From 997cd8b56bc086a02b9c7c006dd62b07b9fcd2f3 Mon Sep 17 00:00:00 2001 From: Claude Sonnet 5 Date: Fri, 3 Jul 2026 23:22:42 +0000 Subject: feat(executor): add DAG auto-cascade-fail + role-typed subtask spawning (Phase 6) Two prerequisites for safe parallel evaluator fan-out (later phase): 1. Auto-cascade-fail: previously, a failed task's dependents just sat PENDING/QUEUED forever (or until something eventually tried to dispatch them and discovered the dependency was dead). Pool.cascadeFail now fires right after a task lands in a terminal failure state (FAILED/TIMED_OUT/ CANCELLED/BUDGET_EXCEEDED, from handleRunResult, the budget-gate reject path, and the checkDepsReady dependency-failure path), recursively cancelling every not-yet-run dependent (PENDING/QUEUED only -- RUNNING and terminal states are left alone) with a message referencing the upstream failure. A visited-set guards recursion, which turned out to be load-bearing rather than defense-in-depth: task creation does not prevent dependency cycles anywhere in this codebase. Correction to an earlier assumption: internal/executor's waitForDependencies is dead code, never called. The live mechanism is checkDepsReady, invoked synchronously in execute() with a self-requeue via time.AfterFunc. Added a freshness re-check (GetTask, bail if no longer QUEUED) at the top of that block so a task cascade-cancelled while sitting in the requeue loop stops silently instead of hitting an invalid CANCELLED->CANCELLED transition or, worse, still getting dispatched. 2. storeChannel.SpawnSubtask hardcoded Agent.Type: "claude" on every spawned child regardless of what role it should play -- a hard blocker for a Planner/Builder task spawning role-typed evaluator subtasks. SubtaskSpec (internal/agentchannel) gains a Role field; when set, the child task gets Agent.Role instead of a hardcoded Type, so Phase 5's role-resolution picks provider/model from that role's escalation ladder. spec.Role == "" (every existing caller) preserves today's exact behavior byte-for-byte -- proven by an explicit regression test, not just new-feature coverage. Threaded the new `role` parameter through both spawn_subtask transports: the native tool-use loop (internal/agentloop/tools.go) and the MCP tool exposed to ContainerRunner-driven claude/gemini agents (internal/executor/agentmcp.go). go build/vet/test -race -count=1 all pass, full suite (20 packages). Co-Authored-By: Claude Sonnet 5 Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs --- internal/agentchannel/agentchannel.go | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'internal/agentchannel') diff --git a/internal/agentchannel/agentchannel.go b/internal/agentchannel/agentchannel.go index 2730dfa..42eacbc 100644 --- a/internal/agentchannel/agentchannel.go +++ b/internal/agentchannel/agentchannel.go @@ -34,6 +34,14 @@ type SubtaskSpec struct { Instructions string Model string MaxBudgetUSD float64 + // Role, when non-empty, names an internal/role.RoleConfig the child task + // should dispatch through (task.AgentConfig.Role — see Phase 5's + // role-based dispatch in internal/executor.Pool.execute()). When set, the + // storeChannel implementation leaves Agent.Type/Model empty on the child + // so tier 0 of the role's escalation ladder resolves them, exactly like + // any other role-typed task. Empty (the default) preserves the prior + // hardcoded "claude" behavior for backward compatibility. + Role string } // AgentChannel is how a Runner reports agent-originated signals to the rest of -- cgit v1.2.3