exponential-cli 1.18.1 → 1.20.0

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
@@ -140,6 +140,7 @@ and live under `goals kr`.
140
140
  exponential goals list --workspace clear --period Q3-2026
141
141
  exponential goals list --workspace clear --tree
142
142
  exponential goals list --all-workspaces # "what am I neglecting" is cross-workspace
143
+ exponential goals list --project <cuid> # objectives (yours) linked to a project
143
144
 
144
145
  exponential goals get 46
145
146
  exponential goals create --workspace clear --title "Ship the CLI" --period Q3-2026
@@ -312,6 +313,27 @@ exponential projects update --id <cuid> --product none
312
313
  exponential projects delete --id <cuid> [--force]
313
314
  ```
314
315
 
316
+ ### Products, tickets, epics and user stories
317
+
318
+ ```bash
319
+ # Products take a slug or a CUID
320
+ exponential products list --workspace clear
321
+ exponential products update <slug|cuid> --workspace clear --description "..." [--fun-ticket-ids|--no-fun-ticket-ids]
322
+ # Deleting a product cascades its features, tickets and epics: refuses unless --force
323
+ exponential products delete <slug|cuid> --workspace clear [--force]
324
+
325
+ # Free-text ticket search within a product: title, shortId or ticket number
326
+ exponential tickets search "login redirect" --product <slug|cuid> --workspace clear [--limit 50]
327
+
328
+ # Epics: their tickets and actions are unlinked, not deleted
329
+ exponential epics delete --id <cuid>
330
+
331
+ # A feature's native user stories
332
+ exponential features stories list --feature <cuid>
333
+ exponential features stories update --id <story-cuid> --i-want "..." [--scope <scope-cuid>|null]
334
+ exponential features stories rm --id <story-cuid>
335
+ ```
336
+
315
337
  ### Workspaces
316
338
 
317
339
  ```bash
@@ -352,6 +374,29 @@ and an ambiguous name is an error rather than a guess.
352
374
 
353
375
  Editing and deleting are author-only. Find ids with `exponential search "<text>"`.
354
376
 
377
+ ### Runner — run your Assistant on this machine
378
+
379
+ An Assistant whose executor is **My machine (local runner)** (Settings → AI assistant → Delegation) is never run on the server. Instead this CLI claims its queued runs with the Assistant's runner key and works them with Claude Code under your own login, in a directory you choose. The server never names the directory or the CLI.
380
+
381
+ ```bash
382
+ # 1. Log in with the Assistant's runner key (Settings → AI assistant → New runner key)
383
+ exponential auth login --token exp_agent_... --api-url https://www.exponential.im
384
+
385
+ # 2. Choose where the spawned session works (local config only)
386
+ exponential runner config set cwd ~/code/my-project
387
+
388
+ # 3. Work queued runs until stopped, or claim one and exit
389
+ exponential runner start
390
+ exponential runner start --once --runner-id laptop
391
+
392
+ # 4. Keep it running as a user service (launchd on macOS, systemd --user on Linux)
393
+ exponential runner install --dry-run # show the service file first
394
+ exponential runner install
395
+ exponential runner uninstall
396
+ ```
397
+
398
+ For each run the runner spawns `claude -p <brief> --output-format stream-json --append-system-prompt <persona>` with a per-run Exponential MCP server (`exponential-mcp` ≥ 0.8) so the session can `report_progress`, `ask_owner` and `finish_run`; the stream is parsed into the run's transcript, heartbeats keep the run alive, and the run is finished with the session's summary. Calls to the app retry with backoff and are idempotent, so a laptop going to sleep loses nothing. Add tools the session may use without asking with `runner config set allowed-tools "Read,Bash(git:*)"`.
399
+
355
400
  ## Output Formats
356
401
 
357
402
  ### JSON Output (for LLMs and automation)