From d34c8c1d725ff7f3f016dcf8208d8e8ebeec4e81 Mon Sep 17 00:00:00 2001
From: DataDave-Dev <153755137+DataDave-Dev@users.noreply.github.com>
Date: Thu, 2 Jul 2026 11:04:21 -0600
Subject: [PATCH] fix(init): don't read a per-function line count as a per-file
 cap

--from-claude-md derived max_lines --max 50 from phrasing like '~50 lines
per function, ~800 per file': the file-cap regex let the gap between the
number and the file word bridge across the comma and the 800, capturing the
function's 50 and then flagging nearly every file. Exclude commas and digits
from that gap so a match can't cross a clause boundary; an ambiguous
comma-joined guideline now derives no cap instead of a wrong one.

Surfaced field-testing becwright against a real Python repo (bot-telegram).
Regression test covers the EN and ES phrasings.
---
 CHANGELOG.md         |  8 ++++++++
 src/becwright/cli.py |  9 ++++++---
 tests/test_init.py   | 10 ++++++++++
 3 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 222fdaa..0721255 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -19,6 +19,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   becwright" error — instead of risking a silent misparse. (The `.bec.yaml`
   export bundle was already versioned via `becwright_bec`.)
 
+### Fixed
+- `becwright init --from-claude-md` no longer misreads a per-*function* line count
+  as a per-*file* cap. A phrase like "~50 lines per function, ~800 per file" used
+  to derive `max_lines --max 50` (flagging nearly every file); the file-cap
+  matcher now refuses to bridge across a comma or another number, so an ambiguous
+  soft guideline derives no cap instead of a wrong one. (Surfaced field-testing a
+  real Python repo.)
+
 ### Documentation
 - Documented becwright's **stable contract** in `documentation/usage.md`: the CLI
   exit codes (`0` pass · `1` a blocking rule failed · `2` config/usage problem)
diff --git a/src/becwright/cli.py b/src/becwright/cli.py
index 2be2e65..359d2c3 100644
--- a/src/becwright/cli.py
+++ b/src/becwright/cli.py
@@ -417,10 +417,13 @@ def _read_claude_md(root: Path) -> str | None:
 
 # A line cap tied to *files* (not functions — that needs an AST): "files < 800
 # lines" or "800 lines per file", EN/ES. The file/module anchor avoids mapping a
-# "functions < 50 lines" rule, which becwright cannot enforce.
+# "functions < 50 lines" rule, which becwright cannot enforce. The gap between the
+# number and the file word excludes commas and digits so a match cannot bridge
+# across a clause boundary — e.g. "~50 lines per function, ~800 per file" must not
+# read the function's 50 as the file cap just because "file" appears later.
 _FILE_LINE_CAP = re.compile(
-    r"(?:files?|archivos?|modules?|m[óo]dulos?)\b[^.\n]{0,40}?(\d{2,4})\s*(?:lines?|l[ií]neas?)"
-    r"|(\d{2,4})\s*(?:lines?|l[ií]neas?)\b[^.\n]{0,25}?(?:per\s+|por\s+)?(?:files?|archivos?|modules?|m[óo]dulos?)",
+    r"(?:files?|archivos?|modules?|m[óo]dulos?)\b[^.,\n\d]{0,40}?(\d{2,4})\s*(?:lines?|l[ií]neas?)"
+    r"|(\d{2,4})\s*(?:lines?|l[ií]neas?)\b[^.,\n\d]{0,25}?(?:per\s+|por\s+)?(?:files?|archivos?|modules?|m[óo]dulos?)",
     re.IGNORECASE,
 )
 
diff --git a/tests/test_init.py b/tests/test_init.py
index 85f7ee9..3196f5e 100644
--- a/tests/test_init.py
+++ b/tests/test_init.py
@@ -320,6 +320,16 @@ def test_max_lines_cap_ignores_function_length():
     assert cli._max_lines_cap("Functions must be under 50 lines.") is None
 
 
+def test_max_lines_cap_does_not_bridge_function_cap_to_file_word():
+    # Real CLAUDE.md phrasing (bot-telegram field test): a per-function number and a
+    # per-file number in one clause, comma-joined. The function number (50) must NOT
+    # be captured just because "archivo"/"file" appears later past the comma. The file
+    # number (800) is elliptical (no "líneas" word of its own), so becwright declines
+    # rather than guessing wrong — an ambiguous soft guideline derives no cap.
+    assert cli._max_lines_cap("~50 líneas por función, ~800 por archivo") is None
+    assert cli._max_lines_cap("~50 lines per function, ~800 per file") is None
+
+
 def test_max_lines_cap_out_of_range():
     assert cli._max_lines_cap("keep files under 40 lines") is None      # below 50
     assert cli._max_lines_cap("files must not exceed 9000 lines") is None  # above 5000