Files
jon-snow/app/brain.py
T
admin 59c9cb837d 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>
2026-05-30 14:03:29 +00:00

47 lines
1.5 KiB
Python

import logging
import os
import litellm
logger = logging.getLogger("jon-snow.brain")
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")
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:
return await litellm.acompletion(
model=model,
messages=messages,
stream=True,
api_base=OLLAMA_BASE_URL if model.startswith("ollama/") else None,
)
except Exception as e:
logger.error(f"Brain error ({model}): {e}")
if use_smart and model != FAST_MODEL:
logger.info("Falling back to FAST_MODEL")
return await litellm.acompletion(
model=FAST_MODEL,
messages=messages,
stream=True,
api_base=OLLAMA_BASE_URL if FAST_MODEL.startswith("ollama/") else None,
)
raise