fix(file): reject overflowed repeat bounds, describe what search covers

An upper bound too large for `Number` arrives as Infinity, and the exception
that lets `{n,}` skip the repeat cap could not tell the two apart — so
`needle{1,<400 digits>}` passed the cap that `needle{1,5000}` fails. The
quantifier now records whether a bound was written at all, and a written one
must be at or under the cap however large it is.

The tool promised every active workspace file. It searches what the index
currently holds: a file still pending, failed, or skipped as unsupported is
not searched, and an agent reading "every file" would take an empty result as
proof of absence. Both descriptions now say so and point at `complete` and
`indexStatus`, which already carry the detail.

The declared query description spoke only for regex mode, which is what the
catalog and the generated docs render — so a builder using exact matching was
told to write a regular expression and to obey a rule that does not apply to
them. It now names both readings; the runtime schema is still enriched with
whichever is in force. The docs overview said literal text, which stopped
being true when regex became the default.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

Author: Vikhyath Mondreti

apps/docs/content/docs/integrations/file.mdx

@@ -16,7 +16,7 @@ The File block is a built-in Sim block for working with files stored in the work
 With the File block, you can:
 
 - **Read and extract content**: Load workspace file objects and extract their text content
-- **Search workspace content**: Find literal text across indexed active workspace files with bounded line-level results
+- **Search workspace content**: Match a regular expression, or an exact piece of text, against the indexed lines of active workspace files with bounded line-level results
 - **Fetch from URLs**: Retrieve and parse files from external URLs with custom headers
 - **Write and append**: Create new workspace files or append content to existing ones
 - **Compress and decompress**: Bundle files into a .zip archive or extract an archive into the workspace
@@ -70,13 +70,13 @@ Extract the text content of one or more workspace files from selected file objec
 
 ### File Search
 
-Search every active workspace file for lines matching a regular expression, and return each matching line once with its file ID and line number.
+Search the indexed text of active workspace files for lines matching a regular expression, and return each matching line once with its file ID and line number. Coverage is what the index currently holds, so check "complete" and "indexStatus" before concluding that something is absent.
 
 #### Input
 
 | Parameter | Type | Required | Description |
 | --------- | ---- | -------- | ----------- |
-| `query` | string | Yes | A regular expression matched against each line, 3-512 characters. Supports "." "*" "+" "?" "\{n,m\}" and their lazy forms, character classes such as "\[a-z\]" and "\[^0-9\]", the classes \d \w \s and \D \W \S, alternation "\|", groups "\(...\)" and "\(?:...\)", the anchors "^" and "$", and the word boundary \b. Lookahead, lookbehind, backreferences, named groups, inline flags such as "\(?i\)", \p\{...\} and POSIX "\[\[:alpha:\]\]" classes are not supported, and a pattern cannot span a line break. The pattern must contain at least 3 consecutive literal characters that every match will include — write "error \d+" rather than "\w+ \d+". Escape any metacharacter you mean literally. Matching is case-insensitive until the pattern contains an uppercase letter you are searching for; uppercase inside an escape or a character class, such as \D or \[A-Z\], does not make it case-sensitive. |
+| `query` | string | Yes | A regular expression matched against each line, 3-512 characters. Supports "." "*" "+" "?" "\{n,m\}" and their lazy forms, character classes such as "\[a-z\]" and "\[^0-9\]", the classes \d \w \s and \D \W \S, alternation "\|", groups "\(...\)" and "\(?:...\)", the anchors "^" and "$", and the word boundary \b. Lookahead, lookbehind, backreferences, named groups, inline flags such as "\(?i\)", \p\{...\} and POSIX "\[\[:alpha:\]\]" classes are not supported, and a pattern cannot span a line break. The pattern must contain at least 3 consecutive literal characters that every match will include — write "error \d+" rather than "\w+ \d+". Escape any metacharacter you mean literally. Matching is case-insensitive until the pattern contains an uppercase letter you are searching for; uppercase inside an escape or a character class, such as \D or \[A-Z\], does not make it case-sensitive. When the workflow builder sets Match to exact instead, the query is matched verbatim and no metacharacter needs escaping. |
 | `mode` | string | No | How the query is read, chosen by the workflow builder: "regex" \(default\) as a regular expression, or "exact" as verbatim text. |
 | `maxResults` | number | No | Hard result cap configured by the workflow builder \(1-200, default 50\). |
 

apps/sim/lib/workspace-files/search/regex.test.ts

@@ -107,6 +107,7 @@ describe('analyzeFileSearchRegex', () => {
       ['foo{2,1}', /counts down/],
       ['a{1,5000}bcd', /exceeds 1000/],
       ['a{5000,}bcd', /exceeds 1000/],
+      [`needle{1,1${'0'.repeat(400)}}`, /exceeds 1000/],
       ['foo{bar}', /Unescaped "\{"/],
     ])('rejects %s', (source, message) => {
       expect(() => analyzeFileSearchRegex(source)).toThrow(FileSearchPatternError)

apps/sim/lib/workspace-files/search/regex.ts

@@ -216,6 +216,12 @@ function repeat(atom: LiteralGuarantee, min: number, max: number): LiteralGuaran
 interface Quantifier {
   min: number
   max: number
+  /**
+   * Whether an upper bound was written at all. `{n,}` has none to cap, but a
+   * bound too large for `Number` also arrives as `Infinity` — without this the
+   * two are indistinguishable and an overflowed bound is read as open-ended.
+   */
+  boundedAbove: boolean
 }
 
 /**
@@ -478,15 +484,15 @@ class FileSearchRegexParser {
     const character = this.peek()
     if (character === '*') {
       this.index += 1
-      return { min: 0, max: Number.POSITIVE_INFINITY }
+      return { min: 0, max: Number.POSITIVE_INFINITY, boundedAbove: false }
     }
     if (character === '+') {
       this.index += 1
-      return { min: 1, max: Number.POSITIVE_INFINITY }
+      return { min: 1, max: Number.POSITIVE_INFINITY, boundedAbove: false }
     }
     if (character === '?') {
       this.index += 1
-      return { min: 0, max: 1 }
+      return { min: 0, max: 1, boundedAbove: true }
     }
     if (character !== '{') return null
     const bounded = this.readQuantifierAt(this.index)
@@ -497,13 +503,15 @@ class FileSearchRegexParser {
     }
     /**
      * `{n,}` has no upper bound to cap — it is `+` with a floor, and both engines
-     * expand it the same way — so only a stated maximum is measured against the
+     * expand it the same way — so only a written maximum is measured against the
      * cap. The minimum is always measured, since that is what an expansion
-     * actually unrolls.
+     * actually unrolls. A written maximum that is not at or under the cap fails,
+     * which covers one too large for `Number` to hold as well as one merely too
+     * big.
      */
     if (
       bounded.min > FILE_SEARCH_PATTERN_MAX_REPEAT ||
-      (Number.isFinite(bounded.max) && bounded.max > FILE_SEARCH_PATTERN_MAX_REPEAT)
+      (bounded.boundedAbove && !(bounded.max <= FILE_SEARCH_PATTERN_MAX_REPEAT))
     ) {
       throw new FileSearchPatternError(
         `Repeat count at position ${this.index + 1} exceeds ${FILE_SEARCH_PATTERN_MAX_REPEAT}`
@@ -522,9 +530,10 @@ class FileSearchRegexParser {
     const match = /^\{(\d+)(,(\d*)?)?\}/.exec(this.source.slice(start))
     if (!match) return null
     const min = Number(match[1])
-    const max =
-      match[2] === undefined ? min : match[3] ? Number(match[3]) : Number.POSITIVE_INFINITY
-    return { min, max, end: start + match[0].length }
+    const exact = match[2] === undefined
+    const boundedAbove = exact || Boolean(match[3])
+    const max = exact ? min : match[3] ? Number(match[3]) : Number.POSITIVE_INFINITY
+    return { min, max, boundedAbove, end: start + match[0].length }
   }
 }
 

apps/sim/tools/file/search.ts

@@ -21,9 +21,9 @@ interface FileSearchResponse extends ToolResponse {
  */
 const TOOL_DESCRIPTIONS: Record<FileSearchMode, string> = {
   regex:
-    'Search every active workspace file for lines matching a regular expression, and return each matching line once with its file ID and line number.',
+    'Search the indexed text of active workspace files for lines matching a regular expression, and return each matching line once with its file ID and line number. Coverage is what the index currently holds, so check "complete" and "indexStatus" before concluding that something is absent.',
   exact:
-    'Search every active workspace file for lines containing an exact piece of text, and return each matching line once with its file ID and line number.',
+    'Search the indexed text of active workspace files for lines containing an exact piece of text, and return each matching line once with its file ID and line number. Coverage is what the index currently holds, so check "complete" and "indexStatus" before concluding that something is absent.',
 }
 
 const QUERY_DESCRIPTIONS: Record<FileSearchMode, string> = {
@@ -33,6 +33,14 @@ const QUERY_DESCRIPTIONS: Record<FileSearchMode, string> = {
     'The exact text to find, 3-512 characters. It is matched verbatim: ".", "*", "(" and every other regular-expression metacharacter is searched for as itself, so nothing needs escaping. Matching is case-insensitive until the text contains an uppercase letter, which makes it case-sensitive.',
 }
 
+/**
+ * What a consumer sees before the mode is known — the catalog, the generated
+ * docs, and a block saved before Match existed. Unlike the runtime schema it is
+ * never enriched with the mode in force, so it has to name both readings rather
+ * than describe only the default.
+ */
+const DECLARED_QUERY_DESCRIPTION = `${QUERY_DESCRIPTIONS.regex} When the workflow builder sets Match to exact instead, the query is matched verbatim and no metacharacter needs escaping.`
+
 export const fileSearchTool: InternalToolConfig<FileSearchParams, FileSearchResponse> = {
   id: 'file_search',
   name: 'File Search',
@@ -43,7 +51,7 @@ export const fileSearchTool: InternalToolConfig<FileSearchParams, FileSearchResp
       type: 'string',
       required: true,
       visibility: 'user-or-llm',
-      description: QUERY_DESCRIPTIONS.regex,
+      description: DECLARED_QUERY_DESCRIPTION,
     },
     mode: {
       type: 'string',