adiuvAI/api
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(contextual): drop floating WS frame, runner, and prompt fallback

Browse Source 
contextual_request + contextual_scope_update are the only WS
flows for ad-hoc contextual chat now. Floating system prompt
constant removed; Langfuse 'floating_system' is deleted in a
separate manual step. Also removes floating-agent LLM slot from
llm.py and the associated LLM_MODEL_FLOATING_AGENT setting entry.
This commit is contained in:
Roberto
2026-05-15 18:53:01 +02:00
parent d63fd5f3b9
commit 052c7e3741
4 changed files with 6 additions and 447 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
app/config/settings.py
View File

@@ -23,9 +23,8 @@ class Settings(BaseSettings):
LLM_EMBED_MODEL: str = "text-embedding-3-small"
# Per-agent model overrides. Leave empty to fall back to LLM_MODEL.
LLM_MODEL_CLASSIFIER: str = "" # _infer_floating_domain (intent routing)
LLM_MODEL_CLASSIFIER: str = "" # classifier (intent routing, future use)
LLM_MODEL_HOME_AGENT: str = "" # home-agent (run_single_agent / stream)
LLM_MODEL_FLOATING_AGENT: str = "" # floating-agent (contextual chat)
LLM_MODEL_UNIFIED_PROCESSOR: str = "" # unified-processor (agent_runner)
LLM_MODEL_CLOUD_PROCESSOR: str = "" # cloud-processor (agent_runner)
LLM_MODEL_BRIEF_AGENT: str = "" # brief-agent (home + project text briefs)