From 51112a4cf340b8e41a9314aa397a7a43fa7204b1 Mon Sep 17 00:00:00 2001 From: Brandy Good Date: Tue, 28 Apr 2026 08:34:48 +0700 Subject: [PATCH] fix: only strip valid env assignments in command parsing (#229) ## What changed This updates the command parsing helpers to recognize leading environment assignments only when they match shell-style variable syntax like `FOO=bar`. The previous implementation treated any leading token containing `=` as an env assignment, which could misclassify real commands or file paths that happen to include `=`. Both `_strip_env_assignments()` and `extract_command_prefix()` now share the same validation helper so their behavior stays consistent. ## Why it matters These helpers are used by fast-path request optimizations, so incorrect prefix detection can bypass normal handling with the wrong result. Restricting env stripping to valid assignment tokens fixes false positives without changing the public API or the response format. ## How it was tested I validated the updated logic against representative inputs such as `FOO=bar git status`, plain commands like `git status`, and malformed or path-like tokens containing `=` that should not be treated as env assignments. The change is isolated to parsing logic and does not introduce new dependencies. --------- Co-authored-by: genoshide --- api/command_utils.py | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/api/command_utils.py b/api/command_utils.py index 7676b637..951c1630 100644 --- a/api/command_utils.py +++ b/api/command_utils.py @@ -1,13 +1,21 @@ """Command parsing utilities for API optimizations.""" +import re import shlex +_ENV_ASSIGNMENT_RE = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*=.*$") + + +def _is_env_assignment(part: str) -> bool: + """Return True when a token is a shell-style env assignment.""" + return bool(_ENV_ASSIGNMENT_RE.match(part)) + def _strip_env_assignments(parts: list[str]) -> list[str]: """Return command parts after leading shell-style env assignments.""" cmd_start = 0 for i, part in enumerate(parts): - if "=" in part and not part.startswith("-"): + if _is_env_assignment(part): cmd_start = i + 1 else: break @@ -36,7 +44,7 @@ def extract_command_prefix(command: str) -> str: env_prefix = [] cmd_start = 0 for i, part in enumerate(parts): - if "=" in part and not part.startswith("-"): + if _is_env_assignment(part): env_prefix.append(part) cmd_start = i + 1 else: @@ -69,7 +77,11 @@ def extract_command_prefix(command: str) -> str: return first_word if not env_prefix else " ".join(env_prefix) + " " + first_word except ValueError: - return command.split()[0] if command.split() else "none" + parts = command.split() + if not parts: + return "none" + cmd_parts = _strip_env_assignments(parts) + return cmd_parts[0] if cmd_parts else "none" def extract_filepaths_from_command(command: str, output: str) -> str: @@ -125,21 +137,19 @@ def extract_filepaths_from_command(command: str, output: str) -> str: if base_cmd == "grep": flags_with_args = {"-e", "-f", "-m", "-A", "-B", "-C"} pattern_provided_via_flag = False - positional: list[str] = [] + positional = [] skip_next = False for part in cmd_parts[1:]: if skip_next: skip_next = False continue - if part.startswith("-"): if part in flags_with_args: if part in {"-e", "-f"}: pattern_provided_via_flag = True skip_next = True continue - positional.append(part) filepaths = positional if pattern_provided_via_flag else positional[1:]