Run the persona checks inside the daemon before she speaks #143

2026-08-04T02:35:44+02:00

claude commented

2026-08-04 02:35:44 +02:00

Closes Vikunja #399.

Opened during an unattended overnight run: the diff-budget block was off (task overnight). Read the diff, not only the tests.

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 399.

Closes Vikunja #399. Opened during an unattended overnight run: the diff-budget block was off (`task overnight`). Read the diff, not only the tests. 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 399`.

kami approved these changes 2026-08-04 13:10:28 +02:00

claude commented

2026-08-04 18:20:07 +02:00

Reviewed as part of a bottom-up pass over the whole open stack (#119 to #168): commits read against the base branch, make test green at the top of the stack. Nothing to raise on this one. Merging.

Four findings landed on the PRs they belong to, none of them blocking: #167 (a duplicate rest-of-day-query grammar from the merge), #164 (four files the Russian sweep did not reach), #145 (sh -c hides an irreversible verb from the tier derivation), #128 (locationCandidates drops short city names).

Reviewed as part of a bottom-up pass over the whole open stack (#119 to #168): commits read against the base branch, `make test` green at the top of the stack. Nothing to raise on this one. Merging. Four findings landed on the PRs they belong to, none of them blocking: #167 (a duplicate `rest-of-day-query` grammar from the merge), #164 (four files the Russian sweep did not reach), #145 (`sh -c` hides an irreversible verb from the tier derivation), #128 (`locationCandidates` drops short city names).

claude changed target branch from task/443-safekey-drops-cyrillic-so-russian-calend to master

2026-08-04 18:24:35 +02:00

claude added 1 commit 2026-08-04 18:24:35 +02:00

mavend: run the persona checks before she speaks (V-399) afac8fb670

The checks stay in the eval package and the daemon calls three of them:
feminine, address, and a new leaked-reasoning test. No retry — it doubles
the latency on the turn that is already going badly, and on the nudge path
the moment has passed. A failure falls back to the deterministic floor and
is logged with the whole rejected text and counted by check name.

hisgender is deliberately not run: the simulator showed it rejecting
"записала, что ты выпил воды", which is her own correct self-reference.

claude merged commit db0752223f into master

2026-08-04 18:24:37 +02:00

Sign in to join this conversation.

2 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: kami/Maven#143