Let the gateway target non-OpenAI upstreams and allow client model passthrough

gateway_thinking_dialect overrides the URL-sniffed protocol dialect for a
reverse-proxied upstream (e.g. Ollama) whose URL carries no identifying
token; upstream_capabilities() uses the same effective dialect to stop
sending stream_options to upstreams that don't support it. gateway_allow_client_model
lets a client-requested model name through even with force-model on, for
an upstream that serves many models with no single stable alias.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XjW4qocnaJxhugUi5ca8Wo

tests/unit/services/openai_gateway/gateway.py

@@ -942,6 +942,107 @@ class FakeClientWithUsage_openai_gateway(FakeClient_openai_gateway):
         )
 
 
+def test_ollama_stream_does_not_send_stream_options(local_db, monkeypatch):
+    monkeypatch.setattr(gwmod.httpx, "AsyncClient", FakeClient_openai_gateway)
+    svc = GatewayService()
+    cfg = svc.effective_config()
+    cfg["gateway_upstream_url"] = "http://127.0.0.1:11434/api/chat"
+    rt = svc.runtime()
+    run_async(
+        rt.handle_chat(
+            {
+                "messages": [{"role": "user", "content": "hi"}],
+                "stream": True,
+                "stream_options": {"include_usage": True},
+            },
+            cfg,
+            ("guest", "ollama_stream_opts"),
+            "test",
+            "default",
+        )
+    )
+    upstream_payload = rt._client.calls[-1][1]
+    assert upstream_payload["stream"] is True
+    assert "stream_options" not in upstream_payload
+    assert upstream_payload["think"] is False
+
+
+def test_ollama_explicit_dialect_overrides_url(local_db, monkeypatch):
+    monkeypatch.setattr(gwmod.httpx, "AsyncClient", FakeClient_openai_gateway)
+    svc = GatewayService()
+    cfg = svc.effective_config()
+    cfg["gateway_upstream_url"] = "https://ai.example.com/v1/chat/completions"
+    cfg["gateway_thinking_dialect"] = "ollama"
+    rt = svc.runtime()
+    run_async(
+        rt.handle_chat(
+            {"messages": [{"role": "user", "content": "hi"}]},
+            cfg,
+            ("guest", "ollama_dialect_override"),
+            "test",
+            "default",
+        )
+    )
+    body = rt._client.calls[-1][1]
+    assert body["think"] is False
+    assert "thinking" not in body
+
+
+def test_client_model_allowed_when_allow_client_model_on(local_db, monkeypatch):
+    monkeypatch.setattr(gwmod.httpx, "AsyncClient", FakeClient_openai_gateway)
+    svc = GatewayService()
+    cfg = svc.effective_config()
+    cfg["gateway_force_model"] = True
+    cfg["gateway_allow_client_model"] = True
+    cfg["gateway_model"] = "deepseek-chat"
+    rt = svc.runtime()
+    run_async(
+        rt.handle_chat(
+            {"model": "llama3.2", "messages": [{"role": "user", "content": "hi"}]},
+            cfg,
+            ("guest", "client_model"),
+            "test",
+            "default",
+        )
+    )
+    assert rt._client.calls[-1][1]["model"] == "llama3.2"
+
+
+def test_molodetz_alias_still_remapped_with_allow_client_model(local_db, monkeypatch):
+    from devplacepy.services.openai_gateway import routing
+
+    monkeypatch.setattr(gwmod.httpx, "AsyncClient", FakeClient_openai_gateway)
+    original = routing.model_store.get("molodetz")
+    routing.model_store.remove("molodetz")
+    try:
+        svc = GatewayService()
+        cfg = svc.effective_config()
+        cfg["gateway_force_model"] = True
+        cfg["gateway_allow_client_model"] = True
+        cfg["gateway_model"] = "deepseek-chat"
+        rt = svc.runtime()
+        run_async(
+            rt.handle_chat(
+                {"model": "molodetz", "messages": [{"role": "user", "content": "hi"}]},
+                cfg,
+                ("guest", "molodetz_alias"),
+                "test",
+                "default",
+            )
+        )
+        assert rt._client.calls[-1][1]["model"] == "deepseek-chat"
+    finally:
+        if original is not None:
+            routing.model_store.set(
+                routing.ModelRouteIn(
+                    **{
+                        field: getattr(original, field)
+                        for field in routing.ModelRouteIn.model_fields
+                    }
+                )
+            )
+
+
 def test_stream_forwarded_to_upstream_with_forced_include_usage(local_db, monkeypatch):
     monkeypatch.setattr(gwmod.httpx, "AsyncClient", FakeClient_openai_gateway)
     svc = GatewayService()

tests/unit/services/openai_gateway/thinking.py

@@ -4,6 +4,7 @@ from devplacepy.services.openai_gateway.thinking import (
     apply_thinking,
     client_thinking_enabled,
     thinking_dialect,
+    upstream_capabilities,
 )
 
 
@@ -15,6 +16,38 @@ def test_dialect_from_upstream_url():
     assert thinking_dialect("https://unknown.example/v1/chat/completions") == "deepseek"
 
 
+def test_upstream_capabilities_openai_full_schema():
+    caps = upstream_capabilities("https://api.deepseek.com/chat/completions")
+    assert caps.dialect == "deepseek"
+    assert caps.supports_stream_options is True
+    assert caps.supports_stream_usage is True
+
+
+def test_upstream_capabilities_ollama_lacks_stream_options():
+    caps = upstream_capabilities("http://127.0.0.1:11434/api/chat")
+    assert caps.dialect == "ollama"
+    assert caps.supports_stream_options is False
+    assert caps.supports_stream_usage is False
+
+
+def test_upstream_capabilities_explicit_dialect_override():
+    caps = upstream_capabilities(
+        "https://ai.example.com/v1/chat/completions", dialect="ollama"
+    )
+    assert caps.dialect == "ollama"
+    assert caps.supports_stream_options is False
+
+
+def test_apply_thinking_respects_explicit_dialect_override():
+    without = apply_thinking({}, "https://ai.example.com/v1/chat/completions")
+    assert without["thinking"] == {"type": "disabled"}
+    with_override = apply_thinking(
+        {}, "https://ai.example.com/v1/chat/completions", dialect="ollama"
+    )
+    assert with_override["think"] is False
+    assert "thinking" not in with_override
+
+
 def test_client_intent_unspecified():
     assert client_thinking_enabled({}) is None
     assert client_thinking_enabled({"messages": []}) is None