0 Fork 1

Files

T

jason.woltje 2c38325eca row 66: managed sessions run the unslop check on both harnesses, the operator note on the RESULT, a correction notice on the next turn, and unslop.jsonl counts (#1559 )

Lands Sage's sage/row66-r5 at 7ffb640ac, round 4 (r4d 82c830779) rebased onto a36523713 after row 197,
approved by Dewey (comment 30085) and Filbert (30086) on manifest 6cfd812da4ca (23 paths, rev 2905). The
rebase had no conflict. The range-diff is = except one pi-session.test.mjs hunk header. Patch-id without
agents/ is d67275ac4251 on 7b9737953, a36523713 and this commit's parent. Gate (mos-1186): unslop,
harness, cli and every scripts/test-*.sh green on r4d, harness 149/0 again on r5. Landing sessions on a
scratch root from the candidate tree: Claude Code r4ab24630d323 showed the note, the injected notice and
counts checked 2, flagged 1, notices 1. Pi r1dd94171bede is launch only until #383 (Vikunja #454).

2026-10-21 13:51:28 -05:00

2.7 KiB

Raw Permalink Blame History

Row 66 landing sessions (mos-1186 items 2-3)

Sage, 2026-10-21. Both ran on a scratch data root built from the candidate tree, branch sage/row66-r5 at 273fff6f9 on a36523713, as row 64's D2 did (rc13bcd555652). The scripts were /mnt/storage/scratch/sage-r66r5x/d2s/d2-build.mjs and d2-drive.mjs. They used the business example with stand-in token files, tracker and Gitea URLs pointing at 127.0.0.1:9, and a scratch project repo. Nothing live was touched. The six skills were installed and enabled on each data root with scripts/skill.sh from the candidate tree.

Before the sessions, the harness suite ran whole on 273fff6f9: 149 pass, 0 fail, 12 s (2026-10-21T18:47:42Z).

Claude Code, run r4ab24630d323 (18:48Z)

The chief and cto were bound, and the coder was launched through launcher.fromSession on claude-code, model claude-sonnet-5-5. The launch bundle names tools/unslop-hook/claude-hook.js, unslop-check.js and lists.json.

Turn 1. cto asked for one sentence with four banned words. The RESULT body mosaic talk would print ends with the operator note: [unslop: 1 reply of this session flagged since the last note: banned word "additionally" x1; banned word "crucial" x1; banned word "testament" x1; banned word "vibrant" x1. The session gets a correction notice on its next turn.]
Turn 2. unslop.jsonl logs notice_injected for that turn. The coder's transcript has the notice as UserPromptSubmit hook additional context in the API request: UNSLOP NOTICE (mechanical style check, not the user speaking): your previous reply contained violations of the fleet writing standard (SYSTEM.md / ms-unslop): .... cto asked the coder to quote it. The coder answered "I can't answer that one, and I won't quote anything from it." So the notice reached the model, which chose not to repeat it. Its reply checked clean.
Counts from unslopCounts: checked 2, flagged 1, patterns ms-unslop:7 4, notices 1, broken null.

This scratch instance has no mosaic talk view of its own, so the note above is the RESULT body the bus returned to cto. That is the text mosaic talk and mosaic follow print.

pi, run r1dd94171bede (launch only)

The coder launched on pi, model claude-sonnet-5-5. The launch bundle names tools/unslop-hook/extension.ts, unslop-check.js and lists.json. No turn ran. This host has no credential pi reads until P19 #383 settles, and mos-0865 D2 rules out mapping the Claude Code token into a pi variable. No unslop.jsonl was written. Counts: checked 0, flagged 0, notices 0.

Still open

Vikunja #454 tracks both live checks. Claude Code runs in the first re-pin whose tree includes row 66, backup first. Pi runs one full session with a tell after #383. See docs/plans/DEFERRED.md.

2.7 KiB Raw Permalink Blame History

Row 66 landing sessions (mos-1186 items 2-3)

Claude Code, run r4ab24630d323 (18:48Z)

pi, run r1dd94171bede (launch only)

Still open

2.7 KiB

Raw Permalink Blame History