step-3: add router refactor with streaming support (orchestrator.py)

- orchestrate_v3(user_id, message, context): classifies intent, returns
  (agent_name, agent_instance) — caller drives execution
- orchestrate_v3_stream(user_id, message, context): yields (agent_name, token)
  pairs; first yield is always (agent_name, "") as a domain-detection signal
- ChatAgent.handle_stream(): default implementation yields handle() result as
  one chunk; subclasses override for true token-level streaming
- Fix stale test_orchestrator.py assertions that expected a JSON final frame
  that orchestrate_stream never emitted

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

app/core/orchestrator.py

@@ -7,7 +7,7 @@ from typing import Any, AsyncGenerator
 
 from langchain_core.messages import HumanMessage, SystemMessage
 
-from app.core.agent_registry import AgentRegistry
+from app.core.agent_registry import AgentRegistry, ChatAgent
 from app.core.llm import get_router_llm
 from app.core.agent_registry import registry as _default_registry
 from app.schemas import ChatRequest, ChatResponse, ExecutionPlan
@@ -140,6 +140,44 @@ async def orchestrate(
     return _build_plan(agent_name, request.message)
 
 
+async def orchestrate_v3(
+    user_id: str,
+    message: str,
+    context: dict[str, Any],
+    reg: AgentRegistry | None = None,
+) -> tuple[str, ChatAgent]:
+    """v3 orchestration — returns (agent_name, agent_instance); caller drives execution.
+
+    Classifies intent and instantiates the matching agent. The caller is responsible
+    for invoking handle(), handle_stream(), or _tool_loop_stream() as needed.
+    """
+    if reg is None:
+        reg = _default_registry
+    agent_name = await classify_intent(message, context, reg)
+    return agent_name, reg.get(agent_name)
+
+
+async def orchestrate_v3_stream(
+    user_id: str,
+    message: str,
+    context: dict[str, Any],
+    reg: AgentRegistry | None = None,
+) -> AsyncGenerator[tuple[str, str], None]:
+    """v3 streaming orchestration — yields (agent_name, token) pairs.
+
+    The first yield always carries the agent_name with an empty token so that
+    callers (e.g. PopupFormatter) can detect the routing domain before any text
+    tokens arrive.
+    """
+    if reg is None:
+        reg = _default_registry
+    agent_name = await classify_intent(message, context, reg)
+    agent = reg.get(agent_name)
+    yield agent_name, ""  # domain signal — no token yet
+    async for token in agent.handle_stream(message, context):
+        yield agent_name, token
+
+
 async def orchestrate_stream(
     request: ChatRequest,
     reg: AgentRegistry | None = None,