From 09a4e34eec470b7ad90d03ee279f71e1089520b2 Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Wed, 4 Feb 2026 02:48:31 +0000
Subject: [PATCH] perf: Release lock before GC in ParakeetManager

Releases the thread lock before calling `gc.collect()` in `_unload_model`.
This prevents the garbage collector (which is stop-the-world) from
blocking other threads (like `transcribe`) that are waiting to acquire
the lock to reload the model. While GC still pauses execution, releasing
the lock allows the `transcribe` thread to proceed as soon as the GIL
allows (potentially loading the new model in parallel with GC if C++
extensions release GIL), rather than being serialized behind the entire
GC operation.

Fixes a discrepancy where the code did not match the documented behavior.

Co-authored-by: Whamp <1115485+Whamp@users.noreply.github.com>
---
 .jules/bolt.md                | 4 ++++
 src/chirp/parakeet_manager.py | 6 +++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/.jules/bolt.md b/.jules/bolt.md
index 96ecba4..efe25c0 100644
--- a/.jules/bolt.md
+++ b/.jules/bolt.md
@@ -1,3 +1,7 @@
 ## 2024-02-18 - Pre-scaled Audio Feedback
 **Learning:** AudioFeedback volume scaling was applied during every playback, causing unnecessary numpy overhead and latency.
 **Action:** Pre-calculate scaled audio during `_load_and_cache` to minimize `_play_cached` latency (from ~1ms to ~0.04ms).
+
+## 2025-05-18 - Unlocked Garbage Collection
+**Learning:** `ParakeetManager` held the model lock during `gc.collect()`, forcing concurrent `transcribe` requests (which require the lock) to wait for full GC completion before they could even *start* reloading the model.
+**Action:** Release the lock before calling `gc.collect()`. This allows `transcribe` to acquire the lock and begin `load_model` (which releases GIL for C++ ops) in parallel with the garbage collection of the old model.
diff --git a/src/chirp/parakeet_manager.py b/src/chirp/parakeet_manager.py
index 54667ef..2cc1440 100644
--- a/src/chirp/parakeet_manager.py
+++ b/src/chirp/parakeet_manager.py
@@ -65,11 +65,15 @@ def _monitor_loop(self) -> None:
                 self._unload_model()
 
     def _unload_model(self) -> None:
+        should_collect = False
         with self._lock:
             if self._model is not None and (time.time() - self._last_access > self._timeout):
                 self._logger.info("Unloading Parakeet model to free memory.")
                 self._model = None
-                gc.collect()
+                should_collect = True
+
+        if should_collect:
+            gc.collect()
 
     def ensure_loaded(self):
         with self._lock: