add configurable llm timeout

.env.example

@@ -19,6 +19,7 @@ BOR_LLM_BASE_URL=https://aipi.reeseapps.com/v1
 BOR_LLM_API_KEY=                  # falls back to $AIPI_KEY, then "not-needed"
 BOR_LLM_CHAT_MODEL=turbo
 # BOR_LLM_RETRIES=3             # retry a dead LLM request before the first token lands (phase 67); 0 = off
+# BOR_LLM_TIMEOUT=300           # HTTP timeout for LLM API calls, seconds (default 120)
 # BOR_LLM_RETRY_DELAY=5        # seconds between LLM retries (phase 67)
 BOR_LLM_EMBED_MODEL=embed
 BOR_LLM_SUMMARY_MODEL=lite          # one-shot completions: document summaries (phase 30), KB overview (phase 31)

app/config.py

@@ -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``

app/rag/llm.py

@@ -186,7 +186,7 @@ class LLMClient:
         self._client = AsyncOpenAI(
             base_url=self.settings.llm_base_url,
             api_key=self.settings.effective_api_key,
-            timeout=120.0,
+            timeout=self.settings.llm_timeout,
         )
 
     async def _post_embeddings(self, texts: list[str]) -> list[list[float]]: