feat: add xAI prompt caching via x-grok-conv-id header

When using xAI's API directly (base_url contains x.ai), send the x-grok-conv-id header set to the Hermes session_id. This routes consecutive requests to the same server, maximizing automatic prompt cache hits. Ref: https://docs.x.ai/developers/advanced-api-usage/prompt-caching
2026-04-29 15:31:38 +08:00 · 2026-04-06 11:43:23 -07:00
1 changed files with 6 additions and 0 deletions
--- a/run_agent.py
+++ b/run_agent.py
@@ -5438,6 +5438,12 @@ class AIAgent:
        if extra_body:
            api_kwargs["extra_body"] = extra_body

+        # xAI prompt caching: send x-grok-conv-id header to route requests
+        # to the same server, maximizing automatic cache hits.
+        # https://docs.x.ai/developers/advanced-api-usage/prompt-caching
+        if "x.ai" in self._base_url_lower and hasattr(self, "session_id") and self.session_id:
+            api_kwargs["extra_headers"] = {"x-grok-conv-id": self.session_id}
+
        return api_kwargs

    def _supports_reasoning_extra_body(self) -> bool: