Commit Graph
6 Commits
Author SHA1 Message Date
steveandClaude Opus 4.8 7b150275ae Address #122 review: pageable read_journal, service-clock removal
Build image / build-and-push (push) Successful in 20s
- read_journal now takes an offset, so the hasMore it returns is
  actionable — an agent can page a journal longer than 50 entries.
- remove_planting goes through a new service RemovePlanting that stamps
  removed_at from s.now() (the injectable clock ClearObject and the fill
  path use), instead of the adapter computing the date off the wall clock.
  It delegates to UpdatePlanting, so the role check, version guard and
  history record are unchanged. Drops the now-unused time import.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01H3zbym8Doka2d7D48maSgZ
2026-07-22 21:39:20 -04:00
steveandClaude Opus 4.8 887a3c2cc6 Agent: add the corrective tools the toolbox was missing (#85 item 3)
Build image / build-and-push (push) Successful in 6s
Gadfly review (reusable) / review (pull_request) Successful in 10m8s
Adversarial Review (Gadfly) / review (pull_request) Successful in 10m8s
The toolbox could create and move but not delete or resize; write the
journal but not read it; clear a whole bed but not pull one plant; report
seed remaining but not record a purchase. Close those gaps with thin
adapters over the SAME service methods the REST API uses, so they inherit
the permission checks unchanged:

  read_journal    → ListJournal   (the write/read asymmetry, most visible)
  update_object   → UpdateObject  (resize / rotate / rename / plantable)
  delete_object   → DeleteObject  (counterpart to create_object)
  remove_planting → UpdatePlanting (soft-remove ONE plop, like clear does)
  list_seed_lots  → ListSeedLots
  record_seed_lot → CreateSeedLot (record a purchase; "I bought 2 packets")

To address a single plop the agent needs its id + version, so
DescribePlanting now carries both — the same way DescribeObject.Version
already lets it edit an object. remove_planting soft-removes (removed_at =
today), mirroring clear_object, so the plant stays in planting history and
the change is undoable.

Deferred deliberately: an undo/revert tool needs a way to list recent
change sets to get a changeSetId, which is a larger addition; noted on the
issue for a follow-up.

Tested through the tool layer (TestCorrectiveTools): resize, single-plop
removal, journal read-back, seed-lot record+list, and delete.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01H3zbym8Doka2d7D48maSgZ
2026-07-22 21:23:46 -04:00
steveandClaude Opus 4.8 7c1faa1515 Fill mode: a "grid" layout that plants individual plants in rows (#77)
Build image / build-and-push (push) Successful in 6s
Gadfly review (reusable) / review (pull_request) Successful in 12m51s
Adversarial Review (Gadfly) / review (pull_request) Successful in 12m51s
Steve chose option 3: keep clumps as the default primitive, add a grid/rows
fill mode, so sketching and planning are different operations with different
outputs rather than one model forced to be both.

A plop is a CLUMP, not a plant — great for "a few plops of garlic in a corner",
useless for drawing a plantable 8-rows-of-garlic bed (that came out as ~15
blobs, #77). FillLayout selects what a fill packs:
- clump (default, unchanged): radius 1.5×spacing, ~7 plants per plop.
- grid: radius spacing/2, pitch = spacing, ONE plant per plop — rows you could
  actually plant from.

The geometry is the SAME hexCenters lattice and the SAME #75 half-spacing edge
rule; only the radius→spacing relationship differs (plopRadiusFor). Grid keeps
no 15cm floor — its whole point is true spacing — while clump keeps it so a
tiny-spacing plant doesn't make invisible clumps.

Threaded through FillRegion/FillNamedRegion (empty layout = clump, so existing
callers are unchanged; unknown layout = ErrInvalidInput), the REST /fill
endpoint (`layout`), and the agent's fill_region tool (`mode`, enum clump|grid),
so "plant the bed in rows" works.

Tests: grid produces many more, single-plant plops than clump on the same bed
(radius spacing/2, derived count 1); unknown layout is refused at both the
service and the API. maxFillPlops still caps a grid fill of a huge bed.

No frontend fill affordance exists yet (fill is agent-only in the UI; the fill
UI was deferred in #82), so the mode toggle rides along when that's built —
noted. Docs: DESIGN placement-model decision.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01H3zbym8Doka2d7D48maSgZ
2026-07-22 00:01:27 -04:00
steve 3a3ce16fce Agent runtime: majordomo in-process, Ollama Cloud config, chat endpoint (#56) (#70)
Build image / build-and-push (push) Successful in 6s
Co-authored-by: Steve Dudenhoeffer <[email protected]>
2026-07-21 06:22:10 +00:00
steve a1bb8ec463 Agent tools: plant lookup, plant creation, journal entries (#55) (#69)
Build image / build-and-push (push) Successful in 11s
Co-authored-by: Steve Dudenhoeffer <[email protected]>
2026-07-21 06:05:05 +00:00
steve 18e4a299c2 Agent seam: bulk ops (FillRegion/ClearObject/DescribeGarden) + DefineTool wrappers (#19)
Build image / build-and-push (push) Successful in 5s
Co-authored-by: Steve Dudenhoeffer <[email protected]>
2026-07-19 05:16:40 +00:00