Add support for GPT-5.2

DOCKER.md

@@ -22,7 +22,7 @@
 Set options in `.env` or pass environment variables:
 - `PORT`: Container listening port (default 8000)
 - `VERBOSE`: `true|false` to enable request/stream logs
-- `CHATGPT_LOCAL_REASONING_EFFORT`: minimal|low|medium|high
+- `CHATGPT_LOCAL_REASONING_EFFORT`: minimal|low|medium|high|xhigh
 - `CHATGPT_LOCAL_REASONING_SUMMARY`: auto|concise|detailed|none
 - `CHATGPT_LOCAL_REASONING_COMPAT`: legacy|o3|think-tags|current
 - `CHATGPT_LOCAL_DEBUG_MODEL`: force model override (e.g., `gpt-5`)

README.md

@@ -115,6 +115,7 @@ curl http://127.0.0.1:8000/v1/chat/completions \
 # Supported models
 - `gpt-5`
 - `gpt-5.1`
+- `gpt-5.2`
 - `gpt-5-codex`
 - `gpt-5.1-codex`
 - `gpt-5.1-codex-max`
@@ -126,7 +127,8 @@ curl http://127.0.0.1:8000/v1/chat/completions \
 ### Thinking effort
 
 - `--reasoning-effort` (choice of 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`. The `gpt-5.1` family (including codex) supports `low`, `medium`, and `high` while `gpt-5.1-codex-max` adds `xhigh`; neither offers a `minimal` variant.
+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`. `gpt-5.2` supports `low`, `medium`, `high`, and `xhigh`. 
 
 ### Thinking summaries
 
@@ -159,7 +161,7 @@ You can enable it by starting the server with this parameter, which will allow O
 If your preferred app doesn’t support selecting reasoning effort, or you just want a simpler approach, this parameter exposes each reasoning level as a separate, queryable model. Each reasoning level also appears individually under ⁠/v1/models, so model pickers in your favorite chat apps will list all reasoning options as distinct models you can switch between.
 
 ## Notes
-If you wish to have the fastest responses, I'd recommend setting `--reasoning-effort` to minimal, and `--reasoning-summary` to none. <br>
+If you wish to have the fastest responses, I'd recommend setting `--reasoning-effort` to low, and `--reasoning-summary` to none. <br>
 All parameters and choices can be seen by sending `python chatmock.py serve --h`<br>
 The context size of this route is also larger than what you get access to in the regular ChatGPT app.<br>
 
@@ -172,4 +174,3 @@ When the model returns a thinking summary, the model will send back thinking tag
 
 
 
-

chatmock/cli.py

@@ -335,7 +335,7 @@ def main() -> None:
         action="store_true",
         default=(os.getenv("CHATGPT_LOCAL_EXPOSE_REASONING_MODELS") or "").strip().lower() in ("1", "true", "yes", "on"),
         help=(
-            "Expose gpt-5 reasoning effort variants (minimal|low|medium|high|xhigh where supported) "
+            "Expose GPT-5 family reasoning effort variants (minimal|low|medium|high|xhigh where supported) "
             "as separate models from /v1/models. This allows choosing effort via model selection in compatible UIs."
         ),
     )

chatmock/reasoning.py

@@ -11,6 +11,8 @@ def allowed_efforts_for_model(model: str | None) -> Set[str]:
     if not base:
         return DEFAULT_REASONING_EFFORTS
     normalized = base.split(":", 1)[0]
+    if normalized.startswith("gpt-5.2"):
+        return {"none", "low", "medium", "high", "xhigh"}
     if normalized.startswith("gpt-5.1-codex-max"):
         return {"low", "medium", "high", "xhigh"}
     if normalized.startswith("gpt-5.1"):

chatmock/routes_ollama.py

@@ -96,6 +96,7 @@ def ollama_tags() -> Response:
     model_ids = [
         "gpt-5",
         "gpt-5.1",
+        "gpt-5.2",
         "gpt-5-codex",
         "gpt-5.1-codex",
         "gpt-5.1-codex-max",
@@ -112,6 +113,11 @@ def ollama_tags() -> Response:
                 "gpt-5.1-high",
                 "gpt-5.1-medium",
                 "gpt-5.1-low",
+                "gpt-5.2-xhigh",
+                "gpt-5.2-high",
+                "gpt-5.2-medium",
+                "gpt-5.2-low",
+                "gpt-5.2-none",
                 "gpt-5-codex-high",
                 "gpt-5-codex-medium",
                 "gpt-5-codex-low",

chatmock/routes_openai.py

@@ -534,6 +534,7 @@ def list_models() -> Response:
     model_groups = [
         ("gpt-5", ["high", "medium", "low", "minimal"]),
         ("gpt-5.1", ["high", "medium", "low"]),
+        ("gpt-5.2", ["xhigh", "high", "medium", "low", "none"]),
         ("gpt-5-codex", ["high", "medium", "low"]),
         ("gpt-5.1-codex", ["high", "medium", "low"]),
         ("gpt-5.1-codex-max", ["xhigh", "high", "medium", "low"]),

chatmock/upstream.py

@@ -42,6 +42,9 @@ def normalize_model_name(name: str | None, debug_model: str | None = None) -> st
         "gpt-5-latest": "gpt-5",
         "gpt-5": "gpt-5",
         "gpt-5.1": "gpt-5.1",
+        "gpt5.2": "gpt-5.2",
+        "gpt-5.2": "gpt-5.2",
+        "gpt-5.2-latest": "gpt-5.2",
         "gpt5-codex": "gpt-5-codex",
         "gpt-5-codex": "gpt-5-codex",
         "gpt-5-codex-latest": "gpt-5-codex",