@lmctl-ai/lmctl 0.1.23 → 0.1.25

package/CHANGELOG.md

@@ -4,6 +4,11 @@ All notable public-preview changes for `@lmctl-ai/lmctl` are recorded here.
 
 ## Unreleased
 
+- Removed static `_CONNECT_` cross-team routing and the `lmctl connect` command.
+  Legacy `_CONNECT_` lines now parse as deprecated no-ops with a lint warning,
+  cross-team Lead sends work at runtime without predeclared edges, runtime
+  cycle protection uses `team_chat_log` + `agent_inflight`, and migration v38
+  drops the retired `team_connection` table.
 - Replaced native `better-sqlite3` with built-in `node:sqlite`; Node >=24.15.0
   is now required and npm install no longer has a native SQLite build step.
 - Added `provider=opencode` model-effort selection with `_MEMBER_ ... model=<id> effort=<variant>`.

package/README.md

@@ -15,7 +15,9 @@ Two things set it apart from how "multi-agent" and "AI review" usually work:
 - **Review is adversarial, not self-review.** The reviewer is a different
   provider *and* model from the author — a Claude lead hands coding to Codex and
   has Gemini review it — so a model's blind spots aren't rubber-stamped by
-  itself in a different hat.
+  itself in a different hat. Different models have different (uncorrelated) blind
+  spots; that **model diversity** is the point — a varied team catches what one
+  model, or its clones, can't.
 - **You build and tune the team — the provider doesn't.** Most "multi-agent"
   tools have one provider auto-spawn agents you can't steer. In lmctl you divide
   the work, compose the team in plain text, pick the provider and model for each