-
Notifications
You must be signed in to change notification settings - Fork 927
perf(agent-core): drop dynamic timestamp from system prompt to restore prefix-cache hits #2533
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
daofazhiran
wants to merge
2
commits into
MoonshotAI:main
Choose a base branch
from
daofazhiran:perf/system-prompt-prefix-cache
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
2 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| --- | ||
| "@moonshot-ai/kimi-code": patch | ||
| --- | ||
|
|
||
| Replace the per-session timestamp in the default system prompt with a static time-lookup reminder. The timestamp changed on every new session, breaking DeepSeek's byte-prefix cache from that point onward — including the ~16.8k-token tools definition — so every new session's first LLM call missed the cache. First-turn cache-miss input drops from ~19.5k tokens to ~88 tokens (99.6% cache hit measured on the built artifact). The static `## Date and Time` section keeps the instruction to fetch the real current time from the environment (e.g. via the `date` command) when it matters, without the cache-breaking value. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
For time-sensitive requests, deleting this whole section removes more than the dynamic ISO value: it also removes the only default-prompt instruction that the agent must refresh the real time from the environment. I checked the remaining default prompt and the only
datemention left is the Bash tool's command list, so cases like expiry/age checks or “what is today?” can be handled from model priors or stale context instead of querying the host. Keep a static, cache-friendly reminder to check the current time when it matters, and mirror it in the legacy prompt too.Useful? React with 👍 / 👎.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Addressed in
61389c6ab— kept## Date and Timeas a static reminder ("get it fresh from the environment, e.g. via thedatecommand") and mirrored it in the legacy template too. No per-session value remains, so byte-prefix caching is unaffected. The added tests assert the rendered prompt is byte-identical across differentnowvalues.