@rasensio/aidlc-content 1.64.0 → 1.65.0
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/docs/roadmap.md +6 -3
- package/package.json +1 -1
package/docs/roadmap.md
CHANGED
|
@@ -148,7 +148,10 @@ Each item goes through these steps:
|
|
|
148
148
|
boundary or the release boundary, or parks the item on a hard stop. A start that
|
|
149
149
|
fails parks the item with `parked — could not start: <error>` and autopilot goes straight on to
|
|
150
150
|
the next ready item; the parked one does not count toward `--items`. Retrying the same item every
|
|
151
|
-
pass is what held a whole `--all` run on one item for five hours.
|
|
151
|
+
pass is what held a whole `--all` run on one item for five hours. An agent that exits with an
|
|
152
|
+
error within 30 seconds of launch parks the item with `agent failed to launch (exit <code>):`
|
|
153
|
+
and the first line it printed, so a flag the agent no longer accepts names itself instead of
|
|
154
|
+
reading as a failed build.
|
|
152
155
|
3. **Your review, after each paused phase.** When a phase in `pause_after` is complete and
|
|
153
156
|
unapproved, the item waits as `awaiting-review` — not parked. Read the artifact in the item's
|
|
154
157
|
worktree, then `aidlc autopilot approve <instance>`; the next pass waits at the next paused
|
|
@@ -185,8 +188,8 @@ never edits a rank or a dependency: deciding what is agreed work stays a person'
|
|
|
185
188
|
six questions on its own. Each is a list with one choice marked recommended:
|
|
186
189
|
|
|
187
190
|
- **The agent, and what it may do.** Claude Code limited to editing files and running git, pnpm,
|
|
188
|
-
node and read-only shell tools (recommended); Claude Code with full access; Codex
|
|
189
|
-
|
|
191
|
+
node and read-only shell tools (recommended); Claude Code with full access; Codex editing and
|
|
192
|
+
running commands inside its `workspace-write` sandbox; or a command you type. This decides what an unattended agent may do on your machine, so
|
|
190
193
|
it is never picked for you: with no terminal, setup needs `--agent <preset>` or
|
|
191
194
|
`--non-interactive`.
|
|
192
195
|
- **How many items build at once** — two (recommended) or one.
|