fix(file): credit runs across a repeat, count matching lines not matches

The tool promised "each match" while the query is distinct on file and line,
so several matches on one line return one row. An agent reading the contract
would have expected otherwise; it now says each matching line once.

A repetition of a non-fixed atom was scored at what one copy guarantees, but
from two copies on its own tail and head meet: every match of
`(?:a(?:x|y)bc){2}` contains `bca`, which neither copy contains alone. That
run is now credited, so patterns the index can serve are no longer rejected.

Scores are capped alongside the strings they measure. Joining two capped
strings yields twice the cap, which `concatenate` could already exceed — the
gate never noticed, since it only compares against three, but the bound is
documented and now holds.

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

Author: icecrasher321

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

@@ -70,7 +70,7 @@ 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 match with its file ID and line number.
+Search every active workspace file for lines matching a regular expression, and return each matching line once with its file ID and line number.
 
 #### Input
 

apps/sim/blocks/blocks/file.ts

@@ -908,7 +908,7 @@ export const FileV5Block: BlockConfig<FileParserV3Output> = {
   - Get Content is how you read file text. It accepts file objects or canonical file IDs and returns a "contents" array with one extracted text string per file (PDF, DOCX, CSV, etc. are parsed automatically).
   - To read the text of files produced by another block, chain into Get Content: set its file input to the upstream file output, e.g. <file.files>, <agent.files>, or <start.files>. Never assume Read (or any file-object output) already contains the text.
   - Get Content's "contents" can be large; it is persisted through the execution large-value system automatically, so prefer it over inlining file text any other way.
-  - Search finds text across all active workspace files and returns structured results with fileId, lineNumber, and text. Queries are case-insensitive until they contain an uppercase letter being searched for; in a regular expression, uppercase inside an escape or character class such as \\D or [A-Z] does not affect this.
+  - Search finds text across all active workspace files and returns one result per matching line — not per match — with fileId, lineNumber, and text. Queries are case-insensitive until they contain an uppercase letter being searched for; in a regular expression, uppercase inside an escape or character class such as \\D or [A-Z] does not affect this.
   - Search reads the query as a line-oriented regular expression: quantifiers, character classes, \\d \\w \\s, alternation, groups, "^" and "$" anchors, and \\b word boundaries. Lookaround, backreferences and patterns spanning a line break are not supported, and a pattern needs at least 3 consecutive literal characters that every match will contain. Set Match to "Exact match" to search for the query text verbatim instead.
   - Match is a builder setting, not an agent one: the agent writes the query, and Match decides how every query from that block is read.
   - Search is eventually consistent. Check "complete" and "indexStatus" when pending, failed, skipped, or partially indexed files matter to the task.

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

@@ -32,6 +32,16 @@ describe('analyzeFileSearchRegex', () => {
       expect(run('ab{3}cd')).toBe(6)
     })
 
+    /**
+     * `(?:a(?:x|y)bc){2}` matches `axbcaybc`, whose `bca` spans the join between
+     * the two copies — a run neither copy contains on its own.
+     */
+    it('credits the run a repetition creates where its copies meet', () => {
+      expect(run('(?:a(?:x|y)bc){2}')).toBe(3)
+      expect(run('(?:ab(?:x|y)c){3}')).toBe(3)
+      expect(run('(?:a(?:x|y)bc){1}')).toBe(2)
+    })
+
     /** `(?:ab){2,5}` cannot match without `abab` in it, so the run is 4, not 2. */
     it('credits a variable repeat with the copies its minimum forces', () => {
       expect(run('(?:ab){2,5}')).toBe(4)

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

@@ -90,6 +90,15 @@ function runLength(text: string): number {
   return [...text].length
 }
 
+/**
+ * A join of two capped strings is twice the cap, so scores are capped as well —
+ * it keeps `best` inside the same bound the strings are held to, and a run
+ * longer than the cap is still a run longer than the gate it is compared to.
+ */
+function boundedRun(text: string): number {
+  return Math.min(FILE_SEARCH_PATTERN_LITERAL_CAP, runLength(text))
+}
+
 function head(text: string): string {
   return text.length > FILE_SEARCH_PATTERN_LITERAL_CAP
     ? text.slice(0, FILE_SEARCH_PATTERN_LITERAL_CAP)
@@ -123,7 +132,7 @@ function concatenate(left: LiteralGuarantee, right: LiteralGuarantee): LiteralGu
     exact: left.exact !== null && right.exact !== null ? head(left.exact + right.exact) : null,
     prefix: head(left.exact !== null ? left.exact + right.prefix : left.prefix),
     suffix: tail(right.exact !== null ? left.suffix + right.exact : right.suffix),
-    best: Math.max(left.best, right.best, runLength(joined)),
+    best: Math.max(left.best, right.best, boundedRun(joined)),
     zeroWidth: left.zeroWidth && right.zeroWidth,
   }
 }
@@ -189,11 +198,17 @@ function repeat(atom: LiteralGuarantee, min: number, max: number): LiteralGuaran
       zeroWidth: false,
     }
   }
+  /**
+   * An atom with no fixed string still repeats back to back, so from two copies
+   * on, its own tail and head meet: every match of `(?:a(?:x|y)bc){2}` contains
+   * `bca`, which neither copy contains alone.
+   */
+  const acrossCopies = min >= 2 ? boundedRun(tail(atom.suffix) + head(atom.prefix)) : 0
   return {
     exact: null,
     prefix: atom.prefix,
     suffix: atom.suffix,
-    best: atom.best,
+    best: Math.max(atom.best, acrossCopies),
     zeroWidth: atom.zeroWidth,
   }
 }

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 match with its file ID and line number.',
+    'Search every active workspace file for lines matching a regular expression, and return each matching line once with its file ID and line number.',
   exact:
-    'Search every active workspace file for lines containing an exact piece of text, and return each match with its file ID and line number.',
+    '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.',
 }
 
 const QUERY_DESCRIPTIONS: Record<FileSearchMode, string> = {