taskforce-loop-engineering 0.15.2 → 0.15.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -2,6 +2,12 @@
2
2
 
3
3
  ## Unreleased
4
4
 
5
+ ## 0.15.3 - 2026-08-22
6
+
7
+ - Remove workspace-specific Ironman queue and dispatcher instructions from the distributed skill.
8
+ - Resolve the installed queue and managed wrapper from each OpenClaw workspace, while keeping existing queue data untouched.
9
+ - Add a distribution self-test that rejects host-specific dispatcher leakage in future packages.
10
+
5
11
  ## 0.15.2 - 2026-08-21
6
12
 
7
13
  - Enrich terminal notifications with final judgement, checkpoint summary, verification count, blockers, and next action.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "taskforce-loop-engineering",
3
- "version": "0.15.2",
3
+ "version": "0.15.3",
4
4
  "private": false,
5
5
  "description": "OpenClaw-native loop engineering CLI, templates, and skill for verifiable agent work loops.",
6
6
  "type": "module",
@@ -20,7 +20,7 @@
20
20
  "check:adapters": "node --check lib/runtime-adapter-sdk.mjs && node scripts/runtime-adapter-conformance.mjs",
21
21
  "demo:adapter": "node examples/adapter-sdk-demo.mjs",
22
22
  "check:production-trust": "node --check lib/runtime-adapter-v1.mjs && node --check lib/durable-journal.mjs && node --check lib/execution-ledger.mjs && node --check lib/production-evidence.mjs && node --check lib/upgrade-planner.mjs && node scripts/production-acceptance.mjs",
23
- "check:config-drift": "node --check scripts/config-drift-self-test.mjs && node scripts/config-drift-self-test.mjs",
23
+ "check:config-drift": "node scripts/distribution-skill-self-test.mjs && node --check scripts/config-drift-self-test.mjs && node scripts/config-drift-self-test.mjs",
24
24
  "check:openclaw-install": "node --check scripts/openclaw-install.mjs && node --check scripts/openclaw-doctor.mjs && node --check scripts/openclaw-smoke.mjs && node --check scripts/openclaw-manage.mjs && node scripts/openclaw-install-self-test.mjs",
25
25
  "check:hermes-install": "node --check scripts/hermes-install.mjs && node --check scripts/hermes-doctor.mjs && node --check scripts/hermes-smoke.mjs && node scripts/hermes-install-self-test.mjs",
26
26
  "check:project-gates": "node --check lib/core.mjs && node scripts/project-gate-reconciliation-self-test.mjs",
@@ -0,0 +1,14 @@
1
+ import assert from 'node:assert/strict';
2
+ import { readFile } from 'node:fs/promises';
3
+
4
+ const skill = await readFile(new URL('../skills/taskforce-loop-engineering/SKILL.md', import.meta.url), 'utf8');
5
+
6
+ for (const forbidden of ['ironman-task-runner', 'ironman-task-runner.mjs']) {
7
+ assert.equal(skill.includes(forbidden), false, `distributed skill contains local dispatcher reference: ${forbidden}`);
8
+ }
9
+
10
+ for (const required of ['agent-tasks', 'scripts/loops/openclaw-loop.mjs', 'configs/loops/queues/']) {
11
+ assert.equal(skill.includes(required), true, `distributed skill is missing generic integration guidance: ${required}`);
12
+ }
13
+
14
+ console.log('distribution skill self-test passed');
@@ -127,15 +127,17 @@ Interpret explicit loop language as follows:
127
127
  - A new explicit `走 loop` request while another task is active is a correction/replacement, not ordinary backlog. Supersede the active task at a safe boundary, retain its evidence and lineage, then start the replacement after the lock is released.
128
128
  - Status, progress, evidence, or failure questions are read-only and must not start another tick unless the user explicitly asks to continue/run.
129
129
 
130
- In this workspace, the default queue is `ironman-task-runner` when no queue is named. Use the installed workspace wrapper when present:
130
+ Do not infer a queue or dispatcher from this skill. Use the integration installed in the current workspace. For OpenClaw, inspect the generated queue configuration under `configs/loops/queues/` and use the managed wrapper when present. A default installation uses queue `agent-tasks` and the generic wrapper below; an operator may choose another queue or worker during installation.
131
131
 
132
132
  ```bash
133
- node scripts/loops/ironman-task-runner.mjs route --message "<original user message>" --confirm-execute [source options]
134
- node scripts/loops/ironman-task-runner.mjs run-once --notify
135
- node scripts/loops/ironman-task-runner.mjs status --json
136
- node scripts/loops/ironman-task-runner.mjs peek --json
133
+ node scripts/loops/openclaw-loop.mjs route --message "<original user message>" [source options]
134
+ node scripts/loops/openclaw-loop.mjs run-once
135
+ loop-engineering queue-status --queue <installed-queue> --root . --json
136
+ loop-engineering queue-peek --queue <installed-queue> --root . --json
137
137
  ```
138
138
 
139
+ If the managed wrapper or queue configuration is absent, stop and run the platform installer/doctor workflow above. Product names, personal agent names, and host-specific dispatchers belong in local workspace instructions, never in this distributed skill.
140
+
139
141
  Pass the original request faithfully. Preserve source channel, target, account, message id, and reply-to metadata so progress, human gates, and terminal results return to the originating conversation. Missing delivery routing must fail closed.
140
142
 
141
143
  ## Task vs Project Classification