@rallycry/conveyor-skills 1.0.5 → 1.0.6
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/package.json
CHANGED
|
@@ -33,10 +33,9 @@ out in an **Environment** note — never assume; check which one you are in.
|
|
|
33
33
|
- **Never boot another environment for work you are doing.** Locally that
|
|
34
34
|
means never `mcp__conveyor__start_task` (it exists only on the local/MCP
|
|
35
35
|
surface, and it spawns a cloud pod that duplicates you). In a pod driving a
|
|
36
|
-
pack
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
Build on the parent, not something a build session opts into.
|
|
36
|
+
pack there is no tool that fires a child build at all — you implement the
|
|
37
|
+
children yourself, serially. A pack has one execution model in both
|
|
38
|
+
environments: one session owns all the state.
|
|
40
39
|
|
|
41
40
|
## Goal and finish line
|
|
42
41
|
|
|
@@ -19,7 +19,8 @@ alternative is where pack incidents come from.
|
|
|
19
19
|
parent already InProgress/ReviewPR has a coordinator — report and stop
|
|
20
20
|
rather than compete.
|
|
21
21
|
2. **Ensure the pack branch exists on origin.** Use the card's `githubBranch`
|
|
22
|
-
if set; otherwise cut `ft/<parent-slug>` from `origin
|
|
22
|
+
if set; otherwise cut `ft/<parent-slug>` from `origin/<base>` (the card's base
|
|
23
|
+
branch — usually `dev`), push `-u`, and
|
|
23
24
|
IMMEDIATELY record it: `mcp__conveyor__update_task` with
|
|
24
25
|
`githubBranch: <branch>`.
|
|
25
26
|
|
|
@@ -162,6 +163,12 @@ spell the argument differently (`base:` locally, `baseBranch:` in a pod).
|
|
|
162
163
|
> always opens the PR for the card the session is bound to, so mid-pack it would
|
|
163
164
|
> open the PARENT's PR early and strand every remaining child. One commit per
|
|
164
165
|
> child keeps the single final PR reviewable child by child.
|
|
166
|
+
>
|
|
167
|
+
> Every child status write carries the child's id: claim with
|
|
168
|
+
> `mcp__conveyor__update_task(task_id: <child>, status: "InProgress")` and land
|
|
169
|
+
> with `update_task(task_id: <child>, status: "ReviewDev")`. Without `task_id`
|
|
170
|
+
> the write targets the PARENT card you are bound to. No per-child build fires
|
|
171
|
+
> in a pod, so a status you do not write is a board that silently lies.
|
|
165
172
|
|
|
166
173
|
Before opening the child's PR, re-check the parent's status. If it went
|
|
167
174
|
InProgress or ReviewPR, a coordinator took over: post that you are yielding,
|
|
@@ -224,12 +231,11 @@ leave the branch pushed, and stop.
|
|
|
224
231
|
`githubBranch: <pack>`), advance the child by hand (`update_task` →
|
|
225
232
|
`ReviewDev`), and post the drift to parent chat so it is visible.
|
|
226
233
|
3. **Sync `dev` into the pack branch — yours to do, in either environment.**
|
|
227
|
-
|
|
228
|
-
|
|
229
|
-
in-session.)
|
|
234
|
+
Nothing server-side syncs the pack branch for you; a session driving the
|
|
235
|
+
pack resolves conflicts in-session.
|
|
230
236
|
|
|
231
237
|
```bash
|
|
232
|
-
git checkout <pack> && git pull && git fetch origin
|
|
238
|
+
git checkout <pack> && git pull && git fetch origin <base> && git merge origin/<base> --no-edit && git push
|
|
233
239
|
```
|
|
234
240
|
|
|
235
241
|
**Merge, never rebase** — the pack branch is shared with open child PRs and
|
|
@@ -238,7 +244,7 @@ leave the branch pushed, and stop.
|
|
|
238
244
|
|
|
239
245
|
If the merge drags in unrelated changes or errors, `dev` may have been
|
|
240
246
|
rewound (a revert or force-push). Verify the previous sync point is still an
|
|
241
|
-
ancestor of `origin
|
|
247
|
+
ancestor of `origin/<base>` (`git merge-base --is-ancestor`); if it is not,
|
|
242
248
|
abort the merge and escalate rather than chasing the noise.
|
|
243
249
|
4. Report the merge to parent chat in a line or two.
|
|
244
250
|
|
|
@@ -248,7 +254,7 @@ leave the branch pushed, and stop.
|
|
|
248
254
|
pack branch's actual state against the acceptance and verification criteria
|
|
249
255
|
— a real checklist pass, not a vibe. Small gap → fix on the pack branch.
|
|
250
256
|
Substantial gap → a new child card with a plan, and the loop continues.
|
|
251
|
-
2. Pre-PR protocol on the pack branch: sync `origin
|
|
257
|
+
2. Pre-PR protocol on the pack branch: sync `origin/<base>` FIRST, then ONE
|
|
252
258
|
verification pass scoped to the pack's cumulative diff against `dev`
|
|
253
259
|
(cross-package packs earn the full suite).
|
|
254
260
|
3. `mcp__conveyor__create_pull_request` on the PARENT: `head:` the pack branch,
|
|
@@ -151,8 +151,8 @@ which no pod reviewer could follow. Same defect the story-points paragraph below
|
|
|
151
151
|
already records.
|
|
152
152
|
|
|
153
153
|
Story points are deliberately NOT yours to change. `update_task`'s agent
|
|
154
|
-
surface omits `storyPointValue` on purpose, and
|
|
155
|
-
|
|
154
|
+
surface omits `storyPointValue` on purpose, and no pod tool carries the card's
|
|
155
|
+
OWN story points — so this used to be an instruction no reviewer could
|
|
156
156
|
follow. It is also a gate you sit behind rather than above: story points set
|
|
157
157
|
the card's graduated merge minimum, so a reviewer that could lower them would
|
|
158
158
|
be lowering the bar for merging the very PR under review. Flag a mis-sized
|
|
@@ -173,6 +173,19 @@ is the reviewer, and the independent review happens later on the pack's PR into
|
|
|
173
173
|
- You wrote this code, which makes self-review the weak point. An independent
|
|
174
174
|
reviewer with the diff and no memory of writing it catches what you cannot.
|
|
175
175
|
|
|
176
|
+
## Reviewing a pack's finale PR
|
|
177
|
+
|
|
178
|
+
A pack parent's PR into the base branch is an ordinary review of the pack's
|
|
179
|
+
cumulative diff — there is no coordination job. The parent's own session
|
|
180
|
+
implemented every child, so read the whole diff against the base and render one
|
|
181
|
+
verdict as above. Child cards have no merge gate of their own, so correcting a
|
|
182
|
+
CHILD's story points with `mcp__conveyor__update_subtask` (`storyPointValue`)
|
|
183
|
+
when the actual work diverged from the estimate is legitimate here, in either
|
|
184
|
+
direction — where the tool exists: a pod's review runner and a local session
|
|
185
|
+
carry it, a task session flipped to review does not (flag the mis-size in the
|
|
186
|
+
verdict instead). The parent card's own story points stay off-limits per the
|
|
187
|
+
note above.
|
|
188
|
+
|
|
176
189
|
## Blocked
|
|
177
190
|
|
|
178
191
|
If the PR cannot be reviewed as it stands — the plan is missing, the diff is
|