Providers: omit temperature for OpenAI reasoning models

* fix: omit temperature for OpenAI reasoning models (o1/o3/o4/gpt-5)

These models only accept the default temperature; sending any explicit
value (even 0.0) returns HTTP 400 "Only the default (1) value is
supported". This broke two paths:

- Endpoint probing in _probe_single_model hardcodes temperature: 0.0, so
  a perfectly valid o3/gpt-5 endpoint is reported as failing in the
  Model Endpoints health check.
- Chat/stream payloads send temperature unconditionally, so a non-default
  temperature preset 400s on these models.

The code already special-cases the same model family for
max_completion_tokens, so this adds a sibling _restricts_temperature()
helper and omits the field for those models, letting the API use its
required default. gpt-4.5 is intentionally excluded (not a reasoning
model; accepts temperature normally).

Adds tests/test_llm_core_temperature.py covering the predicate and the
synchronous payload builder.

* fix: also omit temperature for reasoning models on the direct-POST paths

The first commit only covered llm_call/llm_call_async/stream_llm and the
endpoint probe. Email auto-summary, urgency-less spam classification, the
email reply-summary endpoint, and gallery vision tagging build their
OpenAI payloads inline and POST them directly (requests/httpx), bypassing
llm_core — so a reasoning model configured there would still 400 on the
temperature field. These sites already branch on _uses_max_completion_tokens,
so they're the same class; added the matching _restricts_temperature guard.

gallery_routes also gains the max_completion_tokens branch it was missing,
so gpt-5 vision tagging works end to end.

Note: email_pollers urgency scoring goes through llm_call_async and was
already covered.

tests/test_llm_core_temperature.py

@@ -0,0 +1,68 @@
+"""Regression tests: OpenAI reasoning models reject a non-default temperature.
+
+o1/o3/o4/gpt-5 only accept the default temperature (1); sending an explicit
+value — even 0.0 — returns HTTP 400 "Only the default (1) value is supported".
+The OpenAI-compatible payload builders must omit the temperature field for these
+models so chat (with a non-default preset) and endpoint probing don't break.
+"""
+import httpx
+import pytest
+
+from src import llm_core
+
+
+@pytest.mark.parametrize(
+    "model",
+    ["o1", "o1-mini", "o3", "o3-mini", "o4-mini", "gpt-5", "gpt-5-mini",
+     "openrouter/openai/o3-mini", "OpenAI/GPT-5"],
+)
+def test_reasoning_models_restrict_temperature(model):
+    assert llm_core._restricts_temperature(model) is True
+
+
+@pytest.mark.parametrize(
+    "model",
+    ["gpt-4o", "gpt-4.1", "gpt-3.5-turbo", "gpt-4.5-preview",
+     "claude-3-5-sonnet", "llama3.1", "", None],
+)
+def test_normal_models_allow_temperature(model):
+    assert llm_core._restricts_temperature(model) is False
+
+
+def _capture_openai_payload(monkeypatch, model, temperature):
+    """Run a synchronous OpenAI-compatible call and return the posted JSON body."""
+    llm_core._response_cache.clear()
+    seen = {}
+
+    def fake_post(url, headers=None, json=None, timeout=None):
+        seen["json"] = json
+        request = httpx.Request("POST", url)
+        return httpx.Response(
+            200,
+            request=request,
+            json={"choices": [{"message": {"content": "OK"}}]},
+        )
+
+    monkeypatch.setattr(llm_core.httpx, "post", fake_post)
+    result = llm_core.llm_call(
+        "https://api.openai.com/v1/chat/completions",
+        model,
+        [{"role": "user", "content": "Say OK"}],
+        temperature=temperature,
+        max_tokens=5,
+    )
+    assert result == "OK"
+    return seen["json"]
+
+
+def test_reasoning_model_payload_omits_temperature(monkeypatch):
+    payload = _capture_openai_payload(monkeypatch, "o3-mini", 0.0)
+    assert "temperature" not in payload
+    # Reasoning models also use max_completion_tokens, which must survive.
+    assert payload["max_completion_tokens"] == 5
+
+
+def test_normal_model_payload_keeps_temperature(monkeypatch):
+    payload = _capture_openai_payload(monkeypatch, "gpt-4o", 0.2)
+    assert payload["temperature"] == 0.2
+    assert payload["max_tokens"] == 5