kaiyuan/chatgpt-on-wechat
1
0
Fork 0
mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-07-17 11:07:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor(edit): unify fuzzy uniqueness check with the fuzzy matcher

Browse Source 
The uniqueness guard counted occurrences via normalize_for_fuzzy_match,
while fuzzy_find_text located matches with a whitespace-flexible regex,
so the two could disagree. Extract the pattern builder as a single
source of truth (_build_fuzzy_pattern) and add count_matches, which
counts with the same exact-then-fuzzy strategy used to locate and
replace. This is the optional follow-up suggested in the review of #2942.

Adds regression tests for exact and fuzzy multi-match rejection.
This commit is contained in:
weijun-xia
2026-07-08 11:13:30 +08:00
parent ce09efe640
commit ed36ca99c0
4 changed files with 101 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
agent/tools/edit/edit.py
View File

@@ -13,7 +13,7 @@ from agent.tools.utils.diff import (
detect_line_ending,
normalize_to_lf,
restore_line_endings,
normalize_for_fuzzy_match,
count_matches,
fuzzy_find_text,
generate_diff_string
)
@@ -110,10 +110,10 @@ class Edit(BaseTool):
"The old text must match exactly including all whitespace and newlines."
)
# Calculate occurrence count (use fuzzy normalized content for consistency)
fuzzy_content = normalize_for_fuzzy_match(normalized_content)
fuzzy_old_text = normalize_for_fuzzy_match(normalized_old_text)
occurrences = fuzzy_content.count(fuzzy_old_text)
# Count occurrences with the same matcher used to locate and
# replace (fuzzy_find_text), so the uniqueness guard cannot
# disagree with what actually gets replaced.
occurrences = count_matches(normalized_content, normalized_old_text)
if occurrences > 1:
return ToolResult.fail(