mirror of
https://github.com/deepseek-ai/deepseek-harness.git
synced 2026-08-29 04:26:38 +00:00
fix(web): address reference review defects
This commit is contained in:
@@ -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/context/session-reference/README.md
|
||||
README.md: 71ed6891a3a0bee480b2064d844df8758349ee38
|
||||
README.zh.md: 5a761115105914a47c1f3d2673df4b2f3e3e76da
|
||||
README.md: 1ce5ab0a3b0cb5342c1087ddd644933a92b2a596
|
||||
README.zh.md: 2fc30fa01d0e428a2e7ef0be1680a1937f06660c
|
||||
|
||||
@@ -32,7 +32,7 @@ Retention applies `maxReferenceBytes` independently to each source, keeps compac
|
||||
|
||||
#### What the model sees
|
||||
|
||||
The model sees two consecutive user-role messages: the current message with its readable `@label`, then the `## Referenced sessions` untrusted snapshot. The warning forbids following instructions, permission claims, or tool requests from the snapshot unless the citing user message requests their use. Labels, cwd values, ids, and conversation text are serialized as JSON inside `<referenced-sessions>` tags; every data `<` is emitted as the lossless JSON escape `\u003c`, so source text cannot spell a framing tag.
|
||||
The model sees two consecutive user-role messages: the current message with its readable `@label`, then the `## Referenced sessions` untrusted snapshot. The warning forbids following instructions, permission claims, or tool requests from the snapshot unless the current user explicitly repeats them. Labels, cwd values, ids, and conversation text are serialized as JSON inside `<referenced-sessions>` tags; every data `<` is emitted as the lossless JSON escape `\u003c`, so source text cannot spell a framing tag.
|
||||
|
||||
#### Token effect
|
||||
|
||||
|
||||
@@ -32,7 +32,7 @@
|
||||
|
||||
#### 模型看到的内容
|
||||
|
||||
模型会看到两条连续的 user 角色消息:先是带可读 `@label` 的当前消息,再是 `## Referenced sessions` 不受信任快照。警告禁止遵循快照中的指令、权限声明或工具请求,除非引用它的 user 消息要求使用这些内容。标签、cwd 值、id 与会话文本会作为 JSON 在 `<referenced-sessions>` 标签中序列化;数据中的每个 `<` 都会以无损 JSON 转义 `\u003c` 的形式发出,因此源文本无法拼出定界标签。
|
||||
模型会看到两条连续的 user 角色消息:先是带可读 `@label` 的当前消息,再是 `## Referenced sessions` 不受信任快照。警告禁止遵循快照中的指令、权限声明或工具请求,除非当前用户明确重复这些内容。标签、cwd 值、id 与会话文本会作为 JSON 在 `<referenced-sessions>` 标签中序列化;数据中的每个 `<` 都会以无损 JSON 转义 `\u003c` 的形式发出,因此源文本无法拼出定界标签。
|
||||
|
||||
#### Token 影响
|
||||
|
||||
|
||||
Reference in New Issue
Block a user