
}

2
packages/opencode/src/session/session.ts
View File

@@ -444,7 +444,7 @@ ${app.git ? await ListTool.execute({ path: app.path.cwd }, { sessionID: input.se
next.parts.push({
type: "tool-invocation",
toolInvocation: {
state: "call",
state: "partial-call",
toolName: value.toolName,
toolCallId: value.toolCallId,
args: {},

158
packages/opencode/src/tool/bash.ts
View File

@@ -1,5 +1,6 @@
import { z } from "zod"
import { Tool } from "./tool"
import DESCRIPTION from "./bash.txt"
const MAX_OUTPUT_LENGTH = 30000
const BANNED_COMMANDS = [
@@ -24,163 +25,23 @@ const BANNED_COMMANDS = [
const DEFAULT_TIMEOUT = 1 * 60 * 1000
const MAX_TIMEOUT = 10 * 60 * 1000
const DESCRIPTION = `Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.
Before executing the command, please follow these steps:
1. Directory Verification:
- If the command will create new directories or files, first use the LS tool to verify the parent directory exists and is the correct location
- For example, before running "mkdir foo/bar", first use LS to check that "foo" exists and is the intended parent directory
2. Security Check:
- For security and to limit the threat of a prompt injection attack, some commands are limited or banned. If you use a disallowed command, you will receive an error message explaining the restriction. Explain the error to the User.
- Verify that the command is not one of the banned commands: ${BANNED_COMMANDS.join(", ")}.
3. Command Execution:
- After ensuring proper quoting, execute the command.
- Capture the output of the command.
4. Output Processing:
- If the output exceeds ${MAX_OUTPUT_LENGTH} characters, output will be truncated before being returned to you.
- Prepare the output for display to the user.
5. Return Result:
- Provide the processed output of the command.
- If any errors occurred during execution, include those in the output.
Usage notes:
- The command argument is required.
- You can specify an optional timeout in milliseconds (up to 600000ms / 10 minutes). If not specified, commands will timeout after 30 minutes.
- VERY IMPORTANT: You MUST avoid using search commands like 'find' and 'grep'. Instead use Grep, Glob, or Agent tools to search. You MUST avoid read tools like 'cat', 'head', 'tail', and 'ls', and use FileRead and LS tools to read files.
- When issuing multiple commands, use the ';' or '&&' operator to separate them. DO NOT use newlines (newlines are ok in quoted strings).
- IMPORTANT: All commands share the same shell session. Shell state (environment variables, virtual environments, current directory, etc.) persist between commands. For example, if you set an environment variable as part of a command, the environment variable will persist for subsequent commands.
- Try to maintain your current working directory throughout the session by using absolute paths and avoiding usage of 'cd'. You may use 'cd' if the User explicitly requests it.
<good-example>
pytest /foo/bar/tests
</good-example>
<bad-example>
cd /foo/bar && pytest tests
</bad-example>
# Committing changes with git
When the user asks you to create a new git commit, follow these steps carefully:
1. Start with a single message that contains exactly three tool_use blocks that do the following (it is VERY IMPORTANT that you send these tool_use blocks in a single message, otherwise it will feel slow to the user!):
- Run a git status command to see all untracked files.
- Run a git diff command to see both staged and unstaged changes that will be committed.
- Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.
2. Use the git context at the start of this conversation to determine which files are relevant to your commit. Add relevant untracked files to the staging area. Do not commit files that were already modified at the start of this conversation, if they are not relevant to your commit.
3. Analyze all staged changes (both previously staged and newly added) and draft a commit message. Wrap your analysis process in <commit_analysis> tags:
<commit_analysis>
- List the files that have been changed or added
- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)
- Brainstorm the purpose or motivation behind these changes
- Do not use tools to explore code, beyond what is available in the git context
- Assess the impact of these changes on the overall project
- Check for any sensitive information that shouldn't be committed
- Draft a concise (1-2 sentences) commit message that focuses on the "why" rather than the "what"
- Ensure your language is clear, concise, and to the point
- Ensure the message accurately reflects the changes and their purpose (i.e. "add" means a wholly new feature, "update" means an enhancement to an existing feature, "fix" means a bug fix, etc.)
- Ensure the message is not generic (avoid words like "Update" or "Fix" without context)
- Review the draft message to ensure it accurately reflects the changes and their purpose
</commit_analysis>
4. Create the commit with a message ending with:
🤖 Generated with opencode
Co-Authored-By: opencode <noreply@opencode.ai>
- In order to ensure good formatting, ALWAYS pass the commit message via a HEREDOC, a la this example:
<example>
git commit -m "$(cat <<'EOF'
Commit message here.
🤖 Generated with opencode
Co-Authored-By: opencode <noreply@opencode.ai>
EOF
)"
</example>
5. If the commit fails due to pre-commit hook changes, retry the commit ONCE to include these automated changes. If it fails again, it usually means a pre-commit hook is preventing the commit. If the commit succeeds but you notice that files were modified by the pre-commit hook, you MUST amend your commit to include them.
6. Finally, run git status to make sure the commit succeeded.
Important notes:
- When possible, combine the "git add" and "git commit" commands into a single "git commit -am" command, to speed things up
- However, be careful not to stage files (e.g. with 'git add .') for commits that aren't part of the change, they may have untracked files they want to keep around, but not commit.
- NEVER update the git config
- DO NOT push to the remote repository
- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.
- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit
- Ensure your commit message is meaningful and concise. It should explain the purpose of the changes, not just describe them.
- Return an empty response - the user will see the git output directly
# Creating pull requests
Use the gh command via the Bash tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a Github URL use the gh command to get the information needed.
IMPORTANT: When the user asks you to create a pull request, follow these steps carefully:
1. Understand the current state of the branch. Remember to send a single message that contains multiple tool_use blocks (it is VERY IMPORTANT that you do this in a single message, otherwise it will feel slow to the user!):
- Run a git status command to see all untracked files.
- Run a git diff command to see both staged and unstaged changes that will be committed.
- Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote
- Run a git log command and 'git diff main...HEAD' to understand the full commit history for the current branch (from the time it diverged from the 'main' branch.)
2. Create new branch if needed
3. Commit changes if needed
4. Push to remote with -u flag if needed
5. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (not just the latest commit, but all commits that will be included in the pull request!), and draft a pull request summary. Wrap your analysis process in <pr_analysis> tags:
<pr_analysis>
- List the commits since diverging from the main branch
- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)
- Brainstorm the purpose or motivation behind these changes
- Assess the impact of these changes on the overall project
- Do not use tools to explore code, beyond what is available in the git context
- Check for any sensitive information that shouldn't be committed
- Draft a concise (1-2 bullet points) pull request summary that focuses on the "why" rather than the "what"
- Ensure the summary accurately reflects all changes since diverging from the main branch
- Ensure your language is clear, concise, and to the point
- Ensure the summary accurately reflects the changes and their purpose (ie. "add" means a wholly new feature, "update" means an enhancement to an existing feature, "fix" means a bug fix, etc.)
- Ensure the summary is not generic (avoid words like "Update" or "Fix" without context)
- Review the draft summary to ensure it accurately reflects the changes and their purpose
</pr_analysis>
6. Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.
<example>
gh pr create --title "the pr title" --body "$(cat <<'EOF'
## Summary
<1-3 bullet points>
## Test plan
[Checklist of TODOs for testing the pull request...]
🤖 Generated with opencode
EOF
)"
</example>
Important:
- Return an empty response - the user will see the gh output directly
- Never update git config`
export const BashTool = Tool.define({
id: "opencode.bash",
description: DESCRIPTION,
parameters: z.object({
command: z.string(),
command: z.string().describe("The command to execute"),
timeout: z
.number()
.min(0)
.max(MAX_TIMEOUT)
.describe("Optional timeout in milliseconds")
.optional(),
.optional()
.describe("Optional timeout in milliseconds"),
description: z
.string()
.describe(
"Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'",
),
}),
async execute(params) {
const timeout = Math.min(params.timeout ?? DEFAULT_TIMEOUT, MAX_TIMEOUT)
@@ -202,6 +63,7 @@ export const BashTool = Tool.define({
metadata: {
stderr,
stdout,
description: params.description,
},
output: stdout.replaceAll(/\x1b\[[0-9;]*m/g, ""),
}

141
packages/opencode/src/tool/bash.txt Normal file
View File

@@ -0,0 +1,141 @@
Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.
Before executing the command, please follow these steps:
1. Directory Verification:
- If the command will create new directories or files, first use the LS tool to verify the parent directory exists and is the correct location
- For example, before running "mkdir foo/bar", first use LS to check that "foo" exists and is the intended parent directory
2. Command Execution:
- Always quote file paths that contain spaces with double quotes (e.g., cd "path with spaces/file.txt")
- Examples of proper quoting:
- cd "/Users/name/My Documents" (correct)
- cd /Users/name/My Documents (incorrect - will fail)
- python "/path/with spaces/script.py" (correct)
- python /path/with spaces/script.py (incorrect - will fail)
- After ensuring proper quoting, execute the command.
- Capture the output of the command.
Usage notes:
- The command argument is required.
- You can specify an optional timeout in milliseconds (up to 600000ms / 10 minutes). If not specified, commands will timeout after 120000ms (2 minutes).
- It is very helpful if you write a clear, concise description of what this command does in 5-10 words.
- If the output exceeds 30000 characters, output will be truncated before being returned to you.
- VERY IMPORTANT: You MUST avoid using search commands like `find` and `grep`. Instead use Grep, Glob, or Task to search. You MUST avoid read tools like `cat`, `head`, `tail`, and `ls`, and use Read and LS to read files.
- If you _still_ need to run `grep`, STOP. ALWAYS USE ripgrep at `rg` (or /usr/bin/rg) first, which all OpenCode users have pre-installed.
- When issuing multiple commands, use the ';' or '&&' operator to separate them. DO NOT use newlines (newlines are ok in quoted strings).
- Try to maintain your current working directory throughout the session by using absolute paths and avoiding usage of `cd`. You may use `cd` if the User explicitly requests it.
<good-example>
pytest /foo/bar/tests
</good-example>
<bad-example>
cd /foo/bar && pytest tests
</bad-example>
# Committing changes with git
When the user asks you to create a new git commit, follow these steps carefully:
1. 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. ALWAYS run the following bash commands in parallel, each using the Bash tool:
- Run a git status command to see all untracked files.
- Run a git diff command to see both staged and unstaged changes that will be committed.
- Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.
2. Analyze all staged changes (both previously staged and newly added) and draft a commit message. Wrap your analysis process in <commit_analysis> tags:
<commit_analysis>
- List the files that have been changed or added
- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)
- Brainstorm the purpose or motivation behind these changes
- Assess the impact of these changes on the overall project
- Check for any sensitive information that shouldn't be committed
- Draft a concise (1-2 sentences) commit message that focuses on the "why" rather than the "what"
- Ensure your language is clear, concise, and to the point
- Ensure the message accurately reflects the changes and their purpose (i.e. "add" means a wholly new feature, "update" means an enhancement to an existing feature, "fix" means a bug fix, etc.)
- Ensure the message is not generic (avoid words like "Update" or "Fix" without context)
- Review the draft message to ensure it accurately reflects the changes and their purpose
</commit_analysis>
3. 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. ALWAYS run the following commands in parallel:
- Add relevant untracked files to the staging area.
- Create the commit with a message ending with:
🤖 Generated with [OpenCode](https://opencode.ai)
Co-Authored-By: OpenCode <noreply@opencode.ai>
- Run git status to make sure the commit succeeded.
4. If the commit fails due to pre-commit hook changes, retry the commit ONCE to include these automated changes. If it fails again, it usually means a pre-commit hook is preventing the commit. If the commit succeeds but you notice that files were modified by the pre-commit hook, you MUST amend your commit to include them.
Important notes:
- Use the git context at the start of this conversation to determine which files are relevant to your commit. Be careful not to stage and commit files (e.g. with `git add .`) that aren't relevant to your commit.
- NEVER update the git config
- DO NOT run additional commands to read or explore code, beyond what is available in the git context
- DO NOT push to the remote repository
- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.
- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit
- Ensure your commit message is meaningful and concise. It should explain the purpose of the changes, not just describe them.
- Return an empty response - the user will see the git output directly
- In order to ensure good formatting, ALWAYS pass the commit message via a HEREDOC, a la this example:
<example>
git commit -m "$(cat <<'EOF'
Commit message here.
🤖 Generated with [OpenCode](https://opencode.ai)
Co-Authored-By: OpenCode <noreply@opencode.ai>
EOF
)"
</example>
# Creating pull requests
Use the gh command via the Bash tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a Github URL use the gh command to get the information needed.
IMPORTANT: When the user asks you to create a pull request, follow these steps carefully:
1. 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. ALWAYS run the following bash commands in parallel using the Bash tool, in order to understand the current state of the branch since it diverged from the main branch:
- Run a git status command to see all untracked files
- Run a git diff command to see both staged and unstaged changes that will be committed
- Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote
- Run a git log command and `git diff main...HEAD` to understand the full commit history for the current branch (from the time it diverged from the `main` branch)
2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request summary. Wrap your analysis process in <pr_analysis> tags:
<pr_analysis>
- List the commits since diverging from the main branch
- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)
- Brainstorm the purpose or motivation behind these changes
- Assess the impact of these changes on the overall project
- Do not use tools to explore code, beyond what is available in the git context
- Check for any sensitive information that shouldn't be committed
- Draft a concise (1-2 bullet points) pull request summary that focuses on the "why" rather than the "what"
- Ensure the summary accurately reflects all changes since diverging from the main branch
- Ensure your language is clear, concise, and to the point
- Ensure the summary accurately reflects the changes and their purpose (ie. "add" means a wholly new feature, "update" means an enhancement to an existing feature, "fix" means a bug fix, etc.)
- Ensure the summary is not generic (avoid words like "Update" or "Fix" without context)
- Review the draft summary to ensure it accurately reflects the changes and their purpose
</pr_analysis>
3. 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. ALWAYS run the following commands in parallel:
- Create new branch if needed
- Push to remote with -u flag if needed
- Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.
<example>
gh pr create --title "the pr title" --body "$(cat <<'EOF'
## Summary
<1-3 bullet points>
## Test plan
[Checklist of TODOs for testing the pull request...]
🤖 Generated with [OpenCode](https://claude.ai/code)
EOF
)"
</example>
Important:
- NEVER update the git config
- Return the PR URL when you're done, so the user can see it
# Other common operations
- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments

117
packages/opencode/src/tool/edit.ts
View File

@@ -5,54 +5,7 @@ import { FileTimes } from "./util/file-times"
import { LSP } from "../lsp"
import { createTwoFilesPatch, diffLines } from "diff"
import { Permission } from "../permission"
const DESCRIPTION = `Edits files by replacing text, creating new files, or deleting content. For moving or renaming files, use the Bash tool with the 'mv' command instead. For larger file edits, use the FileWrite tool to overwrite files.
Before using this tool:
1. Use the FileRead tool to understand the file's contents and context
2. Verify the directory path is correct (only applicable when creating new files):
- Use the LS tool to verify the parent directory exists and is the correct location
To make a file edit, provide the following:
1. file_path: The relative path to the file to modify (must be relative, not absolute)
2. old_string: The text to replace (must be unique within the file, and must match the file contents exactly, including all whitespace and indentation)
3. new_string: The edited text to replace the old_string
Special cases:
- To create a new file: provide file_path and new_string, leave old_string empty
- To delete content: provide file_path and old_string, leave new_string empty
The tool will replace ONE occurrence of old_string with new_string in the specified file.
CRITICAL REQUIREMENTS FOR USING THIS TOOL:
1. UNIQUENESS: The old_string MUST uniquely identify the specific instance you want to change. This means:
- Include AT LEAST 3-5 lines of context BEFORE the change point
- Include AT LEAST 3-5 lines of context AFTER the change point
- Include all whitespace, indentation, and surrounding code exactly as it appears in the file
2. SINGLE INSTANCE: This tool can only change ONE instance at a time. If you need to change multiple instances:
- Make separate calls to this tool for each instance
- Each call must uniquely identify its specific instance using extensive context
3. VERIFICATION: Before using this tool:
- Check how many instances of the target text exist in the file
- If multiple instances exist, gather enough context to uniquely identify each one
- Plan separate tool calls for each instance
WARNING: If you do not follow these requirements:
- The tool will fail if old_string matches multiple locations
- The tool will fail if old_string doesn't match exactly (including whitespace)
- You may change the wrong instance if you don't include enough context
When making edits:
- Ensure the edit results in idiomatic, correct code
- Do not leave the code in a broken state
- Always use relative file paths
Remember: when making multiple file edits in a row to the same file, you should prefer to send all edits in a single message with multiple calls to this tool, rather than multiple messages with a single call each.`
import DESCRIPTION from "./edit.txt"
export const EditTool = Tool.define({
id: "opencode.edit",
@@ -60,24 +13,31 @@ export const EditTool = Tool.define({
parameters: z.object({
filePath: z.string().describe("The absolute path to the file to modify"),
oldString: z.string().describe("The text to replace"),
newString: z.string().describe("The text to replace it with"),
newString: z
.string()
.describe(
"The text to replace it with (must be different from old_string)",
),
replaceAll: z
.boolean()
.default(false)
.describe("Replace all occurences of old_string (default false)"),
}),
async execute(params, ctx) {
if (!params.filePath) {
throw new Error("filePath is required")
}
let filePath = params.filePath
if (!path.isAbsolute(filePath)) {
filePath = path.join(process.cwd(), filePath)
}
const filepath = path.isAbsolute(params.filePath)
? params.filePath
: path.join(process.cwd(), params.filePath)
await Permission.ask({
id: "opencode.edit",
sessionID: ctx.sessionID,
title: "Edit this file: " + filePath,
title: "Edit this file: " + filepath,
metadata: {
filePath,
filePath: filepath,
oldString: params.oldString,
newString: params.newString,
},
@@ -88,23 +48,23 @@ export const EditTool = Tool.define({
await (async () => {
if (params.oldString === "") {
contentNew = params.newString
await Bun.write(filePath, params.newString)
await Bun.write(filepath, params.newString)
return
}
const read = FileTimes.get(ctx.sessionID, filePath)
const read = FileTimes.get(ctx.sessionID, filepath)
if (!read)
throw new Error(
`You must read the file ${filePath} before editing it. Use the View tool first`,
`You must read the file ${filepath} before editing it. Use the View tool first`,
)
const file = Bun.file(filePath)
if (!(await file.exists())) throw new Error(`File ${filePath} not found`)
const file = Bun.file(filepath)
if (!(await file.exists())) throw new Error(`File ${filepath} not found`)
const stats = await file.stat()
if (stats.isDirectory())
throw new Error(`Path is a directory, not a file: ${filePath}`)
throw new Error(`Path is a directory, not a file: ${filepath}`)
if (stats.mtime.getTime() > read.getTime())
throw new Error(
`File ${filePath} has been modified since it was last read.\nLast modification: ${read.toISOString()}\nLast read: ${stats.mtime.toISOString()}\n\nPlease read the file again before modifying it.`,
`File ${filepath} has been modified since it was last read.\nLast modification: ${read.toISOString()}\nLast read: ${stats.mtime.toISOString()}\n\nPlease read the file again before modifying it.`,
)
contentOld = await file.text()
@@ -113,31 +73,38 @@ export const EditTool = Tool.define({
throw new Error(
`oldString not found in file. Make sure it matches exactly, including whitespace and line breaks`,
)
const lastIndex = contentOld.lastIndexOf(params.oldString)
if (index !== lastIndex)
throw new Error(
`oldString appears multiple times in the file. Please provide more context to ensure a unique match`,
)
contentNew =
contentOld.substring(0, index) +
params.newString +
contentOld.substring(index + params.oldString.length)
if (params.replaceAll) {
contentNew = contentOld.replaceAll(params.oldString, params.newString)
}
if (!params.replaceAll) {
const lastIndex = contentOld.lastIndexOf(params.oldString)
if (index !== lastIndex)
throw new Error(
`oldString appears multiple times in the file. Please provide more context to ensure a unique match`,
)
contentNew =
contentOld.substring(0, index) +
params.newString +
contentOld.substring(index + params.oldString.length)
}
await file.write(contentNew)
})()
const changes = diffLines(contentOld, contentNew)
const diff = createTwoFilesPatch(filePath, filePath, contentOld, contentNew)
const diff = createTwoFilesPatch(filepath, filepath, contentOld, contentNew)
FileTimes.read(ctx.sessionID, filePath)
FileTimes.read(ctx.sessionID, filepath)
let output = ""
await LSP.file(filePath)
await LSP.file(filepath)
const diagnostics = await LSP.diagnostics()
for (const [file, issues] of Object.entries(diagnostics)) {
if (issues.length === 0) continue
if (file === filePath) {
if (file === filepath) {
output += `\nThis file has errors, please fix\n<file_diagnostics>\n${issues.map(LSP.Diagnostic.pretty).join("\n")}\n</file_diagnostics>\n`
continue
}

9
packages/opencode/src/tool/edit.txt Normal file
View File

@@ -0,0 +1,9 @@
Performs exact string replacements in files.
Usage:
- You must use your `Read` tool at least once in the conversation before editing. This tool will error if you attempt an edit without reading the file.
- When editing text from Read tool output, ensure you preserve the exact indentation (tabs/spaces) as it appears AFTER the line number prefix. The line number prefix format is: spaces + line number + tab. Everything after that tab is the actual file content to match. Never include any part of the line number prefix in the old_string or new_string.
- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.
- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.
- The edit will FAIL if `old_string` is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use `replace_all` to change every instance of `old_string`.
- Use `replace_all` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.

19
packages/opencode/src/tool/example.ts
View File

@@ -1,19 +0,0 @@
import { z } from "zod"
import { Tool } from "./tool"
export const ExampleTool = Tool.define({
id: "opencode.example",
description: "Example tool",
parameters: z.object({
foo: z.string().describe("The foo parameter"),
bar: z.number().describe("The bar parameter"),
}),
async execute() {
return {
metadata: {
lol: "hey",
},
output: "Hello, world!",
}
},
})

50
packages/opencode/src/tool/glob.ts
View File

@@ -1,41 +1,8 @@
import { z } from "zod"
import path from "path"
import { Tool } from "./tool"
import { App } from "../app/app"
const DESCRIPTION = `Fast file pattern matching tool that finds files by name and pattern, returning matching paths sorted by modification time (newest first).
WHEN TO USE THIS TOOL:
- Use when you need to find files by name patterns or extensions
- Great for finding specific file types across a directory structure
- Useful for discovering files that match certain naming conventions
HOW TO USE:
- Provide a glob pattern to match against file paths
- Optionally specify a starting directory (defaults to current working directory)
- Results are sorted with most recently modified files first
GLOB PATTERN SYNTAX:
- '*' matches any sequence of non-separator characters
- '**' matches any sequence of characters, including separators
- '?' matches any single non-separator character
- '[...]' matches any character in the brackets
- '[!...]' matches any character not in the brackets
COMMON PATTERN EXAMPLES:
- '*.js' - Find all JavaScript files in the current directory
- '**/*.js' - Find all JavaScript files in any subdirectory
- 'src/**/*.{ts,tsx}' - Find all TypeScript files in the src directory
- '*.{html,css,js}' - Find all HTML, CSS, and JS files
LIMITATIONS:
- Results are limited to 100 files (newest first)
- Does not search file contents (use Grep tool for that)
- Hidden files (starting with '.') are skipped
TIPS:
- For the most useful results, combine with the Grep tool: first find files with Glob, then search their contents with Grep
- When doing iterative exploration that may require multiple rounds of searching, consider using the Agent tool instead
- Always check if results are truncated and refine your search pattern if needed`
import DESCRIPTION from "./glob.txt"
export const GlobTool = Tool.define({
id: "opencode.glob",
@@ -45,13 +12,17 @@ export const GlobTool = Tool.define({
path: z
.string()
.describe(
"The directory to search in. Defaults to the current working directory.",
`The directory to search in. If not specified, the current working directory will be used. IMPORTANT: Omit this field to use the default directory. DO NOT enter "undefined" or "null" - simply omit it for the default behavior. Must be a valid directory path if provided.`,
)
.optional(),
}),
async execute(params) {
const app = App.info()
const search = params.path || app.path.cwd
let search = params.path ?? app.path.cwd
search = path.isAbsolute(search)
? search
: path.resolve(app.path.cwd, search)
const limit = 100
const glob = new Bun.Glob(params.pattern)
const files = []
@@ -61,12 +32,13 @@ export const GlobTool = Tool.define({
truncated = true
break
}
const stats = await Bun.file(file)
const full = path.resolve(search, file)
const stats = await Bun.file(full)
.stat()
.then((x) => x.mtime.getTime())
.catch(() => 0)
files.push({
path: file,
path: full,
mtime: stats,
})
}

6
packages/opencode/src/tool/glob.txt Normal file
View File

@@ -0,0 +1,6 @@
- Fast file pattern matching tool that works with any codebase size
- Supports glob patterns like "**/*.js" or "src/**/*.ts"
- Returns matching file paths sorted by modification time
- Use this tool when you need to find files by name patterns
- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead
- You have the capability to call multiple tools in a single response. It is always better to speculatively perform multiple searches as a batch that are potentially useful.

362
packages/opencode/src/tool/grep.ts
View File

@@ -1,259 +1,9 @@
import { z } from "zod"
import { Tool } from "./tool"
import { App } from "../app/app"
import { spawn } from "child_process"
import { promises as fs } from "fs"
import path from "path"
import { Ripgrep } from "../ripgrep"
const DESCRIPTION = `Fast content search tool that finds files containing specific text or patterns, returning matching file paths sorted by modification time (newest first).
WHEN TO USE THIS TOOL:
- Use when you need to find files containing specific text or patterns
- Great for searching code bases for function names, variable declarations, or error messages
- Useful for finding all files that use a particular API or pattern
HOW TO USE:
- Provide a regex pattern to search for within file contents
- Set literal_text=true if you want to search for the exact text with special characters (recommended for non-regex users)
- Optionally specify a starting directory (defaults to current working directory)
- Optionally provide an include pattern to filter which files to search
- Results are sorted with most recently modified files first
REGEX PATTERN SYNTAX (when literal_text=false):
- Supports standard regular expression syntax
- 'function' searches for the literal text "function"
- 'log\\..*Error' finds text starting with "log." and ending with "Error"
- 'import\\s+.*\\s+from' finds import statements in JavaScript/TypeScript
COMMON INCLUDE PATTERN EXAMPLES:
- '*.js' - Only search JavaScript files
- '*.{ts,tsx}' - Only search TypeScript files
- '*.go' - Only search Go files
LIMITATIONS:
- Results are limited to 100 files (newest first)
- Performance depends on the number of files being searched
- Very large binary files may be skipped
- Hidden files (starting with '.') are skipped
TIPS:
- For faster, more targeted searches, first use Glob to find relevant files, then use Grep
- When doing iterative exploration that may require multiple rounds of searching, consider using the Agent tool instead
- Always check if results are truncated and refine your search pattern if needed
- Use literal_text=true when searching for exact text containing special characters like dots, parentheses, etc.`
interface GrepMatch {
path: string
modTime: number
lineNum: number
lineText: string
}
function escapeRegexPattern(pattern: string): string {
const specialChars = [
"\\",
".",
"+",
"*",
"?",
"(",
")",
"[",
"]",
"{",
"}",
"^",
"$",
"|",
]
let escaped = pattern
for (const char of specialChars) {
escaped = escaped.replaceAll(char, "\\" + char)
}
return escaped
}
function globToRegex(glob: string): string {
let regexPattern = glob.replaceAll(".", "\\.")
regexPattern = regexPattern.replaceAll("*", ".*")
regexPattern = regexPattern.replaceAll("?", ".")
// Handle {a,b,c} patterns
regexPattern = regexPattern.replace(/\{([^}]+)\}/g, (_, inner) => {
return "(" + inner.replace(/,/g, "|") + ")"
})
return regexPattern
}
async function searchWithRipgrep(
pattern: string,
searchPath: string,
include?: string,
): Promise<GrepMatch[]> {
return new Promise((resolve, reject) => {
const args = ["-n", pattern]
if (include) {
args.push("--glob", include)
}
args.push(searchPath)
const rg = spawn("rg", args)
let output = ""
let errorOutput = ""
rg.stdout.on("data", (data) => {
output += data.toString()
})
rg.stderr.on("data", (data) => {
errorOutput += data.toString()
})
rg.on("close", async (code) => {
if (code === 1) {
// No matches found
resolve([])
return
}
if (code !== 0) {
reject(new Error(`ripgrep failed: ${errorOutput}`))
return
}
const lines = output.trim().split("\n")
const matches: GrepMatch[] = []
for (const line of lines) {
if (!line) continue
// Parse ripgrep output format: file:line:content
const parts = line.split(":", 3)
if (parts.length < 3) continue
const filePath = parts[0]
const lineNum = parseInt(parts[1], 10)
const lineText = parts[2]
try {
const stats = await fs.stat(filePath)
matches.push({
path: filePath,
modTime: stats.mtime.getTime(),
lineNum,
lineText,
})
} catch {
// Skip files we can't access
continue
}
}
resolve(matches)
})
rg.on("error", (err) => {
reject(err)
})
})
}
async function searchFilesWithRegex(
pattern: string,
rootPath: string,
include?: string,
): Promise<GrepMatch[]> {
const matches: GrepMatch[] = []
const regex = new RegExp(pattern)
let includePattern: RegExp | undefined
if (include) {
const regexPattern = globToRegex(include)
includePattern = new RegExp(regexPattern)
}
async function walkDir(dir: string) {
if (matches.length >= 200) return
try {
const entries = await fs.readdir(dir, { withFileTypes: true })
for (const entry of entries) {
if (matches.length >= 200) break
const fullPath = path.join(dir, entry.name)
if (entry.isDirectory()) {
// Skip hidden directories
if (entry.name.startsWith(".")) continue
await walkDir(fullPath)
} else if (entry.isFile()) {
// Skip hidden files
if (entry.name.startsWith(".")) continue
if (includePattern && !includePattern.test(fullPath)) {
continue
}
try {
const content = await fs.readFile(fullPath, "utf-8")
const lines = content.split("\n")
for (let i = 0; i < lines.length; i++) {
if (regex.test(lines[i])) {
const stats = await fs.stat(fullPath)
matches.push({
path: fullPath,
modTime: stats.mtime.getTime(),
lineNum: i + 1,
lineText: lines[i],
})
break // Only first match per file
}
}
} catch {
// Skip files we can't read
continue
}
}
}
} catch {
// Skip directories we can't read
return
}
}
await walkDir(rootPath)
return matches
}
async function searchFiles(
pattern: string,
rootPath: string,
include?: string,
limit: number = 100,
): Promise<{ matches: GrepMatch[]; truncated: boolean }> {
let matches: GrepMatch[]
try {
matches = await searchWithRipgrep(pattern, rootPath, include)
} catch {
matches = await searchFilesWithRegex(pattern, rootPath, include)
}
// Sort by modification time (newest first)
matches.sort((a, b) => b.modTime - a.modTime)
const truncated = matches.length > limit
if (truncated) {
matches = matches.slice(0, limit)
}
return { matches, truncated }
}
import DESCRIPTION from "./grep.txt"
export const GrepTool = Tool.define({
id: "opencode.grep",
@@ -274,12 +24,6 @@ export const GrepTool = Tool.define({
'File pattern to include in the search (e.g. "*.js", "*.{ts,tsx}")',
)
.optional(),
literalText: z
.boolean()
.describe(
"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.",
)
.optional(),
}),
async execute(params) {
if (!params.pattern) {
@@ -289,56 +33,98 @@ export const GrepTool = Tool.define({
const app = App.info()
const searchPath = params.path || app.path.cwd
// If literalText is true, escape the pattern
const searchPattern = params.literalText
? escapeRegexPattern(params.pattern)
: params.pattern
const rgPath = await Ripgrep.filepath()
const args = ["-n", params.pattern]
if (params.include) {
args.push("--glob", params.include)
}
args.push(searchPath)
const { matches, truncated } = await searchFiles(
searchPattern,
searchPath,
params.include,
100,
)
const proc = Bun.spawn([rgPath, ...args], {
stdout: "pipe",
stderr: "pipe",
})
if (matches.length === 0) {
const output = await new Response(proc.stdout).text()
const errorOutput = await new Response(proc.stderr).text()
const exitCode = await proc.exited
if (exitCode === 1) {
return {
metadata: { matches: 0, truncated },
metadata: { matches: 0, truncated: false },
output: "No files found",
}
}
const lines = [`Found ${matches.length} matches`]
if (exitCode !== 0) {
throw new Error(`ripgrep failed: ${errorOutput}`)
}
let currentFile = ""
for (const match of matches) {
if (currentFile !== match.path) {
if (currentFile !== "") {
lines.push("")
}
currentFile = match.path
lines.push(`${match.path}:`)
}
if (match.lineNum > 0) {
lines.push(` Line ${match.lineNum}: ${match.lineText}`)
} else {
lines.push(` ${match.path}`)
const lines = output.trim().split("\n")
const matches = []
for (const line of lines) {
if (!line) continue
const parts = line.split(":", 3)
if (parts.length < 3) continue
const filePath = parts[0]
const lineNum = parseInt(parts[1], 10)
const lineText = parts[2]
const file = Bun.file(filePath)
const stats = await file.stat().catch(() => null)
if (!stats) continue
matches.push({
path: filePath,
modTime: stats.mtime.getTime(),
lineNum,
lineText,
})
}
matches.sort((a, b) => b.modTime - a.modTime)
const limit = 100
const truncated = matches.length > limit
const finalMatches = truncated ? matches.slice(0, limit) : matches
if (finalMatches.length === 0) {
return {
metadata: { matches: 0, truncated: false },
output: "No files found",
}
}
const outputLines = [`Found ${finalMatches.length} matches`]
let currentFile = ""
for (const match of finalMatches) {
if (currentFile !== match.path) {
if (currentFile !== "") {
outputLines.push("")
}
currentFile = match.path
outputLines.push(`${match.path}:`)
}
outputLines.push(` Line ${match.lineNum}: ${match.lineText}`)
}
if (truncated) {
lines.push("")
lines.push(
outputLines.push("")
outputLines.push(
"(Results are truncated. Consider using a more specific path or pattern.)",
)
}
return {
metadata: {
matches: matches.length,
matches: finalMatches.length,
truncated,
},
output: lines.join("\n"),
output: outputLines.join("\n"),
}
},
})

8
packages/opencode/src/tool/grep.txt Normal file
View File

@@ -0,0 +1,8 @@
- Fast content search tool that works with any codebase size
- Searches file contents using regular expressions
- Supports full regex syntax (eg. "log.*Error", "function\s+\w+", etc.)
- Filter files by pattern with the include parameter (eg. "*.js", "*.{ts,tsx}")
- Returns file paths with at least one match sorted by modification time
- Use this tool when you need to find files containing specific patterns
- If you need to identify/count the number of matches within files, use the Bash tool with `rg` (ripgrep) directly. Do NOT use `grep`.
- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead

3
packages/opencode/src/tool/ls.ts
View File

@@ -2,6 +2,7 @@ import { z } from "zod"
import { Tool } from "./tool"
import { App } from "../app/app"
import * as path from "path"
import DESCRIPTION from "./ls.txt"
const IGNORE_PATTERNS = [
"node_modules/",
@@ -19,7 +20,7 @@ const IGNORE_PATTERNS = [
export const ListTool = Tool.define({
id: "opencode.list",
description: "List directory contents",
description: DESCRIPTION,
parameters: z.object({
path: z.string().optional(),
ignore: z.array(z.string()).optional(),

1
packages/opencode/src/tool/ls.txt Normal file
View File

@@ -0,0 +1 @@
Lists files and directories in a given path. The path parameter must be an absolute path, not a relative path. You can optionally provide an array of glob patterns to ignore with the ignore parameter. You should generally prefer the Glob and Grep tools, if you know which directories to search.

26
packages/opencode/src/tool/lsp-diagnostics.ts
View File

@@ -3,33 +3,11 @@ import { Tool } from "./tool"
import path from "path"
import { LSP } from "../lsp"
import { App } from "../app/app"
import DESCRIPTION from "./lsp-diagnostics.txt"
export const LspDiagnosticTool = Tool.define({
id: "opencode.lsp_diagnostics",
description: `Get diagnostics for a file and/or project.
WHEN TO USE THIS TOOL:
- Use when you need to check for errors or warnings in your code
- Helpful for debugging and ensuring code quality
- Good for getting a quick overview of issues in a file or project
HOW TO USE:
- Provide a path to a file to get diagnostics for that file
- Results are displayed in a structured format with severity levels
FEATURES:
- Displays errors, warnings, and hints
- Groups diagnostics by severity
- Provides detailed information about each diagnostic
LIMITATIONS:
- Results are limited to the diagnostics provided by the LSP clients
- May not cover all possible issues in the code
- Does not provide suggestions for fixing issues
TIPS:
- Use in conjunction with other tools for a comprehensive code review
- Combine with the LSP client for real-time diagnostics`,
description: DESCRIPTION,
parameters: z.object({
path: z.string().describe("The path to the file to get diagnostics."),
}),

1
packages/opencode/src/tool/lsp-diagnostics.txt Normal file
View File

@@ -0,0 +1 @@
do not use

7
packages/opencode/src/tool/lsp-hover.ts
View File

@@ -3,14 +3,11 @@ import { Tool } from "./tool"
import path from "path"
import { LSP } from "../lsp"
import { App } from "../app/app"
import DESCRIPTION from "./lsp-hover.txt"
export const LspHoverTool = Tool.define({
id: "opencode.lsp_hover",
description: `
Looks up hover information for a given position in a source file using the Language Server Protocol (LSP).
This includes type information, documentation, or symbol details at the specified line and character.
Useful for providing code insights, explanations, or context-aware assistance based on the user's current cursor location.
`,
description: DESCRIPTION,
parameters: z.object({
file: z.string().describe("The path to the file to get diagnostics."),
line: z.number().describe("The line number to get diagnostics."),

1
packages/opencode/src/tool/lsp-hover.txt Normal file
View File

@@ -0,0 +1 @@
do not use

41
packages/opencode/src/tool/multiedit.txt Normal file
View File

@@ -0,0 +1,41 @@
This is a tool for making multiple edits to a single file in one operation. It is built on top of the Edit tool and allows you to perform multiple find-and-replace operations efficiently. Prefer this tool over the Edit tool when you need to make multiple edits to the same file.
Before using this tool:
1. Use the Read tool to understand the file's contents and context
2. Verify the directory path is correct
To make multiple file edits, provide the following:
1. file_path: The absolute path to the file to modify (must be absolute, not relative)
2. edits: An array of edit operations to perform, where each edit contains:
- old_string: The text to replace (must match the file contents exactly, including all whitespace and indentation)
- new_string: The edited text to replace the old_string
- replace_all: Replace all occurences of old_string. This parameter is optional and defaults to false.
IMPORTANT:
- All edits are applied in sequence, in the order they are provided
- Each edit operates on the result of the previous edit
- All edits must be valid for the operation to succeed - if any edit fails, none will be applied
- This tool is ideal when you need to make several changes to different parts of the same file
CRITICAL REQUIREMENTS:
1. All edits follow the same requirements as the single Edit tool
2. The edits are atomic - either all succeed or none are applied
3. Plan your edits carefully to avoid conflicts between sequential operations
WARNING:
- The tool will fail if edits.old_string doesn't match the file contents exactly (including whitespace)
- The tool will fail if edits.old_string and edits.new_string are the same
- Since edits are applied in sequence, ensure that earlier edits don't affect the text that later edits are trying to find
When making edits:
- Ensure all edits result in idiomatic, correct code
- Do not leave the code in a broken state
- Always use absolute file paths (starting with /)
- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.
- Use replace_all for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.
If you want to create a new file, use:
- A new file path, including dir name if needed
- First edit: empty old_string and the new file's contents as new_string
- Subsequent edits: normal edit operations on the created content

30
packages/opencode/src/tool/patch.ts
View File

@@ -3,35 +3,7 @@ import * as path from "path"
import * as fs from "fs/promises"
import { Tool } from "./tool"
import { FileTimes } from "./util/file-times"
const DESCRIPTION = `Applies a patch to multiple files in one operation. This tool is useful for making coordinated changes across multiple files.
The patch text must follow this format:
*** Begin Patch
*** Update File: /path/to/file
@@ Context line (unique within the file)
Line to keep
-Line to remove
+Line to add
Line to keep
*** Add File: /path/to/new/file
+Content of the new file
+More content
*** Delete File: /path/to/file/to/delete
*** End Patch
Before using this tool:
1. Use the FileRead tool to understand the files' contents and context
2. Verify all file paths are correct (use the LS tool)
CRITICAL REQUIREMENTS FOR USING THIS TOOL:
1. UNIQUENESS: Context lines MUST uniquely identify the specific sections you want to change
2. PRECISION: All whitespace, indentation, and surrounding code must match exactly
3. VALIDATION: Ensure edits result in idiomatic, correct code
4. PATHS: Always use absolute file paths (starting with /)
The tool will apply all changes in a single atomic operation.`
import DESCRIPTION from "./patch.txt"
const PatchParams = z.object({
patchText: z

1
packages/opencode/src/tool/patch.txt Normal file
View File

@@ -0,0 +1 @@
do not use

36
packages/opencode/src/tool/view.ts → packages/opencode/src/tool/read.ts
View File

@@ -4,44 +4,14 @@ import * as path from "path"
import { Tool } from "./tool"
import { LSP } from "../lsp"
import { FileTimes } from "./util/file-times"
import DESCRIPTION from "./read.txt"
const MAX_READ_SIZE = 250 * 1024
const DEFAULT_READ_LIMIT = 2000
const MAX_LINE_LENGTH = 2000
const DESCRIPTION = `File viewing tool that reads and displays the contents of files with line numbers, allowing you to examine code, logs, or text data.
WHEN TO USE THIS TOOL:
- Use when you need to read the contents of a specific file
- Helpful for examining source code, configuration files, or log files
- Perfect for looking at text-based file formats
HOW TO USE:
- Provide the path to the file you want to view
- Optionally specify an offset to start reading from a specific line
- Optionally specify a limit to control how many lines are read
FEATURES:
- Displays file contents with line numbers for easy reference
- Can read from any position in a file using the offset parameter
- Handles large files by limiting the number of lines read
- Automatically truncates very long lines for better display
- Suggests similar file names when the requested file isn't found
LIMITATIONS:
- Maximum file size is 250KB
- Default reading limit is 2000 lines
- Lines longer than 2000 characters are truncated
- Cannot display binary files or images
- Images can be identified but not displayed
TIPS:
- Use with Glob tool to first find files you want to view
- For code exploration, first use Grep to find relevant files, then View to examine them
- When viewing large files, use the offset parameter to read specific sections`
export const ViewTool = Tool.define({
id: "opencode.view",
export const ReadTool = Tool.define({
id: "opencode.read",
description: DESCRIPTION,
parameters: z.object({
filePath: z.string().describe("The path to the file to read"),

13
packages/opencode/src/tool/read.txt Normal file
View File

@@ -0,0 +1,13 @@
Reads a file from the local filesystem. You can access any file directly by using this tool.
Assume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.
Usage:
- The file_path parameter must be an absolute path, not a relative path
- By default, it reads up to 2000 lines starting from the beginning of the file
- You can optionally specify a line offset and limit (especially handy for long files), but it's recommended to read the whole file by not providing these parameters
- Any lines longer than 2000 characters will be truncated
- Results are returned using cat -n format, with line numbers starting at 1
- This tool allows OpenCode to read images (eg PNG, JPG, etc). When reading an image file the contents are presented visually as OpenCode is a multimodal LLM.
- You have the capability to call multiple tools in a single response. It is always better to speculatively read multiple files as a batch that are potentially useful.
- You will regularly be asked to read screenshots. If the user provides a path to a screenshot ALWAYS use this tool to view the file at the path. This tool will work with all temporary file paths like /var/folders/123/abc/T/TemporaryItems/NSIRD_screencaptureui_ZfB1tD/Screenshot.png
- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents.

16
packages/opencode/src/tool/task.txt Normal file
View File

@@ -0,0 +1,16 @@
Launch a new agent that has access to the following tools: Bash, Glob, Grep, LS, Read, Edit, MultiEdit, Write, NotebookRead, NotebookEdit, WebFetch, TodoRead, TodoWrite, WebSearch. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries, use the Agent tool to perform the search for you.
When to use the Agent tool:
- If you are searching for a keyword like "config" or "logger", or for questions like "which file does X?", the Agent tool is strongly recommended
When NOT to use the Agent tool:
- If you want to read a specific file path, use the Read or Glob tool instead of the Agent tool, to find the match more quickly
- If you are searching for a specific class definition like "class Foo", use the Glob tool instead, to find the match more quickly
- If you are searching for code within a specific file or set of 2-3 files, use the Read tool instead of the Agent tool, to find the match more quickly
Usage notes:
1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses
2. When the agent is done, it will return a single message back to you. The result returned by the agent is not visible to the user. To show the user the result, you should send a text message back to the user with a concise summary of the result.
3. Each agent invocation is stateless. You will not be able to send additional messages to the agent, nor will the agent be able to communicate with you outside of its final report. Therefore, your prompt should contain a highly detailed task description for the agent to perform autonomously and you should specify exactly what information the agent should return back to you in its final and only message to you.
4. The agent's outputs should generally be trusted
5. Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent

14
packages/opencode/src/tool/todoread.txt Normal file
View File

@@ -0,0 +1,14 @@
Use this tool to read the current to-do list for the session. This tool should be used proactively and frequently to ensure that you are aware of
the status of the current task list. You should make use of this tool as often as possible, especially in the following situations:
- At the beginning of conversations to see what's pending
- Before starting new tasks to prioritize work
- When the user asks about previous tasks or plans
- Whenever you're uncertain about what to do next
- After completing tasks to update your understanding of remaining work
- After every few messages to ensure you're on track
Usage:
- This tool takes in no parameters. So leave the input blank or empty. DO NOT include a dummy object, placeholder string or a key like "input" or "empty". LEAVE IT BLANK.
- Returns a list of todo items with their status, priority, and content
- Use this information to track progress and plan next steps
- If no todos exist yet, an empty list will be returned

167
packages/opencode/src/tool/todowrite.txt Normal file
View File

@@ -0,0 +1,167 @@
Use this tool to create and manage a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.
It also helps the user understand the progress of the task and overall progress of their requests.
## When to Use This Tool
Use this tool proactively in these scenarios:
1. Complex multi-step tasks - When a task requires 3 or more distinct steps or actions
2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations
3. User explicitly requests todo list - When the user directly asks you to use the todo list
4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)
5. After receiving new instructions - Immediately capture user requirements as todos. Feel free to edit the todo list based on new information.
6. After completing a task - Mark it complete and add any new follow-up tasks
7. When you start working on a new task, mark the todo as in_progress. Ideally you should only have one todo as in_progress at a time. Complete existing tasks before starting new ones.
## When NOT to Use This Tool
Skip using this tool when:
1. There is only a single, straightforward task
2. The task is trivial and tracking it provides no organizational benefit
3. The task can be completed in less than 3 trivial steps
4. The task is purely conversational or informational
NOTE that you should not use this tool if there is only one trivial task to do. In this case you are better off just doing the task directly.
## Examples of When to Use the Todo List
<example>
User: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!
Assistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.
*Creates todo list with the following items:*
1. Create dark mode toggle component in Settings page
2. Add dark mode state management (context/store)
3. Implement CSS-in-JS styles for dark theme
4. Update existing components to support theme switching
5. Run tests and build process, addressing any failures or errors that occur
*Begins working on the first task*
<reasoning>
The assistant used the todo list because:
1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes
2. The user explicitly requested tests and build be run afterward
3. The assistant inferred that tests and build need to pass by adding "Ensure tests and build succeed" as the final task
</reasoning>
</example>
<example>
User: Help me rename the function getCwd to getCurrentWorkingDirectory across my project
Assistant: Let me first search through your codebase to find all occurrences of 'getCwd'.
*Uses grep or search tools to locate all instances of getCwd in the codebase*
Assistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.
*Creates todo list with specific items for each file that needs updating*
<reasoning>
The assistant used the todo list because:
1. First, the assistant searched to understand the scope of the task
2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps
3. The todo list helps ensure every instance is tracked and updated systematically
4. This approach prevents missing any occurrences and maintains code consistency
</reasoning>
</example>
<example>
User: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.
Assistant: I'll help implement these features. First, let's add all the features to the todo list.
*Creates a todo list breaking down each feature into specific tasks based on the project architecture*
Assistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.
<reasoning>
The assistant used the todo list because:
1. The user provided multiple complex features to implement in a comma separated list
2. The todo list helps organize these large features into manageable tasks
3. This approach allows for tracking progress across the entire implementation
</reasoning>
</example>
<example>
User: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>
Assistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.
*Reviews component structure, render patterns, state management, and data fetching*
Assistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.
*Creates todo list with items like: 1) Implement memoization for expensive calculations in ProductList, 2) Add virtualization for long lists in Dashboard, 3) Optimize image loading in Gallery component, 4) Fix state update loops in ShoppingCart, 5) Review bundle size and implement code splitting*
Let's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>
<reasoning>
The assistant used the todo list because:
1. First, the assistant examined the codebase to identify specific performance issues
2. Based on this analysis, it identified multiple optimization opportunities
3. Performance optimization is a non-trivial task requiring multiple steps
4. The todo list helps methodically track improvements across different components
5. This systematic approach ensures all performance bottlenecks are addressed
</reasoning>
</example>
## Examples of When NOT to Use the Todo List
<example>
User: How do I print 'Hello World' in Python?
Assistant: In Python, you can print "Hello World" with this simple code:
python
print("Hello World")
This will output the text "Hello World" to the console when executed.</assistant>
<reasoning>
The assistant did not use the todo list because this is a single, trivial task that can be completed in one step. There's no need to track multiple tasks or steps for such a straightforward request.
</reasoning>
</example>
<example>
User: What does the git status command do?
Assistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.
<reasoning>
The assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.
</reasoning>
</example>
<example>
User: Can you add a comment to the calculateTotal function to explain what it does?
Assistant: Sure, let me add a comment to the calculateTotal function to explain what it does.
* Uses the Edit tool to add a comment to the calculateTotal function *
<reasoning>
The assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.
</reasoning>
</example>
<example>
User: Run npm install for me and tell me what happens.
Assistant: I'll run the npm install command for you.
*Executes: npm install*
The command completed successfully. Here's the output:
[Output of npm install command]
All dependencies have been installed according to your package.json file.
<reasoning>
The assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.
</reasoning>
</example>
## Task States and Management
1. **Task States**: Use these states to track progress:
- pending: Task not yet started
- in_progress: Currently working on (limit to ONE task at a time)
- completed: Task finished successfully
- cancelled: Task no longer needed
2. **Task Management**:
- Update task status in real-time as you work
- Mark tasks complete IMMEDIATELY after finishing (don't batch completions)
- Only have ONE task in_progress at any time
- Complete current tasks before starting new ones
- Cancel tasks that become irrelevant
3. **Task Breakdown**:
- Create specific, actionable items
- Break complex tasks into smaller, manageable steps
- Use clear, descriptive task names
When in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.

35
packages/opencode/src/tool/fetch.ts → packages/opencode/src/tool/webfetch.ts
View File

@@ -1,43 +1,14 @@
import { z } from "zod"
import { Tool } from "./tool"
import TurndownService from "turndown"
import DESCRIPTION from "./webfetch.txt"
const MAX_RESPONSE_SIZE = 5 * 1024 * 1024 // 5MB
const DEFAULT_TIMEOUT = 30 * 1000 // 30 seconds
const MAX_TIMEOUT = 120 * 1000 // 2 minutes
const DESCRIPTION = `Fetches content from a URL and returns it in the specified format.
WHEN TO USE THIS TOOL:
- Use when you need to download content from a URL
- Helpful for retrieving documentation, API responses, or web content
- Useful for getting external information to assist with tasks
HOW TO USE:
- Provide the URL to fetch content from
- Specify the desired output format (text, markdown, or html)
- Optionally set a timeout for the request
FEATURES:
- Supports three output formats: text, markdown, and html
- Automatically handles HTTP redirects
- Sets reasonable timeouts to prevent hanging
- Validates input parameters before making requests
LIMITATIONS:
- Maximum response size is 5MB
- Only supports HTTP and HTTPS protocols
- Cannot handle authentication or cookies
- Some websites may block automated requests
TIPS:
- Use text format for plain text content or simple API responses
- Use markdown format for content that should be rendered with formatting
- Use html format when you need the raw HTML structure
- Set appropriate timeouts for potentially slow websites`
export const FetchTool = Tool.define({
id: "opencode.fetch",
export const WebFetchTool = Tool.define({
id: "opencode.webfetch",
description: DESCRIPTION,
parameters: z.object({
url: z.string().describe("The URL to fetch content from"),

14
packages/opencode/src/tool/webfetch.txt Normal file
View File

@@ -0,0 +1,14 @@
- Fetches content from a specified URL
- Takes a URL and a prompt as input
- Fetches the URL content, converts HTML to markdown
- Returns the model's response about the content
- Use this tool when you need to retrieve and analyze web content
Usage notes:
- IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions. All MCP-provided tools start with "mcp__".
- The URL must be a fully-formed valid URL
- HTTP URLs will be automatically upgraded to HTTPS
- The prompt should describe what information you want to extract from the page
- This tool is read-only and does not modify any files
- Results may be summarized if the content is very large
- Includes a self-cleaning 15-minute cache for faster responses when repeatedly accessing the same URL

11
packages/opencode/src/tool/websearch.txt Normal file
View File

@@ -0,0 +1,11 @@
- Allows OpenCode to search the web and use the results to inform responses
- Provides up-to-date information for current events and recent data
- Returns search result information formatted as search result blocks
- Use this tool for accessing information beyond Claude's knowledge cutoff
- Searches are performed automatically within a single API call
Usage notes:
- Domain filtering is supported to include or block specific websites
- Web search is only available in the US

8
packages/opencode/src/tool/write.txt Normal file
View File

@@ -0,0 +1,8 @@
Writes a file to the local filesystem.
Usage:
- This tool will overwrite the existing file if there is one at the provided path.
- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.
- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.
- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.
- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked.