agentlas 1.0.8 → 1.0.9

package/CHANGELOG.md

@@ -1,5 +1,32 @@
 # Changelog
 
+## 1.0.9 — 2026-07-27
+
+Three repairs of one mistake, found by a live run that a 4-agent task force
+(two of them managers over 8 and 10 sub-workers) completed in full before the
+result was thrown away.
+
+- **Field bounds are now stated in the prompt that must obey them.** A nested
+  manager wrote a synthesis brief over 2,000 characters and the whole run —
+  20 model calls, 14 minutes, every worker's finished output — was discarded
+  on a contract error. The engine enforced that ceiling and had never told the
+  manager it existed, so the one repair attempt it does allow failed the same
+  way. Every enforced bound now appears in the stage's schema requirements
+  with headroom (1,900 against a 2,000 ceiling).
+- **An empty worker deliverable reaches its retry.** The corrective re-run had
+  always existed but a contract assertion fired first, so it was dead code.
+- **A failed nested team leaves a real ledger.** Nested executions were
+  recorded only on success, so a mid-flight failure left `nestedExecutions`
+  empty while 20 model calls had already been billed, and the failure receipt
+  minted an `invocationId` with `crypto.randomUUID()` that had never named a
+  real call. Nested runs are now written as `running` when they start and
+  updated per stage; stages that never ran stay `null` rather than invented,
+  and failures carry the real invocation id.
+
+These four defects (with the verifier overflow in 1.0.7) share one shape: a
+fail-closed assertion placed ahead of the repair path it makes unreachable,
+enforcing a limit the other side was never told. Four regression tests pin it.
+
 ## 1.0.8 — 2026-07-27
 
 - **Arrow keys navigate the slash palette instead of collapsing it.** Moving

package/engine/agentlas-workforce.cjs

@@ -1737,6 +1737,9 @@ function buildPrompts(task, identity) {
     "Choose capabilityBindingPlan.inventory only from POLICY_FILTERED_LOCAL_TOOL_MENU_DATA. Cover every requiredToolCapabilities id exactly once for each slot/release pair. One selected tool row may cover multiple capabilities. If a required capability has no exact ready tool, do not invent a binding; return the best schema-valid plan and allow deterministic validation to reject it.",
     "Each bound inventory row must explicitly contain slotId, agentReleaseId, permissionPolicyDigest, provider, toolId, capabilityIds, status=bound. An empty inventory is required when every slot has no required tool capability.",
     "synthesis must explicitly author slotId, agentReleaseId, and brief. verifier must explicitly author slotId, agentReleaseId, brief, and a non-empty criteria array. The host will not add, remove, normalize, or substitute a release or field.",
+    // 호스트가 강제하는 상한을 미리 알려준다 — 알려주지 않은 상한은 첫 시도를 반드시
+    // 깨고 교정 1회로도 회복되지 않는다(2026-07-27 라이브 실측, 중첩 매니저 동일 계열).
+    "Field bounds are hard: each packet objective at most 3800 characters, each expectedOutput at most 1900, at most 64 inputs of at most 1900 characters each, each synthesis/verifier brief at most 1900, and at most 32 verifier criteria of at most 450 characters each. Write briefs and criteria tightly.",
   ].join("\n");
   return {
     searchSystem: [
@@ -3149,6 +3152,9 @@ function create(deps = {}) {
           "Return exactly one agentlas.workforce-team-delegation-plan.v1 object with plannedWorkerIds, packets, and synthesisBrief.",
           `plannedWorkerIds and packet ids must be exactly this declared order: ${stableJson(exactWorkerIds)}.`,
           "Every packet contains exactly id, objective, inputs, expectedOutput. No worker may be omitted, added, reordered, or substituted.",
+          // 상한을 말해주지 않으면 첫 시도가 반드시 상한을 넘고, 교정 1회로도 못 줄인다
+          // (2026-07-27 라이브 실측: synthesisBrief > 2000자로 4워커 런이 통째로 폐기).
+          "Field bounds are hard: synthesisBrief at most 1900 characters, each packet objective at most 3800, each expectedOutput at most 1900, and at most 64 inputs of at most 1900 characters each. Write briefs tightly; do not restate the packet contents.",
         ].join("\n");
         let attemptPrompt = stableJson({ sharedTask: workOrder.taskBrief, roleSlot: slotById.get(packet.slotId), packet, declaredWorkerIds: exactWorkerIds });
         let priorDigest = null;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentlas",
-  "version": "1.0.8",
+  "version": "1.0.9",
   "description": "Agentlas agent terminal — chat with your installed AI agents and teams from the terminal, Claude Code style. Standalone: no desktop app required.",
   "bin": {
     "agentlas": "bin/agentlas.cjs"