feat(llm-deepseek): configure max token defaults

examples/jsonrpc-agent/cordis.yml

@@ -7,8 +7,8 @@
     maxTokensAsSuccess: !!js "process.env.DSH_MAX_TOKENS_AS_SUCCESS === undefined ? true : JSON.parse(process.env.DSH_MAX_TOKENS_AS_SUCCESS)"
 
 # The DeepSeek adapter. Shipped default: full thinking at max effort on every
-# request (wire-only defaults; they never enter the request header). The model
-# arrives per session over JSON-RPC, so it is not pinned here.
+# request; exact-model resolution materializes request defaults before logging.
+# The model arrives per session over JSON-RPC, so it is not pinned here.
 - id: llm-deepseek
   name: '@deepseek-ai/dsh-llm-deepseek'
   config: