feat: Add GPT-5.4 mini. (#101)

* feat: Add gpt-5.4-mini.

This just adds gpt-5.4-mini at (low/med/high/xhigh) reasoning levels.

* Fix formatting in README for reasoning effort section

---------

Co-authored-by: Ra's al Ghul <ras@alghul.com>
Co-authored-by: Game_Time <108236317+RayBytes@users.noreply.github.com>

Author: 3 people

README.md

@@ -110,6 +110,7 @@ curl http://127.0.0.1:8000/v1/chat/completions \
 
 # Supported models
 - `gpt-5.4`
+- `gpt-5.4-mini`
 - `gpt-5.2`
 - `gpt-5.1`
 - `gpt-5`
@@ -127,7 +128,7 @@ curl http://127.0.0.1:8000/v1/chat/completions \
 
 - `--reasoning-effort` (choice of none,minimal,low,medium,high,xhigh)<br>
 GPT-5 has a configurable amount of "effort" it can put into thinking, which may cause it to take more time for a response to return, but may overall give a smarter answer. Applying this parameter after `serve` forces the server to use this reasoning effort by default, unless overrided by the API request with a different effort set. The default reasoning effort without setting this parameter is `medium`.<br>
-    The `gpt-5.1` family (including codex) supports `low`, `medium`, and `high` while `gpt-5.1-codex-max` adds `xhigh`. The `gpt-5.2` and `gpt-5.3` families (including codex) support `low`, `medium`, `high`, and `xhigh`. GPT-5.4 supports `none`, `low`, `medium`, `high`, and `xhigh`.
+    The `gpt-5.1` family (including codex) supports `low`, `medium`, and `high` while `gpt-5.1-codex-max` adds `xhigh`. The `gpt-5.2` and `gpt-5.3` families (including codex) support `low`, `medium`, `high`, and `xhigh`. `gpt-5.4` supports `none`, `low`, `medium`, `high`, and `xhigh`.
 
 ### Thinking summaries
 

chatmock/model_registry.py

@@ -47,6 +47,13 @@ class ModelSpec:
         allowed_efforts=frozenset(("none", "low", "medium", "high", "xhigh")),
         variant_efforts=("xhigh", "high", "medium", "low", "none"),
     ),
+    ModelSpec(
+        public_id="gpt-5.4-mini",
+        upstream_id="gpt-5.4-mini",
+        aliases=("gpt5.4-mini", "gpt-5.4-mini-latest"),
+        allowed_efforts=frozenset(("low", "medium", "high", "xhigh")),
+        variant_efforts=("xhigh", "high", "medium", "low"),
+    ),
     ModelSpec(
         public_id="gpt-5.3-codex",
         upstream_id="gpt-5.3-codex",

tests/test_models.py

@@ -9,22 +9,28 @@ class ModelRegistryTests(unittest.TestCase):
     def test_normalizes_aliases(self) -> None:
         self.assertEqual(normalize_model_name("gpt5"), "gpt-5")
         self.assertEqual(normalize_model_name("gpt5.4"), "gpt-5.4")
+        self.assertEqual(normalize_model_name("gpt5.4-mini"), "gpt-5.4-mini")
         self.assertEqual(normalize_model_name("codex"), "codex-mini-latest")
 
     def test_strips_reasoning_suffixes(self) -> None:
         self.assertEqual(normalize_model_name("gpt-5.4-high"), "gpt-5.4")
+        self.assertEqual(normalize_model_name("gpt-5.4-mini-high"), "gpt-5.4-mini")
         self.assertEqual(normalize_model_name("gpt-5.2_codemirror"), "gpt-5.2_codemirror")
         self.assertEqual(normalize_model_name("gpt-5.1-codex:max"), "gpt-5.1-codex:max")
         self.assertEqual(normalize_model_name("gpt-5.1-codex:high"), "gpt-5.1-codex")
 
     def test_allowed_efforts_follow_registry(self) -> None:
         self.assertEqual(allowed_efforts_for_model("gpt-5.4"), frozenset(("none", "low", "medium", "high", "xhigh")))
+        self.assertEqual(allowed_efforts_for_model("gpt-5.4-mini"), frozenset(("low", "medium", "high", "xhigh")))
         self.assertEqual(allowed_efforts_for_model("gpt-5.1-codex"), frozenset(("low", "medium", "high")))
 
     def test_public_models_include_variants(self) -> None:
         model_ids = list_public_models(expose_reasoning_models=True)
         self.assertIn("gpt-5.4", model_ids)
+        self.assertIn("gpt-5.4-mini", model_ids)
         self.assertIn("gpt-5.4-none", model_ids)
+        self.assertIn("gpt-5.4-mini-xhigh", model_ids)
+        self.assertNotIn("gpt-5.4-mini-none", model_ids)
         self.assertIn("gpt-5.1-codex-max-xhigh", model_ids)
         self.assertNotIn("codex-mini-high", model_ids)
 

tests/test_routes.py

@@ -33,13 +33,17 @@ def test_openai_models_list(self) -> None:
         response = self.client.get("/v1/models")
         body = response.get_json()
         self.assertEqual(response.status_code, 200)
-        self.assertIn("gpt-5.4", [item["id"] for item in body["data"]])
+        model_ids = [item["id"] for item in body["data"]]
+        self.assertIn("gpt-5.4", model_ids)
+        self.assertIn("gpt-5.4-mini", model_ids)
 
     def test_ollama_tags_list(self) -> None:
         response = self.client.get("/api/tags")
         body = response.get_json()
         self.assertEqual(response.status_code, 200)
-        self.assertIn("gpt-5.4", [item["name"] for item in body["models"]])
+        model_names = [item["name"] for item in body["models"]]
+        self.assertIn("gpt-5.4", model_names)
+        self.assertIn("gpt-5.4-mini", model_names)
 
     @patch("chatmock.routes_openai.start_upstream_request")
     def test_chat_completions(self, mock_start) -> None:
@@ -54,12 +58,12 @@ def test_chat_completions(self, mock_start) -> None:
         )
         response = self.client.post(
             "/v1/chat/completions",
-            json={"model": "gpt5.4", "messages": [{"role": "user", "content": "hi"}]},
+            json={"model": "gpt5.4-mini", "messages": [{"role": "user", "content": "hi"}]},
         )
         body = response.get_json()
         self.assertEqual(response.status_code, 200)
         self.assertEqual(body["choices"][0]["message"]["content"], "hello")
-        self.assertEqual(body["model"], "gpt5.4")
+        self.assertEqual(body["model"], "gpt5.4-mini")
 
     @patch("chatmock.routes_ollama.start_upstream_request")
     def test_ollama_chat(self, mock_start) -> None: