@plori/cli 0.5.0 → 0.6.0

package/README.md

@@ -106,7 +106,9 @@ plori workspace run mate "Research this topic and save the result to work/report
 
 Creation prints an idempotency key. Reuse it with `--idempotency-key` when you
 retry the same request. A name can identify more than one Workspace. Use its ID
-from `plori workspace list` if names are duplicated.
+from `plori workspace list` if names are duplicated. The list includes your own
+and shared Workspaces, with `ACCOUNT` and `ROLE` columns. JSON includes
+`account` (`user_id`, `email`) and `role` (`owner`, `member` or `viewer`).
 
 For commands that take an agent, set `AGENT_ID` to the creation response's
 `default_manager_agent_id`. The Workspace name is not an agent name.
@@ -180,19 +182,24 @@ plori workspace run mate "build it" --follow  # stream the turn live (tools on s
 echo "summarize this" | plori workspace run mate -  # message from stdin
 plori account watch --agent "$AGENT_ID"  # one JSON line per run ending
 plori account inbox  # what ended, and what waits on you
-plori schedules create "$AGENT_ID" "daily report" --in 86400
+plori schedules create mate "daily report" --in 86400
+plori schedules list mate
+plori schedules cancel mate <schedule-id>
 plori input list "$AGENT_ID"  # runs paused on an approval or a question
 plori input answer <run-id> <tool-call-id> --approve
 plori input answer <run-id> <tool-call-id> --approve --always-allow  # + stop asking for this tool
 plori account balance && plori account disk
 
 plori workflow list  # all your workflows
-plori workflow list --agent "$AGENT_ID"  # one agent's (use "none" for unassigned)
-plori workflow create "rss digest" --trigger cron --cron "0 9 * * *"
-plori workflow run "rss digest"  # run it now (real fire, billed)
-plori workflow execution "rss digest" <exec-id>  # poll one run
+plori workflow list --workspace mate
+plori workflow create "rss digest" --workspace mate --trigger cron --cron "0 9 * * *"
+plori workflow run "rss digest" --workspace mate  # run it now (real fire, billed)
+plori workflow execution "rss digest" <exec-id> --workspace mate  # poll one run
 ```
 
+Schedules take a Workspace name or UUID. `plori workflow create` requires `--workspace`.
+Build the draft with `plori workspace run mate "Build the steps for workflow <id>"`.
+
 Agents are addressed by name or UUID. Every command accepts `--json`; when
 stdout is not a TTY the output is JSON automatically, so scripts and agents
 can parse without flags. `plori conversation attach` is the one exception: it is a live
@@ -206,6 +213,21 @@ the exit codes are listed under [Agent-driven use](#agent-driven-use).
 `plori workspace run` prints the reply in a terminal and a JSON result when piped.
 Tool progress goes to stderr. Reuse the Workspace for later tasks.
 
+An idle conversation starts a run. If it is running, the server accepts plain text as
+steering or queues it. The CLI prints the receipt and exits `0`, including with
+`--follow`. It does not wait for the running or paused run to end. The receipt
+contains `status` (`steering` or `queued`), `steer_id` and `run_id`, plus the
+conversation and Workspace ids. That `run_id` identifies the running or paused
+run, not a result for this message. Use `plori runs list "$AGENT_ID"` to find a
+later queued turn. There is no lookup from `steer_id` to that later run.
+
+If the paused run has exactly one ordinary question assigned to you, the message
+answers it. Otherwise it queues, with `pending_inputs` identifying the request
+and assignee. Sending a message does not cancel a pending request.
+`409 conversation_busy` still applies to attachments or run options in a busy
+conversation, and to working-copy conflicts. Send attachments and options when
+idle.
+
 ### Start a run and keep working
 
 A local agent (a Claude Code or Codex shell, an orchestrator) does not have to
@@ -273,7 +295,7 @@ tools return: `run_id`, `status`, `session_id`, `url`, `pending_inputs`.
 
 | code | meaning |
 | ---- | ------- |
-| 0 | the command succeeded; a run that was waited for completed |
+| 0 | the command succeeded. A waited run completed, or the server accepted a message as steering or queued |
 | 1 | API or runtime failure |
 | 2 | usage error |
 | 3 | missing, rejected, or expired credentials |
@@ -328,9 +350,11 @@ and starts the worker. It waits for the copy to be ready, for up to 600 seconds.
 Use `--timeout` to change that limit. If the Workspace has no saved revision yet,
 retry when its storage is ready.
 
-`--max-tokens` sets the new group's limit in cache-weighted tokens. The default
-is 2,000,000. To share an existing group's limit, use `--task-group <id>` without
-`--max-tokens`.
+`--max-tokens` sets a token figure that is recorded on the new group, in
+cache-weighted tokens. The default is 2,000,000. The figure does not limit model
+calls. The account's credit balance limits spend. A member can also have a
+monthly spend cap that refuses new run starts with `402`. To add the worker to
+an existing group, use `--task-group <id>` without `--max-tokens`.
 
 The command prints the worker ID and a `worker status` command on stderr. It
 also prints a generated idempotency key if you omit `--idempotency-key`.
@@ -375,10 +399,9 @@ plori advanced worker spawn "$WORKSPACE_ID" 'Update the selected files' --name w
 plori worker status "$WORKSPACE_ID" "$REQUEST_ID" --wait --wait-seconds 600
 ```
 
-`--max-tokens` is the group's shared limit in cache-weighted tokens. It must
-be positive. Starting a worker reserves one full context window plus output
-from this limit, so 2,000,000 tokens covers one worker. Raise the limit when
-several workers share the group.
+`--max-tokens` is a token figure recorded on the group, in cache-weighted tokens.
+It must be positive. It does not limit model calls. A stopped group refuses new
+model calls and starts no new workers.
 Spawn returns a request. Status returns the run result when it is available,
 with the worker's save and review state. A finished run does not mean its files
 are saved. `--executor` is the id of an existing agent to run as the worker.
@@ -441,7 +464,7 @@ plori advanced workspace retention "$WORKSPACE_ID" --view pins
 ```
 
 Cost output is the API JSON. A null or missing amount is unknown, not zero, and a
-task group's token limit is not a cost. `resources` is one page of observations. Continue
+task group's token figure is not a cost. `resources` is one page of observations. Continue
 it with `--resource-cursor`. An expired retention state means the item can be
 removed, not that it is already deleted. `advanced workspace pin` keeps a copy or changeset
 until `--expires-at` and needs `--kind`, `--resource` and `--idempotency-key`.

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@plori/cli",
   "description": "Plori runs AI agents in Workspaces.",
-  "version": "0.5.0",
+  "version": "0.6.0",
   "license": "MIT",
   "homepage": "https://plori.ai",
   "repository": {
@@ -26,10 +26,10 @@
     "node": ">=18"
   },
   "optionalDependencies": {
-    "@plori/cli-darwin-arm64": "0.5.0",
-    "@plori/cli-darwin-x64": "0.5.0",
-    "@plori/cli-linux-x64": "0.5.0",
-    "@plori/cli-linux-arm64": "0.5.0",
-    "@plori/cli-win32-x64": "0.5.0"
+    "@plori/cli-darwin-arm64": "0.6.0",
+    "@plori/cli-darwin-x64": "0.6.0",
+    "@plori/cli-linux-x64": "0.6.0",
+    "@plori/cli-linux-arm64": "0.6.0",
+    "@plori/cli-win32-x64": "0.6.0"
   }
 }