tweak: adjust read tool so that it can handle reading directories

.opencode/skill/bun-file-io/SKILL.md

@@ -32,6 +32,9 @@ description: Use this when you are working on file operations like reading, writ
 - Decode tool stderr with `Bun.readableStreamToText`.
 - For large writes, use `Bun.write(Bun.file(path), text)`.
 
+NOTE: Bun.file(...).exists() will return `false` if the value is a directory.
+Use Filesystem.exists(...) instead if path can be file or directory
+
 ## Quick checklist
 
 - Use Bun APIs first.

packages/opencode/src/tool/edit.txt

@@ -2,7 +2,7 @@ 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 oldString or newString.
+- 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: line number + colon + space (e.g., `1: `). Everything after that space is the actual file content to match. Never include any part of the line number prefix in the oldString or newString.
 - 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 `oldString` is not found in the file with an error "oldString not found in content".

packages/opencode/src/tool/read.ts

@@ -17,9 +17,9 @@ const MAX_BYTES = 50 * 1024
 export const ReadTool = Tool.define("read", {
   description: DESCRIPTION,
   parameters: z.object({
-    filePath: z.string().describe("The path to the file to read"),
-    offset: z.coerce.number().describe("The line number to start reading from (0-based)").optional(),
-    limit: z.coerce.number().describe("The number of lines to read (defaults to 2000)").optional(),
+    filePath: z.string().describe("The absolute path to the file to read (directories are not yet supported)"),
+    offset: z.coerce.number().describe("The 0-based line offset to start reading from").optional(),
+    limit: z.coerce.number().describe("The maximum number of lines to read (defaults to 2000)").optional(),
   }),
   async execute(params, ctx) {
     let filepath = params.filePath
@@ -40,7 +40,9 @@ export const ReadTool = Tool.define("read", {
     })
 
     const file = Bun.file(filepath)
-    if (!(await file.exists())) {
+    const stat = await file.stat().catch(() => undefined)
+
+    if (!stat) {
       const dir = path.dirname(filepath)
       const base = path.basename(filepath)
 
@@ -60,6 +62,45 @@ export const ReadTool = Tool.define("read", {
       throw new Error(`File not found: ${filepath}`)
     }
 
+    if (stat.isDirectory()) {
+      const dirents = await fs.promises.readdir(filepath, { withFileTypes: true })
+      const entries = await Promise.all(
+        dirents.map(async (dirent) => {
+          if (dirent.isDirectory()) return dirent.name + "/"
+          if (dirent.isSymbolicLink()) {
+            const target = await fs.promises.stat(path.join(filepath, dirent.name)).catch(() => undefined)
+            if (target?.isDirectory()) return dirent.name + "/"
+          }
+          return dirent.name
+        }),
+      )
+      entries.sort((a, b) => a.localeCompare(b))
+
+      const limit = params.limit ?? DEFAULT_READ_LIMIT
+      const offset = params.offset || 0
+      const sliced = entries.slice(offset, offset + limit)
+      const truncated = sliced.length < entries.length
+
+      const output = [
+        `<path>${filepath}</path>`,
+        `<type>directory</type>`,
+        `<entries>`,
+        sliced.join("\n"),
+        truncated
+          ? `\n(Showing ${sliced.length} of ${entries.length} entries. Use 'offset' parameter to read beyond entry ${offset + sliced.length})`
+          : `\n(${entries.length} entries)`,
+        `</entries>`,
+      ].join("\n")
+
+      return {
+        title,
+        output,
+        metadata: {
+          truncated,
+        },
+      }
+    }
+
     const instructions = await InstructionPrompt.resolve(ctx.messages, filepath, ctx.messageID)
 
     // Exclude SVG (XML-based) and vnd.fastbidsheet (.fbs extension, commonly FlatBuffers schema files)
@@ -112,11 +153,11 @@ export const ReadTool = Tool.define("read", {
     }
 
     const content = raw.map((line, index) => {
-      return `${(index + offset + 1).toString().padStart(5, "0")}| ${line}`
+      return `${index + offset + 1}: ${line}`
     })
     const preview = raw.slice(0, 20).join("\n")
 
-    let output = "<file>\n"
+    let output = [`<path>${filepath}</path>`, `<type>file</type>`, "<content>"].join("\n")
     output += content.join("\n")
 
     const totalLines = lines.length
@@ -131,7 +172,7 @@ export const ReadTool = Tool.define("read", {
     } else {
       output += `\n\n(End of file - total ${totalLines} lines)`
     }
-    output += "\n</file>"
+    output += "\n</content>"
 
     // just warms the lsp client
     LSP.touchFile(filepath, false)

packages/opencode/src/tool/read.txt

@@ -1,12 +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.
+Read a file from the local filesystem. If the file does not exist, an error is returned.
 
 Usage:
-- The filePath 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
-- 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.
-- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents.
-- You can read image files using this tool.
+- The filePath parameter should be an absolute path.
+- By default, this tool returns up to 2000 lines from the start of the file.
+- To read later sections, call this tool again with a larger offset.
+- Use the grep tool to find specific content in large files or files with long lines.
+- If you are unsure of the correct file path, use the glob tool to look up filenames by glob pattern.
+- Contents are returned with each line prefixed by its line number as `<line>: <content>`. For example, if a file has contents "foo\n", you will receive "1: foo\n". For directories, entries are returned one per line (without line numbers) with a trailing `/` for subdirectories.
+- Any line longer than 2000 characters is truncated.
+- Call this tool in parallel when you know there are multiple files you want to read.
+- Avoid tiny repeated slices (30 line chunks). If you need more context, read a larger window.
+- This tool can read image files and PDFs and return them as file attachments.