From be5b60bddbcfc1f075a4eda7b9f46e8ae3ec5185 Mon Sep 17 00:00:00 2001
From: Michael Panchenko <michael.panchenko@oraios-ai.de>
Date: Thu, 14 May 2026 22:43:00 +0200
Subject: [PATCH] Make dotall optional in affected tools

---
 CHANGELOG.md                     |  8 ++++
 src/serena/project.py            | 16 +++++++-
 src/serena/tools/file_tools.py   | 65 ++++++++------------------------
 src/serena/tools/memory_tools.py | 11 +++++-
 src/serena/util/text_utils.py    | 17 +++++++--
 5 files changed, 60 insertions(+), 57 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 715a2c6f..3e05a886 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,6 +10,14 @@ Status of the `main` branch. Changes prior to the next official version change w
   - Modal markup cleanup: extract shared CSS classes (`.modal-info`, `.modal-hint`, `.modal-prompt`, `.modal-field`, `.modal-input`, `.modal-select`, `.modal-textarea`, `.modal-actions`, `.btn-secondary`) and remove duplicated inline styles from all seven modals. Inputs and textareas get an accent-colored focus ring; the modal backdrop has a subtle blur.
   - Add Language: replace the native `<select>` with a filterable combobox — type to filter, keyboard navigation (Up/Down/Enter/Esc), substring highlight, click-outside to close. The typed value is validated against the available languages list before submission.
 
+* Tools:
+  - `edit_memory`: New `dotall` parameter (default `False`) controlling whether ``.`` matches
+    newlines in regex mode. **Behavior change**: previously DOTALL was forced on; the new default
+    restricts ``.`` to a single line, which is safer for typical line-bounded memory edits and
+    avoids accidentally consuming large spans of content. Pass `dotall=True` for multi-line edits.
+  - `search_for_pattern`: New `dotall` parameter (default `True`, preserving existing behavior)
+    exposing the DOTALL flag, and the docstring was tightened.
+
 # v1.3.0 (2026-05-11)
 
 * General:
diff --git a/src/serena/project.py b/src/serena/project.py
index 21c5b3e1..72cc33c7 100644
--- a/src/serena/project.py
+++ b/src/serena/project.py
@@ -715,7 +715,14 @@ class MemoriesManager:
         return f"Memory renamed from {old_name} to {new_name}."
 
     def edit_memory(
-        self, name: str, needle: str, repl: str, mode: Literal["literal", "regex"], allow_multiple_occurrences: bool, is_tool_context: bool
+        self,
+        name: str,
+        needle: str,
+        repl: str,
+        mode: Literal["literal", "regex"],
+        allow_multiple_occurrences: bool,
+        is_tool_context: bool,
+        dotall: bool = True,
     ) -> str:
         """
         Edit a memory by replacing content matching a pattern.
@@ -725,6 +732,8 @@ class MemoriesManager:
         :param repl: the replacement string
         :param mode: "literal" or "regex"
         :param allow_multiple_occurrences:
+        :param is_tool_context: whether the call originates from a tool invocation (affects write-access checks)
+        :param dotall: whether to compile the regex with the DOTALL flag (``.`` matches newlines). Only relevant in regex mode.
         """
         name = self._prepare_name(name)
         self._check_not_ignored(name)
@@ -734,7 +743,7 @@ class MemoriesManager:
             raise FileNotFoundError(f"Memory {name} not found.")
         with open(memory_file_path, encoding=self._encoding) as f:
             original_content = f.read()
-        replacer = ContentReplacer(mode=mode, allow_multiple_occurrences=allow_multiple_occurrences)
+        replacer = ContentReplacer(mode=mode, allow_multiple_occurrences=allow_multiple_occurrences, dotall=dotall)
         updated_content = replacer.replace(original_content, needle, repl)
         with open(memory_file_path, "w", encoding=self._encoding) as f:
             f.write(updated_content)
@@ -1291,6 +1300,7 @@ class Project(ToStringMixin):
         context_lines_after: int = 0,
         paths_include_glob: str | None = None,
         paths_exclude_glob: str | None = None,
+        dotall: bool = True,
     ) -> list[MatchedConsecutiveLines]:
         """
         Search for a pattern across all (non-ignored) source files
@@ -1301,6 +1311,7 @@ class Project(ToStringMixin):
         :param context_lines_after: Number of lines of context to include after each match
         :param paths_include_glob: Glob pattern to filter which files to include in the search
         :param paths_exclude_glob: Glob pattern to filter which files to exclude from the search. Takes precedence over paths_include_glob.
+        :param dotall: Whether to compile the regex with the DOTALL flag (``.`` matches newlines).
         :return: List of matched consecutive lines with context
         """
         relative_file_paths = self.gather_source_files(relative_path=relative_path)
@@ -1313,6 +1324,7 @@ class Project(ToStringMixin):
             context_lines_after=context_lines_after,
             paths_include_glob=paths_include_glob,
             paths_exclude_glob=paths_exclude_glob,
+            dotall=dotall,
         )
 
     def retrieve_content_around_line(
diff --git a/src/serena/tools/file_tools.py b/src/serena/tools/file_tools.py
index c913ca60..83aa837e 100644
--- a/src/serena/tools/file_tools.py
+++ b/src/serena/tools/file_tools.py
@@ -332,59 +332,24 @@ class SearchForPatternTool(Tool):
         paths_exclude_glob: str = "",
         relative_path: str = "",
         restrict_search_to_code_files: bool = False,
+        dotall: bool = True,
         max_answer_chars: int = -1,
     ) -> str:
         """
-        Offers a flexible search for arbitrary patterns in the codebase, including the
-        possibility to search in non-code files.
-        Generally, symbolic operations like find_symbol or find_referencing_symbols
-        should be preferred if you know which symbols you are looking for.
+        Searches for a regex pattern across project files, returning whole matched lines (plus optional context).
+        Prefer `find_symbol`/`find_referencing_symbols` when looking for known symbols.
 
-        Pattern Matching Logic:
-            For each match, the returned result will contain the full lines where the
-            substring pattern is found, as well as optionally some lines before and after it. The pattern will be compiled with
-            DOTALL, meaning that the dot will match all characters including newlines.
-            This also means that it never makes sense to have .* at the beginning or end of the pattern,
-            but it may make sense to have it in the middle for complex patterns.
-            If a pattern matches multiple lines, all those lines will be part of the match.
-            Be careful to not use greedy quantifiers unnecessarily, it is usually better to use non-greedy quantifiers like .*? to avoid
-            matching too much content.
-
-        File Selection Logic:
-            The files in which the search is performed can be restricted very flexibly.
-            Using `restrict_search_to_code_files` is useful if you are only interested in code symbols (i.e., those
-            symbols that can be manipulated with symbolic tools like find_symbol).
-            You can also restrict the search to a specific file or directory,
-            and provide glob patterns to include or exclude certain files on top of that.
-            The globs are matched against relative file paths from the project root (not to the `relative_path` parameter that
-            is used to further restrict the search).
-            Smartly combining the various restrictions allows you to perform very targeted searches.
-
-        :param substring_pattern: Regular expression for a substring pattern to search for
-        :param context_lines_before: Number of lines of context to include before each match
-        :param context_lines_after: Number of lines of context to include after each match
-        :param paths_include_glob: optional glob pattern specifying files to include in the search.
-            Matches against relative file paths from the project root (e.g., "*.py", "src/**/*.ts").
-            Supports standard glob patterns (*, ?, [seq], **, etc.) and brace expansion {a,b,c}.
-            Only matches files, not directories. If left empty, all non-ignored files will be included.
-        :param paths_exclude_glob: optional glob pattern specifying files to exclude from the search.
-            Matches against relative file paths from the project root (e.g., "*test*", "**/*_generated.py").
-            Supports standard glob patterns (*, ?, [seq], **, etc.) and brace expansion {a,b,c}.
-            Takes precedence over paths_include_glob. Only matches files, not directories. If left empty, no files are excluded.
-        :param relative_path: only subpaths of this path (relative to the repo root) will be analyzed. If a path to a single
-            file is passed, only that will be searched. The path must exist, otherwise a `FileNotFoundError` is raised.
-        :param max_answer_chars: if the output is longer than this number of characters,
-            no content will be returned.
-            -1 means the default value from the config will be used.
-            Don't adjust unless there is really no other way to get the content
-            required for the task. Instead, if the output is too long, you should
-            make a stricter query.
-        :param restrict_search_to_code_files: whether to restrict the search to only those files where
-            analyzed code symbols can be found. Otherwise, will search all non-ignored files.
-            Set this to True if your search is only meant to discover code that can be manipulated with symbolic tools.
-            For example, for finding classes or methods from a name pattern.
-            Setting to False is a better choice if you also want to search in non-code files, like in html or yaml files,
-            which is why it is the default.
+        :param substring_pattern: regular expression to search for.
+        :param context_lines_before: number of context lines to include before each match.
+        :param context_lines_after: number of context lines to include after each match.
+        :param paths_include_glob: optional glob (relative to project root, e.g. ``"src/**/*.ts"``) restricting which files are searched.
+        :param paths_exclude_glob: optional glob to exclude files; takes precedence over `paths_include_glob`.
+        :param relative_path: restricts the search to this file or subdirectory of the project root. Must exist.
+        :param restrict_search_to_code_files: whether to search only files containing analyzable code symbols
+            (useful when looking for class/method definitions); otherwise also search non-code files.
+        :param dotall: whether to compile the regex with the DOTALL flag (``.`` matches newlines, enabling multi-line matches).
+        :param max_answer_chars: if the output exceeds this many characters, a progressively shortened summary is returned instead.
+            ``-1`` uses the configured default.
         :return: A mapping from file paths to matched consecutive lines (0-based line numbers).
         """
         relative_path = relative_path.strip()
@@ -403,6 +368,7 @@ class SearchForPatternTool(Tool):
                 context_lines_after=context_lines_after,
                 paths_include_glob=paths_include_glob.strip(),
                 paths_exclude_glob=paths_exclude_glob.strip(),
+                dotall=dotall,
             )
         else:
             if os.path.isfile(abs_path):
@@ -426,6 +392,7 @@ class SearchForPatternTool(Tool):
                 root_path=self.get_project_root(),
                 paths_include_glob=paths_include_glob,
                 paths_exclude_glob=paths_exclude_glob,
+                dotall=dotall,
             )
 
         # group matches by file
diff --git a/src/serena/tools/memory_tools.py b/src/serena/tools/memory_tools.py
index 0fd98ec4..8c2de38e 100644
--- a/src/serena/tools/memory_tools.py
+++ b/src/serena/tools/memory_tools.py
@@ -104,6 +104,7 @@ class EditMemoryTool(Tool, ToolMarkerCanEdit):
         repl: str,
         mode: Literal["literal", "regex"],
         allow_multiple_occurrences: bool = False,
+        dotall: bool = False,
     ) -> str:
         r"""
         Replace content matching a regular expression in a memory.
@@ -112,10 +113,16 @@ class EditMemoryTool(Tool, ToolMarkerCanEdit):
         :param needle: the string or regex pattern to search for. In regex mode, be careful to not replace too much!
             If `mode` is "literal", this string will be matched exactly.
             If `mode` is "regex", this string will be treated as a regular expression (syntax of Python's `re` module,
-            with flags DOTALL and MULTILINE enabled).
+            with the MULTILINE flag enabled and DOTALL controlled by the `dotall` parameter).
         :param repl: the replacement string (verbatim).
         :param mode: either "literal" or "regex", specifying how the `needle` parameter is to be interpreted.
         :param allow_multiple_occurrences: whether to allow matching and replacing multiple occurrences.
             If false and multiple occurrences are found, an error will be returned.
+        :param dotall: whether to compile the regex with the DOTALL flag, so that ``.`` matches newlines.
+            Only relevant in regex mode. Defaults to False, restricting ``.`` to a single line, which is the safer
+            choice for typical line-bounded memory edits and avoids accidentally consuming entire blocks of content.
+            Set to True deliberately when you intend a multi-line replacement (alternatively, use ``[\s\S]*?``).
         """
-        return self.memories_manager.edit_memory(memory_name, needle, repl, mode, allow_multiple_occurrences, is_tool_context=True)
+        return self.memories_manager.edit_memory(
+            memory_name, needle, repl, mode, allow_multiple_occurrences, is_tool_context=True, dotall=dotall
+        )
diff --git a/src/serena/util/text_utils.py b/src/serena/util/text_utils.py
index 523ba294..ddadf549 100644
--- a/src/serena/util/text_utils.py
+++ b/src/serena/util/text_utils.py
@@ -145,6 +145,7 @@ def search_text(
     context_lines_before: int = 0,
     context_lines_after: int = 0,
     is_glob: bool = False,
+    dotall: bool = True,
 ) -> list[MatchedConsecutiveLines]:
     """
     Search for a pattern in text content. Supports both regex and glob-like patterns.
@@ -159,6 +160,8 @@ def search_text(
     :param context_lines_after: Number of context lines to include after matches
     :param is_glob: If True, pattern is treated as a glob-like pattern (e.g., "*.py", "test_??.py")
              and will be converted to regex internally
+    :param dotall: Whether to compile the regex with the DOTALL flag (``.`` matches newlines).
+        Only takes effect when `allow_multiline_match` is True (the line-by-line branch never spans newlines).
 
     :return: List of `TextSearchMatch` objects
 
@@ -180,8 +183,8 @@ def search_text(
     if is_glob:
         pattern = glob_to_regex(pattern)
     if allow_multiline_match:
-        # For multiline matches, we need to use the DOTALL flag to make '.' match newlines
-        compiled_pattern = re.compile(pattern, re.DOTALL)
+        # For multiline matches, optionally use DOTALL so '.' matches newlines
+        compiled_pattern = re.compile(pattern, re.DOTALL if dotall else 0)
         # Search across the entire content as a single string
         for match in compiled_pattern.finditer(content):
             start_pos = match.start()
@@ -327,6 +330,7 @@ def search_files(
     context_lines_after: int = 0,
     paths_include_glob: str | None = None,
     paths_exclude_glob: str | None = None,
+    dotall: bool = True,
 ) -> list[MatchedConsecutiveLines]:
     """
     Search for a pattern in a list of files.
@@ -340,6 +344,7 @@ def search_files(
     :param context_lines_after: Number of context lines to include after matches
     :param paths_include_glob: Optional glob pattern to include files from the list
     :param paths_exclude_glob: Optional glob pattern to exclude files from the list
+    :param dotall: Whether to compile the regex with the DOTALL flag (``.`` matches newlines).
     :return: List of MatchedConsecutiveLines objects
     """
     # Pre-filter paths (done sequentially to avoid overhead)
@@ -375,6 +380,7 @@ def search_files(
                 allow_multiline_match=True,
                 context_lines_before=context_lines_before,
                 context_lines_after=context_lines_after,
+                dotall=dotall,
             )
             if len(search_results) > 0:
                 log.debug(f"Found {len(search_results)} matches in {path}")
@@ -430,16 +436,19 @@ class ContentReplacer:
     provides dual modes for maximum flexibility.
     """
 
-    def __init__(self, mode: Literal["literal", "regex"], allow_multiple_occurrences: bool):
+    def __init__(self, mode: Literal["literal", "regex"], allow_multiple_occurrences: bool, dotall: bool = True):
         """
 
         :param mode: the mode indicating whether to the needle in replacements corresponds to a regular expression
             (mode "regex") or to a literal string (mode "literal")
         :param allow_multiple_occurrences: whether it is allowed that the search expression matches multiple occurrences.
             If False, an error will be raised if more than one match is found.
+        :param dotall: whether to compile the regex with the DOTALL flag, which makes ``.`` match newlines.
+            Only relevant in regex mode. The MULTILINE flag is always enabled (so ``^`` and ``$`` match line boundaries).
         """
         self.mode = mode
         self.allow_multiple_occurrences = allow_multiple_occurrences
+        self.dotall = dotall
 
     @staticmethod
     def _create_replacement_function(regex_pattern: str, repl_template: str, regex_flags: int) -> Callable[[re.Match], str]:
@@ -505,7 +514,7 @@ class ContentReplacer:
         else:
             raise ValueError(f"Invalid mode: '{self.mode}', expected 'literal' or 'regex'.")
 
-        regex_flags = re.DOTALL | re.MULTILINE
+        regex_flags = re.MULTILINE | (re.DOTALL if self.dotall else 0)
 
         # create replacement function with validation and backreference handling
         repl_fn = self._create_replacement_function(regex, repl, regex_flags=regex_flags)