fix(cloud): align planner configuration and records

apps/cloud-api/tests/test_llm_provider_planner_resolution.py

@@ -10,10 +10,10 @@ from cloud_api.app import create_app
 
 class _FakePlannerClient:
     def __init__(self) -> None:
-        self.calls = 0
+        self.calls: list[dict[str, object]] = []
 
-    def decide(self, **_kwargs) -> ToolCallDecision:
-        self.calls += 1
+    def decide(self, **kwargs) -> ToolCallDecision:
+        self.calls.append(kwargs)
         return ToolCallDecision(tool_name="tap", arguments={"x": 1, "y": 2})
 
 
@@ -38,7 +38,12 @@ def _login_admin(client: TestClient) -> dict[str, str]:
 
 
 def _create_profile(
-    client: TestClient, headers: dict[str, str], *, name: str, model: str
+    client: TestClient,
+    headers: dict[str, str],
+    *,
+    name: str,
+    model: str,
+    timeout_seconds: float,
 ) -> dict:
     response = client.post(
         "/v1/planner/providers",
@@ -48,7 +53,7 @@ def _create_profile(
             "provider_type": "openai-compatible",
             "model": model,
             "base_url": "https://compat.example/v1",
-            "timeout_seconds": 30,
+            "timeout_seconds": timeout_seconds,
             "api_key": f"key-for-{name}",
         },
     )
@@ -95,7 +100,11 @@ def test_planner_uses_the_newly_activated_database_profile(monkeypatch) -> None:
     with TestClient(app) as client:
         admin_headers = _login_admin(client)
         first = _create_profile(
-            client, admin_headers, name="First", model="first-model"
+            client,
+            admin_headers,
+            name="First",
+            model="first-model",
+            timeout_seconds=41,
         )
         assert (
             client.post(
@@ -115,9 +124,14 @@ def test_planner_uses_the_newly_activated_database_profile(monkeypatch) -> None:
         assert first_decision.status_code == 200, first_decision.text
         assert resolved_profiles[-1].profile.model == "first-model"
         assert resolved_profiles[-1].api_key == "key-for-First"
+        assert fake.calls[-1]["timeout"] == 41
 
         second = _create_profile(
-            client, admin_headers, name="Second", model="second-model"
+            client,
+            admin_headers,
+            name="Second",
+            model="second-model",
+            timeout_seconds=57,
         )
         settings = client.get("/v1/planner/providers").json()["settings"]
         activated = client.post(
@@ -134,7 +148,8 @@ def test_planner_uses_the_newly_activated_database_profile(monkeypatch) -> None:
         )
         assert second_decision.status_code == 200, second_decision.text
         assert resolved_profiles[-1].profile.model == "second-model"
-        assert fake.calls == 2
+        assert fake.calls[-1]["timeout"] == 57
+        assert len(fake.calls) == 2
 
 
 def test_planner_fails_closed_without_an_active_database_profile(monkeypatch) -> None:

apps/device-host-agent/host_agent/cloud_planner_client.py

@@ -28,10 +28,21 @@ import httpx
 from cloud.internal_api.models import PlannerDecisionError, PlannerDecisionResponse
 from host_agent.config import HostAgentConfig
 from host_agent.planner_context import current_planner_execution_context
-from runtime.tool_calling_client import ToolCallDecision, ToolCallUnavailable, ToolCallUsage
+from runtime.tool_calling_client import (
+    ToolCallDecision,
+    ToolCallUnavailable,
+    ToolCallUsage,
+)
 from runtime.tool_specs import ToolSpec
 
 
+_CLOUD_PROVIDER_MAX_TIMEOUT_SECONDS = 120.0
+_CLOUD_PROXY_TRANSPORT_GRACE_SECONDS = 5.0
+_CLOUD_PROXY_HTTP_TIMEOUT_SECONDS = (
+    _CLOUD_PROVIDER_MAX_TIMEOUT_SECONDS + _CLOUD_PROXY_TRANSPORT_GRACE_SECONDS
+)
+
+
 class CloudProxyToolCallingClient:
     def __init__(
         self,
@@ -69,7 +80,9 @@ class CloudProxyToolCallingClient:
                 }
                 for spec in tools
             ],
-            "timeout_seconds": timeout,
+            # Legacy Cloud API versions use this field. Current Cloud API versions
+            # resolve the provider timeout from the active Provider profile.
+            "timeout_seconds": min(timeout, _CLOUD_PROVIDER_MAX_TIMEOUT_SECONDS),
         }
         context = current_planner_execution_context()
         if context is not None:
@@ -85,7 +98,7 @@ class CloudProxyToolCallingClient:
                 f"/internal/v1/hosts/{self.config.host_id}/planner/decide",
                 json=payload,
                 headers={"Authorization": f"Bearer {self.config.token}"},
-                timeout=timeout + 5,
+                timeout=_CLOUD_PROXY_HTTP_TIMEOUT_SECONDS,
             )
         except httpx.HTTPError as exc:
             raise ToolCallUnavailable(str(exc)) from exc

apps/device-host-agent/tests/test_cloud_planner_client.py

@@ -5,7 +5,10 @@ import json
 import httpx
 import pytest
 
-from host_agent.cloud_planner_client import CloudProxyToolCallingClient
+from host_agent.cloud_planner_client import (
+    _CLOUD_PROXY_HTTP_TIMEOUT_SECONDS,
+    CloudProxyToolCallingClient,
+)
 from host_agent.config import HostAgentConfig
 from host_agent.planner_context import PlannerExecutionContext, _context
 from runtime.tool_calling_client import ToolCallDecision, ToolCallUnavailable
@@ -79,6 +82,29 @@ def test_decide_base64_encodes_screenshot() -> None:
     assert body["screenshot_base64"] == "aGVsbG8="
 
 
+def test_decide_clamps_legacy_timeout_and_waits_for_cloud_profile_timeout() -> None:
+    seen_requests: list[httpx.Request] = []
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        seen_requests.append(request)
+        return httpx.Response(200, json={"tool_name": "tap", "arguments": {}})
+
+    client = _client(handler)
+
+    client.decide(
+        system_prompt="sp",
+        user_prompt="up",
+        screenshot=None,
+        tools=_TOOLS,
+        timeout=180.0,
+    )
+
+    request = seen_requests[0]
+    body = json.loads(request.content)
+    assert body["timeout_seconds"] == 120.0
+    assert request.extensions["timeout"]["read"] == _CLOUD_PROXY_HTTP_TIMEOUT_SECONDS
+
+
 def test_decide_includes_bound_assignment_context() -> None:
     seen_requests: list[httpx.Request] = []