Address fifth round of Gadfly findings on #76

- fillLoaded's doc listed what it does and omitted the non-finite-region
  rejection this PR added to it.
- Trim the half-spacing rule's restatement in DESIGN.md to the decision and a
  pointer. The rule, the square-foot arithmetic and the failure mode are
  written out once, in hexCenters, rather than near-verbatim in four places.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01H3zbym8Doka2d7D48maSgZ

CLAUDE.md

@@ -85,6 +85,12 @@ Frontend: React 19 + Vite + Tailwind 4 + TanStack Router/Query, built into
   deliberately. `ErrForbidden` means "you can see it but may not do that".
 - **Plops (plantings) live in their parent object's local frame**, origin at the
   object's center, `-y` is north. Moving or rotating a bed moves its plants free.
+- **A plop is a clump, not a plant.** `defaultPlopRadius` is `1.5 × spacing`, so a
+  plop is three spacings across and holds `π·r²/spacing²` plants. Reasoning about
+  fills as if one plop were one plant gets the geometry wrong every time — which
+  is how #75 happened: requiring the whole circle inside the bed inset the outer
+  row by 1.5 spacings when the horticultural rule is *half* a spacing. Spacing is
+  a constraint between neighbouring plants; a bed edge is nobody's neighbour.
 - **Soft removal**: "clear bed" sets `removed_at`; the editor reads
   `removed_at IS NULL`. Hard delete is a different operation.
 - **Migrations** are numbered `.sql` files in `internal/store/migrations/`, run
@@ -92,6 +98,29 @@ Frontend: React 19 + Vite + Tailwind 4 + TanStack Router/Query, built into
 - **Every service mutation lands in history** (#48). If you add one, record it —
   see `internal/service/revisions.go`. Multi-row operations pass all their
   changes to a single `record` call so they undo as one unit.
+- **The history write is detached from cancellation on purpose.** `commitScope`
+  calls `context.WithoutCancel` — that is not a mistake to tidy up. By the time
+  a commit runs, the rows it describes are already written, so cancelling it
+  cannot undo anything; it can only leave real changes with no way to undo them.
+  This was a live bug twice (#73): a client disconnect mid-request orphaned 18
+  plantings. Fixing it per-call-site is how it came back, which is why the rule
+  lives in `commitScope` where no caller can forget it.
+
+## Testing
+
+Match the test to the failure it would catch:
+
+- **Anything addressed by its own id needs an API-level test through the router.**
+  Service tests can't see a route that was never registered — PATCH/DELETE
+  `/journal/:id` once shipped fully implemented, fully unit-tested, and
+  completely unreachable.
+- **Watch for fixtures that assert your assumptions instead of the API.** A test
+  for the undo message passed because the fixture I wrote populated a field the
+  real response leaves empty. If a test builds the thing it's testing against,
+  it is checking your mental model, not the system.
+- Some things only real use finds. The agent's whole loop is covered by
+  majordomo's scriptable fake provider (`provider/fake`), which is worth using —
+  but the three worst v2 bugs all turned up in one live session afterwards.
 
 ## Workflow
 
@@ -100,6 +129,22 @@ fix what's real → merge when the pipeline is green. Do not grade Gadfly findin
 A push to `main` builds the image and deploys to Komodo; the live instance at
 `pansy.orgrimmar.dudenhoeffer.casa` updates a few minutes later.
 
+**Gadfly reviews the PR as opened, not as merged.** The workflow triggers on
+`opened`/`reopened`/`ready_for_review` — deliberately *not* `synchronize` — so
+every commit you push afterwards, including the ones you push in response to
+Gadfly itself, is unreviewed unless you ask. Once you've stopped pushing and
+before you merge, comment **`@gadfly review`** on the PR to re-trigger it. The
+phrase is required, and this is not hypothetical: on #76 the follow-up commit
+was the one that contained a real bug.
+
+**A skipped Gadfly run reports success.** A comment without the trigger phrase
+still starts the workflow, which logs `comment does not contain trigger phrase`
+and exits green in ~2 seconds. So "the pipeline is green" does NOT mean "this
+was reviewed". Confirm a re-review actually ran by its **duration** — a real
+pass takes ~10 minutes, a skip takes 2 seconds. Don't look for a new consensus
+comment: Gadfly EDITS its existing status-board and consensus comments in place,
+so their `created_at` stays at the first review and only `updated_at` moves.
+
 Workflow- and config-only changes (CI, this file, docs) go straight to `main`
 without the PR dance.
 
@@ -113,7 +158,16 @@ implemented in later per-issue sessions.
 the `_PATH`/`_ADDR` names you might guess. Authentik is the primary IdP;
 OIDC-first with local passwords as fallback.
 
-Agent config (v2): `OLLAMA_CLOUD_API_KEY` and `PANSY_AGENT_MODEL` (default
+Agent config: `OLLAMA_CLOUD_API_KEY`, `PANSY_AGENT_MODEL` (default
-`ollama-cloud/glm-5.2:cloud`), set in Komodo. Model strings pass verbatim to
+`ollama-cloud/glm-5.2:cloud`) and `PANSY_AGENT_ENABLED`, set in Komodo. Model
-`majordomo.Parse`, so a comma-separated spec gives failover for free.
+strings pass verbatim to `majordomo.Parse`, so a comma-separated spec gives
-`majordomo` and `executus` are sibling repos at `../`.
+failover for free — don't parse that grammar in pansy.
+
+`majordomo` is a **real dependency** now, resolved from the Gitea instance as a
+pseudo-version. There is no `replace` directive and there must not be one: a
+`replace` pointing at `../majordomo` builds on your laptop and breaks the Docker
+build, which has no sibling checkout. `executus` is a sibling repo at `../` and
+is not a dependency.
+
+The `majordomo` build tag is **gone**. Don't reintroduce it — an untagged CI that
+never compiles the agent is worse than a slightly larger binary.

DESIGN.md

@@ -7,6 +7,7 @@ Work is tracked in Gitea issues; the tracking epic links every piece in dependen
 ## Decisions
 
 - **Placement model:** freeform plops (not a square-foot grid), scaled by real plant spacing. Grid snapping may come later as a toggle.
+- **Spacing is a plant-to-plant rule, so bed edges get half of it.** A bed edge is not a competitor for soil, light or water, so the outer row owes it half the spacing rather than a full one. `FillRegion` centres its lattice accordingly, and lets a plop — a *clump* three spacings across — cross the edge by up to half a spacing so its outermost plants land at that half-spacing. The rule, the square-foot-chart arithmetic behind it, and the failure mode it prevents are written out once in `hexCenters`; #75 is what getting it wrong looked like.
 - **Stack:** Go 1.26.x backend, module `gitea.stevedudenhoeffer.com/steve/pansy`; React + TypeScript + Vite + Tailwind frontend, production build embedded via `embed.FS` → one static binary (`CGO_ENABLED=0`).
 - **Users:** multi-user with ownership. Users own gardens; a garden can be shared with other users as viewer (read) or editor (edit content). Owner additionally shares/deletes.
 - **Auth:** OIDC-first (Authentik is the primary IdP), local argon2id passwords as an optional fallback.
@@ -23,6 +24,7 @@ SQLite, centimeters everywhere (display-side imperial conversion only), `version
 - **garden_objects** — one polymorphic table: `kind` (`bed`|`grow_bag`|`container`|`in_ground`|`tree`|`path`|`structure`), name, `shape` (`rect`|`circle`; `polygon` + `points` JSON reserved in schema, not in the v1 editor), center `x_cm`,`y_cm` in garden space, `width_cm`,`height_cm` (circle: width=diameter), `rotation_deg`, `z_index`, `plantable` bool, nullable `color` override, `props` JSON for kind-specific extras (bed height, tree species…), notes.
 - **seed_lots** — one purchase: vendor, source URL, sku, lot code, purchase date, packed-for year, quantity + unit, cost, germination %. `owner_id` is on the LOT, not inherited from the plant, so you can record buying generic built-in Garlic from Johnny's and keep it private. `plantings.seed_lot_id` (ON DELETE SET NULL) attributes a plop to a purchase; **`remaining` is derived** (quantity − summed effective count of active plantings), never stored — a decremented column drifts the moment a planting is edited behind its back and can't be audited afterwards. Lots are never shared along with a garden.
 - **plants** — catalog, plus `source_url`/`vendor` provenance for the variety itself. `owner_id NULL` = built-in (~30 seeded via migration, read-only, clone to customize). name, category (`vegetable`|`herb`|`flower`|`fruit`|`tree_shrub`|`cover`), `spacing_cm` (mature spacing), `color` hex, `icon` (emoji string — zero assets in v1), nullable `days_to_maturity`, notes. Users see built-ins + their own.
+- **agent_conversations** / **agent_messages** — the assistant's chat, one thread per (user, garden). Only the user/assistant TEXT of each turn is stored, not the model's full transcript: continuity needs what was said and what came back, and replaying a stored tool call would replay a decision made against a garden that has since moved on. `agent_messages.change_set_id` is the handle the chat panel uses to offer Undo on the turn that caused it.
 - **journal_entries** — the grow log: `garden_id` (NOT NULL), nullable `object_id`/`planting_id` to narrow the target, author, body, `observed_at`. `notes` on a garden/object/plant says what the thing IS and a new note overwrites the old; a journal entry says what HAPPENED and when, and entries accumulate. `garden_id` is set even for a bed- or plop-level entry so permission checks reuse `requireGardenRole` unchanged rather than inventing a second ACL path. `observed_at` is distinct from `created_at` — you write up Saturday's observations on Sunday. Deliberately **not** in the revision history: entries are already append-shaped and individually versioned.
 - **change_sets** / **revisions** — the undo substrate. A change set groups the row-level revisions one logical operation produced (`source` ui/agent/api, `summary`, nullable `agent_run_id`, nullable `reverts_id`); a revision is `(entity_type, entity_id, op, before, after)` with full JSON row snapshots. The unit of undo is the **operation, not the row**. Revert is itself a change set, so an undo can be undone; it is version-guarded per entity and reports conflicts rather than clobbering a later edit. Garden *deletion* is deliberately not revertible (the cascade is invisible to the service, and would take the history with it).
 - **plantings** ("plops") — object_id, plant_id, center `x_cm`,`y_cm` **in the parent object's local frame** (moving/rotating a bed moves its plants for free), `radius_cm` (a plop is a circular patch), nullable `count` (NULL = derived: `max(1, round(π·r² / spacing_cm²))`), nullable label, `planted_at`/`removed_at` dates. "Clear bed" sets `removed_at`; v1 shows rows where `removed_at IS NULL`. Year-over-year history and a future plan/scenario layer build on these dates without schema surgery.
@@ -64,6 +66,11 @@ POST /gardens/:id/objects     PATCH,DELETE /objects/:id
 POST /objects/:id/plantings   PATCH,DELETE /plantings/:id
 GET,POST /plants              PATCH,DELETE /plants/:id            (own plants only)
 GET,POST /seed-lots           GET,PATCH,DELETE /seed-lots/:id     (own lots only; private)
+GET,POST /gardens/:id/journal PATCH,DELETE /journal/:id           (editor writes; author edits own)
+GET  /gardens/:id/journal/counts  ← entries per object, for the "has notes" indicator
+POST /agent/chat              ← SSE: step events, then the finished turn (editor only)
+GET,DELETE /gardens/:id/agent/history                             (the actor's own thread)
+GET  /capabilities            ← what this instance can do, so the UI offers only what works
 GET,POST /gardens/:id/shares  PATCH,DELETE /gardens/:id/shares/:userId    (invite by email)
 ```
 
@@ -77,6 +84,7 @@ GET,POST /gardens/:id/shares  PATCH,DELETE /gardens/:id/shares/:userId    (invit
 cmd/pansy/main.go        config load → store.Open → migrate → service → api → ListenAndServe
 internal/config/         PANSY_PORT, PANSY_DB, PANSY_BASE_URL, PANSY_REGISTRATION,
                          PANSY_OIDC_* (issuer/client_id/secret/button label), PANSY_LOCAL_AUTH,
+                         PANSY_AGENT_MODEL / OLLAMA_CLOUD_API_KEY / PANSY_AGENT_ENABLED,
                          trusted proxies
 internal/store/          sqlite.go (open/pragmas), migrate.go, migrations/*.sql (embedded),
                          queries per entity (users.go, gardens.go, objects.go, plantings.go,
@@ -89,7 +97,8 @@ internal/service/        ★ THE SEAM. All permission checks + business ops. aut
 internal/api/            thin gin handlers (decode → service → encode), session middleware,
                          ginserver setup, routes.go, oidc.go, spa.go (embed fallback)
 internal/webdist/        dist.go: //go:embed all:dist   (web build copied in by Makefile)
-internal/agent/          later: llm.DefineTool[Args] wrappers over the SAME service methods
+internal/agent/          tools.go (llm.DefineTool wrappers over the SAME service methods),
+                         runtime.go (model resolution, run loop, one change set per turn)
 web/                     Vite app
 Makefile                 (cd web && npm run build) → copy dist → CGO_ENABLED=0 go build
 ```
@@ -111,7 +120,7 @@ React 19 + TypeScript + Vite + Tailwind 4 (`@tailwindcss/vite`), `@tanstack/reac
 - **Routes:** `/login`, `/register`, `/gardens` (list), `/gardens/:id` (editor, `?focus=objectId`), `/plants` (catalog). Auth guard on the router root via `/auth/me`.
 - **State:** TanStack Query for all server state (editor keyed on `gardens/:id/full`; optimistic mutations with version-conflict rollback). One small Zustand store for ephemeral editor state only: viewport, selection, focused object, active tool, in-flight drag.
 - **Editor components (`web/src/editor/`):** `GardenCanvas` (svg root + viewport g), `useViewport` (use-gesture pan/zoom/pinch), `ObjectShape`, `PlopMarker` (semantic-zoom branching), `Palette` (drag-to-place object kinds), `EditorRail` (the one side panel), `Inspector`, `HistoryPanel`, `PlantPicker`.
-- **One rail, tabs inside it.** The inspector, history, journal, and later the chat panel all want the same strip of screen; rather than each bolting on its own chrome they are tabs in `EditorRail` — so the canvas is one width instead of a different width per panel, and adding a panel is adding a tab. Selecting an object switches to the Inspector tab automatically, so the rail is never something you operate before you can edit; on a phone the same tabs render in the bottom sheet the inspector already used. Pure geometry helpers (local↔world transforms, unit formatting) in `web/src/lib/geometry.ts`, unit-tested.
+- **One rail, tabs inside it.** The inspector, history, journal and assistant all want the same strip of screen; rather than each bolting on its own chrome they are tabs in `EditorRail` — so the canvas is one width instead of a different width per panel, and adding a panel is adding a tab. Selecting an object switches to the Inspector tab automatically, so the rail is never something you operate before you can edit; on a phone the same tabs render in the bottom sheet the inspector already used. Pure geometry helpers (local↔world transforms, unit formatting) in `web/src/lib/geometry.ts`, unit-tested.
 
 ## Roadmap
 
@@ -123,7 +132,8 @@ React 19 + TypeScript + Vite + Tailwind 4 (`@tailwindcss/vite`), `@tanstack/reac
 6. **Plops** — focus-zoom, place/move/resize, derived counts, semantic zoom. *The core vision lands here.*
 7. **Sharing** — invite by email, roles, viewer read-only mode.
 8. **Polish** — imperial toggle, mobile ergonomics, clear-bed, keyboard nudging.
-9. **Agent seam** — `ops.go` bulk ops + `internal/agent` DefineTool wrappers; optional mort-style API-key agent endpoint. The agent harness itself lives in majordomo/executus, outside pansy.
+9. **Agent seam** — `ops.go` bulk ops + `internal/agent` DefineTool wrappers.
+10. **Garden assistant** — majordomo in-process, Ollama Cloud, streaming chat. Each turn runs inside ONE change set (`source='agent'`), so a turn that clears a bed and replants it undoes as one action; that is what makes acting without a confirmation prompt defensible. Bounded by a step cap and a timeout — loop safety, not spend control. The `majordomo` build tag is gone: a tag that keeps the agent out of the binary only earns its keep if you'd ship a build without it, and the agent is the point.
 
 ## Deliberate v1 limits
 

README.md

@@ -63,12 +63,17 @@ All configuration is via environment variables; every value has a default, so `.
 | `PANSY_OIDC_BUTTON_LABEL` | `Sign in with Authentik` | Label for the OIDC button on the login page.                |
 | `PANSY_TRUSTED_PROXIES`   | *(none)*           | Comma-separated proxy CIDRs/IPs to trust for client-IP resolution. |
 
-The garden assistant reads two more. Both are **read only once the assistant lands** ([#56](https://gitea.stevedudenhoeffer.com/steve/pansy/issues/56)); setting them earlier is harmless and setting neither leaves the assistant off.
+The garden assistant reads three more. Setting none of them leaves the assistant off; the app runs exactly as it does without it.
 
 | Variable                | Default                        | Description                                                                 |
-| ----------------------- | ----------------------------- | --------------------------------------------------------------------------- |
+| ----------------------- | ------------------------------ | --------------------------------------------------------------------------- |
-| `OLLAMA_CLOUD_API_KEY`  | *(empty)*                     | Ollama Cloud API key. Without it the assistant is disabled, not broken.      |
+| `OLLAMA_CLOUD_API_KEY`  | *(empty)*                      | Ollama Cloud API key. Without it the assistant is disabled, not broken — the chat routes simply aren't registered. |
-| `PANSY_AGENT_MODEL`     | `ollama-cloud/glm-5.2:cloud`  | Model spec, passed verbatim to `majordomo.Parse` — a comma-separated list is a failover chain. |
+| `PANSY_AGENT_MODEL`     | `ollama-cloud/glm-5.2:cloud`   | Model spec, passed verbatim to `majordomo.Parse` — a comma-separated list is a failover chain, e.g. `ollama-cloud/glm-5.2:cloud,ollama-cloud/kimi-k2.6:cloud`. |
+| `PANSY_AGENT_ENABLED`   | on when a key is present       | Turns the assistant off without removing the key.                            |
+
+The assistant acts without asking first, which is only reasonable because every turn is one undoable change set — see the History panel in the editor.
+
+**If you set the key and the assistant still doesn't appear**, check that the variable reaches the *container*, not just your orchestrator's stack config — Compose needs it listed under the service's `environment:`. pansy logs `garden assistant disabled` at startup with which of the three conditions failed, so the answer is in the first few lines of the log.
 
 Local email/password auth is live (`POST /api/v1/auth/register`, `/auth/login`, `/auth/logout`, `GET /auth/me`, `GET /auth/providers`); the session is an HttpOnly cookie (`Secure` when `PANSY_BASE_URL` is https). The first account registered becomes admin, and it may register even when `PANSY_REGISTRATION=closed` to bootstrap the instance.
 
@@ -108,7 +113,8 @@ services:
       # PANSY_OIDC_ISSUER: https://auth.example.com/application/o/pansy/
       # PANSY_OIDC_CLIENT_ID: ...
       # PANSY_OIDC_CLIENT_SECRET: ...
-      # OLLAMA_CLOUD_API_KEY: ...     # enables the garden assistant
+      # OLLAMA_CLOUD_API_KEY: ${OLLAMA_CLOUD_API_KEY}   # enables the garden assistant
+      # PANSY_AGENT_MODEL: ollama-cloud/glm-5.2:cloud
     restart: unless-stopped
 volumes:
   pansy-data:

go.mod

@@ -3,14 +3,30 @@ module gitea.stevedudenhoeffer.com/steve/pansy
 go 1.26.2
 
 require (
+	gitea.stevedudenhoeffer.com/steve/majordomo v0.0.0-20260718232210-a941f5ff4a3f
 	github.com/coreos/go-oidc/v3 v3.20.0
 	github.com/gin-gonic/gin v1.10.1
 	github.com/samber/slog-gin v1.15.0
-	golang.org/x/crypto v0.31.0
+	golang.org/x/crypto v0.36.0
 	golang.org/x/oauth2 v0.36.0
 	modernc.org/sqlite v1.34.4
 )
 
+require (
+	cloud.google.com/go v0.116.0 // indirect
+	cloud.google.com/go/auth v0.9.3 // indirect
+	cloud.google.com/go/compute/metadata v0.5.0 // indirect
+	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
+	github.com/google/go-cmp v0.6.0 // indirect
+	github.com/google/s2a-go v0.1.8 // indirect
+	github.com/googleapis/enterprise-certificate-proxy v0.3.4 // indirect
+	github.com/gorilla/websocket v1.5.3 // indirect
+	go.opencensus.io v0.24.0 // indirect
+	google.golang.org/genai v1.59.0 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1 // indirect
+	google.golang.org/grpc v1.66.2 // indirect
+)
+
 require (
 	github.com/bytedance/sonic v1.11.9 // indirect
 	github.com/bytedance/sonic/loader v0.1.1 // indirect
@@ -40,9 +56,9 @@ require (
 	go.opentelemetry.io/otel v1.29.0 // indirect
 	go.opentelemetry.io/otel/trace v1.29.0 // indirect
 	golang.org/x/arch v0.8.0 // indirect
-	golang.org/x/net v0.33.0 // indirect
+	golang.org/x/net v0.38.0 // indirect
-	golang.org/x/sys v0.28.0 // indirect
+	golang.org/x/sys v0.31.0 // indirect
-	golang.org/x/text v0.21.0 // indirect
+	golang.org/x/text v0.23.0 // indirect
 	google.golang.org/protobuf v1.34.2 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 	modernc.org/gc/v3 v3.0.0-20240107210532-573471604cb6 // indirect

go.sum

@@ -1,11 +1,24 @@
+cloud.google.com/go v0.26.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw=
+cloud.google.com/go v0.116.0 h1:B3fRrSDkLRt5qSHWe40ERJvhvnQwdZiHu0bJOpldweE=
+cloud.google.com/go v0.116.0/go.mod h1:cEPSRWPzZEswwdr9BxE6ChEn01dWlTaF05LiC2Xs70U=
+cloud.google.com/go/auth v0.9.3 h1:VOEUIAADkkLtyfr3BLa3R8Ed/j6w1jTBmARx+wb5w5U=
+cloud.google.com/go/auth v0.9.3/go.mod h1:7z6VY+7h3KUdRov5F1i8NDP5ZzWKYmEPO842BgCsmTk=
+cloud.google.com/go/compute/metadata v0.5.0 h1:Zr0eK8JbFv6+Wi4ilXAR8FJ3wyNdpxHKJNPos6LTZOY=
+cloud.google.com/go/compute/metadata v0.5.0/go.mod h1:aHnloV2TPI38yx4s9+wAZhHykWvVCfu7hQbF+9CWoiY=
+gitea.stevedudenhoeffer.com/steve/majordomo v0.0.0-20260718232210-a941f5ff4a3f h1:Zt91pngDr+TIU14sxv3fk1QS7bMQetvccFNg8kPaltA=
+gitea.stevedudenhoeffer.com/steve/majordomo v0.0.0-20260718232210-a941f5ff4a3f/go.mod h1:UZLveG17SmENt4sne2RSLIbioix30RZbRIQUzBAnOyY=
+github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
 github.com/bytedance/sonic v1.11.9 h1:LFHENlIY/SLzDWverzdOvgMztTxcfcF+cqNsz9pK5zg=
 github.com/bytedance/sonic v1.11.9/go.mod h1:LysEHSvpvDySVdC2f87zGWf6CIKJcAvqab1ZaiQtds4=
 github.com/bytedance/sonic/loader v0.1.1 h1:c+e5Pt1k/cy5wMveRDyk2X4B9hF4g7an8N3zCYjJFNM=
 github.com/bytedance/sonic/loader v0.1.1/go.mod h1:ncP89zfokxS5LZrJxl5z0UJcsk4M4yY2JpfqGeCtNLU=
+github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
+github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
 github.com/cloudwego/base64x v0.1.4 h1:jwCgWpFanWmN8xoIUHa2rtzmkd5J2plF/dnLS6Xd/0Y=
 github.com/cloudwego/base64x v0.1.4/go.mod h1:0zlkT4Wn5C6NdauXdJRhSKRlJvmclQ1hhJgA0rcu/8w=
 github.com/cloudwego/iasm v0.2.0 h1:1KNIy1I1H9hNNFEEH3DVnI4UujN+1zjpuk6gwHLTssg=
 github.com/cloudwego/iasm v0.2.0/go.mod h1:8rXZaNYT2n95jn+zTI1sDr+IgcD2GVs0nlbbQPiEFhY=
+github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
 github.com/coreos/go-oidc/v3 v3.20.0 h1:EtE0WIBHk03N+DqGkY4+UONzzZHk7amKt6IyNd7OsZE=
 github.com/coreos/go-oidc/v3 v3.20.0/go.mod h1:DYCf24+ncYi+XkIH97GY1+dqoRlbaSI26KVTCI9SrY4=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -13,6 +26,10 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
 github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
+github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
+github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
+github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1mIlRU8Am5FuJP05cCM98=
+github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
 github.com/gabriel-vasile/mimetype v1.4.4 h1:QjV6pZ7/XZ7ryI2KuyeEDE8wnh7fHP9YnQy+R0LnH8I=
 github.com/gabriel-vasile/mimetype v1.4.4/go.mod h1:JwLei5XPtWdGiMFB5Pjle1oEeoSeEuJfJE+TtfvdB/s=
 github.com/gin-contrib/sse v0.1.0 h1:Y/yl/+YNO8GZSjAhjMsSuLt29uWRFHdHYUb5lYOV9qE=
@@ -31,13 +48,40 @@ github.com/go-playground/validator/v10 v10.22.0 h1:k6HsTZ0sTnROkhS//R0O+55JgM8C4
 github.com/go-playground/validator/v10 v10.22.0/go.mod h1:dbuPbCMFw/DrkbEynArYaCwl3amGuJotoKCe95atGMM=
 github.com/goccy/go-json v0.10.3 h1:KZ5WoDbxAIgm2HNbYckL0se1fHD6rz5j4ywS6ebzDqA=
 github.com/goccy/go-json v0.10.3/go.mod h1:oq7eo15ShAhp70Anwd5lgX2pLfOS3QCiwU/PULtXL6M=
+github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
+github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
+github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da h1:oI5xCqsCo564l8iNU+DwB5epxmsaqB+rhGL0m5jtYqE=
+github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
+github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
+github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/golang/protobuf v1.3.2/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8=
+github.com/golang/protobuf v1.4.0-rc.1.0.20200221234624-67d41d38c208/go.mod h1:xKAWHe0F5eneWXFV3EuXVDTCmh+JuBKY0li0aMyXATA=
+github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrUpVNzEA03Pprs=
+github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w=
+github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0=
+github.com/golang/protobuf v1.4.1/go.mod h1:U8fpvMrcmy5pZrNK1lt4xCsGvpyWQ/VVv6QDs8UjoX8=
+github.com/golang/protobuf v1.4.3/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
+github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
+github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
+github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
+github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.3/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
 github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/pprof v0.0.0-20240409012703-83162a5b38cd h1:gbpYu9NMq8jhDVbvlGkMFWCjLFlqqEZjEmObmhUy6Vo=
 github.com/google/pprof v0.0.0-20240409012703-83162a5b38cd/go.mod h1:kf6iHlnVGwgKolg33glAes7Yg/8iWP8ukqeldJSO7jw=
+github.com/google/s2a-go v0.1.8 h1:zZDs9gcbt9ZPLV0ndSyQk6Kacx2g/X+SKYovpnz3SMM=
+github.com/google/s2a-go v0.1.8/go.mod h1:6iNWHTpQ+nfNRN5E00MSdfDwVesa8hhS32PhPO8deJA=
+github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/googleapis/enterprise-certificate-proxy v0.3.4 h1:XYIDZApgAnrN1c855gTgghdIA6Stxb52D5RnLI1SLyw=
+github.com/googleapis/enterprise-certificate-proxy v0.3.4/go.mod h1:YKe7cfqYXjKGpGvmSg28/fFvhNzinZQm8DGnaburhGA=
+github.com/gorilla/websocket v1.5.3 h1:saDtZ6Pbx/0u+bgYQ3q96pZgCzfhKXGPqt7kZ72aNNg=
+github.com/gorilla/websocket v1.5.3/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
 github.com/hashicorp/golang-lru/v2 v2.0.7 h1:a+bsQ5rvGLjzHuww6tVxozPZFVghXaHOwFs4luLUK2k=
 github.com/hashicorp/golang-lru/v2 v2.0.7/go.mod h1:QeFd9opnmA6QUJc5vARoKUSoFhyfM2/ZepoAG6RGpeM=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
@@ -65,6 +109,7 @@ github.com/pelletier/go-toml/v2 v2.2.2 h1:aYUidT7k73Pcl9nb2gScu7NSrKCSHIDE89b3+6
 github.com/pelletier/go-toml/v2 v2.2.2/go.mod h1:1t835xjRzz80PqgE6HHgN2JOsmgYu/h4qDAS4n929Rs=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
 github.com/samber/slog-gin v1.15.0 h1:Kqs/ilXd9divtslWjbz5DVptmLlzyntbBiXUAta2SFg=
@@ -85,6 +130,8 @@ github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS
 github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
 github.com/ugorji/go/codec v1.2.12 h1:9LC83zGrHhuUA9l16C9AHXAqEV/2wBQ4nkvumAE65EE=
 github.com/ugorji/go/codec v1.2.12/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
+go.opencensus.io v0.24.0 h1:y73uSU6J157QMP2kn2r30vwW1A2W2WFwSCGnAVxeaD0=
+go.opencensus.io v0.24.0/go.mod h1:vNK8G9p7aAivkbmorf4v+7Hgx+Zs0yY+0fOtgBfjQKo=
 go.opentelemetry.io/otel v1.29.0 h1:PdomN/Al4q/lN6iBJEN3AwPvUiHPMlt93c8bqTG5Llw=
 go.opentelemetry.io/otel v1.29.0/go.mod h1:N/WtXPs1CNCUEx+Agz5uouwCba+i+bJGFicT8SR4NP8=
 go.opentelemetry.io/otel/trace v1.29.0 h1:J/8ZNK4XgR7a21DZUAsbF8pZ5Jcw1VhACmnYt39JTi4=
@@ -92,24 +139,77 @@ go.opentelemetry.io/otel/trace v1.29.0/go.mod h1:eHl3w0sp3paPkYstJOmAimxhiFXPg+M
 golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
 golang.org/x/arch v0.8.0 h1:3wRIsP3pM4yUptoR96otTUOXI367OS0+c9eeRi9doIc=
 golang.org/x/arch v0.8.0/go.mod h1:FEVrYAQjsQXMVJ1nsMoVVXPZg6p2JE2mx8psSWTDQys=
-golang.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
-golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
+golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
+golang.org/x/crypto v0.36.0 h1:AnAEvhDddvBdpY+uR+MyHmuZzzNqXSe/GvuDeob5L34=
+golang.org/x/crypto v0.36.0/go.mod h1:Y4J0ReaxCR1IMaabaSMugxJES1EpwhBHhv2bDHklZvc=
+golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
+golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
+golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU=
+golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
 golang.org/x/mod v0.17.0 h1:zY54UmvipHiNd+pm+m0x9KhZ9hl1/7QNMyxXbc6ICqA=
 golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
-golang.org/x/net v0.33.0 h1:74SYHlV8BIgHIFC/LrYkOGIwL19eTYXQ5wc6TBuO36I=
+golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
-golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
+golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20190213061140-3a22650c66bd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20201110031124-69a78807bb2b/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
+golang.org/x/net v0.38.0 h1:vRMAPTMaeGqVhG5QyLJHqNDwecKTomGeqbnfZyKlBI8=
+golang.org/x/net v0.38.0/go.mod h1:ivrbrMbzFq5J41QOQh0siUuly180yBYtLp+CKbEaFx8=
+golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.36.0 h1:peZ/1z27fi9hUOFCAZaHyrpWG5lwe0RJEEEeH0ThlIs=
 golang.org/x/oauth2 v0.36.0/go.mod h1:YDBUJMTkDnJS+A4BP4eZBjCqtokkg1hODuPjwiGPO7Q=
-golang.org/x/sync v0.10.0 h1:3NQrjDixjgGwUOCaF8w2+VYHv0Ve/vGYSbdkTa98gmQ=
+golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.12.0 h1:MHc5BpPuC30uJk597Ri8TV3CNZcTLu6B6z4lJy+g6Jw=
+golang.org/x/sync v0.12.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
+golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.28.0 h1:Fksou7UEQUWlKvIdsqzJmUmCX3cZuD2+P3XyyzwMhlA=
+golang.org/x/sys v0.31.0 h1:ioabZlmFYtWhL+TRYpcnNlLwhyxaM9kWTDEmfnprqik=
-golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.31.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
-golang.org/x/text v0.21.0 h1:zyQAAkrwaneQ066sspRyJaG9VNi/YJ1NfzcGB3hZ/qo=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
-golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
+golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.23.0 h1:D71I7dUrlY+VX0gQShAThNGHFxZ13dGLBHQLVl1mJlY=
+golang.org/x/text v0.23.0/go.mod h1:/BLNzu4aZCJ1+kcD0DNRotWKage4q2rGVAg4o22unh4=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
+golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
+golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
 golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d h1:vU5i/LfpvrRCpgM/VPfJLg5KjxD3E+hfT1SH+d9zLwg=
 golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=
+golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
+google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
+google.golang.org/genai v1.59.0 h1:xp+ydkJFW8hO0hTUaAkr8TrLM9HFP3NYAwFhPd0nDqA=
+google.golang.org/genai v1.59.0/go.mod h1:mDdPDFXo1Ats7f1WXVyZgWb/CkMzFWTWJruIMy7hGIU=
+google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
+google.golang.org/genproto v0.0.0-20190819201941-24fa4b261c55/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc=
+google.golang.org/genproto v0.0.0-20200526211855-cb27e3aa2013/go.mod h1:NbSheEEYHJ7i3ixzK3sjbqSGDJWnxyFXZblF3eUsNvo=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1 h1:pPJltXNxVzT4pK9yD8vR9X75DaWYYmLGMsEvBfFQZzQ=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240903143218-8af14fe29dc1/go.mod h1:UqMtugtsSgubUsoxbuAoiCXvqvErP7Gf0so0mK9tHxU=
+google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
+google.golang.org/grpc v1.23.0/go.mod h1:Y5yQAOtifL1yxbo5wqy6BxZv8vAUGQwXBOALyacEbxg=
+google.golang.org/grpc v1.25.1/go.mod h1:c3i+UQWmh7LiEpx4sFZnkU36qjEYZ0imhYfXVyQciAY=
+google.golang.org/grpc v1.27.0/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk=
+google.golang.org/grpc v1.33.2/go.mod h1:JMHMWHQWaTccqQQlmk3MJZS+GWXOdAesneDmEnv2fbc=
+google.golang.org/grpc v1.66.2 h1:3QdXkuq3Bkh7w+ywLdLvM56cmGvQHUMZpiCzt6Rqaoo=
+google.golang.org/grpc v1.66.2/go.mod h1:s3/l6xSSCURdVfAnL+TqCNMyTDAGN6+lZeVxnZR128Y=
+google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8=
+google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0=
+google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM=
+google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miEFZTKqfCUM6K7xSMQL9OKL/b6hQv+e19PK+JZNE=
+google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo=
+google.golang.org/protobuf v1.22.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.23.1-0.20200526195155-81db48ad09cc/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.25.0/go.mod h1:9JNX74DMeImyA3h4bdi1ymwjUzf21/xIlbajtzgsN7c=
 google.golang.org/protobuf v1.34.2 h1:6xV6lTsCfpGD21XK49h7MhtcApnLqkfYgPcdHftf6hg=
 google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
@@ -118,6 +218,8 @@ gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
+honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
 modernc.org/cc/v4 v4.21.4 h1:3Be/Rdo1fpr8GrQ7IVw9OHtplU4gWbb+wNgeoBMmGLQ=
 modernc.org/cc/v4 v4.21.4/go.mod h1:HM7VJTZbUCR3rV8EYBi9wxnJ0ZBRiGE5OeGXNA0IsLQ=
 modernc.org/ccgo/v4 v4.19.2 h1:lwQZgvboKD0jBwdaeVCTouxhxAyN6iawF3STraAal8Y=

internal/agent/doc.go

@@ -1,18 +1,36 @@
-// Package agent adapts pansy's service layer to majordomo tools so an agent can
+// Package agent is pansy's garden assistant: a majordomo toolbox over the
-// drive a garden in natural language ("fill the NE corner with garlic, the NW
+// service layer, plus the run loop that drives a model with it.
-// with basil, the south half with beans"). Each tool runs as a fixed actor and
-// therefore inherits pansy's ACL checks for free — a viewer's fill_region returns
-// ErrForbidden, exactly as the REST API would.
 //
-// Two deliberate separations keep the core server lean:
+// Every tool runs as a fixed actor, so the agent inherits pansy's permission
+// checks for free — a viewer's fill_region returns ErrForbidden, exactly as the
+// REST API would. That is the whole reason the tools are thin adapters over
+// internal/service and never reach past it; the moment one does, the ACL story
+// stops being automatic and becomes something to remember.
 //
-//   - cmd/pansy does NOT import this package, so the server binary carries no
+// # A turn is one change set
-//     agent/LLM dependencies.
-//   - the tool wiring (tools.go) sits behind the `majordomo` build tag, so the
-//     default `go build ./...` / `go test ./...` compiles without the majordomo
-//     module. Build the agent tools with `-tags majordomo` once majordomo is a
-//     dependency (`go get gitea.stevedudenhoeffer.com/steve/majordomo`).
 //
-// The agent harness itself (model loop, chat surface) lives in the
+// Runs wrap their whole turn in a single change set (source "agent"), so
-// majordomo/executus stack, outside this repo; this package is only the toolbox.
+// "empty the garlic bed and plant cucumbers" — one object edit and a dozen
+// planting inserts — undoes as one action rather than thirteen. That is what
+// makes acting without a confirmation prompt defensible: the answer to "it did
+// the wrong thing" is one click, not an archaeology exercise.
+//
+// # No build tag
+//
+// This package used to sit behind a `majordomo` build tag, with cmd/pansy
+// deliberately not importing it, so the default build carried no LLM
+// dependency. Both separations are gone, on purpose: a tag that keeps the agent
+// out of the binary only earns its keep if you would ever ship a build without
+// the agent, and the agent is the point. Keeping it would have meant an
+// untagged CI that never compiled the code that matters.
+//
+// majordomo is stdlib-first and pure Go, so CGO_ENABLED=0 and the single static
+// binary survive it.
+//
+// # Unconfigured instances
+//
+// With no API key the assistant is simply not offered: the chat route isn't
+// registered and the capability isn't advertised — the same shape as OIDC
+// 404ing when unconfigured. An instance without a key starts and serves the app
+// exactly as it did before.
 package agent

internal/agent/runtime.go

@@ -0,0 +1,240 @@
+package agent
+
+import (
+	"context"
+	"crypto/rand"
+	"encoding/hex"
+	"errors"
+	"fmt"
+	"log/slog"
+	"strings"
+	"time"
+
+	"gitea.stevedudenhoeffer.com/steve/majordomo"
+	"gitea.stevedudenhoeffer.com/steve/majordomo/agent"
+	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
+	"gitea.stevedudenhoeffer.com/steve/majordomo/provider/ollama"
+
+	"gitea.stevedudenhoeffer.com/steve/pansy/internal/config"
+	"gitea.stevedudenhoeffer.com/steve/pansy/internal/domain"
+	"gitea.stevedudenhoeffer.com/steve/pansy/internal/service"
+)
+
+// Loop bounds. These exist so a stuck run terminates, NOT to control spend —
+// pansy is a personal tool and multi-tenant cost control is explicitly not a
+// concern here. A model that gets wedged calling describe_garden forever should
+// stop on its own, and a hung upstream shouldn't hold a connection open all day.
+const (
+	maxSteps = 24
+	// A turn that legitimately fills several beds does a lot of round trips, so
+	// this is generous; it is a backstop, not a budget.
+	runTimeout = 4 * time.Minute
+	// Successive all-error steps, and identical repeated calls, that end a run.
+	maxConsecutiveToolErrors = 4
+	maxSameCallRepeats       = 3
+)
+
+// Runner drives a model over pansy's toolbox. One per process; Run is safe to
+// call concurrently.
+type Runner struct {
+	svc   *service.Service
+	model llm.Model
+}
+
+// NewRunner resolves the configured model and returns a Runner, or an error if
+// the assistant can't be offered. Callers should treat an error as "no
+// assistant" rather than a startup failure — an instance with no key must still
+// serve the app.
+func NewRunner(svc *service.Service, cfg *config.Config) (*Runner, error) {
+	if !cfg.Agent.Ready() {
+		return nil, errors.New("agent: not configured")
+	}
+
+	// A private registry, not the package-level default: pansy passes the key it
+	// was configured with rather than depending on ambient environment, and
+	// majordomo's own ollama-cloud preset reads OLLAMA_API_KEY while pansy (like
+	// gadfly) is configured with OLLAMA_CLOUD_API_KEY. Registering the provider
+	// explicitly makes that bridge visible instead of a mysterious empty token.
+	reg := majordomo.New()
+	reg.RegisterProvider(ollama.Cloud(ollama.WithToken(cfg.Agent.OllamaCloudAPIKey)))
+
+	// The spec goes to Parse VERBATIM. The grammar — including comma-separated
+	// failover chains — is majordomo's, and re-implementing any of it here would
+	// only mean two places to update when it grows.
+	model, err := reg.Parse(cfg.Agent.Model)
+	if err != nil {
+		return nil, fmt.Errorf("agent: resolve model %q: %w", cfg.Agent.Model, err)
+	}
+	return &Runner{svc: svc, model: model}, nil
+}
+
+// Turn is the outcome of one exchange.
+type Turn struct {
+	// Reply is what to show the user.
+	Reply string `json:"reply"`
+	// ChangeSetID is the change set this turn produced, if it changed anything —
+	// the handle the UI needs to offer Undo.
+	ChangeSetID *int64 `json:"changeSetId,omitempty"`
+	// Steps is how many model round trips it took.
+	Steps int `json:"steps"`
+	// Truncated is set when the run hit its step cap rather than finishing.
+	Truncated bool `json:"truncated,omitempty"`
+}
+
+// Run executes one turn against a garden, as actorID.
+//
+// The whole turn runs inside ONE change set, so everything the model did undoes
+// together. That is what makes acting without a confirmation prompt defensible.
+// The scope is opened even for a turn that turns out to be a question — a change
+// set with no revisions is never written, so asking costs nothing.
+func (r *Runner) Run(ctx context.Context, actorID, gardenID int64, message string, history []llm.Message, onStep func(agent.Step)) (*Turn, error) {
+	message = strings.TrimSpace(message)
+	if message == "" {
+		return nil, domain.ErrInvalidInput
+	}
+
+	ctx, cancel := context.WithTimeout(ctx, runTimeout)
+	defer cancel()
+
+	garden, err := r.svc.GetGarden(ctx, actorID, gardenID)
+	if err != nil {
+		return nil, err
+	}
+
+	// An id for this run, stamped on the change set so a row in the history list
+	// can be matched to the log lines that produced it. Without it, "the agent
+	// did something odd on Tuesday" has no thread back to what it was thinking.
+	runID := newRunID()
+	slog.Info("agent: run start", "run", runID, "garden", gardenID, "actor", actorID)
+
+	var (
+		result   *agent.Result
+		runErr   error
+		truncErr bool
+	)
+	changeSet, err := r.svc.WithChangeSet(ctx, actorID, gardenID, service.ChangeSetOptions{
+		Source:     domain.SourceAgent,
+		Summary:    turnSummary(message),
+		AgentRunID: &runID,
+	}, func(ctx context.Context) error {
+		box := NewToolbox(r.svc, actorID)
+		a := agent.New(r.model, systemPrompt(garden),
+			agent.WithMaxSteps(maxSteps),
+			agent.WithToolErrorLimits(maxConsecutiveToolErrors, maxSameCallRepeats),
+		)
+		a.AddToolbox(box)
+
+		opts := []agent.RunOption{agent.WithHistory(history)}
+		if onStep != nil {
+			opts = append(opts, agent.OnStep(onStep))
+		}
+		result, runErr = a.Run(ctx, message, opts...)
+		// A run that ran out of steps still DID things, and those things must be
+		// recorded and undoable. So the loop-guard errors don't fail the scope —
+		// they're reported to the user instead.
+		if runErr != nil && isLoopLimit(runErr) {
+			truncErr = true
+			return nil
+		}
+		return runErr
+	})
+	if err != nil {
+		// WithChangeSet records whatever committed before failing, so the partial
+		// work is undoable even though the turn errored.
+		return nil, err
+	}
+
+	turn := &Turn{Truncated: truncErr}
+	if changeSet != nil {
+		turn.ChangeSetID = &changeSet.ID
+	}
+	if result != nil {
+		turn.Reply = result.Output
+		turn.Steps = len(result.Steps)
+	}
+	if turn.Reply == "" {
+		turn.Reply = fallbackReply(turn)
+	}
+	return turn, nil
+}
+
+// isLoopLimit reports whether an error is one of majordomo's loop guards firing
+// rather than a genuine failure. Those runs have a partial result worth keeping.
+func isLoopLimit(err error) bool {
+	return errors.Is(err, agent.ErrMaxSteps) || errors.Is(err, agent.ErrToolLoop)
+}
+
+// fallbackReply covers a run that finished with no text — a model that made its
+// last tool call and then stopped. Silence reads as a failure, so say what
+// happened.
+func fallbackReply(t *Turn) string {
+	switch {
+	case t.Truncated:
+		return "I stopped partway through — that turned into more steps than I should take in one go. " +
+			"Have a look at what changed, and tell me what to do next."
+	case t.ChangeSetID != nil:
+		return "Done — have a look at the canvas."
+	default:
+		return "I didn't change anything."
+	}
+}
+
+// newRunID returns a short random identifier for one run.
+func newRunID() string {
+	var b [8]byte
+	if _, err := rand.Read(b[:]); err != nil {
+		// The id is for correlating logs, not for security. A clock-based
+		// fallback is worse than random and better than an empty string.
+		return fmt.Sprintf("t%d", time.Now().UnixNano())
+	}
+	return hex.EncodeToString(b[:])
+}
+
+// turnSummary is what the history list shows for this turn. The user's own words
+// are the most useful label available, trimmed to fit a list row.
+//
+// Trimmed by RUNES, not bytes: slicing a byte offset would cut a multibyte
+// character in half and store invalid UTF-8 in the summary — which is not a
+// hypothetical for text people type.
+func turnSummary(message string) string {
+	const max = 120
+	s := strings.Join(strings.Fields(message), " ")
+	runes := []rune(s)
+	if len(runes) > max {
+		s = strings.TrimSpace(string(runes[:max])) + "…"
+	}
+	return s
+}
+
+// systemPrompt gives the model the conventions it cannot infer.
+//
+// The compass convention in particular is not guessable: -y is north because
+// screen y grows downward, and a model that assumes otherwise plants the south
+// half when asked for the north one.
+func systemPrompt(g *domain.Garden) string {
+	units := "metric — all measurements are centimeters"
+	if g.UnitPref == domain.UnitImperial {
+		units = "imperial for display, but every measurement you send or receive is in CENTIMETERS"
+	}
+	return fmt.Sprintf(`You are pansy's garden assistant. You help plan and edit a real garden by calling tools.
+
+The garden you are working on is %q (id %d), %.0f x %.0f cm. The user's units are %s.
+
+Conventions you cannot guess and must not assume:
+- Positions in a garden are centimeters from its top-left corner: x grows east, y grows SOUTH.
+- Inside an object (a bed), positions are relative to that object's CENTER, and -y is NORTH.
+  So the north half of a bed is negative y. Getting this backwards plants the wrong end.
+- Objects and plantings are version-guarded. Use the version from describe_garden when editing.
+
+How to work:
+- Start from describe_garden to see what is actually there. Do not guess ids.
+- Use find_plant to turn a plant name into an id. If it returns several candidates,
+  pick the one that matches what the user said, or ask them which they meant.
+- To replant a bed with something else: clear_object, then fill_region with region "all".
+- When a tool refuses (for example, the user only has view access to this garden),
+  explain what happened in plain words. Do not retry it.
+
+When you are done, say briefly what you changed — the user is watching the canvas
+and wants to know what to look at. If you changed nothing, say that too.`,
+		g.Name, g.ID, g.WidthCM, g.HeightCM, units)
+}

internal/agent/runtime_test.go

@@ -0,0 +1,359 @@
+package agent
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"strings"
+	"testing"
+	"time"
+	"unicode/utf8"
+
+	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
+	"gitea.stevedudenhoeffer.com/steve/majordomo/provider/fake"
+
+	"gitea.stevedudenhoeffer.com/steve/pansy/internal/config"
+	"gitea.stevedudenhoeffer.com/steve/pansy/internal/domain"
+	"gitea.stevedudenhoeffer.com/steve/pansy/internal/service"
+)
+
+// scriptedRunner wires a Runner to a fake provider so the whole loop — tools,
+// change-set scoping, loop guards — is exercised with no live model.
+func scriptedRunner(t *testing.T, svc *service.Service, steps ...fake.Step) *Runner {
+	t.Helper()
+	p := fake.New("fake")
+	for _, s := range steps {
+		p.Enqueue("m", s)
+	}
+	model, err := p.Model("m")
+	if err != nil {
+		t.Fatalf("fake model: %v", err)
+	}
+	return &Runner{svc: svc, model: model}
+}
+
+// toolCall scripts one model turn that calls a tool.
+func toolCall(name string, args any) fake.Step {
+	raw, _ := json.Marshal(args)
+	return fake.ReplyWith(llm.Response{
+		FinishReason: llm.FinishToolCalls,
+		ToolCalls:    []llm.ToolCall{{ID: "c1", Name: name, Arguments: raw}},
+	})
+}
+
+// TestTurnIsOneChangeSet is the acceptance criterion the whole "act freely"
+// posture rests on: a turn that clears a bed and replants it — one object edit
+// and many planting inserts — has to undo as ONE action, not thirteen.
+func TestTurnIsOneChangeSet(t *testing.T) {
+	ctx := context.Background()
+	svc, owner := newAgentTestService(t)
+
+	g, err := svc.CreateGarden(ctx, owner, service.GardenInput{Name: "Plot", WidthCM: 2000, HeightCM: 2000})
+	if err != nil {
+		t.Fatalf("garden: %v", err)
+	}
+	garlic := mustPlant(t, svc, owner, "Garlic", 15, "🧄")
+	cucumber := mustPlant(t, svc, owner, "Cucumber", 45, "🥒")
+	bed, err := svc.CreateObject(ctx, owner, g.ID, service.ObjectInput{
+		Kind: domain.KindBed, Name: "Garlic bed", XCM: 1000, YCM: 1000, WidthCM: 400, HeightCM: 400,
+	})
+	if err != nil {
+		t.Fatalf("bed: %v", err)
+	}
+	if _, err := svc.FillNamedRegion(ctx, owner, bed.ID, "all", garlic.ID, nil); err != nil {
+		t.Fatalf("seed garlic: %v", err)
+	}
+
+	before, _, err := svc.GardenHistory(ctx, owner, g.ID, 0, 0)
+	if err != nil {
+		t.Fatalf("history: %v", err)
+	}
+
+	r := scriptedRunner(t, svc,
+		toolCall("clear_object", map[string]any{"objectId": bed.ID}),
+		toolCall("fill_region", map[string]any{"objectId": bed.ID, "region": "all", "plantId": cucumber.ID}),
+		fake.Reply("Cleared the garlic and replanted the bed with cucumbers."),
+	)
+
+	turn, err := r.Run(ctx, owner, g.ID, "change the garlic bed to cucumbers this year", nil, nil)
+	if err != nil {
+		t.Fatalf("Run: %v", err)
+	}
+	if turn.ChangeSetID == nil {
+		t.Fatal("a turn that changed things produced no change set")
+	}
+	if !strings.Contains(turn.Reply, "cucumbers") {
+		t.Errorf("reply = %q", turn.Reply)
+	}
+
+	// Exactly ONE new change set, whatever the model did inside the turn.
+	after, _, err := svc.GardenHistory(ctx, owner, g.ID, 0, 0)
+	if err != nil {
+		t.Fatalf("history: %v", err)
+	}
+	if len(after)-len(before) != 1 {
+		t.Fatalf("turn produced %d change sets, want exactly 1", len(after)-len(before))
+	}
+	cs := after[0]
+	if cs.Source != domain.SourceAgent {
+		t.Errorf("source = %q, want agent", cs.Source)
+	}
+	if cs.Summary != "change the garlic bed to cucumbers this year" {
+		t.Errorf("summary = %q, want the user's own words", cs.Summary)
+	}
+
+	// The bed really is cucumbers now.
+	full, _ := svc.GardenFull(ctx, owner, g.ID, nil)
+	if len(full.Plantings) == 0 {
+		t.Fatal("bed ended up empty")
+	}
+	for _, p := range full.Plantings {
+		if p.PlantID != cucumber.ID {
+			t.Errorf("unexpected plant %d still in the bed", p.PlantID)
+		}
+	}
+
+	// And one undo puts it back.
+	if _, conflicts, err := svc.RevertChangeSet(ctx, owner, *turn.ChangeSetID, domain.SourceUI); err != nil || len(conflicts) != 0 {
+		t.Fatalf("undo: err=%v conflicts=%+v", err, conflicts)
+	}
+	full, _ = svc.GardenFull(ctx, owner, g.ID, nil)
+	for _, p := range full.Plantings {
+		if p.PlantID != garlic.ID {
+			t.Errorf("after undo the bed holds plant %d, want the garlic back", p.PlantID)
+		}
+	}
+}
+
+// TestViewerGetsAnExplainableRefusal — the ACL story only works if the model can
+// narrate the refusal, so a tool denial has to reach it as a tool RESULT it can
+// read, not as a 500 that ends the run.
+func TestViewerGetsAnExplainableRefusal(t *testing.T) {
+	ctx := context.Background()
+	svc, owner := newAgentTestService(t)
+	viewer, err := svc.Register(ctx, service.RegisterInput{Email: "[email protected]", DisplayName: "V", Password: "password123"})
+	if err != nil {
+		t.Fatalf("register: %v", err)
+	}
+	g, err := svc.CreateGarden(ctx, owner, service.GardenInput{Name: "Plot", WidthCM: 2000, HeightCM: 2000})
+	if err != nil {
+		t.Fatalf("garden: %v", err)
+	}
+	bed, err := svc.CreateObject(ctx, owner, g.ID, service.ObjectInput{
+		Kind: domain.KindBed, XCM: 1000, YCM: 1000, WidthCM: 400, HeightCM: 400,
+	})
+	if err != nil {
+		t.Fatalf("bed: %v", err)
+	}
+	if _, err := svc.AddShare(ctx, owner, g.ID, "[email protected]", domain.RoleViewer); err != nil {
+		t.Fatalf("share: %v", err)
+	}
+
+	// A viewer can't open a change set at all, so the turn is refused up front —
+	// before any model call — and the API turns that into a plain explanation.
+	r := scriptedRunner(t, svc, fake.Reply("unused"))
+	_, err = r.Run(ctx, viewer.ID, g.ID, "plant garlic in that bed", nil, nil)
+	if !errors.Is(err, domain.ErrForbidden) {
+		t.Fatalf("viewer turn err = %v, want ErrForbidden", err)
+	}
+
+	// And at the tool layer, a refusal comes back as a readable tool result
+	// rather than killing the run.
+	box := NewToolbox(svc, viewer.ID)
+	raw, _ := json.Marshal(map[string]any{"objectId": bed.ID})
+	res := box.Execute(ctx, llm.ToolCall{ID: "1", Name: "clear_object", Arguments: raw})
+	if !res.IsError {
+		t.Fatal("a viewer's clear_object succeeded")
+	}
+	if res.Content == "" {
+		t.Error("the refusal carried no text for the model to explain")
+	}
+}
+
+// TestRunStopsAtTheStepCap — a model that gets wedged should stop on its own,
+// and what it managed to do must still be recorded and undoable.
+func TestRunStopsAtTheStepCap(t *testing.T) {
+	ctx := context.Background()
+	svc, owner := newAgentTestService(t)
+	g, err := svc.CreateGarden(ctx, owner, service.GardenInput{Name: "Plot", WidthCM: 2000, HeightCM: 2000})
+	if err != nil {
+		t.Fatalf("garden: %v", err)
+	}
+
+	// More describe_garden calls than the cap allows, forever.
+	steps := make([]fake.Step, 0, maxSteps+4)
+	for i := 0; i < maxSteps+4; i++ {
+		steps = append(steps, toolCall("describe_garden", map[string]any{"gardenId": g.ID}))
+	}
+	r := scriptedRunner(t, svc, steps...)
+
+	turn, err := r.Run(ctx, owner, g.ID, "look at the garden", nil, nil)
+	if err != nil {
+		t.Fatalf("a capped run should end cleanly, got %v", err)
+	}
+	if !turn.Truncated {
+		t.Error("turn.Truncated = false; the run hit the cap and should say so")
+	}
+	if turn.Reply == "" {
+		t.Error("a capped run said nothing; silence reads as a hang")
+	}
+	// It only read, so there is nothing to undo — and no empty change set either.
+	if turn.ChangeSetID != nil {
+		t.Errorf("a read-only turn produced change set %d", *turn.ChangeSetID)
+	}
+}
+
+// TestReadOnlyTurnWritesNoChangeSet — asking a question must not litter the
+// history with empty entries.
+func TestReadOnlyTurnWritesNoChangeSet(t *testing.T) {
+	ctx := context.Background()
+	svc, owner := newAgentTestService(t)
+	g, err := svc.CreateGarden(ctx, owner, service.GardenInput{Name: "Plot", WidthCM: 2000, HeightCM: 2000})
+	if err != nil {
+		t.Fatalf("garden: %v", err)
+	}
+	before, _, _ := svc.GardenHistory(ctx, owner, g.ID, 0, 0)
+
+	r := scriptedRunner(t, svc,
+		toolCall("describe_garden", map[string]any{"gardenId": g.ID}),
+		fake.Reply("It's empty — nothing planted yet."),
+	)
+	turn, err := r.Run(ctx, owner, g.ID, "what's in the garden?", nil, nil)
+	if err != nil {
+		t.Fatalf("Run: %v", err)
+	}
+	if turn.ChangeSetID != nil {
+		t.Errorf("a question produced change set %d", *turn.ChangeSetID)
+	}
+	after, _, _ := svc.GardenHistory(ctx, owner, g.ID, 0, 0)
+	if len(after) != len(before) {
+		t.Errorf("history grew by %d for a read-only turn", len(after)-len(before))
+	}
+}
+
+// TestNewRunnerNeedsConfiguration — an instance with no key must not get a
+// half-built runner; the caller treats the error as "no assistant" and carries on.
+func TestNewRunnerNeedsConfiguration(t *testing.T) {
+	svc, _ := newAgentTestService(t)
+	for _, cfg := range []*config.Config{
+		{Agent: config.AgentConfig{Enabled: false, OllamaCloudAPIKey: "k", Model: "ollama-cloud/x"}},
+		{Agent: config.AgentConfig{Enabled: true, OllamaCloudAPIKey: "", Model: "ollama-cloud/x"}},
+		{Agent: config.AgentConfig{Enabled: true, OllamaCloudAPIKey: "k", Model: ""}},
+	} {
+		if _, err := NewRunner(svc, cfg); err == nil {
+			t.Errorf("NewRunner accepted %+v", cfg.Agent)
+		}
+	}
+	// A model spec naming a provider that doesn't exist is a configuration
+	// error, not a panic at first use.
+	if _, err := NewRunner(svc, &config.Config{Agent: config.AgentConfig{
+		Enabled: true, OllamaCloudAPIKey: "k", Model: "nonesuch/model",
+	}}); err == nil {
+		t.Error("NewRunner accepted an unresolvable model spec")
+	}
+}
+
+// TestTurnSummaryFitsAHistoryRow — the user's own words are the most useful
+// label for a change set, but a paragraph would wreck the list.
+func TestTurnSummaryFitsAHistoryRow(t *testing.T) {
+	if got := turnSummary("  change   the garlic bed\n to cucumbers "); got != "change the garlic bed to cucumbers" {
+		t.Errorf("turnSummary = %q", got)
+	}
+	long := turnSummary(strings.Repeat("plant garlic ", 40))
+	if len(long) > 130 || !strings.HasSuffix(long, "…") {
+		t.Errorf("long summary = %q (%d chars)", long, len(long))
+	}
+}
+
+// TestSystemPromptStatesTheCompassConvention — -y being north is not guessable,
+// and a model that assumes otherwise plants the wrong end of the bed.
+func TestSystemPromptStatesTheCompassConvention(t *testing.T) {
+	p := systemPrompt(&domain.Garden{ID: 1, Name: "Plot", WidthCM: 500, HeightCM: 400, UnitPref: domain.UnitImperial})
+	for _, want := range []string{"NORTH", "-y", "centimeters", "Plot", "version"} {
+		if !strings.Contains(p, want) {
+			t.Errorf("system prompt is missing %q:\n%s", want, p)
+		}
+	}
+	if !strings.Contains(p, fmt.Sprintf("%.0f", 500.0)) {
+		t.Error("system prompt doesn't state the garden's size")
+	}
+}
+
+// TestPartialWorkSurvivesATimeout is the finding that mattered most on this PR.
+//
+// The run context carries a timeout. When it fires, WithChangeSet's recovery
+// path has to record what already committed — and doing that with the SAME
+// dead context would fail, losing the history for changes that really happened.
+// The user-facing message says "anything I'd already changed is in History", so
+// this isn't just a gap, it's a promise the code has to keep.
+func TestPartialWorkSurvivesATimeout(t *testing.T) {
+	ctx := context.Background()
+	svc, owner := newAgentTestService(t)
+	g, err := svc.CreateGarden(ctx, owner, service.GardenInput{Name: "Plot", WidthCM: 2000, HeightCM: 2000})
+	if err != nil {
+		t.Fatalf("garden: %v", err)
+	}
+	bed, err := svc.CreateObject(ctx, owner, g.ID, service.ObjectInput{
+		Kind: domain.KindBed, Name: "Bed", XCM: 1000, YCM: 1000, WidthCM: 400, HeightCM: 400,
+	})
+	if err != nil {
+		t.Fatalf("bed: %v", err)
+	}
+	before, _, _ := svc.GardenHistory(ctx, owner, g.ID, 0, 0)
+
+	// A turn that renames the bed, then dies with the context already cancelled.
+	cancelled, cancel := context.WithCancel(ctx)
+	r := scriptedRunner(t, svc,
+		toolCall("move_object", map[string]any{
+			"objectId": bed.ID, "xCm": 600.0, "yCm": 600.0, "version": bed.Version,
+		}),
+		fake.Step{Err: context.DeadlineExceeded},
+	)
+	// Cancel once the first tool call has landed, so the failure path runs with a
+	// dead context — exactly the timeout case.
+	go func() {
+		time.Sleep(50 * time.Millisecond)
+		cancel()
+	}()
+	_, err = r.Run(cancelled, owner, g.ID, "move the bed", nil, nil)
+	if err == nil {
+		t.Fatal("expected the turn to fail")
+	}
+
+	// The move committed, so it must be in history and undoable.
+	after, _, herr := svc.GardenHistory(ctx, owner, g.ID, 0, 0)
+	if herr != nil {
+		t.Fatalf("history: %v", herr)
+	}
+	if len(after) != len(before)+1 {
+		t.Fatalf("the failed turn recorded %d change sets, want 1 — its work is otherwise un-undoable",
+			len(after)-len(before))
+	}
+	if !strings.Contains(after[0].Summary, "failed partway") {
+		t.Errorf("summary = %q, want it marked as partial", after[0].Summary)
+	}
+	if _, conflicts, rerr := svc.RevertChangeSet(ctx, owner, after[0].ID, domain.SourceUI); rerr != nil || len(conflicts) != 0 {
+		t.Fatalf("the partial turn should be undoable: err=%v conflicts=%+v", rerr, conflicts)
+	}
+	o, _ := svc.DescribeGarden(ctx, owner, g.ID)
+	if len(o.Objects) > 0 && o.Objects[0].XCM != bed.XCM {
+		t.Errorf("undo left the bed at %v, want %v", o.Objects[0].XCM, bed.XCM)
+	}
+}
+
+// TestTurnSummaryTrimsByRunes — slicing a byte offset would cut a multibyte
+// character in half and store invalid UTF-8 in the history summary.
+func TestTurnSummaryTrimsByRunes(t *testing.T) {
+	// 200 multibyte runes: a byte slice at 120 would land mid-character.
+	got := turnSummary(strings.Repeat("🌱", 200))
+	if !utf8.ValidString(got) {
+		t.Errorf("turnSummary produced invalid UTF-8: %q", got)
+	}
+	if !strings.HasSuffix(got, "…") {
+		t.Errorf("long summary should be elided, got %q", got)
+	}
+	if n := utf8.RuneCountInString(got); n > 121 {
+		t.Errorf("summary is %d runes, want it trimmed", n)
+	}
+}

internal/agent/tools.go

@@ -1,5 +1,3 @@
-//go:build majordomo
-
 package agent
 
 import (
@@ -36,11 +34,36 @@ func NewToolbox(svc *service.Service, actorID int64) *llm.Toolbox {
 			"Place one plop of a plant inside a plantable object, positioned in the object's LOCAL frame (0,0 = object center, -y = north).",
 			a.placePlanting),
 		llm.DefineTool("fill_region",
-			"Fill a named region of a plantable object with a plant, hex-packed. Region is one of nw/ne/sw/se (corners), north/south/east/west or top/bottom/left/right (halves), or all.",
+			"Fill part of a plantable object with one plant, hex-packed at the plant's spacing. "+
+				"region is a compass name, not coordinates: nw|ne|sw|se for the quarter corners, "+
+				"north|south|east|west (or top|bottom|left|right) for halves, or all for the whole thing. "+
+				"North is the top of the garden. Example: to replant a whole bed, clear_object then "+
+				"fill_region with region=all. Filling skips spots already covered by an existing plant, "+
+				"so it is safe to run twice.",
 			a.fillRegion),
 		llm.DefineTool("clear_object",
-			"Remove all plants from an object (soft-remove; history is kept).",
+			"Remove all plants from an object. They are soft-removed, so the planting history for past "+
+				"seasons is kept and the change can be undone. Use this before replanting a bed with "+
+				"something else.",
 			a.clearObject),
+		llm.DefineTool("find_plant",
+			"Look up plants in the user's catalog by name or category, to get the plantId that "+
+				"place_planting and fill_region need. Returns SEVERAL candidates when the query is "+
+				"ambiguous — \"garlic\" may match both the built-in \"Garlic\" and a custom \"German Red "+
+				"Garlic\" — so pick the one that fits what the user asked for, or ask them which. Each "+
+				"result also reports how much seed the user has left of it, when they have recorded any.",
+			a.findPlant),
+		llm.DefineTool("create_plant",
+			"Add a new plant to the user's own catalog, for when they name a variety that isn't in it "+
+				"yet. Check find_plant first — creating a duplicate of something that already exists is "+
+				"worse than reusing it. The plant belongs to the user, not to any garden.",
+			a.createPlant),
+		llm.DefineTool("add_journal_entry",
+			"Write a dated observation into the garden's grow journal — what happened, and when. "+
+				"Attach it to one bed with objectId when it is about that bed. This is for events "+
+				"(\"powdery mildew on the west bed\", \"first frost\"), not for descriptions of what a "+
+				"thing is. observedAt defaults to today; set it to backdate.",
+			a.addJournalEntry),
 	)
 }
 
@@ -108,6 +131,42 @@ func (a *adapter) fillRegion(ctx context.Context, args struct {
 	return a.svc.FillNamedRegion(ctx, a.actor, args.ObjectID, args.Region, args.PlantID, args.SpacingOverride)
 }
 
+func (a *adapter) findPlant(ctx context.Context, args struct {
+	Query string `json:"query" description:"plant name or category to search for, e.g. \"cucumber\" or \"herb\"; empty lists the catalog"`
+}) (any, error) {
+	return a.svc.FindPlants(ctx, a.actor, args.Query)
+}
+
+func (a *adapter) createPlant(ctx context.Context, args struct {
+	Name           string  `json:"name" description:"the variety's name, e.g. \"German Red Garlic\""`
+	Category       string  `json:"category" description:"vegetable | herb | flower | fruit | tree_shrub | cover"`
+	SpacingCM      float64 `json:"spacingCm" description:"mature in-row spacing in cm; this is what fill_region packs to"`
+	Color          string  `json:"color" description:"hex color for the plant on the canvas, e.g. #8a5a8a"`
+	Icon           string  `json:"icon" description:"a single emoji to draw it with, e.g. 🧄"`
+	DaysToMaturity *int    `json:"daysToMaturity" description:"optional days from planting to harvest"`
+	SourceURL      string  `json:"sourceUrl" description:"optional http(s) link to where the seed came from"`
+	Vendor         string  `json:"vendor" description:"optional vendor name, e.g. \"Johnny\u0027s Selected Seeds\""`
+}) (any, error) {
+	return a.svc.CreatePlant(ctx, a.actor, service.PlantInput{
+		Name: args.Name, Category: args.Category, SpacingCM: args.SpacingCM,
+		Color: args.Color, Icon: args.Icon, DaysToMaturity: args.DaysToMaturity,
+		SourceURL: args.SourceURL, Vendor: args.Vendor,
+	})
+}
+
+func (a *adapter) addJournalEntry(ctx context.Context, args struct {
+	GardenID   int64  `json:"gardenId" description:"garden the observation is about"`
+	ObjectID   *int64 `json:"objectId" description:"optional bed the observation is about; omit for a garden-level note"`
+	Body       string `json:"body" description:"what happened, in plain words"`
+	ObservedAt string `json:"observedAt" description:"optional date it happened, YYYY-MM-DD; defaults to today"`
+}) (any, error) {
+	in := service.JournalInput{ObjectID: args.ObjectID, Body: args.Body}
+	if args.ObservedAt != "" {
+		in.ObservedAt = &args.ObservedAt
+	}
+	return a.svc.CreateJournalEntry(ctx, a.actor, args.GardenID, in)
+}
+
 func (a *adapter) clearObject(ctx context.Context, args struct {
 	ObjectID int64 `json:"objectId" description:"object to remove all plants from"`
 }) (any, error) {

internal/agent/tools_test.go

@@ -1,10 +1,9 @@
-//go:build majordomo
-
 package agent
 
 import (
 	"context"
 	"encoding/json"
+	"strings"
 	"testing"
 
 	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
@@ -24,21 +23,8 @@ import (
 // Build/run with: go test -tags majordomo ./internal/agent/
 func TestToolboxScenario(t *testing.T) {
 	ctx := context.Background()
-	db, err := store.Open(":memory:")
+	svc, ownerID := newAgentTestService(t)
-	if err != nil {
+	box := NewToolbox(svc, ownerID)
-		t.Fatalf("open: %v", err)
-	}
-	t.Cleanup(func() { db.Close() })
-	if err := db.Migrate(ctx); err != nil {
-		t.Fatalf("migrate: %v", err)
-	}
-	svc := service.New(db, &config.Config{Registration: config.RegistrationOpen, LocalAuth: true})
-
-	owner, err := svc.Register(ctx, service.RegisterInput{Email: "[email protected]", DisplayName: "A", Password: "password123"})
-	if err != nil {
-		t.Fatalf("register: %v", err)
-	}
-	box := NewToolbox(svc, owner.ID)
 
 	call := func(name string, args any) llm.ToolResult {
 		t.Helper()
@@ -48,13 +34,13 @@ func TestToolboxScenario(t *testing.T) {
 
 	// Garden + plants are set up directly (there are no create_garden/plant tools);
 	// the agent-facing bits — object + fills + describe — go through the toolbox.
-	g, err := svc.CreateGarden(ctx, owner.ID, service.GardenInput{Name: "Plot", WidthCM: 2000, HeightCM: 2000})
+	g, err := svc.CreateGarden(ctx, ownerID, service.GardenInput{Name: "Plot", WidthCM: 2000, HeightCM: 2000})
 	if err != nil {
 		t.Fatalf("garden: %v", err)
 	}
-	garlic := mustPlant(t, svc, owner.ID, "Garlic", 15, "🧄")
+	garlic := mustPlant(t, svc, ownerID, "Garlic", 15, "🧄")
-	basil := mustPlant(t, svc, owner.ID, "Basil", 25, "🌿")
+	basil := mustPlant(t, svc, ownerID, "Basil", 25, "🌿")
-	beans := mustPlant(t, svc, owner.ID, "Beans", 10, "🫘")
+	beans := mustPlant(t, svc, ownerID, "Beans", 10, "🫘")
 
 	// create_object → a 400×400 bed.
 	res := call("create_object", map[string]any{
@@ -119,7 +105,7 @@ func TestToolboxScenario(t *testing.T) {
 	if err != nil {
 		t.Fatalf("register viewer: %v", err)
 	}
-	if _, err := svc.AddShare(ctx, owner.ID, g.ID, "[email protected]", domain.RoleViewer); err != nil {
+	if _, err := svc.AddShare(ctx, ownerID, g.ID, "[email protected]", domain.RoleViewer); err != nil {
 		t.Fatalf("share: %v", err)
 	}
 	viewerBox := NewToolbox(svc, viewerUser.ID)
@@ -150,3 +136,233 @@ func mustPlant(t *testing.T, svc *service.Service, owner int64, name string, spa
 	}
 	return p
 }
+
+// TestGarlicBedToCucumbers is the flagship interaction from #58, driven end to
+// end through the tool layer: "change the garlic garden bed to instead be
+// cucumbers this year".
+//
+// The sequence is the one a model would actually run — describe to find the bed,
+// find_plant to turn the word "cucumber" into an id, clear, refill — and until
+// find_plant existed step three had no way to get its plantId, which blocked the
+// whole thing on one missing tool.
+func TestGarlicBedToCucumbers(t *testing.T) {
+	ctx := context.Background()
+	svc, owner := newAgentTestService(t)
+	box := NewToolbox(svc, owner)
+
+	call := func(name string, args any) llm.ToolResult {
+		t.Helper()
+		raw, _ := json.Marshal(args)
+		return box.Execute(ctx, llm.ToolCall{ID: "1", Name: name, Arguments: raw})
+	}
+
+	g, err := svc.CreateGarden(ctx, owner, service.GardenInput{Name: "Plot", WidthCM: 2000, HeightCM: 2000})
+	if err != nil {
+		t.Fatalf("garden: %v", err)
+	}
+	garlic := mustPlant(t, svc, owner, "Garlic", 15, "🧄")
+	mustPlant(t, svc, owner, "Cucumber", 45, "🥒")
+
+	bed, err := svc.CreateObject(ctx, owner, g.ID, service.ObjectInput{
+		Kind: domain.KindBed, Name: "Garlic bed", XCM: 1000, YCM: 1000, WidthCM: 400, HeightCM: 400,
+	})
+	if err != nil {
+		t.Fatalf("bed: %v", err)
+	}
+	if _, err := svc.FillNamedRegion(ctx, owner, bed.ID, "all", garlic.ID, nil); err != nil {
+		t.Fatalf("seed the garlic: %v", err)
+	}
+
+	// 1. describe_garden — "the garlic bed" resolves to an object id, because the
+	//    description carries the NAMES of what's planted in each object.
+	res := call("describe_garden", map[string]any{"gardenId": g.ID})
+	if res.IsError {
+		t.Fatalf("describe_garden: %s", res.Content)
+	}
+	if !strings.Contains(res.Content, "Garlic") {
+		t.Fatalf("describe_garden didn't name what's planted: %s", res.Content)
+	}
+
+	// 2. find_plant — the step that used to be impossible.
+	res = call("find_plant", map[string]any{"query": "cucumber"})
+	if res.IsError {
+		t.Fatalf("find_plant: %s", res.Content)
+	}
+	var matches []struct {
+		ID   int64  `json:"id"`
+		Name string `json:"name"`
+	}
+	if err := json.Unmarshal([]byte(res.Content), &matches); err != nil {
+		t.Fatalf("decode find_plant: %v (%s)", err, res.Content)
+	}
+	if len(matches) == 0 || matches[0].Name != "Cucumber" {
+		t.Fatalf("find_plant(cucumber) = %+v", matches)
+	}
+
+	// 3. clear_object, 4. fill_region.
+	if r := call("clear_object", map[string]any{"objectId": bed.ID}); r.IsError {
+		t.Fatalf("clear_object: %s", r.Content)
+	}
+	if r := call("fill_region", map[string]any{
+		"objectId": bed.ID, "region": "all", "plantId": matches[0].ID,
+	}); r.IsError {
+		t.Fatalf("fill_region: %s", r.Content)
+	}
+
+	// The bed is cucumbers, and no garlic is still growing in it.
+	full, err := svc.GardenFull(ctx, owner, g.ID, nil)
+	if err != nil {
+		t.Fatalf("GardenFull: %v", err)
+	}
+	if len(full.Plantings) == 0 {
+		t.Fatal("the bed ended up empty")
+	}
+	for _, p := range full.Plantings {
+		if p.PlantID == garlic.ID {
+			t.Errorf("garlic is still active in the bed")
+		}
+		if p.PlantID != matches[0].ID {
+			t.Errorf("unexpected plant %d in the bed", p.PlantID)
+		}
+	}
+}
+
+// TestFindPlantReturnsCandidatesNotAGuess — "garlic" against a catalog holding
+// both "Garlic" and "German Red Garlic" is genuinely ambiguous, and silently
+// picking one is how the agent plants the wrong thing.
+func TestFindPlantReturnsCandidatesNotAGuess(t *testing.T) {
+	ctx := context.Background()
+	svc, owner := newAgentTestService(t)
+	box := NewToolbox(svc, owner)
+
+	mustPlant(t, svc, owner, "German Red Garlic", 15, "🧄")
+
+	raw, _ := json.Marshal(map[string]any{"query": "garlic"})
+	res := box.Execute(ctx, llm.ToolCall{ID: "1", Name: "find_plant", Arguments: raw})
+	if res.IsError {
+		t.Fatalf("find_plant: %s", res.Content)
+	}
+	var matches []struct {
+		Name string `json:"name"`
+	}
+	if err := json.Unmarshal([]byte(res.Content), &matches); err != nil {
+		t.Fatalf("decode: %v", err)
+	}
+	names := map[string]bool{}
+	for _, m := range matches {
+		names[m.Name] = true
+	}
+	// The built-in catalog seeds a plain "Garlic"; the custom one is ours.
+	if !names["Garlic"] || !names["German Red Garlic"] {
+		t.Errorf("find_plant(garlic) = %+v, want both the built-in and the custom variety", matches)
+	}
+	// Exact match ranks first, so a caller taking [0] gets the least surprising one.
+	if len(matches) > 0 && matches[0].Name != "Garlic" {
+		t.Errorf("first match = %q, want the exact name", matches[0].Name)
+	}
+}
+
+// TestCreatePlantIsUserScoped — the catalog belongs to the user, not to any
+// garden, so someone with no editable garden can still name a new variety. The
+// issue asks for this to be asserted rather than assumed.
+func TestCreatePlantIsUserScoped(t *testing.T) {
+	ctx := context.Background()
+	svc, owner := newAgentTestService(t)
+	other, err := svc.Register(ctx, service.RegisterInput{Email: "[email protected]", DisplayName: "B", Password: "password123"})
+	if err != nil {
+		t.Fatalf("register: %v", err)
+	}
+	box := NewToolbox(svc, other.ID)
+
+	raw, _ := json.Marshal(map[string]any{
+		"name": "Painted Mountain Corn", "category": "vegetable",
+		"spacingCm": 30.0, "color": "#c08a3f", "icon": "🌽",
+	})
+	res := box.Execute(ctx, llm.ToolCall{ID: "1", Name: "create_plant", Arguments: raw})
+	if res.IsError {
+		t.Fatalf("create_plant: %s", res.Content)
+	}
+	var created struct {
+		ID      int64  `json:"id"`
+		OwnerID *int64 `json:"ownerId"`
+		Name    string `json:"name"`
+	}
+	if err := json.Unmarshal([]byte(res.Content), &created); err != nil {
+		t.Fatalf("decode: %v", err)
+	}
+	if created.OwnerID == nil || *created.OwnerID != other.ID {
+		t.Errorf("ownerId = %v, want the acting user %d", created.OwnerID, other.ID)
+	}
+	// And it stays theirs: the other user's catalog doesn't gain it.
+	ownerPlants, err := svc.ListPlants(ctx, owner)
+	if err != nil {
+		t.Fatalf("ListPlants: %v", err)
+	}
+	for _, p := range ownerPlants {
+		if p.Name == "Painted Mountain Corn" {
+			t.Error("a plant created by one user showed up in another's catalog")
+		}
+	}
+}
+
+// TestJournalToolWritesADatedObservation — "note that the west bed has mildew"
+// is squarely the kind of thing you say out loud while walking around.
+func TestJournalToolWritesADatedObservation(t *testing.T) {
+	ctx := context.Background()
+	svc, owner := newAgentTestService(t)
+	box := NewToolbox(svc, owner)
+
+	g, err := svc.CreateGarden(ctx, owner, service.GardenInput{Name: "Plot", WidthCM: 2000, HeightCM: 2000})
+	if err != nil {
+		t.Fatalf("garden: %v", err)
+	}
+	bed, err := svc.CreateObject(ctx, owner, g.ID, service.ObjectInput{
+		Kind: domain.KindBed, Name: "West bed", XCM: 500, YCM: 500, WidthCM: 200, HeightCM: 200,
+	})
+	if err != nil {
+		t.Fatalf("bed: %v", err)
+	}
+
+	raw, _ := json.Marshal(map[string]any{
+		"gardenId": g.ID, "objectId": bed.ID,
+		"body": "Powdery mildew on the west bed", "observedAt": "2026-08-14",
+	})
+	res := box.Execute(ctx, llm.ToolCall{ID: "1", Name: "add_journal_entry", Arguments: raw})
+	if res.IsError {
+		t.Fatalf("add_journal_entry: %s", res.Content)
+	}
+
+	entries, _, err := svc.ListJournal(ctx, owner, g.ID, service.JournalQuery{ObjectID: &bed.ID})
+	if err != nil {
+		t.Fatalf("ListJournal: %v", err)
+	}
+	if len(entries) != 1 {
+		t.Fatalf("got %d entries, want 1", len(entries))
+	}
+	if entries[0].Body != "Powdery mildew on the west bed" || entries[0].ObservedAt != "2026-08-14" {
+		t.Errorf("unexpected entry: %+v", entries[0])
+	}
+	if entries[0].AuthorID != owner {
+		t.Errorf("author = %d, want the acting user %d", entries[0].AuthorID, owner)
+	}
+}
+
+// newAgentTestService spins up an in-memory pansy with one registered user.
+func newAgentTestService(t *testing.T) (*service.Service, int64) {
+	t.Helper()
+	ctx := context.Background()
+	db, err := store.Open(":memory:")
+	if err != nil {
+		t.Fatalf("open: %v", err)
+	}
+	t.Cleanup(func() { db.Close() })
+	if err := db.Migrate(ctx); err != nil {
+		t.Fatalf("migrate: %v", err)
+	}
+	svc := service.New(db, &config.Config{Registration: config.RegistrationOpen, LocalAuth: true})
+	owner, err := svc.Register(ctx, service.RegisterInput{Email: "[email protected]", DisplayName: "A", Password: "password123"})
+	if err != nil {
+		t.Fatalf("register: %v", err)
+	}
+	return svc, owner.ID
+}

internal/api/agent.go

@@ -0,0 +1,253 @@
+package api
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"log/slog"
+	"net/http"
+	"sync"
+	"time"
+
+	mdagent "gitea.stevedudenhoeffer.com/steve/majordomo/agent"
+	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
+	"github.com/gin-gonic/gin"
+
+	"gitea.stevedudenhoeffer.com/steve/pansy/internal/agent"
+	"gitea.stevedudenhoeffer.com/steve/pansy/internal/domain"
+)
+
+// The garden assistant's chat surface (#56).
+//
+// Streaming, because a turn that clears a bed and replants it makes a dozen tool
+// calls over tens of seconds. Without streaming that is a long silence followed
+// by everything at once, which reads as a hang — and the whole design rests on
+// watching the canvas change as it happens.
+
+// keepAliveInterval is how often a quiet stream emits a comment frame. Well
+// under the 30–60s idle timeout typical of reverse proxies, which is the thing
+// it exists to stay ahead of.
+const keepAliveInterval = 20 * time.Second
+
+// chatRequest is the body of POST /agent/chat.
+type chatRequest struct {
+	GardenID int64  `json:"gardenId" binding:"required"`
+	Message  string `json:"message" binding:"required"`
+}
+
+// chatEvent is one server-sent event. Exactly one field is set.
+type chatEvent struct {
+	// Step reports a completed model round trip: which tools it called.
+	Step *stepEvent `json:"step,omitempty"`
+	// Done carries the finished turn.
+	Done *agent.Turn `json:"done,omitempty"`
+	// Error is a turn that failed, in words meant for a person.
+	Error string `json:"error,omitempty"`
+	// Warning rides alongside Done: the turn worked, but something adjacent to it
+	// didn't, and saying nothing would be the quieter lie.
+	Warning string `json:"warning,omitempty"`
+}
+
+type stepEvent struct {
+	Index int      `json:"index"`
+	Tools []string `json:"tools"`
+}
+
+func (h *handlers) agentChat(c *gin.Context) {
+	var req chatRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		writeAPIError(c, http.StatusBadRequest, "INVALID_INPUT", "a gardenId and a message are required")
+		return
+	}
+	actor := mustActor(c)
+
+	history, err := h.svc.AgentHistory(c.Request.Context(), actor.ID, req.GardenID)
+	if err != nil {
+		writeServiceError(c, err)
+		return
+	}
+
+	stream := openEventStream(c)
+	send := stream.send
+
+	// A model thinking hard between tool calls sends nothing for a while, and an
+	// idle proxy will cut a quiet connection. Deferred so a panic in the run
+	// can't leak the ticker goroutine; stopping it twice is harmless.
+	stopBeat := stream.keepAlive(keepAliveInterval)
+	defer stopBeat()
+
+	turn, err := h.agent.Run(c.Request.Context(), actor.ID, req.GardenID, req.Message,
+		replayHistory(history),
+		func(s mdagent.Step) {
+			send(chatEvent{Step: &stepEvent{Index: s.Index, Tools: toolNames(s)}})
+		})
+	stopBeat()
+	if err != nil {
+		// The stream is already open, so an error is an event rather than a
+		// status code — the client has committed to reading a stream by now.
+		send(chatEvent{Error: chatErrorMessage(err)})
+		return
+	}
+
+	// The turn itself succeeded — the garden really did change — so Done goes out
+	// regardless. But if the transcript couldn't be saved, say so: a clean "done"
+	// followed by a conversation that has forgotten the exchange after a reload is
+	// exactly the kind of quiet inconsistency that makes a tool feel unreliable.
+	//
+	// Detached from the request context, because the commonest reason this fails
+	// is the client having gone away — and the exchange is worth keeping either
+	// way, since the change set it produced certainly is.
+	if _, err := h.svc.RecordAgentExchange(context.WithoutCancel(c.Request.Context()), actor.ID, req.GardenID,
+		req.Message, turn.Reply, turn.ChangeSetID); err != nil {
+		slog.Error("api: record agent exchange", "error", err, "garden", req.GardenID)
+		send(chatEvent{Done: turn, Warning: "I couldn't save this exchange, so it won't be here after a reload. Anything I changed is still on the canvas, and in History."})
+		return
+	}
+	send(chatEvent{Done: turn})
+}
+
+// eventStream serializes writes to one SSE response.
+//
+// The mutex is load-bearing, not decoration: step events are sent from the
+// agent's run goroutine while the keep-alive ticker writes from its own, and two
+// goroutines writing a ResponseWriter concurrently is a data race that corrupts
+// frames long before it crashes anything.
+type eventStream struct {
+	c  *gin.Context
+	mu sync.Mutex
+}
+
+// openEventStream puts the response into SSE mode.
+//
+// Headers go out before the first write and the stream is flushed immediately,
+// so a proxy holding the response until it looks complete can't reintroduce
+// exactly the silence streaming exists to remove.
+func openEventStream(c *gin.Context) *eventStream {
+	c.Header("Content-Type", "text/event-stream")
+	c.Header("Cache-Control", "no-cache")
+	c.Header("X-Accel-Buffering", "no")
+	c.Writer.Flush()
+	return &eventStream{c: c}
+}
+
+func (s *eventStream) send(ev chatEvent) {
+	b, err := json.Marshal(ev)
+	if err != nil {
+		slog.Error("api: encode chat event", "error", err)
+		return
+	}
+	s.write(fmt.Sprintf("data: %s\n\n", b))
+}
+
+func (s *eventStream) write(frame string) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	_, _ = io.WriteString(s.c.Writer, frame)
+	s.c.Writer.Flush()
+}
+
+// keepAlive writes an SSE comment frame on an interval until the returned
+// function is called, so a long silence while the model thinks doesn't look like
+// a dead connection to whatever sits in between. SSE ignores comment frames, so
+// this costs the client nothing.
+func (s *eventStream) keepAlive(every time.Duration) func() {
+	done := make(chan struct{})
+	stopped := make(chan struct{})
+	go func() {
+		defer close(stopped)
+		t := time.NewTicker(every)
+		defer t.Stop()
+		for {
+			select {
+			case <-done:
+				return
+			case <-s.c.Request.Context().Done():
+				return
+			case <-t.C:
+				s.write(": keep-alive\n\n")
+			}
+		}
+	}()
+	// Idempotent: the handler stops it explicitly when the run returns and again
+	// via defer, so a panic can't leak the goroutine.
+	var once sync.Once
+	return func() {
+		once.Do(func() { close(done) })
+		<-stopped
+	}
+}
+
+// getAgentHistory returns the actor's thread for a garden.
+func (h *handlers) getAgentHistory(c *gin.Context) {
+	gardenID, ok := parseIDParam(c, "id")
+	if !ok {
+		return
+	}
+	msgs, err := h.svc.AgentHistory(c.Request.Context(), mustActor(c).ID, gardenID)
+	if err != nil {
+		writeServiceError(c, err)
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{"messages": msgs})
+}
+
+// deleteAgentHistory is the "start over" escape hatch.
+func (h *handlers) deleteAgentHistory(c *gin.Context) {
+	gardenID, ok := parseIDParam(c, "id")
+	if !ok {
+		return
+	}
+	if err := h.svc.ClearAgentHistory(c.Request.Context(), mustActor(c).ID, gardenID); err != nil {
+		writeServiceError(c, err)
+		return
+	}
+	c.Status(http.StatusNoContent)
+}
+
+// replayHistory turns stored text into model messages.
+//
+// Only the text is replayed — no stored tool calls. Continuity needs what was
+// said and what came back; replaying a tool call would be replaying a decision
+// made against a garden that has since moved on.
+func replayHistory(msgs []domain.AgentMessage) []llm.Message {
+	out := make([]llm.Message, 0, len(msgs))
+	for _, m := range msgs {
+		if m.Role == domain.AgentRoleUser {
+			out = append(out, llm.UserText(m.Body))
+		} else {
+			out = append(out, llm.AssistantText(m.Body))
+		}
+	}
+	return out
+}
+
+func toolNames(s mdagent.Step) []string {
+	names := make([]string, 0, len(s.Results))
+	for _, r := range s.Results {
+		names = append(names, r.Name)
+	}
+	return names
+}
+
+// chatErrorMessage turns a failure into something worth reading. Permission
+// errors in particular get named: "the agent broke" and "you can only view this
+// garden" want very different reactions.
+func chatErrorMessage(err error) string {
+	switch {
+	case errors.Is(err, domain.ErrForbidden):
+		return "You can only view this garden, so I can't change anything in it."
+	case errors.Is(err, domain.ErrNotFound):
+		return "I can't find that garden."
+	case errors.Is(err, domain.ErrInvalidInput):
+		return "I didn't get a message to work from."
+	case errors.Is(err, io.EOF), errors.Is(err, context.Canceled):
+		return "The connection dropped partway through. Anything I'd already changed is on the canvas, and in History."
+	case errors.Is(err, context.DeadlineExceeded):
+		return "That took too long and I stopped. Anything I'd already changed is on the canvas, and in History."
+	default:
+		slog.Error("api: agent run failed", "error", err)
+		return "Something went wrong talking to the model. Anything I'd already changed is on the canvas, and in History."
+	}
+}

internal/api/agent_test.go

@@ -0,0 +1,33 @@
+package api
+
+import (
+	"net/http"
+	"strconv"
+	"testing"
+)
+
+// TestAgentRoutesAbsentWithoutAKey — an instance with no API key must start,
+// serve the app, and simply not offer the assistant. The routes aren't
+// registered at all, so this is a 404 rather than a handler that apologizes:
+// the same shape as OIDC when unconfigured.
+func TestAgentRoutesAbsentWithoutAKey(t *testing.T) {
+	r := authEngine(t, localCfg()) // localCfg has no agent configuration
+	cookie := registerAndCookie(t, r, "[email protected]")
+	gid := createGardenAPI(t, r, cookie, "G")
+
+	w := doJSON(t, r, http.MethodPost, "/api/v1/agent/chat",
+		map[string]any{"gardenId": gid, "message": "plant garlic"}, cookie)
+	if w.Code != http.StatusNotFound {
+		t.Errorf("chat without a key: status %d, want 404", w.Code)
+	}
+
+	path := "/api/v1/gardens/" + strconv.FormatInt(gid, 10) + "/agent/history"
+	if w := doJSON(t, r, http.MethodGet, path, nil, cookie); w.Code != http.StatusNotFound {
+		t.Errorf("history without a key: status %d, want 404", w.Code)
+	}
+
+	// And the rest of the app is entirely unaffected.
+	if w := doJSON(t, r, http.MethodGet, fullPath(gid), nil, cookie); w.Code != http.StatusOK {
+		t.Errorf("editor load: status %d, want 200 — an unconfigured agent must not break the app", w.Code)
+	}
+}

internal/api/api.go

@@ -12,6 +12,7 @@ import (
 	"github.com/gin-gonic/gin"
 	sloggin "github.com/samber/slog-gin"
 
+	"gitea.stevedudenhoeffer.com/steve/pansy/internal/agent"
 	"gitea.stevedudenhoeffer.com/steve/pansy/internal/config"
 	"gitea.stevedudenhoeffer.com/steve/pansy/internal/service"
 )
@@ -22,6 +23,9 @@ type handlers struct {
 	cfg  *config.Config
 	svc  *service.Service
 	oidc *oidcClient // nil unless OIDC is configured (see config.OIDCReady)
+	// agent is nil unless the assistant is configured; the chat routes are only
+	// registered when it isn't, so a handler never has to check.
+	agent *agent.Runner
 }
 
 // New builds the gin engine with the standard middleware stack and registers the
@@ -49,6 +53,10 @@ func New(cfg *config.Config, svc *service.Service) *gin.Engine {
 	// is set; see csrfGuard).
 	v1.Use(h.csrfGuard())
 	v1.GET("/healthz", healthz)
+	// What this instance can actually do, so the UI offers only what works.
+	// Registered after the agent below, because it reports whether the runner
+	// actually built — not merely whether it was configured to.
+	v1.GET("/capabilities", h.capabilities)
 
 	// Auth endpoints are exempt from requireAuth (you can't be logged in yet);
 	// /me is the one that needs a session. Feature routers in later issues attach
@@ -118,6 +126,38 @@ func New(cfg *config.Config, svc *service.Service) *gin.Engine {
 	plantings.PATCH("/:id", h.updatePlanting)
 	plantings.DELETE("/:id", h.deletePlanting)
 
+	// The garden assistant, registered only when it can actually be offered —
+	// the same shape as OIDC. An instance with no API key serves the app
+	// normally and simply doesn't have these routes.
+	if !cfg.Agent.Ready() {
+		// Say WHY, at startup, in the logs an operator is already looking at.
+		// Someone who set the key and sees no assistant otherwise has nothing to
+		// check — and "is the variable reaching the container?" is exactly the
+		// question they need answered.
+		slog.Info("api: garden assistant disabled",
+			"enabled", cfg.Agent.Enabled,
+			"hasApiKey", cfg.Agent.OllamaCloudAPIKey != "",
+			"model", cfg.Agent.Model,
+			"hint", "needs OLLAMA_CLOUD_API_KEY set in the container's environment (not just the stack's)")
+	}
+	if cfg.Agent.Ready() {
+		runner, err := agent.NewRunner(svc, cfg)
+		if err != nil {
+			// Configured but unusable (an unresolvable model spec, say). Log it and
+			// carry on without the assistant rather than refusing to start: a
+			// garden planner that won't boot because of a chat feature is worse
+			// than one without chat.
+			slog.Error("api: garden assistant disabled", "error", err)
+		} else {
+			h.agent = runner
+			agentGroup := v1.Group("/agent", h.requireAuth())
+			agentGroup.POST("/chat", h.agentChat)
+			gardens.GET("/:id/agent/history", h.getAgentHistory)
+			gardens.DELETE("/:id/agent/history", h.deleteAgentHistory)
+			slog.Info("api: garden assistant enabled", "model", cfg.Agent.Model)
+		}
+	}
+
 	// Undo. A change set is addressed by its own id; the service resolves the
 	// owning garden for the permission check, same as objects and plantings.
 	changeSets := v1.Group("/change-sets", h.requireAuth())
@@ -155,6 +195,16 @@ func New(cfg *config.Config, svc *service.Service) *gin.Engine {
 	return r
 }
 
+// capabilities reports what this instance can actually do, so the UI offers only
+// what works.
+//
+// It reports whether the runner BUILT, not whether it was configured: a
+// configured-but-unresolvable model leaves the routes unregistered, and saying
+// "yes" there would offer a chat tab whose first message 404s.
+func (h *handlers) capabilities(c *gin.Context) {
+	c.JSON(http.StatusOK, gin.H{"agent": h.agent != nil})
+}
+
 // healthz is a liveness probe: always returns {"ok": true} when the server is up.
 func healthz(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{"ok": true})

internal/config/config.go

@@ -19,6 +19,9 @@ const (
 	RegistrationClosed = "closed"
 )
 
+// DefaultAgentModel is the assistant's model when PANSY_AGENT_MODEL is unset.
+const DefaultAgentModel = "ollama-cloud/glm-5.2:cloud"
+
 // Config is the fully-resolved runtime configuration.
 type Config struct {
 	// Port is the TCP port the HTTP server listens on (PANSY_PORT, default 8080).
@@ -37,6 +40,8 @@ type Config struct {
 	LocalAuth bool
 	// OIDC holds the optional OpenID Connect provider settings.
 	OIDC OIDCConfig
+	// Agent holds the garden-assistant settings.
+	Agent AgentConfig
 	// TrustedProxies is the set of proxy CIDRs/IPs gin trusts for client IP
 	// resolution (PANSY_TRUSTED_PROXIES, comma-separated). Empty trusts none.
 	TrustedProxies []string
@@ -51,6 +56,33 @@ type OIDCConfig struct {
 	ButtonLabel  string // PANSY_OIDC_BUTTON_LABEL — login-page button text
 }
 
+// AgentConfig holds the garden assistant's settings.
+type AgentConfig struct {
+	// Model is the majordomo model spec, passed VERBATIM to majordomo.Parse
+	// (PANSY_AGENT_MODEL). The grammar is majordomo's, not pansy's — parsing or
+	// validating it here would only mean two places to update when it grows. A
+	// comma-separated spec is a failover chain, so
+	// "ollama-cloud/glm-5.2:cloud,ollama-cloud/kimi-k2.6:cloud" gets a fallback
+	// for free.
+	Model string
+	// OllamaCloudAPIKey authenticates against Ollama Cloud
+	// (OLLAMA_CLOUD_API_KEY — the same secret name gadfly uses, which is why
+	// it isn't majordomo's own OLLAMA_API_KEY; pansy passes it explicitly rather
+	// than relying on ambient environment).
+	OllamaCloudAPIKey string
+	// Enabled turns the assistant on (PANSY_AGENT_ENABLED). Defaults to on when
+	// a key is present, so an instance with no key starts cleanly and simply
+	// doesn't offer the agent — the same shape as OIDC 404ing when unconfigured.
+	Enabled bool
+}
+
+// Ready reports whether the assistant can actually be offered. Both the route
+// registration and whatever advertises capabilities gate on this, so what's
+// advertised always matches what's live.
+func (a AgentConfig) Ready() bool {
+	return a.Enabled && a.OllamaCloudAPIKey != "" && a.Model != ""
+}
+
 // Enabled reports whether enough OIDC config is present to attempt discovery.
 func (o OIDCConfig) Enabled() bool {
 	return o.Issuer != "" && o.ClientID != ""
@@ -87,6 +119,16 @@ func Load() *Config {
 		TrustedProxies: envList("PANSY_TRUSTED_PROXIES"),
 	}
 
+	agentKey := envStr("OLLAMA_CLOUD_API_KEY", "")
+	cfg.Agent = AgentConfig{
+		Model:             envStr("PANSY_AGENT_MODEL", DefaultAgentModel),
+		OllamaCloudAPIKey: agentKey,
+		// Default on when a key is present: having configured the key IS the
+		// opt-in, and making people set a second flag to use what they just
+		// configured is a papercut with no upside.
+		Enabled: envBool("PANSY_AGENT_ENABLED", agentKey != ""),
+	}
+
 	if cfg.Registration != RegistrationOpen && cfg.Registration != RegistrationClosed {
 		slog.Warn("config: invalid PANSY_REGISTRATION, defaulting to open", "value", cfg.Registration)
 		cfg.Registration = RegistrationOpen

internal/domain/domain.go

@@ -191,6 +191,28 @@ type JournalEntry struct {
 	AuthorName string `json:"authorName,omitempty"`
 }
 
+// Roles a stored agent message can have.
+const (
+	AgentRoleUser      = "user"
+	AgentRoleAssistant = "assistant"
+)
+
+// AgentMessage is one side of a chat exchange with the garden assistant. Only
+// the text is kept, not the model's full transcript with its tool calls:
+// continuity needs what was said and what came back, and replaying a stored tool
+// call would be replaying a decision made against a garden that has since moved
+// on.
+type AgentMessage struct {
+	ID             int64  `json:"id"`
+	ConversationID int64  `json:"conversationId"`
+	Role           string `json:"role"`
+	Body           string `json:"body"`
+	// ChangeSetID is what this turn changed, if anything — the handle the chat
+	// panel needs to offer Undo on the message that caused it.
+	ChangeSetID *int64 `json:"changeSetId,omitempty"`
+	CreatedAt   string `json:"createdAt"`
+}
+
 // RevertConflict reports one entity a revert deliberately left alone, because
 // reverting it would have discarded a change made after the change set being
 // reverted. The rest of the change set still reverts.

internal/service/agent.go

@@ -0,0 +1,62 @@
+package service
+
+import (
+	"context"
+
+	"gitea.stevedudenhoeffer.com/steve/pansy/internal/domain"
+)
+
+// Chat persistence for the garden assistant (#56). The run loop itself lives in
+// internal/agent; this is the part that needs pansy's permission checks.
+
+// maxRetainedTurns caps how much of a thread is kept in context. Retained turns
+// are a working memory, not an archive — a season of chat replayed into every
+// prompt would cost more than it informs.
+const maxRetainedTurns = 20
+
+// AgentHistory returns the recent messages of the actor's own thread for a
+// garden they can edit, oldest first.
+//
+// Requires EDITOR, not viewer: the assistant acts, so being able to talk to it
+// about a garden is the same permission as being able to change it. A viewer
+// asking it to plant something would get a refusal from every tool anyway, and
+// offering the conversation would be offering something that cannot work.
+func (s *Service) AgentHistory(ctx context.Context, actorID, gardenID int64) ([]domain.AgentMessage, error) {
+	if _, err := s.requireGardenRole(ctx, actorID, gardenID, roleEditor); err != nil {
+		return nil, err
+	}
+	conv, err := s.store.EnsureConversation(ctx, gardenID, actorID)
+	if err != nil {
+		return nil, err
+	}
+	return s.store.ListAgentMessages(ctx, conv, maxRetainedTurns*2)
+}
+
+// RecordAgentExchange stores one user message and the assistant's reply, and
+// returns the reply row. Called by the runtime after a turn completes.
+func (s *Service) RecordAgentExchange(ctx context.Context, actorID, gardenID int64, userMessage, reply string, changeSetID *int64) (*domain.AgentMessage, error) {
+	if _, err := s.requireGardenRole(ctx, actorID, gardenID, roleEditor); err != nil {
+		return nil, err
+	}
+	conv, err := s.store.EnsureConversation(ctx, gardenID, actorID)
+	if err != nil {
+		return nil, err
+	}
+	if _, err := s.store.AppendAgentMessage(ctx, &domain.AgentMessage{
+		ConversationID: conv, Role: domain.AgentRoleUser, Body: userMessage,
+	}); err != nil {
+		return nil, err
+	}
+	return s.store.AppendAgentMessage(ctx, &domain.AgentMessage{
+		ConversationID: conv, Role: domain.AgentRoleAssistant, Body: reply, ChangeSetID: changeSetID,
+	})
+}
+
+// ClearAgentHistory drops the actor's thread for a garden — the "start over"
+// escape hatch when a conversation has gone somewhere unhelpful.
+func (s *Service) ClearAgentHistory(ctx context.Context, actorID, gardenID int64) error {
+	if _, err := s.requireGardenRole(ctx, actorID, gardenID, roleEditor); err != nil {
+		return err
+	}
+	return s.store.DeleteConversation(ctx, gardenID, actorID)
+}

internal/service/ops.go

@@ -28,13 +28,9 @@ type Region struct {
 	MinX, MinY, MaxX, MaxY float64
 }
 
-// contains reports whether a local point lies in the region.
-func (r Region) contains(x, y float64) bool {
-	return x >= r.MinX && x <= r.MaxX && y >= r.MinY && y <= r.MaxY
-}
-
 // clampTo intersects the region with an object's local bounds (±halfW, ±halfH),
-// so an oversized caller-supplied region can't make hexCenters loop forever.
+// so a fill can't plant outside the object it was aimed at. A region that misses
+// the object entirely comes back empty — see empty().
 func (r Region) clampTo(halfW, halfH float64) Region {
 	return Region{
 		MinX: math.Max(r.MinX, -halfW), MinY: math.Max(r.MinY, -halfH),
@@ -42,6 +38,16 @@ func (r Region) clampTo(halfW, halfH float64) Region {
 	}
 }
 
+// empty reports whether the region encloses nothing.
+//
+// This exists because clampTo expresses "no overlap" by INVERTING the region —
+// Max clamps below Min — rather than by zeroing it, which is not something a
+// reader guesses. Naming it once here beats a bare `MaxX < MinX` at each place
+// that has to care.
+func (r Region) empty() bool {
+	return r.MaxX < r.MinX || r.MaxY < r.MinY
+}
+
 // rect builds a rectangular region.
 func rect(minX, minY, maxX, maxY float64) Region {
 	return Region{MinX: minX, MinY: minY, MaxX: maxX, MaxY: maxY}
@@ -94,9 +100,11 @@ func defaultPlopRadius(spacingCM float64) float64 {
 // FillRegion lays a hex-packed field of plops of one plant across a region of a
 // plantable object the actor can edit. Plop radius comes from the plant's spacing
 // (or spacingOverride) via defaultPlopRadius; centers sit on a hex lattice at 2×
-// radius pitch, kept where the center is inside the region. A candidate is
+// radius pitch, centered in the region, and set in from each edge by the plop's
-// skipped when its plop would sit entirely inside an existing active plop (so
+// radius less half a spacing — see hexCenters for why that half-spacing is what
-// re-filling doesn't stack duplicates). Returns the plops it created.
+// the edge is owed. A candidate is skipped when its plop would sit entirely
+// inside an existing active plop (so re-filling doesn't stack duplicates).
+// Returns the plops it created.
 func (s *Service) FillRegion(ctx context.Context, actorID, objectID int64, region Region, plantID int64, spacingOverride *float64) ([]domain.Planting, error) {
 	o, _, err := s.objectForRole(ctx, actorID, objectID, roleEditor)
 	if err != nil {
@@ -106,9 +114,9 @@ func (s *Service) FillRegion(ctx context.Context, actorID, objectID int64, regio
 }
 
 // fillLoaded is the shared body of FillRegion/FillNamedRegion given an object
-// already loaded and authorized (roleEditor). It clamps the region to the
+// already loaded and authorized (roleEditor). It rejects a non-finite region,
-// object's bounds, refuses fills over maxFillPlops, and inserts the whole batch
+// clamps the region to the object's bounds, refuses fills over maxFillPlops, and
-// in one transaction rather than one round-trip per plop.
+// inserts the whole batch in one transaction rather than one round-trip per plop.
 func (s *Service) fillLoaded(ctx context.Context, actorID int64, o *domain.GardenObject, region Region, plantID int64, spacingOverride *float64) ([]domain.Planting, error) {
 	if !o.Plantable {
 		return nil, domain.ErrInvalidInput
@@ -129,9 +137,21 @@ func (s *Service) fillLoaded(ctx context.Context, actorID int64, o *domain.Garde
 		return nil, domain.ErrInvalidInput
 	}
 
+	// A caller-supplied region is arbitrary floats, and non-finite ones survive
+	// everything downstream: clamping keeps them, the inverted-region guard can't
+	// see NaN (it compares false both ways), and fitAxis centres on them happily.
+	// Nothing corrupt reaches the table — SQLite stores NaN as NULL and the NOT
+	// NULL constraint refuses it — but the caller gets an opaque store error for
+	// NaN, and for +Inf a silent zero-plop success. Both are lies about what went
+	// wrong; say "bad input" here instead.
+	if !isFinite(region.MinX) || !isFinite(region.MinY) ||
+		!isFinite(region.MaxX) || !isFinite(region.MaxY) {
+		return nil, domain.ErrInvalidInput
+	}
+
 	region = region.clampTo(o.WidthCM/2, o.HeightCM/2)
-	centers := hexCenters(region, radius)
+	centers, total := hexCenters(region, radius, spacing, maxFillPlops)
-	if len(centers) > maxFillPlops {
+	if total > maxFillPlops {
 		return nil, domain.ErrInvalidInput // region too large for this spacing; ask for less
 	}
 
@@ -169,32 +189,112 @@ func (s *Service) fillLoaded(ctx context.Context, actorID int64, o *domain.Garde
 
 type localPoint struct{ x, y float64 }
 
-// hexCenters returns hex-packed lattice centers whose center lies in the region.
+// hexCenters returns hex-packed lattice centers filling a region: rows radius·√3
-// Rows are spaced radius·√3 apart and every other row is offset by radius, the
+// apart, alternate rows offset by half a pitch, at a 2×radius pitch. The lattice
-// standard hexagonal packing at a 2×radius pitch. The lattice is anchored one
+// is CENTERED, so the leftover is shared between opposite edges instead of piling
-// radius inside the region's min corner so the first plop sits inside it.
+// up against the far one.
-func hexCenters(r Region, radius float64) []localPoint {
+//
+// # How close to the edge the outer row goes
+//
+// Spacing is a constraint BETWEEN NEIGHBOURING PLANTS competing for the same
+// soil, light and water. A bed edge is not a competitor, so the outer row only
+// owes it HALF the spacing — the half it would otherwise share with a neighbour.
+// That is the arithmetic inside every square-foot-gardening chart: 4 per square
+// is 6" apart and 3" from the square's edge; 9 per square is 4" apart and 2"
+// from the edge. Garlic at 9 per square goes in 2" from the frame, not 6".
+//
+// A plop is a CLUMP, not a plant — defaultPlopRadius makes it 1.5×spacing, so
+// three spacings across — and its plants sit out to its rim. So keeping the whole
+// circle inside the bed would inset the outer row by a full 1.5 spacings, three
+// times what the rule allows. Instead the clump may hang over the edge by up to
+// half a spacing, which puts its outermost plants exactly the half-spacing from
+// the edge that the rule asks for. Overhang is capped there and nowhere near the
+// full radius: a clump mostly outside the bed is a drawing of plants in the path.
+//
+// Do not "simplify" this back to anchoring at the region's min corner. That is
+// what #75 was: staggered rows start a full pitch in, and the leftover all lands
+// on the far edge, where clumps hang outside a bed that nothing clips them to.
+//
+// # Counting before building
+//
+// hexCenters returns the total alongside the points, and works that total out
+// BEFORE building anything: a fill large enough to be refused shouldn't allocate
+// its whole lattice first just to be counted and thrown away. Over `limit` it
+// returns (nil, total), so the caller can still refuse with the real number.
+func hexCenters(r Region, radius, spacing float64, limit int) ([]localPoint, int) {
 	if radius <= 0 {
-		return nil
+		return nil, 0
+	}
+	// An empty region has no inside to plant. The old loop-until-past-MaxX form
+	// got this for free by never entering the loop; counting positions up front
+	// does not, and would site a plop off the bed.
+	if r.empty() {
+		return nil, 0
 	}
 	pitch := 2 * radius
 	rowH := pitch * math.Sqrt(3) / 2
-	const eps = 1e-6
+
-	var pts []localPoint
+	// How far a clump's centre must stay inside the edge: its own radius, less the
-	row := 0
+	// half-spacing of overhang the rule allows. Never negative, and never past the
-	for y := r.MinY + radius; y <= r.MaxY+eps; y += rowH {
+	// centre of the clump.
-		xStart := r.MinX + radius
+	inset := math.Max(0, radius-math.Max(0, spacing)/2)
-		if row%2 == 1 {
+
-			xStart += radius
+	rows, y0 := fitAxis(r.MaxY-r.MinY, rowH, inset)
+	cols, x0 := fitAxis(r.MaxX-r.MinX, pitch, inset)
+
+	// Exact, not an upper bound: staggered rows hold one fewer, so rows*cols would
+	// over-reserve by ~12% — and, more to the point, allocating it is the thing we
+	// are trying to avoid when the answer is "too many".
+	staggered := cols
+	if cols > 1 {
+		staggered = cols - 1
 	}
-		for x := xStart; x <= r.MaxX+eps; x += pitch {
+	total := (rows+1)/2*cols + rows/2*staggered
-			if r.contains(x, y) {
+	if total > limit {
-				pts = append(pts, localPoint{x, y})
+		return nil, total
+	}
+
+	pts := make([]localPoint, 0, total)
+	for row := 0; row < rows; row++ {
+		y := r.MinY + y0 + float64(row)*rowH
+		n, x := cols, r.MinX+x0
+		// The stagger falls out of centering: an offset row holds one fewer plop,
+		// and centering THAT run puts it exactly half a pitch off its neighbours.
+		// A single-column region has nothing to stagger against.
+		if row%2 == 1 && cols > 1 {
+			n, x = staggered, r.MinX+x0+pitch/2
+		}
+		for i := 0; i < n; i++ {
+			pts = append(pts, localPoint{x + float64(i)*pitch, y})
 		}
 	}
-		row++
+	return pts, total
 }
-	return pts
+
+// fitAxis returns how many lattice positions fit along a span at `step`, keeping
+// at least `inset` from each end, and the offset from the span's start that
+// centers them — so the leftover is split between the two edges rather than all
+// landing on the far one.
+//
+// A span too small to hold even one position at that inset still gets one, in the
+// middle: filling a bed narrower than a single plop with one plop is a better
+// answer than refusing to plant it.
+//
+// The step<=0 half of that guard is currently unreachable — hexCenters, the only
+// caller, returns early unless radius > 0, which makes both steps it passes
+// positive. It stays because dividing by a non-positive step yields ±Inf and then
+// a garbage int conversion, and a helper this small should not require reading
+// its caller to know it is safe. Deliberate, not an oversight.
+func fitAxis(length, step, inset float64) (n int, start float64) {
+	if step <= 0 || length < 2*inset {
+		return 1, length / 2
+	}
+	// The epsilon keeps an exact fit from being lost to floating point — a 60cm
+	// span at a 30cm step should give 2 positions, not 1 because the division
+	// landed on 0.9999999.
+	const eps = 1e-9
+	n = int(math.Floor((length-2*inset)/step+eps)) + 1
+	return n, (length - float64(n-1)*step) / 2
 }
 
 // coveredByExisting reports whether a new plop (center, radius) would sit

internal/service/ops_test.go

@@ -3,6 +3,8 @@ package service
 import (
 	"context"
 	"errors"
+	"math"
+	"sort"
 	"testing"
 
 	"gitea.stevedudenhoeffer.com/steve/pansy/internal/domain"
@@ -71,6 +73,165 @@ func TestDefaultPlopRadius(t *testing.T) {
 	}
 }
 
+// TestHexCentersEdgeInset pins the spacing rule the packing exists to honour:
+// spacing is a constraint between neighbouring plants, so a bed edge — which is
+// nobody's neighbour — is owed half a pitch, not a whole one.
+//
+// The bug this guards against was visible to anyone who filled a bed: staggered
+// rows began a full pitch in, leaving a bare strip a whole plop wide down one
+// side of every other row, while the far edge had plops hanging off it.
+func TestHexCentersEdgeInset(t *testing.T) {
+	for _, tc := range []struct {
+		name                  string
+		w, h, radius, spacing float64
+		wantRowStarts         []float64 // x of the first plop in rows 0 and 1
+	}{
+		// 4ft × 8ft bed, garlic at 15cm spacing → radius 22.5, pitch 45. Three
+		// columns, the outer ones overhanging by 6.5cm — under the 7.5cm the rule
+		// allows. Anchored at the corner this row started at -38.5 and its
+		// staggered neighbour a full 45 further in still.
+		{"4ft bed of garlic", 122, 244, 22.5, 15, []float64{-45, -22.5}},
+		// An exact fit: 90 wide at pitch 30 → 3 columns, no overhang needed.
+		{"exact fit", 90, 90, 15, 10, []float64{-30, -15}},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			r := rect(-tc.w/2, -tc.h/2, tc.w/2, tc.h/2)
+			pts, total := hexCenters(r, tc.radius, tc.spacing, maxFillPlops)
+			if len(pts) == 0 {
+				t.Fatal("no centers")
+			}
+			// The count is derived up front so an oversized fill is refused without
+			// building its lattice — which only works if it matches what gets built.
+			if total != len(pts) {
+				t.Errorf("reported total %d, built %d", total, len(pts))
+			}
+
+			// A clump may cross the edge, but only by the half-spacing the rule
+			// allows — never enough to be mostly out in the path.
+			budget := tc.spacing / 2
+			for _, p := range pts {
+				over := math.Max(
+					math.Max(r.MinX-(p.x-tc.radius), (p.x+tc.radius)-r.MaxX),
+					math.Max(r.MinY-(p.y-tc.radius), (p.y+tc.radius)-r.MaxY),
+				)
+				if over > budget+1e-6 {
+					t.Errorf("plop at (%.1f,%.1f) overhangs by %.2f, budget %.2f", p.x, p.y, over, budget)
+				}
+			}
+
+			// The margins match on opposite edges: the leftover is shared, not piled
+			// against the far side.
+			minX, maxX, minY, maxY := pts[0].x, pts[0].x, pts[0].y, pts[0].y
+			for _, p := range pts {
+				minX, maxX = math.Min(minX, p.x), math.Max(maxX, p.x)
+				minY, maxY = math.Min(minY, p.y), math.Max(maxY, p.y)
+			}
+			if w, e := minX-r.MinX, r.MaxX-maxX; math.Abs(w-e) > 1e-6 {
+				t.Errorf("lopsided horizontally: west margin %.2f, east %.2f", w, e)
+			}
+			if n, s := minY-r.MinY, r.MaxY-maxY; math.Abs(n-s) > 1e-6 {
+				t.Errorf("lopsided vertically: north margin %.2f, south %.2f", n, s)
+			}
+
+			// The staggered row is offset by HALF a pitch, not a whole one.
+			starts := map[float64]float64{}
+			for _, p := range pts {
+				if x, ok := starts[p.y]; !ok || p.x < x {
+					starts[p.y] = p.x
+				}
+			}
+			ys := make([]float64, 0, len(starts))
+			for y := range starts {
+				ys = append(ys, y)
+			}
+			sort.Float64s(ys)
+			for i, want := range tc.wantRowStarts {
+				if i >= len(ys) {
+					t.Fatalf("only %d rows, want at least %d", len(ys), len(tc.wantRowStarts))
+				}
+				if got := starts[ys[i]]; math.Abs(got-want) > 1e-6 {
+					t.Errorf("row %d starts at x=%.2f, want %.2f", i, got, want)
+				}
+			}
+		})
+	}
+}
+
+// TestHexCentersTinyRegion covers a region too small to hold a plop at the
+// half-pitch inset: planting one in the middle beats refusing to plant at all.
+//
+// The off-centre case earns its place — a region symmetric about the origin
+// can't tell "the middle of the region" from "the origin", so on its own it
+// would pass for an implementation that just returned (0,0).
+func TestHexCentersTinyRegion(t *testing.T) {
+	for _, tc := range []struct {
+		name         string
+		r            Region
+		wantX, wantY float64
+	}{
+		{"centred on the origin", rect(-5, -5, 5, 5), 0, 0},
+		{"off in a corner", rect(20, -40, 30, -30), 25, -35},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			pts, _ := hexCenters(tc.r, 15, 10, maxFillPlops)
+			if len(pts) != 1 || pts[0].x != tc.wantX || pts[0].y != tc.wantY {
+				t.Errorf("got %+v, want one plop at (%v,%v)", pts, tc.wantX, tc.wantY)
+			}
+		})
+	}
+}
+
+// TestFillRegionRejectsNonFiniteRegion: non-finite bounds survive clamping and
+// the inverted-region guard (NaN compares false both ways). Without the explicit
+// check, NaN surfaced as a raw store error ("NOT NULL constraint failed") and
+// +Inf as a silent success that planted nothing — neither of which tells the
+// caller what it actually did wrong.
+func TestFillRegionRejectsNonFiniteRegion(t *testing.T) {
+	ctx := context.Background()
+	s := newTestService(t, openConfig())
+	owner := seedUser(t, s, "[email protected]")
+	g, _ := s.CreateGarden(ctx, owner, GardenInput{Name: "Big", WidthCM: 2000, HeightCM: 2000})
+	bed := seedFillBed(t, s, owner, g.ID, 100, 100)
+	plant := seedOwnPlant(t, s, owner, 10)
+
+	nan := math.NaN()
+	for _, r := range []Region{
+		{MinX: nan, MinY: -50, MaxX: 50, MaxY: 50},
+		{MinX: -50, MinY: -50, MaxX: 50, MaxY: math.Inf(1)},
+	} {
+		created, err := s.FillRegion(ctx, owner, bed.ID, r, plant.ID, nil)
+		if !errors.Is(err, domain.ErrInvalidInput) {
+			t.Errorf("FillRegion(%+v) err = %v, want ErrInvalidInput", r, err)
+		}
+		for _, p := range created {
+			if !isFinite(p.XCM) || !isFinite(p.YCM) {
+				t.Errorf("persisted a plop with non-finite coordinates: %+v", p)
+			}
+		}
+	}
+}
+
+// TestFillRegionOutsideObjectPlantsNothing covers a region that misses the object
+// entirely. clampTo inverts such a region rather than emptying it, and an
+// inverted region must plant nothing — not one plop at some point off the bed.
+func TestFillRegionOutsideObjectPlantsNothing(t *testing.T) {
+	ctx := context.Background()
+	s := newTestService(t, openConfig())
+	owner := seedUser(t, s, "[email protected]")
+	g, _ := s.CreateGarden(ctx, owner, GardenInput{Name: "Big", WidthCM: 2000, HeightCM: 2000})
+	bed := seedFillBed(t, s, owner, g.ID, 100, 100) // local bounds ±50
+	plant := seedOwnPlant(t, s, owner, 10)
+
+	// Wholly east of the bed: clampTo gives MinX=500, MaxX=50.
+	created, err := s.FillRegion(ctx, owner, bed.ID, rect(500, -50, 600, 50), plant.ID, nil)
+	if err != nil {
+		t.Fatalf("FillRegion: %v", err)
+	}
+	if len(created) != 0 {
+		t.Errorf("filled %d plops for a region outside the bed, want 0: %+v", len(created), created)
+	}
+}
+
 // seedFillBed makes a plantable bed of the given size centered in a big garden.
 func seedFillBed(t *testing.T, s *Service, owner, gardenID int64, w, h float64) *domain.GardenObject {
 	t.Helper()
@@ -99,16 +260,24 @@ func TestFillRegionDeterministicPacking(t *testing.T) {
 	if err != nil {
 		t.Fatalf("FillRegion: %v", err)
 	}
-	// Hex lattice on [-30,30]² at pitch 30, rows ~26 apart → 4 plops (2 rows × 2).
+	// Hex lattice on [-30,30]² at pitch 30, rows ~26 apart, centered: a row of 2
-	if len(created) != 4 {
+	// (x=±15), then a staggered row of 1 (x=0) → 3 plops.
-		t.Fatalf("filled %d plops, want 4 (60×60 bed, radius 15)", len(created))
+	//
+	// This was 4 while the lattice was anchored at the min corner, and the fourth
+	// sat at x=30 — centred ON the east edge, so half of it lay outside the bed,
+	// well past the half-spacing (5cm here) the rule allows. Packing one fewer
+	// plop is the point of the fix, not a regression in it.
+	if len(created) != 3 {
+		t.Fatalf("filled %d plops, want 3 (60×60 bed, radius 15)", len(created))
 	}
 	for _, p := range created {
 		if p.RadiusCM != 15 || p.PlantedAt == nil || p.DerivedCount < 1 {
 			t.Errorf("unexpected created plop: %+v", p)
 		}
-		if p.XCM < -30 || p.XCM > 30 || p.YCM < -30 || p.YCM > 30 {
+		// This bed fits its lattice exactly, so nothing should need to overhang.
-			t.Errorf("plop center out of bed bounds: %+v", p)
+		if p.XCM-p.RadiusCM < -30 || p.XCM+p.RadiusCM > 30 ||
+			p.YCM-p.RadiusCM < -30 || p.YCM+p.RadiusCM > 30 {
+			t.Errorf("plop overhangs a bed it fits inside: %+v", p)
 		}
 	}
 

internal/service/plants.go

@@ -2,6 +2,7 @@ package service
 
 import (
 	"context"
+	"sort"
 	"strings"
 
 	"gitea.stevedudenhoeffer.com/steve/pansy/internal/domain"
@@ -69,6 +70,124 @@ func (s *Service) ListPlants(ctx context.Context, actorID int64) ([]domain.Plant
 	return s.store.ListPlantsForActor(ctx, actorID)
 }
 
+// PlantMatch is a candidate from FindPlants: the plant, plus what seed the actor
+// has left of it, so an agent can say "you only have enough for half that bed"
+// instead of confidently planting seed that doesn't exist.
+type PlantMatch struct {
+	domain.Plant
+	// SeedRemaining is the total left across the actor's lots of this plant, and
+	// SeedUnit the unit they're counted in. Both are omitted when there are no
+	// lots — and also when the lots disagree about the unit, because adding
+	// grams to packets produces a number that means nothing. SeedLots still
+	// reports how many there are, so "several lots, no single total" is
+	// distinguishable from "no seed at all".
+	SeedRemaining *float64 `json:"seedRemaining,omitempty"`
+	SeedUnit      string   `json:"seedUnit,omitempty"`
+	SeedLots      int      `json:"seedLots,omitempty"`
+}
+
+// maxPlantMatches caps FindPlants. A model given fifty candidates is not being
+// helped; if the query is that broad the answer is to ask a better one.
+const maxPlantMatches = 10
+
+// FindPlants returns the plants in the actor's visible catalog (built-ins plus
+// their own) whose name or category matches the query, best match first.
+//
+// It deliberately returns SEVERAL candidates rather than one guess. "garlic"
+// against a catalog holding both "Garlic" and "German Red Garlic" is genuinely
+// ambiguous, and a caller with the surrounding conversation is far better placed
+// to disambiguate than a fuzzy-match heuristic here. An empty query returns the
+// catalog head rather than nothing, so a caller can browse.
+func (s *Service) FindPlants(ctx context.Context, actorID int64, query string) ([]PlantMatch, error) {
+	plants, err := s.store.ListPlantsForActor(ctx, actorID)
+	if err != nil {
+		return nil, err
+	}
+	q := strings.ToLower(strings.TrimSpace(query))
+
+	type scored struct {
+		plant domain.Plant
+		rank  int
+	}
+	ranked := make([]scored, 0, len(plants))
+	for _, p := range plants {
+		name := strings.ToLower(p.Name)
+		switch {
+		case q == "":
+			ranked = append(ranked, scored{p, 3})
+		case name == q:
+			ranked = append(ranked, scored{p, 0})
+		case strings.HasPrefix(name, q):
+			ranked = append(ranked, scored{p, 1})
+		case strings.Contains(name, q):
+			ranked = append(ranked, scored{p, 2})
+		case strings.Contains(strings.ToLower(p.Category), q):
+			ranked = append(ranked, scored{p, 3})
+		}
+	}
+	// Stable by rank then name, so the same query always answers the same way —
+	// a tool whose results reshuffle between calls is one a model can't reason
+	// about across turns.
+	sort.SliceStable(ranked, func(i, j int) bool {
+		if ranked[i].rank != ranked[j].rank {
+			return ranked[i].rank < ranked[j].rank
+		}
+		return ranked[i].plant.Name < ranked[j].plant.Name
+	})
+	if len(ranked) > maxPlantMatches {
+		ranked = ranked[:maxPlantMatches]
+	}
+
+	matches := make([]PlantMatch, 0, len(ranked))
+	for _, r := range ranked {
+		matches = append(matches, PlantMatch{Plant: r.plant})
+	}
+	if err := s.attachSeedRemaining(ctx, actorID, matches); err != nil {
+		return nil, err
+	}
+	return matches, nil
+}
+
+// attachSeedRemaining fills SeedRemaining/SeedUnit from the actor's lots.
+func (s *Service) attachSeedRemaining(ctx context.Context, actorID int64, matches []PlantMatch) error {
+	if len(matches) == 0 {
+		return nil
+	}
+	lots, err := s.ListSeedLots(ctx, actorID, nil)
+	if err != nil {
+		return err
+	}
+	byPlant := map[int64][]domain.SeedLot{}
+	for _, l := range lots {
+		byPlant[l.PlantID] = append(byPlant[l.PlantID], l)
+	}
+	for i := range matches {
+		ls := byPlant[matches[i].ID]
+		if len(ls) == 0 {
+			continue
+		}
+		matches[i].SeedLots = len(ls)
+		unit := ls[0].Unit
+		mixed := false
+		total := 0.0
+		for _, l := range ls {
+			total += l.Remaining
+			if l.Unit != unit {
+				mixed = true
+			}
+		}
+		if mixed {
+			// Dropping only the LABEL would leave a number that reads as a
+			// quantity and isn't one. Drop the total with it; SeedLots still says
+			// there is seed here, just not one figure for it.
+			continue
+		}
+		matches[i].SeedRemaining = &total
+		matches[i].SeedUnit = unit
+	}
+	return nil
+}
+
 // CreatePlant adds a plant owned by the actor. To "clone" a built-in the client
 // simply POSTs a copy — there is no dedicated endpoint, and the copy is owned by
 // (and editable by) the actor.

internal/service/plants_test.go

@@ -237,3 +237,138 @@ func TestDeletePlantInUseIsBlocked(t *testing.T) {
 		t.Errorf("delete freed plant: %v", err)
 	}
 }
+
+// TestFindPlantsRanksAndDisambiguates — FindPlants deliberately returns several
+// candidates rather than one guess, because "garlic" against a catalog holding
+// both "Garlic" and "German Red Garlic" is genuinely ambiguous and a caller with
+// the surrounding context is better placed to choose than a heuristic here.
+func TestFindPlantsRanksAndDisambiguates(t *testing.T) {
+	s := newTestService(t, openConfig())
+	owner := seedUser(t, s, "[email protected]")
+	ctx := context.Background()
+
+	custom, err := s.CreatePlant(ctx, owner, PlantInput{
+		Name: "German Red Garlic", Category: domain.CategoryVegetable, SpacingCM: 15,
+		Color: "#8a5a8a", Icon: "🧄",
+	})
+	if err != nil {
+		t.Fatalf("CreatePlant: %v", err)
+	}
+
+	got, err := s.FindPlants(ctx, owner, "garlic")
+	if err != nil {
+		t.Fatalf("FindPlants: %v", err)
+	}
+	names := map[string]bool{}
+	for _, m := range got {
+		names[m.Name] = true
+	}
+	if !names["Garlic"] || !names[custom.Name] {
+		t.Errorf("got %v, want both the built-in and the custom variety", names)
+	}
+	// Exact match first, so a caller taking [0] gets the least surprising one.
+	if got[0].Name != "Garlic" {
+		t.Errorf("first match = %q, want the exact name", got[0].Name)
+	}
+
+	// Prefix beats substring: "german" should surface the custom one first.
+	pre, err := s.FindPlants(ctx, owner, "german")
+	if err != nil {
+		t.Fatalf("FindPlants: %v", err)
+	}
+	if len(pre) == 0 || pre[0].Name != custom.Name {
+		t.Errorf("FindPlants(german) = %+v, want the custom variety first", pre)
+	}
+
+	// Category search works, and a query matching nothing says so plainly.
+	if herbs, _ := s.FindPlants(ctx, owner, "herb"); len(herbs) == 0 {
+		t.Error("category search found nothing")
+	}
+	if none, _ := s.FindPlants(ctx, owner, "zzzzz"); len(none) != 0 {
+		t.Errorf("FindPlants(zzzzz) = %+v, want nothing", none)
+	}
+}
+
+// TestFindPlantsReportsSeedRemaining — so a caller can say "you only have enough
+// for half that bed" instead of confidently planting seed that doesn't exist.
+func TestFindPlantsReportsSeedRemaining(t *testing.T) {
+	s := newTestService(t, openConfig())
+	owner := seedUser(t, s, "[email protected]")
+	other := seedUser(t, s, "[email protected]")
+	ctx := context.Background()
+
+	plant := seedOwnPlant(t, s, owner, 15)
+	if _, err := s.CreateSeedLot(ctx, owner, SeedLotInput{
+		PlantID: plant.ID, Quantity: 100, Unit: domain.UnitSeeds,
+	}); err != nil {
+		t.Fatalf("CreateSeedLot: %v", err)
+	}
+
+	got, err := s.FindPlants(ctx, owner, plant.Name)
+	if err != nil {
+		t.Fatalf("FindPlants: %v", err)
+	}
+	if len(got) == 0 || got[0].SeedRemaining == nil || *got[0].SeedRemaining != 100 {
+		t.Fatalf("seedRemaining = %+v, want 100", got[0].SeedRemaining)
+	}
+	if got[0].SeedUnit != domain.UnitSeeds {
+		t.Errorf("seedUnit = %q", got[0].SeedUnit)
+	}
+
+	// A plant with no lots reports nothing rather than a misleading zero.
+	builtin, err := s.FindPlants(ctx, owner, "Garlic")
+	if err != nil {
+		t.Fatalf("FindPlants: %v", err)
+	}
+	if len(builtin) > 0 && builtin[0].SeedRemaining != nil {
+		t.Errorf("a plant with no lots reported %v remaining", *builtin[0].SeedRemaining)
+	}
+
+	// And lots are private: another user searching the same plant sees no seed.
+	// (They can't see the custom plant at all, so search a built-in instead.)
+	if _, err := s.CreateSeedLot(ctx, other, SeedLotInput{
+		PlantID: builtinPlantID(t, s, other), Quantity: 50, Unit: domain.UnitSeeds,
+	}); err != nil {
+		t.Fatalf("CreateSeedLot(other): %v", err)
+	}
+	mine, _ := s.FindPlants(ctx, owner, "Garlic")
+	for _, m := range mine {
+		if m.SeedRemaining != nil {
+			t.Errorf("saw another user's seed count on %q", m.Name)
+		}
+	}
+}
+
+// TestFindPlantsOmitsATotalItCannotHonestlyGive — lots in different units can't
+// be summed. Dropping only the unit LABEL would leave a number that reads as a
+// quantity and isn't one; the count of lots still says there is seed here.
+func TestFindPlantsOmitsATotalItCannotHonestlyGive(t *testing.T) {
+	s := newTestService(t, openConfig())
+	owner := seedUser(t, s, "[email protected]")
+	plant := seedOwnPlant(t, s, owner, 15)
+	ctx := context.Background()
+
+	for _, u := range []string{domain.UnitSeeds, domain.UnitGrams} {
+		if _, err := s.CreateSeedLot(ctx, owner, SeedLotInput{PlantID: plant.ID, Quantity: 50, Unit: u}); err != nil {
+			t.Fatalf("CreateSeedLot(%s): %v", u, err)
+		}
+	}
+
+	got, err := s.FindPlants(ctx, owner, plant.Name)
+	if err != nil {
+		t.Fatalf("FindPlants: %v", err)
+	}
+	if len(got) == 0 {
+		t.Fatal("plant not found")
+	}
+	if got[0].SeedRemaining != nil {
+		t.Errorf("reported %v across mismatched units; that number means nothing", *got[0].SeedRemaining)
+	}
+	if got[0].SeedUnit != "" {
+		t.Errorf("seedUnit = %q, want empty", got[0].SeedUnit)
+	}
+	// But "several lots, no single total" must stay distinguishable from "none".
+	if got[0].SeedLots != 2 {
+		t.Errorf("seedLots = %d, want 2", got[0].SeedLots)
+	}
+}

internal/service/revisions.go

@@ -6,6 +6,7 @@ import (
 	"errors"
 	"fmt"
 	"log/slog"
+	"sort"
 	"sync"
 
 	"gitea.stevedudenhoeffer.com/steve/pansy/internal/domain"
@@ -99,7 +100,8 @@ type ChangeSetOptions struct {
 	Source string
 	// Summary is the one-line description shown in the history list.
 	Summary string
-	// AgentRunID joins this change set back to the executus run that produced it.
+	// AgentRunID joins this change set back to the agent run that produced it,
+	// so a change in the history list can be correlated with the run's log lines.
 	AgentRunID *string
 }
 
@@ -148,11 +150,19 @@ func partialSummary(summary string) string {
 // commitScope writes a scope's buffered revisions as one change set. revertsID is
 // set only by RevertChangeSet. A scope with no revisions writes nothing — an
 // operation that changed nothing doesn't belong in history.
+//
+// The write is DETACHED FROM CANCELLATION, always, and that belongs here rather
+// than at each call site so no caller can be the one that forgets. By the time a
+// commit runs, the data changes it describes have already been written — so
+// cancelling it cannot undo anything. It can only lose the record of what
+// happened and leave real changes with no way to undo them, which is the one
+// thing the whole change-set design exists to prevent.
 func (s *Service) commitScope(ctx context.Context, sc *changeScope, revertsID *int64) (*domain.ChangeSet, error) {
 	revs := sc.taken()
 	if len(revs) == 0 {
 		return nil, nil
 	}
+	ctx = context.WithoutCancel(ctx)
 	return s.store.WriteChangeSet(ctx, &domain.ChangeSet{
 		GardenID:   sc.gardenID,
 		ActorID:    sc.actorID,
@@ -193,9 +203,13 @@ func (s *Service) record(ctx context.Context, gardenID, actorID int64, summary s
 		sc.append(revs)
 		return
 	}
-	if _, err := s.store.WriteChangeSet(ctx, &domain.ChangeSet{
+	// Auto-scope: one operation, its own change set. Written through the same
-		GardenID: gardenID, ActorID: actorID, Source: domain.SourceUI, Summary: summary,
+	// detached path as everything else — a REST client that hangs up right after
-	}, revs); err != nil {
+	// its PATCH landed must not leave that change without history, and this is
+	// the path virtually every mutation takes.
+	auto := &changeScope{gardenID: gardenID, actorID: actorID, source: domain.SourceUI, summary: summary}
+	auto.append(revs)
+	if _, err := s.commitScope(ctx, auto, nil); err != nil {
 		slog.Error("service: record change set", "error", err, "garden", gardenID, "summary", summary)
 	}
 }
@@ -307,6 +321,7 @@ func (s *Service) RevertChangeSet(ctx context.Context, actorID, changeSetID int6
 		if err != nil {
 			// Record what actually landed before surfacing the failure, so the
 			// partial revert is visible and undoable rather than orphaned.
+			// (commitScope detaches from cancellation itself.)
 			if _, cerr := s.commitScope(ctx, sc, &target.ID); cerr != nil {
 				slog.Error("service: partial revert could not be recorded", "error", cerr, "changeSet", changeSetID)
 			}
@@ -327,9 +342,48 @@ func (s *Service) RevertChangeSet(ctx context.Context, actorID, changeSetID int6
 	if err != nil {
 		return nil, nil, err
 	}
+	// Fill in the per-op counts. commitScope returns the freshly inserted row,
+	// which carries no tally — and a caller receiving a change set with an empty
+	// Counts cannot tell "nothing was reverted" from "the tally wasn't loaded".
+	// That ambiguity is not theoretical: it made the chat panel report a
+	// successful undo as "nothing left to undo".
+	if cs != nil {
+		cs.Counts = countRevisions(sc.taken())
+	}
 	return cs, conflicts, nil
 }
 
+// countRevisions tallies revisions by (entity type, op).
+//
+// This deliberately reproduces in Go what ListChangeSets does in SQL, because a
+// change set that has just been written has no rows to GROUP BY yet — the
+// alternative is a second round trip to count what we are already holding.
+// The parity is a real cross-layer contract, and TestRevertResultCarriesItsCounts
+// compares the two breakdowns row for row so it can't drift silently.
+func countRevisions(revs []domain.Revision) []domain.ChangeCount {
+	type key struct{ entityType, op string }
+	seen := map[key]int{}
+	order := []key{}
+	for _, r := range revs {
+		k := key{r.EntityType, r.Op}
+		if _, ok := seen[k]; !ok {
+			order = append(order, k)
+		}
+		seen[k]++
+	}
+	sort.Slice(order, func(i, j int) bool {
+		if order[i].entityType != order[j].entityType {
+			return order[i].entityType < order[j].entityType
+		}
+		return order[i].op < order[j].op
+	})
+	counts := make([]domain.ChangeCount, 0, len(order))
+	for _, k := range order {
+		counts = append(counts, domain.ChangeCount{EntityType: k.entityType, Op: k.op, N: seen[k]})
+	}
+	return counts
+}
+
 // entityKey identifies a row across the entity types a revision can name.
 type entityKey struct {
 	entityType string

internal/service/revisions_test.go

@@ -704,3 +704,192 @@ func TestClearObjectOnlyClearsWhatItSnapshotted(t *testing.T) {
 		t.Errorf("cleared %d of %d with %d revisions — all three should match", n, len(before), len(revs))
 	}
 }
+
+// TestRevertResultCarriesItsCounts — found by using the thing.
+//
+// commitScope returns the freshly inserted row, which carries no tally. A caller
+// receiving a change set with empty Counts cannot tell "nothing was reverted"
+// from "the tally wasn't loaded", and the chat panel read that ambiguity the
+// wrong way: a successful undo reported "nothing left to undo", which is the
+// worst possible thing to say about an action that just worked.
+//
+// It also pins the cross-layer contract that fix created. countRevisions tallies
+// in Go what ListChangeSets tallies in SQL, and nothing but this test stops the
+// two drifting — so it compares the FULL per-(entity, op) breakdown, not just
+// the totals, which would agree even if the groupings had diverged.
+func TestRevertResultCarriesItsCounts(t *testing.T) {
+	s := newTestService(t, openConfig())
+	owner := seedUser(t, s, "[email protected]")
+	g := seedGarden(t, s, owner)
+	bed := seedBed(t, s, owner, g.ID)
+	plant := seedOwnPlant(t, s, owner, 15)
+	ctx := context.Background()
+
+	if _, err := s.FillNamedRegion(ctx, owner, bed.ID, "all", plant.ID, nil); err != nil {
+		t.Fatalf("fill: %v", err)
+	}
+	// A second, different kind of change, so the breakdown has more than one row
+	// to get wrong.
+	if _, err := s.UpdateObject(ctx, owner, bed.ID, ObjectPatch{Name: strPtr("North Bed")}, bed.Version); err != nil {
+		t.Fatalf("rename: %v", err)
+	}
+	sets := history(t, s, owner, g.ID)
+	rename, fill := sets[0], sets[1]
+
+	undoRename, conflicts, err := s.RevertChangeSet(ctx, owner, rename.ID, domain.SourceUI)
+	if err != nil || len(conflicts) != 0 {
+		t.Fatalf("revert rename: err=%v conflicts=%+v", err, conflicts)
+	}
+	undoFill, conflicts, err := s.RevertChangeSet(ctx, owner, fill.ID, domain.SourceUI)
+	if err != nil || len(conflicts) != 0 {
+		t.Fatalf("revert fill: err=%v conflicts=%+v", err, conflicts)
+	}
+
+	for _, undo := range []*domain.ChangeSet{undoRename, undoFill} {
+		if undo == nil {
+			t.Fatal("a revert that did work returned no change set")
+		}
+		if len(undo.Counts) == 0 {
+			t.Fatalf("change set %d came back with no tally — an empty tally reads as 'nothing happened'", undo.ID)
+		}
+	}
+	// Undoing a fill deletes every plop it created, so the tallies must match.
+	if got, want := countsTotal(undoFill.Counts), countsTotal(fill.Counts); got != want {
+		t.Errorf("undo of the fill reports %d changes, want %d", got, want)
+	}
+
+	// The SQL tally and the Go tally must agree, row for row.
+	listed := history(t, s, owner, g.ID)
+	byID := map[int64][]domain.ChangeCount{}
+	for _, cs := range listed {
+		byID[cs.ID] = cs.Counts
+	}
+	for _, undo := range []*domain.ChangeSet{undoRename, undoFill} {
+		fromSQL, ok := byID[undo.ID]
+		if !ok {
+			t.Fatalf("revert %d is missing from the history list", undo.ID)
+		}
+		if !sameCounts(undo.Counts, fromSQL) {
+			t.Errorf("change set %d: revert returned %+v, the list read says %+v — countRevisions and the SQL grouping have drifted",
+				undo.ID, undo.Counts, fromSQL)
+		}
+	}
+}
+
+// sameCounts compares two tallies regardless of order.
+func sameCounts(a, b []domain.ChangeCount) bool {
+	if len(a) != len(b) {
+		return false
+	}
+	index := func(cs []domain.ChangeCount) map[string]int {
+		m := map[string]int{}
+		for _, c := range cs {
+			m[c.EntityType+"/"+c.Op] = c.N
+		}
+		return m
+	}
+	ia, ib := index(a), index(b)
+	for k, v := range ia {
+		if ib[k] != v {
+			return false
+		}
+	}
+	return true
+}
+
+// countsTotal sums a tally — the server-side twin of the client's totalChanges.
+func countsTotal(counts []domain.ChangeCount) int {
+	n := 0
+	for _, c := range counts {
+		n += c.N
+	}
+	return n
+}
+
+// TestSucceededTurnRecordsEvenIfTheCallerWentAway is the production bug.
+//
+// The failure path was detached from cancellation; the SUCCESS path was not. An
+// agent turn whose client disconnects can still COMPLETE — and then the success
+// path committed with a dead context, the write failed, and real changes were
+// left with no change set and no way to undo them. Found live with 18 plantings
+// behind no history at all.
+//
+// Nothing about a commit needs the caller to still be there: by the time it
+// runs, the data it describes has already been written.
+func TestSucceededTurnRecordsEvenIfTheCallerWentAway(t *testing.T) {
+	s := newTestService(t, openConfig())
+	owner := seedUser(t, s, "[email protected]")
+	g := seedGarden(t, s, owner)
+	bed := seedBed(t, s, owner, g.ID)
+	plant := seedOwnPlant(t, s, owner, 15)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	before := len(history(t, s, owner, g.ID))
+
+	// fn does its work and SUCCEEDS, but the caller goes away before it returns.
+	cs, err := s.WithChangeSet(ctx, owner, g.ID, ChangeSetOptions{
+		Source: domain.SourceAgent, Summary: "plant beans in the second bed",
+	}, func(ctx context.Context) error {
+		if _, err := s.FillNamedRegion(ctx, owner, bed.ID, "all", plant.ID, nil); err != nil {
+			return err
+		}
+		cancel() // the client disconnects, mid-turn, after the work landed
+		return nil
+	})
+	if err != nil {
+		t.Fatalf("WithChangeSet: %v", err)
+	}
+	if cs == nil {
+		t.Fatal("the turn changed things but produced no change set")
+	}
+
+	after := history(t, s, owner, g.ID)
+	if len(after) != before+1 {
+		t.Fatalf("recorded %d change sets, want 1", len(after)-before)
+	}
+	if after[0].Summary != "plant beans in the second bed" {
+		t.Errorf("summary = %q; a completed turn shouldn't be marked partial", after[0].Summary)
+	}
+	// And it's undoable, which is the entire point.
+	if _, conflicts, err := s.RevertChangeSet(context.Background(), owner, cs.ID, domain.SourceUI); err != nil || len(conflicts) != 0 {
+		t.Fatalf("the recorded turn should be undoable: err=%v conflicts=%+v", err, conflicts)
+	}
+	active, _ := s.store.ListActivePlantingsForObject(context.Background(), bed.ID)
+	if len(active) != 0 {
+		t.Errorf("%d plantings survived the undo", len(active))
+	}
+}
+
+// TestAutoScopedMutationRecordsEvenIfTheCallerWentAway — the same rule for the
+// path virtually every mutation takes.
+//
+// A plain REST PATCH auto-scopes into its own change set. If the client hangs up
+// between the row landing and the change set being written, that change is
+// orphaned exactly as an agent turn's was — and this path is used far more.
+func TestAutoScopedMutationRecordsEvenIfTheCallerWentAway(t *testing.T) {
+	s := newTestService(t, openConfig())
+	owner := seedUser(t, s, "[email protected]")
+	g := seedGarden(t, s, owner)
+	bed := seedBed(t, s, owner, g.ID)
+	before := len(history(t, s, owner, g.ID))
+
+	// The row write and the history write share this context; cancelling after
+	// the mutation returns is the client hanging up mid-request.
+	ctx, cancel := context.WithCancel(context.Background())
+	if _, err := s.UpdateObject(ctx, owner, bed.ID, ObjectPatch{XCM: f64Ptr(300)}, bed.Version); err != nil {
+		t.Fatalf("UpdateObject: %v", err)
+	}
+	cancel()
+
+	after := history(t, s, owner, g.ID)
+	if len(after) != before+1 {
+		t.Fatalf("recorded %d change sets, want 1 — the move is otherwise un-undoable", len(after)-before)
+	}
+	if _, conflicts, err := s.RevertChangeSet(context.Background(), owner, after[0].ID, domain.SourceUI); err != nil || len(conflicts) != 0 {
+		t.Fatalf("the recorded move should be undoable: err=%v conflicts=%+v", err, conflicts)
+	}
+	back, _ := s.store.GetObject(context.Background(), bed.ID)
+	if back.XCM != bed.XCM {
+		t.Errorf("undo left x at %v, want %v", back.XCM, bed.XCM)
+	}
+}

internal/store/agent.go

@@ -0,0 +1,95 @@
+package store
+
+import (
+	"context"
+	"fmt"
+
+	"gitea.stevedudenhoeffer.com/steve/pansy/internal/domain"
+)
+
+// agentMessageColumns lists agent_messages columns in scan order.
+const agentMessageColumns = `id, conversation_id, role, body, change_set_id, created_at`
+
+// EnsureConversation returns the (garden, user) conversation id, creating it on
+// first use. One thread per person per garden: two people editing a shared
+// garden hold separate dialogues, and merging them would put words in someone's
+// mouth.
+func (d *DB) EnsureConversation(ctx context.Context, gardenID, userID int64) (int64, error) {
+	var id int64
+	err := d.sql.QueryRowContext(ctx,
+		`SELECT id FROM agent_conversations WHERE garden_id = ? AND user_id = ?`,
+		gardenID, userID).Scan(&id)
+	if err == nil {
+		return id, nil
+	}
+	if err := d.sql.QueryRowContext(ctx,
+		`INSERT INTO agent_conversations (garden_id, user_id) VALUES (?, ?)
+		 ON CONFLICT (garden_id, user_id) DO UPDATE SET updated_at = updated_at
+		 RETURNING id`,
+		gardenID, userID).Scan(&id); err != nil {
+		return 0, fmt.Errorf("store: ensure conversation: %w", err)
+	}
+	return id, nil
+}
+
+// AppendAgentMessage records one side of an exchange.
+func (d *DB) AppendAgentMessage(ctx context.Context, m *domain.AgentMessage) (*domain.AgentMessage, error) {
+	var out domain.AgentMessage
+	if err := d.sql.QueryRowContext(ctx,
+		`INSERT INTO agent_messages (conversation_id, role, body, change_set_id)
+		 VALUES (?, ?, ?, ?)
+		 RETURNING `+agentMessageColumns,
+		m.ConversationID, m.Role, m.Body, m.ChangeSetID,
+	).Scan(&out.ID, &out.ConversationID, &out.Role, &out.Body, &out.ChangeSetID, &out.CreatedAt); err != nil {
+		return nil, fmt.Errorf("store: append agent message: %w", err)
+	}
+	// Touch the conversation so a "most recent thread" read is possible later.
+	if _, err := d.sql.ExecContext(ctx,
+		`UPDATE agent_conversations SET updated_at = strftime('%Y-%m-%dT%H:%M:%SZ', 'now') WHERE id = ?`,
+		m.ConversationID); err != nil {
+		return nil, fmt.Errorf("store: touch conversation: %w", err)
+	}
+	return &out, nil
+}
+
+// ListAgentMessages returns the last `limit` messages of a conversation in
+// chronological order.
+//
+// Reading the TAIL rather than the head is the point: an old opening exchange is
+// the least useful context for "now do the same to the north bed", and an
+// uncapped read would grow without bound over a season.
+func (d *DB) ListAgentMessages(ctx context.Context, conversationID int64, limit int) ([]domain.AgentMessage, error) {
+	rows, err := d.sql.QueryContext(ctx,
+		`SELECT `+agentMessageColumns+` FROM (
+		   SELECT `+agentMessageColumns+` FROM agent_messages
+		    WHERE conversation_id = ? ORDER BY id DESC LIMIT ?
+		 ) ORDER BY id`,
+		conversationID, limit)
+	if err != nil {
+		return nil, fmt.Errorf("store: list agent messages: %w", err)
+	}
+	defer rows.Close()
+
+	msgs := []domain.AgentMessage{}
+	for rows.Next() {
+		var m domain.AgentMessage
+		if err := rows.Scan(&m.ID, &m.ConversationID, &m.Role, &m.Body, &m.ChangeSetID, &m.CreatedAt); err != nil {
+			return nil, fmt.Errorf("store: scan agent message: %w", err)
+		}
+		msgs = append(msgs, m)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, fmt.Errorf("store: iterate agent messages: %w", err)
+	}
+	return msgs, nil
+}
+
+// DeleteConversation clears a thread (the messages cascade).
+func (d *DB) DeleteConversation(ctx context.Context, gardenID, userID int64) error {
+	if _, err := d.sql.ExecContext(ctx,
+		`DELETE FROM agent_conversations WHERE garden_id = ? AND user_id = ?`,
+		gardenID, userID); err != nil {
+		return fmt.Errorf("store: delete conversation: %w", err)
+	}
+	return nil
+}

internal/store/migrations/0009_agent_chat.sql

@@ -0,0 +1,36 @@
+-- Agent conversations (#56): multi-turn chat with the garden assistant.
+--
+-- "Now do the same to the north bed" needs the previous exchange, and history
+-- held only by the client would be lost on a refresh — which is exactly when
+-- someone reloads to see whether the agent's change actually landed.
+--
+-- One conversation per (user, garden). Two people editing a shared garden get
+-- separate threads: a conversation is a dialogue with one person, and merging
+-- them would put words in someone's mouth.
+CREATE TABLE agent_conversations (
+    id         INTEGER PRIMARY KEY,
+    garden_id  INTEGER NOT NULL REFERENCES gardens (id) ON DELETE CASCADE,
+    user_id    INTEGER NOT NULL REFERENCES users (id)   ON DELETE CASCADE,
+    created_at TEXT    NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%SZ', 'now')),
+    updated_at TEXT    NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%SZ', 'now')),
+    UNIQUE (garden_id, user_id)
+);
+
+-- Only the user/assistant TEXT of each turn is kept, not the full model
+-- transcript with its tool calls. Continuity needs what was said and what came
+-- back; replaying a stored tool call would be replaying a decision made against
+-- a garden that has since moved on. It also keeps the schema free of majordomo's
+-- message shape, which is a dependency's business, not the database's.
+CREATE TABLE agent_messages (
+    conversation_id INTEGER NOT NULL REFERENCES agent_conversations (id) ON DELETE CASCADE,
+    id              INTEGER PRIMARY KEY,
+    role            TEXT    NOT NULL CHECK (role IN ('user', 'assistant')),
+    body            TEXT    NOT NULL,
+    -- The change set this turn produced, so the panel can offer Undo on the
+    -- message that caused it. SET NULL rather than CASCADE: losing the history
+    -- entry must not delete what was said about it.
+    change_set_id   INTEGER REFERENCES change_sets (id) ON DELETE SET NULL,
+    created_at      TEXT    NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%SZ', 'now'))
+);
+
+CREATE INDEX idx_agent_messages_conversation ON agent_messages (conversation_id, id);

internal/store/revisions.go

@@ -119,7 +119,9 @@ func (d *DB) ListChangeSets(ctx context.Context, gardenID int64, limit, offset i
 		return sets, nil
 	}
 
-	// One grouped query for the whole page rather than N per-row counts.
+	// One grouped query for the whole page rather than N per-row counts. The
+	// service's countRevisions mirrors this grouping for change sets it has just
+	// written; TestRevertResultCarriesItsCounts holds the two in step.
 	countRows, err := d.sql.QueryContext(ctx,
 		`SELECT change_set_id, entity_type, op, COUNT(*)
 		   FROM revisions

web/src/components/plants/DeleteSeedLotModal.tsx

@@ -0,0 +1,50 @@
+import { useState } from 'react'
+import { Alert } from '@/components/ui/Alert'
+import { Button } from '@/components/ui/Button'
+import { Modal } from '@/components/ui/Modal'
+import { errorMessage } from '@/lib/api'
+import { formatQuantity, useDeleteSeedLot, type SeedLot } from '@/lib/seedLots'
+
+/**
+ * Retire a lot. Worth confirming because it's the one place cost and germination
+ * data lives — and worth saying plainly that the plantings survive it, since
+ * "will this wipe my garden" is the reasonable fear.
+ */
+export function DeleteSeedLotModal({ lot, onClose }: { lot: SeedLot; onClose: () => void }) {
+  const del = useDeleteSeedLot()
+  const [error, setError] = useState<string | null>(null)
+
+  return (
+    <Modal title="Retire this seed lot?" onClose={onClose} busy={del.isPending}>
+      <div className="flex flex-col gap-3">
+        <p className="text-sm text-fg">
+          {formatQuantity(lot.quantity)} {lot.unit}
+          {lot.vendor ? ` from ${lot.vendor}` : ''}
+          {lot.packedForYear != null ? `, packed for ${lot.packedForYear}` : ''}.
+        </p>
+        <p className="text-sm text-muted">
+          Anything planted from it stays exactly where it is — it just stops being attributed to this purchase.
+        </p>
+        {error && <Alert>{error}</Alert>}
+        <div className="mt-1 flex justify-end gap-2">
+          <Button type="button" variant="ghost" onClick={onClose} disabled={del.isPending}>
+            Cancel
+          </Button>
+          <Button
+            type="button"
+            variant="danger"
+            disabled={del.isPending}
+            onClick={() =>
+              del.mutate(lot.id, {
+                onSuccess: onClose,
+                onError: (err) => setError(errorMessage(err, 'Could not retire the lot.')),
+              })
+            }
+          >
+            {del.isPending ? 'Retiring…' : 'Retire lot'}
+          </Button>
+        </div>
+      </div>
+    </Modal>
+  )
+}

web/src/components/plants/PlantCard.tsx

@@ -1,6 +1,10 @@
+import { useState } from 'react'
 import { PlantIcon } from './PlantIcon'
+import { LotStateChip, SeedLotList } from './SeedLotList'
+import { SourceLink } from './SourceLink'
 import { cardActionClass, cardDangerClass } from '@/components/ui/cardActions'
 import { CATEGORY_LABELS, isBuiltin, type Plant } from '@/lib/plants'
+import { formatQuantity, summarizeLots, type SeedLot } from '@/lib/seedLots'
 import { formatSpacing, type UnitPref } from '@/lib/units'
 
 /**
@@ -11,17 +15,30 @@ import { formatSpacing, type UnitPref } from '@/lib/units'
 export function PlantCard({
   plant,
   unit,
+  lots,
   onEdit,
   onDelete,
   onDuplicate,
+  onAddLot,
+  onEditLot,
+  onDeleteLot,
 }: {
   plant: Plant
   unit: UnitPref
+  /** This plant's purchases. A lot may reference a built-in, so even a built-in
+   *  card can carry seed. */
+  lots: SeedLot[]
   onEdit: () => void
   onDelete: () => void
   onDuplicate: () => void
+  onAddLot: () => void
+  onEditLot: (lot: SeedLot) => void
+  onDeleteLot: (lot: SeedLot) => void
 }) {
   const builtin = isBuiltin(plant)
+  const [showLots, setShowLots] = useState(false)
+  const summary = summarizeLots(lots)
+
   return (
     <div className="flex flex-col rounded-xl border border-border bg-surface">
       <div className="flex items-start gap-3 p-4">
@@ -38,6 +55,12 @@ export function PlantCard({
           <p className="mt-0.5 text-sm text-muted">
             {CATEGORY_LABELS[plant.category]} · {formatSpacing(plant.spacingCm, unit)} spacing
           </p>
+          {(plant.vendor || plant.sourceUrl) && (
+            <p className="mt-0.5 flex flex-wrap items-center gap-1.5 text-xs text-muted">
+              {plant.vendor && <span>{plant.vendor}</span>}
+              <SourceLink url={plant.sourceUrl} />
+            </p>
+          )}
           {plant.notes && <p className="mt-1 line-clamp-2 text-xs text-muted">{plant.notes}</p>}
         </div>
         <span
@@ -46,7 +69,34 @@ export function PlantCard({
           title={plant.color}
         />
       </div>
-      <div className="flex justify-end gap-1 border-t border-border px-2 py-1.5">
+      {showLots && (
+        <div className="border-t border-border px-3 py-2">
+          <SeedLotList lots={lots} canEdit onAdd={onAddLot} onEdit={onEditLot} onDelete={onDeleteLot} />
+        </div>
+      )}
+
+      <div className="flex items-center justify-end gap-1 border-t border-border px-2 py-1.5">
+        {/* The seed count sits with the actions rather than in the body: it's
+            what you scan for down a list of twenty packets, so it wants a fixed
+            place on the card. */}
+        <button
+          type="button"
+          onClick={() => setShowLots((v) => !v)}
+          className={`${cardActionClass} mr-auto flex items-center gap-1.5`}
+          aria-expanded={showLots}
+        >
+          {lots.length === 0 ? (
+            <span className="text-muted">No seed</span>
+          ) : (
+            <>
+              <span className="tabular-nums">
+                {formatQuantity(summary.remaining)}
+                {summary.unit ? ` ${summary.unit}` : ''} left
+              </span>
+              <LotStateChip state={summary.state} />
+            </>
+          )}
+        </button>
         <button type="button" onClick={onDuplicate} className={cardActionClass}>
           Duplicate
         </button>

web/src/components/plants/PlantFormModal.tsx

@@ -16,6 +16,7 @@ import {
   type PlantCategory,
   type PlantInput,
 } from '@/lib/plants'
+import { safeExternalUrl } from '@/lib/seedLots'
 import { cmFromSpacing, spacingFromCm, spacingUnitLabel, type UnitPref } from '@/lib/units'
 
 const DEFAULT_COLOR = '#4a7c3f'
@@ -61,6 +62,8 @@ export function PlantFormModal({
   const [color, setColor] = useState(expandHex(source?.color ?? DEFAULT_COLOR))
   const [icon, setIcon] = useState(source?.icon ?? DEFAULT_ICON)
   const [days, setDays] = useState(source?.daysToMaturity != null ? String(source.daysToMaturity) : '')
+  const [sourceUrl, setSourceUrl] = useState(source?.sourceUrl ?? '')
+  const [vendor, setVendor] = useState(source?.vendor ?? '')
   const [notes, setNotes] = useState(source?.notes ?? '')
   const [version, setVersion] = useState(plant?.version ?? 0)
   const [conflict, setConflict] = useState<string | null>(null)
@@ -96,6 +99,14 @@ export function PlantFormModal({
       daysToMaturity = d
     }
 
+    // The server refuses anything that isn't http(s) with a host, but say so here
+    // rather than letting a paste of "johnnyseeds.com" come back as a generic
+    // error with no hint about which field or why.
+    if (sourceUrl.trim() && !safeExternalUrl(sourceUrl.trim())) {
+      setFormError('The source link needs to be a full http:// or https:// address.')
+      return
+    }
+
     const input: PlantInput = {
       name: name.trim(),
       category,
@@ -103,6 +114,8 @@ export function PlantFormModal({
       color,
       icon: icon.trim(),
       daysToMaturity,
+      sourceUrl: sourceUrl.trim(),
+      vendor: vendor.trim(),
       notes: notes.trim(),
     }
 
@@ -194,6 +207,27 @@ export function PlantFormModal({
           onChange={(e) => setDays(e.target.value)}
         />
 
+        {/* Provenance for the variety itself. What you bought and what's left
+            of it is a seed lot, added from the plant card. */}
+        <div className="grid grid-cols-2 gap-3">
+          <TextField
+            label="Vendor"
+            name="vendor"
+            placeholder="Johnny's Selected Seeds"
+            value={vendor}
+            onChange={(e) => setVendor(e.target.value)}
+          />
+          <TextField
+            label="Source link"
+            name="sourceUrl"
+            type="url"
+            inputMode="url"
+            placeholder="https://…"
+            value={sourceUrl}
+            onChange={(e) => setSourceUrl(e.target.value)}
+          />
+        </div>
+
         <TextArea label="Notes" name="notes" rows={2} value={notes} onChange={(e) => setNotes(e.target.value)} />
 
         {formError && <Alert>{formError}</Alert>}

web/src/components/plants/SeedLotList.tsx

@@ -0,0 +1,161 @@
+import { Button } from '@/components/ui/Button'
+import { cn } from '@/lib/cn'
+import { SourceLink } from './SourceLink'
+import {
+  formatCost,
+  formatQuantity,
+  formatUnitCost,
+  lotState,
+  type LotState,
+  type SeedLot,
+} from '@/lib/seedLots'
+
+const STATE_LABEL: Record<LotState, string> = {
+  over: 'over-planted',
+  empty: 'empty',
+  low: 'low',
+  ok: 'in stock',
+  unknown: 'no count',
+}
+
+// Encoded in colour AND words, because this is the thing you skim down a list of
+// twenty packets deciding what to order — a bare number doesn't survive that.
+const STATE_CLASS: Record<LotState, string> = {
+  // "over" is a discrepancy to look at rather than a shortage to act on, so it
+  // reads as a distinct warning rather than sharing "low"'s styling.
+  over: 'bg-orange-500/25 text-orange-900 dark:text-orange-200',
+  empty: 'bg-red-500/15 text-red-800 dark:text-red-300',
+  low: 'bg-amber-500/20 text-amber-800 dark:text-amber-300',
+  ok: 'bg-accent/20 text-accent-strong',
+  unknown: 'bg-border/60 text-muted',
+}
+
+export function LotStateChip({ state, className }: { state: LotState; className?: string }) {
+  return (
+    <span
+      className={cn(
+        'shrink-0 rounded px-1.5 py-0.5 text-[10px] font-medium uppercase tracking-wide',
+        STATE_CLASS[state],
+        className,
+      )}
+    >
+      {STATE_LABEL[state]}
+    </span>
+  )
+}
+
+/** A proportional bar for how much of a lot is left, so the state reads before
+ *  any of the text does. Omitted when there's no quantity to be a fraction of. */
+function RemainingBar({ lot }: { lot: SeedLot }) {
+  if (lot.quantity <= 0) return null
+  const pct = Math.max(0, Math.min(100, (lot.remaining / lot.quantity) * 100))
+  const state = lotState(lot)
+  return (
+    <div className="mt-1 h-1 w-full overflow-hidden rounded-full bg-border/60">
+      <div
+        className={cn(
+          'h-full rounded-full',
+          state === 'ok' ? 'bg-accent' : state === 'low' ? 'bg-amber-500' : 'bg-red-500',
+        )}
+        style={{ width: `${pct}%` }}
+      />
+    </div>
+  )
+}
+
+/**
+ * A plant's purchases: what came from where, and what's left of each.
+ *
+ * Two lots of the same variety are two separate rows with independent counts,
+ * which is the whole reason inventory lives on the purchase rather than on the
+ * plant (#50).
+ */
+export function SeedLotList({
+  lots,
+  canEdit,
+  onAdd,
+  onEdit,
+  onDelete,
+}: {
+  lots: SeedLot[]
+  canEdit: boolean
+  onAdd: () => void
+  onEdit: (lot: SeedLot) => void
+  onDelete: (lot: SeedLot) => void
+}) {
+  return (
+    <div className="flex flex-col gap-2">
+      {lots.length === 0 && (
+        <p className="text-xs text-muted">
+          No seed recorded. Add a lot to track what you bought and how much is left.
+        </p>
+      )}
+      {lots.map((lot) => (
+        <LotRow key={lot.id} lot={lot} canEdit={canEdit} onEdit={() => onEdit(lot)} onDelete={() => onDelete(lot)} />
+      ))}
+      {canEdit && (
+        <Button variant="ghost" className="self-start px-2 py-1 text-xs" onClick={onAdd}>
+          + Add seed lot
+        </Button>
+      )}
+    </div>
+  )
+}
+
+function LotRow({
+  lot,
+  canEdit,
+  onEdit,
+  onDelete,
+}: {
+  lot: SeedLot
+  canEdit: boolean
+  onEdit: () => void
+  onDelete: () => void
+}) {
+  const cost = formatCost(lot.costCents)
+  const unitCost = formatUnitCost(lot)
+
+  return (
+    <div className="rounded-lg border border-border px-2 py-1.5">
+      <div className="flex items-start gap-2">
+        <div className="min-w-0 flex-1">
+          <p className="flex flex-wrap items-center gap-1.5 text-sm text-fg">
+            <span className="font-medium tabular-nums">
+              {formatQuantity(lot.remaining)} / {formatQuantity(lot.quantity)} {lot.unit}
+            </span>
+            <LotStateChip state={lotState(lot)} />
+          </p>
+          <p className="mt-0.5 flex flex-wrap items-center gap-x-1.5 gap-y-0.5 text-xs text-muted">
+            {lot.vendor && <span>{lot.vendor}</span>}
+            {lot.packedForYear != null && <span>packed for {lot.packedForYear}</span>}
+            {lot.purchasedAt && <span>bought {lot.purchasedAt}</span>}
+            {lot.germinationPct != null && <span>{lot.germinationPct}% germ.</span>}
+            {cost && <span>{unitCost ? `${cost} (${unitCost})` : cost}</span>}
+            <SourceLink url={lot.sourceUrl} />
+          </p>
+          <RemainingBar lot={lot} />
+        </div>
+        {canEdit && (
+          <div className="flex shrink-0 flex-col items-end">
+            <button
+              type="button"
+              onClick={onEdit}
+              className="rounded px-1.5 py-0.5 text-xs text-muted outline-none hover:text-fg focus-visible:ring-2 focus-visible:ring-accent/40"
+            >
+              Edit
+            </button>
+            <button
+              type="button"
+              onClick={onDelete}
+              className="rounded px-1.5 py-0.5 text-xs text-red-700 outline-none hover:underline focus-visible:ring-2 focus-visible:ring-accent/40 dark:text-red-400"
+            >
+              Retire
+            </button>
+          </div>
+        )}
+      </div>
+      {lot.notes && <p className="mt-1 text-xs text-muted">{lot.notes}</p>}
+    </div>
+  )
+}

web/src/components/plants/SeedLotModal.tsx

@@ -0,0 +1,248 @@
+import { useState, type FormEvent } from 'react'
+import { Alert } from '@/components/ui/Alert'
+import { Button } from '@/components/ui/Button'
+import { Modal } from '@/components/ui/Modal'
+import { Select } from '@/components/ui/Select'
+import { TextArea } from '@/components/ui/TextArea'
+import { TextField } from '@/components/ui/TextField'
+import { errorMessage } from '@/lib/api'
+import {
+  conflictSeedLot,
+  LOT_UNITS,
+  safeExternalUrl,
+  useCreateSeedLot,
+  useUpdateSeedLot,
+  type LotUnit,
+  type SeedLot,
+} from '@/lib/seedLots'
+import type { Plant } from '@/lib/plants'
+
+/**
+ * Record a purchase, or correct one. Everything except quantity and unit is
+ * optional — the point is to make writing it down cheap enough to bother with,
+ * and a form that demands a SKU and a lot code gets skipped.
+ */
+export function SeedLotModal({
+  plant,
+  lot,
+  onClose,
+}: {
+  plant: Plant
+  /** Editing an existing lot, or undefined to record a new one. */
+  lot?: SeedLot
+  onClose: () => void
+}) {
+  const isEdit = !!lot
+  const create = useCreateSeedLot()
+  const update = useUpdateSeedLot()
+  const pending = create.isPending || update.isPending
+
+  // A new lot inherits the plant's vendor and source link, since the usual case
+  // is buying the variety you already recorded from the place you recorded it.
+  const [vendor, setVendor] = useState(lot?.vendor ?? plant.vendor ?? '')
+  const [sourceUrl, setSourceUrl] = useState(lot?.sourceUrl ?? plant.sourceUrl ?? '')
+  const [quantity, setQuantity] = useState(lot ? String(lot.quantity) : '')
+  const [unit, setUnit] = useState<LotUnit>(lot?.unit ?? 'seeds')
+  const [purchasedAt, setPurchasedAt] = useState(lot?.purchasedAt ?? '')
+  const [packedForYear, setPackedForYear] = useState(lot?.packedForYear != null ? String(lot.packedForYear) : '')
+  const [cost, setCost] = useState(lot?.costCents != null ? (lot.costCents / 100).toFixed(2) : '')
+  const [germination, setGermination] = useState(lot?.germinationPct != null ? String(lot.germinationPct) : '')
+  const [sku, setSku] = useState(lot?.sku ?? '')
+  const [lotCode, setLotCode] = useState(lot?.lotCode ?? '')
+  const [notes, setNotes] = useState(lot?.notes ?? '')
+  const [version, setVersion] = useState(lot?.version ?? 0)
+  const [conflict, setConflict] = useState<string | null>(null)
+  const [error, setError] = useState<string | null>(null)
+
+  async function onSubmit(e: FormEvent) {
+    e.preventDefault()
+    setError(null)
+    setConflict(null)
+
+    const qty = quantity.trim() === '' ? 0 : Number(quantity)
+    if (!Number.isFinite(qty) || qty < 0) {
+      setError('Quantity must be a number, or left blank.')
+      return
+    }
+    if (sourceUrl.trim() && !safeExternalUrl(sourceUrl.trim())) {
+      setError('The source link needs to be a full http:// or https:// address.')
+      return
+    }
+    let year: number | null = null
+    if (packedForYear.trim()) {
+      const y = Number(packedForYear)
+      if (!Number.isInteger(y) || y < 1900 || y > 2200) {
+        setError('Packed-for year should be a four-digit year.')
+        return
+      }
+      year = y
+    }
+    let costCents: number | null = null
+    if (cost.trim()) {
+      const c = Number(cost)
+      if (!Number.isFinite(c) || c < 0) {
+        setError('Cost must be an amount, or left blank.')
+        return
+      }
+      costCents = Math.round(c * 100)
+    }
+    let germinationPct: number | null = null
+    if (germination.trim()) {
+      const g = Number(germination)
+      if (!Number.isFinite(g) || g < 0 || g > 100) {
+        setError('Germination is a percentage between 0 and 100.')
+        return
+      }
+      germinationPct = g
+    }
+
+    const input = {
+      plantId: plant.id,
+      vendor: vendor.trim(),
+      sourceUrl: sourceUrl.trim(),
+      sku: sku.trim(),
+      lotCode: lotCode.trim(),
+      purchasedAt: purchasedAt.trim() === '' ? null : purchasedAt.trim(),
+      packedForYear: year,
+      quantity: qty,
+      unit,
+      costCents,
+      germinationPct,
+      notes: notes.trim(),
+    }
+
+    try {
+      if (isEdit) {
+        await update.mutateAsync({ id: lot.id, version, ...input })
+      } else {
+        await create.mutateAsync(input)
+      }
+      onClose()
+    } catch (err) {
+      const current = conflictSeedLot(err)
+      if (current) {
+        // Someone edited this lot elsewhere. Rebase onto the fresh row so a
+        // re-save applies, rather than making them retype everything — the same
+        // contract every other version-guarded form here honours.
+        setVersion(current.version)
+        setVendor(current.vendor)
+        setSourceUrl(current.sourceUrl)
+        setQuantity(String(current.quantity))
+        setUnit(current.unit)
+        setPurchasedAt(current.purchasedAt ?? '')
+        setPackedForYear(current.packedForYear != null ? String(current.packedForYear) : '')
+        setCost(current.costCents != null ? (current.costCents / 100).toFixed(2) : '')
+        setGermination(current.germinationPct != null ? String(current.germinationPct) : '')
+        setSku(current.sku)
+        setLotCode(current.lotCode)
+        setNotes(current.notes)
+        setConflict('This lot changed elsewhere. The latest values are shown — review and save again.')
+        return
+      }
+      setError(errorMessage(err, isEdit ? 'Could not save the lot.' : 'Could not record the lot.'))
+    }
+  }
+
+  return (
+    <Modal title={isEdit ? 'Edit seed lot' : `Seed lot — ${plant.name}`} onClose={onClose} busy={pending}>
+      <form onSubmit={onSubmit} className="flex flex-col gap-3">
+        {conflict && <Alert tone="info">{conflict}</Alert>}
+
+        <div className="grid grid-cols-2 gap-3">
+          <TextField
+            label="Quantity"
+            name="quantity"
+            type="number"
+            inputMode="decimal"
+            step="any"
+            min="0"
+            value={quantity}
+            onChange={(e) => setQuantity(e.target.value)}
+          />
+          <Select
+            label="Unit"
+            name="unit"
+            value={unit}
+            onChange={(e) => setUnit(e.target.value as LotUnit)}
+            options={LOT_UNITS.map((u) => ({ value: u.value, label: u.label }))}
+          />
+        </div>
+
+        <div className="grid grid-cols-2 gap-3">
+          <TextField label="Vendor" name="vendor" value={vendor} onChange={(e) => setVendor(e.target.value)} />
+          <TextField
+            label="Source link"
+            name="sourceUrl"
+            type="url"
+            inputMode="url"
+            placeholder="https://…"
+            value={sourceUrl}
+            onChange={(e) => setSourceUrl(e.target.value)}
+          />
+        </div>
+
+        <div className="grid grid-cols-2 gap-3">
+          <TextField
+            label="Purchased"
+            name="purchasedAt"
+            type="date"
+            value={purchasedAt}
+            onChange={(e) => setPurchasedAt(e.target.value)}
+          />
+          <TextField
+            label="Packed for"
+            name="packedForYear"
+            type="number"
+            inputMode="numeric"
+            placeholder="2026"
+            value={packedForYear}
+            onChange={(e) => setPackedForYear(e.target.value)}
+          />
+        </div>
+
+        <div className="grid grid-cols-2 gap-3">
+          <TextField
+            label="Cost"
+            name="cost"
+            type="number"
+            inputMode="decimal"
+            step="0.01"
+            min="0"
+            placeholder="4.99"
+            value={cost}
+            onChange={(e) => setCost(e.target.value)}
+          />
+          <TextField
+            label="Germination %"
+            name="germination"
+            type="number"
+            inputMode="decimal"
+            step="any"
+            min="0"
+            max="100"
+            value={germination}
+            onChange={(e) => setGermination(e.target.value)}
+          />
+        </div>
+
+        <div className="grid grid-cols-2 gap-3">
+          <TextField label="SKU" name="sku" value={sku} onChange={(e) => setSku(e.target.value)} />
+          <TextField label="Lot code" name="lotCode" value={lotCode} onChange={(e) => setLotCode(e.target.value)} />
+        </div>
+
+        <TextArea label="Notes" name="lotNotes" rows={2} value={notes} onChange={(e) => setNotes(e.target.value)} />
+
+        {error && <Alert>{error}</Alert>}
+
+        <div className="mt-1 flex justify-end gap-2">
+          <Button type="button" variant="ghost" onClick={onClose} disabled={pending}>
+            Cancel
+          </Button>
+          <Button type="submit" disabled={pending}>
+            {pending ? 'Saving…' : isEdit ? 'Save' : 'Record lot'}
+          </Button>
+        </div>
+      </form>
+    </Modal>
+  )
+}

web/src/components/plants/SourceLink.tsx

@@ -0,0 +1,27 @@
+import { safeExternalUrl } from '@/lib/seedLots'
+
+/**
+ * A link out to where seed came from.
+ *
+ * The href is a URL somebody pasted, so it is re-checked here before rendering
+ * and carries rel="noopener noreferrer" — the server scheme-checks it too (#50),
+ * but a link is rendered from whatever the client was handed, and "the backend
+ * validated it" is not a reason to hand javascript: to an anchor tag.
+ *
+ * Renders nothing at all when the URL is absent or unsafe, so callers don't each
+ * have to remember to guard.
+ */
+export function SourceLink({ url, label = 'source' }: { url: string; label?: string }) {
+  const safe = safeExternalUrl(url)
+  if (!safe) return null
+  return (
+    <a
+      href={safe}
+      target="_blank"
+      rel="noopener noreferrer"
+      className="underline decoration-dotted underline-offset-2 hover:text-fg"
+    >
+      {label} ↗
+    </a>
+  )
+}

web/src/editor/ChatPanel.tsx

@@ -0,0 +1,239 @@
+import { useEffect, useRef, useState, type ReactNode } from 'react'
+import { Alert } from '@/components/ui/Alert'
+import { errorMessage } from '@/lib/api'
+import { Button } from '@/components/ui/Button'
+import { TextArea } from '@/components/ui/TextArea'
+import { cn } from '@/lib/cn'
+import {
+  describeStep,
+  streamChat,
+  useAgentHistory,
+  useAgentRefresh,
+  useClearAgentHistory,
+  type AgentStep,
+  type AgentTurn,
+} from '@/lib/agent'
+import { useUndo } from '@/lib/history'
+import { UndoButton } from './UndoButton'
+
+/**
+ * Talk to the garden assistant, in the editor beside the canvas.
+ *
+ * Here rather than on its own page because watching the garden change as the
+ * agent works IS the confirmation — which is what makes acting without asking
+ * first tolerable. It also means the agent never has to guess which garden you
+ * mean.
+ */
+export function ChatPanel({ gardenId, canEdit }: { gardenId: number; canEdit: boolean }) {
+  const history = useAgentHistory(gardenId, true)
+  const clear = useClearAgentHistory(gardenId)
+  const refresh = useAgentRefresh(gardenId)
+  const undo = useUndo(gardenId)
+
+  const [input, setInput] = useState('')
+  // The turn in flight: what we sent, the steps so far, and how it ended.
+  const [pending, setPending] = useState<{ message: string; steps: AgentStep[] } | null>(null)
+  const [error, setError] = useState<string | null>(null)
+  const [warning, setWarning] = useState<string | null>(null)
+  const abort = useRef<AbortController | null>(null)
+  const bottom = useRef<HTMLDivElement>(null)
+
+  // Deliberately NOT aborted on unmount. Selecting an object auto-switches the
+  // rail to the inspector, so aborting here would mean clicking the canvas
+  // mid-turn silently killed the turn — and the canvas is exactly what you're
+  // meant to be watching. The request continues, the exchange is persisted
+  // server-side, and coming back to this tab shows it. Only Stop aborts, and
+  // even that only stops us READING: the turn keeps running server-side, which
+  // is why its work still lands in History either way.
+
+  // Follow the conversation as it grows, including mid-turn as steps arrive.
+  useEffect(() => {
+    bottom.current?.scrollIntoView({ behavior: 'smooth', block: 'end' })
+  }, [history.data, pending])
+
+  const send = () => {
+    const message = input.trim()
+    if (!message || pending) return
+    setInput('')
+    setError(null)
+    setWarning(null)
+    setPending({ message, steps: [] })
+
+    const controller = new AbortController()
+    abort.current = controller
+
+    void streamChat(
+      gardenId,
+      message,
+      {
+        onStep: (step) => {
+          setPending((p) => (p ? { ...p, steps: [...p.steps, step] } : p))
+          // The canvas updating under the conversation is the whole point of
+          // putting the chat here, so refresh it as each step lands — but only
+          // it: nothing else can have changed until the turn commits.
+          refresh.canvas()
+        },
+        onDone: (turn: AgentTurn) => {
+          setPending(null)
+          refresh.everything()
+          if (turn.truncated) {
+            setError('That turned into more steps than I should take at once — check what changed before continuing.')
+          }
+        },
+        onWarning: setWarning,
+        onError: (message) => {
+          setPending(null)
+          setError(message)
+          // Something may still have landed before it failed.
+          refresh.everything()
+        },
+      },
+      controller.signal,
+    )
+  }
+
+  const messages = history.data ?? []
+
+  return (
+    <div className="flex h-full flex-col gap-3">
+      <div className="flex items-center justify-between gap-2">
+        <h2 className="text-sm font-semibold text-fg">Assistant</h2>
+        {messages.length > 0 && (
+          <button
+            type="button"
+            onClick={() =>
+              clear.mutate(undefined, {
+                onError: (err) => setError(errorMessage(err, "Couldn't clear the conversation.")),
+              })
+            }
+            disabled={clear.isPending}
+            className="rounded px-1.5 py-0.5 text-xs text-muted outline-none hover:text-fg focus-visible:ring-2 focus-visible:ring-accent/40"
+          >
+            Start over
+          </button>
+        )}
+      </div>
+
+      {!canEdit && (
+        <p className="rounded-md bg-border/40 px-2 py-1 text-xs text-muted">
+          You can only view this garden, so the assistant can't change anything in it.
+        </p>
+      )}
+
+      <div className="flex min-h-0 flex-1 flex-col gap-2 overflow-y-auto">
+        {history.isPending && <p className="text-sm text-muted">Loading the conversation…</p>}
+        {/* A failed load rendering as an empty thread would look like the
+            conversation had been lost, which is a much worse thing to believe. */}
+        {history.isError && (
+          <Alert>{errorMessage(history.error, "Couldn't load the conversation.")}</Alert>
+        )}
+
+        {history.isSuccess && messages.length === 0 && !pending && (
+          <p className="text-sm text-muted">
+            Ask for what you want and it'll do it — “change the garlic bed to cucumbers this year”, “fill the
+            north half of the west bed with beans”, “what's in here?”. Everything it does lands as one change you
+            can undo.
+          </p>
+        )}
+
+        {messages.map((m) => (
+          <Bubble key={m.id} role={m.role} body={m.body}>
+            {/* Undo on the turn itself, so the common case never involves
+                opening the History panel. Same hook #49 uses, not a second
+                implementation. */}
+            {m.role === 'assistant' && m.changeSetId != null && canEdit && (
+              <UndoButton changeSet={{ id: m.changeSetId }} undo={undo} className="mt-1 items-start" />
+            )}
+          </Bubble>
+        ))}
+
+        {pending && (
+          <>
+            <Bubble role="user" body={pending.message} />
+            <div className="rounded-lg border border-border px-2.5 py-2 text-sm">
+              <ol className="flex flex-col gap-0.5">
+                {pending.steps.map((s) => (
+                  <li key={s.index} className="text-xs text-muted">
+                    {describeStep(s)}…
+                  </li>
+                ))}
+              </ol>
+              <p className="mt-1 flex items-center gap-1.5 text-xs text-muted">
+                <span className="inline-block h-1.5 w-1.5 animate-pulse rounded-full bg-accent" />
+                {pending.steps.length === 0 ? 'Thinking…' : 'Working…'}
+              </p>
+            </div>
+          </>
+        )}
+
+        {warning && <Alert tone="info">{warning}</Alert>}
+        {error && <Alert>{error}</Alert>}
+        <div ref={bottom} />
+      </div>
+
+      <div className="flex flex-col gap-2 border-t border-border pt-2">
+        <TextArea
+          label="Message"
+          name="agentMessage"
+          rows={2}
+          placeholder="Change the garlic bed to cucumbers this year"
+          value={input}
+          disabled={!!pending}
+          onChange={(e) => setInput(e.target.value)}
+          onKeyDown={(e) => {
+            // Enter sends, Shift+Enter breaks the line — the convention every
+            // chat box uses, and typing a newline by accident mid-thought is a
+            // worse failure than the reverse.
+            if (e.key === 'Enter' && !e.shiftKey) {
+              e.preventDefault()
+              send()
+            }
+          }}
+        />
+        <div className="flex justify-end gap-2">
+          {pending && (
+            <Button
+              variant="ghost"
+              className="px-2 py-1 text-xs"
+              onClick={() => {
+                abort.current?.abort()
+                setPending(null)
+                refresh.everything()
+              }}
+            >
+              Stop
+            </Button>
+          )}
+          <Button className="px-3 py-1.5 text-sm" disabled={!!pending || input.trim() === ''} onClick={send}>
+            {pending ? 'Working…' : 'Send'}
+          </Button>
+        </div>
+      </div>
+    </div>
+  )
+}
+
+function Bubble({
+  role,
+  body,
+  children,
+}: {
+  role: 'user' | 'assistant'
+  body: string
+  children?: ReactNode
+}) {
+  const mine = role === 'user'
+  return (
+    <div className={cn('flex flex-col', mine ? 'items-end' : 'items-start')}>
+      <div
+        className={cn(
+          'max-w-[90%] whitespace-pre-wrap rounded-lg px-2.5 py-2 text-sm',
+          mine ? 'bg-accent/15 text-fg' : 'border border-border text-fg',
+        )}
+      >
+        {body}
+      </div>
+      {children}
+    </div>
+  )
+}

web/src/editor/GardenCanvas.tsx

@@ -96,6 +96,7 @@ export function GardenCanvas({
   const focusedObjectId = useEditorStore((s) => s.focusedObjectId)
   const setFocusedObject = useEditorStore((s) => s.setFocusedObject)
   const armedPlant = useEditorStore((s) => s.armedPlant)
+  const armedLotId = useEditorStore((s) => s.armedLotId)
   const liveObject = useEditorStore((s) => s.liveObject)
   const livePlanting = useEditorStore((s) => s.livePlanting)
   const { fitToRect } = useViewport(svgRef)
@@ -200,7 +201,14 @@ export function GardenCanvas({
     const radiusCm = Math.max(1.5 * armedPlant.spacingCm, 15)
     // Stay armed for repeat-placement; don't select (the placement sheet covers
     // the object, so a selection would be hidden until placement ends anyway).
-    createPlanting.mutate({ objectId: focusedObject.id, plantId: armedPlant.id, xCm: x, yCm: y, radiusCm })
+    createPlanting.mutate({
+      objectId: focusedObject.id,
+      plantId: armedPlant.id,
+      xCm: x,
+      yCm: y,
+      radiusCm,
+      seedLotId: armedLotId ?? undefined,
+    })
   }
 
   const halfFW = focusedObject ? focusedObject.widthCm / 2 : 0

web/src/editor/HistoryPanel.tsx

@@ -116,7 +116,7 @@ function HistoryEntry({
           <UndoButton
             changeSet={changeSet}
             undo={undo}
-            className="w-32 shrink-0"
+            className="w-32 shrink-0 text-right"
             label={reverted ? 'Undo again' : 'Undo'}
           />
         )}

web/src/editor/PlantPicker.tsx

@@ -4,6 +4,16 @@ import { fieldControlClass } from '@/components/ui/field'
 import { CategoryChips } from '@/components/plants/CategoryChips'
 import { PlantIcon } from '@/components/plants/PlantIcon'
 import { CATEGORY_LABELS, filterPlants, usePlants, type CategoryFilter, type Plant } from '@/lib/plants'
+import {
+  attributableLots,
+  formatQuantity,
+  lotsByPlant,
+  lotState,
+  summarizeLots,
+  useSeedLots,
+  type SeedLot,
+} from '@/lib/seedLots'
+import { LotStateChip } from '@/components/plants/SeedLotList'
 import { formatSpacing, type UnitPref } from '@/lib/units'
 
 const RECENT_KEY = 'pansy:recent-plants'
@@ -41,11 +51,20 @@ export function PlantPicker({
   onClose,
   unit = 'metric',
 }: {
-  onSelect: (plant: Plant) => void
+  // The chosen plant, and the lot it should be attributed to when that isn't
+  // ambiguous. Undefined lot means "don't attribute" — which is the honest
+  // answer when there are no lots, and the deliberate one when the user skips.
+  onSelect: (plant: Plant, lot?: SeedLot) => void
   onClose: () => void
   unit?: UnitPref
 }) {
   const plants = usePlants()
+  const seedLots = useSeedLots()
+  const lotsFor = useMemo(() => lotsByPlant(seedLots.data), [seedLots.data])
+  // Set when a plant with SEVERAL lots is picked: which packet did this come out
+  // of? One lot auto-attributes and zero lots stays silent, because forcing that
+  // question on every placement is how a nicety becomes an obstacle.
+  const [choosingLotFor, setChoosingLotFor] = useState<Plant | null>(null)
   const [query, setQuery] = useState('')
   const [category, setCategory] = useState<CategoryFilter>('all')
   const [recent, setRecent] = useState<number[]>(() => loadRecent())
@@ -74,8 +93,21 @@ export function PlantPicker({
   }, [all, recent, query])
 
   function choose(p: Plant) {
+    const lots = attributableLots(lotsFor.get(p.id) ?? [])
+    if (lots.length > 1) {
+      setChoosingLotFor(p)
+      return
+    }
     setRecent(recordRecent(p.id))
-    onSelect(p)
+    // A single lot attributes even when its count says empty. The count records
+    // what was written down, not a fact about the packet — dropping attribution
+    // there would make a wrong number harder to correct rather than easier.
+    onSelect(p, lots[0])
+  }
+
+  function chooseLot(p: Plant, lot?: SeedLot) {
+    setRecent(recordRecent(p.id))
+    onSelect(p, lot)
   }
 
   // A plant option row. keyPrefix namespaces the key so a plant appearing in
@@ -92,11 +124,22 @@ export function PlantPicker({
         <span className="block truncate font-medium text-fg">{p.name}</span>
         <span className="block text-xs text-muted">
           {CATEGORY_LABELS[p.category]} · {formatSpacing(p.spacingCm, unit)}
+          {remainingLabel(lotsFor.get(p.id) ?? [])}
         </span>
       </span>
     </button>
   )
 
+  // What's left, shown where you're deciding what to plant. Silent when there
+  // are no lots — most plants won't have any, and "0 left" on all of them would
+  // be noise that trains you to ignore the number. summarizeLots owns the
+  // unit-agreement rule; a second copy of it here would drift.
+  function remainingLabel(lots: SeedLot[]): string {
+    if (lots.length === 0) return ''
+    const { remaining, unit } = summarizeLots(lots)
+    return ` · ${formatQuantity(remaining)}${unit ? ` ${unit}` : ''} left`
+  }
+
   return (
     <div
       className="fixed inset-0 z-50 flex items-end justify-center bg-black/40 sm:items-center sm:p-4"
@@ -132,7 +175,41 @@ export function PlantPicker({
           <CategoryChips value={category} onChange={setCategory} size="sm" />
         </div>
 
+        {choosingLotFor && (
           <div className="min-h-0 flex-1 overflow-y-auto p-2">
+            <p className="px-3 pb-1 pt-2 text-xs font-semibold uppercase tracking-wide text-muted">
+              Which lot of {choosingLotFor.name}?
+            </p>
+            {attributableLots(lotsFor.get(choosingLotFor.id) ?? []).map((lot) => (
+                <button
+                  key={lot.id}
+                  type="button"
+                  onClick={() => chooseLot(choosingLotFor, lot)}
+                  className="flex w-full items-center gap-3 rounded-lg px-3 py-2.5 text-left outline-none transition-colors hover:bg-border/50 focus-visible:bg-border/50"
+                >
+                  <span className="min-w-0 flex-1">
+                    <span className="block truncate text-sm font-medium text-fg">
+                      {lot.vendor || 'Unnamed lot'}
+                      {lot.packedForYear != null ? ` · ${lot.packedForYear}` : ''}
+                    </span>
+                    <span className="block text-xs text-muted">
+                      {formatQuantity(lot.remaining)} of {formatQuantity(lot.quantity)} {lot.unit} left
+                    </span>
+                  </span>
+                  <LotStateChip state={lotState(lot)} />
+                </button>
+            ))}
+            <button
+              type="button"
+              onClick={() => chooseLot(choosingLotFor, undefined)}
+              className="w-full rounded-lg px-3 py-2.5 text-left text-sm text-muted outline-none transition-colors hover:bg-border/50 focus-visible:bg-border/50"
+            >
+              Don't attribute to a lot
+            </button>
+          </div>
+        )}
+
+        <div className={cn('min-h-0 flex-1 overflow-y-auto p-2', choosingLotFor && 'hidden')}>
           {plants.isPending && <p className="p-4 text-sm text-muted">Loading plants…</p>}
           {plants.isError && <p className="p-4 text-sm text-red-600 dark:text-red-400">Couldn't load plants.</p>}
 

web/src/editor/UndoButton.tsx

@@ -1,6 +1,6 @@
 import { Button } from '@/components/ui/Button'
 import { cn } from '@/lib/cn'
-import type { ChangeSet, UndoOutcome, useUndo } from '@/lib/history'
+import type { UndoOutcome, UndoTarget, useUndo } from '@/lib/history'
 
 /**
  * Undo, plus what happened. Paired with useUndo so the history list and the
@@ -14,7 +14,7 @@ export function UndoButton({
   className,
   label = 'Undo',
 }: {
-  changeSet: ChangeSet
+  changeSet: UndoTarget
   undo: ReturnType<typeof useUndo>
   className?: string
   label?: string
@@ -43,8 +43,12 @@ const TONE_CLASS: Record<Exclude<UndoOutcome['tone'], 'pending'>, string> = {
 
 function OutcomeNote({ outcome }: { outcome: UndoOutcome }) {
   if (outcome.tone === 'pending') return null
+  // No text alignment of its own: the container decides. The history list stacks
+  // this to the right of an entry, the chat panel puts it under a left-aligned
+  // message, and a hard-coded text-right made the chat's copy read against its
+  // own column.
   return (
-    <p role="status" className={cn('text-right text-xs', TONE_CLASS[outcome.tone])}>
+    <p role="status" className={cn('text-xs', TONE_CLASS[outcome.tone])}>
       {outcome.message}
     </p>
   )

web/src/editor/store.ts

@@ -47,7 +47,10 @@ interface EditorState {
   // The plant armed for placing plops (set after the PlantPicker choice); stays
   // armed for repeat-placement until cleared (Escape / done). null = not placing.
   armedPlant: Plant | null
-  setArmedPlant: (p: Plant | null) => void
+  // Which seed lot placements should be attributed to, when the armed plant has
+  // one worth naming. Cleared with the plant.
+  armedLotId: number | null
+  setArmedPlant: (p: Plant | null, lotId?: number | null) => void
 
   // During a move/resize/rotate, the object's live geometry is held here so the
   // canvas renders it instantly; the PATCH fires only on gesture end.
@@ -98,7 +101,8 @@ export const useEditorStore = create<EditorState>((set) => ({
   setJournalObjectId: (id) => set({ journalObjectId: id }),
 
   armedPlant: null,
-  setArmedPlant: (p) => set({ armedPlant: p }),
+  armedLotId: null,
+  setArmedPlant: (p, lotId = null) => set({ armedPlant: p, armedLotId: p ? lotId : null }),
 
   liveObject: null,
   setLiveObject: (o) => set({ liveObject: o }),
@@ -118,6 +122,7 @@ export const useEditorStore = create<EditorState>((set) => ({
       selectedPlantingId: null,
       focusedObjectId: null,
       armedPlant: null,
+      armedLotId: null,
       armedKind: null,
       liveObject: null,
       livePlanting: null,

web/src/lib/agent.test.ts

@@ -0,0 +1,29 @@
+import { describe, expect, it } from 'vitest'
+import { describeStep } from './agent'
+
+describe('describeStep', () => {
+  // Raw tool names tell you the agent is busy; these tell you what it's busy
+  // DOING, which is the difference between the panel feeling alive and hung.
+  it("names tools in the app's own vocabulary", () => {
+    expect(describeStep({ index: 0, tools: ['clear_object'] })).toBe('Clearing a bed')
+    expect(describeStep({ index: 1, tools: ['find_plant'] })).toBe('Looking up a plant')
+  })
+
+  it('collapses repeats within one step', () => {
+    expect(describeStep({ index: 0, tools: ['fill_region', 'fill_region'] })).toBe('Filling a bed')
+  })
+
+  it('joins distinct tools', () => {
+    expect(describeStep({ index: 0, tools: ['clear_object', 'fill_region'] })).toBe('Clearing a bed, Filling a bed')
+  })
+
+  it('says something for a step with no tool calls', () => {
+    expect(describeStep({ index: 0, tools: [] })).toBe('Thinking')
+  })
+
+  // A tool added server-side before the client knows about it should degrade to
+  // something readable rather than showing snake_case at the user.
+  it('falls back readably for an unknown tool', () => {
+    expect(describeStep({ index: 0, tools: ['prune_orchard'] })).toBe('prune orchard')
+  })
+})

web/src/lib/agent.ts

@@ -0,0 +1,232 @@
+// The garden assistant's client (#57).
+//
+// The chat lives in the editor, not on its own page, because watching the canvas
+// change as the agent works IS the confirmation — which is what makes acting
+// without asking first tolerable. So this module's job is as much about
+// surfacing progress as it is about sending a message.
+
+import { useMutation, useQuery, useQueryClient } from '@tanstack/react-query'
+import { z } from 'zod'
+import { API_BASE, api } from './api'
+import { gardenFullKey } from './objects'
+import { historyKey } from './history'
+
+const capabilitiesSchema = z.object({ agent: z.boolean() })
+
+/** Whether this instance has the assistant configured. Without it the panel
+ *  isn't rendered at all — a dead button is worse than no button. */
+export function useCapabilities() {
+  return useQuery({
+    queryKey: ['capabilities'] as const,
+    queryFn: async () => capabilitiesSchema.parse(await api.get('/capabilities')),
+    staleTime: Infinity, // server config; it doesn't change under a running page
+  })
+}
+
+export const agentMessageSchema = z.object({
+  id: z.number(),
+  conversationId: z.number(),
+  role: z.enum(['user', 'assistant']),
+  body: z.string(),
+  changeSetId: z.number().optional(),
+  createdAt: z.string(),
+})
+export type AgentMessage = z.infer<typeof agentMessageSchema>
+
+const historySchema = z.object({ messages: z.array(agentMessageSchema) })
+
+export function agentHistoryKey(gardenId: number) {
+  return ['gardens', gardenId, 'agent-history'] as const
+}
+
+/** The stored conversation, so a reload doesn't lose the thread — which is
+ *  exactly when someone reloads, to check whether a change actually landed. */
+export function useAgentHistory(gardenId: number, enabled: boolean) {
+  return useQuery({
+    queryKey: agentHistoryKey(gardenId),
+    enabled,
+    queryFn: async (): Promise<AgentMessage[]> =>
+      historySchema.parse(await api.get(`/gardens/${gardenId}/agent/history`)).messages,
+  })
+}
+
+export function useClearAgentHistory(gardenId: number) {
+  const qc = useQueryClient()
+  return useMutation({
+    mutationFn: async (): Promise<void> => {
+      await api.delete(`/gardens/${gardenId}/agent/history`)
+    },
+    onSuccess: () => qc.invalidateQueries({ queryKey: agentHistoryKey(gardenId) }),
+  })
+}
+
+/** One completed turn, as the server reports it. */
+export interface AgentTurn {
+  reply: string
+  changeSetId?: number
+  steps: number
+  truncated?: boolean
+}
+
+/** A step the model just finished, named in the app's own vocabulary. */
+export interface AgentStep {
+  index: number
+  tools: string[]
+}
+
+// What each tool is doing, in words. Raw tool names ("fill_region") tell you the
+// agent is busy; these tell you what it's busy DOING, which is the difference
+// between the panel feeling alive and feeling hung.
+const TOOL_LABELS: Record<string, string> = {
+  list_gardens: 'Looking at your gardens',
+  describe_garden: 'Reading the garden',
+  create_object: 'Adding a bed',
+  move_object: 'Moving a bed',
+  place_planting: 'Planting',
+  fill_region: 'Filling a bed',
+  clear_object: 'Clearing a bed',
+  find_plant: 'Looking up a plant',
+  create_plant: 'Adding a plant to your catalog',
+  add_journal_entry: 'Writing a journal note',
+}
+
+export function describeStep(step: AgentStep): string {
+  if (step.tools.length === 0) return 'Thinking'
+  const labels = step.tools.map((t) => TOOL_LABELS[t] ?? t.replace(/_/g, ' '))
+  // Repeated tools in one step read as one action, not a list of identical ones.
+  return [...new Set(labels)].join(', ')
+}
+
+const chatEventSchema = z.object({
+  step: z.object({ index: z.number(), tools: z.array(z.string()) }).optional(),
+  done: z
+    .object({
+      reply: z.string(),
+      changeSetId: z.number().optional(),
+      steps: z.number(),
+      truncated: z.boolean().optional(),
+    })
+    .optional(),
+  error: z.string().optional(),
+  // The turn worked but something adjacent to it didn't — currently, the
+  // exchange couldn't be saved. Dropping this on the floor would recreate
+  // exactly the silent swallow the server added it to avoid.
+  warning: z.string().optional(),
+})
+
+export interface StreamHandlers {
+  onStep: (step: AgentStep) => void
+  onDone: (turn: AgentTurn) => void
+  onError: (message: string) => void
+  /** The turn succeeded, but something alongside it didn't. */
+  onWarning?: (message: string) => void
+}
+
+/**
+ * Send a message and stream the reply.
+ *
+ * Hand-rolled rather than EventSource, which can only issue GETs — this needs a
+ * POST body. The wire format is still SSE so a proxy that understands it doesn't
+ * buffer, and so switching to EventSource later wouldn't change the server.
+ */
+export async function streamChat(
+  gardenId: number,
+  message: string,
+  handlers: StreamHandlers,
+  signal?: AbortSignal,
+): Promise<void> {
+  let res: Response
+  try {
+    res = await fetch(`${API_BASE}/agent/chat`, {
+      method: 'POST',
+      headers: { 'content-type': 'application/json' },
+      body: JSON.stringify({ gardenId, message }),
+      credentials: 'same-origin',
+      signal,
+    })
+  } catch {
+    // An abort here is the caller's own doing — Stop, or navigating away — not a
+    // failure to report back to them. The read loop below already knew this; the
+    // request path did not.
+    if (signal?.aborted) return
+    handlers.onError('Could not reach the server.')
+    return
+  }
+  if (!res.ok || !res.body) {
+    handlers.onError(
+      res.status === 404
+        ? "This instance doesn't have the assistant configured."
+        : 'The assistant is not available right now.',
+    )
+    return
+  }
+
+  const reader = res.body.getReader()
+  const decoder = new TextDecoder()
+  let buffer = ''
+  for (;;) {
+    let chunk: ReadableStreamReadResult<Uint8Array>
+    try {
+      chunk = await reader.read()
+    } catch {
+      // An aborted read is the caller navigating away, not a failure worth
+      // reporting back to them.
+      if (signal?.aborted) return
+      handlers.onError('The connection dropped partway through.')
+      return
+    }
+    if (chunk.done) break
+    buffer += decoder.decode(chunk.value, { stream: true })
+
+    // SSE frames are separated by a blank line; anything after the last one is
+    // a partial frame to keep for the next chunk.
+    const frames = buffer.split('\n\n')
+    buffer = frames.pop() ?? ''
+    for (const frame of frames) {
+      const line = frame.split('\n').find((l) => l.startsWith('data:'))
+      if (!line) continue
+      // Parsed AND validated: a malformed or unexpected frame shouldn't kill a
+      // working stream, and shouldn't be trusted into the UI either.
+      const parsed = chatEventSchema.safeParse(safeJson(line.slice(5).trim()))
+      if (!parsed.success) continue
+      const e = parsed.data
+      if (e.warning) handlers.onWarning?.(e.warning)
+      if (e.error) handlers.onError(e.error)
+      else if (e.step) handlers.onStep(e.step)
+      else if (e.done) handlers.onDone(e.done)
+    }
+  }
+}
+
+function safeJson(raw: string): unknown {
+  try {
+    return JSON.parse(raw)
+  } catch {
+    return null
+  }
+}
+
+/**
+ * Refreshes for the two moments that need different amounts of work.
+ *
+ * Mid-turn, only the canvas can have changed: the change set isn't written until
+ * the turn commits, and the exchange isn't stored until it finishes. Refetching
+ * those on every step would be up to 2×(N−1) requests per turn for data that
+ * cannot have moved.
+ */
+export function useAgentRefresh(gardenId: number) {
+  const qc = useQueryClient()
+  const canvas = () => {
+    void qc.invalidateQueries({ queryKey: gardenFullKey(gardenId) })
+  }
+  return {
+    /** After a step: the garden may have changed under the conversation. */
+    canvas,
+    /** After a turn: the change set and the stored exchange exist now too. */
+    everything: () => {
+      canvas()
+      void qc.invalidateQueries({ queryKey: historyKey(gardenId) })
+      void qc.invalidateQueries({ queryKey: agentHistoryKey(gardenId) })
+    },
+  }
+}

web/src/lib/history.test.ts

@@ -49,6 +49,14 @@ describe('describeConflict', () => {
 describe('describeUndo', () => {
   const target = changeSet({ counts: [{ entityType: 'object', op: 'update', n: 3 }] })
 
+  // The bug this pair exists for: a real revert response carries a change set
+  // whose counts the server didn't populate. Reading that as "nothing happened"
+  // told the user a successful undo had done nothing.
+  it('trusts the change set, not the tally, for whether anything happened', () => {
+    const out = describeUndo({ id: 5 }, { changeSet: changeSet({ id: 6, counts: [] }), conflicts: [] })
+    expect(out).toEqual({ tone: 'ok', message: 'Undone.' })
+  })
+
   it('is a plain success when nothing conflicted', () => {
     const out = describeUndo(target, {
       changeSet: changeSet({ id: 2, counts: [{ entityType: 'object', op: 'update', n: 3 }] }),
@@ -61,6 +69,7 @@ describe('describeUndo', () => {
   // already a no-op — reachable by undoing a creation whose object is gone.
   // Claiming "Undone." there reports work that didn't happen.
   it("doesn't claim to have undone a no-op", () => {
+    // A NULL change set — not an empty tally — is the server's no-op signal.
     const out = describeUndo(target, { changeSet: null, conflicts: [] })
     expect(out.tone).toBe('ok')
     expect(out.message).toBe('Nothing left to undo — this was already reversed.')
@@ -113,3 +122,29 @@ describe('totalChanges', () => {
     ).toBe(13)
   })
 })
+
+describe('describeUndo with an unknown total', () => {
+  // The chat panel offers Undo on a turn knowing only its change set id — the
+  // agent's reply carries the id, not the tally. Inventing a denominator to
+  // fill the sentence would be worse than not having one.
+  it("doesn't invent a denominator it was never given", () => {
+    const out = describeUndo(
+      { id: 5 },
+      {
+        changeSet: changeSet({ id: 6, counts: [{ entityType: 'planting', op: 'delete', n: 2 }] }),
+        conflicts: [{ entityType: 'object', entityId: 7, reason: 'changed', name: 'North Bed' }],
+      },
+    )
+    expect(out.tone).toBe('partial')
+    expect(out.message).toBe('Partly undone — “North Bed” was edited since, so it was left alone.')
+    expect(out.message).not.toMatch(/\d+ of \d+/)
+  })
+
+  it('still reports a clean undo the same way', () => {
+    const out = describeUndo(
+      { id: 5 },
+      { changeSet: changeSet({ id: 6, counts: [{ entityType: 'object', op: 'update', n: 1 }] }), conflicts: [] },
+    )
+    expect(out).toEqual({ tone: 'ok', message: 'Undone.' })
+  })
+})

web/src/lib/history.ts

@@ -113,9 +113,10 @@ export function useRevertChangeSet(gardenId: number) {
   })
 }
 
-/** How many rows a change set touched, for "3 changes" in the list. */
+/** How many rows a change set touched, for "3 changes" in the list. Undefined
-export function totalChanges(cs: ChangeSet): number {
+ *  counts total zero, which callers read as "no denominator to quote". */
-  return cs.counts.reduce((sum, c) => sum + c.n, 0)
+export function totalChanges(cs: { counts?: ChangeCount[] }): number {
+  return (cs.counts ?? []).reduce((sum, c) => sum + c.n, 0)
 }
 
 const ENTITY_NOUNS: Record<ChangeCount['entityType'], [string, string]> = {
@@ -171,7 +172,7 @@ export function useUndo(gardenId: number) {
   const revert = useRevertChangeSet(gardenId)
   const [outcomes, setOutcomes] = useState<Record<number, UndoOutcome>>({})
 
-  const undo = (cs: ChangeSet) => {
+  const undo = (cs: UndoTarget) => {
     setOutcomes((prev) => ({ ...prev, [cs.id]: { tone: 'pending', message: 'Undoing…' } }))
     revert.mutate(cs.id, {
       onSuccess: (result) => {
@@ -197,6 +198,19 @@ export function useUndo(gardenId: number) {
   }
 }
 
+/**
+ * What undo needs to know about a change set.
+ *
+ * `counts` is optional because the chat panel offers Undo on a turn knowing only
+ * its change set id — the agent's reply carries the id, not the tally. Fabricating
+ * counts to satisfy a type would produce a confidently wrong "1 of 1 changes
+ * undone"; leaving them out lets describeUndo say what it actually knows.
+ */
+export interface UndoTarget {
+  id: number
+  counts?: ChangeCount[]
+}
+
 export interface UndoOutcome {
   tone: 'pending' | 'ok' | 'partial' | 'error'
   message: string
@@ -208,19 +222,25 @@ export interface UndoOutcome {
  * useful thing to report: a bare failure would be a lie about the two that did
  * apply, and a bare success would hide the one that didn't.
  */
-export function describeUndo(target: ChangeSet, result: RevertResult): UndoOutcome {
+export function describeUndo(target: UndoTarget, result: RevertResult): UndoOutcome {
   const skipped = result.conflicts.map(describeConflict).join('; ')
+  // A NULL change set is the server's signal that nothing needed doing. An empty
+  // `counts` is not the same thing and must not be read as one — that conflation
+  // made a successful undo report "nothing left to undo", which is the worst
+  // possible thing to tell someone about an action that just worked.
+  const didSomething = result.changeSet != null
   const applied = result.changeSet ? totalChanges(result.changeSet) : 0
   if (result.conflicts.length === 0) {
-    // The server answers 200 with a null change set when every revision was
+    // Reachable by undoing a creation whose object is already gone.
-    // already a no-op — reachable by undoing a creation whose object is gone.
+    if (!didSomething) return { tone: 'ok', message: 'Nothing left to undo — this was already reversed.' }
-    // Claiming "Undone." there would be reporting work that didn't happen.
-    if (applied === 0) return { tone: 'ok', message: 'Nothing left to undo — this was already reversed.' }
     return { tone: 'ok', message: 'Undone.' }
   }
-  if (applied === 0) {
+  if (!didSomething) {
     return { tone: 'error', message: `Nothing was undone — ${skipped}.` }
   }
+  // Only claim a denominator when we have one. "2 of 3" from a caller that
+  // never knew the total would be a number invented to fill a sentence.
   const total = totalChanges(target)
-  return { tone: 'partial', message: `${applied} of ${total} changes undone — ${skipped}.` }
+  const scale = total > 0 && applied > 0 ? `${applied} of ${total} changes undone` : 'Partly undone'
+  return { tone: 'partial', message: `${scale} — ${skipped}.` }
 }

web/src/lib/objects.ts

@@ -258,6 +258,8 @@ export interface PlantingCreate {
   radiusCm: number
   count?: number | null
   label?: string | null
+  /** Attributes the plop to a purchase, so that lot can report what's left. */
+  seedLotId?: number
 }
 
 export function useCreatePlanting(gardenId: number) {

web/src/lib/plants.ts

@@ -31,6 +31,10 @@ export const plantSchema = z.object({
   color: z.string(),
   icon: z.string(),
   daysToMaturity: z.number().nullable().optional(),
+  // Provenance for the VARIETY — the page you'd go back to to buy it again.
+  // What you actually bought, and how much is left, lives in seedLots.ts.
+  sourceUrl: z.string().default(''),
+  vendor: z.string().default(''),
   notes: z.string(),
   version: z.number(),
   createdAt: z.string(),
@@ -75,6 +79,8 @@ export interface PlantInput {
   color: string
   icon: string
   daysToMaturity: number | null
+  sourceUrl: string
+  vendor: string
   notes: string
 }
 

web/src/lib/seedLots.test.ts

@@ -0,0 +1,149 @@
+import { describe, expect, it } from 'vitest'
+import {
+  attributableLots,
+  formatCost,
+  formatQuantity,
+  formatUnitCost,
+  lotState,
+  lotsByPlant,
+  safeExternalUrl,
+  summarizeLots,
+  type SeedLot,
+} from './seedLots'
+
+function lot(over: Partial<SeedLot> = {}): SeedLot {
+  return {
+    id: 1,
+    ownerId: 1,
+    plantId: 1,
+    vendor: '',
+    sourceUrl: '',
+    sku: '',
+    lotCode: '',
+    quantity: 100,
+    unit: 'seeds',
+    notes: '',
+    version: 1,
+    createdAt: '2026-01-01T00:00:00Z',
+    updatedAt: '2026-01-01T00:00:00Z',
+    used: 0,
+    remaining: 100,
+    ...over,
+  }
+}
+
+describe('safeExternalUrl', () => {
+  // The server already scheme-checks this, but a link is rendered from whatever
+  // the client was handed. "The backend validated it" is not a reason to hand
+  // javascript: to an anchor tag.
+  it('accepts http and https', () => {
+    expect(safeExternalUrl('https://www.johnnyseeds.com/x')).toBe('https://www.johnnyseeds.com/x')
+    expect(safeExternalUrl('http://example.com/')).toBe('http://example.com/')
+  })
+
+  it('refuses everything else', () => {
+    for (const bad of [
+      '',
+      'javascript:alert(1)',
+      'JavaScript:alert(1)',
+      'data:text/html,<script>alert(1)</script>',
+      'file:///etc/passwd',
+      '//evil.example.com',
+      '/seeds/garlic',
+      'not a url',
+    ]) {
+      expect(safeExternalUrl(bad)).toBeNull()
+    }
+  })
+})
+
+describe('lotState', () => {
+  it('reads the state, not just the number', () => {
+    expect(lotState(lot({ quantity: 100, remaining: 100 }))).toBe('ok')
+    expect(lotState(lot({ quantity: 100, remaining: 20 }))).toBe('low')
+    expect(lotState(lot({ quantity: 100, remaining: 0 }))).toBe('empty')
+    // Planting more than you recorded buying is real, and worth showing plainly
+    // rather than clamping to zero.
+    expect(lotState(lot({ quantity: 100, remaining: -5 }))).toBe('over')
+  })
+
+  it('has nothing to say about a lot with no recorded quantity', () => {
+    expect(lotState(lot({ quantity: 0, remaining: 0 }))).toBe('unknown')
+  })
+})
+
+describe('summarizeLots', () => {
+  it('totals remaining and reports the worst state', () => {
+    const s = summarizeLots([
+      lot({ id: 1, quantity: 100, remaining: 80 }),
+      lot({ id: 2, quantity: 50, remaining: 5 }),
+    ])
+    expect(s.remaining).toBe(85)
+    expect(s.unit).toBe('seeds')
+    expect(s.state).toBe('low') // the one that needs attention wins
+  })
+
+  it("drops the unit when lots don't agree, rather than summing dishonestly", () => {
+    const s = summarizeLots([
+      lot({ id: 1, unit: 'seeds', quantity: 100, remaining: 100 }),
+      lot({ id: 2, unit: 'grams', quantity: 10, remaining: 10 }),
+    ])
+    expect(s.unit).toBeNull()
+  })
+
+  it('says nothing for a plant with no lots', () => {
+    expect(summarizeLots([])).toEqual({ remaining: 0, unit: null, state: 'unknown' })
+  })
+})
+
+describe('cost formatting', () => {
+  it('renders whole currency from cents', () => {
+    expect(formatCost(499)).toBe('$4.99')
+    expect(formatCost(undefined)).toBeNull()
+  })
+
+  it('gives per-unit cost extra precision when it would round to nothing', () => {
+    expect(formatUnitCost(lot({ costCents: 499, quantity: 100 }))).toBe('$0.050/seed')
+    expect(formatUnitCost(lot({ costCents: 1200, quantity: 4, unit: 'packets' }))).toBe('$3.00/packet')
+  })
+
+  it('has no per-unit cost without both halves', () => {
+    expect(formatUnitCost(lot({ costCents: undefined }))).toBeNull()
+    expect(formatUnitCost(lot({ costCents: 499, quantity: 0 }))).toBeNull()
+  })
+})
+
+describe('lotsByPlant', () => {
+  it('groups, and copes with nothing', () => {
+    const grouped = lotsByPlant([lot({ id: 1, plantId: 7 }), lot({ id: 2, plantId: 7 }), lot({ id: 3, plantId: 9 })])
+    expect(grouped.get(7)?.length).toBe(2)
+    expect(grouped.get(9)?.length).toBe(1)
+    expect(lotsByPlant(undefined).size).toBe(0)
+  })
+})
+
+describe('attributableLots', () => {
+  // An exhausted lot is still offered: the count records what was written down,
+  // not a fact about the packet, so refusing to attribute a planting because the
+  // number says zero would make a wrong number harder to correct, not easier.
+  it('offers exhausted lots, just not first', () => {
+    const empty = lot({ id: 1, remaining: 0 })
+    const full = lot({ id: 2, remaining: 100 })
+    expect(attributableLots([empty, full]).map((l) => l.id)).toEqual([2, 1])
+    expect(attributableLots([empty]).length).toBe(1)
+  })
+
+  it("doesn't mutate its input", () => {
+    const lots = [lot({ id: 1, remaining: 0 }), lot({ id: 2, remaining: 100 })]
+    attributableLots(lots)
+    expect(lots.map((l) => l.id)).toEqual([1, 2])
+  })
+})
+
+describe('formatQuantity', () => {
+  it('keeps whole counts whole and fractional ones readable', () => {
+    expect(formatQuantity(100)).toBe('100')
+    expect(formatQuantity(12.5)).toBe('12.5')
+    expect(formatQuantity(-15)).toBe('-15') // over-planted lots go negative
+  })
+})

web/src/lib/seedLots.ts

@@ -0,0 +1,212 @@
+// Seed lots (#51): what you actually bought, and what's left of it.
+//
+// A lot is one purchase of one variety. Inventory belongs to the purchase rather
+// than to the variety because the same garlic from two vendors in two years is
+// two different things — see #50 for the reasoning behind the shape.
+
+import { useMutation, useQuery, useQueryClient } from '@tanstack/react-query'
+import { z } from 'zod'
+import { ApiError, api } from './api'
+
+export const lotUnitSchema = z.enum(['seeds', 'grams', 'ounces', 'packets', 'bulbs', 'plants'])
+export type LotUnit = z.infer<typeof lotUnitSchema>
+
+export const LOT_UNITS: { value: LotUnit; label: string }[] = [
+  { value: 'seeds', label: 'seeds' },
+  { value: 'grams', label: 'grams' },
+  { value: 'ounces', label: 'ounces' },
+  { value: 'packets', label: 'packets' },
+  { value: 'bulbs', label: 'bulbs' },
+  { value: 'plants', label: 'plants' },
+]
+
+export const seedLotSchema = z.object({
+  id: z.number(),
+  ownerId: z.number(),
+  plantId: z.number(),
+  vendor: z.string(),
+  sourceUrl: z.string(),
+  sku: z.string(),
+  lotCode: z.string(),
+  purchasedAt: z.string().optional(),
+  packedForYear: z.number().optional(),
+  quantity: z.number(),
+  unit: lotUnitSchema,
+  costCents: z.number().optional(),
+  germinationPct: z.number().optional(),
+  notes: z.string(),
+  version: z.number(),
+  createdAt: z.string(),
+  updatedAt: z.string(),
+  // Computed server-side: used is the summed effective count of active
+  // plantings attributed to this lot; remaining is quantity - used, and may be
+  // NEGATIVE when more was planted than the lot recorded buying.
+  used: z.number(),
+  remaining: z.number(),
+})
+export type SeedLot = z.infer<typeof seedLotSchema>
+
+const seedLotsKey = ['seed-lots'] as const
+
+export function useSeedLots() {
+  return useQuery({
+    queryKey: seedLotsKey,
+    queryFn: async (): Promise<SeedLot[]> => z.array(seedLotSchema).parse(await api.get('/seed-lots')),
+  })
+}
+
+export interface SeedLotInput {
+  plantId: number
+  vendor: string
+  sourceUrl: string
+  sku: string
+  lotCode: string
+  purchasedAt: string | null
+  packedForYear: number | null
+  quantity: number
+  unit: LotUnit
+  costCents: number | null
+  germinationPct: number | null
+  notes: string
+}
+
+function invalidate(qc: ReturnType<typeof useQueryClient>) {
+  void qc.invalidateQueries({ queryKey: seedLotsKey })
+}
+
+export function useCreateSeedLot() {
+  const qc = useQueryClient()
+  return useMutation({
+    mutationFn: async (input: SeedLotInput): Promise<SeedLot> =>
+      seedLotSchema.parse(await api.post('/seed-lots', input)),
+    onSuccess: () => invalidate(qc),
+  })
+}
+
+export function useUpdateSeedLot() {
+  const qc = useQueryClient()
+  return useMutation({
+    mutationFn: async (vars: Partial<SeedLotInput> & { id: number; version: number }): Promise<SeedLot> => {
+      const { id, ...rest } = vars
+      return seedLotSchema.parse(await api.patch(`/seed-lots/${id}`, rest))
+    },
+    onSuccess: () => invalidate(qc),
+  })
+}
+
+export function useDeleteSeedLot() {
+  const qc = useQueryClient()
+  return useMutation({
+    mutationFn: async (id: number): Promise<void> => {
+      await api.delete(`/seed-lots/${id}`)
+    },
+    onSuccess: () => invalidate(qc),
+  })
+}
+
+/**
+ * The lots a placement could be attributed to, best first.
+ *
+ * Lots with seed left come first, but an exhausted one is still offered: the
+ * count is a record of what you wrote down, not a fact about the packet, and
+ * refusing to attribute a planting because the number says zero would make the
+ * number harder to correct rather than easier.
+ */
+export function attributableLots(lots: SeedLot[]): SeedLot[] {
+  return [...lots].sort((a, b) => Number(b.remaining > 0) - Number(a.remaining > 0))
+}
+
+/** The current server row carried by a 409, so an edit form can rebase onto it
+ *  and the user can re-save rather than losing what they typed. Every other
+ *  entity's form does this; a lot is no different. */
+export function conflictSeedLot(err: unknown): SeedLot | null {
+  if (!(err instanceof ApiError) || !err.isConflict) return null
+  const parsed = seedLotSchema.safeParse((err.body as { current?: unknown })?.current)
+  return parsed.success ? parsed.data : null
+}
+
+/** Group lots by the plant they belong to. */
+export function lotsByPlant(lots: SeedLot[] | undefined): Map<number, SeedLot[]> {
+  const map = new Map<number, SeedLot[]>()
+  for (const lot of lots ?? []) {
+    const list = map.get(lot.plantId)
+    if (list) list.push(lot)
+    else map.set(lot.plantId, [lot])
+  }
+  return map
+}
+
+/**
+ * How a lot is doing, as a state rather than a number — this is the thing you
+ * scan for when deciding what to order, and a number alone doesn't survive being
+ * skimmed down a list.
+ *
+ * "over" means more was planted than the lot recorded buying. That's a real
+ * situation (a miscounted packet, a lot entered after the fact) and worth
+ * showing plainly rather than clamping to zero and hiding the discrepancy.
+ */
+export type LotState = 'over' | 'empty' | 'low' | 'ok' | 'unknown'
+
+const LOW_FRACTION = 0.2
+
+export function lotState(lot: SeedLot): LotState {
+  if (lot.quantity <= 0) return 'unknown' // no quantity recorded: nothing to be low on
+  if (lot.remaining < 0) return 'over'
+  if (lot.remaining === 0) return 'empty'
+  if (lot.remaining / lot.quantity <= LOW_FRACTION) return 'low'
+  return 'ok'
+}
+
+/** The total remaining across a plant's lots, and the worst state among them —
+ *  what a plant card shows before you open it. */
+export function summarizeLots(lots: SeedLot[]): { remaining: number; unit: LotUnit | null; state: LotState } {
+  if (lots.length === 0) return { remaining: 0, unit: null, state: 'unknown' }
+  // Mixed units can't be summed honestly; report the majority unit's total only
+  // when they all agree, else leave the unit off and let the per-lot rows speak.
+  const unit = lots.every((l) => l.unit === lots[0].unit) ? lots[0].unit : null
+  const remaining = lots.reduce((sum, l) => sum + l.remaining, 0)
+  const order: LotState[] = ['over', 'empty', 'low', 'ok', 'unknown']
+  const state = order.find((s) => lots.some((l) => lotState(l) === s)) ?? 'unknown'
+  return { remaining, unit, state }
+}
+
+/** Quantities are stored as REAL because grams and ounces are fractional, but a
+ *  whole number of seeds shouldn't render as "100.0". */
+export function formatQuantity(n: number): string {
+  return Number.isInteger(n) ? String(n) : n.toFixed(1)
+}
+
+/** Whole currency from cents, e.g. 499 → "$4.99". */
+export function formatCost(cents: number | undefined): string | null {
+  if (cents == null) return null
+  return new Intl.NumberFormat(undefined, { style: 'currency', currency: 'USD' }).format(cents / 100)
+}
+
+/** Cost per unit, when both are known and it says something useful. */
+export function formatUnitCost(lot: SeedLot): string | null {
+  if (lot.costCents == null || lot.quantity <= 0) return null
+  const per = lot.costCents / 100 / lot.quantity
+  return `${new Intl.NumberFormat(undefined, { style: 'currency', currency: 'USD', minimumFractionDigits: per < 0.1 ? 3 : 2 }).format(per)}/${singular(lot.unit)}`
+}
+
+function singular(unit: LotUnit): string {
+  return unit.endsWith('s') ? unit.slice(0, -1) : unit
+}
+
+/**
+ * Whether a stored URL is safe to render as a link.
+ *
+ * The server already scheme-checks this (#50), but a link is rendered from
+ * whatever the client was handed — an old row, a different server version, a
+ * response someone tampered with — and "the backend validated it" is not a
+ * reason to hand `javascript:` to an anchor tag. Cheap to check twice.
+ */
+export function safeExternalUrl(raw: string): string | null {
+  if (!raw) return null
+  try {
+    const u = new URL(raw)
+    return u.protocol === 'http:' || u.protocol === 'https:' ? u.toString() : null
+  } catch {
+    return null
+  }
+}

web/src/pages/GardenEditorPage.tsx

@@ -5,6 +5,7 @@ import { Button } from '@/components/ui/Button'
 import { GardenCanvas } from '@/editor/GardenCanvas'
 import { EditorRail, type RailTab } from '@/editor/EditorRail'
 import { HistoryPanel } from '@/editor/HistoryPanel'
+import { ChatPanel } from '@/editor/ChatPanel'
 import { JournalPanel } from '@/editor/JournalPanel'
 import { Inspector } from '@/editor/Inspector'
 import { PlopInspector } from '@/editor/PlopInspector'
@@ -30,7 +31,9 @@ import {
 } from '@/lib/objects'
 import { toEditorPlanting } from '@/lib/plantings'
 import type { Plant } from '@/lib/plants'
+import { useCapabilities } from '@/lib/agent'
 import { useJournalCounts } from '@/lib/journal'
+import { attributableLots, lotsByPlant, useSeedLots, type SeedLot } from '@/lib/seedLots'
 import { useSeedTray } from '@/lib/seedTray'
 import { usePageTitle } from '@/lib/usePageTitle'
 
@@ -63,6 +66,7 @@ export function GardenEditorPage() {
   const journalObjectId = useEditorStore((s) => s.journalObjectId)
   const setJournalObjectId = useEditorStore((s) => s.setJournalObjectId)
   const journalCounts = useJournalCounts(gid)
+  const capabilities = useCapabilities()
   const journalTotal = useMemo(
     () => [...(journalCounts.data?.values() ?? [])].reduce((a, b) => a + b, 0),
     [journalCounts.data],
@@ -74,6 +78,8 @@ export function GardenEditorPage() {
   const updateObject = useUpdateObject(gid)
   const ensurePlant = useEnsurePlantInFull(gid)
   const { trayPlants, add: addToTray, remove: removeFromTray } = useSeedTray(gid)
+  const seedLots = useSeedLots()
+  const lotsByPlantId = useMemo(() => lotsByPlant(seedLots.data), [seedLots.data])
 
   // Which plant-picker flow is open: 'place' arms a plant for repeat placement;
   // 'change' swaps the selected plop's plant.
@@ -277,9 +283,18 @@ export function GardenEditorPage() {
   // Arm a plant for tap-to-place. The full catalog carries plants not yet in this
   // garden's /full payload, so make sure the chosen one is in the cache first —
   // otherwise its placed plops render without an icon/color until a refetch.
-  function armPlant(plant: Plant) {
+  // The Seed Tray arms a plant directly, without going through the picker, so it
+  // has to do the picker's single-lot auto-attribution itself — otherwise the
+  // quickest way to place a plant is the one path that silently loses which
+  // packet it came from. Several lots is genuinely ambiguous, so that case stays
+  // unattributed rather than guessing; the picker is where you choose.
+  function armPlant(plant: Plant, lot?: SeedLot) {
     ensurePlant(plant)
-    setArmedPlant(plant)
+    if (lot === undefined) {
+      const lots = attributableLots(lotsByPlantId.get(plant.id) ?? [])
+      lot = lots.length === 1 ? lots[0] : undefined
+    }
+    setArmedPlant(plant, lot?.id ?? null)
   }
 
   // Removing the armed plant from the tray also disarms it, so placement doesn't
@@ -294,14 +309,14 @@ export function GardenEditorPage() {
   // a not-yet-placed plant isn't in that map, which used to silently abort the
   // pick (nothing armed, picker left open). Picking (place OR change) makes sure
   // the plant renders and drops it into this garden's tray for quick reuse.
-  function onPickPlant(plant: Plant) {
+  function onPickPlant(plant: Plant, lot?: SeedLot) {
     if (!canEdit) return // defense in depth: viewers can't reach the picker anyway
     ensurePlant(plant)
     addToTray(plant)
     if (picker === 'change' && selectedPlop) {
       updatePlanting.mutate({ id: selectedPlop.id, version: selectedPlop.version, plantId: plant.id })
     } else {
-      setArmedPlant(plant) // 'place' mode: arm for repeat placement
+      setArmedPlant(plant, lot?.id ?? null) // 'place' mode: arm for repeat placement
     }
     setPicker(null)
   }
@@ -373,6 +388,16 @@ export function GardenEditorPage() {
     },
   ]
 
+  // Only when the instance actually has the assistant configured. A tab that
+  // opens onto an apology is worse than no tab.
+  if (capabilities.data?.agent) {
+    railTabs.push({
+      id: 'chat',
+      label: 'Assistant',
+      render: () => <ChatPanel gardenId={gid} canEdit={canEdit} />,
+    })
+  }
+
   return (
     <div className="flex h-[calc(100vh-8rem)] flex-col gap-3 md:flex-row">
       <div className="shrink-0 md:w-40">
@@ -410,6 +435,15 @@ export function GardenEditorPage() {
         >
           History
         </Button>
+        {capabilities.data?.agent && (
+          <Button
+            variant="ghost"
+            className="mt-1 w-full text-sm"
+            onClick={() => setRailTab(railTab === 'chat' ? null : 'chat')}
+          >
+            💬 Assistant
+          </Button>
+        )}
       </div>
 
       <div className="relative flex min-h-0 flex-1 flex-col gap-2">

web/src/pages/PlantsPage.tsx

@@ -7,8 +7,11 @@ import { CategoryChips } from '@/components/plants/CategoryChips'
 import { PlantCard } from '@/components/plants/PlantCard'
 import { PlantFormModal } from '@/components/plants/PlantFormModal'
 import { DeletePlantModal } from '@/components/plants/DeletePlantModal'
+import { SeedLotModal } from '@/components/plants/SeedLotModal'
+import { DeleteSeedLotModal } from '@/components/plants/DeleteSeedLotModal'
 import { PlantPicker } from '@/editor/PlantPicker'
 import { filterPlants, usePlants, type CategoryFilter, type Plant } from '@/lib/plants'
+import { lotsByPlant, useSeedLots, type SeedLot } from '@/lib/seedLots'
 import type { UnitPref } from '@/lib/units'
 import { usePageTitle } from '@/lib/usePageTitle'
 
@@ -19,6 +22,9 @@ type Dialog =
   | { kind: 'duplicate'; plant: Plant }
   | { kind: 'delete'; plant: Plant }
   | { kind: 'picker' }
+  | { kind: 'addLot'; plant: Plant }
+  | { kind: 'editLot'; plant: Plant; lot: SeedLot }
+  | { kind: 'deleteLot'; lot: SeedLot }
   | null
 
 // There's no per-user unit preference server-side (only per-garden), so the
@@ -35,6 +41,8 @@ function loadUnit(): UnitPref {
 export function PlantsPage() {
   usePageTitle('Plants')
   const plants = usePlants()
+  const seedLots = useSeedLots()
+  const lots = useMemo(() => lotsByPlant(seedLots.data), [seedLots.data])
   const [unit, setUnit] = useState<UnitPref>(() => loadUnit())
   const [query, setQuery] = useState('')
   const [category, setCategory] = useState<CategoryFilter>('all')
@@ -108,9 +116,13 @@ export function PlantsPage() {
                 key={p.id}
                 plant={p}
                 unit={unit}
+                lots={lots.get(p.id) ?? []}
                 onEdit={() => setDialog({ kind: 'edit', plant: p })}
                 onDelete={() => setDialog({ kind: 'delete', plant: p })}
                 onDuplicate={() => setDialog({ kind: 'duplicate', plant: p })}
+                onAddLot={() => setDialog({ kind: 'addLot', plant: p })}
+                onEditLot={(lot) => setDialog({ kind: 'editLot', plant: p, lot })}
+                onDeleteLot={(lot) => setDialog({ kind: 'deleteLot', lot })}
               />
             ))}
           </div>
@@ -121,6 +133,9 @@ export function PlantsPage() {
       {dialog?.kind === 'edit' && <PlantFormModal plant={dialog.plant} unit={unit} onClose={close} />}
       {dialog?.kind === 'duplicate' && <PlantFormModal template={dialog.plant} unit={unit} onClose={close} />}
       {dialog?.kind === 'delete' && <DeletePlantModal plant={dialog.plant} onClose={close} />}
+      {dialog?.kind === 'addLot' && <SeedLotModal plant={dialog.plant} onClose={close} />}
+      {dialog?.kind === 'editLot' && <SeedLotModal plant={dialog.plant} lot={dialog.lot} onClose={close} />}
+      {dialog?.kind === 'deleteLot' && <DeleteSeedLotModal lot={dialog.lot} onClose={close} />}
       {dialog?.kind === 'picker' && (
         <PlantPicker
           unit={unit}