docs(system-prompt): combine cache guarantees in model-experience field
Keep the merged in-history and stable suffix guarantees within the required single KV Cache effect paragraph. No behavior or guarantee changes.
This commit is contained in:
1 parent
c1be95a0cd
commit
73865675a4
3 files changed
+4
-8
No files matched your search
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/core/system-prompt/README.md
|
||||
README.md: 55cee727b7c87615cfb1f9e031c7ddb4f396db07
|
||||
README.zh.md: 411ed029c850c730ce10b059e92badf0e6e8c88a
|
||||
README.md: e098a1e6a80bdc521f25a6b35a4ba9c1b6410155
|
||||
README.zh.md: 7e6597d51d66bbcf934b8451e8e0844916f4df10
|
||||
@@ -146,9 +146,7 @@ Identity is a fixed per-request cost when enabled. Persona prefixes, suffixes, a
|
||||
|
||||
#### KV Cache effect
|
||||
|
||||
Prefix-stable while identity, persona, variables, section text, and order render identically: an unchanged rendering leaves the system nodes untouched unless an incapable route or a new request series must consolidate retained in-history prompts. Without `systemPromptUpdate`, non-empty prompt text is consolidated at the first system node through logged per-node replacements, so a head rewrite loses prefix reuse from its first changed token; when the prepared call declares `systemPromptUpdate: 'in-history'`, the agent loop appends a non-empty changed prompt after the cached history inside a continuing request series, so the prefix through that history stays reusable ([decision rule](../agent-loop/README.md#understand-the-implementation)).
|
||||
|
||||
With the same model, persona prefix, tools, and preceding instructions, different source paths, local Web URLs, or persona suffix values leave the reusable first-party prefix unchanged. Persona prefix changes can alter the early prefix. Any change may invalidate reuse from the first changed token; provider cache sharing and measured hit rates are not guaranteed.
|
||||
Prefix-stable while identity, persona, variables, section text, and order render identically: an unchanged rendering leaves the system nodes untouched unless an incapable route or a new request series must consolidate retained in-history prompts. Without `systemPromptUpdate`, non-empty prompt text is consolidated at the first system node through logged per-node replacements, so a head rewrite loses prefix reuse from its first changed token; when the prepared call declares `systemPromptUpdate: 'in-history'`, the agent loop appends a non-empty changed prompt after the cached history inside a continuing request series, so the prefix through that history stays reusable ([decision rule](../agent-loop/README.md#understand-the-implementation)). With the same model, persona prefix, tools, and preceding instructions, different source paths, local Web URLs, or persona suffix values leave the reusable first-party prefix unchanged. Persona prefix changes can alter the early prefix. Any change may invalidate reuse from the first changed token; provider cache sharing and measured hit rates are not guaranteed.
|
||||
|
||||
### Tool schemas
|
||||
|
||||
|
||||
@@ -146,9 +146,7 @@ You are an AI agent powered by DeepSeek Harness.
|
||||
|
||||
#### KV Cache 影响
|
||||
|
||||
只要身份、persona、变量、段文本与顺序的渲染完全相同,前缀就保持稳定:渲染未变时系统节点保持不动,除非不具备能力的路由或新请求序列必须归并保留的历史内提示词。没有 `systemPromptUpdate` 时,非空提示词文本通过有日志记录的逐节点替换归并到首个系统节点,因此头节点重写会从首个变化的 token 起失去前缀复用;当已准备调用声明 `systemPromptUpdate: 'in-history'` 时,agent loop(智能体循环)会在同一请求序列延续期间把变化后的非空提示词追加到已缓存历史之后,因此直到该历史末尾的前缀仍可复用([决策规则](../agent-loop/README.zh.md#understand-the-implementation))。
|
||||
|
||||
模型、persona 前缀、工具与前置指令一致时,不同源码路径、本地 Web URL 或 persona 后缀值不会改变可复用的第一方前缀。Persona 前缀变化可能改变靠前的前缀。任何变更都可能从第一个变化的 token 起使复用失效;不保证提供方共享缓存或实际命中率。
|
||||
只要身份、persona、变量、段文本与顺序的渲染完全相同,前缀就保持稳定:渲染未变时系统节点保持不动,除非不具备能力的路由或新请求序列必须归并保留的历史内提示词。没有 `systemPromptUpdate` 时,非空提示词文本通过有日志记录的逐节点替换归并到首个系统节点,因此头节点重写会从首个变化的 token 起失去前缀复用;当已准备调用声明 `systemPromptUpdate: 'in-history'` 时,agent loop(智能体循环)会在同一请求序列延续期间把变化后的非空提示词追加到已缓存历史之后,因此直到该历史末尾的前缀仍可复用([决策规则](../agent-loop/README.zh.md#understand-the-implementation))。 模型、persona 前缀、工具与前置指令一致时,不同源码路径、本地 Web URL 或 persona 后缀值不会改变可复用的第一方前缀。Persona 前缀变化可能改变靠前的前缀。任何变更都可能从第一个变化的 token 起使复用失效;不保证提供方共享缓存或实际命中率。
|
||||
|
||||
### 工具 schema
|
||||
|
||||
|
||||
Reference in new issue
Block a user