Expired65% confidenceSolutionExact time
The project's model layer integrates DeepSeek as the primary inference model, Zhipu as the backup model, and a separately configured summarization model, reflecting a Model Routing design.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
7/14/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/12/2026(expired)
Sources
Harness架构实战：企业级Agent项目全解析
Related Claims
UnverifiedLarge model development relies on the comprehension capabilities of underlying large models, including models such as DeepSeek, Kimi, Doubao, and GPT.77% similarUnverifiedDeepAgent is built on LangGraph at its foundation, representing a paradigm in which task planning is entirely delegated to the large model for autonomous completion.77% similarVerifiedDeepSeek's MTP base-version draft model is co-optimized during main model training to align the draft model's output distribution with the target model, distinguishing it from post-hoc distillation approaches.75% similarUnverifiedAfter switching, the /model command can be used to select models such as DeepSeek; the user experience is close to the official model but slightly inferior in terms of output quality.75% similarUnverifiedDeep learning models consist of two components—architecture and weights—where the architecture determines how the model thinks and the weights carry the knowledge the model has learned.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/503857API
curl https://kongchang.com/api/v1/knowledge/claims/503857MCP
get_claim(id=503857)