johba/harb
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

chore: planner run journal 2026-03-20 (#1064)

Browse source 
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>
This commit is contained in:
johba 2026-03-20 16:25:57 +01:00
parent 8583ec9119
commit 810f47cdd6
2 changed files with 63 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

33
planner/MEMORY.md Normal file
View file

@ -0,0 +1,33 @@
# Planner Memory
## 2026-03-20 — First planner run
### Milestone state
- **Foundation**: COMPLETE. Agent loop, supervisor, planner, multi-project all working.
- **Adoption**: NOT STARTED. No bootstrap command, no docs, landing page exists but lacks content.
- **Scale**: PARTIALLY started (multi-project works for 3 repos).
### Evidence pipeline state
- 6 evidence dimensions defined (red-team, evolution, holdout, user-test, resources, protocol)
- 4 have formulas in harb (red-team, evolution, holdout, user-test) — all recently fixed
- 2 have NO formulas at all (resources, protocol) — filed #1059
- 0/6 dimensions have any data on disk
- #1047 blocks evolution specifically (results not committed via PR)
- Red-team is independent and was dispatched as action #1058
### Patterns
- Predictor (goblin) over-signals on evidence gaps — all 5 predictions were about missing evidence data. Expected to normalize once pipelines produce their first runs.
- High blocked:backlog ratio across projects suggests deep dependency chains. Gardener should be monitoring for circular deps.
- The factory is self-hosting successfully — all agents run, CI passes, PRs merge. The gap is external visibility, not internal capability.
### Strategic direction
- Adoption is the leverage multiplier: everything in Scale depends on having users first.
- Created #1060 (disinto init), #1061 (docs), #1062 (metrics dashboard) as the Adoption on-ramp.
- #1061 depends on #1060 — quickstart needs the bootstrap flow to reference.
- #1062 (metrics dashboard) is the social proof play — show the factory working rather than just claiming it.
### Watch list
- #1020 + #1047: evolution pipeline needs commit-via-PR fix before runs produce persistent evidence
- #1022: holdout/user-test blocked on evolution data existing
- #341: stale issue (extraction already done) — gardener should close or update
- Disk at 79% — evidence formulas will add data; monitor trajectory

30
planner/journal/2026-03-20.md Normal file
View file

@ -0,0 +1,30 @@
# 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