Keep prompt reservations briefly after successful dispatch so rapid idle/message/error transitions cannot inject the same follow-up twice.
Route all production session prompt calls through the shared gate, restore skipped background resume state, release holds after abort/recovery paths, and preserve Ralph/ULW loop state when a dispatch is deferred.
Add regression coverage for session routing, static prompt route auditing, team-mode live messaging, model suggestion retries, call-omo-agent reuse, background parent wakes, runtime fallback, compaction recovery, Atlas, and Ralph/ULW loops.
When many background tasks complete in rapid succession while the parent
session is idle, each completion fired its own promptAsync call, stacking
N consecutive `<system-reminder>` user messages with no assistant turn
between. Hyperplan + many parallel explore subagents made this very
visible to the user.
Route the idle-path through the existing pendingParentWakes queue with a
100ms debounce window. Notifications arriving during the debounce join
the same batch, the 150ms settle window also coalesces newcomers, and a
single batched prompt fires to the parent. Busy-path semantics are
unchanged (still 1s retry).
Prior attempts (1c05c60dc, ea55c385b, a337635e3) all coalesced only the
busy-defer path, leaving the idle-immediate-send path uncoalesced.
Reframe the skill's Lifecycle section so the lead treats teams as
ephemeral, one-per-phase units. The moment a phase ends or the shape
no longer fits, call team_delete and spawn a fresh team. Restructure
through delete-then-create, never in place.
Also fixes a misframing in old step 5: team_shutdown_request is a
per-session self-shutdown signal, not a 'wind down the team' command.
team_delete is what tears the whole team down.
mergeWithClaudeCodeAgents deduplicated by raw agent.name.toLowerCase() while
matchesRequestedAgent strips invisible characters, the numeric sort prefix,
and wrapper characters via stripAgentListSortPrefix. A project or user agent
named with a zero-width prefix, quote wrappers, or a sort prefix survived as
a visible duplicate of the hidden native build or demoted plan agent and
matched subagent_type="build" or "plan", which let an OMO orchestrator reach
the hidden execution agent the previous filter was meant to block.
Apply the same canonicalization to the dedup key so visible aliases of hidden
server agents collapse onto the hidden entry instead of bypassing the filter.
Adds three regression tests covering ZWSP, quote-wrapper, and sort-prefix
bypass paths.
bun.lock: refresh platform optionalDependencies to 4.1.1 so frozen-lockfile
install succeeds in CI.
OpenCode injects native execution agents like build (and a demoted plan in OMO mode) as { mode: 'subagent', hidden: true }. The dynamic agent discovery in subagent-discovery.ts only filtered by mode, so a hidden agent still resolved as a callable target via task(). This created a boundary leak: an OMO orchestrator (sisyphus, prometheus, etc.) could delegate work into the hidden native build/plan path instead of the OMO category/skill pipeline.
Add hidden?: boolean to AgentInfo, plumb it through mergeWithClaudeCodeAgents, and skip hidden agents in both findCallableAgentMatch and listCallableAgentNames so hidden natives are neither matched nor advertised in 'Available agents' error messages. The OpenCode SDK Agent type already exposes hidden?: boolean, so no schema work is required.
Verified by adding three regression tests in zauc-mocks-subagent-resolver/subagent-resolver.test.ts: hidden 'build' is rejected, hidden 'plan' is rejected, and hidden agents are excluded from the Available agents list. Full delegate-task suite (395 tests) and call-omo-agent suite (57 tests) pass; bun run typecheck is clean.
Prevent delayed loop-start message counts from overwriting active Ralph Loop state after the loop has already advanced, so ULW completion can still enter Oracle verification instead of iterating forever.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
YeonGyu-Kim