Skip to content

hy4flash: the prompt line splits the Engram's host step into waiting for rows and normalizing - #468

Open
giveen wants to merge 1 commit into
jesdga95:mainfrom
giveen:engram-prompt-timing
Open

giveen wants to merge 1 commit into
jesdga95:mainfrom
giveen:engram-prompt-timing

Conversation

@giveen

@giveen giveen commented Nov 19, 2026

Copy link
Copy Markdown
Contributor

Split out of #466 at review 5982149603, item 3, so that PR is only the ring retry.

What changed

engram_step timed the whole host step into one figure, and it ran on every call: a decode that followed a prompt added its own Engram work to the prompt line. Now:

  • the step is timed only while a prompt's buffers are open (big_.rows != 0), so the line reports a prompt;
  • it is split into the wait for PleReader::collect and the normalization loop, printed as (%.0f ms waiting for rows, %.0f ms normalizing);
  • the two figures are reset with the rest of the prompt counters when the prompt's buffers go back.

The log line's prefix, level and the figures the server parses are unchanged; the new text is inside the existing Engram clause.

Verification

…ts for rows

The one Engram figure was an undivided host step, and a decode that followed a prompt added its own Engram work to it. The step is now timed only while a prompt's buffers are open, and split into the wait for the reader's rows and the normalization.
@giveen
giveen force-pushed the engram-prompt-timing branch from 3f35369 to b7df086 Compare November 19, 2026 22:27

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant