M5c-1 plan: task 11, the Honcho worker that sends turns

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-09-28 08:45:55 -07:00
co-authored by Claude Opus 5.5
parent a359f34a73
commit 67ddda514b
11 changed files with 2291 additions and 5 deletions
+3 -2
View File
@@ -114,7 +114,8 @@ This is the complete list.
- Copy, from `docs/plans/M5c1/files/` (the same path under it):
- new tests: `crates/memoryd/tests/honcho_state.rs`, `crates/memoryd/tests/honcho_turns.rs`,
`crates/memoryd/tests/honcho_serve.rs`
and `crates/memoryd/tests/honcho_serve.rs` from `honcho_serve.rs-task09` (this task's
version; task 11 gives a later one)
- new test support: `crates/memoryd/tests/support/brokerd.rs` (a fake `brokerd` state
socket), `crates/memoryd/tests/support/turns.rs` (logs of turns with speakers)
- the skeletons `crates/memoryd/src/honcho/state.rs` and `crates/memoryd/src/honcho/turns.rs`
@@ -529,7 +530,7 @@ message, so a turn sent twice stays twice.
```sh
cp docs/plans/M5c1/files/crates/memoryd/tests/honcho_state.rs crates/memoryd/tests/
cp docs/plans/M5c1/files/crates/memoryd/tests/honcho_turns.rs crates/memoryd/tests/
cp docs/plans/M5c1/files/crates/memoryd/tests/honcho_serve.rs crates/memoryd/tests/
cp docs/plans/M5c1/files/crates/memoryd/tests/honcho_serve.rs-task09 crates/memoryd/tests/honcho_serve.rs
cp docs/plans/M5c1/files/crates/memoryd/tests/support/brokerd.rs crates/memoryd/tests/support/
cp docs/plans/M5c1/files/crates/memoryd/tests/support/turns.rs crates/memoryd/tests/support/
```
+624
View File
@@ -0,0 +1,624 @@
# M5c-1 task 11: `memoryd`'s Honcho worker sends decided turns
**Branch:** `m5c1` (run `git switch m5c1`; `git status --short` must be empty, otherwise stop)
**Commit subject:** `memoryd: the Honcho worker sends decided turns, waits out outages, retries undecided turns`
**Log row:** the Task cell is `M5c1/11-memoryd-honcho-worker`.
## Goal
Task 09 decides each finished turn into the ledger; nothing sends it yet. This task adds the
worker that does (M5c spec, section 5): one thread in `memoryd`, started with `[honcho]` only.
- **Start** (`serve::start`, `[honcho]` only), before anything under the home is made and before
any socket is bound: the ledger is read through (as in task 09), the sessions it knows wait
again (`TurnSync::resume`, below), and the three clients are built (task 10) with their keys.
A key that cannot be read stops `memoryd`: exit 1, `bxcore::secrets`' own lines with the
pointer `secret-unavailable`, no socket bound. The key files' plaintext warnings are logged.
After the sockets are bound the worker's thread starts.
- **Sending**, oldest first, `Action::Turn` items only: the other actions (conclusions, fleet
messages, retractions) wait in the outbox untouched, for task 13. For each turn the worker
reads its records from `loopd`'s log again, takes the speaker's text and the final reply (task
08's `user_text` and `final_reply`, made public here), neutralises both
(`bxcore::sanitize::neutralise`), cuts each into parts of at most 25,000 characters, makes sure
of its Honcho session (`honcho_session` and `ensure_session`, task 10) and adds every part of
both as one batch, the speaker's first, then the agent's. The ids Honcho gives go in a `Sent`
record. A turn the log no longer holds (a damaged log, a missing turn or reply) is marked
`Failed` with kind `log` and no status; one that needs more than 100 messages, with kind
`too-long`.
- **Honcho unreachable** (a connection error, a timeout, a 5xx): wait, then try the same turn
again: 5 s, 10 s, 20 s and so on up to 10 minutes. The outage is logged once when it starts
and once when it ends (the first answer of any kind), not at every try.
- **Refused** (another 4xx, or a body that cannot be read): the turn is marked `Failed` with the
error's kind and status, logged once, and the next turn goes on.
- **Key refused** (401, 403): nothing more is sent to that workspace until `memoryd` restarts,
logged once; its turns stay waiting, and the other workspaces go on.
- **Nothing to send:** the worker walks task 09's waiting sessions (`TurnSync::retry`: the
"worker's retry" of spec 5, step 3), and so it does right after an outage ends. Then it sleeps
30 s, or until the next `SessionUpdated` wakes it.
- **A ledger that cannot be written** stops the worker until `memoryd` restarts (logged once): a
send whose `Sent` line could not be written would otherwise be sent again at every step.
**What a restart knows.** The ledger says what was sent: nothing is sent twice (unless a crash
falls between a send and its `Sent` line). The sessions task 09 was waiting on are rebuilt from
the ledger: each session with a decided turn waits again at the turns its log holds, and the
next walk decides what is left (never a turn still running: task 09's `decidable`). A session
with no decided turn is not scanned: it is picked up at its next `SessionUpdated`. So a session
first reported while `brokerd` was down, and never again before a restart, waits until its next
turn. (Scanning every session would decide old history; task 15 adds the cutoff for turns from
before Honcho was turned on.)
`memoryd` has no shutdown: it runs until its process ends, and the worker with it. Its waits are
plain sleeps; only the idle sleep is woken early, by a `SessionUpdated`.
## Interfaces
In `crates/memoryd/src/honcho/worker.rs` (the module `memoryd::honcho::worker`):
```rust
pub const MAX_PART: usize = 25_000;
pub const MAX_BATCH: usize = 100;
pub const UNREACHABLE: &str = "see docs/runbook.md#honcho-unreachable";
pub const SEND_REFUSED: &str = "see docs/runbook.md#honcho-send-refused";
pub const KEY_REFUSED: &str = "see docs/runbook.md#honcho-key-refused";
pub const LOG_DAMAGED: &str = "see docs/runbook.md#session-log-damaged";
pub struct Tuning { pub backoff: Duration, pub backoff_max: Duration, pub idle: Duration }
// Tuning::DEFAULT = 5 s, 600 s, 30 s
pub struct Wake { /* private */ } // Default; notify(&self); wait(&self, timeout)
pub enum Step { Done, Backoff(Duration), Idle, Stopped }
pub type AskBox = Box<dyn Fn(&SessionId) -> Result<SessionStateReply, String> + Send>;
pub struct Worker { /* private */ }
impl Worker {
pub fn new(sync: Arc<Mutex<TurnSync>>, clients: Clients, wake: Arc<Wake>, ask: AskBox,
log: Log, tuning: Tuning, agent: &str) -> Worker;
pub fn run(self);
pub fn step(&mut self) -> Step;
}
pub fn parts(text: &str) -> Vec<String>;
pub fn read_turn(path: &Path, turn: u64) -> Option<(String, String)>;
pub fn batch(text: &str, reply: &str, speaker: &str, agent: &str, session: &SessionId,
turn: u64) -> Vec<MessageCreate>;
pub struct Opened { pub sync: Arc<Mutex<TurnSync>>, /* private */ }
pub fn open(config: &Config, honcho: &HonchoConfig, log: &Log) -> Result<Opened, StartError>;
pub fn spawn(opened: Opened, config: &Config, wake: Arc<Wake>, log: Log) -> Result<(), String>;
```
`run` is `step` in a loop: `Backoff(d)` sleeps `d`, `Idle` sleeps on the `Wake` for
`tuning.idle`, `Stopped` returns. The tests call `step` directly, with short waits, and see each
`Backoff` it returns.
In `crates/memoryd/src/honcho/turns.rs`, `TurnSync` gains `sessions(&self) -> &Path`,
`resume(&mut self)`, `append(&mut self, Record) -> Result<(), LedgerError>` and
`retry(&mut self, ask, now, log)` (the walk `updated` did, now also callable alone). In
`serve.rs`, `StartError` gains `Secret(String)`, and `Memoryd` holds the `TurnSync` in an `Arc`
shared with the worker, and a `Wake` it notifies after each `SessionUpdated`'s decisions.
## The batch
Fixture `08-messages-add-batch.json` is the shape: `POST
/v3/workspaces/<workspace>/sessions/<honcho session>/messages` with
```json
{"messages": [
{"content": "<part>", "peer_id": "<speaker>", "metadata": {"agent": "<agent>", "boxmaker_session": "<id>", "turn": 1}},
{"content": "<part>", "peer_id": "<agent>", "metadata": {"agent": "<agent>", "boxmaker_session": "<id>", "turn": 1}}
]}
```
answered 201 with the messages made, whose `id`s go in the `Sent` record in order. Fixtures 09
and 10: a message of 25,000 characters is taken, one of 25,001 refused (422). Characters, not
bytes: `parts` cuts by `char`. The number of messages in one batch Honcho takes is not in the
recorded responses; `MAX_BATCH` is 100, `roncho`'s limit for a batch of conclusions, and a turn
that needs more (over 2,500,000 characters) is marked failed without a request.
## The lines the worker logs
| When | The line |
|---|---|
| an outage starts | `memoryd: <error>; sends wait and are retried; see docs/runbook.md#honcho-unreachable` |
| it ends | `memoryd: Honcho answers again; waiting sends go on` |
| a send is refused | `memoryd: turn <n> of session <id> was not sent: <error>; it is marked failed; see docs/runbook.md#honcho-send-refused` |
| a turn cannot be read | `memoryd: turn <n> of session <id> cannot be sent (log); it is marked failed; see docs/runbook.md#session-log-damaged` |
| a turn is too long | the same with `(too-long)` and `see docs/runbook.md#honcho-send-refused` |
| a key is refused | `memoryd: Honcho refused the key of workspace <name> (HTTP <status>); nothing more is sent to it until memoryd restarts; see docs/runbook.md#honcho-key-refused` |
| the ledger cannot be written | `memoryd: <ledger error>; the Honcho worker stops until memoryd restarts; see docs/runbook.md#honcho-ledger-damaged` |
`<error>` is a `HonchoError`'s `Display` (task 10): its kind and status, never a body. No line
holds a turn's text or a key.
## Every place that changes
This is the complete list.
| Place | What happens there |
|---|---|
| `crates/memoryd/src/honcho/decide.rs` | `user_text` and `final_reply` made public (edits D1, D2) |
| `crates/memoryd/src/honcho/mod.rs` | `pub mod worker;` (edit H1) |
| `crates/memoryd/src/honcho/turns.rs` | `sessions`, `resume`, `append`, `retry` (edits T1 to T3) |
| `crates/memoryd/src/honcho/worker.rs` | new: a skeleton you copy, then fill 11 bodies |
| `crates/memoryd/src/serve.rs` | imports, `Memoryd`, `StartError::Secret`, `start`, `decide_turns` (edits S1 to S8) |
| `crates/memoryd/src/main.rs` | a key's error printed with its own pointer (edit M1) |
| `crates/memoryd/tests/honcho_serve.rs` | a new version, given (task 09's test with a skipped turn in its cut-off ledger, since a worker now runs beside it) |
| `docs/runbook.md` | three entries appended |
| everything else | **no change** |
## Files
- Copy, from `docs/plans/M5c1/files/` (the same path under it):
- new tests: `crates/memoryd/tests/honcho_worker.rs`, `crates/memoryd/tests/honcho_worker_more.rs`
- new test support: `crates/memoryd/tests/support/worker.rs`
- a **new version** of `crates/memoryd/tests/honcho_serve.rs` (it replaces the file in the
tree; `honcho_serve.rs-task09` beside it is the older one: do not copy that)
- the skeleton `crates/memoryd/src/honcho/worker.rs`
- Append, from `docs/plans/M5c1/files/`, to the end of `docs/runbook.md`, each with one blank
line before it, in this order: `runbook-honcho-unreachable.md`, `runbook-honcho-send-refused.md`,
`runbook-honcho-key-refused.md` (step 7 gives the commands).
- Modify: the files of edits D1 to M1, `docs/implementer-log.md`.
- Do not touch: any other source file, any other test or support file, the fixtures, any
`Cargo.toml`, and in the skeleton anything but the 11 `todo!()` bodies.
## Facts you need
- **What the skeleton gives whole:** the types, `Worker::new`, `run`, `step` (the table of what
each outcome does), `send` (read, batch, check the size, make sure of the session, add),
`open` and `spawn`. Read `step` and `send` before you fill the helpers they call.
- **The shared state.** `TurnSync` (task 09) holds the ledger and the waiting sessions. The
socket threads take its lock to decide; the worker takes it to find the next turn, to append
its records and to walk, and never holds it while it talks to Honcho or reads a log.
- **`Condvar`.** `Wake` is a `Mutex<bool>` and a `Condvar`: `notify` sets the flag and
`notify_one`s; `wait` waits with `wait_timeout_while(guard, timeout, |woken| !*woken)`, which
returns at once if the flag is already set (a `SessionUpdated` that came while the worker was
busy is not lost) and then clears it.
- **`Duration::saturating_mul(2)`** doubles a wait without overflow; `.min(max)` caps it.
- **The given tests.**
- `honcho_worker.rs` (12 tests): the limits and `parts`; a turn sent once as one batch,
exactly, then idle; parts over 25,000 characters; both texts neutralised (a tag from `TAGS`);
a new speaker's turn to `mm-a-2`; an outage (backoffs 1, 2, 4, 8, 8, 8 ms with the tests'
`FAST` waits), its two lines, the sends in order after it, a new outage from the first wait
again; a 422 marked failed and the next sent; a 401 stopping one workspace only; a 403
ending an outage; a turn gone from the log, or without its reply, marked failed; a turn too
long for a batch.
- `honcho_worker_more.rs` (10 tests): the default waits; undecided turns decided when idle
and after an outage; a restart sending nothing again and resuming only the sessions the
ledger knows; a running turn never decided; a conclusion left waiting; a ledger that cannot
be written stopping the worker; no log line with a turn's text; `memoryd` sending a reported
turn at once (woken, not after 30 s); a key that cannot be read stopping the start and the
process.
- `support/worker.rs`: a home, a `TurnSync`, `brokerd` as a closure, collected log lines, and
a worker against the fake Honcho with short waits.
- The calls the bodies use:
| Call | Signature, and what it gives |
|---|---|
| `Mutex::lock` | `m.lock().unwrap_or_else(\|p\| p.into_inner())`: the guard, even after a panic elsewhere |
| `Condvar::notify_one`, `wait_timeout_while` | `cv.wait_timeout_while(guard, timeout, \|v\| cond) -> LockResult<(MutexGuard, WaitTimeoutResult)>` |
| `str::chars`, `slice::chunks` | `text.chars().collect::<Vec<char>>()`; `chars.chunks(n)`: slices of at most `n` |
| `neutralise` | `bxcore::sanitize::neutralise(text: &str) -> Cow<'_, str>` |
| `MessageCreate` | `roncho::MessageCreate::new(content, peer_id).with_metadata(Map<String, Value>)` |
| `Ledger::outbox`, `decisions` | tasks 07 and 10: `Vec<(Item, Action)>` in decision order; an iterator of `(&Item, &Action)` |
| `honcho_session` | task 10: `honcho_session(ledger.decisions(), session, turn) -> Option<HonchoSession>` |
| `read_log`, `turn_records`, `user_text`, `final_reply` | tasks 09 and 08 |
| `TurnSync::retry`, `append` | this task's edits T2 and T3 |
## The edits, exactly
Nothing else in these files changes. Each quoted "before" block occurs exactly once in its file.
### `crates/memoryd/src/honcho/decide.rs`
**D1.** In `decide.rs`, the line
```rust
fn user_text(turn: &[LogRecord]) -> (&str, Option<&str>) {
```
becomes
```rust
pub fn user_text(turn: &[LogRecord]) -> (&str, Option<&str>) {
```
**D2.** The line
```rust
fn final_reply(turn: &[LogRecord]) -> Option<&str> {
```
becomes
```rust
pub fn final_reply(turn: &[LogRecord]) -> Option<&str> {
```
### `crates/memoryd/src/honcho/mod.rs`
**H1.** The line
```rust
pub mod turns;
```
becomes
```rust
pub mod turns;
pub mod worker;
```
### `crates/memoryd/src/honcho/turns.rs`
**T1.** In `impl TurnSync`, the line
```rust
/// The sessions that still have undecided turns, with the highest turn reported for each.
```
becomes
```rust
/// The directory of `loopd`'s session logs.
pub fn sessions(&self) -> &Path {
&self.sessions
}
/// The sessions that still have undecided turns, with the highest turn reported for each.
```
**T2.** The lines
```rust
/// `loopd` reported that turn `turn` of `session` ended. Remember it, then walk every session
/// with undecided turns, in the order of their ids, until one stops the walk.
```
become
```rust
/// After a restart: each session with a decided turn in the ledger waits again, at the turns
/// its log holds, so that a turn left undecided before the restart is decided at the next
/// walk (`decidable` holds back one still running). A session with no decided turn is left
/// to its next report: sessions from before Honcho was turned on are never walked.
pub fn resume(&mut self) {
let mut sessions: Vec<SessionId> = Vec::new();
for (item, _) in self.ledger.decisions() {
if let Item::Turn { session, .. } = item
&& !sessions.contains(session)
{
sessions.push(session.clone());
}
}
for session in sessions {
if let Ok(records) = read_log(&log_path(&self.sessions, &session)) {
self.reported.insert(
session.as_str().to_string(),
(session.clone(), turns(&records)),
);
}
}
}
/// Append `record` to the ledger (the worker's `Sent` and `Failed`).
pub fn append(&mut self, record: Record) -> Result<(), ledger::LedgerError> {
self.ledger.append(record)
}
/// `loopd` reported that turn `turn` of `session` ended. Remember it, then walk.
```
**T3.** In `updated`, the lines
```rust
entry.1 = entry.1.max(turn);
for (session, turn) in self.waiting() {
```
become
```rust
entry.1 = entry.1.max(turn);
self.retry(ask, now, log);
}
/// Walk every session with undecided turns, in the order of their ids, until one stops the
/// walk: at a report, and from the worker when it has nothing to send (M5c spec, section 5).
pub fn retry(&mut self, ask: Ask<'_>, now: Timestamp, log: &dyn Fn(&str)) {
for (session, turn) in self.waiting() {
```
### `crates/memoryd/src/serve.rs`
**S1.** The lines
```rust
use crate::honcho::ledger::{self, Ledger, LedgerError};
use crate::honcho::state;
use crate::honcho::turns::{self, TurnSync};
```
become
```rust
use crate::honcho::ledger::{self, LedgerError};
use crate::honcho::state;
use crate::honcho::turns::TurnSync;
use crate::honcho::worker::{self, Wake};
```
**S2.** In `pub struct Memoryd`, the lines
```rust
honcho: Option<Mutex<TurnSync>>,
log: Log,
}
```
become
```rust
honcho: Option<Arc<Mutex<TurnSync>>>,
/// Wakes the Honcho worker when a turn has been decided.
wake: Arc<Wake>,
log: Log,
}
```
**S3.** In `pub enum StartError`, the lines
```rust
Failed(String),
Ledger(LedgerError),
}
```
become
```rust
Failed(String),
Ledger(LedgerError),
/// A Honcho key that cannot be read: `bxcore::secrets`' line, with its own pointer.
Secret(String),
}
```
**S4.** In `impl std::fmt::Display for StartError`, the line
```rust
StartError::Failed(why) => write!(f, "{why}"),
```
becomes
```rust
StartError::Failed(why) | StartError::Secret(why) => write!(f, "{why}"),
```
**S5.** The lines
```rust
/// With `[honcho]`, read the ledger through first. Then create what is missing under `memory/`,
/// open the index and catch it up, and bind the three sockets. The error names what failed.
pub fn start(config: Config, log: Log) -> Result<Running, StartError> {
let honcho = match config.honcho_config()? {
Some(honcho) => {
let path = config.memory_dir().join(turns::LEDGER);
let ledger = Ledger::open(&path).map_err(StartError::Ledger)?;
if ledger.repaired() {
(log)(
format!(
"memoryd: {}: a last line cut off by a crash was dropped",
path.display()
)
.as_str(),
);
}
Some(Mutex::new(TurnSync::new(
ledger,
&honcho.agent,
&config.sessions_dir(),
)))
}
None => None,
};
```
become
```rust
/// With `[honcho]`, read the ledger through and the keys first. Then create what is missing
/// under `memory/`, open the index and catch it up, bind the three sockets, and start the Honcho
/// worker. The error names what failed.
pub fn start(config: Config, log: Log) -> Result<Running, StartError> {
let opened = match config.honcho_config()? {
Some(honcho) => Some(worker::open(&config, &honcho, &log)?),
None => None,
};
```
**S6.** In `start`, the lines
```rust
(admin_listener, Which::Admin),
];
```
become
```rust
(admin_listener, Which::Admin),
];
let wake = Arc::new(Wake::default());
let honcho = match opened {
Some(opened) => {
let sync = Arc::clone(&opened.sync);
worker::spawn(opened, &config, Arc::clone(&wake), Arc::clone(&log))?;
Some(sync)
}
None => None,
};
```
**S7.** In `start`, where `Memoryd` is built, the lines
```rust
honcho,
log,
```
become
```rust
honcho,
wake,
log,
```
**S8.** In `decide_turns`, the lines
```rust
Timestamp::now(),
&*self.log,
);
}
```
become
```rust
Timestamp::now(),
&*self.log,
);
drop(sync);
self.wake.notify();
}
```
### `crates/memoryd/src/main.rs`
**M1.** The lines
```rust
// The ledger's line names its own pointer, `honcho-ledger-damaged`.
Err(e @ serve::StartError::Ledger(_)) => {
```
become
```rust
// The ledger's and a key's lines name their own pointers.
Err(e @ (serve::StartError::Ledger(_) | serve::StartError::Secret(_))) => {
```
## Steps
- [ ] **1. Copy the given tests.** From the repository root, four commands:
```sh
cp docs/plans/M5c1/files/crates/memoryd/tests/honcho_worker.rs crates/memoryd/tests/
cp docs/plans/M5c1/files/crates/memoryd/tests/honcho_worker_more.rs crates/memoryd/tests/
cp docs/plans/M5c1/files/crates/memoryd/tests/honcho_serve.rs crates/memoryd/tests/
cp docs/plans/M5c1/files/crates/memoryd/tests/support/worker.rs crates/memoryd/tests/support/
```
- [ ] **2. See them fail.** `cargo build --tests --keep-going -p memoryd`, with a shell timeout
of 600000 ms: two test targets do not compile. `honcho_worker`, 3 errors: `E0432`
(``unresolved import `memoryd::honcho::worker` ``) in the test file and in
`support/worker.rs`, and `E0599` (``no method named `resume` found for struct `TurnSync` ``).
`honcho_worker_more`, 4 errors: the same three, and `E0599` (``no variant, associated function,
or constant named `Secret` found for enum `StartError` ``). Every other target compiles, and
`cargo test -p memoryd --test honcho_serve` passes its 6 tests already.
- [ ] **3. The module.** Make edits D1, D2, H1, T1 to T3, S1 to S8 and M1, then copy the
skeleton:
```sh
cp docs/plans/M5c1/files/crates/memoryd/src/honcho/worker.rs crates/memoryd/src/honcho/
```
`cargo check -p memoryd`: no error, and 21 warnings, all from the unfilled bodies: six
`unused import` lines (`bxcore::sanitize::neutralise`; `Map` and `json`; `final_reply`,
`turn_records` and `user_text`; `Action` and `self`; `honcho_session`; `read_log`), thirteen
`unused variable` (`text` and `turn` twice each, and `agent`, `error`, `messages`, `path`,
`record`, `reply`, `session`, `speaker`, `timeout` once each), ``fields `woken` and `ready` are
never read`` and ``fields `ask` and `outage` are never read``.
- [ ] **4. Fill the eleven bodies of `worker.rs`, one at a time, in the order of the file**, each
from its comment, and run `cargo check -p memoryd` after each: `notify`, `wait`, `parts`,
`read_turn`, `batch`, `ids`, `next`, `unreachable`, `recovered`, `retry`, `record`. When a body
is filled, delete its instruction comment (the `//` lines inside the body) and keep the
function's doc comment (`///`) as it is. Change nothing else. After the last,
`cargo check -p memoryd` prints no warning.
- [ ] **5. The tests.** With a shell timeout of 600000 ms, and every test passes (12, 10, 6, and
the existing ones unchanged):
```sh
cargo test -p memoryd --test honcho_worker --test honcho_worker_more --test honcho_serve \
--test honcho_turns --test honcho_client --test honcho_start --test serve
```
- [ ] **6. Check.** Three commands:
- `grep -n 'thread::spawn\|Builder::new()' crates/memoryd/src/honcho/worker.rs` prints one
line, in `spawn`: the worker is the one new thread.
- `grep -rn 'runbook.md#honcho-unreachable\|runbook.md#honcho-send-refused\|runbook.md#honcho-key-refused' crates/memoryd/src`
prints three lines, the constants in `worker.rs`.
- `git diff --stat -- crates/bxcore crates/loopd crates/brokerd crates/gatewayd crates/bxctl
Cargo.toml Cargo.lock crates/memoryd/Cargo.toml` prints nothing.
- [ ] **7. The runbook.** From the repository root, three commands:
```sh
{ echo; cat docs/plans/M5c1/files/runbook-honcho-unreachable.md; } >> docs/runbook.md
{ echo; cat docs/plans/M5c1/files/runbook-honcho-send-refused.md; } >> docs/runbook.md
{ echo; cat docs/plans/M5c1/files/runbook-honcho-key-refused.md; } >> docs/runbook.md
```
Then `grep -c '^## honcho-' docs/runbook.md` prints `5`.
- [ ] **8. Run the gate.** `cargo fmt --all`, then `make gate`, with a shell timeout of 600000 ms.
Expected last line: `gate: ok`, with 1300 tests: 1278 before this task, plus 22 new ones (12 in
`honcho_worker.rs`, 10 in `honcho_worker_more.rs`).
- [ ] **9. Log and commit.** Add your row to `docs/implementer-log.md`; its Task cell is
`M5c1/11-memoryd-honcho-worker`. `git status --short` lists `decide.rs`, `honcho/mod.rs`,
`turns.rs`, `serve.rs`, `main.rs`, `tests/honcho_serve.rs`, `docs/runbook.md` and your log as
modified, and `worker.rs`, the two new test files and `tests/support/worker.rs` as new. Stage
with `git add crates/memoryd docs/runbook.md 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 1300 tests.
- `git diff HEAD~1 --stat` lists only the files of step 9.
## Stop and report if
- A "before" block of D1 to M1 is not in its file exactly as shown, or is there more than once.
- Step 2 or 3 shows a different result: other test targets, errors of another kind, or other
warnings.
- `cargo check` reports an error after a body you filled or an edit you made, and the comment or
the edit does not tell you how to fix it. Quote the error, and stop.
- A comment in the skeleton does not fit the code under it, or disagrees with this task's tables.
Quote both and stop.
- After step 4 a test fails although each body follows its comment and each edit is as shown.
Do not change a test, a support file or the skeleton's given code: stop, and give the failing
tests' names and their messages.
- A test seems to need a real Honcho, a new fixture or a longer wait. It does not; stop and say
why you think so.
- The fix seems to need a change anywhere else: `client.rs`, `ledger.rs`, another crate, a
second thread. It does not; stop and say why you think so.
- A test outside the new files fails in the gate: check once whether it fails without your
change, then stop and report both results.
- The gate passes with a count other than 1300.
## What the given tests pin
Each of these changes to the finished code makes at least one given test fail (36 tried; one
cannot change behaviour): a part of 25,001, or parts cut by bytes; no neutralising; the agent
first, or the reply from the speaker; the wrong turn in the metadata; no batch limit; no session
made first; the messages sent to the Boxmaker id instead of the Honcho session; the ids dropped;
the wait not doubled or not capped; the outage logged at every try, its end not logged, no
retry after it, or a refused key not ending it; a refused key not remembered, its workspace not
skipped, or its turns failed; a refused send not recorded; a local failure not recorded; the
newest turn first; no retry when idle, or idle after a retry that decided something; a ledger
that cannot be written ignored, or `stopped` ignored; the wake doing nothing; a turn without its
reply sent anyway; every session in `sessions/` resumed, or none; the retry treated as a report;
no worker started, or not woken; a key's error taken for a start failure, or printed with the
start pointer.
## After this task
- Task 13 sends the other actions (conclusions, their deletion, fleet messages and retractions)
from the same worker.
- Task 15 adds the cutoff: turns from before Honcho was turned on are skipped.
@@ -0,0 +1,403 @@
//! The worker: one thread that sends what the ledger says is waiting, oldest first (M5c spec,
//! section 5). A turn is read again from `loopd`'s log, neutralised, cut into parts Honcho takes,
//! and added to its Honcho session as one batch; the ids Honcho gives go in the ledger. An outage
//! is waited out with a doubling wait and logged when it starts and when it ends; a refused send is
//! marked failed; a refused key stops that workspace until `memoryd` restarts. When nothing waits,
//! the worker decides what `brokerd` could not answer for before, then sleeps until a turn ends.
use std::collections::HashSet;
use std::path::Path;
use std::sync::{Arc, Condvar, Mutex};
use std::time::Duration;
use bxcore::sanitize::neutralise;
use bxcore::{SessionId, SessionStateReply, Timestamp};
use roncho::MessageCreate;
use serde_json::{Map, json};
use crate::config::Config;
use crate::honcho::client::{Clients, HonchoError, Timeouts, classify};
use crate::honcho::config::HonchoConfig;
use crate::honcho::decide::{final_reply, turn_records, user_text};
use crate::honcho::ledger::{self, Action, Item, Ledger, Record, Workspace};
use crate::honcho::naming::{HonchoSession, honcho_session};
use crate::honcho::state;
use crate::honcho::turns::{LEDGER, TurnSync, log_path, read_log};
use crate::serve::{Log, StartError};
/// The most characters Honcho takes in one message (recorded: 25,000 is taken, 25,001 refused).
pub const MAX_PART: usize = 25_000;
/// The most messages the worker puts in one batch. A turn that needs more is marked failed.
pub const MAX_BATCH: usize = 100;
pub const UNREACHABLE: &str = "see docs/runbook.md#honcho-unreachable";
pub const SEND_REFUSED: &str = "see docs/runbook.md#honcho-send-refused";
pub const KEY_REFUSED: &str = "see docs/runbook.md#honcho-key-refused";
pub const LOG_DAMAGED: &str = "see docs/runbook.md#session-log-damaged";
/// The worker's waits. Tests shorten them.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub struct Tuning {
/// The first wait in an outage; each next one doubles, up to `backoff_max`.
pub backoff: Duration,
pub backoff_max: Duration,
/// How long the worker sleeps with nothing to send, unless a turn ends first.
pub idle: Duration,
}
impl Tuning {
pub const DEFAULT: Tuning = Tuning {
backoff: Duration::from_secs(5),
backoff_max: Duration::from_secs(600),
idle: Duration::from_secs(30),
};
}
/// Wakes the worker from its idle sleep when a turn ends.
#[derive(Debug, Default)]
pub struct Wake {
woken: Mutex<bool>,
ready: Condvar,
}
impl Wake {
/// Wake the worker if it sleeps, or make its next sleep return at once.
pub fn notify(&self) {
// `let mut woken = self.woken.lock().unwrap_or_else(|p| p.into_inner());`, then
// `*woken = true;` and `self.ready.notify_one();`.
todo!()
}
/// Sleep until `notify`, or at most `timeout`.
pub fn wait(&self, timeout: Duration) {
// `let woken = self.woken.lock().unwrap_or_else(|p| p.into_inner());`. Then
// `let (mut woken, _) = self.ready.wait_timeout_while(woken, timeout, |woken| !*woken)`
// `.unwrap_or_else(|p| p.into_inner());`, and `*woken = false;` (the wake is used up).
todo!()
}
}
/// What one step of the worker did, and so what the loop does next.
#[derive(Debug, Clone, PartialEq, Eq)]
pub enum Step {
/// A turn was sent, or marked failed: go on at once.
Done,
/// Honcho is unreachable: wait this long, then try the same turn again.
Backoff(Duration),
/// Nothing to send, and the retry decided nothing new: sleep.
Idle,
/// The ledger cannot be written: the worker stops.
Stopped,
}
/// `brokerd`'s answer for a session, for the retry.
pub type AskBox = Box<dyn Fn(&SessionId) -> Result<SessionStateReply, String> + Send>;
/// Why a turn could not be sent.
enum Unsent {
Honcho(HonchoError),
/// The turn cannot be read from the log any more, or is too long for one batch.
Local(&'static str),
}
/// A turn to send: its item, workspace, speaker and Honcho session.
struct Next {
item: Item,
session: SessionId,
turn: u64,
workspace: Workspace,
speaker: String,
honcho: Option<HonchoSession>,
}
pub struct Worker {
sync: Arc<Mutex<TurnSync>>,
clients: Clients,
wake: Arc<Wake>,
ask: AskBox,
log: Log,
tuning: Tuning,
agent: String,
/// In an outage: the next wait.
outage: Option<Duration>,
/// Workspaces whose key was refused: nothing more is sent to them until restart.
refused: HashSet<Workspace>,
stopped: bool,
}
/// `text` in parts of at most `MAX_PART` characters, in order. Empty text has no part.
pub fn parts(text: &str) -> Vec<String> {
// `let chars: Vec<char> = text.chars().collect();` then
// `chars.chunks(MAX_PART).map(|chunk| chunk.iter().collect()).collect()`.
todo!()
}
/// Turn `turn`'s user text and final reply, read again from the log at `path`. `None` when the log
/// does not read, or has no such turn, or the turn no reply.
pub fn read_turn(path: &Path, turn: u64) -> Option<(String, String)> {
// Each step with `?`: `read_log(path).ok()?` into `records`; then
// `let records = turn_records(&records, turn)?;`; `let (text, _) = user_text(records);`;
// `let reply = final_reply(records)?;`. Then `Some((text.to_string(), reply.to_string()))`.
todo!()
}
/// A turn's messages, in one batch: the speaker's text, then the agent's reply, each neutralised
/// and in parts of at most `MAX_PART` characters, each part with the turn's metadata.
pub fn batch(
text: &str,
reply: &str,
speaker: &str,
agent: &str,
session: &SessionId,
turn: u64,
) -> Vec<MessageCreate> {
// A `Map` `metadata` with `"agent"` -> `json!(agent)`, `"boxmaker_session"` ->
// `json!(session.as_str())`, `"turn"` -> `json!(turn)` (in this order). Then for each
// `(content, peer)` of `[(text, speaker), (reply, agent)]`, for each `part` of
// `parts(&neutralise(content))`, push
// `MessageCreate::new(part, peer).with_metadata(metadata.clone())`. Return the messages.
todo!()
}
/// The ids of the messages Honcho made, in order.
fn ids(messages: &[roncho::Message]) -> Vec<String> {
// `messages.iter().map(|m| m.id.clone()).collect()`.
todo!()
}
impl Worker {
/// `agent` is `[honcho] agent`. `sync` and `wake` are shared with the socket threads.
pub fn new(
sync: Arc<Mutex<TurnSync>>,
clients: Clients,
wake: Arc<Wake>,
ask: AskBox,
log: Log,
tuning: Tuning,
agent: &str,
) -> Worker {
Worker {
sync,
clients,
wake,
ask,
log,
tuning,
agent: agent.to_string(),
outage: None,
refused: HashSet::new(),
stopped: false,
}
}
/// Step until the ledger cannot be written; wait as each step says.
pub fn run(mut self) {
loop {
match self.step() {
Step::Done => {}
Step::Backoff(wait) => std::thread::sleep(wait),
Step::Idle => self.wake.wait(self.tuning.idle),
Step::Stopped => return,
}
}
}
/// Send the oldest waiting turn, or, with none, retry the undecided ones.
pub fn step(&mut self) -> Step {
if self.stopped {
return Step::Stopped;
}
let Some(next) = self.next() else {
self.retry();
return match self.next() {
Some(_) => Step::Done,
None => Step::Idle,
};
};
match self.send(&next) {
Ok(sent) => {
self.recovered();
self.record(Record::Sent {
time: Timestamp::now(),
item: next.item,
ids: sent,
})
}
Err(Unsent::Honcho(e @ HonchoError::Unreachable { .. })) => self.unreachable(&e),
Err(Unsent::Honcho(HonchoError::KeyRefused { status })) => {
self.recovered();
self.refused.insert(next.workspace);
(self.log)(&format!(
"memoryd: Honcho refused the key of workspace {} (HTTP {status}); nothing more is sent to it until memoryd restarts; {KEY_REFUSED}",
self.clients.client(next.workspace).workspace_id()
));
Step::Done
}
Err(Unsent::Honcho(e)) => {
self.recovered();
(self.log)(&format!(
"memoryd: turn {} of session {} was not sent: {e}; it is marked failed; {SEND_REFUSED}",
next.turn,
next.session.as_str()
));
self.record(Record::Failed {
time: Timestamp::now(),
item: next.item,
status: e.status(),
kind: e.kind().to_string(),
})
}
Err(Unsent::Local(kind)) => {
let pointer = if kind == "log" {
LOG_DAMAGED
} else {
SEND_REFUSED
};
(self.log)(&format!(
"memoryd: turn {} of session {} cannot be sent ({kind}); it is marked failed; {pointer}",
next.turn,
next.session.as_str()
));
self.record(Record::Failed {
time: Timestamp::now(),
item: next.item,
status: None,
kind: kind.to_string(),
})
}
}
}
/// The oldest waiting turn whose workspace's key was not refused. Other actions wait.
fn next(&self) -> Option<Next> {
// Lock `self.sync` (`unwrap_or_else(|p| p.into_inner())`), `let ledger =
// sync.ledger();`, then `ledger.outbox().into_iter().find_map(|(item, action)| { .. })`:
// `None` unless `item` is `Item::Turn { session, turn }` (by `&item`) and `action` is
// `Action::Turn { workspace, speaker }` (each by `let .. else`), and `None` if
// `self.refused.contains(&workspace)`; else `Some(Next { honcho:
// honcho_session(ledger.decisions(), session, *turn), session: session.clone(), turn:
// *turn, item: item.clone(), workspace, speaker })`.
todo!()
}
/// Read the turn again, make sure of its Honcho session, and add its messages as one batch.
fn send(&mut self, next: &Next) -> Result<Vec<String>, Unsent> {
let sessions = self
.sync
.lock()
.unwrap_or_else(|p| p.into_inner())
.sessions()
.to_path_buf();
let (text, reply) = read_turn(&log_path(&sessions, &next.session), next.turn)
.ok_or(Unsent::Local("log"))?;
let honcho = next.honcho.as_ref().ok_or(Unsent::Local("log"))?;
let messages = batch(
&text,
&reply,
&next.speaker,
&self.agent,
&next.session,
next.turn,
);
if messages.len() > MAX_BATCH {
return Err(Unsent::Local("too-long"));
}
self.clients
.ensure_session(next.workspace, honcho)
.map_err(Unsent::Honcho)?;
let client = self.clients.client(next.workspace);
match client.add_messages(&honcho.name, &messages) {
Ok(made) => Ok(ids(&made)),
Err(e) => Err(Unsent::Honcho(classify(&e))),
}
}
/// Honcho did not answer: log the outage's start once, and wait longer each time.
fn unreachable(&mut self, error: &HonchoError) -> Step {
// `let wait = match self.outage`: `Some(wait)` -> `wait`; `None` -> log
// `format!("memoryd: {error}; sends wait and are retried; {UNREACHABLE}")`, then
// `self.tuning.backoff`. Then
// `self.outage = Some(wait.saturating_mul(2).min(self.tuning.backoff_max));` and
// `Step::Backoff(wait)`.
todo!()
}
/// Honcho answered: if that ends an outage, log it once, and decide what waited meanwhile.
fn recovered(&mut self) {
// If `self.outage.take().is_some()`: log exactly
// `memoryd: Honcho answers again; waiting sends go on`, then `self.retry();`.
todo!()
}
/// Task 09's walk, for the turns `brokerd` could not answer for.
fn retry(&mut self) {
// Lock `self.sync` as in `next` (as `mut sync`), then
// `sync.retry(&*self.ask, Timestamp::now(), &*self.log);`.
todo!()
}
/// Append the worker's record. A ledger that cannot be written stops the worker: the send
/// would be repeated at every step.
fn record(&mut self, record: Record) -> Step {
// `let result =
// self.sync.lock().unwrap_or_else(|p| p.into_inner()).append(record);`. `Ok(())` ->
// `Step::Done`. `Err(e)` -> log `format!("memoryd: {e}; the Honcho worker stops until
// memoryd restarts; {}", ledger::RUNBOOK)`, then `self.stopped = true;`, `Step::Stopped`.
todo!()
}
}
/// With `[honcho]`, at start: the ledger read through, the sessions that wait again, and the
/// clients with their keys read. Nothing is bound or started yet.
pub struct Opened {
pub sync: Arc<Mutex<TurnSync>>,
clients: Clients,
agent: String,
}
/// Open the ledger (a cut-off last line is logged), resume the waiting sessions, and build the
/// clients (their key files' warnings are logged). A key that cannot be read is `Secret`.
pub fn open(config: &Config, honcho: &HonchoConfig, log: &Log) -> Result<Opened, StartError> {
let path = config.memory_dir().join(LEDGER);
let ledger = Ledger::open(&path).map_err(StartError::Ledger)?;
if ledger.repaired() {
(log)(&format!(
"memoryd: {}: a last line cut off by a crash was dropped",
path.display()
));
}
let mut sync = TurnSync::new(ledger, &honcho.agent, &config.sessions_dir());
sync.resume();
let env = |name: &str| std::env::var_os(name);
let (clients, warnings) =
Clients::new(honcho, &env, Timeouts::WRITES).map_err(StartError::Secret)?;
for warning in warnings {
(log)(&warning);
}
Ok(Opened {
sync: Arc::new(Mutex::new(sync)),
clients,
agent: honcho.agent.clone(),
})
}
/// Start the worker's thread, asking `brokerd` on `config`'s state socket.
pub fn spawn(opened: Opened, config: &Config, wake: Arc<Wake>, log: Log) -> Result<(), String> {
let socket = config.state_socket();
let ask: AskBox =
Box::new(move |session: &SessionId| state::ask(&socket, session, state::WAIT));
let worker = Worker::new(
opened.sync,
opened.clients,
wake,
ask,
log,
Tuning::DEFAULT,
&opened.agent,
);
std::thread::Builder::new()
.name("honcho".to_string())
.spawn(move || worker.run())
.map(|_| ())
.map_err(|e| format!("cannot start the Honcho worker: {e}"))
}
@@ -2,7 +2,8 @@
//! `session_updated` before `brokerd` is asked, and a silent `brokerd` holds up neither `loopd`
//! nor a memory call; without `[honcho]` nothing is asked or written; a damaged ledger stops the
//! start with its pointer, and a cut-off last line is dropped and logged. Every wait has a
//! deadline. Do not edit.
//! deadline. (From M5c-1 task 11 a Honcho worker runs beside it; nothing here waits for it, and the
//! cut-off line is a skipped turn, so that it has nothing to send.) Do not edit.
#[path = "support/brokerd.rs"]
mod brokerd;
@@ -41,6 +42,9 @@ fleet = \"fleet\"
const DECIDED: &str = r#"{"type":"decided","time":"2026-09-28T10:00:00.000Z","item":{"type":"turn","session":"mm-a","turn":1},"action":{"type":"turn","workspace":"trusted","speaker":"kyle"}}"#;
/// A turn decided to go nowhere: the worker has nothing to send for it.
const SKIPPED: &str = r#"{"type":"decided","time":"2026-09-28T10:00:00.000Z","item":{"type":"turn","session":"mm-a","turn":1},"action":{"type":"skip","why":"the turn has no single speaker"}}"#;
struct Home {
config: Config,
text: String,
@@ -263,7 +267,7 @@ fn a_damaged_ledger_stops_the_start() {
fn a_cut_off_last_line_is_dropped_and_logged() {
let home = Home::new("serve-repaired", true);
std::fs::create_dir_all(home.dir.path().join("memory")).unwrap();
std::fs::write(home.ledger(), format!("{DECIDED}\n{{\"type\":\"se")).unwrap();
std::fs::write(home.ledger(), format!("{SKIPPED}\n{{\"type\":\"se")).unwrap();
let lines = home.serve();
assert_eq!(
*lines.lock().unwrap(),
@@ -272,7 +276,7 @@ fn a_cut_off_last_line_is_dropped_and_logged() {
home.ledger().display()
)]
);
assert_eq!(home.ledger_text(), format!("{DECIDED}\n"));
assert_eq!(home.ledger_text(), format!("{SKIPPED}\n"));
}
/// A `memoryd` process, killed and waited for when dropped: declared after its `Home`, so it
@@ -0,0 +1,329 @@
//! `memoryd` deciding turns as it serves (M5c spec, section 5): `loopd` has its answer to
//! `session_updated` before `brokerd` is asked, and a silent `brokerd` holds up neither `loopd`
//! nor a memory call; without `[honcho]` nothing is asked or written; a damaged ledger stops the
//! start with its pointer, and a cut-off last line is dropped and logged. Every wait has a
//! deadline. Do not edit.
#[path = "support/brokerd.rs"]
mod brokerd;
#[path = "support/logs.rs"]
mod logs;
#[path = "support/tmp.rs"]
mod tmp;
#[path = "support/turns.rs"]
mod turns;
use std::os::unix::net::UnixStream;
use std::path::{Path, PathBuf};
use std::process::{Command, Stdio};
use std::sync::{Arc, Mutex};
use std::time::{Duration, Instant};
use brokerd::{Answer, FakeBrokerd};
use bxcore::{
CallId, DataClass, Envelope, MemoryCall, Message, SessionId, SessionUpdated, ToolRequest,
read_frame, write_frame,
};
use memoryd::config::Config;
use memoryd::honcho::ledger::LedgerError;
use memoryd::serve::{self, StartError};
use tmp::TempDir;
use turns::{clean, write_turns};
const SECTION: &str = "[honcho]
url = \"http://127.0.0.1:9\"
agent = \"boxmaker0\"
owner = \"kyle\"
trusted = \"boxmaker0-trusted\"
untrusted = \"boxmaker0-untrusted\"
fleet = \"fleet\"
";
const DECIDED: &str = r#"{"type":"decided","time":"2026-09-28T10:00:00.000Z","item":{"type":"turn","session":"mm-a","turn":1},"action":{"type":"turn","workspace":"trusted","speaker":"kyle"}}"#;
struct Home {
config: Config,
text: String,
dir: TempDir,
}
impl Home {
fn new(tag: &str, honcho: bool) -> 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(),
if honcho { SECTION } else { "" }
);
Home {
config: Config::parse(&text).unwrap(),
text,
dir,
}
}
fn ledger(&self) -> PathBuf {
self.dir.path().join("memory/honcho.jsonl")
}
fn ledger_text(&self) -> String {
std::fs::read_to_string(self.ledger()).unwrap_or_default()
}
/// `serve::start`, run on a thread; its log lines are collected.
fn serve(&self) -> Arc<Mutex<Vec<String>>> {
let lines = Arc::new(Mutex::new(Vec::new()));
let sink = Arc::clone(&lines);
let log: serve::Log = Arc::new(move |l: &str| sink.lock().unwrap().push(l.to_string()));
let running = serve::start(self.config.clone(), log).unwrap();
std::thread::spawn(move || running.run());
lines
}
}
/// One request and its answer, with a 10 s limit; how long the answer took.
fn ask(socket: &Path, msg: Message) -> (Message, Duration) {
let started = Instant::now();
let mut stream = UnixStream::connect(socket).unwrap();
stream
.set_read_timeout(Some(Duration::from_secs(10)))
.unwrap();
let env = Envelope {
v: 1,
id: 7,
r#final: true,
msg,
};
write_frame(&mut stream, &env).unwrap();
let reply = read_frame(&mut stream).unwrap();
(reply.msg, started.elapsed())
}
fn updated(home: &Home, session: &str, turn: u64) -> (Message, Duration) {
let msg = Message::SessionUpdated(SessionUpdated {
session: SessionId::new(session).unwrap(),
turn,
});
ask(&home.config.loop_socket(), msg)
}
/// Waits up to 10 s for `done`; true if it came.
fn within_10s(done: impl Fn() -> bool) -> bool {
let deadline = Instant::now() + Duration::from_secs(10);
while Instant::now() < deadline {
if done() {
return true;
}
std::thread::sleep(Duration::from_millis(10));
}
false
}
#[test]
fn a_reported_turn_is_decided_after_loopd_has_its_answer() {
let home = Home::new("serve-decide", true);
write_turns(home.dir.path(), "mm-a", &[turns::finished(Some("kyle"))]);
write_turns(home.dir.path(), "mm-z", &[turns::finished(Some("kyle"))]);
let fake = FakeBrokerd::start(&home.config.state_socket(), Answer::State(clean()));
let _lines = home.serve();
// A report on another socket is refused, and decides nothing.
let wrong = Message::SessionUpdated(SessionUpdated {
session: SessionId::new("mm-z").unwrap(),
turn: 1,
});
let (answer, _) = ask(&home.config.admin_socket(), wrong);
assert!(matches!(answer, Message::Error(_)), "{answer:?}");
let (answer, _) = updated(&home, "mm-a", 1);
assert!(matches!(answer, Message::Ok(_)), "{answer:?}");
assert!(within_10s(|| home.ledger_text().contains("\"turn\":1}")));
// The line as `DECIDED`, but for its time, which is the decision's.
let text = home.ledger_text();
assert_eq!(text.lines().count(), 1, "{text}");
let mut got: serde_json::Value = serde_json::from_str(&text).unwrap();
let mut want: serde_json::Value = serde_json::from_str(DECIDED).unwrap();
got["time"] = serde_json::Value::Null;
want["time"] = serde_json::Value::Null;
assert_eq!(got, want);
assert_eq!(fake.seen().len(), 1);
}
#[test]
fn a_silent_brokerd_holds_up_neither_loopd_nor_memory() {
let home = Home::new("serve-silent", true);
write_turns(home.dir.path(), "mm-a", &[turns::finished(Some("kyle"))]);
write_turns(home.dir.path(), "mm-b", &[turns::finished(Some("kyle"))]);
let fake = FakeBrokerd::start(&home.config.state_socket(), Answer::Hang);
let lines = home.serve();
let (answer, took) = updated(&home, "mm-a", 1);
assert!(matches!(answer, Message::Ok(_)), "{answer:?}");
assert!(took < Duration::from_secs(1), "loopd waited {took:?}");
assert!(fake.wait_for(1), "brokerd was never asked");
// While the question hangs: another report, and a memory call.
let (answer, took) = updated(&home, "mm-b", 1);
assert!(matches!(answer, Message::Ok(_)), "{answer:?}");
assert!(took < Duration::from_secs(1), "loopd waited {took:?}");
let call = Message::MemoryCall(MemoryCall {
request: ToolRequest {
session: SessionId::new("mm-b").unwrap(),
call: CallId(1),
tool: "recall".to_string(),
arguments: r#"{"query":"hello"}"#.to_string(),
},
taint: DataClass::Private,
untrusted: false,
});
let (answer, took) = ask(&home.config.broker_socket(), call);
assert!(matches!(answer, Message::ToolResponse(_)), "{answer:?}");
assert!(
took < Duration::from_secs(1),
"the memory call waited {took:?}"
);
// After 5 s without a byte, the outage is logged once, and nothing is decided.
let pointer = "turns wait undecided; see docs/runbook.md#broker-state-unavailable";
assert!(within_10s(|| lines
.lock()
.unwrap()
.iter()
.any(|l| l.contains(pointer))));
let logged = lines.lock().unwrap().clone();
let outage: Vec<&String> = logged.iter().filter(|l| l.contains(pointer)).collect();
assert_eq!(outage.len(), 1, "{logged:?}");
let start = format!("memoryd: {}: ", home.config.state_socket().display());
assert!(outage[0].starts_with(&start), "{}", outage[0]);
assert_eq!(home.ledger_text(), "");
}
#[test]
fn without_honcho_nothing_is_asked_or_written() {
let home = Home::new("serve-off", false);
write_turns(home.dir.path(), "mm-a", &[turns::finished(Some("kyle"))]);
let fake = FakeBrokerd::start(&home.config.state_socket(), Answer::State(clean()));
let lines = home.serve();
let (answer, _) = updated(&home, "mm-a", 1);
assert!(matches!(answer, Message::Ok(_)), "{answer:?}");
// A negative: nothing may happen, so there is nothing to wait for but a while.
std::thread::sleep(Duration::from_millis(300));
assert!(fake.seen().is_empty());
assert!(!home.ledger().exists());
assert!(
lines.lock().unwrap().is_empty(),
"{:?}",
lines.lock().unwrap()
);
}
#[test]
fn a_damaged_ledger_stops_the_start() {
let home = Home::new("serve-damaged", true);
std::fs::create_dir_all(home.dir.path().join("memory")).unwrap();
std::fs::write(home.ledger(), "not json\n").unwrap();
let log: serve::Log = Arc::new(|_: &str| {});
let err = match serve::start(home.config.clone(), log) {
Err(err) => err,
Ok(_) => panic!("memoryd started"),
};
assert!(
matches!(
err,
StartError::Ledger(LedgerError::Damaged { line: 1, .. })
),
"{err:?}"
);
let shown = err.to_string();
assert!(shown.starts_with(&format!("{}:1: ", home.ledger().display())));
assert!(
shown.ends_with("; see docs/runbook.md#honcho-ledger-damaged"),
"{shown}"
);
assert_eq!(shown.matches("see docs/runbook.md").count(), 1, "{shown}");
assert!(!home.config.loop_socket().exists(), "a socket was bound");
// A ledger that cannot be read is named with the same pointer.
std::fs::remove_file(home.ledger()).unwrap();
std::fs::create_dir(home.ledger()).unwrap();
let log: serve::Log = Arc::new(|_: &str| {});
let err = match serve::start(home.config.clone(), log) {
Err(err) => err,
Ok(_) => panic!("memoryd started"),
};
assert!(
matches!(err, StartError::Ledger(LedgerError::Io(..))),
"{err:?}"
);
let shown = err.to_string();
assert!(shown.starts_with(&format!("{}: ", home.ledger().display())));
assert!(
shown.ends_with("; see docs/runbook.md#honcho-ledger-damaged"),
"{shown}"
);
}
#[test]
fn a_cut_off_last_line_is_dropped_and_logged() {
let home = Home::new("serve-repaired", true);
std::fs::create_dir_all(home.dir.path().join("memory")).unwrap();
std::fs::write(home.ledger(), format!("{DECIDED}\n{{\"type\":\"se")).unwrap();
let lines = home.serve();
assert_eq!(
*lines.lock().unwrap(),
vec![format!(
"memoryd: {}: a last line cut off by a crash was dropped",
home.ledger().display()
)]
);
assert_eq!(home.ledger_text(), format!("{DECIDED}\n"));
}
/// A `memoryd` process, killed and waited for when dropped: declared after its `Home`, so it
/// drops first.
struct Daemon(std::process::Child);
impl Drop for Daemon {
fn drop(&mut self) {
let _ = self.0.kill();
let _ = self.0.wait();
}
}
#[test]
fn memoryd_exits_with_the_ledgers_line() {
let home = Home::new("serve-exit", true);
let config = home.dir.write("memoryd.toml", &home.text);
std::fs::create_dir_all(home.dir.path().join("memory")).unwrap();
std::fs::write(home.ledger(), "not json\n").unwrap();
let mut child = Daemon(
Command::new(env!("CARGO_BIN_EXE_memoryd"))
.args(["serve", "--config"])
.arg(&config)
.stdin(Stdio::null())
.stdout(Stdio::null())
.stderr(Stdio::piped())
.spawn()
.unwrap(),
);
let deadline = Instant::now() + Duration::from_secs(10);
let mut code = None;
while Instant::now() < deadline {
if let Ok(Some(status)) = child.0.try_wait() {
code = status.code();
break;
}
std::thread::sleep(Duration::from_millis(20));
}
let _ = child.0.kill();
let _ = child.0.wait();
let mut stderr = String::new();
if let Some(mut pipe) = child.0.stderr.take() {
let _ = std::io::Read::read_to_string(&mut pipe, &mut stderr);
}
assert_eq!(code, Some(1), "{stderr}");
let start = format!("memoryd: {}:1: ", home.ledger().display());
assert!(stderr.starts_with(&start), "{stderr}");
assert!(
stderr.ends_with("; see docs/runbook.md#honcho-ledger-damaged\n"),
"{stderr}"
);
assert_eq!(stderr.lines().count(), 1, "{stderr}");
assert!(!home.config.loop_socket().exists(), "a socket was bound");
}
@@ -0,0 +1,380 @@
//! The Honcho worker, stepped by hand against the fake Honcho (M5c spec, section 5): a turn sent
//! once as one batch, the speaker's parts then the agent's, neutralised, in parts of 25,000
//! characters, to the `-2` session for a new speaker; an outage waited out with a doubling wait
//! and logged twice in all; a refused send marked failed; a refused key stopping its workspace
//! only; a turn the log no longer holds marked failed; other actions left waiting. The waits and
//! a restart are in `honcho_worker_more.rs`. Do not edit.
#[path = "support/honcho.rs"]
mod honcho;
#[path = "support/logs.rs"]
mod logs;
#[path = "support/tmp.rs"]
mod tmp;
#[path = "support/turns.rs"]
mod turns;
#[path = "support/worker.rs"]
mod worker;
use std::time::Duration;
use bxcore::sanitize::TAGS;
use bxcore::{DataClass, SessionStateReply};
use honcho::{FakeHoncho, Mode, Request};
use logs::assistant;
use memoryd::honcho::ledger::{Item, Record};
use memoryd::honcho::worker::{MAX_BATCH, MAX_PART, Step, parts};
use serde_json::{Value, json};
use turns::{sid, spoken};
use worker::{FAST, Home};
/// The ids fixture 08 answers with.
const IDS: [&str; 2] = ["7HqDWzXcKAdw9tnElCNFg", "mjsyhwuGsXTh1_zG_tWRx"];
fn message_posts(fake: &FakeHoncho) -> Vec<Request> {
fake.requests()
.into_iter()
.filter(|r| r.path.ends_with("/messages"))
.collect()
}
fn turn(text: &str, speaker: &str, reply: &str) -> Vec<bxcore::LogRecord> {
vec![spoken(text, Some(speaker)), assistant(2, Some(reply), &[])]
}
fn meta(session: &str, turn: u64) -> Value {
json!({ "agent": "boxmaker0", "boxmaker_session": session, "turn": turn })
}
fn sent(session: &str, turn: u64) -> impl Fn(&Record) -> bool {
let item = Item::Turn {
session: sid(session),
turn,
};
move |r| matches!(r, Record::Sent { item: i, .. } if *i == item)
}
#[test]
fn the_limits() {
assert_eq!(MAX_PART, 25_000);
assert_eq!(MAX_BATCH, 100);
assert!(parts("").is_empty());
assert_eq!(parts("abc"), vec!["abc".to_string()]);
let long = "é".repeat(MAX_PART);
assert_eq!(parts(&long), vec![long.clone()], "characters, not bytes");
let over = format!("{long}xy");
assert_eq!(parts(&over), vec![long, "xy".to_string()]);
}
#[test]
fn a_turn_is_sent_once_as_one_batch() {
let fake = FakeHoncho::start();
let home = Home::new("worker-once");
home.log("mm-a", &[turn("hello", "kyle", "hi")]);
home.report("mm-a", 1);
let mut w = home.worker(&fake, FAST);
assert_eq!(w.step(), Step::Done);
let posts = message_posts(&fake);
assert_eq!(posts.len(), 1);
assert_eq!(
posts[0].path,
"/v3/workspaces/boxmaker0-trusted/sessions/mm-a/messages"
);
assert_eq!(
posts[0].body,
Some(json!({ "messages": [
{ "content": "hello", "peer_id": "kyle", "metadata": meta("mm-a", 1) },
{ "content": "hi", "peer_id": "boxmaker0", "metadata": meta("mm-a", 1) },
] }))
);
// The session was made first, with both peers.
assert_eq!(fake.requests().len(), 5);
assert!(fake.requests()[3].path.ends_with("/sessions"));
let records = home.records();
assert_eq!(records.len(), 2);
assert!(matches!(&records[1], Record::Sent { ids, .. } if *ids == IDS));
fake.clear();
assert_eq!(w.step(), Step::Idle);
assert!(fake.requests().is_empty());
assert!(home.lines().is_empty(), "{:?}", home.lines());
}
#[test]
fn a_text_over_the_limit_is_sent_in_parts() {
let fake = FakeHoncho::start();
let home = Home::new("worker-parts");
let text = "a".repeat(MAX_PART + 1);
let reply = "é".repeat(MAX_PART);
home.log("mm-a", &[turn(&text, "kyle", &reply)]);
home.report("mm-a", 1);
let mut w = home.worker(&fake, FAST);
assert_eq!(w.step(), Step::Done);
let body = message_posts(&fake)[0].body.clone().unwrap();
let got: Vec<(usize, String)> = body["messages"]
.as_array()
.unwrap()
.iter()
.map(|m| {
(
m["content"].as_str().unwrap().chars().count(),
m["peer_id"].as_str().unwrap().to_string(),
)
})
.collect();
assert_eq!(
got,
vec![
(MAX_PART, "kyle".to_string()),
(1, "kyle".to_string()),
(MAX_PART, "boxmaker0".to_string()),
]
);
}
#[test]
fn both_texts_are_neutralised() {
let fake = FakeHoncho::start();
let home = Home::new("worker-neutral");
let text = format!("a{}b", TAGS[0].text);
let reply = format!("c{}d", TAGS[1].text);
home.log("mm-a", &[turn(&text, "kyle", &reply)]);
home.report("mm-a", 1);
let mut w = home.worker(&fake, FAST);
assert_eq!(w.step(), Step::Done);
let body = message_posts(&fake)[0].body.clone().unwrap();
let contents: Vec<String> = body["messages"]
.as_array()
.unwrap()
.iter()
.map(|m| m["content"].as_str().unwrap().to_string())
.collect();
assert_eq!(contents.len(), 2);
for (content, tag) in contents.iter().zip([TAGS[0].text, TAGS[1].text]) {
assert!(!content.contains(tag));
assert!(content.contains("&lt;"), "not neutralised");
}
}
#[test]
fn a_new_speaker_goes_to_the_next_session() {
let fake = FakeHoncho::start();
let home = Home::new("worker-second");
home.log(
"mm-a",
&[turn("one", "kyle", "a"), turn("two", "ana_b", "b")],
);
home.report("mm-a", 2);
let mut w = home.worker(&fake, FAST);
assert_eq!(w.step(), Step::Done);
assert_eq!(w.step(), Step::Done);
let posts = message_posts(&fake);
assert_eq!(posts.len(), 2);
assert!(posts[0].path.ends_with("/sessions/mm-a/messages"));
assert!(posts[1].path.ends_with("/sessions/mm-a-2/messages"));
let second = fake
.requests()
.into_iter()
.find(|r| r.path.ends_with("/sessions") && r.body.as_ref().unwrap()["id"] == "mm-a-2")
.unwrap();
let peers = second.body.unwrap()["peers"].clone();
assert_eq!(peers["kyle"]["observe_me"], true);
assert_eq!(peers["ana_b"]["observe_me"], true);
assert_eq!(peers["boxmaker0"]["observe_me"], false);
}
#[test]
fn an_outage_is_waited_out_and_logged_twice_in_all() {
let fake = FakeHoncho::start();
let home = Home::new("worker-outage");
home.log("mm-a", &[turn("private-alpha", "kyle", "a")]);
home.log("mm-b", &[turn("private-beta", "kyle", "b")]);
home.report("mm-a", 1);
home.report("mm-b", 1);
let mut w = home.worker(&fake, FAST);
fake.set(Mode::Status(503));
let waits: Vec<Step> = (0..6).map(|_| w.step()).collect();
let ms = |n| Step::Backoff(Duration::from_millis(n));
assert_eq!(waits, vec![ms(1), ms(2), ms(4), ms(8), ms(8), ms(8)]);
assert_eq!(home.lines().len(), 1, "{:?}", home.lines());
fake.set(Mode::Fixtures);
assert_eq!(w.step(), Step::Done);
assert_eq!(w.step(), Step::Done);
let lines = home.lines();
assert_eq!(lines.len(), 2, "{lines:?}");
assert_eq!(
lines[0],
"memoryd: Honcho is unreachable (server, HTTP 503); sends wait and are retried; see docs/runbook.md#honcho-unreachable"
);
assert_eq!(
lines[1],
"memoryd: Honcho answers again; waiting sends go on"
);
// In order: mm-a, then mm-b.
let records = home.records();
let a = records.iter().position(sent("mm-a", 1)).unwrap();
let b = records.iter().position(sent("mm-b", 1)).unwrap();
assert!(a < b);
// A new outage starts from the first wait again.
home.log("mm-c", &[turn("c", "kyle", "c")]);
home.report("mm-c", 1);
fake.set(Mode::Hang);
assert_eq!(w.step(), ms(1));
assert!(home.lines()[2].contains("(timeout)"), "{:?}", home.lines());
}
#[test]
fn a_refused_send_is_marked_failed_and_the_next_goes_on() {
let fake = FakeHoncho::start();
let home = Home::new("worker-refused");
home.log("mm-a", &[turn("private-alpha", "kyle", "a")]);
home.log("mm-b", &[turn("private-beta", "kyle", "b")]);
home.report("mm-a", 1);
home.report("mm-b", 1);
let mut w = home.worker(&fake, FAST);
fake.set(Mode::Status(422));
assert_eq!(w.step(), Step::Done);
let failed = home.records().into_iter().find_map(|r| match r {
Record::Failed {
item, status, kind, ..
} => Some((item, status, kind)),
_ => None,
});
assert_eq!(
failed,
Some((
Item::Turn {
session: sid("mm-a"),
turn: 1
},
Some(422),
"status".to_string()
))
);
let lines = home.lines();
assert_eq!(
lines,
vec![
"memoryd: turn 1 of session mm-a was not sent: Honcho refused the request (status, HTTP 422); it is marked failed; see docs/runbook.md#honcho-send-refused"
.to_string()
]
);
fake.set(Mode::Fixtures);
assert_eq!(w.step(), Step::Done);
assert!(home.records().iter().any(sent("mm-b", 1)));
assert_eq!(w.step(), Step::Idle, "the failed turn is not tried again");
}
#[test]
fn a_refused_key_stops_its_workspace_only() {
let fake = FakeHoncho::start();
let home = Home::new("worker-key");
home.log("mm-a", &[turn("a", "kyle", "a")]);
home.log("mm-b", &[turn("b", "kyle", "b")]);
home.report("mm-a", 1);
*home.answer.lock().unwrap() = Ok(SessionStateReply {
class: DataClass::Private,
untrusted: true,
});
home.report("mm-b", 1);
let mut w = home.worker(&fake, FAST);
fake.set(Mode::Status(401));
assert_eq!(w.step(), Step::Done);
assert_eq!(
home.lines(),
vec![
"memoryd: Honcho refused the key of workspace boxmaker0-trusted (HTTP 401); nothing more is sent to it until memoryd restarts; see docs/runbook.md#honcho-key-refused"
.to_string()
]
);
fake.set(Mode::Fixtures);
fake.clear();
assert_eq!(w.step(), Step::Done);
assert!(home.records().iter().any(sent("mm-b", 1)));
assert!(
fake.requests()
.iter()
.all(|r| !r.path.contains("boxmaker0-trusted"))
);
assert_eq!(w.step(), Step::Idle);
// The trusted turn waits: neither sent nor failed.
let sync = home.sync.lock().unwrap();
assert_eq!(sync.ledger().outbox().len(), 1);
assert_eq!(sync.ledger().counts().failed, 0);
}
#[test]
fn a_turn_the_log_no_longer_holds_is_marked_failed() {
let fake = FakeHoncho::start();
let home = Home::new("worker-gone");
home.log("mm-a", &[turn("a", "kyle", "a")]);
home.report("mm-a", 1);
let path = home.dir.path().join("sessions/mm-a/0.jsonl");
std::fs::write(&path, "not json\n").unwrap();
let mut w = home.worker(&fake, FAST);
assert_eq!(w.step(), Step::Done);
assert!(matches!(
home.records().last(),
Some(Record::Failed { status: None, kind, .. }) if kind == "log"
));
assert_eq!(
home.lines(),
vec![
"memoryd: turn 1 of session mm-a cannot be sent (log); it is marked failed; see docs/runbook.md#session-log-damaged"
.to_string()
]
);
assert!(message_posts(&fake).is_empty());
}
#[test]
fn a_turn_without_its_reply_any_more_is_marked_failed() {
let fake = FakeHoncho::start();
let home = Home::new("worker-noreply");
home.log("mm-a", &[turn("a", "kyle", "a")]);
home.report("mm-a", 1);
// The log now ends in a tool round: the reply is gone.
home.log("mm-a", &[turns::running(Some("kyle"))]);
let mut w = home.worker(&fake, FAST);
assert_eq!(w.step(), Step::Done);
assert!(matches!(
home.records().last(),
Some(Record::Failed { status: None, kind, .. }) if kind == "log"
));
assert!(message_posts(&fake).is_empty());
}
#[test]
fn a_refused_key_ends_an_outage() {
let fake = FakeHoncho::start();
let home = Home::new("worker-key-outage");
home.log("mm-a", &[turn("a", "kyle", "a")]);
home.report("mm-a", 1);
let mut w = home.worker(&fake, FAST);
fake.set(Mode::Status(503));
assert!(matches!(w.step(), Step::Backoff(_)));
fake.set(Mode::Status(403));
assert_eq!(w.step(), Step::Done);
let lines = home.lines();
assert_eq!(lines.len(), 3, "{lines:?}");
assert_eq!(
lines[1],
"memoryd: Honcho answers again; waiting sends go on"
);
assert!(lines[2].ends_with("see docs/runbook.md#honcho-key-refused"));
}
#[test]
fn a_turn_too_long_for_one_batch_is_marked_failed() {
let fake = FakeHoncho::start();
let home = Home::new("worker-long");
let text = "a".repeat(MAX_PART * MAX_BATCH);
home.log("mm-a", &[turn(&text, "kyle", "a")]);
home.report("mm-a", 1);
let mut w = home.worker(&fake, FAST);
assert_eq!(w.step(), Step::Done);
assert!(matches!(
home.records().last(),
Some(Record::Failed { status: None, kind, .. }) if kind == "too-long"
));
assert!(fake.requests().is_empty());
}
@@ -0,0 +1,327 @@
//! The Honcho worker's other duties (M5c spec, section 5): with nothing to send it decides what
//! `brokerd` could not answer for; after a restart nothing is sent again, and a session with a
//! decided turn waits again (a session without one does not); a running turn is never decided;
//! actions of later tasks wait; a ledger that cannot be written stops it; no log line holds a
//! turn's text. Then `memoryd` itself: a reported turn reaches Honcho, woken at once, and a key
//! that cannot be read stops the start. Do not edit.
#[path = "support/brokerd.rs"]
mod brokerd;
#[path = "support/honcho.rs"]
mod honcho;
#[path = "support/logs.rs"]
mod logs;
#[path = "support/tmp.rs"]
mod tmp;
#[path = "support/turns.rs"]
mod turns;
#[path = "support/worker.rs"]
mod worker;
use std::process::{Command, Stdio};
use std::sync::{Arc, Mutex};
use std::time::{Duration, Instant};
use brokerd::{Answer, FakeBrokerd};
use bxcore::{Envelope, Message, SessionId, SessionUpdated, read_frame, write_frame};
use honcho::{FakeHoncho, Mode};
use logs::assistant;
use memoryd::config::Config;
use memoryd::honcho::ledger::{Item, Record};
use memoryd::honcho::worker::{Step, Tuning};
use memoryd::serve::{self, StartError};
use tmp::TempDir;
use turns::{clean, running, sid, spoken};
use worker::{FAST, Home};
fn turn(text: &str, speaker: &str, reply: &str) -> Vec<bxcore::LogRecord> {
vec![spoken(text, Some(speaker)), assistant(2, Some(reply), &[])]
}
fn messages(fake: &FakeHoncho) -> usize {
fake.requests()
.iter()
.filter(|r| r.path.ends_with("/messages"))
.count()
}
fn is_sent(records: &[Record], session: &str, turn: u64) -> bool {
let item = Item::Turn {
session: sid(session),
turn,
};
records
.iter()
.any(|r| matches!(r, Record::Sent { item: i, .. } if *i == item))
}
fn decided(records: &[Record], session: &str, turn: u64) -> bool {
let item = Item::Turn {
session: sid(session),
turn,
};
records
.iter()
.any(|r| matches!(r, Record::Decided { item: i, .. } if *i == item))
}
#[test]
fn the_default_waits() {
assert_eq!(
Tuning::DEFAULT,
Tuning {
backoff: Duration::from_secs(5),
backoff_max: Duration::from_secs(600),
idle: Duration::from_secs(30),
}
);
}
#[test]
fn with_nothing_to_send_undecided_turns_are_decided() {
let fake = FakeHoncho::start();
let home = Home::new("worker-retry");
home.log("mm-a", &[turn("a", "kyle", "a")]);
*home.answer.lock().unwrap() = Err("brokerd is down".to_string());
home.report("mm-a", 1);
assert!(!decided(&home.records(), "mm-a", 1));
let mut w = home.worker(&fake, FAST);
assert_eq!(w.step(), Step::Idle, "brokerd still down");
*home.answer.lock().unwrap() = Ok(clean());
assert_eq!(w.step(), Step::Done, "decided now");
assert!(decided(&home.records(), "mm-a", 1));
assert_eq!(w.step(), Step::Done, "sent");
assert!(is_sent(&home.records(), "mm-a", 1));
}
#[test]
fn an_outage_that_ends_is_followed_by_the_retry() {
let fake = FakeHoncho::start();
let home = Home::new("worker-after-outage");
home.log("mm-a", &[turn("a", "kyle", "a")]);
home.log("mm-b", &[turn("b", "kyle", "b")]);
home.report("mm-a", 1);
*home.answer.lock().unwrap() = Err("brokerd is down".to_string());
home.report("mm-b", 1);
let mut w = home.worker(&fake, FAST);
fake.set(Mode::Status(502));
assert!(matches!(w.step(), Step::Backoff(_)));
*home.answer.lock().unwrap() = Ok(clean());
fake.set(Mode::Fixtures);
assert_eq!(w.step(), Step::Done);
// mm-a is sent, and the outage's end decided mm-b before any idle step.
assert!(decided(&home.records(), "mm-b", 1));
}
#[test]
fn a_restart_sends_nothing_again_and_resumes_the_sessions_it_knows() {
let fake = FakeHoncho::start();
let mut home = Home::new("worker-restart");
home.log("mm-a", &[turn("a", "kyle", "a")]);
home.report("mm-a", 1);
home.worker(&fake, FAST).step();
assert_eq!(messages(&fake), 1);
// While memoryd is down: mm-a has a second turn, never reported; mm-z, never seen, one.
home.log("mm-a", &[turn("a", "kyle", "a"), turn("b", "kyle", "b")]);
home.log("mm-z", &[turn("z", "kyle", "z")]);
home.restart();
let mut w = home.worker(&fake, FAST);
assert_eq!(w.step(), Step::Done, "mm-a's second turn decided");
assert_eq!(w.step(), Step::Done, "and sent");
assert_eq!(w.step(), Step::Idle);
let records = home.records();
assert!(is_sent(&records, "mm-a", 2));
assert!(!decided(&records, "mm-z", 1), "a session never reported");
assert_eq!(messages(&fake), 2, "turn 1 was sent again");
}
#[test]
fn a_restart_never_decides_a_running_turn() {
let fake = FakeHoncho::start();
let mut home = Home::new("worker-running");
home.log("mm-a", &[turn("a", "kyle", "a")]);
home.report("mm-a", 1);
home.worker(&fake, FAST).step();
home.log("mm-a", &[turn("a", "kyle", "a"), running(Some("kyle"))]);
home.restart();
let mut w = home.worker(&fake, FAST);
assert_eq!(w.step(), Step::Idle);
assert!(!decided(&home.records(), "mm-a", 2));
}
#[test]
fn actions_of_later_tasks_wait() {
let fake = FakeHoncho::start();
let mut home = Home::new("worker-later");
let conclude = r#"{"type":"decided","time":"2026-09-28T10:00:00.000Z","item":{"type":"edit","id":"2026-09-28-0001","part":0},"action":{"type":"conclude","workspace":"trusted","peer":"kyle","session":"mm-a","text":"a fact"}}"#;
std::fs::write(home.ledger_path(), format!("{conclude}\n")).unwrap();
home.restart();
let mut w = home.worker(&fake, FAST);
assert_eq!(w.step(), Step::Idle);
assert_eq!(home.records().len(), 1, "the conclusion was failed or sent");
assert!(fake.requests().is_empty());
}
#[test]
fn a_ledger_that_cannot_be_written_stops_the_worker() {
let fake = FakeHoncho::start();
let home = Home::new("worker-ledger");
home.log("mm-a", &[turn("a", "kyle", "a")]);
home.report("mm-a", 1);
let mut w = home.worker(&fake, FAST);
let ledger = home.ledger_path();
let kept = std::fs::read_to_string(&ledger).unwrap();
std::fs::remove_file(&ledger).unwrap();
std::fs::create_dir(&ledger).unwrap();
assert_eq!(w.step(), Step::Stopped);
assert_eq!(w.step(), Step::Stopped);
assert_eq!(
messages(&fake),
1,
"sent once; its sent line could not be written"
);
let lines = home.lines();
assert_eq!(lines.len(), 1, "{lines:?}");
assert!(lines[0].ends_with(
"; the Honcho worker stops until memoryd restarts; see docs/runbook.md#honcho-ledger-damaged"
));
std::fs::remove_dir(&ledger).unwrap();
std::fs::write(&ledger, kept).unwrap();
}
#[test]
fn no_log_line_holds_a_turns_text() {
let fake = FakeHoncho::start();
let home = Home::new("worker-quiet");
for (session, status) in [("mm-a", 503), ("mm-b", 422), ("mm-c", 401)] {
home.log(
session,
&[turn("private-question", "kyle", "private-answer")],
);
home.report(session, 1);
let mut w = home.worker(&fake, FAST);
fake.set(Mode::Status(status));
w.step();
}
let lines = home.lines();
assert_eq!(lines.len(), 3, "{lines:?}");
for line in lines {
assert!(!line.contains("private"), "{line}");
}
}
/// `memoryd serve`'s config for `home`, with `[honcho]` at `url`.
fn serve_config(home: &TempDir, url: &str, extra: &str) -> String {
let soul = home.write("etc/soul.md", "You are Boxmaker.\n");
format!(
"[paths]\nhome = \"{}\"\n[memory]\nsoul_starter = \"{}\"\n[honcho]\nurl = \"{url}\"\nagent = \"boxmaker0\"\nowner = \"kyle\"\ntrusted = \"boxmaker0-trusted\"\nuntrusted = \"boxmaker0-untrusted\"\nfleet = \"fleet\"\n{extra}",
home.path().display(),
soul.display()
)
}
#[test]
fn memoryd_sends_a_reported_turn_at_once() {
let fake = FakeHoncho::start();
let dir = TempDir::new("worker-serve");
turns::write_turns(dir.path(), "mm-a", &[turn("a", "kyle", "a")]);
let config = Config::parse(&serve_config(&dir, &fake.url, "")).unwrap();
let _brokerd = FakeBrokerd::start(&config.state_socket(), Answer::State(clean()));
let lines = Arc::new(Mutex::new(Vec::new()));
let sink = Arc::clone(&lines);
let log: serve::Log = Arc::new(move |l: &str| sink.lock().unwrap().push(l.to_string()));
let running = serve::start(config.clone(), log).unwrap();
std::thread::spawn(move || running.run());
// The worker has slept since start (30 s when idle): the report wakes it.
std::thread::sleep(Duration::from_millis(100));
let mut stream = std::os::unix::net::UnixStream::connect(config.loop_socket()).unwrap();
stream
.set_read_timeout(Some(Duration::from_secs(10)))
.unwrap();
let report = Envelope {
v: 1,
id: 1,
r#final: true,
msg: Message::SessionUpdated(SessionUpdated {
session: SessionId::new("mm-a").unwrap(),
turn: 1,
}),
};
write_frame(&mut stream, &report).unwrap();
assert!(matches!(
read_frame(&mut stream).unwrap().msg,
Message::Ok(_)
));
let deadline = Instant::now() + Duration::from_secs(10);
while Instant::now() < deadline && messages(&fake) == 0 {
std::thread::sleep(Duration::from_millis(10));
}
assert_eq!(messages(&fake), 1, "{:?}", lines.lock().unwrap());
}
#[test]
fn a_key_that_cannot_be_read_stops_the_start() {
let fake = FakeHoncho::start();
let dir = TempDir::new("worker-key-start");
let text = serve_config(
&dir,
&fake.url,
"[secrets.honcho_trusted]\nenv = \"MEMORYD_TEST_UNSET_KEY\"\n",
);
let config = Config::parse(&text).unwrap();
let log: serve::Log = Arc::new(|_: &str| {});
let err = match serve::start(config.clone(), log) {
Err(err) => err,
Ok(_) => panic!("memoryd started"),
};
assert!(matches!(err, StartError::Secret(_)), "{err:?}");
assert!(!config.loop_socket().exists(), "a socket was bound");
// The process: exit 1 with the secret's own lines and pointer, not the start pointer.
let path = dir.write("memoryd.toml", &text);
let mut child = Daemon(
Command::new(env!("CARGO_BIN_EXE_memoryd"))
.args(["serve", "--config"])
.arg(&path)
.env_remove("MEMORYD_TEST_UNSET_KEY")
.stdin(Stdio::null())
.stdout(Stdio::null())
.stderr(Stdio::piped())
.spawn()
.unwrap(),
);
let deadline = Instant::now() + Duration::from_secs(10);
let mut code = None;
while Instant::now() < deadline {
if let Ok(Some(status)) = child.0.try_wait() {
code = status.code();
break;
}
std::thread::sleep(Duration::from_millis(20));
}
let _ = child.0.kill();
let _ = child.0.wait();
let mut stderr = String::new();
if let Some(mut pipe) = child.0.stderr.take() {
let _ = std::io::Read::read_to_string(&mut pipe, &mut stderr);
}
assert_eq!(code, Some(1), "{stderr}");
assert!(
stderr.starts_with("memoryd: secret honcho_trusted: "),
"{stderr}"
);
assert!(
stderr.ends_with("\nsee docs/runbook.md#secret-unavailable\n"),
"{stderr}"
);
assert!(!stderr.contains("memoryd-start-failed"), "{stderr}");
}
/// A `memoryd` process, killed and waited for when dropped.
struct Daemon(std::process::Child);
impl Drop for Daemon {
fn drop(&mut self) {
let _ = self.0.kill();
let _ = self.0.wait();
}
}
@@ -0,0 +1,133 @@
//! A Honcho worker for tests, stepped by hand: a home with session logs and a ledger, the fake
//! Honcho, `brokerd` as a closure whose answer the test sets, and the log lines collected. Do not
//! edit.
#![allow(dead_code)] // each test file uses a different part of this module
use std::collections::BTreeMap;
use std::ffi::OsString;
use std::path::PathBuf;
use std::sync::{Arc, Mutex};
use std::time::Duration;
use bxcore::{LogRecord, SessionStateReply, Timestamp};
use memoryd::honcho::client::{Clients, Timeouts};
use memoryd::honcho::config::HonchoConfig;
use memoryd::honcho::ledger::{Ledger, Record};
use memoryd::honcho::turns::{LEDGER, TurnSync};
use memoryd::honcho::worker::{Tuning, Wake, Worker};
use memoryd::serve::Log;
use crate::honcho::FakeHoncho;
use crate::tmp::TempDir;
use crate::turns::{clean, sid, write_turns};
pub const FAST: Tuning = Tuning {
backoff: Duration::from_millis(1),
backoff_max: Duration::from_millis(8),
idle: Duration::from_millis(1),
};
pub fn config(url: &str) -> HonchoConfig {
HonchoConfig {
url: url.to_string(),
agent: "boxmaker0".to_string(),
owner: "kyle".to_string(),
trusted: "boxmaker0-trusted".to_string(),
untrusted: "boxmaker0-untrusted".to_string(),
fleet: "fleet".to_string(),
read: Vec::new(),
keys: BTreeMap::new(),
}
}
pub struct Home {
pub sync: Arc<Mutex<TurnSync>>,
/// What `brokerd` answers.
pub answer: Arc<Mutex<Result<SessionStateReply, String>>>,
pub lines: Arc<Mutex<Vec<String>>>,
pub dir: TempDir,
}
impl Home {
pub fn new(tag: &str) -> Home {
let dir = TempDir::new(tag);
std::fs::create_dir_all(dir.path().join("memory")).unwrap();
Home {
sync: Arc::new(Mutex::new(TurnSync::new(
Ledger::open(&dir.path().join("memory").join(LEDGER)).unwrap(),
"boxmaker0",
&dir.path().join("sessions"),
))),
answer: Arc::new(Mutex::new(Ok(clean()))),
lines: Arc::new(Mutex::new(Vec::new())),
dir,
}
}
pub fn ledger_path(&self) -> PathBuf {
self.dir.path().join("memory").join(LEDGER)
}
/// A new `TurnSync` over the ledger as it is on disk, resumed: what a restart makes.
pub fn restart(&mut self) {
let mut sync = TurnSync::new(
Ledger::open(&self.ledger_path()).unwrap(),
"boxmaker0",
&self.dir.path().join("sessions"),
);
sync.resume();
self.sync = Arc::new(Mutex::new(sync));
}
pub fn log(&self, session: &str, turns: &[Vec<LogRecord>]) {
write_turns(self.dir.path(), session, turns);
}
/// `loopd` reports turn `turn` of `session`: decided now, with `answer`.
pub fn report(&self, session: &str, turn: u64) {
let answer = Arc::clone(&self.answer);
let ask = move |_: &bxcore::SessionId| answer.lock().unwrap().clone();
let lines = Arc::clone(&self.lines);
let log = move |line: &str| lines.lock().unwrap().push(line.to_string());
let now = Timestamp::parse("2026-09-28T10:00:00.000Z").unwrap();
self.sync
.lock()
.unwrap()
.updated(&sid(session), turn, &ask, now, &log);
}
pub fn worker(&self, fake: &FakeHoncho, tuning: Tuning) -> Worker {
let no_env = |_: &str| -> Option<OsString> { None };
let timeouts = Timeouts {
connect: Duration::from_secs(5),
read: Duration::from_millis(300),
};
let (clients, _) = Clients::new(&config(&fake.url), &no_env, timeouts).unwrap();
let answer = Arc::clone(&self.answer);
let lines = Arc::clone(&self.lines);
let log: Log = Arc::new(move |line: &str| lines.lock().unwrap().push(line.to_string()));
Worker::new(
Arc::clone(&self.sync),
clients,
Arc::new(Wake::default()),
Box::new(move |_: &bxcore::SessionId| answer.lock().unwrap().clone()),
log,
tuning,
"boxmaker0",
)
}
/// Every record of the ledger on disk, in order.
pub fn records(&self) -> Vec<Record> {
std::fs::read_to_string(self.ledger_path())
.unwrap_or_default()
.lines()
.map(|l| serde_json::from_str(l).unwrap())
.collect()
}
pub fn lines(&self) -> Vec<String> {
self.lines.lock().unwrap().clone()
}
}
@@ -0,0 +1,24 @@
## honcho-key-refused
**What you see.** `memoryd` logs one line when Honcho refuses a workspace's key, then this entry:
```text
memoryd: Honcho refused the key of workspace boxmaker0-trusted (HTTP 401); nothing more is sent to it until memoryd restarts; see docs/runbook.md#honcho-key-refused
```
**Why.** Each workspace is sent to with its own key, `[secrets.honcho_trusted]`,
`honcho_untrusted` or `honcho_fleet` (M5c spec, section 10), or none. A 401 or 403 means the key
is wrong, expired, or missing where Honcho now wants one. Trying again would be refused again, so
`memoryd` stops sending to that workspace until it restarts; its turns stay waiting in
`memory/honcho.jsonl`, and the other workspaces go on. The key is never printed.
**Confirm.** Which workspace is named, and where its key comes from:
```sh
grep -n -A2 '^\[secrets\.honcho_' /etc/boxmaker/memoryd.toml
```
**Fix.** Put the right key where `[secrets.<name>]` points (see `secret-unavailable` for the
sources), or remove the table if the workspace needs no key, then restart `memoryd`.
**Check.** After the restart the waiting turns are sent, and no line names this entry.
@@ -0,0 +1,31 @@
## honcho-send-refused
**What you see.** `memoryd` logs one line for a turn that Honcho refused, or that could not be
sent at all, then this entry:
```text
memoryd: turn 3 of session mm-chat-1 was not sent: Honcho refused the request (status, HTTP 422); it is marked failed; see docs/runbook.md#honcho-send-refused
```
or `memoryd: turn 3 of session mm-chat-1 cannot be sent (too-long); it is marked failed; …` for a
turn whose text needs more than 100 messages of 25,000 characters.
**Why.** Honcho answered with a 4xx other than 401 or 403, a redirect, or a body `roncho` could
not read; sending the same again would get the same answer, or could store it twice. So the turn
is marked `failed` in `memory/honcho.jsonl`, with the kind and the status, and the next turn goes
on. The line never holds the turn's text or Honcho's answer (a 422 echoes the whole request).
**Confirm.**
```sh
grep -n '"type":"failed"' "$BOXMAKER_HOME/memory/honcho.jsonl"
```
A 422 usually means a name Honcho does not accept, or text over its limit; a 404, a workspace or
session removed on the Honcho side.
**Fix.** A failed turn is not sent again by itself. To send it again after fixing the cause,
stop `memoryd`, keep a copy of the ledger, remove the turn's `failed` line (see
`honcho-ledger-damaged` for what removing a line means), and start `memoryd`.
**Check.** The next turns are sent (`sent` lines follow).
@@ -0,0 +1,30 @@
## honcho-unreachable
**What you see.** `memoryd` logs one line when it cannot reach Honcho, then this entry:
```text
memoryd: Honcho is unreachable (connect); sends wait and are retried; see docs/runbook.md#honcho-unreachable
```
The word in parentheses is the kind: `connect` (nothing answers at `[honcho] url`), `timeout` (5
seconds to connect, or 30 without a byte), `closed`, `io`, or `server, HTTP 5xx` (Honcho answered
with a server error). When a send goes through again, `memoryd` logs `memoryd: Honcho answers
again; waiting sends go on`. Conversations are not affected.
**Why.** Every finished turn that is decided for Honcho waits in the ledger,
`memory/honcho.jsonl`, until it is sent (M5c spec, section 5). While Honcho does not answer,
`memoryd` tries the oldest waiting turn again, waiting 5 seconds, then 10, 20 and so on up to 10
minutes between tries, and logs the outage once, not at every try. Nothing is lost: the turns go,
in order, once Honcho answers. A restart of `memoryd` starts the waits again from 5 seconds.
**Confirm.**
```sh
grep -n '^url' /etc/boxmaker/memoryd.toml
curl -sS -m 5 "<url>/health"
```
**Fix.** Start Honcho, or make the network path to it work (on straylight, rift over the
tailnet: `tailscale status`). If `[honcho] url` is wrong, correct it and restart `memoryd`.
**Check.** `memoryd` logs `Honcho answers again`, and `memory/honcho.jsonl` gains `sent` lines.