@ai-dev-methodologies/rlp-desk 0.3.3 → 0.3.4

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.
Files changed (2) hide show
  1. package/README.md +10 -0
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -183,6 +183,14 @@ RLP Desk supports two execution modes. Both honor the same governance protocol.
183
183
  | Inside tmux session | **Works** | **Works** — panes split in current window |
184
184
  | Outside tmux session | **Works** | **Rejected** — "start tmux first" |
185
185
 
186
+ ### Choosing Your Mode
187
+
188
+ | Need | Use |
189
+ |------|-----|
190
+ | Reliable autonomous loop (no interruption) | `--mode tmux` |
191
+ | Interactive development, quick tasks | `--mode agent` (default) |
192
+ | Long campaigns, CI, overnight runs | `--mode tmux` |
193
+
186
194
  ### Agent Mode (default) — "Smart Mode"
187
195
 
188
196
  ```
@@ -193,6 +201,8 @@ The current Claude Code session acts as the Leader, dispatching Workers and Veri
193
201
 
194
202
  - Works anywhere — no tmux required
195
203
  - Dynamic model routing — Leader upgrades models on failure
204
+
205
+ **Known limitation:** Agent mode runs inside Claude Code's turn-based request-response model. If the LLM outputs text without a tool call, the turn terminates and the loop pauses until the user sends "continue." This is a platform constraint — the protocol mitigates it but cannot guarantee 100% uninterrupted execution. For guaranteed autonomous loops, use tmux mode.
196
206
  - Fix Loop — extracts verifier issues and feeds them back to the next worker
197
207
  - Best for interactive development
198
208
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@ai-dev-methodologies/rlp-desk",
3
- "version": "0.3.3",
3
+ "version": "0.3.4",
4
4
  "description": "Fresh-context iterative loops for Claude Code — autonomous task completion with independent verification",
5
5
  "scripts": {
6
6
  "postinstall": "node scripts/postinstall.js",