agents: remove send(operator) and the operator inbox; alert on turn failures

Agents reach the operator over matrix now (#5115). A `send` to
`operator` is refused, by the broker and by the MCP allow-list check,
with an error that names the matrix MCP tools. The dashboard's Y3R C4LL
tab goes with it: the operator inbox, `GET /api/operator-inbox`,
`Broker::unread_for_recipient`, and the browser notifications that only
ever fired on operator-bound messages.

The harness no longer posts turn failures and plugin-install failures
to the operator inbox. Both are already logged at warn; a new Grafana
rule, `hh-agent-turn-failed`, fires per agent on the harness's
`turn failed` line.

Dashboard-to-agent messaging (op-send, the agent web UI's message box,
mark-all-read for agent inboxes) is unchanged.

Decisions per mara on #5115: q1 a, q2 a plus a grafana alert, q3 keep
dashboard-to-agent messaging and leave swarm-level code alone.

docs/turn-loop/README.md

@@ -126,9 +126,7 @@ user-configured MCP server can push its own todos the same way. See
 what each built-in todo producer watches and how the store + `get_loose_ends`
 merge work.
 
-Plugin install failures aren't fatal: each entry comes back as a
-human-readable failure string that gets routed via
-`Surface::send_to_operator` to the operator.
+Plugin install failures aren't fatal: the harness logs each at `warn` and skips it.
 
 ### Turn outcomes
 
@@ -144,7 +142,7 @@ else a `TurnError`) drives the post-claude branch:
 | `Err(SessionNotFound)` | resume + create self-heal both missed ("shouldn't happen"); requeue inflight so the next turn creates fresh — no status park, message not dropped |
 | `Err(ApiStall)` | idle watchdog sent claude SIGINT after `HIVE_TURN_IDLE_SECS` (default 600) of output silence and claude exited; sleep `HIVE_STALL_SLEEP_SECS` (default 60), requeue inflight, status back to `online` |
 | `Err(AgentStall(note))` | the same, for an ACP agent: after `HIVE_TURN_IDLE_SECS` with no `session/update` the harness sent the agent `session/cancel`, and SIGINT if it ignored that; `note` says which |
-| `Err(Failed(err))` | route `[system] \`<qualified-label>\` claude turn failed:\n<err>` to `operator` via `send_to_operator` |
+| `Err(Failed(err))` | the harness logs it at `warn` as `turn failed`, the line the Grafana alert rule `hh-agent-turn-failed` (`nix/host-modules/swarm-grafana.nix`) fires on |
 
 `ApiStall` catches an Anthropic API stall — a multi-retry connection storm where
 the stream goes silent for minutes. On `claude` the idle watchdog lives in

docs/turn-loop/mcp.md

@@ -32,14 +32,13 @@ is opt-in via the P3RM1SS10NS tab.
 **Messaging** (`messaging` group): `send(to, body, in_reply_to?)`,
 `recv(max?)`, `ack_until(up_to)`.
 
-- `send` — message a peer (logical name) or the operator
-  (`to: "operator"`). Optional `in_reply_to: i64` links the
-  message to a prior id for thread rendering. Per-agent
-  `services.hyperhive.agent.allowedRecipients` (default: empty = unrestricted) limits
-  which names `send` accepts — useful for sandboxing: set
-  `[ "operator" ]` to restrict a sub-agent to operator messages only.
-  The operator stays reachable regardless of this list, so an agent can
-  always report a block.
+- `send` — message a peer on this hive (logical name). Optional
+  `in_reply_to: i64` links the message to a prior id for thread
+  rendering. Per-agent `services.hyperhive.agent.allowedRecipients`
+  (default: empty = unrestricted) limits which names `send` accepts —
+  useful for sandboxing. The broker refuses `to: "operator"` with an error
+  that points at the matrix MCP tools: agents reach the operator over
+  matrix ([matrix](../tools/matrix.md)).
 - `recv` — drain inbox. Always an immediate peek, never blocks. `max`
   (default 1, cap 5) drains up to N rows. `recv` prefixes each returned row
   with `[msg #<id>]` (broker row id; note the highest id seen, then pass