Guard the tool-pair validator when transformed assistant messages belong to a tracked subagent session, while keeping normal main-session orphaned tool_use repair intact.
Constraint: code-yeongyu/oh-my-openagent#3996 reports background Oracle sessions hanging after synthetic placeholder tool_result insertion.
Rejected: disable tool-pair-validator globally | would regress main-session compaction/orphaned tool_use repair.
Confidence: high
Scope-risk: narrow
Directive: Keep subagent skip coverage and normal repair coverage together when changing tool-pair validation.
Tested: bun test src/hooks/tool-pair-validator/hook.test.ts src/plugin/messages-transform.test.ts
Tested: bun run typecheck
Not-tested: live Oracle background task e2e; no remote push or PR comment performed.
The sort shim always placed core agents (sisyphus, hephaestus, prometheus,
atlas) before any custom agent, ignoring the user's configured default_agent
in opencode.json. This caused the TUI to always show Sisyphus as the selected
agent on startup regardless of default_agent.
Add setDefaultAgentForSort() which inserts the configured default_agent at
rank 0 in the sort shim's rank map. Called from applyAgentConfig after
resolving the effective default_agent value.
Fixes#3900
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.
When runtime-fallback aborts an in-flight request to swap in a fallback
model, opencode emits session.error{isAbort:true} as a consequence. The
existing event handler treated that as a user cancellation and called
resetRetryState — wiping attemptCount. Every subsequent provider
auto-retry signal then started over at attempt:1, never reaching
max_fallback_attempts, producing an infinite retry loop firing a new
fallback every ~2 seconds.
The bug only surfaces when the configured fallback target itself
silently fails (e.g. github-copilot quota exhausted): the original
model keeps re-emitting retry signals, our handler keeps "fixing"
them, the counter never advances. Reproducible on upstream/dev HEAD
(5ffbe0e24e).
Fix:
- New `internallyAbortedSessions: Set<string>` on HookDeps tracks
sessions whose abort we triggered ourselves.
- abortSessionRequest in auto-retry.ts adds the session to the set
when called with one of our internal sources:
"session.status.retry-signal", "message.updated.retry-signal",
"session.timeout". The "session.stop" source (user-initiated) is
intentionally NOT marked — that path must still wipe state.
- handleSessionError in event-handler.ts checks the set before the
cancellation branch. If the session is marked, consume the flag
(delete it so a later user-abort still gets the reset) and skip
resetRetryState. The state's attemptCount is preserved, so the
next iteration progresses 1→2→3→... until max_fallback_attempts.
- dispose() clears the new set alongside the other per-session maps.
Tests: 3 new event-handler integration tests cover the fix
(internal-abort preserves state, external-abort still resets,
consecutive internal-abort cycles advance attemptCount). Existing
tests pass: 7/7 on event-handler. Pre-existing 2 dispose-test flakes
on the full runtime-fallback suite were verified to exist on
upstream/dev without this patch — unrelated.
bun run build: pass. bun run typecheck: pass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
resolveModelForDelegateTask returned input.userModel immediately without
availability checking when it was set, silently ignoring the user's
configured fallback_models. Effect: a team-mode category member
(e.g. hyperplan's 'artistry' category) configured with
{ model: "opencode/gemini-3.1-pro", fallback_models: [...] }
spawned with the unreachable primary even though a listed fallback was
reachable, leading to a dropped/broken team member instead of graceful
degradation.
Now, when the provider-models cache is warm AND userFallbackModels is
non-empty, the function verifies userModel is reachable via
fuzzyMatchModel. If not, it iterates userFallbackModels and promotes the
first reachable entry. Cold-cache (first-run) behavior is preserved -
the userModel is returned as-is when availability data is unavailable,
matching the existing 'trust the user' contract covered by the
pre-cache test fixtures.
Adds three regression tests covering: (1) unreachable primary + reachable
fallback -> fallback promoted, (2) reachable primary + reachable fallback
-> primary kept (fast path), (3) unreachable primary + unreachable
fallback -> legacy trust-user behavior preserved.
Sync the PR branch with the newest dev branch and resolve the new import-level conflicts in background-agent manager and runtime-fallback tests. Preserve both the delegated bootstrap coverage from this branch and the newer upstream test utilities and runtime wiring changes, then re-verify the affected delegated fallback suites and typecheck.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
The circuit breaker in manager.ts uses recordToolCall to detect when a subagent gets stuck repeating identical tool_use blocks. It passed partInfo.state?.input as the tool-input signature. When a model (Kimi K2.6 in the reporter's case) emits duplicate tool_use parts faster than the tool actually starts running, state.input is still null, so loop-detector falls back to the bare 'tool::__unknown-input__' signature. As soon as one part has state.input populated (next event), the signature flips to 'tool::{actual-args}' and the consecutive counter resets to 1, repeatedly. The breaker never reaches its 20-call threshold.
Add a top-level input?: Record<string, unknown> field to the local MessagePartInfo interface and prefer state.input when present, falling back to the part's own input when state is still pre-running. The OpenCode part payload carries the tool input as soon as the tool_use block is generated, so this fallback restores signature stability across the model's repeated emissions.
Verification: added 2 regression tests in manager-circuit-breaker.test.ts. Test 1 (reproduce) emits 20 part.updated events with only top-level input and asserts the task is cancelled by the breaker — fails before the fix, passes after. Test 2 confirms that when state.input IS present, it still wins over the top-level input (precedence preserved). All 10 manager-circuit-breaker tests pass, all 20 loop-detector tests pass, typecheck clean.
The task() tool schema declares run_in_background as a REQUIRED parameter, but three prompt-template files contained category-based task() examples that omitted it. When agents copied these patterns into actual tool calls, the runtime validator threw 'run_in_background parameter is REQUIRED', breaking delegation.
Add run_in_background=false to the four offending category-based examples: 2 in src/agents/dynamic-agent-category-skills-guide.ts (Delegation Pattern + Category Domain Matching CORRECT/WRONG pair), 1 in src/agents/hephaestus/gpt-5-3-codex.ts (frontend example), and 1 in src/agents/sisyphus/gemini.ts (Example 4 DELEGATE). Subagent-type explore/librarian examples already correctly use run_in_background=true. atlas/shared-prompt.ts examples were already correct.
Verification: bun test src/agents/ — 373 pass, 0 fail. bun run typecheck — clean. Grep confirms no remaining category task() examples lack the parameter.
YeonGyu-Kim