feat(engine): name the served model on each perfstats line #108

Merged
rcsheets merged 1 commit from feat/perfstats-served-model into main 2026-10-02 19:58:35 +00:00
Owner

The periodic engine: perfstats line (serve --log-perfstats-interval) now carries a served_model field with the served model name, as its first field.

The name was previously only in the startup log, so a perfstats line read on its own, or in a log that aggregates several instances, did not say which model it measured. The key matches the served_model field the engine already uses when it warns about a generic default name.

The weight-loading progress lines that share the interval are unchanged.

Testing

go build ./..., go vet ./..., gofmt and go test ./... are clean. A new engine test runs the perfstats loop and checks every line names the served model; it passes under -race.

🤖 Generated with Claude Code

The periodic `engine: perfstats` line (`serve --log-perfstats-interval`) now carries a `served_model` field with the served model name, as its first field. The name was previously only in the startup log, so a perfstats line read on its own, or in a log that aggregates several instances, did not say which model it measured. The key matches the `served_model` field the engine already uses when it warns about a generic default name. The weight-loading progress lines that share the interval are unchanged. ## Testing `go build ./...`, `go vet ./...`, `gofmt` and `go test ./...` are clean. A new engine test runs the perfstats loop and checks every line names the served model; it passes under `-race`. 🤖 Generated with [Claude Code](https://claude.com/claude-code)
feat(engine): name the served model on each perfstats line
All checks were successful
ci / test_and_build (pull_request) Successful in 30s
22f2d90bcd
The periodic "engine: perfstats" line now starts with a served_model
field, so a line read on its own, or in a log that aggregates several
instances, says which model it measures.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Collaborator

❓ Verdict: No verdict returned

Jump to the current review

Review history
  • 2026-10-02 09:36 UTC · safety check · failed · r-bf7b28-88d5c1
  • 2026-10-02 10:19 UTC · safety check · No verdict returned · r-bf8518-6cd9c1 · current
<!-- pr-reviewer:history --> **❓ Verdict: No verdict returned** [Jump to the current review](#issuecomment-4809) <details><summary>Review history</summary> - 2026-10-02 09:36 UTC · safety check · failed · `r-bf7b28-88d5c1` - 2026-10-02 10:19 UTC · safety check · No verdict returned · `r-bf8518-6cd9c1` · **current** </details>
Author
Owner

@pr-reviewer-bot review

@pr-reviewer-bot review
Collaborator

Automated review by pr-reviewer v0.52.3 | Safety Check | Granite | tracking id r-bf8518-6cd9c1
This is an AI-generated review and may contain mistakes.

Status: ✅ Completed


❓ Verdict: No verdict returned

(No review body returned)

<!-- pr-reviewer:review --> *Automated review by [pr-reviewer](https://git.brooktrails.org/brooktrails/pr-reviewer) v0.52.3 | Safety Check | Granite | tracking id `r-bf8518-6cd9c1`* *This is an AI-generated review and may contain mistakes.* **Status:** ✅ Completed --- **❓ Verdict: No verdict returned** (No review body returned)
rcsheets deleted branch feat/perfstats-served-model 2026-10-02 19:58:36 +00:00
Sign in to join this conversation.
No reviewers
No labels
No milestone
No project
No assignees
2 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference
brooktrails/gllm!108
No description provided.