<feed xmlns='http://www.w3.org/2005/Atom'>
<title>claudomator.git/internal/executor/cascade_test.go, branch fix/dockersandbox-gitpush-host-security</title>
<subtitle>claudomator — task automation server
</subtitle>
<id>https://git.terst.org/claudomator.git/atom?h=fix%2Fdockersandbox-gitpush-host-security</id>
<link rel='self' href='https://git.terst.org/claudomator.git/atom?h=fix%2Fdockersandbox-gitpush-host-security'/>
<link rel='alternate' type='text/html' href='https://git.terst.org/claudomator.git/'/>
<updated>2026-07-03T23:22:42+00:00</updated>
<entry>
<title>feat(executor): add DAG auto-cascade-fail + role-typed subtask spawning (Phase 6)</title>
<updated>2026-07-03T23:22:42+00:00</updated>
<author>
<name>Claude Sonnet 5</name>
<email>noreply@anthropic.com</email>
</author>
<published>2026-07-03T23:22:42+00:00</published>
<link rel='alternate' type='text/html' href='https://git.terst.org/claudomator.git/commit/?id=997cd8b56bc086a02b9c7c006dd62b07b9fcd2f3'/>
<id>urn:sha1:997cd8b56bc086a02b9c7c006dd62b07b9fcd2f3</id>
<content type='text'>
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-&gt;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 &lt;noreply@anthropic.com&gt;
Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs
</content>
</entry>
</feed>
