A subagent inherited the parent's built-in tool list, which correctly has
no `Bash` -- the agent reaches a shell through the `bash` MCP server, not
the built-in. Subagents get no such server, so the intersection was empty
and they could not run a command at all: no commits, no pushes, no gates.
Add `subagent_builtin_tools_for`/`_arg`, which reuse the shared resolver
and append `Bash` only when `Execution` -- the group that gates the `bash`
MCP server -- is present. Only the subagent spawn path calls them, so the
harness's own `--tools`/`--allowedTools` are unchanged.
The capability transfers; the mechanism does not.
Refs #4422
The comments and docs around the empty-`--tools` assert stated a
mechanism: that an empty value parses as *unset* and therefore grants
MORE built-ins than omitting the flag. That claim came from a
measurement, and the installed `claude --help` (2.1.268) says the
opposite in as many words — `Use "" to disable all tools`. One of the two
is wrong and this repo is not the place that settles it.
The rule the code enforces is right under both readings, which is
precisely why it should not be argued from either: we never emit an empty
`--tools`, because what an empty one means is release-dependent and
nothing here wants a subagent with no built-in tools regardless. So the
prose now states the rule and the ambiguity, and asserts nothing about
`""` in either direction — replacing the claim with its opposite would be
the same mistake sourced differently.
No behaviour change: the assert, the resolution and every test are
untouched.
Two test comments also gained the limit they were quietly missing.
`no_spawned_tool_escapes_the_session` hardcodes ten names, so it is a
canary for tools someone thought to list, not a guarantee — the
guarantee is the subset property, which covers tools nobody has invented
yet. And `a_subagent_gets_no_builtin_its_parent_lacks` resolves both
sides in one process off one env var, so it catches a code divergence but
not the two real systemd units disagreeing about `HIVE_TOOL_GROUPS` —
which is what they did until the previous commit, and is not a thing a
unit test can reach.
Refs #4416
`build_config` spawned a subagent with `--dangerously-skip-permissions`
and no `--tools` at all, so it got claude's entire built-in set —
`SendMessage` and `ListAgents` (message peers, or the operator, as its
parent), `Task*` including `TaskStop`, which takes an *agent* id and so
reaches clean outside the run, `Cron*`, `RemoteTrigger` and
`EnterWorktree`/`ExitWorktree`. None of that is part of "do this bounded
task in this directory", and none of it is something the parent agent
itself can do: the harness has always passed `--tools`.
Pass the same one. The value comes from
`hive_sh4re::permissions::builtin_tools_arg()` — literally the function
the harness resolves its own session with — so the subagent's set is the
parent's set, `HIVE_TOOL_GROUPS` and all. That inheritance is the
requirement, not an implementation detail: a hardcoded subagent list
would hand `WebFetch`/`WebSearch` to the subagent of an agent without the
`web_tools` group, which is a privilege escalation, and would drift from
the parent's list the first time anyone added a tool to either.
`--tools` is the real gate: it holds under
`--dangerously-skip-permissions`, unlike `--allowedTools`, which only
auto-approves prompts. It does not filter MCP tools, so the
`goal_reached`/`need_help` signal surface is deliberately unnamed in it
and survives on `--strict-mcp-config` alone.
`build_config`'s doc comment claimed `strict_mcp_config` was *the* safety
property and that a subagent got "nothing implicit and nothing more".
That was false for built-ins, and is what hid this gap for as long as it
did; it now says which flag covers which half and that neither
substitutes for the other.
An empty `--tools` value parses as *unset* and grants more than omitting
the flag, so an empty resolution can only be a bug — `build_config`
asserts against it and a test pins the non-emptiness alongside the
subset-of-parent property.
Refs #4416
A NeedHelp status is waiting for an answer; `Turn 2 of 5` was
competing with the thing the reader actually needs, which is what it
asked for. Cut it at the describe_stopped call site (it already
formats a distinct sentence per stop reason) rather than in
describe_turns/describe_status, so TurnCap — where the count is the
whole point — and the running-turn case are untouched.
Refs #4415
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
`goal_reached`/`need_help` took the session name as a tool argument, so
identity was an assertion by the caller and the only guard on it was
`occupancy()` — "does that name have a turn in flight", which two
concurrently running siblings both satisfy for each other. A subagent
could stop its sibling's run by naming it.
Identity moves into the URL. Each spawned run is minted an unguessable
token (`Uuid::new_v4`, the OS CSPRNG), the URL carrying it goes into that
one subagent's own `--mcp-config`, and the route resolves it back to a
session before dispatching to a handler bound to that session. Neither
tool takes a `name` any more: a subagent has no field in which to name a
sibling, and a sibling's name — which a brief may well mention — is not a
token.
One route with a path parameter, not a route per session: the `Router` is
built once at startup and subagents come and go for the daemon's whole
life. An unminted or revoked token gets a bare 404, the same answer either
way, so nothing enumerates. A run's token is revoked when the run ends
(`finish_turn`) or when a call never reached a spawn.
Two things fall out of that:
- the config file becomes one per session. A single shared path was
already a race between two `start`s; with a per-session URL in it, the
loser would read the winner's identity.
- `occupancy()` stops being the identity guard and is gone from the signal
path entirely rather than kept "just in case" — a revoked token can't
reach it, and it never answered the question it was standing in for.
It still backs `status`, which is what it was always actually for.
Refs #4403
Refs #4413
a_signal_url_reaches_the_subagent_and_a_status_check_renders_no_config
built a config with a signal_url, which makes mcp_config::build write a
real --mcp-config file and resolve hive_agent_sock::paths::harness_dir.
That reads HYPERHIVE_HARNESS_DIR, which the meta flake injects into every
in-container service but a nix-sandboxed cargo test does not set — so the
test passed locally and panicked in CI. Set the var to a scratch dir for
the duration of this one test instead.
Refs #4403
`start` takes an optional `goal`. With one set a session stops being a
single turn: when a turn ends and nothing has said to stop, the daemon
spawns another turn re-prompting the subagent toward that goal, up to
`max_turns` (default 5, per-session). Without a goal nothing changes —
one turn, one todo, same as before.
Four things end a run, each recorded distinctly and reported by `status`:
the turn ending with no goal, `goal_reached`, `need_help`, and the turn
cap. The last says so out loud rather than stopping quietly — the todo
states the harness limit was reached and the goal was never reported
reached. Every stop extends the done message rather than replacing it,
and lands in the session's report file when it has one. The path is
never inferred: it comes from `start`'s `report_file` or from the
subagent naming where it wrote.
`goal_reached` and `need_help` are the subagent's own, served on a second
route (`/signal/mcp`) that carries those two tools and nothing else, so
reporting on a run can't become starting one. `goal_reached` is built as
a label, never a gate: it is self-reported by a subagent that has just
been re-prompted with "you haven't reached the goal", which is exactly
the incentive to claim it — the same failure class as a build report
asserting the tests pass. Every surface that renders it says so.
`need_help` is the blocking signal, and shows in `status` as its own
state so a parent polling it sees the block without reading a file.
`status` also carries `turn N of M`: with 4330's last-event age, that
separates working from wedged from out of turns off one answer.
Two bugs the new tests caught: a `tokio::fs::File` was dropped without
flushing, so the report line was written to nothing, and the plain idle
answer dropped the turn counter.
Also documents `await_resume`'s third case — a closed channel with no
send, which fails open the same as `Underway` — per argus on #4411.
Refs #4403
`continue` returned "started" the instant `Claude::spawn` handed back a
pid, and a resume that matched nothing only surfaced later, as an
end-of-turn todo. By then the caller had moved on believing it had a
running subagent.
A pid is proof enough for `start`, which creates its session: the spawn
succeeding is the whole story. It is not proof for a resume — claude
exits non-zero a fraction of a second *after* the process exists. So
`continue` now waits for the first real answer and reports a miss as its
own `Err`, carrying claude's message and the directory searched.
The wait ends on whichever comes first, so a successful `continue` pays
no fixed delay: the turn's first non-terminal stream event settles it at
about the same moment a miss's exit would have. Measured on this box:
14 runs of the driver's own invocation against a missing session took
550-1087 ms spawn to exit, and a healthy turn's first event lands at
roughly 500 ms. The five-second cap is ~4.6x the slowest miss and is only
ever reached by a child that neither speaks nor exits.
The underway signal reads the event's kind, not its content: a missed
resume is not silent — it emits a terminal `result` event and stderr
before exiting — so "any sink callback" would have reported every miss as
a successful start. Liveness still counts all three callbacks.
The end-of-turn todo is unchanged for every failure later in the turn;
the only one it no longer repeats is the miss the caller was just handed.
Refs #4405
A session cannot be moved between directories, so a hint reading
"pass dir" could be misread as pointing an existing session at any
directory. Say instead that dir names the directory the session was
started in.
Refs #4405
`status` could only answer running / starting / idle / killed / none,
because every turn ran against `&NoopSink` and the whole stream-json
stream was discarded. "Running" describes a wedged subagent exactly as
well as a busy one, leaving a caller to tell them apart from `ps` output
and CPU-time deltas.
So the daemon now keeps a `name -> last_event_at` clock, bumped by
`LivenessSink` on every line of every stream — stream-json events, plain
stdout chatter and stderr alike — and `status` reports its age on a
running answer: a few seconds means working, an age climbing into the
minutes with no end-of-turn todo means wedged. Nothing is read out of the
content; classifying *what* a subagent is doing is a separate question
and waits on its own driver work. In memory with the rest of this
daemon's state, dropped when the turn ends, no persistence.
The clock is seeded at the spawn rather than at the first line, so a
subagent that wedged before emitting anything still reports a climbing
age rather than no age at all — the case an age is worth most in.
Separately, `continue`'s existence pre-check is gone. It could only
repeat the lookup `Claude::spawn` was about to do, and its message —
"no session named `x` exists" — was false in the common failure: the
session existed, just not under the claude home + cwd `build_store`
resolved from. claude's own `--resume` is the authority and exits
non-zero (`does not match any session title`) rather than quietly
starting a fresh session, so the turn fails on its own. `classify_end`
appends the one fact the CLI's message lacks — the directory searched:
claude error: no session matched the requested id or title (searched
<claude_home> for cwd <cwd>; if the session was started elsewhere,
pass `dir`)
The `dirs` map's durability is untouched; whether to persist it stays an
open operator decision.
Module doc, `docs/tools/subagent.md`, the `continue`/`status` tool
descriptions and the `base:claude-subagents` skill all updated — including
`continue`'s `dir` doc, which said "the daemon remembers it" without
saying that a restart is both when it forgets and when you most want it.
Refs #4330
Refs #4405
The `status` tool description enumerated all five states it can report, so
every caller paid for four answers it didn't get and read the explanation
in the wrong place. The description now states only what the tool is for
and that it costs nothing to call; each answer it returns carries its own
meaning and the caller's next move instead — running, starting and idle
were terse, the not-found error terser still, and they had been leaning on
the enumeration to be legible. The killed answer and the end-of-turn todo
are unchanged. `continue`'s description keeps its killed-resume sentence:
that describes what the tool does, not a state it might hand back.
Refs #4326
argus's review on #4333 flagged one real vale error (Microsoft.Contractions):
"did not" in the new "A killed turn" section reads as "didn't" instead. The
rest of the diff's new prose (docs/tools/subagent.md and the tool
descriptions in hive-subagent-mcp/src/mcp.rs) has no other instance of the
same expansion, confirmed both by a local `vale --minAlertLevel=error` run
(clean) and by grepping the added lines. Also tidies session.rs's module doc:
the two `//!` runs split to dodge the 30-line comment-block lint had a bare
trailing `//!` right before the blank separator; dropped so the first run
ends on content.
Refs #4326
A subagent whose claude process died on a signal — the kernel's OOM
killer, a stopped unit, an `interrupt` — was indistinguishable from one
that finished its turn: its entry left the `running` map, `status` fell
through to "a session exists on disk" and answered `idle`, and the
end-of-turn todo said the subagent had "finished". The usual next move
on that reading is `continue`, which resumes work that was cut mid-turn
with nothing having recorded that it was cut.
The driver already preserves how the child ended — `RunningClaude::wait`
returns `Error::Exit` carrying the `ExitStatus`, whose `signal()` is the
whole answer — so this reads it rather than having to recover it:
`classify_end` turns the outcome into `Complete` / `Killed { signal }` /
`Failed`, and `State::finish_turn` remembers a kill against the name
(cleared by the next confirmed spawn under it).
What an agent sees as a result:
- `status` reports the session killed, naming the signal, instead of idle;
- the todo the daemon pushes without being asked says the subagent was
KILLED mid-turn rather than that it finished;
- `continue` still resumes such a session, but its reply says the
previous turn was killed, so no caller carries on from cut-off work
believing it was complete.
Refs #4326
