@lumenflow/cli 4.21.0 → 4.22.0

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.
@@ -217,6 +217,18 @@ cloud:
217
217
  | Complete | `wu:done --id WU-XXX` | Creates PR, commits metadata on lane branch |
218
218
  | Cleanup | `wu:cleanup --id WU-XXX` | Post-merge: creates stamp, updates state, deletes branch |
219
219
 
220
+ ### Cloud Orchestration Parity
221
+
222
+ The orchestration contract is the same in local and cloud modes:
223
+
224
+ - **Planning**: logical waves and bottlenecks come from the same initiative dependency graph.
225
+ - **Handoff**: `wu:brief` / `wu:delegate` remain the worker-context generators.
226
+ - **Execution**: local runs use worktrees; cloud runs use lane branches and PRs.
227
+ - **Finish**: local completion ends at `wu:done`; cloud completion ends at merge plus `wu:cleanup`.
228
+ - **Status**: `orchestrate:init-status`, `orchestrate:monitor`, `delegation:list`, and shared memory help summarize the run, but live truth still reconciles against WU status, branch/worktree state, gates, and final stamps.
229
+
230
+ `mem:inbox` is only the signal slice of orchestration traffic. Use it together with the broader control-plane evidence instead of treating it as the whole execution ledger.
231
+
220
232
  ### Vendor-Specific Notes
221
233
 
222
234
  - **Codex**: Set `LUMENFLOW_CLOUD=1` or pass `--cloud`
@@ -233,6 +245,7 @@ If your AI coding assistant isn't listed above, LumenFlow still works:
233
245
  1. Run `lumenflow init` to create universal entry points
234
246
  2. Tell your AI to read `AGENTS.md` and `LUMENFLOW.md`
235
247
  3. The workflow commands (`wu:claim`, `wu:done`, `gates`) work the same
248
+ 4. Initiative orchestration follows the same control-plane model across vendors: plan, hand off, execute, reconcile, finish, then advance
236
249
 
237
250
  **Want enhanced integration for your AI?** See [Adding New Integrations](#adding-new-integrations) below.
238
251