feat: rebuild as multi-user web agent

tests/test_runtime_api.py

@@ -0,0 +1,163 @@
+from __future__ import annotations
+
+import json
+
+import httpx
+from fastapi.testclient import TestClient
+
+from agent_platform.runtime.app import create_app
+from agent_platform.store import RuntimeStore
+
+
+class FakeModelProvider:
+    def __init__(self) -> None:
+        self.completed = []
+        self.forwarded = []
+
+    async def complete(self, **kwargs):
+        self.completed.append(kwargs)
+        return {
+            "choices": [{"message": {"role": "assistant", "content": "work complete"}, "finish_reason": "stop"}],
+            "usage": {"total_tokens": 10},
+        }
+
+    async def forward(self, payload):
+        self.forwarded.append(payload)
+        request = httpx.Request("POST", "https://model.example.test/v1/chat/completions")
+        if payload.get("stream"):
+            return httpx.Response(
+                200,
+                request=request,
+                headers={"content-type": "text/event-stream"},
+                content=(
+                    'data: {"model":"ChatGPT-5.6:Luna","choices":[{"index":0,"delta":'
+                    '{"tool_calls":[{"index":0,"id":"call-1","type":"function","function":'
+                    '{"name":"read_file","arguments":"{}"}}]},"finish_reason":null}]}\n\n'
+                    "data: [DONE]\n\n"
+                ),
+            )
+        return httpx.Response(
+            200,
+            request=request,
+            headers={"content-type": "application/json"},
+            json={
+                "model": payload["model"],
+                "choices": [{"message": {"role": "assistant", "content": "chat reply"}, "finish_reason": "stop"}],
+            },
+        )
+
+    async def close(self):
+        return None
+
+
+class FakeTools:
+    async def close(self):
+        return None
+
+    def specs(self, *, read_only=False, allow_delegate=True):
+        return []
+
+    async def execute(self, name, arguments, context):
+        raise AssertionError("No tool should be called")
+
+
+def headers(settings, identity_jwt, chat_id="chat-1"):
+    return {
+        "Authorization": f"Bearer {settings.internal_provider_key}",
+        "X-OpenWebUI-User-Jwt": identity_jwt,
+        "X-OpenWebUI-Chat-Id": chat_id,
+    }
+
+
+def test_model_list_requires_internal_key(settings) -> None:
+    app = create_app(
+        settings,
+        store=RuntimeStore(settings.database_url),
+        provider=FakeModelProvider(),
+        tools=FakeTools(),
+    )
+    with TestClient(app) as client:
+        assert client.get("/v1/models").status_code == 401
+        response = client.get(
+            "/v1/models",
+            headers={"Authorization": f"Bearer {settings.internal_provider_key}"},
+        )
+        assert response.status_code == 200
+        assert len(response.json()["data"]) == 6
+
+
+def test_chat_maps_provider_model_and_work_upgrade_is_one_way(settings, identity_jwt) -> None:
+    provider = FakeModelProvider()
+    app = create_app(settings, store=RuntimeStore(settings.database_url), provider=provider, tools=FakeTools())
+    with TestClient(app) as client:
+        chat = client.post(
+            "/v1/chat/completions",
+            headers=headers(settings, identity_jwt),
+            json={"model": "chat-light", "messages": [{"role": "user", "content": "hello"}]},
+        )
+        assert chat.status_code == 200
+        assert provider.forwarded[0]["model"] == "ChatGPT-5.6:Luna"
+        assert chat.json()["model"] == "chat-light"
+
+        work = client.post(
+            "/v1/chat/completions",
+            headers=headers(settings, identity_jwt),
+            json={"model": "work-high", "messages": [{"role": "user", "content": "do it"}]},
+        )
+        assert work.status_code == 200
+        assert provider.completed[-1]["model"] == "ChatGPT-5.6:Sol"
+
+        downgrade = client.post(
+            "/v1/chat/completions",
+            headers=headers(settings, identity_jwt),
+            json={"model": "chat-medium", "messages": [{"role": "user", "content": "back"}]},
+        )
+        assert downgrade.status_code == 409
+
+
+def test_chat_stream_hides_provider_model_and_preserves_native_tool_calls(settings, identity_jwt) -> None:
+    provider = FakeModelProvider()
+    app = create_app(settings, store=RuntimeStore(settings.database_url), provider=provider, tools=FakeTools())
+    with TestClient(app) as client:
+        response = client.post(
+            "/v1/chat/completions",
+            headers=headers(settings, identity_jwt, "chat-stream"),
+            json={
+                "model": "chat-light",
+                "stream": True,
+                "messages": [{"role": "user", "content": "inspect"}],
+            },
+        )
+    assert response.status_code == 200
+    assert '"model": "chat-light"' in response.text
+    assert "ChatGPT-5.6:Luna" not in response.text
+    assert '"tool_calls"' in response.text
+    assert '"name": "read_file"' in response.text
+    assert "data: [DONE]" in response.text
+
+
+def test_work_stream_never_emits_delta_tool_calls(settings, identity_jwt) -> None:
+    app = create_app(
+        settings,
+        store=RuntimeStore(settings.database_url),
+        provider=FakeModelProvider(),
+        tools=FakeTools(),
+    )
+    with TestClient(app) as client:
+        response = client.post(
+            "/v1/chat/completions",
+            headers=headers(settings, identity_jwt, "stream-chat"),
+            json={
+                "model": "work-medium",
+                "stream": True,
+                "messages": [{"role": "user", "content": "do it"}],
+            },
+        )
+        assert response.status_code == 200
+        assert "work complete" in response.text
+        assert "tool_calls" in response.text  # rendered Work status details
+        for line in response.text.splitlines():
+            if line.startswith("data: {"):
+                chunk = json.loads(line.removeprefix("data: "))
+                assert "tool_calls" not in chunk["choices"][0]["delta"]
+        assert '"finish_reason": "stop"' in response.text