Fix Tinfoil spend gap: raise timeout 30->180s, num_retries 2->0

DeepSeek V4.1 Flash is a reasoning model; 30s timeout caused LiteLLM to
abandon in-flight generations (falling back to GPT-OSS) while Tinfoil still
completed and billed them. num_retries re-hit Tinfoil up to 3x. Result: Tinfoil
billed ~2x the tokens LiteLLM logged. Generous timeout + zero retries stops
the silent re-billing.

config.yaml

@@ -46,9 +46,16 @@ model_list:
       cache_read_input_token_cost: 0.00000010
 
 # Fallback: if DeepSeek is down, use GPT-OSS
+# NOTE: DeepSeek V4.1 Flash is a reasoning model — generations routinely run
+# longer than 30s. A 30s timeout caused LiteLLM to abandon in-flight DeepSeek
+# requests (falling back to GPT-OSS), while Tinfoil still completed and billed
+# the abandoned generation. num_retries amplified this by re-hitting Tinfoil up
+# to 3x per request. Result: Tinfoil billed ~2x the tokens LiteLLM logged.
+# Fix: a generous timeout so generations complete inside LiteLLM (and get
+# logged), and zero retries so a slow/failed request is never re-billed.
 router_settings:
-  num_retries: 2
+  num_retries: 0
-  timeout: 30
+  timeout: 180
   fallbacks:
     - deepseek-v4-1-flash:
         - gpt-oss-120b
@@ -62,4 +69,4 @@ litellm_settings:
   salt_key: os.environ/LITELLM_SALT_KEY
   drop_params: true
   num_threads: 4
-  request_timeout: 30
+  request_timeout: 180