@autonoma-ai/planner 0.1.25 → 0.1.26

package/README.md

@@ -35,7 +35,9 @@ answer.
 
 On an interactive terminal the pipeline phase runs inside a live Ink dashboard: a horizontal
 pipeline strip across the top (step status, spinner on the running step, sub-progress), the
-file list on the left (each generated file with its status), and a wide document viewer showing
+file list on the left (each generated file with its status - a test also carries its review
+verdict there: `REVIEWING`, `✓ REVIEWED`, or `FIXING` while a fix agent rewrites it), and a
+wide document viewer showing
 the file currently being written, live from disk - known documents (frontmatter, pages.json)
 render as readable cards and tables instead of raw source. An IDE-style ACTIVITY panel at the
 bottom streams the agent's tool calls. Navigate with arrows or `h/j/k/l` (left/right switch
@@ -150,8 +152,9 @@ the changes loose in your working tree. When it reports the session complete, th
 the recipe it produced and continues to test generation.
 
 - `--agent <name>` - preselect the agent to hand off to (`claude` or `codex`). Omit to auto-detect;
-  if both are installed you're prompted to pick, and headless - where there is nobody to ask - the
-  first is used and named in a warning.
+  if both are installed you're prompted to pick once and that choice is remembered for later runs
+  (in `~/.autonoma/preferences.json`), and headless - where there is nobody to ask - the first is
+  used and named in a warning. The flag always wins over what was remembered.
 - `--permission-mode <mode>` - how much autonomy the agent runs with: `default` (approve each
   command), `acceptEdits` (auto-edit files, approve commands), or `bypassPermissions` (fully
   autonomous, the default). Both the agent and the mode you pick are persisted for `--resume`. For