@lmctl-ai/lmctl 0.1.158 → 0.1.160

package/examples/book-team.lmctl

@@ -5,8 +5,18 @@
 # checks. Keep chapter plans and decisions in durable-memory/ so refreshed
 # sessions can recover the book state.
 # Suggested flow:
-#   lmctl chat book-team.lmctl Lead "Draft chapter 1 from durable-memory/outline.md" --detach
-#   lmctl jobs watch <job_id>
+#   lmctl chat book-team.lmctl Lead "Draft chapter 1 from durable-memory/outline.md"
+#
+# lmctl chat is synchronous but does not always wait for a reply: when the
+# receiver is free the message is delivered and chat blocks for the reply; when
+# the receiver is BUSY the message is enqueued and chat returns immediately.
+# Both cases exit 0, so exit code alone cannot tell you a reply arrived.
+# Check with --json: status="ok" is a delivered reply (with replyText),
+# status="enqueued" means it was queued. lmctl status shows pending lanes.
+#
+# For async, lmctl is foreground/background agnostic: wrap the same command in
+# your provider or host runtime's native background facility (e.g. Claude
+# background Bash) rather than an lmctl flag.
 
 _MEMBER_ alias=Lead provider=claude
 _MEMBER_ alias=Outliner provider=claude

package/examples/research-team.lmctl

@@ -5,8 +5,18 @@
 # ask Critic to identify weak evidence or contradictions, then have Synthesizer
 # merge the strongest findings into a concise response.
 # Suggested flow:
-#   lmctl chat research-team.lmctl Lead "Research <question>" --detach
-#   lmctl jobs watch <job_id>
+#   lmctl chat research-team.lmctl Lead "Research <question>"
+#
+# lmctl chat is synchronous but does not always wait for a reply: when the
+# receiver is free the message is delivered and chat blocks for the reply; when
+# the receiver is BUSY the message is enqueued and chat returns immediately.
+# Both cases exit 0, so exit code alone cannot tell you a reply arrived.
+# Check with --json: status="ok" is a delivered reply (with replyText),
+# status="enqueued" means it was queued. lmctl status shows pending lanes.
+#
+# For async, lmctl is foreground/background agnostic: wrap the same command in
+# your provider or host runtime's native background facility (e.g. Claude
+# background Bash) rather than an lmctl flag.
 
 _MEMBER_ alias=Lead provider=claude
 _MEMBER_ alias=Researcher1 provider=codex

package/examples/review-team.lmctl

@@ -5,8 +5,18 @@
 # reviews, asks SecurityReviewer for trust-boundary concerns when relevant, and
 # routes findings back to Author before final signoff.
 # Suggested flow:
-#   lmctl chat review-team.lmctl Lead "Implement <task> and get review signoff" --detach
-#   lmctl jobs watch <job_id>
+#   lmctl chat review-team.lmctl Lead "Implement <task> and get review signoff"
+#
+# lmctl chat is synchronous but does not always wait for a reply: when the
+# receiver is free the message is delivered and chat blocks for the reply; when
+# the receiver is BUSY the message is enqueued and chat returns immediately.
+# Both cases exit 0, so exit code alone cannot tell you a reply arrived.
+# Check with --json: status="ok" is a delivered reply (with replyText),
+# status="enqueued" means it was queued. lmctl status shows pending lanes.
+#
+# For async, lmctl is foreground/background agnostic: wrap the same command in
+# your provider or host runtime's native background facility (e.g. Claude
+# background Bash) rather than an lmctl flag.
 
 _MEMBER_ alias=Lead provider=claude
 _MEMBER_ alias=Author provider=codex

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lmctl-ai/lmctl",
-  "version": "0.1.158",
+  "version": "0.1.160",
   "description": "A provider-agnostic control plane for teams of AI coding agents — across providers, with independent review and durable memory.",
   "type": "module",
   "homepage": "https://lmctl.com",

package/dist/config/ai_test_templates/example-test.md.template

@@ -1,50 +0,0 @@
----
-name: example-test
-description: Replace with a one-line description of what this test verifies
-type: smoke
-tags: [example]
-last_run_at: never
-last_run_status: unknown
-last_run_id: 0
----
-
-# Test: example
-
-Replace this content with your real test case. The structure below is what the QA Tester agent expects.
-
-## Setup
-
-Describe what the system state must be before running this test. Examples:
-- A project exists with a configured team
-- An image fixture is present at a known path
-- The serve daemon is running on $LMCTL_API_URL
-
-Use shell-style commands (the Tester will execute them) or describe in prose if manual steps are needed.
-
-## Action
-
-What the test actually does. Be specific about commands, inputs, and expected intermediate observations.
-
-```bash
-# Example action
-curl -X GET $LMCTL_API_URL/api/status \
-  -H "Authorization: Bearer $LMCTL_API_TOKEN"
-```
-
-## Expected
-
-What "pass" looks like:
-- HTTP 200 response
-- JSON body contains key `jobs` with `total >= 0`
-- Response time under 1 second
-
-The Interpreter agent reads this section + the Action's actual observations to emit STANCE: pass / fail / inconclusive.
-
-## Cleanup
-
-Idempotent cleanup steps. Should be safe to run even if Setup or Action failed.
-
-```bash
-# Example cleanup
-# (nothing to clean up for this read-only example)
-```

package/dist/config/ai_test_templates/index.md.template

@@ -1,27 +0,0 @@
-# AI Test Suite - index
-
-This directory holds **AI-driven manual tests** for this project. Each chapter (`*.md`) describes one test case that an LLM agent (the QA Tester) executes; an Interpreter agent judges pass/fail.
-
-**This is NOT for unit/integration tests** - those live in `tests/` and run via your test framework (e.g., `npm test`). `ai-test/` is for things that need LLM-quality judgment: vision quality, prompt-driven behavior, end-to-end scenarios that exercise the full stack.
-
-## Conventions
-
-- One test case per `.md` file
-- YAML frontmatter (agent-writable: `last_run_*` fields)
-- Markdown body sections: `## Setup`, `## Action`, `## Expected`, `## Cleanup`
-- Issues found by qa-suite reference the chapter via `ai_test_path` (e.g. `ai-test/test-image-upload-basic.md`)
-
-## Test cases
-
-See individual chapters in this directory. Use `grep -l 'type: smoke' ai-test/*.md` (etc.) to filter.
-
-## How to add a new test case
-
-1. Copy a chapter as a template: `cp ai-test/example-test.md ai-test/test-my-new-case.md`
-2. Edit frontmatter (name, description, type, tags)
-3. Edit body (Setup, Action, Expected, Cleanup)
-4. Commit alongside the code change that motivated the test
-
-## Pointer to lmctl's own ai-test/ (canonical example)
-
-See `<lmctl-repo>/ai-test/` for the test corpus used to verify lmctl itself.