container_view: clear live-only fields when stopped (#432)
per mara's review on #433, move the gating from the dashboard into the host so a stopped container's stale on-disk state (rate_limited sentinel, hyperhive-needs-login, last-turn-stats row, status blob) never reaches the wire in the first place. when build_all sees is_running == false: - needs_login → false - ctx_tokens / context_window_tokens → None - rate_limited → false - status_text / status_set_at → None static / declared fields (extra_links, deployed_sha, pending_reminders, needs_update, parent) stay populated regardless of run state. extend AgentMeta (both AgentResponse + ManagerResponse) with a `running: bool` field so get_agent_meta callers can tell whether the target is up — answers the second half of #432 ("agent meta should probably show the info that it is not running as well"). read_agent_status_live wraps the existing read_agent_status with the same is_running gate so the manager/agent socket handlers don't have to know about sentinel semantics. format_agent_meta now prints a `running: yes|no` line so claude sees the run state in plain text alongside hyperhive_rev. frontend follow-up in the same commit: drop the redundant `c.running &&` guards on ctx_tokens / status_text in renderContainers — the backend now guarantees those fields are absent when the container is stopped, so the existing truthy-check is sufficient. the `■ not running` badge + icon / links fetch short-circuits stay (those are pure presentation / network-noise wins the backend can't address).
This commit is contained in:
parent
683e59c757
commit
7b4917b256
6 changed files with 131 additions and 42 deletions
|
|
@ -559,13 +559,13 @@ window.marked = marked;
|
|||
})
|
||||
.catch(() => { /* graceful: agent down → no strip */ });
|
||||
}
|
||||
// Status / runtime badges (#432). Pending transients always win
|
||||
// (start / stop / restart / rebuild is in progress). Otherwise:
|
||||
// when the container is stopped, surface a single `■ stopped`
|
||||
// badge and skip everything that depends on a live harness
|
||||
// (alive / rate-limited / needs-login / ctx / status text);
|
||||
// those badges go stale the moment the harness goes away and
|
||||
// just confuse the operator if we keep showing them.
|
||||
// Status / runtime badges. Pending transients always win
|
||||
// (start / stop / restart / rebuild is in progress). Otherwise,
|
||||
// when the container is stopped, surface a single `■ not
|
||||
// running` badge; the backend has already cleared rate_limited /
|
||||
// needs_login / ctx_tokens / status_text in that case (#432) so
|
||||
// the rest of the chain is a no-op for stopped containers — but
|
||||
// we still want SOME badge there so the row doesn't look empty.
|
||||
if (pending) {
|
||||
head.append(el('span', { class: 'pending-state' },
|
||||
el('span', { class: 'spinner' }, '◐'), ' ', pending + '…'));
|
||||
|
|
@ -603,7 +603,7 @@ window.marked = marked;
|
|||
},
|
||||
`⏰ ${c.pending_reminders}`));
|
||||
}
|
||||
if (c.running && c.ctx_tokens != null) {
|
||||
if (c.ctx_tokens != null) {
|
||||
const k = Math.round(c.ctx_tokens / 1000);
|
||||
// Thresholds track the model's real context window when the
|
||||
// backend supplies it; otherwise fall back to fixed constants.
|
||||
|
|
@ -625,10 +625,11 @@ window.marked = marked;
|
|||
|
||||
// ── agent status text ─────────────────────────────────────────
|
||||
// Self-reported status (via set_status MCP tool) — only fresh
|
||||
// while the harness is up. Skip on stopped containers (#432);
|
||||
// the text is from the last time the harness was running and
|
||||
// just misleads now.
|
||||
if (c.running && c.status_text) {
|
||||
// while the harness is up. The backend already clears
|
||||
// `status_text` on stopped containers (#432) so we can render
|
||||
// unconditionally here: a stopped container simply has no
|
||||
// `status_text` and skips this block naturally.
|
||||
if (c.status_text) {
|
||||
const nowUnix = Math.floor(Date.now() / 1000);
|
||||
const ageStr = c.status_set_at != null
|
||||
? ` (set ${fmtAgeSecs(nowUnix - c.status_set_at)} ago)` : '';
|
||||
|
|
|
|||
|
|
@ -52,6 +52,7 @@ pub enum SocketReply {
|
|||
AgentMeta {
|
||||
name: String,
|
||||
role: String,
|
||||
running: bool,
|
||||
hyperhive_rev: Option<String>,
|
||||
status_text: Option<String>,
|
||||
status_set_at: Option<i64>,
|
||||
|
|
@ -75,12 +76,14 @@ impl From<hive_sh4re::AgentResponse> for SocketReply {
|
|||
hive_sh4re::AgentResponse::AgentMeta {
|
||||
name,
|
||||
role,
|
||||
running,
|
||||
hyperhive_rev,
|
||||
status_text,
|
||||
status_set_at,
|
||||
} => Self::AgentMeta {
|
||||
name,
|
||||
role,
|
||||
running,
|
||||
hyperhive_rev,
|
||||
status_text,
|
||||
status_set_at,
|
||||
|
|
@ -107,12 +110,14 @@ impl From<hive_sh4re::ManagerResponse> for SocketReply {
|
|||
hive_sh4re::ManagerResponse::AgentMeta {
|
||||
name,
|
||||
role,
|
||||
running,
|
||||
hyperhive_rev,
|
||||
status_text,
|
||||
status_set_at,
|
||||
} => Self::AgentMeta {
|
||||
name,
|
||||
role,
|
||||
running,
|
||||
hyperhive_rev,
|
||||
status_text,
|
||||
status_set_at,
|
||||
|
|
@ -270,21 +275,28 @@ fn loose_end_kind_label(kind: hive_sh4re::CancelLooseEndKind) -> &'static str {
|
|||
}
|
||||
|
||||
/// Format helper for `get_agent_meta`: renders an agent's identity +
|
||||
/// current status as a short human-readable block. `name`, `role`, and
|
||||
/// `hyperhive_rev` are always shown; `status` only appears when one is
|
||||
/// set, otherwise the line reads `status: <none>`.
|
||||
/// current status as a short human-readable block. `name`, `role`,
|
||||
/// `hyperhive_rev`, and `running` are always shown; `status` only
|
||||
/// appears when one is set, otherwise the line reads `status: <none>`.
|
||||
/// When `running` is false the host has already cleared `status_text`
|
||||
/// (it would be stale from before the stop, #432) so the status line
|
||||
/// is implicitly `<none>` in that case — but the explicit `running:
|
||||
/// no` line tells the caller WHY.
|
||||
#[must_use]
|
||||
pub fn format_agent_meta(resp: Result<SocketReply, anyhow::Error>) -> String {
|
||||
match resp {
|
||||
Ok(SocketReply::AgentMeta {
|
||||
name,
|
||||
role,
|
||||
running,
|
||||
hyperhive_rev,
|
||||
status_text,
|
||||
status_set_at,
|
||||
}) => {
|
||||
let rev = hyperhive_rev.as_deref().unwrap_or("<unknown>");
|
||||
let mut out = format!("name: {name}\nrole: {role}\nhyperhive_rev: {rev}");
|
||||
let run = if running { "yes" } else { "no" };
|
||||
let mut out =
|
||||
format!("name: {name}\nrole: {role}\nhyperhive_rev: {rev}\nrunning: {run}");
|
||||
match status_text {
|
||||
None => out.push_str("\nstatus: <none>"),
|
||||
Some(s) => {
|
||||
|
|
|
|||
|
|
@ -246,8 +246,12 @@ async fn dispatch(req: &AgentRequest, agent: &str, coord: &Arc<Coordinator>) ->
|
|||
}
|
||||
AgentRequest::GetAgentMeta { name } => {
|
||||
let target = name.as_deref().unwrap_or(agent);
|
||||
let (status_text, status_set_at) =
|
||||
crate::container_view::read_agent_status(target);
|
||||
// #432: gate status on the target's running state so a
|
||||
// stopped container's stale on-disk status doesn't leak
|
||||
// through. Also surface `running` itself so callers can
|
||||
// tell (e.g. "iris is down" vs "iris has no status set").
|
||||
let (status_text, status_set_at, running) =
|
||||
crate::container_view::read_agent_status_live(target).await;
|
||||
let role = if target == hive_sh4re::MANAGER_AGENT {
|
||||
"manager"
|
||||
} else {
|
||||
|
|
@ -257,6 +261,7 @@ async fn dispatch(req: &AgentRequest, agent: &str, coord: &Arc<Coordinator>) ->
|
|||
AgentResponse::AgentMeta {
|
||||
name: target.to_owned(),
|
||||
role,
|
||||
running,
|
||||
hyperhive_rev: crate::auto_update::current_flake_rev(&coord.hyperhive_flake),
|
||||
status_text,
|
||||
status_set_at,
|
||||
|
|
|
|||
|
|
@ -117,14 +117,6 @@ pub async fn build_all(coord: &Coordinator) -> Vec<ContainerView> {
|
|||
};
|
||||
let deployed_full = locked.get(&format!("agent-{logical}")).map(std::string::String::as_str);
|
||||
let needs_update = crate::auto_update::agent_config_pending(&logical, deployed_full);
|
||||
// needs_login fires when EITHER the claude session dir is
|
||||
// missing (boot-time / fresh container) OR the harness wrote
|
||||
// the auth-failed sentinel because a turn hit 401 (#419). The
|
||||
// manager has its own session lifecycle and never participates
|
||||
// in needs_login.
|
||||
let needs_login = !is_manager
|
||||
&& (!claude_has_session(&Coordinator::agent_claude_dir(&logical))
|
||||
|| auth_failed_sentinel(&logical));
|
||||
let deployed_sha = deployed_full.map(|s| s[..s.len().min(12)].to_owned());
|
||||
// Recipient name the broker uses for this agent — sub-agents
|
||||
// are addressed by logical name, the manager by the
|
||||
|
|
@ -140,18 +132,41 @@ pub async fn build_all(coord: &Coordinator) -> Vec<ContainerView> {
|
|||
.broker
|
||||
.count_pending_reminders_for(reminder_recipient)
|
||||
.unwrap_or(0);
|
||||
let last_turn = read_last_turn(&logical);
|
||||
let ctx_tokens = last_turn.as_ref().map(|(toks, _)| *toks);
|
||||
let context_window_tokens = last_turn
|
||||
.as_ref()
|
||||
.and_then(|(_, model)| resolve_ctx_window(model, &coord.context_window_tokens));
|
||||
let rate_limited = is_rate_limited(&logical);
|
||||
let extra_links = read_dashboard_links(&logical);
|
||||
let (status_text, status_set_at) = read_status(&logical);
|
||||
let parent = topology.get(&logical).cloned().flatten();
|
||||
let running = lifecycle::is_running(&logical).await;
|
||||
// Live-only fields (#432) — only meaningful while the harness
|
||||
// is up. When the container is stopped, sentinel files +
|
||||
// turn-stats rows + the on-disk status blob are all stale
|
||||
// snapshots from before the stop, so we clear them here
|
||||
// rather than letting the dashboard / `get_agent_meta` surface
|
||||
// misleading values. Static / declared fields (extra_links,
|
||||
// deployed_sha, pending_reminders, needs_update, parent) stay
|
||||
// populated regardless of run state.
|
||||
let (needs_login, ctx_tokens, context_window_tokens, rate_limited, status_text, status_set_at) =
|
||||
if running {
|
||||
// needs_login fires when EITHER the claude session dir is
|
||||
// missing (boot-time / fresh container) OR the harness wrote
|
||||
// the auth-failed sentinel because a turn hit 401 (#419). The
|
||||
// manager has its own session lifecycle and never participates
|
||||
// in needs_login.
|
||||
let needs_login = !is_manager
|
||||
&& (!claude_has_session(&Coordinator::agent_claude_dir(&logical))
|
||||
|| auth_failed_sentinel(&logical));
|
||||
let last_turn = read_last_turn(&logical);
|
||||
let ctx_tokens = last_turn.as_ref().map(|(toks, _)| *toks);
|
||||
let context_window_tokens = last_turn
|
||||
.as_ref()
|
||||
.and_then(|(_, model)| resolve_ctx_window(model, &coord.context_window_tokens));
|
||||
let rate_limited = is_rate_limited(&logical);
|
||||
let (status_text, status_set_at) = read_status(&logical);
|
||||
(needs_login, ctx_tokens, context_window_tokens, rate_limited, status_text, status_set_at)
|
||||
} else {
|
||||
(false, None, None, false, None, None)
|
||||
};
|
||||
out.push(ContainerView {
|
||||
port: lifecycle::agent_web_port(&logical),
|
||||
running: lifecycle::is_running(&logical).await,
|
||||
running,
|
||||
container: c.clone(),
|
||||
name: logical,
|
||||
is_manager,
|
||||
|
|
@ -219,6 +234,10 @@ fn auth_failed_sentinel(name: &str) -> bool {
|
|||
/// Read the agent's free-text status and the Unix timestamp when it was last set
|
||||
/// (derived from the file's mtime). Returns `(None, None)` when the file is absent
|
||||
/// or empty. `pub` so `agent_server` and `manager_server` can populate `AgentMeta`.
|
||||
///
|
||||
/// NB: callers building `AgentMeta` for a *stopped* container should
|
||||
/// clear the result — the on-disk status is a stale snapshot from
|
||||
/// before the stop (#432). Use `read_agent_status_live` for that.
|
||||
pub fn read_agent_status(name: &str) -> (Option<String>, Option<i64>) {
|
||||
let path = Coordinator::agent_notes_dir(name).join("hyperhive-status");
|
||||
let meta = std::fs::metadata(&path).ok();
|
||||
|
|
@ -237,6 +256,34 @@ fn read_status(name: &str) -> (Option<String>, Option<i64>) {
|
|||
read_agent_status(name)
|
||||
}
|
||||
|
||||
/// Wraps `read_agent_status` with the same "stopped containers have
|
||||
/// stale state" gate `build_all` uses (#432). Returns
|
||||
/// `(None, None, false)` when the container isn't running so callers
|
||||
/// don't have to know about the sentinel rules — they just hand back
|
||||
/// what we give them.
|
||||
///
|
||||
/// Returned tuple is `(status_text, status_set_at, running)`. The
|
||||
/// `name` argument is the broker-side recipient — `MANAGER_AGENT` for
|
||||
/// the manager, the logical agent name otherwise — so callers can
|
||||
/// reuse the same string they used to look the agent up.
|
||||
pub async fn read_agent_status_live(name: &str) -> (Option<String>, Option<i64>, bool) {
|
||||
// The lifecycle helper wants the on-disk name (`hm1nd` for the
|
||||
// manager, the bare logical name for sub-agents) and internally
|
||||
// adds the `h-` prefix. Map the broker-side `MANAGER_AGENT`
|
||||
// sentinel back to the lifecycle name here so callers don't have
|
||||
// to bother.
|
||||
let lifecycle_name = if name == hive_sh4re::MANAGER_AGENT {
|
||||
lifecycle::MANAGER_NAME
|
||||
} else {
|
||||
name
|
||||
};
|
||||
if !lifecycle::is_running(lifecycle_name).await {
|
||||
return (None, None, false);
|
||||
}
|
||||
let (text, set_at) = read_agent_status(name);
|
||||
(text, set_at, true)
|
||||
}
|
||||
|
||||
/// Read the agent's most recent completed turn from its turn-stats
|
||||
/// `SQLite`: the context-window size (prompt tokens) and the model name.
|
||||
/// Returns `None` when the file is absent or has no rows. Best-effort
|
||||
|
|
|
|||
|
|
@ -494,12 +494,17 @@ async fn dispatch(req: &ManagerRequest, coord: &Arc<Coordinator>) -> ManagerResp
|
|||
}
|
||||
ManagerRequest::GetAgentMeta { name } => {
|
||||
let target = name.as_deref().unwrap_or(MANAGER_AGENT);
|
||||
let (status_text, status_set_at) =
|
||||
crate::container_view::read_agent_status(target);
|
||||
// #432: gate status on the target's running state so a
|
||||
// stopped container's stale on-disk status doesn't leak
|
||||
// through. Also surface `running` itself so callers can
|
||||
// tell (e.g. "iris is down" vs "iris has no status set").
|
||||
let (status_text, status_set_at, running) =
|
||||
crate::container_view::read_agent_status_live(target).await;
|
||||
let role = if target == MANAGER_AGENT { "manager" } else { "agent" }.to_owned();
|
||||
ManagerResponse::AgentMeta {
|
||||
name: target.to_owned(),
|
||||
role,
|
||||
running,
|
||||
hyperhive_rev: crate::auto_update::current_flake_rev(&coord.hyperhive_flake),
|
||||
status_text,
|
||||
status_set_at,
|
||||
|
|
|
|||
|
|
@ -517,14 +517,20 @@ pub enum AgentResponse {
|
|||
/// `GetAgentMeta` result: identity + status metadata for an agent.
|
||||
/// `role` is `"agent"` for sub-agents and `"manager"` for the
|
||||
/// manager. `hyperhive_rev` is `None` only when the configured
|
||||
/// flake URL has no canonical path. `status_text` is the last value
|
||||
/// written via `SetStatus`, or `None` when none has been set or the
|
||||
/// agent name is unknown. `status_set_at` is a Unix timestamp
|
||||
/// (seconds since epoch) of when the status was last written;
|
||||
/// `None` when no status is set.
|
||||
/// flake URL has no canonical path. `running` reflects whether the
|
||||
/// target's container is currently up (#432); when it's false,
|
||||
/// `status_text` / `status_set_at` are intentionally cleared by the
|
||||
/// host because the on-disk values are stale snapshots from before
|
||||
/// the stop. `status_text` is the last value written via
|
||||
/// `SetStatus`, or `None` when none has been set or the agent name
|
||||
/// is unknown. `status_set_at` is a Unix timestamp (seconds since
|
||||
/// epoch) of when the status was last written; `None` when no
|
||||
/// status is set.
|
||||
AgentMeta {
|
||||
name: String,
|
||||
role: String,
|
||||
#[serde(default = "default_true")]
|
||||
running: bool,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
hyperhive_rev: Option<String>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
|
|
@ -534,6 +540,14 @@ pub enum AgentResponse {
|
|||
},
|
||||
}
|
||||
|
||||
/// Serde default for the `running` field on legacy wire payloads that
|
||||
/// predate #432 — older harnesses never serialised it, and `true`
|
||||
/// matches the historical assumption (the host only knew how to ask
|
||||
/// about live containers).
|
||||
fn default_true() -> bool {
|
||||
true
|
||||
}
|
||||
|
||||
// -----------------------------------------------------------------------------
|
||||
// Manager socket — /run/hyperhive/manager/mcp.sock on the host, bind-mounted
|
||||
// into the manager container at /run/hive/mcp.sock.
|
||||
|
|
@ -944,10 +958,15 @@ pub enum ManagerResponse {
|
|||
ReminderRollup(ReminderStats),
|
||||
/// Mirror of `AgentResponse::AgentMeta` on the manager surface.
|
||||
/// `role` is `"manager"` for the manager and `"agent"` for any
|
||||
/// sub-agent looked up by name.
|
||||
/// sub-agent looked up by name. `running` is false when the
|
||||
/// target's container is stopped (#432) — in that case
|
||||
/// `status_text` / `status_set_at` are cleared by the host so
|
||||
/// stale pre-stop values don't leak through.
|
||||
AgentMeta {
|
||||
name: String,
|
||||
role: String,
|
||||
#[serde(default = "default_true")]
|
||||
running: bool,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
hyperhive_rev: Option<String>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
|
|
|
|||
Loading…
Reference in a new issue