Unverified50% confidenceFactExact time
In the THINK layer of VQ Agent Core, when no local model is available, understand() returns the original request with a via="skipped" marker rather than hiding the situation, and compose() returns a factual structured summary without fabricating content.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedThe four DECIDE backends of VQ Agent Core expose the same interface: decide(), classify_reply(), score_lead(), should_escalate(), so switching backends only requires changing a configuration value without modifying the calling code.74% similarUnverifiedVQ Agent Core calls _decide_gate() to enter the DECIDE layer when the routing confidence is below router.confidence_threshold in config.yaml (default 0.7) or the request is ambiguous.62% similarUnverifiedOpen-source Hub has added a virtual aggregated Provider feature that abstracts a virtual layer on top of multiple real model providers, allowing users to schedule model resources from different providers on demand through a unified entry point.61% similarUnverifiedVQ Agent Core currently has no UI and no hosted service, and the local DECIDE backend requires a PC-class machine; it is a usable foundation rather than a finished product.60% similarUnverifiedvLLM's KV Connector interface defines standard methods such as send_kv_caches_and_hidden_states and recv_kv_caches_and_hidden_states, enabling connectors to insert cache routing logic without modifying the core inference logic.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1011786API
curl https://kongchang.com/api/v1/knowledge/claims/1011786MCP
get_claim(id=1011786)