bxcore: ask_memory's arguments and their shape checks

Co-Authored-By: ornith-1.5-35b-a3b <agent@wntrmute.dev>

docs/implementer-log.md

@@ -6,6 +6,7 @@ reviewer adds findings under "Reviews" once per milestone.
 
 | Task | Date | Status | Gate runs | First gate | Deviations | Notes | Model |
 |---|---|---|---|---|---|---|---|
+| M5c2/01-wire-ask-memory | 2026-09-28 | done | 2 | pass | none | Copied the given test `crates/bxcore/tests/ask_memory_args.rs` from `docs/plans/M5c2/files/`. Step 2 (`cargo build --tests --keep-going -p bxcore`) showed exactly the two named failures: E0432 `unresolved import bxcore::AskMemoryArgs` and E0432 for `bxcore::memory::ASK_MEMORY`, `MAX_QUESTION`, `MAX_WORKSPACE_NAME`, `MAX_WORKSPACES`, `OWN_WORKSPACE`; every other target compiled. Made the edits exactly as the task gives: M1 (module doc naming `ask_memory` and the `[honcho]` content rule), M2 (`ASK_MEMORY`), M3 (`MAX_QUESTION` 2000, `MAX_WORKSPACES` 2, `MAX_WORKSPACE_NAME` 512, `OWN_WORKSPACE` "own"), M4 (`AskMemoryArgs { question, workspaces }` with `deny_unknown_fields`, `workspaces` `serde(default)`), M5 (`check` in the fixed order — the question empty then its length in characters, the number of names, then each name empty/form/repeat — and `asked` returning `["own"]` for an empty list), the private `workspace_name`, M6 (`MemoryCall` doc), X1 (`pub use memory::AskMemoryArgs` in lib.rs after the `log` line, leaving the `pub use memory::{...}` block). No `skip_serializing_if` on `AskMemoryArgs`; `grep -c 'skip_serializing_if'` prints 5. `cargo check -p bxcore` clean. `cargo test` passes: 8 in `ask_memory_args`, 6 in `memory_args`, 5 in `memory_wire`. `git diff --stat` lists only lib.rs (1 added) and memory.rs. `make gate` printed `gate: ok` with 1372 tests (1371 in `cargo test --workspace`, plus the 1 ignored `end_to_end` the gate runs separately; the +8 over the 1364 before is exactly the 8 new `ask_memory_args`). No new dependency, so `Cargo.lock` unchanged. | ornith-1.5-35b-a3b |
 | M5c1/15-memoryd-honcho-began | 2026-09-28 | done | 2 | pass | none | Copied the given tests from `docs/plans/M5c1/files/crates/memoryd/tests/`: the three new `honcho_ledger_began.rs` (5), `honcho_decide_began.rs` (4), `honcho_began_serve.rs` (2) and new versions of `honcho_ledger.rs`, `honcho_ledger_file.rs`, `honcho_decide.rs`, `honcho_turns.rs`, `honcho_naming.rs`, `honcho_serve.rs`, `honcho_mirror.rs`, `honcho_mirror_serve.rs`, `honcho_edits.rs`, `honcho_worker_more.rs`, `honcho_sync.rs` and the support `ledger.rs`, `turns.rs`, `worker.rs` (14 modified, 3 new). Step 2 (`cargo build --tests --keep-going -p memoryd`) showed the 14 named targets not compiling: E0061 (`decide` 5 args, `conclusion` 3), E0432 (`BEFORE_SYNC`), E0559 (`Unconclude` no `peer`), E0599 (no `began`/`begin`/`BeganNotFirst`/`Began`); every other target compiled. Made the edits exactly as the task gives: L1-L13 in `ledger.rs` (`Unconclude.peer`; `Record::Began`; the `BeganNotFirst`/`NotBegun` errors and their two Display lines; the `began`/`records` fields and init, the `first_not_began` check in `open`, the new `began()`, `conclusion` by peer, `check` refusing a second `Began`, `apply` counting records and setting `began`); D1-D5 in `decide.rs` (`Timestamp` import, `BEFORE_SYNC`, the doc, the `began` parameter, the first check on the `User` record's time); T1 (`turns.rs` passing `ledger().began()`); M1 (`mirror.rs` `Unconclude`'s `peer`); W1 (`worker.rs` `conclusion` with `peer`); A1-A2 (`start.rs` imports and `Opened::begin`, writing `Began` once when `began().is_none()`); S1-S2 (`serve.rs` doc and `opened.begin()` after `store.init`, before the sockets). `cargo check -p memoryd` clean after all edits; `cargo test -p memoryd` every suite passes; the other-crates `git diff --stat` is empty. `make gate` printed `gate: ok` with 1345 tests (1344 in `cargo test --workspace`, plus the 1 ignored `end_to_end` the gate runs separately; the +13 over baseline is exactly the 11 in the three new files, 1 more in `honcho_mirror.rs`, 1 more in `honcho_edits.rs`). One `loopd` `pointers` test failed once in a manual full-workspace run under load (`6 passed; 1 failed`) but passes in isolation and in a clean run without my change, and both `make gate` runs printed `gate: ok`: it is a load-dependent flake, not this task (loopd is untouched, the edit is all in memoryd). | ornith-1.5-35b-a3b |
 | M5c1/14-bxctl-memory-sync | 2026-09-28 | done | 1 | pass | none | Copied the two given tests from `docs/plans/M5c1/files/`: `crates/memoryd/tests/honcho_sync.rs` (from `honcho_sync.rs-task14`) and `crates/bxctl/tests/cli_memory_sync.rs`, and the skeleton `crates/memoryd/src/honcho/report.rs`. Step 2 showed exactly the named failures: `honcho_sync` with 5 (E0432 for `memoryd::honcho::report`, E0432 for `...::ledger::Failure`/`label`, two E0599 for `failures`, one E0599 for the missing `Sync`); `cli_memory_sync` with 6 (all the missing `Sync`). Made X1 (`MemoryCommand::Sync`), B1-B3 (`memory sync` parsed as `Ask::Admin(MemoryCommand::Sync, String::new())`, the module doc), U1 (the usage line), L1-L9 (`Failure { item, time, status, kind }`; `State::Failed { time, status, kind }`; the `fails: Vec<Item>` field, kept in `apply` on every `Failed` record; `failures()` oldest first via `filter_map`; renamed private `describe` to public `label`); R1 (`use crate::honcho::report`; `Mirror::report` under the ledger's lock); H1 (`pub mod report;`); S1/S2 (`Sync` answered with `mirror.report()` or `NOT_CONFIGURED`). Copied the skeleton. The task's U1 code block rendered every line with one extra leading space, but the actual `USAGE` literal uses two spaces before a command and six before its explanation (as `cli::usage_explains_the_speaker_flag` enforces), so I matched those. `cargo check -p memoryd` clean after filling the body: `counts()` for the first line, then when `failures()` is non-empty push `"\nfailed, oldest first:"` and each `format!("\n  {}  {}  {}", time.to_rfc3339(), label(&item), kind)` with ` (HTTP {status})` appended when `status` is `Some`. `cargo test` all pass: `honcho_sync` 4, `honcho_ledger` 12, `honcho_ledger_file` 12, `honcho_worker` 12, `cli_memory_sync` 4, every other suite unchanged. `grep -n 'MemoryCommand::Sync'` prints two lines, `git diff --stat -- crates/loopd crates/brokerd crates/gatewayd Cargo.toml Cargo.lock` prints nothing. `make gate` printed `gate: ok` with 1332 tests (1331 in `cargo test --workspace`, plus the 1 ignored `end_to_end` the gate runs separately). No new dependency, so `Cargo.lock` is unchanged. | ornith-1.5-35b-a3b |
 | M5c1/13-memoryd-honcho-edits | 2026-09-28 | done | 1 | pass | none | Copied the given files from `docs/plans/M5c1/files/`: the test `crates/memoryd/tests/honcho_edits.rs` (from `honcho_edits.rs-task13`), new versions of `crates/memoryd/tests/honcho_worker_more.rs` (from `honcho_worker_more.rs-task13`) and `tests/support/honcho.rs` (from `support/honcho.rs`), and the skeletons `crates/memoryd/src/honcho/edits.rs` and `crates/memoryd/src/honcho/start.rs` (given whole). Step 2 showed exactly the named failure: `honcho_edits` with one E0432 (`unresolved import memoryd::honcho::edits`); every other target compiled; `honcho_worker_more` 10, `honcho_client` 13, `honcho_worker` 12 passed. Made H1 (`pub mod edits;` after `pub mod decide;` in `honcho/mod.rs`), H2 (`pub mod start;` after `pub mod naming;`), C1 (`owner: String` field in `Clients`), C2 (`owner: config.owner.clone()` in `Clients::new`) and C3 (`ensure_memory_session`: ensure workspace, the agent's peer, the owner's, then the `<id>_memory` session with both peers `observe_me(false) observe_others(false)`); copied the two skeletons. `cargo check -p memoryd` gave 22 warnings (six unused imports, sixteen unused variables, exactly the task named). Filled its five bodies in the order of the file, deleting each instruction comment and keeping the doc comments, each from its comment and `cargo check` after: `memory_session` (`format!("{}{MEMORY_SUFFIX}", session.as_str())`); `conclude` (`memory_session`, `ensure_memory_session`, `ConclusionCreate::new(neutralise(text), peer, peer).with_session_id(name)` in `ConclusionBatchCreate::new(vec![..])`, `create_conclusions` -> the ids); `unconclude` (`Some(id)` -> `delete_conclusion` then `vec![id]`, `None` -> `Vec::new()`); `fleet_batch` (`Map` metadata `agent`/`boxmaker_session`/`edit`, `parts(neutralise(text))` each `MessageCreate::new(part, agent)` with the metadata); `fleet` (`HonchoSession { name: session id, speakers: [] }`, `ensure_session(Fleet, ...)`, `add_messages` -> the ids). `cargo check` clean. Made W1 (imports: drop `Config`/`Timeouts`/`HonchoConfig`/`mirror`/`state`/`LEDGER`/`read_log`/`StartError`, add `edits`, re-export `start::{Opened, open, spawn}`); W2 (`Job` enum `Turn`/`Conclude`/`Unconclude`/`Fleet`, `Next` holds `item`/`workspace`/`job`); W3 (`label` naming a turn or a part); W4 and W5 (the two log lines use `label(&next.item)`); W6 (`next` matching every `(Item, Action)` pair into a `Job`, `send` dispatching and `send_turn` split out); W7 (the start code removed, it moves to `start.rs`). `cargo check -p memoryd` clean, `worker.rs` 486 lines. Step 6 all pass: `honcho_edits` 10, `honcho_worker_more` 10, `honcho_worker` 12, `honcho_client` 13, `honcho_keys` 3, `honcho_mirror_serve` 6, `honcho_serve` 6. Step 7: `fn open`/`fn spawn` both in `start.rs`, no `Action::Retract` in `worker.rs`, the other-crates `git diff --stat` empty. `cargo fmt --all`; `make gate` printed `gate: ok` with 1324 tests (1313 in `cargo test --workspace`, plus the 10 in `honcho_edits.rs` and the 1 ignored `end_to_end` the gate runs separately). No new dependency, so `Cargo.lock` is unchanged. | ornith-1.5-35b-a3b |