diff --git a/docs/plans/M5c2/01-wire-ask-memory.md b/docs/plans/M5c2/01-wire-ask-memory.md
index 13cfacc..ccbdc0b 100644
--- a/docs/plans/M5c2/01-wire-ask-memory.md
+++ b/docs/plans/M5c2/01-wire-ask-memory.md
@@ -12,7 +12,7 @@ agents, a question about one or two of its workspaces (M5c spec, section 9). Thi
 the tool's arguments to `bxcore`, with their shape checks, the way `recall`'s are there
 (`RecallArgs`, its name constant `RECALL`, its limit `MAX_QUERY`, and `RecallArgs::check`). Later
 tasks use them: task 02 (`brokerd` parses the arguments with them), task 04 (`loopd` declares the
-tool), tasks 10 and 11 (`memoryd` answers it).
+tool), tasks 10 and 12 (`memoryd` answers it).
 
 ```json
 {"question":"Who wrote the launch note?","workspaces":["fleet","boxmaker1"]}
diff --git a/docs/plans/M5c2/02-brokerd-ask-memory.md b/docs/plans/M5c2/02-brokerd-ask-memory.md
index ca8a134..329b830 100644
--- a/docs/plans/M5c2/02-brokerd-ask-memory.md
+++ b/docs/plans/M5c2/02-brokerd-ask-memory.md
@@ -25,7 +25,7 @@ section 9):
 
 `brokerd`'s wait for `memoryd` stays 30 s for every memory tool in this task; task 03 gives
 `ask_memory` its own. Nothing yet asks `brokerd` for `ask_memory`: `loopd` declares it in task 04
-and `memoryd` answers it from task 11. Until then, a call reaching `memoryd` is answered
+and `memoryd` answers it from task 12. Until then, a call reaching `memoryd` is answered
 `memoryd runs only recall and memory`, a failed result.
 
 ## Every place that changes
diff --git a/docs/plans/M5c2/10-memoryd-ask-memory.md b/docs/plans/M5c2/10-memoryd-ask-memory.md
index 22f1ecd..8cfa10a 100644
--- a/docs/plans/M5c2/10-memoryd-ask-memory.md
+++ b/docs/plans/M5c2/10-memoryd-ask-memory.md
@@ -10,7 +10,7 @@ is empty; otherwise stop. Never switch branch.
 `ask_memory { question, workspaces }` (task 01) asks Honcho's dialectic about one or two
 workspaces (M5c spec, section 9). `brokerd` sends it to `memoryd` (tasks 02, 03), and `loopd`
 declares it (task 04). This task writes what `memoryd` does with it, as a new module
-`crates/memoryd/src/honcho/ask.rs`, modelled on task 08's `search.rs`. Task 11 wires it into
+`crates/memoryd/src/honcho/ask.rs`, modelled on task 08's `search.rs`. Task 12 wires it into
 `memoryd`'s serving; until then nothing calls it.
 
 - **`ask(readers, args, wait, log) -> Asked`**:
@@ -59,7 +59,7 @@ This is the complete list.
 | `crates/memoryd/src/recall.rs` | `one_line`, and `snippet` calls it (edit R1) |
 | `crates/memoryd/tests/honcho_ask.rs` | new, given |
 | `crates/memoryd/tests/support/honcho.rs` | new version, given |
-| everything else | **no change**: not `serve.rs` (task 11), not `search.rs`, no `Cargo.toml` |
+| everything else | **no change**: not `serve.rs` (task 12), not `search.rs`, no `Cargo.toml` |
 
 ## Files
 
diff --git a/docs/plans/M5c2/12-memoryd-serve-ask-memory.md b/docs/plans/M5c2/12-memoryd-serve-ask-memory.md
new file mode 100644
index 0000000..ca09419
--- /dev/null
+++ b/docs/plans/M5c2/12-memoryd-serve-ask-memory.md
@@ -0,0 +1,276 @@
+# M5c-2 task 12: `memoryd` serves `ask_memory`, never under the state lock
+
+**Branch:** `m5c2`. Check it: `git branch --show-current` prints `m5c2` and `git status --short`
+is empty; otherwise stop. Never switch branch.
+**Commit subject:** `memoryd: ask_memory served beside recall and memory, outside the lock`
+**Log row:** the Task cell is `M5c2/12-memoryd-serve-ask-memory`.
+
+## Goal
+
+The last piece of `ask_memory` (M5c spec, section 9). `brokerd` decides it and sends it to
+`memoryd` (tasks 02, 03), `loopd` declares it (task 04), and task 10 wrote what `memoryd` does
+with it (`honcho/ask.rs`: `ask`, then `answer`). This task makes `memoryd`'s `call` answer it.
+
+- **`call`** gets a third arm, `ask_memory`, which **never takes the state lock**: its chats may
+  take 150 s, and nothing else may wait behind them. `memory` keeps the lock for the whole call,
+  and `recall` for its local part (task 09), as before.
+- **Its arguments are checked again**, as `recall`'s are (its `recall::local` calls
+  `RecallArgs::check` first): `AskMemoryArgs` is decoded from the call's arguments (an error is
+  `ask_memory's arguments: {serde's error}`), then `check()`, whose error is `bxcore`'s sentence.
+  Either is a failed result, as for `recall`. `brokerd` has checked them already; `memoryd` does
+  not rely on that.
+- **With `[honcho]`**: `ask::ask(&reading.readers, &args, ask::CHAT_WAIT, &self.log)`, then
+  `ask::answer`, which becomes a `ToolResponse::Result` with its text and its label, as
+  `recall`'s answer does. An unknown name or a question holding a secret is `answer`'s sentence,
+  a result too.
+- **Without `[honcho]`**: a result, not an error, labelled `private` and trusted, which the model
+  reads and moves on from: `ask_memory: Honcho is not configured for this agent; recall searches
+  its own memory` (`ask::NOT_CONFIGURED`).
+- **Another tool**: the sentence becomes `memoryd runs only recall, memory and ask_memory`. No
+  given test or fixture pins the old one.
+- **No new fail-closed state.** A workspace that does not answer is an `unavailable` line in a
+  result, not a stop, and `memoryd` without `[honcho]` answers with a sentence. No runbook entry
+  and no pointer is needed. `bxctl` has no `ask_memory` command, and its usage does not change.
+
+`serve.rs` is 456 lines after this task (433 after task 11).
+
+## Every place that changes
+
+This is the complete list.
+
+| Place | What happens there |
+|---|---|
+| `crates/memoryd/src/honcho/ask.rs` | `NOT_CONFIGURED` (edit A1) |
+| `crates/memoryd/src/serve.rs` | two `use` lines; `call`'s third arm and its sentence; `ask_memory` (edits E1 to E4) |
+| `crates/memoryd/tests/honcho_ask_serve.rs` | new, given |
+| everything else | **no change**: not `search.rs`, not the runbook, not `bxctl`, no `Cargo.toml` |
+
+## Files
+
+- Copy, from `docs/plans/M5c2/files/` (the same path under it): the new test
+  `crates/memoryd/tests/honcho_ask_serve.rs`.
+- Modify: `crates/memoryd/src/honcho/ask.rs`, `crates/memoryd/src/serve.rs`,
+  `docs/implementer-log.md`.
+- Do not touch: any other file.
+
+## Facts you need
+
+- **`serve.rs` today**: `call` matches the tool's name; `recall` is `self.recall(&call)` (task
+  09); `memory` is `self.memory(&self.lock(), &call)`; each returns `Result<Recalled, String>`,
+  turned into a result or a failed response below the `match`. `self.reading` is
+  `Option<search::Reading>`, `Some` with `[honcho]` (task 09); its `readers` is an
+  `Arc<Readers>`, and `&reading.readers` passes as `&Readers`.
+- **From task 10**: `ask::ask(&Readers, &AskMemoryArgs, Duration, &Log) -> Asked`,
+  `ask::answer(Asked) -> Recalled`, `ask::CHAT_WAIT` (150 s). From task 01:
+  `bxcore::AskMemoryArgs` with `check(&self) -> Result<(), String>`, and
+  `bxcore::memory::ASK_MEMORY` (`"ask_memory"`).
+- **The given test** `honcho_ask_serve.rs` (6 tests; well under a second), through `memoryd`'s
+  `brokerd` socket, against the fake Honcho:
+  - `own`'s answer, `[1] memory · own · private`, trusted; a `fleet` answer, `memory-tainted`,
+    the result untrusted (T58, end to end);
+  - while every chat hangs, a `memory` call is answered within 2 s and the `ask_memory` is still
+    waiting; then the fake Honcho is stopped, which ends the chat, and the answer is
+    `own: unavailable`. (So the test does not wait the 150 s.)
+  - without `[honcho]`, the sentence above, private and trusted;
+  - bad arguments: an empty question and three workspaces with `bxcore`'s sentences, an unknown
+    field with `ask_memory's arguments: unknown field `reasoning``, and nothing sent;
+  - an unknown name's sentence as the result, nothing sent;
+  - an unknown tool's new sentence.
+- The items the edits use. This table is complete.
+
+  | Item | Where |
+  |---|---|
+  | `serde_json::from_str::<AskMemoryArgs>`, `AskMemoryArgs::check` | E4, as `recall`'s arm |
+  | `ask::ask`, `ask::answer`, `ask::CHAT_WAIT`, `ask::NOT_CONFIGURED` | E4 |
+  | `Recalled { text, class, untrusted }`, `DataClass::Private` | E4 |
+
+## The edits, exactly
+
+Nothing else in these files changes. Each quoted "before" block occurs exactly once in its file
+when its turn comes (make them in order).
+
+### `crates/memoryd/src/honcho/ask.rs`
+
+**A1.** The line (its spaces are checked: the sentence is compared letter for letter)
+
+```rust
+/// The text of an answer with no content.
+```
+
+becomes
+
+```rust
+/// The answer without `[honcho]`: a result, not an error, so that the model reads it and moves on.
+pub const NOT_CONFIGURED: &str =
+    "ask_memory: Honcho is not configured for this agent; recall searches its own memory";
+
+/// The text of an answer with no content.
+```
+
+### `crates/memoryd/src/serve.rs`
+
+**E1.** Add one line. The lines
+
+```rust
+use std::time::Duration;
+
+use bxcore::{
+```
+
+become
+
+```rust
+use std::time::Duration;
+
+use bxcore::AskMemoryArgs;
+use bxcore::{
+```
+
+**E2.** Add one line. The line
+
+```rust
+use crate::edit::{self, Context};
+```
+
+becomes
+
+```rust
+use crate::edit::{self, Context};
+use crate::honcho::ask;
+```
+
+**E3.** The lines (its spaces are checked: the new sentence is compared letter for letter)
+
+```rust
+    /// A decided call from `brokerd`: `recall` or `memory`. `memory` runs under the one lock;
+    /// `recall` takes it for the local index only (`recall`). `Failed` carries the sentence for
+    /// the model.
+    fn call(&self, call: MemoryCall) -> ToolResponse {
+        let result = match call.request.tool.as_str() {
+            bxcore::memory::RECALL => self.recall(&call),
+            bxcore::memory::MEMORY => self.memory(&self.lock(), &call),
+            _ => {
+                return ToolResponse::Failed {
+                    message: "memoryd runs only recall and memory".to_string(),
+                };
+            }
+        };
+```
+
+become
+
+```rust
+    /// A decided call from `brokerd`: `recall`, `memory` or `ask_memory`. `memory` runs under
+    /// the one lock; `recall` takes it for the local index only (`recall`); `ask_memory` never
+    /// takes it. `Failed` carries the sentence for the model.
+    fn call(&self, call: MemoryCall) -> ToolResponse {
+        let result = match call.request.tool.as_str() {
+            bxcore::memory::RECALL => self.recall(&call),
+            bxcore::memory::MEMORY => self.memory(&self.lock(), &call),
+            bxcore::memory::ASK_MEMORY => self.ask_memory(&call),
+            _ => {
+                return ToolResponse::Failed {
+                    message: "memoryd runs only recall, memory and ask_memory".to_string(),
+                };
+            }
+        };
+```
+
+**E4.** The line
+
+```rust
+    /// `memory`: refused, staged for review, or applied and journalled; then what it appended to
+```
+
+becomes
+
+```rust
+    /// `ask_memory` (M5c spec, section 9): the workspaces named, asked by Honcho's chat, never
+    /// under the lock. Its arguments are checked again, as `recall`'s are. Without `[honcho]`, a
+    /// sentence that says so, labelled private and trusted.
+    fn ask_memory(&self, call: &MemoryCall) -> Result<Recalled, String> {
+        let args: AskMemoryArgs = match serde_json::from_str(&call.request.arguments) {
+            Ok(args) => args,
+            Err(e) => return Err(format!("ask_memory's arguments: {e}")),
+        };
+        args.check()?;
+        let Some(reading) = &self.reading else {
+            return Ok(Recalled {
+                text: ask::NOT_CONFIGURED.to_string(),
+                class: DataClass::Private,
+                untrusted: false,
+            });
+        };
+        let asked = ask::ask(&reading.readers, &args, ask::CHAT_WAIT, &self.log);
+        Ok(ask::answer(asked))
+    }
+
+    /// `memory`: refused, staged for review, or applied and journalled; then what it appended to
+```
+
+## Steps
+
+- [ ] **1. Copy the given test.** From the repository root, one command:
+
+  ```sh
+  cp docs/plans/M5c2/files/crates/memoryd/tests/honcho_ask_serve.rs crates/memoryd/tests/
+  ```
+
+- [ ] **2. See it fail.** `cargo test --no-fail-fast -p memoryd --test honcho_ask_serve`, with a
+  shell timeout of 600000 ms: it compiles, and all 6 tests fail, since `memoryd` answers every
+  `ask_memory` with `memoryd runs only recall and memory` (the hang test after its 10 s
+  deadline for the chat, which is never sent).
+- [ ] **3. The edits.** Make edits A1 and E1 to E4, in order. `cargo check -p memoryd` prints no
+  error and no warning.
+- [ ] **4. The tests.** With a shell timeout of 600000 ms, every test passes: 6 in
+  `honcho_ask_serve`, and as before 10 in `honcho_ask`, 4 in `honcho_recall_serve`, 4 in
+  `serve_admin` and 8 in `serve`:
+
+  ```sh
+  cargo test -p memoryd --test honcho_ask_serve --test honcho_ask --test honcho_recall_serve \
+    --test serve_admin --test serve
+  ```
+- [ ] **5. Check.** Two commands:
+  - `git diff --stat` lists exactly `crates/memoryd/src/honcho/ask.rs` and
+    `crates/memoryd/src/serve.rs`.
+  - `wc -l crates/memoryd/src/serve.rs` prints 456.
+- [ ] **6. Run the gate.** `cargo fmt --all`, then `make gate`, with a shell timeout of 600000 ms.
+  Expected last line: `gate: ok`. The test count is the passed total of `cargo test --workspace`
+  plus one, for the ignored `end_to_end` test that the gate runs on its own: **1454** after this
+  task, 1448 before it; the 6 new ones are the tests of `honcho_ask_serve.rs`. To count, add up
+  the `N passed` of every `test result:` line the gate's `cargo test --workspace` printed, and
+  add 1. Never run the gate again only to count.
+- [ ] **7. Log and commit.** Add your row to `docs/implementer-log.md`; its Task cell is
+  `M5c2/12-memoryd-serve-ask-memory`. Stage with
+  `git add crates/memoryd docs/implementer-log.md Cargo.lock`, then commit as `AGENTS.md` says.
+  `Cargo.lock` does not change in this task; the `git add` is harmless.
+
+## Done when
+
+- `make gate` prints `gate: ok` with 1454 tests.
+- `git diff HEAD~1 --stat` lists only `ask.rs`, `serve.rs`, `honcho_ask_serve.rs` and
+  `docs/implementer-log.md`.
+
+## Stop and report if
+
+- The branch check at the top fails.
+- A "before" block is not in its file exactly as shown when its turn comes, or is there more
+  than once.
+- Step 2 shows a different result: a compile error, or a test passing.
+- `cargo check` in step 3 prints an error or a warning. Quote it, and stop.
+- A test fails in step 4. Do not change a test: stop, and give the failing tests' names and
+  their messages.
+- The fix seems to need a change anywhere else: `ask.rs` beyond A1, `search.rs`, the runbook,
+  `bxctl`, a new configuration key. It does not; stop and say why you think so.
+- A test outside the given file fails in the gate: check once whether it fails without your
+  change (`git stash -u`, run it, `git stash pop`), then stop and report both results.
+- The gate passes with a count other than 1454.
+- A comment in an edit does not fit the code under it. Quote it and stop.
+
+## What the given tests pin
+
+Each of these changes to the finished code makes at least one given test fail (9 tried, all
+caught): `ask_memory` under the state lock; not routed at all; its arguments not checked, or a
+decoding error without `ask_memory's arguments: `; without `[honcho]`, an error instead of a
+result, a result labelled untrusted, or other words; the unknown tool's old sentence; the
+answer's label dropped.
diff --git a/docs/plans/M5c2/README.md b/docs/plans/M5c2/README.md
index d38ad96..6ee8465 100644
--- a/docs/plans/M5c2/README.md
+++ b/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
diff --git a/docs/plans/M5c2/files/crates/memoryd/tests/honcho_ask_serve.rs b/docs/plans/M5c2/files/crates/memoryd/tests/honcho_ask_serve.rs
new file mode 100644
index 0000000..a2995d4
--- /dev/null
+++ b/docs/plans/M5c2/files/crates/memoryd/tests/honcho_ask_serve.rs
@@ -0,0 +1,232 @@
+//! `memoryd` answering `ask_memory` through its `brokerd` socket (M5c spec, section 9), against a
+//! fake Honcho: `own`'s answer with its labels, a fleet answer making the result untrusted (T58);
+//! a chat that hangs holds up no memory call, because `ask_memory` never takes the state lock;
+//! without `[honcho]`, a sentence that says so; bad arguments refused with `bxcore`'s sentences;
+//! an unknown name's sentence as the result; an unknown tool refused. Every wait has a deadline.
+//! Do not edit.
+
+#[path = "support/honcho.rs"]
+mod honcho;
+#[path = "support/tmp.rs"]
+mod tmp;
+
+use std::os::unix::net::UnixStream;
+use std::path::Path;
+use std::sync::Arc;
+use std::time::{Duration, Instant};
+
+use bxcore::{
+    CallId, DataClass, Envelope, MemoryCall, Message, SessionId, ToolRequest, ToolResponse,
+    read_frame, write_frame,
+};
+use honcho::{FakeHoncho, Mode};
+use memoryd::config::Config;
+use memoryd::serve;
+use tmp::TempDir;
+
+const QUESTION: &str = r#"{"question":"What does the owner drink in the afternoon?"}"#;
+
+/// `[honcho]` for `url`, reading `boxmaker1`'s workspace.
+fn section(url: &str) -> String {
+    format!(
+        "[honcho]\nurl = \"{url}\"\nagent = \"boxmaker0\"\nowner = \"kyle\"\ntrusted = \"boxmaker0-trusted\"\nuntrusted = \"boxmaker0-untrusted\"\nfleet = \"fleet\"\n[[honcho.read]]\nagent = \"boxmaker1\"\nworkspace = \"boxmaker1-trusted\"\n"
+    )
+}
+
+struct Home {
+    config: Config,
+    /// Removed when the test ends; declared last, so it outlives what writes into it (T44).
+    _dir: TempDir,
+}
+
+impl Home {
+    /// A `memoryd` serving on a thread, with `[honcho]` at `url` when there is one.
+    fn serve(tag: &str, url: Option<&str>) -> Home {
+        let dir = TempDir::new(tag);
+        let soul = dir.write("etc/soul.md", "You are Boxmaker.\n");
+        let text = format!(
+            "[paths]\nhome = \"{}\"\n[memory]\nsoul_starter = \"{}\"\n{}",
+            dir.path().display(),
+            soul.display(),
+            url.map(section).unwrap_or_default()
+        );
+        let config = Config::parse(&text).unwrap();
+        let log: serve::Log = Arc::new(|_: &str| {});
+        let running = serve::start(config.clone(), log).unwrap();
+        std::thread::spawn(move || running.run());
+        Home { config, _dir: dir }
+    }
+}
+
+/// One call on `brokerd`'s socket and its answer, within 20 s; how long it took.
+fn call(socket: &Path, tool: &str, arguments: &str) -> (ToolResponse, Duration) {
+    let started = Instant::now();
+    let mut stream = UnixStream::connect(socket).unwrap();
+    stream
+        .set_read_timeout(Some(Duration::from_secs(20)))
+        .unwrap();
+    let env = Envelope {
+        v: 1,
+        id: 5,
+        r#final: true,
+        msg: Message::MemoryCall(MemoryCall {
+            request: ToolRequest {
+                session: SessionId::new("mm-now").unwrap(),
+                call: CallId(5),
+                tool: tool.to_string(),
+                arguments: arguments.to_string(),
+            },
+            taint: DataClass::Private,
+            untrusted: false,
+        }),
+    };
+    write_frame(&mut stream, &env).unwrap();
+    match read_frame(&mut stream).unwrap().msg {
+        Message::ToolResponse(response) => (response, started.elapsed()),
+        other => panic!("{other:?}"),
+    }
+}
+
+fn result(response: ToolResponse) -> (String, DataClass, bool) {
+    match response {
+        ToolResponse::Result {
+            content,
+            class,
+            untrusted,
+            truncated,
+        } => {
+            assert!(!truncated);
+            (content, class, untrusted)
+        }
+        other => panic!("{other:?}"),
+    }
+}
+
+fn failed(response: ToolResponse) -> String {
+    match response {
+        ToolResponse::Failed { message } => message,
+        other => panic!("{other:?}"),
+    }
+}
+
+/// `own`'s answer, trusted; a fleet answer, untrusted, as `brokerd` will label the session
+/// (T58, end to end).
+#[test]
+fn each_answer_comes_back_with_its_workspaces_label() {
+    let fake = FakeHoncho::start();
+    let home = Home::serve("ask-serve-labels", Some(&fake.url));
+    let socket = home.config.broker_socket();
+    let (content, class, untrusted) = result(call(&socket, "ask_memory", QUESTION).0);
+    assert!(
+        content.starts_with("[1] memory · own · private\n  Based on what I found in memory, "),
+        "{content}"
+    );
+    assert_eq!((class, untrusted), (DataClass::Private, false));
+    let fleet = r#"{"question":"What does the owner drink?","workspaces":["fleet"]}"#;
+    let (content, class, untrusted) = result(call(&socket, "ask_memory", fleet).0);
+    assert!(
+        content.starts_with("[1] memory-tainted · fleet · private\n  "),
+        "{content}"
+    );
+    assert_eq!((class, untrusted), (DataClass::Private, true));
+}
+
+/// `ask_memory` never takes the state lock: while its chat hangs, a memory call is answered at
+/// once. Stopping the fake Honcho ends the chat, and the answer says the workspace was
+/// unavailable.
+#[test]
+fn a_hanging_chat_holds_up_no_memory_call() {
+    let fake = FakeHoncho::start();
+    fake.set(Mode::Hang);
+    let home = Home::serve("ask-serve-hang", Some(&fake.url));
+    let socket = home.config.broker_socket();
+    let for_ask = socket.clone();
+    let asking = std::thread::spawn(move || call(&for_ask, "ask_memory", QUESTION));
+    let deadline = Instant::now() + Duration::from_secs(10);
+    while !fake.requests().iter().any(|r| r.path.ends_with("/chat")) {
+        assert!(Instant::now() < deadline, "the chat was never sent");
+        std::thread::sleep(Duration::from_millis(10));
+    }
+    let note = r#"{"action":"note","text":"tea is kept in the blue tin"}"#;
+    let (answer, took) = call(&socket, "memory", note);
+    assert!(matches!(answer, ToolResponse::Result { .. }), "{answer:?}");
+    assert!(
+        took < Duration::from_secs(2),
+        "the memory call waited {took:?}"
+    );
+    assert!(!asking.is_finished(), "the chat is still waiting");
+    drop(fake);
+    let (answer, _) = asking.join().unwrap();
+    let (content, class, untrusted) = result(answer);
+    assert_eq!(content, "own: unavailable");
+    assert_eq!((class, untrusted), (DataClass::Private, false));
+}
+
+/// Without `[honcho]`, a result the model reads and moves on from, private and trusted.
+#[test]
+fn without_honcho_the_answer_says_so() {
+    let home = Home::serve("ask-serve-off", None);
+    let (content, class, untrusted) =
+        result(call(&home.config.broker_socket(), "ask_memory", QUESTION).0);
+    assert_eq!(
+        content,
+        "ask_memory: Honcho is not configured for this agent; recall searches its own memory"
+    );
+    assert_eq!((class, untrusted), (DataClass::Private, false));
+}
+
+/// `memoryd` checks the arguments again, as it does `recall`'s: a refusal is `bxcore`'s sentence.
+#[test]
+fn bad_arguments_are_refused_with_the_checks_sentences() {
+    let fake = FakeHoncho::start();
+    let home = Home::serve("ask-serve-bad", Some(&fake.url));
+    let socket = home.config.broker_socket();
+    assert_eq!(
+        failed(call(&socket, "ask_memory", r#"{"question":"  "}"#).0),
+        "question is empty; write the question to ask"
+    );
+    let three = r#"{"question":"q","workspaces":["own","untrusted","fleet"]}"#;
+    assert_eq!(
+        failed(call(&socket, "ask_memory", three).0),
+        "workspaces names 3, over the limit of 2; ask about the others in another call"
+    );
+    let unknown = failed(
+        call(
+            &socket,
+            "ask_memory",
+            r#"{"question":"q","reasoning":"low"}"#,
+        )
+        .0,
+    );
+    assert!(
+        unknown.starts_with("ask_memory's arguments: unknown field `reasoning`"),
+        "{unknown}"
+    );
+    assert_eq!(fake.requests().len(), 0, "nothing was sent");
+}
+
+/// A name that is none of this agent's workspaces: the sentence listing the names it may use,
+/// as the result, and nothing sent.
+#[test]
+fn an_unknown_names_sentence_is_the_result() {
+    let fake = FakeHoncho::start();
+    let home = Home::serve("ask-serve-unknown", Some(&fake.url));
+    let asked = r#"{"question":"q","workspaces":["boxmaker9"]}"#;
+    let (content, class, untrusted) =
+        result(call(&home.config.broker_socket(), "ask_memory", asked).0);
+    assert_eq!(
+        content,
+        "no workspace is named boxmaker9; ask own, untrusted, fleet or boxmaker1"
+    );
+    assert_eq!((class, untrusted), (DataClass::Private, false));
+    assert_eq!(fake.requests().len(), 0);
+}
+
+#[test]
+fn an_unknown_tool_is_refused() {
+    let home = Home::serve("ask-serve-tool", None);
+    assert_eq!(
+        failed(call(&home.config.broker_socket(), "forget", "{}").0),
+        "memoryd runs only recall, memory and ask_memory"
+    );
+}