M5c-2 plan: task 12, memoryd serves ask_memory

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

docs/plans/M5c2/README.md

@@ -84,7 +84,7 @@ Honcho sources and chats outside its state lock, and answers `ask_memory`.
 | 09 | `memoryd`: `recall` with `[honcho]` runs the local part under the state lock and the Honcho part outside it; the readers taken at start; without `[honcho]`, `recall` as before | memoryd |
 | 10 | `memoryd`: `ask_memory`: workspace names checked against `[honcho]`, both chats at once, each answer tagged and capped, labels, `<workspace>: unavailable`; a question holding a secret sends nothing | memoryd |
 | 11 | `memoryd`, making room: `reindex` and `admin` move unchanged from `serve.rs` to `serve/admin.rs`, with tests for four of their behaviours no test pinned | memoryd |
-| 12 | `memoryd` serves `ask_memory` beside `recall` and `memory`, outside the lock; `bxctl`'s usage and the runbook where a new message needs a pointer | memoryd, bxctl |
+| 12 | `memoryd` serves `ask_memory` beside `recall` and `memory`, never under the state lock; its arguments checked again; without `[honcho]`, a sentence as the result; no new fail-closed state, so no runbook entry, and `bxctl` unchanged | memoryd |
 
 After task 12, the design model runs the M5c-2 device check (spec 13) on straylight, rift and the
 owner's Mattermost: a second `memoryd` under its own name writes a fleet note that `recall` finds,
@@ -111,6 +111,7 @@ The gate count is the passed total of `cargo test --workspace` plus one, for the
 | 09 | 1434 | 8, 8 |
 | 10 | 1444 | 18, 18 |
 | 11 | 1448 | 8, 8 |
+| 12 | 1454 | 9, 9 |
 
 **A flaky test, fixed before the run:** `bxctl`'s `chat_approvals` test
 `json_prints_only_json_and_never_asks_brokerd` failed once in 5 loaded runs of the whole workspace