Skip to content

Context estimate very incorrect when using with local strata server #96

Closed

Description

@Eeems

When using Strata locally, I'm seeing agentty report 65.0k/65.5k while streaming a response, and then sometimes resetting down to the actual 33.0k/65.5k context size after the request completes. I'm often seeing the context size reported by agentty report being above 100% even though the strata web dashboard reports it at a much lower value. This makes the context usage estimate extremely unreliable as it rarely reports anything near what is in actual use.

Strata makes current prompt token usage available in the /metrics endpoint at .live.prompt_tokens, which can be used instead of guessing current context usage.

Activity

  1. 1ay1 commented on Oct 15, 2026

    @1ay1
    Owner

    fixed in 60f3e22 and 1c3ebfd, cached tokens were counted twice on openai-style servers like strata so 33k read as 65k; the gauge now shows the real prompt size, reopen if you still see it off.

  2. web-connect commented on Oct 15, 2026

    @web-connect

    I might see off. Maybe verify with author before closing

  3. 1ay1 commented on Oct 15, 2026

    @1ay1
    Owner

    hehe, lemme know I will reopen it

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions