memoryd: the Honcho workspaces it reads, with their clients and labels

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 |
 |---|---|---|---|---|---|---|---|
+| M5c2/05-memoryd-honcho-readers | 2026-09-29 | done | 1 | pass | none | Copied the given test `crates/memoryd/tests/honcho_read.rs` (new), new versions of `crates/memoryd/tests/honcho_client.rs` and `honcho_start.rs` (they replace the tree's), and the new source `crates/memoryd/src/honcho/read.rs` (complete, no `todo!`). Step 2 (`cargo build --tests --keep-going -p memoryd`) showed exactly the two named failures: `honcho_read` with one E0432 `unresolved import memoryd::honcho::config::RESERVED` and one E0432 `unresolved import memoryd::honcho::read`; every other target compiled. `cargo test --no-fail-fast` on `honcho_client` and `honcho_start` failed the two named tests: `the_timeouts` (`CHAT_READ` is 180 s) and `a_read_key_that_cannot_be_read_stops_memoryd` (memoryd starts instead of stopping). Made the edits exactly as the task gives: H1 (`pub mod read;` after `pub mod naming;` in `honcho/mod.rs`); C1 (`CHAT_READ` = 150 s, doc now `M5c spec, section 9`); C2 (`client` `pub(crate)`); C3 (`key` `pub(crate)`); G1 (`RESERVED` `["own", "untrusted", "fleet"]` before the key names, doc naming section 9); G2 (the reserved-names check in `read_workspace` after the this-agent check, its sentence split with `\` as shown); O1 (`use ...read::{ReadTimeouts, Readers}`); O2 (`Opened::readers` `Arc<Readers>` after `sync`, before `clients`); O3 (`Readers::new` beside `Clients::new`, `StartError::Secret`, the readers' warnings filtered to those not among the writers' then logged once); D1 (the reserved names among the `honcho-config-invalid` reasons in `docs/runbook.md`). `cargo check -p memoryd` clean, no warning. `cargo test` passes: 8 in `honcho_read`, 13 in `honcho_client`, 8 in `honcho_config`, 3 in `honcho_keys` (1 ignored), 5 in `honcho_start`. `git diff --stat -- crates/memoryd/src` lists only `client.rs`, `config.rs`, `mod.rs` and `start.rs`; `git diff --stat -- crates/memoryd/src/serve.rs crates/memoryd/src/recall.rs crates/memoryd/src/worker.rs Cargo.toml Cargo.lock` prints nothing. `make gate` printed `gate: ok` with 1403 tests (1402 in `cargo test --workspace`, plus the 1 ignored `end_to_end` the gate runs separately; the +9 over the 1394 before is exactly the 8 `honcho_read` tests and the 1 new `honcho_start` test). No new dependency, so `Cargo.lock` unchanged. | ornith-1.5-35b-a3b |
 | M5c2/04-loopd-ask-memory | 2026-09-28 | done | 1 | pass | none | Copied the three given tests from `docs/plans/M5c2/files/crates/loopd/tests/`: `ask_memory_tool.rs` (new) and `broker_port_ask_wait.rs` (new), and a new version of `device.rs` (replaces the tree's). Step 2 (`cargo build --tests --keep-going -p loopd`) showed exactly the 14 named failures: `ask_memory_tool` with one E0432 `unresolved imports loopd::memory::ASK_MEMORY`, `loopd::memory::ask_memory_schema` and three E0599 for `m5c` on `Registry`; `broker_port_ask_wait` with one E0432 `unresolved import loopd::broker_port::ASK_MEMORY_WAIT`, five E0599 for `timeout_for` and three for `with_ask_wait`; `device` with one E0599 for `m5c`; every other target compiled. Made the edits exactly as the task gives: S1 (`ASK_MEMORY` = `bxcore::memory::ASK_MEMORY`), S2 (`ask_memory_schema` with `maxItems: 2`, description one string split with `\` as shown); T1 (`m5a()` comment drops `loopd serve`); T2 (`m5c()` inserts `ask_memory` core at index 3 after `m5a()`); N1 (`main.rs` uses `Registry::m5c()`); Y1 (`config/system.md` last sentence names `ask_memory`); P1 (`ASK_MEMORY_WAIT` 180 s before `POINTER`), P2 (`BrokerPort` gains `ask_timeout` after `timeout`), P3 (`new` sets `ask_timeout: ASK_MEMORY_WAIT`, adds `with_ask_wait` via struct update and `timeout_for` matching `ASK_MEMORY` -> `timeout.max(ask_timeout)` else `timeout`), P4 (`with_log` sets `ask_timeout: ASK_MEMORY_WAIT`), P5 (`call` binds `timeout = self.timeout_for(&request.tool)`, uses it for the first deadline), P6 (write timeout), P7 (the pending-frame extension). `cargo check -p loopd` clean, and `grep -n 'self.timeout'` prints the three expected lines. `cargo test` passes: 6 in `ask_memory_tool`, 4 in `broker_port_ask_wait`, 15 in `broker_port`, 2 in `broker_port_bad`, 2 in `broker_port_cap`, 4 in `memory`, 6 in `turn_broker`. `git diff --stat` lists only the five edited files and `device.rs`; `git diff config/system.md | grep -c '^[-+]You are'` prints 2. `make gate` printed `gate: ok` with 1394 tests (1393 in `cargo test --workspace`, plus the 1 ignored `end_to_end`; the +10 over the 1384 before is exactly the 6 in `ask_memory_tool.rs` and 4 in `broker_port_ask_wait.rs`). No new dependency, so `Cargo.lock` unchanged. | ornith-1.5-35b-a3b |
 | M5c2/03-brokerd-ask-memory-wait | 2026-09-28 | done | 1 | pass | none | Copied the given test `crates/brokerd/tests/memory_wait.rs` from `docs/plans/M5c2/files/crates/brokerd/tests/`. Step 2 (`cargo build --tests --keep-going -p brokerd`) showed exactly the 10 named failures: one E0432 `unresolved import brokerd::memory_port::ASK_MEMORY_WAIT`, six E0599 for `wait_for`, three E0599 for `with_ask_wait`; every other target compiled. Made edits W1 (module doc naming `ask_memory` and the `ask_memory` wait of its own), W2 (`use crate::args::ToolName`), W3 (`MEMORY_WAIT` doc now says `recall` or `memory`; added `ASK_MEMORY_WAIT` 170 s after it with no blank line between, `MemoryPort` gains `ask_wait` last, `new` sets `ask_wait: ASK_MEMORY_WAIT`, `with_ask_wait` via struct update, `wait_for` matches `AskMemory` -> `ask_wait` else `wait`), W4 (ask comment `self.wait_for(spec.tool())`), W5 (`ask` binds `wait = self.wait_for(spec.tool())` and uses it for both timeouts). `cargo check -p brokerd` clean. `cargo test -p brokerd --test memory_wait --test memory_port --test ask_memory_tool` passes: 3 in `memory_wait`, 5 in `memory_port`, 9 in `ask_memory_tool`. `git diff --stat` lists only `memory_port.rs`; `grep -n 'MEMORY_WAIT' crates/brokerd/src/main.rs` prints the `use` line and `MemoryPort::new(cfg.memory_socket(), MEMORY_WAIT)`. `make gate` printed `gate: ok` with 1384 tests (1383 in `cargo test --workspace`, plus the 1 ignored `end_to_end`; the +3 over the 1381 before is exactly the 3 new `memory_wait` tests). No new dependency, so `Cargo.lock` unchanged. | ornith-1.5-35b-a3b |
 | M5c2/02-brokerd-ask-memory | 2026-09-28 | done | 1 | pass | none | Copied the given tests from `docs/plans/M5c2/files/crates/brokerd/tests/`: `ask_memory_tool.rs` (new) and new versions of `grants.rs` and `memory_tools.rs`. Step 2 (`cargo build --tests --keep-going -p brokerd`) showed exactly the 11 named failures: one E0432 `unresolved import brokerd::builtin::ASK_MEMORY`, one E0599 for `AskMemory` on `ToolArgs`, nine E0599 for `AskMemory` on `ToolName`; every other target compiled. `cargo test --no-fail-fast` on `grants` and `memory_tools` failed the two named lines (`an_empty_directory_is_a_valid_empty_set`, `grant_files_cannot_name_the_memory_tools_or_take_a_built_in_id`). Made edits A1 (`use bxcore::AskMemoryArgs`), A2 (`ToolName::AskMemory`), A3 (`ask_memory` in `parse`), A4 (`ask_memory` in `as_str`), A5 (`is_memory`), A6 (`ToolArgs::AskMemory`), A7 (`tool()`), A8 (`canonical_json`), A9 (`parse` decodes then runs `check`); B1 (module doc naming the three tools), B2 (`ASK_MEMORY` grant text, `BUILT_IN` sentence naming the three, `sources` with `builtin-ask-memory` last), C1 (`time_limit`), P1 (`matching` takes no constraints), R1 (`runner` no mounts/egress). `cargo check -p brokerd` clean. `cargo test` passes: 9 in `ask_memory_tool`, 17 in `grants`, 4 in `memory_tools`, 5 in `memory_port`, 8 in `runner`. `git diff --stat -- crates/brokerd/src` lists only the five files, not `grants.rs`/`container.rs`/`memory_port.rs`; the other-crates diff is empty. `make gate` printed `gate: ok` with 1381 tests (1380 in `cargo test --workspace`, plus the 1 ignored `end_to_end`; the +9 over the 1372 before is exactly the 9 new `ask_memory_tool` tests). No new dependency, so `Cargo.lock` unchanged. | ornith-1.5-35b-a3b |

docs/runbook.md

@@ -916,9 +916,10 @@ they do not belong in, so `memoryd` checks the section before it starts. The rea
   or a space is not allowed.
 - `agent` and `owner` are the same peer, or two of `trusted`, `untrusted` and `fleet` are the same
   workspace.
-- A `[[honcho.read]]` names this agent, names an agent twice, or names one of this agent's three
-  workspaces; or its `trust` is not `trusted` or `untrusted`, or its `class` not `public`,
-  `private` or `secret` (all lower case).
+- A `[[honcho.read]]` names this agent, names an agent twice, names an agent `own`, `untrusted`
+  or `fleet` (the names `ask_memory` gives this agent's own workspaces), or names one of this
+  agent's three workspaces; or its `trust` is not `trusted` or `untrusted`, or its `class` not
+  `public`, `private` or `secret` (all lower case).
 - A `[secrets.<name>]` is not `honcho_trusted`, `honcho_untrusted`, `honcho_fleet` or
   `honcho_read_<agent>` for an agent in `[[honcho.read]]`; or it does not name exactly one
   well-formed `credential`, `env` or `file` (as in `secret-unavailable`); or there is no