Unverified50% confidenceSolutionExact time
Repeatedly emphasizing in the system prompt to firmly trust documentation and examples can make the model obediently call existing packages rather than reinventing the wheel.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/16/2026
First Seen
Valid until: 12/15/2026
Sources
Related Entities
Related Claims
Unverified工具调用早期实现依赖ReAct等提示词技巧，模型通过文本格式输出行动指令，再由外部代码解析执行66% similarUnverifiedThe session log is Harness's "source of truth," and system prompts, model outputs, tool calls and results, sub-agent scheduling, and context injection can all be replayed along the event stream65% similarUnverified自定义工具（Custom Tool）可以将重复流程封装起来实现一键复用，绕过重复推理65% similarUnverifiedEvery coding tool comes with its own system prompt, which encodes a large number of "opinions" on topics such as how to format code patches, when to proactively ask questions, and how aggressively to use tools.65% similarUnverifiedThe general principle for achieving cache hits is to keep the prefix of the request context as stable as possible, placing fixed content such as system prompts and tool definitions at the very front, with per-turn user input appended at the end.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/924555API
curl https://kongchang.com/api/v1/knowledge/claims/924555MCP
get_claim(id=924555)