You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Add a per-provider maxReadFileLine setting that allows users to override
the default 2000-line limit when reading files. This helps users with
slower local providers (e.g. CPU-based inference) avoid timeouts by
reducing prompt size.
Changes:
- Add maxReadFileLine to baseProviderSettingsSchema (packages/types)
- Update createReadFileTool() to reflect the effective limit in tool description
- Thread the setting through getNativeTools() and buildNativeToolsArray()
- Enforce the limit at execution time in ReadFileTool.processTextFile()
- Apply the limit to @ mention file reads via parseMentions chain
- Add MaxReadFileLineControl UI component in provider advanced settings
- Add English localization keys for the new setting
- Fix affected tests to account for new parameter
Closes#11407
` 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.`+
71
76
` IMPORTANT: Indentation mode requires anchor_line to be useful. Without it, only header content (imports) is returned.`
72
77
73
-
constlimitNote=` By default, returns up to ${DEFAULT_LINE_LIMIT} lines per file. Lines longer than ${MAX_LINE_LENGTH} characters are truncated.`
78
+
constlimitNote=` By default, returns up to ${effectiveLineLimit} lines per file. Lines longer than ${MAX_LINE_LENGTH} characters are truncated.`
0 commit comments