johba/harb
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
harb/planner/journal/2026-03-20.md
johba 810f47cdd6 chore: planner run journal 2026-03-20 (#1064) 
Planner journal entry from first cron-driven run.

Moved from disinto PR #390 — planner journals belong in the harb repo.

Reviewed-on: https://codeberg.org/johba/harb/pulls/1064
Reviewed-by: Disinto_bot <disinto_bot@noreply.codeberg.org>
2026-03-20 16:25:57 +01:00

2 KiB
Raw Blame History

Planner run — 2026-03-20 14:25 UTC

Predictions triaged

  • #1024: DISMISS — temporal "system idle" observation, stale; individual formula runs covered by other predictions
  • #1023: PROMOTE_BACKLOG → #1059 — evidence/resources and evidence/protocol have no formulas, not just missing data
  • #1022: WATCH — holdout/user-test depend on evolution output existing first
  • #1021: PROMOTE_ACTION → #1058 — red-team is independent, formula fix merged, first baseline needed for dual-gate evolution
  • #1020: WATCH — #1047 blocks clean evolution runs (results not committed via PR)

Issues created

  • #1058: action: run red-team formula on harb — first evidence baseline
  • #1059: feat: implement evidence/resources and evidence/protocol logging
  • #1060: feat: disinto init — one-command project bootstrap
  • #1061: feat: quickstart guide and architecture docs on disinto.ai
  • #1062: feat: live factory metrics dashboard on disinto.ai

Observations

  • Foundation milestone is complete: all 4 bullets working (agent loop, supervisor, planner, multi-project)
  • Adoption milestone is the bottleneck: no bootstrap command, no user-facing docs, landing page underutilized
  • Evidence pipelines: 4 formulas exist in harb but 0/6 evidence dimensions have data; #1047 blocks evolution specifically
  • Blocked issue ratio is high: disinto 64 blocked / 35 backlog, harb 50 blocked / 27 backlog — may indicate deep dependency chains
  • Disk at 79%, swap at 1828 MB — not critical but worth monitoring as evidence formulas start producing data
  • #341 (Extract Dark Factory) is stale — the extraction already happened; disinto IS the standalone repo

Deferred

  • Plugin system for custom agents — needs stable API and users first
  • Community-contributed formulas — depends on plugin system
  • Hosted option — too early, no external adoption yet
  • GitHub mirror — nice-to-have for reach, not blocking
  • Multi-project improvements — already working for 3 projects, refinement can wait