@loompad/cli 1.2.0 → 1.2.2

package/docs/release-notes/v1.2.1.md

@@ -0,0 +1,40 @@
+## Loom 1.2.1: what two real field tests found
+
+Loom 1.2 was put through two tests. The first was a full `loom council` on a real project: 23 tests became 52, and only the planner touched a file. The second ran six projects at once (a council, an orchestra, a route, a night shift, a crew and reviews), and the daemon never fell over. Together they found 25 things to fix.
+
+### Proof tells "couldn't run" from "failed"
+- **Which command:** Proof now re-runs the test command the agent itself ran and passed. Before, it guessed `python -m pytest`, got *command not found*, and reported "the tests fail" for a change that passed 52/52.
+- **Just the test part:** it keeps only the test step of that command. `pytest | tail -3` always reports tail's success, so re-running it whole would pass failing tests.
+- **Python projects:** a guessed pytest command uses the project's `.venv`, or `python3`.
+- **If it can't start:** a test command that can't run at all is **unverified**, and Proof says how to set `proof.testCommand`.
+- **On the council card:** Prove shows ✓ only when the tests really passed, ✗ when they didn't, **?** when unverified.
+
+### The council keeps its word
+- The planner's decisions are stored exactly as written. Underscores were being stripped, so `tests/test_reach.py` reached project memory as "testreach.py".
+- The fix round gets **every** finding, low ones too. One dropped "low" was a test the planner had promised to write.
+- A reviewer that answers with nothing counts as failed, not done.
+- A reviewer that takes longer than `review.timeoutMin` (15 minutes by default) is stopped and left out, so one slow free model doesn't hold everyone up.
+- Plans go to `.loom/plans/`, not a new folder in your repo.
+
+### Sign-ins and cost
+- Grok shows as **signed out** when its session has expired. Before, a leftover token made it look ready. `loom doctor` also reports a sign-in failure a real turn hit, even after a restart.
+- `loom send` warns before re-reading a large session whose cache has expired, with an estimated cost. A one-line question once cost $4.75 that way. `--fresh` starts that chat's session over.
+
+### Six projects at once
+- **A council that waits for its own answer.** If a reviewer ran out of quota, its review was handed to the planner as a turn of its own, and the council read that turn as the planner's fix reply. Now a council waits for the reply to its own prompt, and a reviewer out of quota is simply left out.
+- **Crews read every way of saying "changes requested"**, so a card goes back to its builder instead of the goal failing. New crews seat your writers as builders and your reviewers as reviewers, and `--builders` / `--reviewer` let you choose. `loom crew budget` works before the first goal.
+- **Night shifts stay in order.** A loop-watch nudge goes in before the next task starts, and the report says what really stopped a task: the shield, the loop watch, Stop or a quota.
+- **Fewer false alarms.**
+  - Five different edits to one file aren't "going in circles".
+  - A `curl -o /dev/null` later on the line isn't a delete outside the project.
+  - A file Antigravity only mentions isn't an edit.
+- **No silent hangs.** An OpenCode prompt that never starts fails after 3 minutes, not an hour, and `loom review --json` always prints JSON.
+- **The baton comes home.** A route that ends on a reviewer hands the baton back to the agent that did the work.
+- **You can see what's working.** `loom status` and the phone's project board count an orchestra, crew, council, shift or review as working.
+- **The digest:**
+  - In the app, "While you were away" shows the open project's digest and closes on Escape.
+  - `loom digest` shows dates across midnight and collapses repeated lines.
+- **Disk:**
+  - Orchestra worktrees for a project on an external drive now live on that drive.
+  - Finished runs' worktrees are removed after a week.
+  - `loom doctor` points out folders left by projects you've removed, and `loom orchestra:clean` removes them.

package/docs/release-notes/v1.2.2.md

@@ -0,0 +1,39 @@
+## Loom 1.2.2: Teams front and centre, and Loom that survives a restart
+
+### Teams get their own tab, and you sign in with GitHub
+- **A Team tab**, right after Chat. Teams used to sit at the bottom of Agents. Signed out, the tab shows what Loom Teams does and one **Sign in with GitHub** button. Once you're on a team, it shows:
+  - members, with their GitHub pictures;
+  - an **Invite** button;
+  - who's working on what, and which files they're touching;
+  - the team's activity and costs.
+- **Loom Desktop asks you to sign in with GitHub** when it opens. "Continue without an account" is right there, since Loom works alone; the account is for Teams.
+- **Invite works.** It said "admin only" in Desktop, because the window signed in like a phone. Desktop now holds the owner's session.
+- **Accounts are GitHub-only**, enforced by the hosted database. An email sign-up could otherwise claim someone else's GitHub name.
+- **Agents shows this project only.** Other projects are on the home screen.
+
+### Survives a restart
+- **Councils resume.** Use `loom council:resume`, or Resume on the card. A council picks up at the stage it stopped at, keeping its plan, reviews and decisions.
+- **Night shifts stay in order after a restart.** A queued task is sent once and never on top of a running turn. The report waits until the work is really done.
+- **`loom up --restart` leaves Loom Desktop's daemon alone**, and windows refresh themselves when the daemon restarts.
+
+### Honest costs and budgets
+- **The cold-session warning prices what you'll really pay.** It learns from that agent's own past turns: it said $0.34 where the real cost was $6.03, and now it says about $4.80. In a terminal it asks before sending.
+- **A turn that would cross an agent's daily budget doesn't start.**
+
+### Crews and reviews
+- **Crews:**
+  - Fixing a merge conflict no longer uses up a card's review rounds.
+  - A failed card has **Accept it anyway**: its work is merged as it is, and the cards waiting on it run.
+- **Reviews:**
+  - A review waits for a busy reviewer instead of failing.
+  - A reviewer that has never finished one is named up front.
+  - A reviewer that runs out of time is stopped, process and all.
+
+### Smaller things
+- A shift or council starting on uncommitted edits tells you, and points to Rewind.
+- Files an agent changed through the shell are counted as edits.
+- `loom memory:repair` fixes decisions recorded before 1.2.1 with their underscores stripped.
+- `loom clients --prune` clears out paired devices that never came back.
+- `loom projects --json` and `loom status --json` exist, and `loom watch --json` is clean JSON.
+- `loom doctor` and `loom agents` no longer call a signed-out agent ready.
+- The window's "N working" matches `loom status`.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@loompad/cli",
-  "version": "1.2.0",
+  "version": "1.2.2",
   "description": "Loom — local-first control plane for coding agents: one CLI, shared memory, baton handoffs and routes across Claude Code, OpenCode, and friends.",
   "type": "module",
   "license": "MIT",