hive-c0re/hive-sh4re: remove the ask/answer wire protocol + core routing

This commit is contained in:
damocles 2026-08-30 01:18:17 +02:00
commit 2850270829
23 changed files with 177 additions and 851 deletions

View file

@ -15,7 +15,6 @@ use crate::broker::Broker;
use crate::container_view::{self, ContainerView};
use crate::dashboard_events::DashboardEvent;
use crate::job_queue::RunningTransient;
use crate::operator_questions::OperatorQuestions;
use crate::socket_server::{self, AgentSocket};
/// Capacity of the dashboard event channel. Slow browser subscribers
@ -32,7 +31,6 @@ const LAST_STOPPED_RUNNING_KEY: &str = "last_stopped_running";
pub struct Coordinator {
pub broker: Arc<Broker>,
pub approvals: Arc<Approvals>,
pub questions: Arc<OperatorQuestions>,
/// Scheduled-prompts queue. One sqlite connection,
/// internal mutex; the worker drains due rows and the manager
/// handlers insert / cancel through the same handle.
@ -467,7 +465,6 @@ impl Coordinator {
} = env;
let broker = Broker::open(db_path).context("open broker")?;
let approvals = Approvals::open(db_path).context("open approvals")?;
let questions = OperatorQuestions::open(db_path).context("open operator_questions")?;
let scheduled_prompts = crate::scheduled_prompts::ScheduledPrompts::open(db_path)
.context("open scheduled_prompts")?;
// BuildLogs wants a directory (it picks its own `build_logs.sqlite`
@ -496,7 +493,6 @@ impl Coordinator {
Ok(Self {
broker: Arc::new(broker),
approvals: Arc::new(approvals),
questions: Arc::new(questions),
scheduled_prompts: Arc::new(scheduled_prompts),
build_logs,
audit_log,
@ -971,9 +967,8 @@ impl Coordinator {
std::fs::create_dir_all(&agent_dir)
.with_context(|| format!("create agent dir {}", agent_dir.display()))?;
let socket_path = Self::socket_path(name);
// Hand the full Coordinator to the per-agent socket — it
// needs broker + operator_questions to handle the agent-side
// `ask` / `answer` tools, not just the broker.
// Hand the full Coordinator to the per-agent socket — it needs
// more than just the broker (approvals, scheduled_prompts, ...).
let socket = socket_server::start(name, &socket_path, self.clone())?;
self.agents.lock().unwrap().insert(name.to_owned(), socket);
Ok(agent_dir)
@ -1336,17 +1331,15 @@ impl Coordinator {
/// Push a `HelperEvent` into an arbitrary agent's inbox. Encoded
/// the same way as `notify_manager` (sender = `SYSTEM_SENDER`,
/// body = JSON-encoded event). Used to route `QuestionAnswered`
/// events back to the agent that called `ask`, `QuestionAsked`
/// events to the target of a peer question, etc.
/// body = JSON-encoded event) — e.g. `ContainerCrash`, `NeedsUpdate`.
pub fn notify_agent(&self, agent: &str, event: &hive_sh4re::manager::HelperEvent) {
self.notify_agent_from(hive_sh4re::manager::SYSTEM_SENDER, agent, event);
}
/// Same as `notify_agent` but with an explicit sender. Use this
/// when the event originates from a known agent or the operator
/// (e.g. `QuestionAnswered` — the answerer should be the `from`,
/// not `system`) so the recipient's terminal shows the right name.
/// rather than the system itself, so the recipient's terminal
/// shows the right name instead of `system`.
pub fn notify_agent_from(
&self,
from: &str,

View file

@ -29,7 +29,6 @@ mod meta;
mod migrate;
mod paths;
mod priv_client;
mod questions;
mod server;
mod snapshot_push;
mod socket_server;
@ -47,9 +46,7 @@ pub(crate) use agent_config::{capabilities, limits, resource_limits, tool_groups
pub(crate) use stats::{
container_stats, hive_stats, host_stats, otel_metrics, sweep_health, warnings,
};
pub(crate) use stores::{
approvals, audit_log, broker, build_logs, db, operator_questions, power, scheduled_prompts,
};
pub(crate) use stores::{approvals, audit_log, broker, build_logs, db, power, scheduled_prompts};
pub(crate) use workers::{
agent_sockets, auto_update, crash_watch, knowledge, mcp_sockets, scheduled_prompts_worker,
};

View file

@ -1,276 +0,0 @@
//! Shared dispatch helpers for the `Ask` / `Answer` flow. Both the
//! agent socket and the manager socket call into here so the routing
//! semantics — recipient = operator vs. peer agent, answerer
//! authorisation, asker-notification — only live in one place.
//!
//! Routing rules at a glance:
//!
//! - `Ask { to: None | Some("operator") }` → stored with `target = NULL`.
//! ⚠️ As of the ask/answer removal's dashboard-backend slice, nothing
//! surfaces or answers an operator-targeted row any more — the
//! dashboard's questions pane, its `/api/answer-question` /
//! `/api/cancel-question` endpoints, and the `pending_all()`/
//! `recent_answered_all()` reads that fed them are all gone. An
//! operator-targeted `ask()` (if anything still calls it — the MCP
//! tool itself was removed earlier in the same effort) would queue a
//! row nothing can ever resolve. Left as-is rather than special-cased,
//! since the whole `Ask`/`Answer` flow this file implements is itself
//! slated for removal next.
//! - `Ask { to: Some(<agent>) }` → stored with `target = <agent>`;
//! a `HelperEvent::QuestionAsked` is pushed into `<agent>`'s
//! inbox so they can `Answer { id, answer }` on their own socket.
//! - `Answer { id, answer }` → permission-checked in
//! `OperatorQuestions::answer` (only the target agent or the
//! operator can answer; both paths fire the same
//! `QuestionAnswered` event to the asker).
use std::sync::Arc;
use crate::coordinator::Coordinator;
use crate::limits;
use crate::socket_server::spawn_question_watchdog;
/// Cap on how long an asker can demand an answer before the watchdog
/// auto-resolves with `[expired]`. Six hours mirrors typical agent
/// session lifetimes — beyond that an unanswered question is
/// effectively a dead thread and should be re-asked, not blocked on.
const MAX_TTL_SECONDS: u64 = 6 * 60 * 60;
/// Handle either surface's `Ask` request. Returns the queued
/// question id on success or a caller-ready error string. Caller is
/// responsible for wrapping in the matching `*Response::Err` /
/// `QuestionQueued` variant.
pub fn handle_ask(
coord: &Arc<Coordinator>,
asker: &str,
question: &str,
options: &[String],
multi: bool,
ttl_seconds: Option<u64>,
to: Option<&str>,
) -> Result<i64, String> {
limits::check_size("question", question)?;
// Normalise `Some("operator")` → None so the storage layer
// only has to think about NULL vs. non-NULL targets, not
// "is this string the operator?".
let target = match to {
None => None,
Some(t) if t == hive_sh4re::manager::OPERATOR_RECIPIENT => None,
Some("") => {
return Err("ask: `to` cannot be empty (omit it for the operator path)".to_owned());
}
Some(t) if t == asker => {
return Err("ask: cannot ask yourself a question (would loop forever)".to_owned());
}
Some(t) => Some(t),
};
let ttl = ttl_seconds.map(|s| s.min(MAX_TTL_SECONDS));
let deadline_at = ttl.and_then(|s| {
let now = std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.ok()
.and_then(|d| i64::try_from(d.as_secs()).ok())
.unwrap_or(0);
i64::try_from(s).ok().map(|s| now + s)
});
let id = coord
.questions
.submit(asker, question, options, multi, deadline_at, target)
.map_err(|e| format!("{e:#}"))?;
tracing::info!(%id, %asker, ?target, ?deadline_at, "question queued");
// Agent-targeted questions need to wake the recipient — drop a
// QuestionAsked event into their inbox so the answerer doesn't
// have to poll. Operator-targeted questions show up on the
// dashboard's pending pane via `pending()` instead.
if let Some(target_agent) = target {
coord.notify_agent(
target_agent,
&hive_sh4re::manager::HelperEvent::QuestionAsked {
id,
asker: asker.to_owned(),
question: question.to_owned(),
options: options.to_vec(),
multi,
},
);
}
if let Some(t) = ttl {
spawn_question_watchdog(coord, id, t);
}
Ok(id)
}
/// Handle either surface's `Answer` request. Returns `Ok(())` on
/// success or a caller-ready error string. Authorisation lives in
/// `OperatorQuestions::answer` — we only have to wire the result
/// back to the asker as a `QuestionAnswered` event.
pub fn handle_answer(
coord: &Arc<Coordinator>,
answerer: &str,
id: i64,
answer: &str,
) -> Result<(), String> {
limits::check_size("answer", answer)?;
let (question, asker, _target) = coord
.questions
.answer(id, answer, answerer)
.map_err(|e| format!("{e:#}"))?;
tracing::info!(%id, %answerer, %asker, "question answered");
// Use answerer as the broker `from` so the asker's terminal shows
// the real name (agent or "operator") instead of "system".
coord.notify_agent_from(
answerer,
&asker,
&hive_sh4re::manager::HelperEvent::QuestionAnswered {
id,
question,
answer: answer.to_owned(),
answerer: answerer.to_owned(),
},
);
Ok(())
}
/// Handle `CancelLooseEnd` from a per-agent socket. Dispatches by kind, each
/// with its own auth check: question / reminder cancels are ownership-only
/// (an agent cancels its own), and approval cancels require the `approvals`
/// tool-group (the grantable capability) AND ownership — the canceller must
/// be the approval's submitter — so no positional / hardcoded privilege and
/// no cross-agent cancellation. (The operator's cancel-anything path is a
/// separate handler.)
/// On question cancel, fires the `QuestionAnswered` event back to the asker
/// so the harness loop can react (mirrors the operator-cancel dashboard path).
pub fn handle_cancel_loose_end(
coord: &Arc<Coordinator>,
canceller: &str,
kind: hive_sh4re::inbox::CancelLooseEndKind,
id: i64,
) -> Result<(), String> {
match kind {
hive_sh4re::inbox::CancelLooseEndKind::Question => {
// Agent-socket path: never privileged — an agent may only cancel
// its own question (ownership). The operator's cancel-anything
// path goes through a separate handler with `privileged = true`.
let (question, asker, _target) = coord
.questions
.cancel(id, canceller, false)
.map_err(|e| format!("{e:#}"))?;
let sentinel = format!("[cancelled by {canceller}]");
tracing::info!(%id, %canceller, %asker, "question cancelled");
// Only notify the asker if they didn't cancel it themselves.
// Self-cancels are already known to the canceller — sending
// a QuestionAnswered back would cause the harness to process
// its own cancel as an incoming answer.
if asker != canceller {
coord.notify_agent_from(
canceller,
&asker,
&hive_sh4re::manager::HelperEvent::QuestionAnswered {
id,
question,
answer: sentinel.clone(),
answerer: canceller.to_owned(),
},
);
}
Ok(())
}
hive_sh4re::inbox::CancelLooseEndKind::Reminder => {
// Reminders are now agent-local (in-container store) — the
// agent-mcp `cancel_loose_end` tool branches on this kind and
// dials the agent's own socket directly, never forwarding to
// hive-c0re. This arm should be unreachable in practice; kept
// only so the match stays exhaustive.
Err(format!(
"reminder {id}: reminders are handled locally by the agent, \
not by hive-c0re"
))
}
hive_sh4re::inbox::CancelLooseEndKind::Approval => {
// Withdrawing an approval needs the grantable `approvals`
// tool-group (held by any approval-submitting orchestrator)
// AND ownership: only the agent that submitted the approval
// may withdraw it. Without the ownership check, any
// approvals-group agent could cancel any other's approval by
// id. A NULL submitter (legacy row predating the column) is
// treated as operator-initiated (no agent tracking predates
// the column).
check_can_cancel_approval(canceller)?;
let submitter = coord
.approvals
.submitter_of(id)
.map_err(|e| format!("{e:#}"))?
.unwrap_or_else(|| "operator".to_owned());
if submitter != canceller {
return Err(format!(
"cancel_loose_end: approval {id} was submitted by {submitter}, \
not {canceller}; only the submitting agent can withdraw it"
));
}
let approval = coord
.approvals
.mark_cancelled(id, canceller)
.map_err(|e| format!("{e:#}"))?;
tracing::info!(%id, %canceller, agent = %approval.agent, "approval cancelled");
let sha_short = approval
.fetched_sha
.as_deref()
.map(|s| s[..s.len().min(12)].to_owned());
coord.emit_approval_resolved(crate::coordinator::ApprovalResolved {
id: approval.id,
agent: approval.agent.as_str(),
approval_kind: approval.kind.as_str(),
sha_short,
status: "cancelled",
note: approval.note,
description: approval.description,
});
Ok(())
}
}
}
/// Capability guard on the `Approval` cancel arm: the caller must hold the
/// `approvals` tool-group (the grantable capability for approval-submitting
/// orchestrators), checked server-side via `tool_groups::groups_for`. Pulled
/// out so the auth check has its own focused unit test — exercising the full
/// `handle_cancel_loose_end` flow would need a `Coordinator` fixture (broker +
/// sqlite + in-memory questions) we don't have. Keys on a grantable capability,
/// not a positional / hardcoded privilege.
fn check_can_cancel_approval(canceller: &str) -> Result<(), String> {
const APPROVALS_GROUP: &str = "approvals";
if crate::tool_groups::groups_for(canceller)
.iter()
.any(|g| g == APPROVALS_GROUP)
{
Ok(())
} else {
Err(
"cancel_loose_end: cancelling approval rows requires the `approvals` tool group"
.to_owned(),
)
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn approval_cancel_rejects_callers_without_the_approvals_group() {
// A caller that doesn't hold the `approvals` tool-group must not be
// able to cancel approval rows even if it invents an id. The guard is
// server-side so client cooperation is irrelevant — and it keys on a
// grantable capability (the tool-group), not on any agent name.
// `groups_for` of a name with no tool_groups.json entry is empty.
let err = check_can_cancel_approval("nobody-with-no-groups").unwrap_err();
assert!(err.contains("approvals` tool group"), "{err}");
}
}
// Real coverage needs a `Coordinator` fixture (broker + sqlite +
// in-memory questions). Skipped for now — the normalisation branches
// in `handle_ask` are short enough to read line-by-line; once we add
// a coord test harness, drop integration tests here for: self-target
// rejection, operator-string passthrough, agent-to-agent QuestionAsked
// emission, and `Answer` authorisation.

View file

@ -208,37 +208,12 @@ pub(crate) async fn dispatch_shared(
}
hive_core_agent_sock::Request::Wake { from, body } => handle_wake(coord, agent, from, body),
hive_core_agent_sock::Request::Recent { limit } => handle_recent(coord, agent, *limit),
hive_core_agent_sock::Request::Ask {
question,
options,
multi,
ttl_seconds,
to,
} => crate::questions::handle_ask(
coord,
agent,
question,
options,
*multi,
*ttl_seconds,
to.as_ref().map(hive_types::Ident::as_str),
)
.map_or_else(
|message| hive_core_agent_sock::Response::Err { message },
|id| hive_core_agent_sock::Response::QuestionQueued { id },
),
hive_core_agent_sock::Request::Answer { id, answer } => {
crate::questions::handle_answer(coord, agent, *id, answer).map_or_else(
|message| hive_core_agent_sock::Response::Err { message },
|()| hive_core_agent_sock::Response::Ok,
)
}
hive_core_agent_sock::Request::SetStatus { text } => handle_set_status(coord, text),
hive_core_agent_sock::Request::GetAgentMeta { name } => {
handle_get_agent_meta(coord, agent, name.as_ref()).await
}
hive_core_agent_sock::Request::CancelLooseEnd { kind, id } => {
crate::questions::handle_cancel_loose_end(coord, agent, *kind, *id).map_or_else(
handle_cancel_loose_end(coord, agent, *kind, *id).map_or_else(
|message| hive_core_agent_sock::Response::Err { message },
|()| hive_core_agent_sock::Response::Ok,
)
@ -790,6 +765,97 @@ fn handle_get_loose_ends(coord: &Arc<Coordinator>, agent: &str, target: Option<&
}
}
/// Handle `CancelLooseEnd` from a per-agent socket. Dispatches by kind, each
/// with its own auth check: reminder cancels are handled entirely in-container
/// (this arm should be unreachable in practice, kept only so the match stays
/// exhaustive) and approval cancels require the `approvals` tool-group (the
/// grantable capability) AND ownership — the canceller must be the approval's
/// submitter — so no positional / hardcoded privilege and no cross-agent
/// cancellation. (The operator's cancel-anything path is a separate handler.)
fn handle_cancel_loose_end(
coord: &Arc<Coordinator>,
canceller: &str,
kind: hive_sh4re::inbox::CancelLooseEndKind,
id: i64,
) -> Result<(), String> {
match kind {
hive_sh4re::inbox::CancelLooseEndKind::Reminder => {
// Reminders are now agent-local (in-container store) — the
// agent-mcp `cancel_loose_end` tool branches on this kind and
// dials the agent's own socket directly, never forwarding to
// hive-c0re. This arm should be unreachable in practice; kept
// only so the match stays exhaustive.
Err(format!(
"reminder {id}: reminders are handled locally by the agent, \
not by hive-c0re"
))
}
hive_sh4re::inbox::CancelLooseEndKind::Approval => {
// Withdrawing an approval needs the grantable `approvals`
// tool-group (held by any approval-submitting orchestrator)
// AND ownership: only the agent that submitted the approval
// may withdraw it. Without the ownership check, any
// approvals-group agent could cancel any other's approval by
// id. A NULL submitter (legacy row predating the column) is
// treated as operator-initiated (no agent tracking predates
// the column).
check_can_cancel_approval(canceller)?;
let submitter = coord
.approvals
.submitter_of(id)
.map_err(|e| format!("{e:#}"))?
.unwrap_or_else(|| "operator".to_owned());
if submitter != canceller {
return Err(format!(
"cancel_loose_end: approval {id} was submitted by {submitter}, \
not {canceller}; only the submitting agent can withdraw it"
));
}
let approval = coord
.approvals
.mark_cancelled(id, canceller)
.map_err(|e| format!("{e:#}"))?;
tracing::info!(%id, %canceller, agent = %approval.agent, "approval cancelled");
let sha_short = approval
.fetched_sha
.as_deref()
.map(|s| s[..s.len().min(12)].to_owned());
coord.emit_approval_resolved(crate::coordinator::ApprovalResolved {
id: approval.id,
agent: approval.agent.as_str(),
approval_kind: approval.kind.as_str(),
sha_short,
status: "cancelled",
note: approval.note,
description: approval.description,
});
Ok(())
}
}
}
/// Capability guard on the `Approval` cancel arm: the caller must hold the
/// `approvals` tool-group (the grantable capability for approval-submitting
/// orchestrators), checked server-side via `tool_groups::groups_for`. Pulled
/// out so the auth check has its own focused unit test — exercising the full
/// `handle_cancel_loose_end` flow would need a `Coordinator` fixture (broker +
/// sqlite). Keys on a grantable capability, not a positional / hardcoded
/// privilege.
fn check_can_cancel_approval(canceller: &str) -> Result<(), String> {
const APPROVALS_GROUP: &str = "approvals";
if crate::tool_groups::groups_for(canceller)
.iter()
.any(|g| g == APPROVALS_GROUP)
{
Ok(())
} else {
Err(
"cancel_loose_end: cancelling approval rows requires the `approvals` tool group"
.to_owned(),
)
}
}
/// Resolve the target agent name for a *named* `GetLooseEnds` query. Rules:
///
/// - `None` (or `Some(caller)`) → the caller's own threads (always allowed).
@ -1077,43 +1143,18 @@ async fn handle_get_logs(agent: &str, lines: Option<u32>) -> Response {
}
}
/// On `Ask { ttl_seconds: Some(n) }`, sleep n seconds and then try to
/// resolve the question with `[expired]`. If the operator (or any
/// other path) already answered it, `answer()` returns Err and we
/// no-op silently. Otherwise fire a `QuestionAnswered` helper event
/// with `answerer = "ttl-watchdog"` so the asker can distinguish a
/// real answer from a deadline trip without parsing the answer text.
const TTL_SENTINEL: &str = "[expired]";
/// Synthetic `answerer` label used when the ttl watchdog resolves a
/// question instead of a real human / agent. Lives in a distinct
/// namespace from agent names + the operator so the asker can pattern
/// match `event.answerer == "ttl-watchdog"`.
const TTL_ANSWERER: &str = "ttl-watchdog";
#[cfg(test)]
mod tests {
use super::*;
pub fn spawn_question_watchdog(coord: &Arc<Coordinator>, id: i64, ttl_secs: u64) {
let coord = coord.clone();
tokio::spawn(async move {
tokio::time::sleep(std::time::Duration::from_secs(ttl_secs)).await;
// Watchdog has its own answerer label so the authorisation
// check in `answer()` permits it for any target. We bypass
// the public `answer()` path by calling it with the operator
// identity, since the operator is always permitted; the
// event we fire carries the real watchdog label for observers.
if let Ok((question, asker, _target)) =
coord
.questions
.answer(id, TTL_SENTINEL, hive_sh4re::manager::OPERATOR_RECIPIENT)
{
tracing::info!(%id, %asker, "question expired (ttl)");
coord.notify_agent(
&asker,
&hive_sh4re::manager::HelperEvent::QuestionAnswered {
id,
question,
answer: TTL_SENTINEL.to_owned(),
answerer: TTL_ANSWERER.to_owned(),
},
);
}
});
#[test]
fn approval_cancel_rejects_callers_without_the_approvals_group() {
// A caller that doesn't hold the `approvals` tool-group must not be
// able to cancel approval rows even if it invents an id. The guard is
// server-side so client cooperation is irrelevant — and it keys on a
// grantable capability (the tool-group), not on any agent name.
// `groups_for` of a name with no tool_groups.json entry is empty.
let err = check_can_cancel_approval("nobody-with-no-groups").unwrap_err();
assert!(err.contains("approvals` tool group"), "{err}");
}
}

View file

@ -1,14 +1,12 @@
//! Sqlite-backed host-side stores (broker, approval / question /
//! schedule queues, build logs, audit trail, power intent) plus the
//! shared connection open/migration helper (`db`). Each submodule is
//! re-exported at the crate root, so `crate::broker::…` etc. keep
//! working unchanged.
//! Sqlite-backed host-side stores (broker, approval / schedule queues,
//! build logs, audit trail, power intent) plus the shared connection
//! open/migration helper (`db`). Each submodule is re-exported at the
//! crate root, so `crate::broker::…` etc. keep working unchanged.
pub mod approvals;
pub mod audit_log;
pub mod broker;
pub mod build_logs;
pub mod db;
pub mod operator_questions;
pub mod power;
pub mod scheduled_prompts;

View file

@ -1,216 +0,0 @@
//! Question queue. Agents submit via `Ask`; the answer comes from
//! either the operator (for `target IS NULL`) or a peer agent (via
//! `Answer`, for agent-to-agent questions). ⚠️ The dashboard no longer
//! has any UI or endpoint for the operator to actually answer a
//! `target IS NULL` row (removed along with the rest of the dashboard's
//! question surface) — see `questions.rs`'s module doc for the current
//! state of that gap.
//!
//! Despite the file name (kept for git history sanity), this table
//! now stores *all* asynchronous questions in the hive — both the
//! operator-targeted ones and the peer-to-peer ones. `target IS
//! NULL` is the operator path (back-compat with rows written before
//! the column existed); `target = '<agent-name>'` is the
//! agent-to-agent path.
use std::path::Path;
use std::sync::Mutex;
use anyhow::{Context, Result, bail};
use chrono::Utc;
use rusqlite::{Connection, OptionalExtension, params};
use crate::db::Migration;
const SCHEMA: &str = r"
CREATE TABLE IF NOT EXISTS operator_questions (
id INTEGER PRIMARY KEY AUTOINCREMENT,
asker TEXT NOT NULL,
question TEXT NOT NULL,
options_json TEXT NOT NULL,
asked_at INTEGER NOT NULL,
answered_at INTEGER,
answer TEXT
);
CREATE INDEX IF NOT EXISTS idx_operator_questions_pending
ON operator_questions (id) WHERE answered_at IS NULL;
";
/// Ordered schema migrations tracked in `schema_versions` (key
/// `"operator_questions"`). Legacy databases are detected via the `target`
/// column — the last column added before versioning — and fast-forwarded
/// past all known migrations.
const MIGRATIONS: &[Migration] = &[
// v1: `multi` — checkbox-style multi-option questions.
Migration {
sql: "ALTER TABLE operator_questions ADD COLUMN \
multi INTEGER NOT NULL DEFAULT 0",
adds_column: Some(("operator_questions", "multi")),
},
// v2: `deadline_at` — optional TTL after which the watchdog auto-resolves.
Migration {
sql: "ALTER TABLE operator_questions ADD COLUMN deadline_at INTEGER",
adds_column: Some(("operator_questions", "deadline_at")),
},
// v3: `target` — recipient of the question. NULL = operator (back-compat
// default); non-null = peer-to-peer question.
Migration {
sql: "ALTER TABLE operator_questions ADD COLUMN target TEXT",
adds_column: Some(("operator_questions", "target")),
},
];
pub struct OperatorQuestions {
conn: Mutex<Connection>,
}
impl OperatorQuestions {
pub fn open(path: &Path) -> Result<Self> {
let conn = crate::db::open(path, "operator_questions")?;
conn.execute_batch(SCHEMA)
.context("apply operator_questions schema")?;
crate::db::apply_versioned_migrations(&conn, "operator_questions", MIGRATIONS)?;
Ok(Self {
conn: Mutex::new(conn),
})
}
pub fn submit(
&self,
asker: &str,
question: &str,
options: &[String],
multi: bool,
deadline_at: Option<i64>,
target: Option<&str>,
) -> Result<i64> {
let conn = self.conn.lock().unwrap();
let options_json = serde_json::to_string(options).unwrap_or_else(|_| "[]".into());
conn.execute(
"INSERT INTO operator_questions
(asker, question, options_json, multi, deadline_at, target, asked_at)
VALUES (?1, ?2, ?3, ?4, ?5, ?6, ?7)",
params![
asker,
question,
options_json,
i64::from(multi),
deadline_at,
target,
Utc::now().timestamp(),
],
)?;
Ok(conn.last_insert_rowid())
}
/// Mark a pending question answered. `answerer` is who's actually
/// answering: `"operator"`, or an agent's own name when responding
/// via `Answer`. Authorisation:
///
/// - Operator-targeted questions (`target IS NULL`) can only be
/// answered by `"operator"`. (Agents must not be able to spoof
/// answers to operator questions — though as of the dashboard's
/// ask/answer surface being removed, nothing currently calls
/// this with `answerer = "operator"` for a `target IS NULL` row
/// at all; the check stays as a guard, not a live path.)
/// - Agent-targeted questions can only be answered by the
/// declared target agent, OR by `"operator"` (operator override
/// for stuck threads — useful when an agent is offline/down
/// and someone has to close the loop).
///
/// Returns `(question, asker, target)` so the caller can fire the
/// `QuestionAnswered` event with the right answerer label and route
/// it back to the original asker.
pub fn answer(
&self,
id: i64,
answer: &str,
answerer: &str,
) -> Result<(String, String, Option<String>)> {
let conn = self.conn.lock().unwrap();
let row: Option<(String, String, Option<String>, Option<i64>)> = conn
.query_row(
"SELECT question, asker, target, answered_at FROM operator_questions WHERE id = ?1",
params![id],
|row| Ok((row.get(0)?, row.get(1)?, row.get(2)?, row.get(3)?)),
)
.optional()?;
let Some((question, asker, target, answered_at)) = row else {
bail!("question {id} not found");
};
if answered_at.is_some() {
bail!("question {id} already answered");
}
// Authorisation check: must match the target, or be the operator
// (operator-targeted questions are operator-only; the operator
// can additionally override agent-to-agent questions to close
// stuck threads).
let authorised = match target.as_deref() {
None => answerer == hive_sh4re::manager::OPERATOR_RECIPIENT,
Some(t) => answerer == t || answerer == hive_sh4re::manager::OPERATOR_RECIPIENT,
};
if !authorised {
bail!(
"question {id} not addressed to '{answerer}' (target = {:?})",
target
.as_deref()
.unwrap_or(hive_sh4re::manager::OPERATOR_RECIPIENT)
);
}
conn.execute(
"UPDATE operator_questions SET answer = ?1, answered_at = ?2 WHERE id = ?3",
params![answer, Utc::now().timestamp(), id],
)?;
Ok((question, asker, target))
}
/// Cancel a pending question on behalf of `canceller`. Returns
/// `(question, asker, target)` so the caller can fire the usual
/// `QuestionAnswered` event to the asker with a `[cancelled by
/// <canceller>]` sentinel.
///
/// Auth: the canceller must be one of:
/// - the original asker (an agent withdrawing their own ask),
/// - the operator (already covered by the existing `answer` path
/// but allowed here too for symmetry / dashboard cancel),
/// - a `privileged` caller (one that arrived on the manager socket —
/// privileged hive-wide cleanup; derived from the socket, not a
/// name match).
///
/// Not the target — that's covered by `answer` (responding with
/// an actual reply, sentinel or otherwise).
pub fn cancel(
&self,
id: i64,
canceller: &str,
privileged: bool,
) -> Result<(String, String, Option<String>)> {
let conn = self.conn.lock().unwrap();
let row: Option<(String, String, Option<String>, Option<i64>)> = conn
.query_row(
"SELECT question, asker, target, answered_at FROM operator_questions WHERE id = ?1",
params![id],
|row| Ok((row.get(0)?, row.get(1)?, row.get(2)?, row.get(3)?)),
)
.optional()?;
let Some((question, asker, target, answered_at)) = row else {
bail!("question {id} not found");
};
if answered_at.is_some() {
bail!("question {id} already answered/cancelled");
}
let authorised = privileged
|| canceller == asker
|| canceller == hive_sh4re::manager::OPERATOR_RECIPIENT;
if !authorised {
bail!("question {id}: '{canceller}' not allowed to cancel (asker = '{asker}')");
}
let sentinel = format!("[cancelled by {canceller}]");
conn.execute(
"UPDATE operator_questions SET answer = ?1, answered_at = ?2 WHERE id = ?3",
params![sentinel, Utc::now().timestamp(), id],
)?;
Ok((question, asker, target))
}
}

View file

@ -6,8 +6,8 @@
//! Stored as the `agent_power` table in the coordinator DB
//! (`/var/lib/hyperhive/db/broker.sqlite`, one tiny row per agent) —
//! same one-file-many-modules pattern as `approvals` /
//! `operator_questions` / `scheduled_prompts`, each with its own
//! connection. Intent persists across hive-c0re restarts; in-flight
//! `scheduled_prompts`, each with its own connection. Intent persists
//! across hive-c0re restarts; in-flight
//! queue work deliberately does not. Setting `wanted` is never a
//! queued node: operator/intent actions update the row synchronously
//! at request time, then submit the DAG whose terminal `Reconcile`