fix: task intent classifier, Hermes brain, rolling run log

- Intent classifier: task phrases now checked before query to prevent
  "add task X" mis-routing; "job item"/"job ticket"/"work order" added
  to TASK_PHRASES; "please add + project keyword" fallback added;
  substring match bug fixed ("in" inside "incident" triggered query)
- brain.py: routes planning fallback to Hermes cloud (claude-sonnet-4-6)
  via HERMES_URL/HERMES_API_KEY env vars; falls back to local Ollama
  if Hermes is unavailable
- main.py: rolling 50-run log written to logs/jon-snow/runs.jsonl

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

app/brain.py

@@ -9,15 +9,21 @@ litellm.set_verbose = False
 FAST_MODEL = os.getenv("FAST_MODEL", "ollama/gemma4")
 SMART_MODEL = os.getenv("SMART_MODEL", "ollama/gemma4")
 OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL", "http://172.27.40.20:11434")
-
-
-def _extra_kwargs(model: str) -> dict:
-    if model.startswith("ollama/"):
-        return {"api_base": OLLAMA_BASE_URL}
-    return {}
+HERMES_URL = os.getenv("HERMES_URL", "")
+HERMES_API_KEY = os.getenv("HERMES_API_KEY", "none")
 
 
 async def stream_completion(messages: list[dict], use_smart: bool = False):
+    if HERMES_URL:
+        logger.info("Brain: routing to Hermes cloud (claude-sonnet-4-6)")
+        return await litellm.acompletion(
+            model="openai/hermes-agent",
+            messages=messages,
+            stream=True,
+            api_base=HERMES_URL,
+            api_key=HERMES_API_KEY,
+        )
+
     model = SMART_MODEL if use_smart else FAST_MODEL
     logger.info(f"Brain: model={model} smart={use_smart}")
     try:
@@ -25,7 +31,7 @@ async def stream_completion(messages: list[dict], use_smart: bool = False):
             model=model,
             messages=messages,
             stream=True,
-            **_extra_kwargs(model),
+            api_base=OLLAMA_BASE_URL if model.startswith("ollama/") else None,
         )
     except Exception as e:
         logger.error(f"Brain error ({model}): {e}")
@@ -35,6 +41,6 @@ async def stream_completion(messages: list[dict], use_smart: bool = False):
                 model=FAST_MODEL,
                 messages=messages,
                 stream=True,
-                **_extra_kwargs(FAST_MODEL),
+                api_base=OLLAMA_BASE_URL if FAST_MODEL.startswith("ollama/") else None,
             )
         raise