Route with a fine-tuned e5-small instead of a generative model: three heads, no free generation #177

2026-08-06T11:21:18+02:00

claude commented

2026-08-06 11:21:18 +02:00

Closes Vikunja #546.

Acceptance criteria and quality gate are in TASK.md on this branch.
Review the review, not the diff — leave comments and the agent will apply them via task start 546.

Closes Vikunja #546. Acceptance criteria and quality gate are in `TASK.md` on this branch. Review the review, not the diff — leave comments and the agent will apply them via `task start 546`.

claude added 1 commit 2026-08-06 11:21:18 +02:00

label seeds with the stage 0 grammars and gemma, and measure both (V-546) 2b3e34c7e8

The plan calls the labeled set the whole project and names the stage 0
grammars as the label functions. cmd/labelgen runs them, the real ones in
buildRouter order, so a rule change moves the training data with it.

Gemma labels the rest at 334ms/call with nothing unparsed, which matches the
plan's estimate. It agrees with the seed files on 197/277, and reading the
disagreements is the finding: the seeds and the router prompt hold different
definitions of system, of a world question and of a bare verb. V-626.

claude merged commit c1d9a4547b into master

2026-08-06 16:25:52 +02:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: kami/Maven#177