hyperhive/docs/turn-loop.md

152 lines
7.7 KiB
Markdown

# Turn loop + MCP
How the harness wakes up, what it asks claude to do, and what tools
claude has access to in return.
## The loop
Each agent harness (`hive-agent` — one serve-loop binary for all
agents) runs:
1. Long-poll `Recv` on its socket. The host-side broker
(`broker.rs::recv_blocking_batch`) returns immediately if there's
a pending message, otherwise waits up to 30 s for a broker `Sent`
event for this recipient.
2. Pop one message. Peek the remaining inbox depth with `Status`.
3. Emit `LiveEvent::TurnStart { from, body, unread }` onto the SSE
bus.
4. Spawn claude (one process per turn) and pipe the wake prompt
over stdin.
5. Stream stdout (JSON lines) into the bus as
`LiveEvent::Stream(value)`. Pump stderr as `Note`.
6. Wait for claude to exit and classify the turn's outcome from the
stream + exit — success, compaction, rate-limit, auth-failure, or
hard failure. The outcome drives the post-turn action (see
[Turn outcomes](#turn-outcomes)); compaction is handled inside the
session (see
[Compaction](turn-loop/claude-invocation.md#compaction)). Rate-limit
and auth-failure detection is described [below](#failure-detection-and-login).
7. Emit `LiveEvent::TurnEnd { ok, note }`. Sleep `poll_ms` to avoid
tight loops on transient failures.
### Failure detection and login
- **Rate limit** — a `429` / `rate_limit` marker on stderr, or a parsed
`{"type":"error"}` rate-limit event on stdout (conversation-text
mentions don't count), sets the `rate_limited` sentinel, parks for
`HIVE_RATE_LIMIT_SLEEP_SECS` (default 300), then retries. The UI shows
a `⊘ rate limited` badge while parked.
- **Auth failure (401)** — `drive_turn` retries once (transient
token-refresh races clear on retry); a second `AuthFailed` writes
`{state_dir}/hyperhive-needs-login`, requeues the message, and parks in
`wait_for_login` — the same path as a cold boot with no session. The
operator re-auths via the per-agent web UI; the queued message then
drives the next turn.
- **Login detection** — both boot (`login::has_session`, Online vs
NeedsLogin) and `wait_for_login`'s resume check key off the credential
files in `login::CRED_FILE_NAMES` (the set `/logout` deletes).
`wait_for_login` resumes only when that set changes (a new file or a
newer mtime), so stale credentials on disk at the 401 don't trigger an
instant false-resume, and leftover session-history files don't read as a
live session after a logout + container recreate.
## Harness binary shape
Three sibling binaries out of the one `hive-ag3nt` crate, all
role-agnostic. (The earlier split into `hive-ag3nt` + `hive-m1nd`
was collapsed because the privilege boundary lives server-side at
the broker socket (`/run/hive/mcp.sock`): `ManagerRequest` calls are
refused by the standard agent socket regardless of who sends them.)
- `hive-agent` — long-running harness loop (the inbox poll +
claude-pump + ack/requeue cycle described above).
- `hive-agent-mcp` — MCP server. Default: stdio child claude spawns
via `--mcp-config` per turn (the serve loop renders the config to
point at this sibling of its own `/proc/self/exe`). With
`--http <addr>`, runs as a persistent streamable-HTTP daemon
instead (used by the `hive-mcp-http` systemd unit when
`hyperhive.mcp.httpPort` is set).
- `hive-agent-wake --from <name> --body <body>` — push a message into
our own inbox so the next turn fires with the given body. Used by
co-process helpers (scrapers, webhook listeners) to nudge claude on
external events. `--body -` reads from stdin.
### `Surface` trait + zero-sized type tags
`AgentRequest` / `AgentResponse` (= `ManagerRequest` / `ManagerResponse`
type aliases) are the wire types. There is one role: agent.
`bin/hive-agent.rs` factors the turn loop through a `Surface` trait
with one zero-sized impl (`AgentSurface`) wrapping:
- One async method per wire op: `ack_turn`, `requeue_inflight`,
`inbox_unread`, `post_turn_counts`, `send_to_parent`, `recv_next`.
`main()` calls `serve_main::<AgentSurface>` for all roles. The turn
loop (`serve_loop` / `handle_turn`) has no per-role branches.
### Boot wiring
`serve_main` reads `HIVE_PORT` (default `DEFAULT_WEB_PORT`) +
`HIVE_LABEL` (default `"hive"` for standalone runs; the meta
flake sets it unconditionally for any container-deployed agent;
see `docs/conventions.md::Hive identity` for the env stack),
opens turn-stats sqlite, prepares the on-boot files (see
[claude-invocation](turn-loop/claude-invocation.md#on-boot-files)),
installs claude plugins, spawns `forge_notify::run` + `web_ui::serve`,
and either drops into `serve_loop` directly (`Online`) or parks on
the login flow first (`NeedsLogin`).
Plugin install failures are not fatal: each entry comes back as a
human-readable failure string that gets routed via
`Surface::send_to_parent` to the agent's topology parent (the
broker resolves `<parent>` per `topology::parent_of`; root agents
and the manager fall through to operator).
### Turn outcomes
`turn::TurnOutcome` (`Result<bool, TurnError>``Ok(compacted)` on success,
else a `TurnError`) drives the post-claude branch:
| Outcome | Action |
| --- | --- |
| `Ok(_)` (`false` normal / `true` compacted) | `ack_turn` |
| `Err(PromptTooLong)` | `drive_turn` archived the session (the lib already compacted + retried and it still overflowed); requeue inflight so the message redelivers into a fresh session that fits — no status park |
| `Err(RateLimited)` | sleep `HIVE_RATE_LIMIT_SLEEP_SECS` (default 300), requeue inflight, status back to `online` |
| `Err(AuthFailed)` | emit `needs_login_idle` sentinel, requeue inflight, park in `wait_for_login` |
| `Err(SessionNotFound)` | resume + create self-heal both missed ("shouldn't happen"); requeue inflight so the next turn creates fresh — no status park, message not dropped |
| `Err(Failed(err))` | route `[system] \`<qualified-label>\` claude turn failed:\n<err>` to `<parent>` via `send_to_parent` |
After the outcome handler, the stats sink records a row and the
`hyperhive-continue` sentinel (dropped by the `request_next_turn`
MCP tool) is consumed if present. `handle_turn` reports the result
to `serve_loop` via `TurnControl { auth_failed, continue_requested,
pending }`. When a continue was requested, the turn did not
auth-fail, and the inbox is empty (`pending == 0`), `serve_loop`
drives the next turn in-process with a synthetic
`{ from: "self", body: "continue" }` message (`synthetic_continue`)
— it never goes through the broker, so the self-continue doesn't
persist to sqlite or show up as a recv'able inbox message. If real
messages are already pending the continue is dropped: those messages
drive the next turn(s) via `recv_next`, so an explicit self-wake
isn't needed (this is the `request_next_turn` contract — "no effect
if a new inbox message arrives before this turn ends"). The
`should_self_continue` predicate encodes exactly that decision.
## Sub-pages
The rest lives in three topic pages under [`turn-loop/`](turn-loop/):
- **[claude-invocation.md](turn-loop/claude-invocation.md)** — how the harness
spawns `claude --print` each turn, the two-pronged compaction (reactive +
proactive), and the on-boot files it materialises (`--mcp-config`,
`--system-prompt-file`).
- **[config.md](turn-loop/config.md)** — the optional per-agent knobs the meta
flake wires in (reference docs, icon, passwordless sudo, dashboard links,
custom static files, connectivity overrides, claude plugins, cargo message
filtering).
- **[mcp.md](turn-loop/mcp.md)** — the MCP tool surface claude sees: core tools,
privileged tool groups, self-wake, authoritative state, the tool envelope,
and the built-in tool whitelist.
Per-subsystem impl detail lives in each module's `//!` doc-comment; these pages
describe present-state behaviour + wiring, not line-level mechanics.