@odla-ai/cli 0.43.0 → 0.44.0

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/README.md CHANGED
@@ -126,15 +126,21 @@ Before project-mutating work, match the request to an open goal. If it is not
126
126
  aligned, discuss that with the user before creating an outcome or implementing.
127
127
  Refine a Backlog task with `--goal` (or an accepted
128
128
  `--alignment-decision`), `--description`, and `--acceptance`, then mark it Ready
129
- and claim the reviewed revision:
129
+ and start it:
130
130
 
131
131
  ```bash
132
132
  npx --yes @odla-ai/cli@latest pm task ready <id> --expected-revision <n>
133
- npx --yes @odla-ai/cli@latest pm task claim <id> --expected-revision <n>
133
+ npx --yes @odla-ai/cli@latest pm start --app <appId>
134
134
  ```
135
135
 
136
- Ready is stored as `todo` for API compatibility. Claims are atomic and assign
137
- the authenticated principal; stale or concurrent claims fail. Use `pm task
136
+ Ready is stored as `todo` for API compatibility. `pm start` claims the
137
+ top-ranked Ready task (or the one you name) in a single call: it reads the
138
+ current revision, compare-and-swaps against it server-side, and reloads once if
139
+ the task moved, returning the task, its goal, and the acceptance criteria. It
140
+ cannot mark work Ready, so an agent cannot authorize its own work. Claims are
141
+ atomic and assign the authenticated principal; stale or concurrent claims fail.
142
+ `pm task claim <id> --expected-revision <n>` remains for a caller that has
143
+ already read the revision. Use `pm task
138
144
  release` for an explicit recovery handoff instead of leaving Doing as a vague
139
145
  status. The complete runbook is installed as
140
146
  `references/pm-work-intake.md` by `odla-ai skill install`.