@skitterbyte/skitterspec-jira 2.16.0 → 2.18.0
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/MIGRATION.md +78 -0
- package/assets/claude-md-section.md +6 -9
- package/assets/commands/allow-main.md +1 -2
- package/assets/core/env.config.json.example +0 -1
- package/assets/core/env.config.md +24 -27
- package/assets/review/page.html +10 -83
- package/assets/rules/spec-planning.md +14 -21
- package/assets/rules/spec-reports.md +112 -54
- package/assets/skills/no-spec/SKILL.md +2 -2
- package/assets/skills/spec/SKILL.md +2 -2
- package/assets/skills/spec-bug/SKILL.md +10 -13
- package/assets/skills/spec-diff/SKILL.md +47 -115
- package/assets/skills/spec-hotfix/SKILL.md +10 -13
- package/assets/skills/spec-next/SKILL.md +59 -42
- package/assets/skills/spec-review/SKILL.md +2 -2
- package/assets/skills/spec-reviewed/SKILL.md +1 -8
- package/package.json +1 -1
- package/src/cli.js +251 -204
- package/src/env/config.js +16 -7
- package/src/env/hooks.js +6 -3
- package/src/env/live.js +48 -0
- package/src/env/review.js +71 -173
- package/src/env/serve.js +3 -7
- package/src/init.js +509 -13
- package/assets/commands/spec-remote-review.md +0 -37
|
@@ -593,10 +593,9 @@ line with it where the engine printed one, and nothing where it did not.
|
|
|
593
593
|
`.claude/rules/spec-reports.md` carries the shape, including why a rigid
|
|
594
594
|
contract took that line.
|
|
595
595
|
|
|
596
|
-
- **Never write the review unasked**, and **never publish
|
|
597
|
-
|
|
598
|
-
|
|
599
|
-
`/spec-diff` §6 owns how.
|
|
596
|
+
- **Never write the review unasked**, and **never publish** — there is no
|
|
597
|
+
publishing (`/spec-diff` §6). A `file://` link is no use on a phone, and the
|
|
598
|
+
stack says why nothing was served.
|
|
600
599
|
**The `reader:` line no longer decides anything here, and that is the point.**
|
|
601
600
|
It is still printed, and it is still the only place that question is answered —
|
|
602
601
|
but the offer does not change with it, because the stack lists every tier
|
|
@@ -606,22 +605,20 @@ that branching is exactly what produced a `file://` page on a session detected
|
|
|
606
605
|
underneath a reader when detection flipped mid-session.
|
|
607
606
|
|
|
608
607
|
So: **relay all three tier lines, every time.** Any `also:` lines sit under
|
|
609
|
-
|
|
610
|
-
|
|
611
|
-
|
|
612
|
-
|
|
608
|
+
their tier — the other addresses this machine has of that kind — so pass them
|
|
609
|
+
on rather than editing them out: in the banner they are indented sub-bullets
|
|
610
|
+
under that tier, labels included, exactly as `.claude/rules/spec-reports.md`
|
|
611
|
+
shows.
|
|
613
612
|
|
|
614
613
|
**Never read an environment variable to decide anything about the offer** — not
|
|
615
614
|
`SSH_CONNECTION`, not `CLAUDE_CODE_*`, not a tty check. There is nothing left
|
|
616
615
|
here for a detection to decide, and a second implementation of one could not be
|
|
617
616
|
tested and would drift.
|
|
618
617
|
|
|
619
|
-
**Serving is the engine's to do
|
|
618
|
+
**Serving is the engine's to do, and there is nothing else.** A `remote` reader
|
|
620
619
|
authorises a local server — one process, ended by one flag, leaving nothing
|
|
621
|
-
behind
|
|
622
|
-
|
|
623
|
-
serve (a busy port, a machine with no network address) it falls back to the
|
|
624
|
-
`file://` URL with its marker, and that is when publishing is worth naming.
|
|
620
|
+
behind. If the engine could not serve (a busy port, a machine with no network
|
|
621
|
+
address) it falls back to the `file://` URL with its marker.
|
|
625
622
|
|
|
626
623
|
- **Never fatal.** A failed render — no worktree, a git error — is one line, and
|
|
627
624
|
the fix is still done. The page is a convenience; the repo is the record.
|
|
@@ -50,8 +50,10 @@ evidence.
|
|
|
50
50
|
Otherwise resolve **in this order**, and stop at the first that answers:
|
|
51
51
|
|
|
52
52
|
1. **The live spec of this checkout** — run
|
|
53
|
-
`skitterspec spec-env live status` and read its `
|
|
54
|
-
|
|
53
|
+
`skitterspec spec-env live status` and read its `in-flight:` line. A spec
|
|
54
|
+
name there is the spec whose branch is checked out here; that is the one to
|
|
55
|
+
build. `none` and `unknown` answer nothing — carry on down the list. (The
|
|
56
|
+
bare report's first line is a bare `spec-env live:` header, not an answer.)
|
|
55
57
|
2. **The worktree you are standing in** — if this session's cwd is inside a
|
|
56
58
|
spec's worktree, that spec is in flight *for this session*. This is the
|
|
57
59
|
manual-parallel path: several specs may be provisioned, and a terminal tab
|
|
@@ -62,10 +64,17 @@ Otherwise resolve **in this order**, and stop at the first that answers:
|
|
|
62
64
|
named, from wherever you happen to be standing:
|
|
63
65
|
|
|
64
66
|
```
|
|
65
|
-
skitterspec spec-env resolve
|
|
67
|
+
skitterspec spec-env resolve --json
|
|
66
68
|
```
|
|
67
69
|
|
|
68
|
-
Take its `spec
|
|
70
|
+
Take its `spec` **only when it names exactly one spec** (`ok: true`); `via`
|
|
71
|
+
says which rung answered.
|
|
72
|
+
|
|
73
|
+
From the primary checkout that includes the spec `/spec-live main` last
|
|
74
|
+
released here (`via: "last-live"`): releasing leaves the session standing
|
|
75
|
+
in the primary checkout, which says nothing on its own, so the engine
|
|
76
|
+
remembers the spec it handed back — for as long as that spec's worktree
|
|
77
|
+
exists — ahead of counting worktrees.
|
|
69
78
|
|
|
70
79
|
This is the **durable** rung, and that is the whole reason it exists. Rungs 1
|
|
71
80
|
to 3 all read *session* state, and session state does not survive a `/clear`,
|
|
@@ -81,13 +90,14 @@ Otherwise resolve **in this order**, and stop at the first that answers:
|
|
|
81
90
|
`.claude/rules/spec-planning.md` states has none left.
|
|
82
91
|
|
|
83
92
|
**Say which spec you resolved and how**, before writing a line of it:
|
|
84
|
-
*"not standing in a worktree — `<spec>` is the only spec provisioned"
|
|
93
|
+
*"not standing in a worktree — `<spec>` is the only spec provisioned"*, or
|
|
94
|
+
*"`<spec>` was last live on this checkout"*. Rungs
|
|
85
95
|
1 to 3 are self-evident to whoever typed the command; this one is not, and
|
|
86
96
|
the operator cannot see from where they sit what you picked.
|
|
87
97
|
|
|
88
|
-
**Several worktrees stay a refusal.** The engine
|
|
89
|
-
|
|
90
|
-
unchanged and stop; never pick from it.
|
|
98
|
+
**Several worktrees stay a refusal.** The engine answers `ok: false` with
|
|
99
|
+
`reason: "ambiguous"` and lists the `candidates`, each with its `worktree`,
|
|
100
|
+
and resolves nothing. Relay that list unchanged and stop; never pick from it.
|
|
91
101
|
|
|
92
102
|
WHAT WOULD FOOL THIS: a worktree left behind by a declined teardown is still
|
|
93
103
|
a worktree, so a finished spec can go on counting as provisioned. That widens
|
|
@@ -96,10 +106,18 @@ Otherwise resolve **in this order**, and stop at the first that answers:
|
|
|
96
106
|
manufacture an *absence*, which is why the absence below is still worth
|
|
97
107
|
refusing on.
|
|
98
108
|
|
|
99
|
-
**If none answers, refuse and stop
|
|
100
|
-
`
|
|
109
|
+
**If none answers, refuse and stop — and say which absence it is.** Rung 4's
|
|
110
|
+
`reason` tells them apart, and they send the reader to different places:
|
|
111
|
+
|
|
112
|
+
- **`reason: "none"`** — no spec has a worktree anywhere:
|
|
113
|
+
`no spec in flight — run /spec-start <name> to start one`.
|
|
114
|
+
- **`reason: "ambiguous"`** — several specs are in flight and this session is
|
|
115
|
+
standing in none of them: `several specs are in flight and this session is
|
|
116
|
+
not in one of them`, then the candidates as the engine listed them (spec and
|
|
117
|
+
worktree), and `/spec-next --worktree <path>` as the way to name one.
|
|
118
|
+
`/spec-start` is wrong here: every one of them is already started.
|
|
101
119
|
|
|
102
|
-
|
|
120
|
+
The first answers a real absence — no worktree anywhere, the engine included —
|
|
103
121
|
rather than a session that merely lost track of where it was standing.
|
|
104
122
|
|
|
105
123
|
**Never fall back to the spec "in context".** A spec discussed in conversation
|
|
@@ -329,6 +347,13 @@ plain markdown list in the conversation — never fenced, and
|
|
|
329
347
|
out of the terminal to find out what to do, which is the failure this exists to
|
|
330
348
|
fix; the steps themselves are what they act on.
|
|
331
349
|
|
|
350
|
+
**Steps you had to write are saved first.** When the phase file holds only a
|
|
351
|
+
vague manual task — "check it on the running host" — and you wrote the steps
|
|
352
|
+
yourself, add them under that task as numbered sub-checkboxes **before** you
|
|
353
|
+
ask. The conversation does not survive a `/clear`, and a later run that makes
|
|
354
|
+
up its own set lists different steps from the ones the reader was shown. A
|
|
355
|
+
phase whose manual steps are already tasks is left as it is.
|
|
356
|
+
|
|
332
357
|
Then ask one question, with three answers:
|
|
333
358
|
|
|
334
359
|
- **All done** — tick those steps and carry on to the end of the phase.
|
|
@@ -347,6 +372,8 @@ needs no new shape in the report.
|
|
|
347
372
|
tasks after an unconfirmed step are not built past it, and the phase did not
|
|
348
373
|
end: **skip §4's done-marking and §5 entirely** — no page, no arm, no wait.
|
|
349
374
|
End `⚠️` and name `/spec-next` in `Next`; it re-lists the same unticked steps.
|
|
375
|
+
Its `Next` lists the open steps a row each, copied from the phase file —
|
|
376
|
+
`.claude/rules/spec-reports.md`, *Open manual steps are rows*.
|
|
350
377
|
|
|
351
378
|
## 4. Record progress
|
|
352
379
|
|
|
@@ -482,11 +509,11 @@ so one subject lives in one place:
|
|
|
482
509
|
|
|
483
510
|
- **local** — <the `local:` URL>
|
|
484
511
|
- **network** — <the `network:` URL, or off with the command that turns it on>
|
|
485
|
-
- **remote** — <the `remote:` URL, or
|
|
512
|
+
- **remote** — <the `remote:` tailnet URL, or what that line says when there is none>
|
|
486
513
|
|
|
487
514
|
<the `live:` line, exactly as the engine printed it — omitted when it printed none>
|
|
488
515
|
|
|
489
|
-
I'm holding here until you send a verdict — the wait covers
|
|
516
|
+
I'm holding here until you send a verdict — the wait covers <the tiers the engine's `covers` names>.
|
|
490
517
|
|
|
491
518
|
`/spec-reviewed` picks it up · `spec-env review skip "<reason>"` moves on
|
|
492
519
|
|
|
@@ -507,22 +534,14 @@ reviewer sees the heading they have always seen.
|
|
|
507
534
|
printed one line per tier, in that order, and `--json` carries the same thing as
|
|
508
535
|
`tiers`. Relay all three whatever they say, including the ones that are off with
|
|
509
536
|
the command that turns them on: a reader who has left the house cannot ask for a
|
|
510
|
-
remote
|
|
537
|
+
remote door they were never shown.
|
|
511
538
|
|
|
512
539
|
**Do not pick one for them.** The engine used to, and the guess failed three
|
|
513
540
|
separate ways in one day. `.claude/rules/spec-reports.md` carries the shape and
|
|
514
541
|
why the *one link, never two* rule now reads
|
|
515
|
-
**one link per
|
|
516
|
-
local and
|
|
517
|
-
covers
|
|
518
|
-
*a verdict here needs `/spec-reviewed`*, because nothing pushes from
|
|
519
|
-
the artifact store into this conversation. Never let the holding line promise a
|
|
520
|
-
wait over that tier.
|
|
521
|
-
|
|
522
|
-
**Publishing is still never yours to do.** `remote` reading `off` is the normal
|
|
523
|
-
state, and the fix for it is the command on that line — typed by the operator,
|
|
524
|
-
or pressed on the page, because a published page is one this tooling cannot
|
|
525
|
-
remove and permitting it is not publishing it.
|
|
542
|
+
**one link per door, each labelled, all into one store** —
|
|
543
|
+
local, network and remote are three doors into one room, so the wait
|
|
544
|
+
covers every one the stack shows.
|
|
526
545
|
|
|
527
546
|
**The `live:` line goes with the stack**, and it is the engine's line too —
|
|
528
547
|
copied as printed, and **absent when the engine printed none**. The page can act
|
|
@@ -537,7 +556,7 @@ verdict.
|
|
|
537
556
|
**Where you are not waiting, it stays the `Review` row** — the counts and the
|
|
538
557
|
page link, and **no question**:
|
|
539
558
|
|
|
540
|
-
| **Review** | <N> files, +<a> −<d> · **local** <URL> · **network** <URL> · **remote**
|
|
559
|
+
| **Review** | <N> files, +<a> −<d> · **local** <URL> · **network** <URL> · **remote** <URL> (tailnet) |
|
|
541
560
|
|
|
542
561
|
At the end of a phase you are always waiting, so this shape belongs to the
|
|
543
562
|
renders that are not this step: a mid-phase `/spec-diff`, a page produced
|
|
@@ -651,10 +670,9 @@ Relay the engine's **stack** — the `local:`, `network:` and `remote:` lines
|
|
|
651
670
|
never the bare `page:` path: a path is not clickable in any terminal, and a page
|
|
652
671
|
nobody can open is a page nobody reads.
|
|
653
672
|
|
|
654
|
-
- **Never write the review unasked**, and **never publish
|
|
655
|
-
|
|
656
|
-
|
|
657
|
-
the ask — publishing is the answer to it, and `/spec-diff` §6 owns how.
|
|
673
|
+
- **Never write the review unasked**, and **never publish** — there is no
|
|
674
|
+
publishing (`/spec-diff` §6). A `file://` link is no use on a phone, and the
|
|
675
|
+
stack says why nothing was served.
|
|
658
676
|
**The `reader:` line no longer decides anything here, and that is the point.**
|
|
659
677
|
It is still printed, and it is still the only place that question is answered —
|
|
660
678
|
but the offer does not change with it, because the stack lists every tier
|
|
@@ -664,23 +682,20 @@ that branching is exactly what produced a `file://` page on a session detected
|
|
|
664
682
|
underneath a reader when detection flipped mid-session.
|
|
665
683
|
|
|
666
684
|
So: **relay all three tier lines, every time.** Any `also:` lines sit under
|
|
667
|
-
|
|
668
|
-
|
|
669
|
-
|
|
670
|
-
|
|
685
|
+
their tier — the other addresses this machine has of that kind — so pass them
|
|
686
|
+
on rather than editing them out: in the banner they are indented sub-bullets
|
|
687
|
+
under that tier, labels included, exactly as `.claude/rules/spec-reports.md`
|
|
688
|
+
shows.
|
|
671
689
|
|
|
672
690
|
**Never read an environment variable to decide anything about the offer** — not
|
|
673
691
|
`SSH_CONNECTION`, not `CLAUDE_CODE_*`, not a tty check. There is nothing left
|
|
674
692
|
here for a detection to decide, and a second implementation of one could not be
|
|
675
693
|
tested and would drift.
|
|
676
694
|
|
|
677
|
-
**Serving is the engine's to do
|
|
695
|
+
**Serving is the engine's to do, and there is nothing else.** The server is one
|
|
678
696
|
process, ended by one flag, leaving nothing behind, and `review.allowNetwork`
|
|
679
|
-
decides whether it binds wide —
|
|
680
|
-
|
|
681
|
-
the stack. Publishing leaves a page this tooling cannot remove, so it stays an
|
|
682
|
-
ask in every case, always — which is why `remote` shows the command rather than
|
|
683
|
-
a URL until someone types it.
|
|
697
|
+
decides whether it binds wide — on the LAN and the tailnet alike — with no
|
|
698
|
+
detection involved.
|
|
684
699
|
|
|
685
700
|
- **Never fatal.** A failed render — no worktree, a git error — is one line and
|
|
686
701
|
the phase is still done. The page is a convenience; the repo is the record.
|
|
@@ -700,9 +715,11 @@ the shape; this section carries only what is specific here.
|
|
|
700
715
|
- `⚠️` — built and green, with something worth knowing (a mirror that did not
|
|
701
716
|
refresh, a deviation from the plan) — or stopped at manual steps answered
|
|
702
717
|
**Some failed** or **Not yet**: the phase stays `🔄`, `Notes` says which steps
|
|
703
|
-
are open, and `Next` is `/commit
|
|
718
|
+
are open, and `Next` is `/commit`, then a row per open step, then
|
|
719
|
+
`/spec-next` to pick them up.
|
|
704
720
|
- `❌` — the phase's tests are red, or it stopped part-way. Quote the failure.
|
|
705
|
-
- `⏸` — no spec in flight,
|
|
721
|
+
- `⏸` — no spec in flight, several in flight with this session in none of
|
|
722
|
+
them, or the name given does not match the one that is.
|
|
706
723
|
|
|
707
724
|
**Fields:** `Tracker` · `Branch` · `Built` · `Tests` · `Notes` · `Review` ·
|
|
708
725
|
`Follow-ups` · `Next`
|
|
@@ -286,9 +286,9 @@ reader:
|
|
|
286
286
|
|
|
287
287
|
- **local** — <the `local:` URL>
|
|
288
288
|
- **network** — <the `network:` URL, or off with the command that turns it on>
|
|
289
|
-
- **remote** — <the `remote:` URL, or
|
|
289
|
+
- **remote** — <the `remote:` tailnet URL, or what that line says when there is none>
|
|
290
290
|
|
|
291
|
-
I'm holding here until you send a verdict — the wait covers
|
|
291
|
+
I'm holding here until you send a verdict — the wait covers <the tiers the engine's `covers` names>.
|
|
292
292
|
|
|
293
293
|
`Commit` commits the refresh · `Request changes` works them now
|
|
294
294
|
|
|
@@ -176,14 +176,7 @@ everything a decision needs, so there is nothing to go looking for, and going
|
|
|
176
176
|
looking is the bypass step 0 forbids. The file is right there and readable; that
|
|
177
177
|
is precisely why the rule is written down rather than assumed.
|
|
178
178
|
|
|
179
|
-
**
|
|
180
|
-
has a published page (`--json` reports a `url`): a reader off the LAN sent their
|
|
181
|
-
pass to the artifact's own `passes` collection rather than to the engine, so an
|
|
182
|
-
empty holding area is not an empty answer yet. Read it with the Artifact tool's
|
|
183
|
-
`read_db`, merge the `blob` through `--notes`, and **delete the document** —
|
|
184
|
-
`/spec-diff` §6 owns the whole sequence, including that a claim consumes.
|
|
185
|
-
|
|
186
|
-
**Nothing waiting in either is an ordinary answer.** Say so and stop. Do not hunt
|
|
179
|
+
**Nothing waiting is an ordinary answer.** Say so and stop. Do not hunt
|
|
187
180
|
through other specs, and do not treat an empty holding area as a problem — a
|
|
188
181
|
`file://` page copies to the clipboard instead of sending, so mention that the
|
|
189
182
|
pass may be on their clipboard waiting to be pasted, and finish.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@skitterbyte/skitterspec-jira",
|
|
3
|
-
"version": "2.
|
|
3
|
+
"version": "2.18.0",
|
|
4
4
|
"description": "Spec-driven development for Claude Code, with one-way Jira Cloud sync — a superset of @skitterbyte/skitterspec: the base filesystem workflow plus /spec-status · /spec-push and the spec-sync CLI. The repo is canonical; Jira is a generated mirror. Install this OR the base OR the Linear superset — exactly one.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"claude",
|