Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Python agent-contextagent-memoryagent-pluginsagentic-ragcontext-databasedsh-pluginknowledge-basememorymemory-managementself-evolvingvector-database
fix(vlm): initialize Codex async client cache (#2208)
civilizedBaboonbaddbeea75e8
diff --git a/openviking/models/vlm/backends/codex_vlm.py b/openviking/models/vlm/backends/codex_vlm.pyindex 71d5c2424..60bcc5129 100644--- a/openviking/models/vlm/backends/codex_vlm.py+++ b/openviking/models/vlm/backends/codex_vlm.py@@ -44,6 +44,7 @@ class CodexVLM(OpenAIVLM):if not normalized.get("api_base"):normalized["api_base"] = DEFAULT_CODEX_BASE_URLsuper().__init__(normalized)+ self._async_client = Nonedef _build_responses_client(self, api_key: str, api_base: str):kwargs = _build_openai_client_kwargs(