OpenJarvis 0.1.2.dev809__tar.gz → 0.1.2.dev811__tar.gz

{openjarvis-0.1.2.dev809 → openjarvis-0.1.2.dev811}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: OpenJarvis
-Version: 0.1.2.dev809
+Version: 0.1.2.dev811
 Summary: OpenJarvis — modular AI assistant backend with composable intelligence primitives
 Project-URL: Homepage, https://github.com/open-jarvis/OpenJarvis
 Project-URL: Documentation, https://open-jarvis.github.io/OpenJarvis/

{openjarvis-0.1.2.dev809 → openjarvis-0.1.2.dev811}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "OpenJarvis"
-version = "0.1.2.dev809"
+version = "0.1.2.dev811"
 description = "OpenJarvis — modular AI assistant backend with composable intelligence primitives"
 readme = "README.md"
 # Upper bound: numpy 2.2.x (pinned transitively via datasets/pandas) ships no

{openjarvis-0.1.2.dev809 → openjarvis-0.1.2.dev811}/src/openjarvis/engine/cloud.py

@@ -893,6 +893,13 @@ class CloudEngine(InferenceEngine):
             "max_tokens": max_tokens,
             "temperature": temperature,
         }
+        # Forward tools / tool_choice (OpenRouter is OpenAI-compatible).
+        tools = kwargs.pop("tools", None)
+        if tools:
+            create_kwargs["tools"] = tools
+        tool_choice = kwargs.pop("tool_choice", None)
+        if tool_choice is not None:
+            create_kwargs["tool_choice"] = tool_choice
         t0 = time.monotonic()
         resp = self._openrouter_client.chat.completions.create(**create_kwargs)
         elapsed = time.monotonic() - t0
@@ -900,7 +907,7 @@ class CloudEngine(InferenceEngine):
         usage = resp.usage
         prompt_tokens = usage.prompt_tokens if usage else 0
         completion_tokens = usage.completion_tokens if usage else 0
-        return {
+        result: Dict[str, Any] = {
             "content": choice.message.content or "",
             "usage": {
                 "prompt_tokens": prompt_tokens,
@@ -911,6 +918,19 @@ class CloudEngine(InferenceEngine):
             "finish_reason": choice.finish_reason or "stop",
             "ttft": elapsed,
         }
+        if getattr(choice.message, "tool_calls", None):
+            result["tool_calls"] = [
+                {
+                    "id": tc.id,
+                    "type": tc.type,
+                    "function": {
+                        "name": tc.function.name,
+                        "arguments": tc.function.arguments,
+                    },
+                }
+                for tc in choice.message.tool_calls
+            ]
+        return result
 
     def _generate_minimax(
         self,
@@ -1195,6 +1215,13 @@ class CloudEngine(InferenceEngine):
             "temperature": temperature,
             "stream": True,
         }
+        # Forward tools / tool_choice (OpenRouter is OpenAI-compatible).
+        tools = kwargs.pop("tools", None)
+        if tools:
+            create_kwargs["tools"] = tools
+        tool_choice = kwargs.pop("tool_choice", None)
+        if tool_choice is not None:
+            create_kwargs["tool_choice"] = tool_choice
         resp = self._openrouter_client.chat.completions.create(**create_kwargs)
         for chunk in resp:
             delta = chunk.choices[0].delta if chunk.choices else None

{openjarvis-0.1.2.dev809 → openjarvis-0.1.2.dev811}/src/openjarvis/server/agent_manager_routes.py

@@ -111,24 +111,35 @@ def _make_lightweight_system(
     model: str,
     config: Any = None,
 ) -> _LightweightSystem:
-    """Build a minimal system with a plain OllamaEngine.
+    """Build a minimal system with a fresh inference engine.
 
     The server's ``app.state.engine`` is heavily wrapped
     (MultiEngine -> InstrumentedEngine -> GuardrailsEngine) and can
-    return empty content from background threads.  Create a fresh
-    OllamaEngine directly (no health checks or model discovery that
-    could interfere with in-flight Ollama requests).
+    return empty content from background threads. Create a fresh
+    engine directly (no health checks or model discovery that
+    could interfere with in-flight requests).
     """
     try:
-        from openjarvis.engine.ollama import OllamaEngine
+        from openjarvis.engine._discovery import get_engine
 
         cfg = config
         if cfg is None:
             from openjarvis.core.config import load_config
 
             cfg = load_config()
-        host = cfg.engine.ollama.host if cfg else ""
-        plain_engine = OllamaEngine(host=host) if host else OllamaEngine()
+
+        pref = cfg.intelligence.preferred_engine
+        key = pref or cfg.engine.default
+        resolved = get_engine(cfg, key)
+
+        if resolved is not None:
+            plain_engine = resolved[1]
+        else:
+            from openjarvis.engine.ollama import OllamaEngine
+
+            host = cfg.engine.ollama.host if cfg else ""
+            plain_engine = OllamaEngine(host=host) if host else OllamaEngine()
+
         # Wrap with InstrumentedEngine so agent ticks are recorded
         # in telemetry (FLOPs, energy, cost savings).
         try:
@@ -842,9 +853,7 @@ async def _stream_managed_agent(
 
         app_config = load_config()
 
-    final_system_prompt = _build_managed_system_prompt(
-        system_prompt or "", app_config
-    )
+    final_system_prompt = _build_managed_system_prompt(system_prompt or "", app_config)
 
     if final_system_prompt and final_system_prompt.strip():
         llm_messages.append(

{openjarvis-0.1.2.dev809 → openjarvis-0.1.2.dev811}/tests/engine/test_cloud.py

@@ -381,3 +381,59 @@ class TestCodexGenerate:
         engine._codex_client = {"token": "t", "url": "http://test"}
         engine.close()
         assert engine._codex_client is None
+
+
+class TestOpenRouterToolForwarding:
+    """Regression for #511: the OpenRouter engine must forward tools/tool_choice
+    to the (OpenAI-compatible) API and parse tool_calls back out of the response.
+    Pre-fix, both were dropped, silently breaking function-calling via OpenRouter.
+    """
+
+    def test_generate_forwards_tools_and_parses_tool_calls(
+        self, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        monkeypatch.delenv("OPENAI_API_KEY", raising=False)
+
+        fake_tc = SimpleNamespace(
+            id="call_1",
+            type="function",
+            function=SimpleNamespace(name="get_weather", arguments='{"city": "NYC"}'),
+        )
+        fake_choice = SimpleNamespace(
+            message=SimpleNamespace(content=None, tool_calls=[fake_tc]),
+            finish_reason="tool_calls",
+        )
+        fake_resp = SimpleNamespace(
+            choices=[fake_choice],
+            usage=SimpleNamespace(prompt_tokens=3, completion_tokens=2, total_tokens=5),
+            model="openai/gpt-4o",
+        )
+        fake_client = mock.MagicMock()
+        fake_client.chat.completions.create.return_value = fake_resp
+
+        EngineRegistry.register_value("cloud", CloudEngine)
+        engine = CloudEngine()
+        engine._openrouter_client = fake_client
+
+        tools = [
+            {
+                "type": "function",
+                "function": {"name": "get_weather", "parameters": {}},
+            }
+        ]
+        result = engine.generate(
+            [Message(role=Role.USER, content="weather in NYC?")],
+            model="openrouter/openai/gpt-4o",
+            tools=tools,
+            tool_choice="auto",
+        )
+
+        # tools / tool_choice are forwarded to the API call
+        sent = fake_client.chat.completions.create.call_args.kwargs
+        assert sent["tools"] == tools
+        assert sent["tool_choice"] == "auto"
+
+        # tool_calls from the response are parsed back into the result
+        assert result["tool_calls"][0]["id"] == "call_1"
+        assert result["tool_calls"][0]["function"]["name"] == "get_weather"
+        assert result["tool_calls"][0]["function"]["arguments"] == '{"city": "NYC"}'

{openjarvis-0.1.2.dev809 → openjarvis-0.1.2.dev811}/tests/server/test_agent_manager_routes.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 import json
 import tempfile
 from pathlib import Path
+from types import SimpleNamespace
 from unittest.mock import MagicMock
 
 import pytest
@@ -488,3 +489,51 @@ class TestResolveToolSpecs:
 
         assert _resolve_tool_specs(None) == []
         assert _resolve_tool_specs([]) == []
+
+
+class TestLightweightSystemEngineResolution:
+    """Regression for #477 / #514: the managed-agent lightweight system must
+    resolve the user's *configured* engine (preferred_engine, else
+    engine.default), not a hardcoded OllamaEngine. We assert the key passed to
+    ``get_engine`` — captured before the system is built — rather than the final
+    (telemetry-wrapped) engine object.
+    """
+
+    @staticmethod
+    def _cfg(preferred, default):
+        # context_from_memory absent on .agent -> memory backend resolves to None
+        return SimpleNamespace(
+            intelligence=SimpleNamespace(preferred_engine=preferred),
+            engine=SimpleNamespace(default=default, ollama=SimpleNamespace(host="")),
+            agent=SimpleNamespace(),
+        )
+
+    def _capture_get_engine(self, monkeypatch):
+        captured = {}
+
+        def fake_get_engine(cfg, key):
+            captured["key"] = key
+            return ("resolved", MagicMock())
+
+        monkeypatch.setattr("openjarvis.engine._discovery.get_engine", fake_get_engine)
+        return captured
+
+    def test_resolves_preferred_engine_over_default(self, monkeypatch):
+        pytest.importorskip("fastapi")
+        from openjarvis.server import agent_manager_routes as amr
+
+        captured = self._capture_get_engine(monkeypatch)
+        amr._make_lightweight_system(
+            engine=MagicMock(), model="m", config=self._cfg("vllm", "ollama")
+        )
+        assert captured["key"] == "vllm"
+
+    def test_falls_back_to_engine_default_without_preference(self, monkeypatch):
+        pytest.importorskip("fastapi")
+        from openjarvis.server import agent_manager_routes as amr
+
+        captured = self._capture_get_engine(monkeypatch)
+        amr._make_lightweight_system(
+            engine=MagicMock(), model="m", config=self._cfg(None, "llamacpp")
+        )
+        assert captured["key"] == "llamacpp"