Agent runtime: majordomo in-process, Ollama Cloud config, chat endpoint (#56)

Everything below the run loop already existed. This is the thing that runs a
model.

The build tag is gone, deliberately. internal/agent's doc comment promised two
separations — cmd/pansy not importing the package, and the tool wiring behind
//go:build majordomo — and both have been rewritten rather than left as a stale
aspiration. 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 meant an untagged CI that never compiled the code that matters.
majordomo is a real dependency now, resolved from the Gitea instance as a
pseudo-version with no replace directive, so the Docker build (which has no
sibling checkout) resolves it the same way this machine does. It is stdlib-first
and pure Go, so CGO_ENABLED=0 and the single static binary survive.

A TURN IS ONE CHANGE SET. That is the whole reason acting without a confirmation
prompt is defensible: "empty the garlic bed and plant cucumbers" is one object
edit and a dozen planting inserts, and it has to undo as one action rather than
thirteen. The scope is opened even for a turn that turns out to be a question,
because a change set with no revisions is never written — so asking costs
nothing and history isn't littered with empty entries.

The model spec goes to majordomo.Parse verbatim. That grammar, including
comma-separated failover chains, is majordomo's; re-implementing any of it here
would only mean two places to update when it grows. The key needs a bridge
though: majordomo's ollama-cloud preset reads OLLAMA_API_KEY while pansy (like
gadfly) is configured with OLLAMA_CLOUD_API_KEY, so the provider is registered
explicitly on a private registry rather than depending on ambient environment.

Runs are bounded by a step cap, a timeout and majordomo's loop guards. This is
loop safety, not cost control — pansy is a personal tool and spend caps are
explicitly not a v2 concern. A capped run does NOT fail: it kept whatever it
managed to do, that work is recorded and undoable, and the reply says it stopped
early rather than going silent.

The chat endpoint streams. A turn that clears a bed and replants it makes a
dozen tool calls over tens of seconds, and without streaming that is a long
silence followed by everything at once — which reads as a hang, and defeats a
design that rests on watching the canvas change as it happens.

Conversations persist per (user, garden). Client-held history would be lost on a
refresh, which is exactly when someone reloads to check whether the agent's
change landed. Only the user/assistant TEXT 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. It also keeps majordomo's message shape out of the schema.

An instance with no key starts, serves the app, and doesn't advertise the agent
— the routes aren't registered at all, the same shape as OIDC 404ing when
unconfigured. A configured-but-unresolvable model logs and disables the
assistant rather than refusing to boot: a garden planner that won't start
because of a chat feature is worse than one without chat.

Tool refusals reach the model as tool results it can explain, not 500s. The ACL
story only works if it can narrate the refusal.

Closes #56

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

CLAUDE.md

@@ -113,7 +113,16 @@ 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
-`ollama-cloud/glm-5.2:cloud`), set in Komodo. Model strings pass verbatim to
-`majordomo.Parse`, so a comma-separated spec gives failover for free.
-`majordomo` and `executus` are sibling repos at `../`.
+Agent config: `OLLAMA_CLOUD_API_KEY`, `PANSY_AGENT_MODEL` (default
+`ollama-cloud/glm-5.2:cloud`) and `PANSY_AGENT_ENABLED`, set in Komodo. Model
+strings pass verbatim to `majordomo.Parse`, so a comma-separated spec gives
+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.