agentlas 1.0.7 → 1.0.9

package/CHANGELOG.md

@@ -1,5 +1,46 @@
 # 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
+  the highlight also wrote the highlighted command into the input line, and
+  the candidate list is derived from that line — so the list became a function
+  of the selection rather than of what you typed. Typing `/s` offered nine
+  commands; two presses of Down rewrote the line to `/switch` and cut the list
+  to two, leaving `/spawn`, `/steer`, `/search`, `/storm` and `/swarm`
+  unreachable no matter how many keys you pressed. Arrows now move the
+  highlight only and leave your query alone. Deleting the line rewrite was not
+  enough on its own: readline treats Up/Down as history navigation and a
+  prepended keypress listener runs first but cannot suppress that default, so
+  the query is now restored if readline moved through history.
+
 ## 1.0.7 — 2026-07-27
 
 - **The selection prompt no longer carries the whole candidate set.** Measured

package/engine/agentlas-config.cjs

@@ -1,7 +1,9 @@
 "use strict";
 /*
  * CLI preferences (separate from the app's SQLite/keychain) — first-run onboarding result.
- * Stored at <userData>/cli-prefs.json: { onboarded, lang, runtime, permission }.
+ * Stored at <userData>/cli-prefs.json: { onboarded, language, runtime, permission }.
+ * `lang` is the v1 key for the same value — still read (engine/agentlas.cjs resolveLang)
+ * so an upgraded user keeps the language they chose, but never written by v2.
  * Persisted permission is read|write; unrestricted/full is session-only.
  */
 const fs = require("node:fs");

package/engine/agentlas-input.cjs

@@ -602,13 +602,27 @@ function attachSlashPalette(rl, opts = {}) {
     stream.write("\x1b7\x1b[E\x1b[0J" + body + "\x1b8");
     state.visible = true;
   }
+  /*
+   * 화살표는 강조만 옮긴다 — 사용자가 친 질의는 그대로 둔다.
+   *
+   * 예전에는 여기서 선택 항목을 입력 줄에 써 넣었다(replaceLine(selectedCommand)).
+   * 그러면 후보 목록이 "질의로 거른 결과"가 아니라 "선택의 함수"가 되어 되먹임이 생긴다:
+   * `/s` 에서 ↓ 두 번이면 줄이 `/switch` 로 바뀌며 후보가 9개→2개로 접히고,
+   * 그 아래 항목(/spawn·/steer·/search·/storm·/swarm)엔 영원히 닿지 못했다.
+   * 오너가 본 "방향키 무브 안 됨"의 정체다(PTY 실측).
+   *
+   * 다만 readline 은 up/down 을 히스토리 이동으로 처리하고, prependListener 로는 그
+   * 기본 동작을 막을 수 없다(전파 중단이 없다). 팔레트가 열려 있는 동안 화살표의 의미는
+   * 목록 이동이므로, readline 이 줄을 건드렸으면 원래 질의로 되돌린다.
+   */
   function move(delta) {
     const list = rows();
     if (!list.length) return false;
     state.selected = (state.selected + delta + list.length) % list.length;
     state.selectedCommand = list[state.selected].command;
+    const query = rl.line || "";
     setImmediate(() => {
-      replaceLine(state.selectedCommand);
+      if ((rl.line || "") !== query) replaceLine(query);
       render();
     });
     return true;

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": "1.0.7",
+  "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"