@mu-crew/mu 3.10.0 → 3.10.1

package/docs/ROADMAP.md

@@ -67,6 +67,13 @@ These have a design but no proven friction yet.
   SQLite update hooks or `fs.watch` on the WAL would cut latency for
   more machinery. Build it when someone hits the limit.
 
+- **`mu agent list --json` as `{items, count}`.** It emits
+  `{workstreamName, agents, orphans}`, the one collection off the
+  documented shape (SKILL.md notes the exception). Conforming breaks
+  `.agents` readers, `mu_delegate` among them; do it with the next
+  breaking release. Reported in
+  docs/bugs/2026-10-08-review-panel-friction.md (#3).
+
 ## Open questions
 
 - **Capability tags on operations.** Today the only authorization is

package/docs/guide/delegate.md

@@ -21,7 +21,8 @@ Delegates called in one turn run in parallel.
 | `cwd` | Start directory. Default: the caller's. Must exist. |
 | `timeout` | Seconds to wait for the answer (default 3600). After it, the answer does not come back; the follow-up gives the `mu agent wait` command. |
 | `workspace` | Own VCS checkout, for delegates that edit files. The follow-up names its path. It isolates repository edits only. |
-| `cli` | Key for `$MU_<CLI>_COMMAND` (default `pi`), e.g. a cheaper model. |
+| `cli` | Key for `$MU_<CLI>_COMMAND` (default `pi`). Only keys set in pi's environment exist. |
+| `model` | pi `--model` value, appended to the cli's command (`sonnet`, `openai/gpt-5:high`). Varies models across a panel. tmux only: herdr refuses a command override. |
 | `keep` | Keep the pane after it finishes, to talk to it again. |
 | `record` | `{ task, workstream? }` (or `task: "<ws>/<task>"`): write the answer's verdict onto that task as a note. See [Record a verdict](#record-a-verdict). |
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mu-crew/mu",
-  "version": "3.10.0",
+  "version": "3.10.1",
   "description": "A persistent, observable crew of pi agents running in one tmux or herdr session per workstream, coordinated through a built-in task DAG.",
   "publishConfig": {
     "access": "public"

package/skills/mu/SKILL.md

@@ -23,7 +23,7 @@ not in `--help` do not exist.
 
 Default output is a card on stdout plus a `Next:` block. Read both.
 Every verb takes `--json`: one stdout object; collections are
-`{items, count}`; `mu sql --json` is bare rows; `mu log --tail` is
+`{items, count}`, except `mu agent list` (`{agents, orphans}`); `mu sql --json` is bare rows; `mu log --tail` is
 NDJSON. Errors are `{error,message,nextSteps,exitCode}` on stderr
 (validation errors add `usage`). **`nextSteps` survives in JSON.**
 

package/skills/mu/recipes/codemode-driver.md

@@ -104,6 +104,9 @@ What the tool did for you, the script now owns:
   tournament runs one round per script.
 - **A script timeout cancels the waits, not the workers.** Workers keep
   running and their tasks stay claimed. Re-read `mu state` and carry on.
+- **Briefs are not template literals.** A backtick in a brief ends the
+  string and the whole script fails before any call starts. Build
+  briefs with `tools.read` from a file, or as plain strings.
 - **Exit codes are data.** `mu task wait` exit 7 means a worker needs
   you; return it to the model instead of retrying.
 

package/skills/mu/recipes/review-panel.md

@@ -57,6 +57,7 @@ triage and the umbrella closes with `--if-ready` (workstream mode).
 - **Reviewers padding the list.** A panel that always finds ten things
   is guessing.
 - **Vary models across angles** ([Models](../SKILL.md#models-and-thinking-effort)); one model's blind spot
-  repeated five times is still one blind spot.
+  repeated five times is still one blind spot. In delegate mode pass
+  `model` to `mu_delegate`; `cli` keys exist only if `$MU_<KEY>_COMMAND` is set.
 - **The panel is not the gate command.** Merge verification still runs on the
   merged tree ([orchestrator-loop](orchestrator-loop.md#merging)).