diff --git a/action.yml b/action.yml
index 9fc00f0..2ce655e 100644
--- a/action.yml
+++ b/action.yml
@@ -75,7 +75,7 @@ inputs:
     description: "AI Model - defaults to GPT-5.2 or Sonnet 4.5 based on API key"
     required: false
   review_model:
-    description: "AI Model for PR reviews (optional, defaults to model)"
+    description: "AI Model for PR reviews (optional, defaults to gpt-5.2-codex)"
     required: false
   first_issue_response:
     description: "Example response to a new issue"
diff --git a/actions/update_file_headers.py b/actions/update_file_headers.py
index 4806977..467fd66 100644
--- a/actions/update_file_headers.py
+++ b/actions/update_file_headers.py
@@ -192,7 +192,7 @@ def main(*args, **kwargs):
     else:
         return
 
-    # Update any year range to current year (handles both - and – dashes)
+    # Update any year range to current year (handles both - and en-dash)
     header = re.sub(r"(\d{4}[–-])\d{4}", rf"\g<1>{current_year}", header)
 
     directory = Path.cwd()
diff --git a/actions/utils/openai_utils.py b/actions/utils/openai_utils.py
index edcdb40..5bb3294 100644
--- a/actions/utils/openai_utils.py
+++ b/actions/utils/openai_utils.py
@@ -20,6 +20,7 @@ MAX_PROMPT_CHARS = round(128000 * 3.3 * 0.5)  # Max characters for prompt (50% o
 # Default models (single source of truth)
 OPENAI_MODEL_DEFAULT = "gpt-5.2-2025-12-11"
 ANTHROPIC_MODEL_DEFAULT = "claude-sonnet-4-5-20250929"
+PR_REVIEW_MODEL_DEFAULT = "gpt-5.2-codex"
 
 MODEL_COSTS = {  # (input, output) per 1M tokens
     # OpenAI models
@@ -27,6 +28,7 @@ MODEL_COSTS = {  # (input, output) per 1M tokens
     "gpt-5.1-codex": (1.25, 10.00),
     "gpt-5.1-2025-11-13": (1.25, 10.00),
     "gpt-5.2-2025-12-11": (1.75, 14.00),
+    "gpt-5.2-codex": (1.75, 14.00),
     "gpt-5-nano-2025-08-07": (0.05, 0.40),
     "gpt-5-mini-2025-08-07": (0.25, 2.00),
     # Anthropic Claude 4.5 models
@@ -150,7 +152,7 @@ def _get_default_model() -> str:
 
 def get_review_model() -> str:
     """Get model for PR reviews, using REVIEW_MODEL if set, otherwise default model."""
-    return REVIEW_MODEL or _get_default_model()
+    return REVIEW_MODEL or PR_REVIEW_MODEL_DEFAULT
 
 
 def get_response(
diff --git a/tests/test_openai_utils.py b/tests/test_openai_utils.py
index 2e9b3ad..dc85ce6 100644
--- a/tests/test_openai_utils.py
+++ b/tests/test_openai_utils.py
@@ -2,7 +2,13 @@
 
 from unittest.mock import MagicMock, patch
 
-from actions.utils.openai_utils import _is_anthropic_model, get_response, get_review_model, remove_outer_codeblocks
+from actions.utils.openai_utils import (
+    PR_REVIEW_MODEL_DEFAULT,
+    _is_anthropic_model,
+    get_response,
+    get_review_model,
+    remove_outer_codeblocks,
+)
 
 
 def test_is_anthropic_model():
@@ -41,8 +47,7 @@ def test_get_review_model_override():
 def test_get_review_model_fallback():
     """Test review model fallback to default model."""
     with patch("actions.utils.openai_utils.REVIEW_MODEL", None):
-        with patch("actions.utils.openai_utils.MODEL", "gpt-5.2-2025-12-11"):
-            assert get_review_model() == "gpt-5.2-2025-12-11"
+        assert get_review_model() == PR_REVIEW_MODEL_DEFAULT
 
 
 @patch("requests.post")