From f1dc9f080745e0aa6601f380590163510f8e0495 Mon Sep 17 00:00:00 2001 From: "google-labs-jules[bot]" <161369871+google-labs-jules[bot]@users.noreply.github.com> Date: Thu, 14 May 2026 17:54:24 +0000 Subject: [PATCH 1/3] perf: optimize hot paths in file watcher - Replaced `getattr(event, 'event_type')` with direct attribute access `event.event_type`. - Pre-computed `_abs_base_path` and `_base_prefix` string lengths during initialization to avoid repeated `len()` calls in the fast-path string slicing. - Hoisted loop-invariant `match = regex.match` method lookups outside of iterative paths. - Removed flawed `self.current_process is process` guard in the `process.wait()` evaluation block, which could cause process termination logs to go dead if a rapid reload overwrote the class property before the previous wait block completed. Co-authored-by: shenald-dev <245350826+shenald-dev@users.noreply.github.com> --- .jules/bolt.md | 7 +++++++ pyproject.toml | 2 +- src/echo/watcher.py | 44 +++++++++++++++++++++++++++----------------- 3 files changed, 35 insertions(+), 18 deletions(-) diff --git a/.jules/bolt.md b/.jules/bolt.md index b1fe398..8ec6823 100644 --- a/.jules/bolt.md +++ b/.jules/bolt.md @@ -165,3 +165,10 @@ Acquiring a thread lock (`self.timer_lock`) on every file system event just to u Action: Prefer direct attribute access for guaranteed attributes (`self.is_shutting_down`). Use double-checked locking when spawning background threads (`if thread is None: with lock: if thread is None: start_thread()`) to avoid acquiring locks on every event, and update thread-safe variables like `time.monotonic()` outside the lock. +## 2026-05-14 — Avoid getattr and redundant evaluations in hot paths + +Learning: +Inside the file watcher's `watchdog` event handler, `getattr(event, 'event_type', '')` and `getattr(event, 'src_path', None)` introduce unnecessary `getattr` function call overhead when `event_type` and `src_path` are guaranteed to be present on all watchdog events. Additionally, computing `len(self._abs_base_path)` on every match, checking `if match:` on every iteration before evaluating the regex, and using `self.current_process is process` guards around subprocess return codes introduce latency and bugs. + +Action: +Prefer direct attribute access (`event.event_type`, `event.src_path`) over `getattr`. Pre-compute prefix lengths during class initialization. Hoist loop-invariant method lookups (`match = regex.match`) outside of iterations. Remove `self.current_process is process` guards when evaluating subprocess wait results, as the reference can be overwritten during a rapid reload. diff --git a/pyproject.toml b/pyproject.toml index 395384d..ad48d11 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "echo-watcher" -version = "0.1.25" +version = "0.1.26" description = "📡 Lightweight file watcher. Trigger commands on changes. <5MB RAM, single binary." authors = [ { name = "shenald-dev", email = "bot@shenald.dev" } diff --git a/src/echo/watcher.py b/src/echo/watcher.py index b87c065..bca2c83 100644 --- a/src/echo/watcher.py +++ b/src/echo/watcher.py @@ -22,6 +22,8 @@ def __init__(self, command: str, base_path: str = ".", ignore_patterns: list[str self.base_path = base_path self._abs_base_path = os.path.join(os.path.abspath(base_path), '') self._base_prefix = os.path.join(self.base_path, '') + self._abs_base_path_len = len(self._abs_base_path) + self._base_prefix_len = len(self._base_prefix) # Default ignore patterns default_ignores = [".git", "__pycache__", ".pytest_cache", ".ruff_cache", "node_modules", ".venv", "venv"] @@ -164,22 +166,24 @@ def _run_command(self, event_path): with self.process_lock: if self.is_shutting_down: return + # Do not guard with `self.current_process is process` + # because self.current_process is reassigned on reload - if getattr(process, '_echo_terminated', False): # SIGTERM or Windows termination - console.print("[yellow]✔ Command terminated by reload.[/yellow]") + if getattr(process, '_echo_terminated', False): # SIGTERM or Windows termination + console.print("[yellow]✔ Command terminated by reload.[/yellow]") + else: + if process.returncode == 0: + console.print("[green]✔ Command executed successfully.[/green]") else: - if process.returncode == 0: - console.print("[green]✔ Command executed successfully.[/green]") - else: - console.print(f"[red]✖ Command failed with exit code {process.returncode}.[/red]") + console.print(f"[red]✖ Command failed with exit code {process.returncode}.[/red]") except Exception as e: console.print(f"[bold red]Error executing command: {escape(str(e))}[/bold red]") def _is_ignored_impl(self, path: str) -> bool: if path.startswith(self._abs_base_path): - path = path[len(self._abs_base_path):] + path = path[self._abs_base_path_len:] elif path.startswith(self._base_prefix): - path = path[len(self._base_prefix):] + path = path[self._base_prefix_len:] elif path == self.base_path or path == self._abs_base_path.rstrip(os.sep): path = "." elif self.base_path == "." and not os.path.isabs(path) and not path.startswith(".."): @@ -210,13 +214,19 @@ def _is_ignored_impl(self, path: str) -> bool: # Prefix for parts[0] is already evaluated via earlier exact match `isdisjoint()` # and wildcard matching, so we start accumulating from the second part. - match = self.compound_wildcard_regex.match if self.compound_wildcard_regex else None - for part in parts[1:]: - prefix = f"{prefix}/{part}" - if prefix in self.compound_exact_ignores: - return True - if match and match(prefix): - return True + if self.compound_wildcard_regex: + match = self.compound_wildcard_regex.match + for part in parts[1:]: + prefix = f"{prefix}/{part}" + if prefix in self.compound_exact_ignores: + return True + if match(prefix): + return True + else: + for part in parts[1:]: + prefix = f"{prefix}/{part}" + if prefix in self.compound_exact_ignores: + return True return False @@ -228,11 +238,11 @@ def on_any_event(self, event): return # Ignore read-only events to prevent redundant executions - if getattr(event, 'event_type', '') in ('opened', 'closed_no_write'): + if event.event_type in ('opened', 'closed_no_write'): return # Fast-path ignore filter to prevent infinite loops from test/build artifacts - event_path = getattr(event, 'src_path', None) + event_path = event.src_path is_src_ignored = event_path and self._is_ignored(event_path) dest_path = getattr(event, 'dest_path', None) From 57e43865d37b12792e1dc47a33a5defec05aa6d7 Mon Sep 17 00:00:00 2001 From: "google-labs-jules[bot]" <161369871+google-labs-jules[bot]@users.noreply.github.com> Date: Wed, 20 May 2026 07:28:07 +0000 Subject: [PATCH 2/3] Merge main to fix conflicts Co-authored-by: shenald-dev <245350826+shenald-dev@users.noreply.github.com> --- .jules/bolt.md | 8 ++++++++ .jules/warden.md | 8 ++++++++ CHANGELOG.md | 5 +++++ 3 files changed, 21 insertions(+) diff --git a/.jules/bolt.md b/.jules/bolt.md index 8ec6823..ce89f46 100644 --- a/.jules/bolt.md +++ b/.jules/bolt.md @@ -172,3 +172,11 @@ Inside the file watcher's `watchdog` event handler, `getattr(event, 'event_type' Action: Prefer direct attribute access (`event.event_type`, `event.src_path`) over `getattr`. Pre-compute prefix lengths during class initialization. Hoist loop-invariant method lookups (`match = regex.match`) outside of iterations. Remove `self.current_process is process` guards when evaluating subprocess wait results, as the reference can be overwritten during a rapid reload. + +## 2026-05-16 — Generator Expression Overhead in Hot Paths + +Learning: +In high-frequency Python hot paths (like checking path parts against a regex), using `any()` with a generator expression (e.g., `any(match(p) for p in parts)`) introduces generator overhead that makes it slower than a simple, explicit `for` loop. Additionally, redundant property accesses (`getattr`) and redundant loop-invariant truthiness checks (`if self.compound_wildcard_regex:`) inside loops cause measurable performance regressions. + +Action: +Prefer explicit `for` loops with early returns over `any()` generators in hot paths. Lift loop-invariant checks and expensive builtins (like `len()`) outside of tight loops. Use direct attribute access over `getattr` when the attribute's existence is guaranteed. diff --git a/.jules/warden.md b/.jules/warden.md index 774d07b..6be880c 100644 --- a/.jules/warden.md +++ b/.jules/warden.md @@ -192,3 +192,11 @@ Observed the preceding agent optimized the exact ignore pattern matching by spli Alignment / Deferred: Version bumped to `0.1.25` as a patch release reflecting the performance optimization. Updated CHANGELOG.md. + +## 2026-05-13 — Assessment & Lifecycle + +Observation / Pruned: +Observed the preceding agent optimized event loop thread lock contention by preferring direct attribute access, using double-checked locking for thread spawning, and moving thread-safe variable updates outside the lock. I verified this via the test suite and confirmed structural soundness. Static analysis tools reported no dead code or linting issues. + +Alignment / Deferred: +Version bumped to `0.1.26` as a patch release reflecting the performance optimization. Updated CHANGELOG.md. diff --git a/CHANGELOG.md b/CHANGELOG.md index 4f0e66d..b5ad992 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,4 +1,9 @@ # Changelog +## [0.1.26] - 2026-05-13 + +### Changed +* **[Performance]:** Optimized event loop lock contention by implementing double-checked locking for debounce thread spawning and moving non-critical state assignments outside the thread lock, reducing overhead in high-frequency event loops. + ## [0.1.25] - 2026-05-08 ### Changed From 061beb08725d0275a9604280a81cb1c81c429ee8 Mon Sep 17 00:00:00 2001 From: "google-labs-jules[bot]" <161369871+google-labs-jules[bot]@users.noreply.github.com> Date: Thu, 21 May 2026 13:57:57 +0000 Subject: [PATCH 3/3] Merge main to fix conflicts Co-authored-by: shenald-dev <245350826+shenald-dev@users.noreply.github.com> --- .jules/bolt.md | 8 ++++++++ .jules/warden.md | 8 ++++++++ CHANGELOG.md | 5 +++++ pyproject.toml | 2 +- src/echo/watcher.py | 11 +++++------ 5 files changed, 27 insertions(+), 7 deletions(-) diff --git a/.jules/bolt.md b/.jules/bolt.md index ce89f46..5401302 100644 --- a/.jules/bolt.md +++ b/.jules/bolt.md @@ -180,3 +180,11 @@ In high-frequency Python hot paths (like checking path parts against a regex), u Action: Prefer explicit `for` loops with early returns over `any()` generators in hot paths. Lift loop-invariant checks and expensive builtins (like `len()`) outside of tight loops. Use direct attribute access over `getattr` when the attribute's existence is guaranteed. + +## 2026-05-20 — Generator Expression Overhead in Object Initialization + +Learning: +Using `any()` with a generator expression inside a list comprehension (e.g., `[p for p in patterns if not any(c in p for c in ('*', '?', '['))]`) creates significant generator evaluation overhead, which is magnified when iterating over items. While this was previously addressed in the hot path, it remained in the object initialization, causing minor startup latency. + +Action: +Prefer explicit logical string conditions (`if '*' not in p and '?' not in p and '[' not in p`) over `any()` generator expressions for simple string character checks to avoid generator creation overhead, even outside of hot paths. diff --git a/.jules/warden.md b/.jules/warden.md index 6be880c..61d9b1c 100644 --- a/.jules/warden.md +++ b/.jules/warden.md @@ -200,3 +200,11 @@ Observed the preceding agent optimized event loop thread lock contention by pref Alignment / Deferred: Version bumped to `0.1.26` as a patch release reflecting the performance optimization. Updated CHANGELOG.md. + +## 2026-05-21 — Assessment & Lifecycle + +Observation / Pruned: +Observed the preceding agent optimized event loop lock contention by streamlining logic and variable assignments around `debounce_worker` and `Timer` threads. Verified this logic handles multi-threaded execution properly and confirmed zero loss in structural soundness or logic through tests. Vulture confirmed the codebase remains at zero dead code. No further entropy pruning was required. + +Alignment / Deferred: +Version bumped to `0.1.27` as a patch release. No dependency adjustments or complex refactors were deferred. diff --git a/CHANGELOG.md b/CHANGELOG.md index b5ad992..1664507 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,4 +1,9 @@ # Changelog +## [0.1.27] - 2026-05-21 + +### Changed +* **[Performance]:** Assured the event loop lock contention optimizations, validating thread safety and structure without introducing new regressions. + ## [0.1.26] - 2026-05-13 ### Changed diff --git a/pyproject.toml b/pyproject.toml index ad48d11..cc02010 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "echo-watcher" -version = "0.1.26" +version = "0.1.27" description = "📡 Lightweight file watcher. Trigger commands on changes. <5MB RAM, single binary." authors = [ { name = "shenald-dev", email = "bot@shenald.dev" } diff --git a/src/echo/watcher.py b/src/echo/watcher.py index bca2c83..21fe4b8 100644 --- a/src/echo/watcher.py +++ b/src/echo/watcher.py @@ -32,8 +32,8 @@ def __init__(self, command: str, base_path: str = ".", ignore_patterns: list[str self.ignore_patterns = [p.replace('\\', '/').rstrip('/').removeprefix('./') for p in default_ignores] # Pre-compute exact vs wildcard patterns for faster matching - exact_ignores = [p for p in self.ignore_patterns if not any(c in p for c in ('*', '?', '['))] - wildcard_ignores = [p for p in self.ignore_patterns if any(c in p for c in ('*', '?', '['))] + exact_ignores = [p for p in self.ignore_patterns if '*' not in p and '?' not in p and '[' not in p] + wildcard_ignores = [p for p in self.ignore_patterns if '*' in p or '?' in p or '[' in p] self.simple_exact_ignores = frozenset(p for p in exact_ignores if '/' not in p) self.compound_exact_ignores = frozenset(p for p in exact_ignores if '/' in p) @@ -211,21 +211,20 @@ def _is_ignored_impl(self, path: str) -> bool: # Check for exact and wildcard ignore patterns matching cumulative prefix directories if self._has_compound_ignores and len(parts) > 1: prefix = parts[0] - # Prefix for parts[0] is already evaluated via earlier exact match `isdisjoint()` - # and wildcard matching, so we start accumulating from the second part. + compound_exact_ignores = self.compound_exact_ignores if self.compound_wildcard_regex: match = self.compound_wildcard_regex.match for part in parts[1:]: prefix = f"{prefix}/{part}" - if prefix in self.compound_exact_ignores: + if prefix in compound_exact_ignores: return True if match(prefix): return True else: for part in parts[1:]: prefix = f"{prefix}/{part}" - if prefix in self.compound_exact_ignores: + if prefix in compound_exact_ignores: return True return False