@lmctl-ai/lmctl 0.1.24 → 0.1.26
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 +4 -0
- package/README.md +4 -2
- package/dist/cli/index.js +435 -457
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,10 @@ All notable public-preview changes for `@lmctl-ai/lmctl` are recorded here.
|
|
|
4
4
|
|
|
5
5
|
## Unreleased
|
|
6
6
|
|
|
7
|
+
- Removed the top-level `lmctl init` command. Provider setup (installing and
|
|
8
|
+
authenticating each provider CLI) is now a documentation concern; lmctl
|
|
9
|
+
detects missing providers/auth at use time during seed/chat. `lmctl status`
|
|
10
|
+
no longer shows a persisted active-providers list.
|
|
7
11
|
- Removed static `_CONNECT_` cross-team routing and the `lmctl connect` command.
|
|
8
12
|
Legacy `_CONNECT_` lines now parse as deprecated no-ops with a lint warning,
|
|
9
13
|
cross-team Lead sends work at runtime without predeclared edges, runtime
|
package/README.md
CHANGED
|
@@ -15,7 +15,9 @@ Two things set it apart from how "multi-agent" and "AI review" usually work:
|
|
|
15
15
|
- **Review is adversarial, not self-review.** The reviewer is a different
|
|
16
16
|
provider *and* model from the author — a Claude lead hands coding to Codex and
|
|
17
17
|
has Gemini review it — so a model's blind spots aren't rubber-stamped by
|
|
18
|
-
itself in a different hat.
|
|
18
|
+
itself in a different hat. Different models have different (uncorrelated) blind
|
|
19
|
+
spots; that **model diversity** is the point — a varied team catches what one
|
|
20
|
+
model, or its clones, can't.
|
|
19
21
|
- **You build and tune the team — the provider doesn't.** Most "multi-agent"
|
|
20
22
|
tools have one provider auto-spawn agents you can't steer. In lmctl you divide
|
|
21
23
|
the work, compose the team in plain text, pick the provider and model for each
|
|
@@ -43,7 +45,7 @@ lmctl run https://lmctl.com/workflows/research.compound.json
|
|
|
43
45
|
```
|
|
44
46
|
|
|
45
47
|
`lmctl` provides subcommands including `api`, `chat`, `code`, `serve`, `intake`,
|
|
46
|
-
`mcp`, `monitor`, `team`, `workflow`, `project`, `workspace`, `diagnose`,
|
|
48
|
+
`mcp`, `monitor`, `team`, `workflow`, `project`, `workspace`, `diagnose`,
|
|
47
49
|
`status`, and `db`. Run `lmctl <command> --help` for details on each, and see the
|
|
48
50
|
[documentation](https://lmctl.com/lmctl) to define your first team.
|
|
49
51
|
|