Skip to content

feat: improve read_file tool descriptions for non-OpenAI models #11192

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
roomote wants to merge 1 commit into from
+3 −3
Closed

feat: improve read_file tool descriptions for non-OpenAI models #11192

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions src/core/prompts/tools/native-tools/read_file.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,7 +70,7 @@ export function createReadFileTool(options: ReadFileToolOptions = {}): OpenAI.Ch
` PREFER indentation mode when you have a specific line number from search results, error messages, or definition lookups - it guarantees complete, syntactically valid code blocks without mid-function truncation.` +
` IMPORTANT: Indentation mode requires anchor_line to be useful. Without it, only header content (imports) is returned.`

const limitNote = ` By default, returns up to ${DEFAULT_LINE_LIMIT} lines per file. Lines longer than ${MAX_LINE_LENGTH} characters are truncated.`
const limitNote = ` Default limit is ${DEFAULT_LINE_LIMIT} lines - use this default by omitting the limit parameter. Only specify a smaller limit if you know the file exceeds ${DEFAULT_LINE_LIMIT} lines and you need pagination. Lines longer than ${MAX_LINE_LENGTH} characters are truncated.`
Copy link
Contributor Author

@roomote roomote bot Feb 4, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The phrase "Only specify a smaller limit" is logically inconsistent with the pagination use case. If a file exceeds 2000 lines and you need pagination, you'd keep the default limit and adjust the offset for subsequent pages, not specify a "smaller" limit. Specifying a smaller limit would result in more pages of smaller chunks, which is exactly the inefficient behavior this PR aims to prevent. Consider removing the word "smaller" to match the clearer wording in the limit parameter description on line 128.

Suggested change
const limitNote = ` Default limit is ${DEFAULT_LINE_LIMIT} lines - use this default by omitting the limit parameter. Only specify a smaller limit if you know the file exceeds ${DEFAULT_LINE_LIMIT} lines and you need pagination. Lines longer than ${MAX_LINE_LENGTH} characters are truncated.`
const limitNote = ` Default limit is ${DEFAULT_LINE_LIMIT} lines - use this default by omitting the limit parameter. Only specify a limit if you know the file exceeds ${DEFAULT_LINE_LIMIT} lines and you need pagination. Lines longer than ${MAX_LINE_LENGTH} characters are truncated.`

Fix it with Roo Code or mention @roomote and request a fix.


const description =
descriptionIntro +
Expand Down Expand Up @@ -117,15 +117,15 @@ export function createReadFileTool(options: ReadFileToolOptions = {}): OpenAI.Ch
type: "string",
enum: ["slice", "indentation"],
description:
"Reading mode. 'slice' (default): read lines sequentially with offset/limit - use for general file exploration or when you don't have a target line number (may truncate code mid-function). 'indentation': extract complete semantic code blocks containing anchor_line - PREFERRED when you have a line number because it guarantees complete, valid code blocks. WARNING: Do not use indentation mode without specifying indentation.anchor_line, or you will only get header content.",
"Reading mode. 'slice' (default): read lines sequentially with offset/limit - use for general file exploration or when you don't have a target line number (may truncate code mid-function). 'indentation': extract complete semantic code blocks containing anchor_line - PREFERRED when you have a line number because it guarantees complete, valid code blocks (ignores offset/limit entirely). WARNING: Do not use indentation mode without specifying indentation.anchor_line, or you will only get header content.",
},
offset: {
type: "integer",
description: "1-based line offset to start reading from (slice mode, default: 1)",
},
limit: {
type: "integer",
description: `Maximum number of lines to return (slice mode, default: ${DEFAULT_LINE_LIMIT})`,
description: `Maximum number of lines to return (slice mode). Default is ${DEFAULT_LINE_LIMIT}. Omit this parameter to use the default. Only specify a value if you need pagination for files larger than ${DEFAULT_LINE_LIMIT} lines.`,
},
indentation: {
type: "object",
Expand Down
Loading