add configurable llm timeout

2026-09-07 22:01:53 -04:00
parent e2bed52751
commit 894637108c
3 changed files with 7 additions and 1 deletions
@@ -80,6 +80,11 @@ class Settings(BaseSettings):
    #: Flat seconds to wait between attempts (phase 67,
    #: ``BOR_LLM_RETRY_DELAY``); the TODO-locked 5 s, no backoff.
    llm_retry_delay: float = 5.0
+    #: HTTP timeout in seconds for LLM API calls (chat + embeddings).
+    #: Increase when long prompt processing or slow models exceed the
+    #: default 120 s (``BOR_LLM_TIMEOUT``; ``0`` = use the OpenAI SDK
+    #: default, which is platform-dependent).
+    llm_timeout: float = 120.0
    # --- Chat history (phase 74, TODO L4: prior turns + prior thinking) ---
    #: Newest client-provided history turns kept per ``POST /api/chat``
    #: (phase 74, ``BOR_HISTORY_MAX_TURNS``): the request's ``history``