joycraft 1.2.2 → 1.4.1
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/README.md +123 -57
- package/dist/joycraft-release.json +1 -1
- package/package.json +3 -3
- package/payload/.agents/skills/joycraft-context/SKILL.md +5 -6
- package/payload/.agents/skills/joycraft-entry/SKILL.md +15 -20
- package/payload/.agents/skills/joycraft-implement/SKILL.md +8 -10
- package/payload/.agents/skills/joycraft-session-end/SKILL.md +8 -13
- package/payload/.agents/skills/joycraft-testing/SKILL.md +0 -6
- package/payload/.agents/skills/joycraft-verify/SKILL.md +5 -8
- package/payload/.joycraft/references/architecture.md +2 -4
- package/payload/.joycraft/references/context.md +11 -34
- package/payload/.joycraft/references/dispatch.md +7 -40
- package/payload/.joycraft/references/gates.md +60 -0
- package/payload/.joycraft/references/retro.md +6 -15
- package/payload/.joycraft/references/settings.md +60 -0
- package/payload/.joycraft/references/setup.md +4 -4
- package/payload/.joycraft/references/worktrees.md +1 -1
- package/payload/.joycraft/runtime/dispatch-start.mjs +61 -4
- package/payload/.joycraft/runtime/gate.mjs +308 -0
- package/payload/.joycraft/runtime/status.mjs +1 -1
- package/payload/PIN +20 -17
- package/payload/scripts/export.mjs +5 -2
package/README.md
CHANGED
|
@@ -30,11 +30,11 @@ Install Joycraft in this project.
|
|
|
30
30
|
Do not commit, publish, or ask me for API keys.
|
|
31
31
|
```
|
|
32
32
|
|
|
33
|
-
**Upgrading from 0.7?** Nothing changes until you choose.
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
[
|
|
37
|
-
|
|
33
|
+
**Upgrading from 0.7?** Nothing changes until you choose. Paste the
|
|
34
|
+
[upgrade prompt](docs/prompts.md#upgrade-from-07): your agent shows you the migration
|
|
35
|
+
plan and waits for your yes. To stay on 0.7, paste the
|
|
36
|
+
[stay on 0.7 prompt](docs/prompts.md#stay-on-07). More:
|
|
37
|
+
[Migrating from 0.7](docs/migrating-from-0.7.md).
|
|
38
38
|
|
|
39
39
|
## How to use it
|
|
40
40
|
|
|
@@ -104,57 +104,55 @@ agent both views: the whole project and the detail of the current step.
|
|
|
104
104
|
(`.joycraft-spec-queue.json`) is the status of record, not the text.
|
|
105
105
|
- **`docs/archive/` is history.** Finished features move there.
|
|
106
106
|
|
|
107
|
-
Joycraft
|
|
108
|
-
|
|
109
|
-
|
|
110
|
-
|
|
111
|
-
|
|
112
|
-
|
|
113
|
-
|
|
114
|
-
|
|
115
|
-
|
|
116
|
-
```yaml
|
|
117
|
-
paths:
|
|
118
|
-
features: working/features # default docs/features
|
|
119
|
-
archive: working/archive # default docs/archive
|
|
120
|
-
hooks:
|
|
121
|
-
afterArchive: node scripts/wiki-sync.mjs
|
|
122
|
-
cleanup:
|
|
123
|
-
impact:
|
|
124
|
-
- source: src/auction/**
|
|
125
|
-
docs: [docs/context/auction-rules.md]
|
|
107
|
+
**Your wiki.** Joycraft works with the wiki you already keep. Tell your agent where
|
|
108
|
+
it is: the agent links it from the context map and can update it each time a
|
|
109
|
+
feature is archived. In doc audits, `docs/features/` and `docs/archive/` are
|
|
110
|
+
working material and history, not current knowledge. A built-in wiki is under
|
|
111
|
+
consideration ([decision D6](docs/context/decision-log.md)).
|
|
112
|
+
|
|
113
|
+
```text
|
|
114
|
+
We keep a wiki in <where>. Link it from the context map, and keep it up to date
|
|
115
|
+
each time a feature is archived.
|
|
126
116
|
```
|
|
127
117
|
|
|
128
|
-
|
|
129
|
-
|
|
118
|
+
### Settings
|
|
119
|
+
|
|
120
|
+
Joycraft works with no settings. To change one, say what you want:
|
|
121
|
+
|
|
122
|
+
```text
|
|
123
|
+
Keep Joycraft's briefs and specs in working/features.
|
|
124
|
+
Whenever a feature is archived, run our wiki sync script.
|
|
125
|
+
The page docs/context/auction-rules.md describes src/auction. Flag it when that code changes.
|
|
126
|
+
```
|
|
130
127
|
|
|
131
|
-
The
|
|
132
|
-
|
|
133
|
-
|
|
128
|
+
The agent writes the change to `joycraft.yaml` at the project root, shows it to you
|
|
129
|
+
first, and checks it. Ask "What are my Joycraft settings?" to see what is in effect.
|
|
130
|
+
The file is yours: Joycraft changes it only when you ask. If a command run after an
|
|
131
|
+
archive fails, the archive still counts as done.
|
|
134
132
|
|
|
135
133
|
### Keeping the workspace clean
|
|
136
134
|
|
|
137
|
-
At the end of a session the agent
|
|
138
|
-
|
|
139
|
-
|
|
140
|
-
|
|
141
|
-
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
|
|
148
|
-
material, broken, missing or unmapped pages, an AGENTS.md over its
|
|
149
|
-
and pages whose code changed.
|
|
135
|
+
At the end of a session the agent checks the workspace for you. You do not run
|
|
136
|
+
anything:
|
|
137
|
+
|
|
138
|
+
- **Status.** It runs the gate check (below). The check finds specs marked done with
|
|
139
|
+
no accepted review and specs whose text disagrees with the queue. It also finds
|
|
140
|
+
features that are finished but not archived.
|
|
141
|
+
- **Worktrees.** It removes its worker worktrees once their spec is done and merged.
|
|
142
|
+
It keeps anything unfinished, unmerged or not made by Joycraft, and says why.
|
|
143
|
+
- **One coordinator.** One session coordinates each queue, so a second session's
|
|
144
|
+
instructions do not reach the first session's workers.
|
|
145
|
+
- **Stale knowledge.** It reports finished features not archived, context pages that
|
|
146
|
+
link to working material, broken, missing or unmapped pages, an AGENTS.md over its
|
|
147
|
+
word budget, and pages whose code changed.
|
|
150
148
|
- The doc audit, based on [doc-cleanup](https://github.com/aka-luan/doc-cleanup),
|
|
151
149
|
runs at every session end without being asked. It covers AGENTS.md, CLAUDE.md, the
|
|
152
150
|
docs the session changed and the pages they link; after a feature is archived, the
|
|
153
151
|
whole project. It checks each claim against the code, keeps your rules and traps,
|
|
154
152
|
puts its findings on the session-end page, and changes nothing until you approve.
|
|
155
153
|
Ask your agent to "clean up the docs" for a full audit at any time.
|
|
156
|
-
-
|
|
157
|
-
|
|
154
|
+
- **Wiring.** It checks that AGENTS.md has the Joycraft lines and a real context map,
|
|
155
|
+
and that CLAUDE.md imports it.
|
|
158
156
|
|
|
159
157
|
Tests name the acceptance criterion they check, `[AC:<criterion-id>]`, so the
|
|
160
158
|
reviewing agent can see which criteria have a test. A criterion with no test is a
|
|
@@ -193,6 +191,69 @@ counts as evidence; your project keeps its own tools.
|
|
|
193
191
|
After an update, the agent checks the review loop again and asks only about what
|
|
194
192
|
changed.
|
|
195
193
|
|
|
194
|
+
### The gates: no spec is done without an accepted review
|
|
195
|
+
|
|
196
|
+
Joycraft's rule is that only an accepted review completes a spec. Without the
|
|
197
|
+
gates, this rule is an instruction in a skill. An agent can forget the rule or skip
|
|
198
|
+
it, for example late in a long session. The gates make the rule a check.
|
|
199
|
+
|
|
200
|
+
**What the gate stops.** The gate check finds three problems:
|
|
201
|
+
|
|
202
|
+
- A spec is marked done with no accepted review, no acceptance from you and no waiver.
|
|
203
|
+
- A spec has one status in the queue and a different status in the spec file.
|
|
204
|
+
- Joycraft cannot read a queue file or a spec file.
|
|
205
|
+
|
|
206
|
+
It sends the agent back with the spec or file name and the next step. A spec that waits at
|
|
207
|
+
`in-review` is not a problem.
|
|
208
|
+
|
|
209
|
+
**Why you want it.** Use the gates for long sessions and for sessions that you do
|
|
210
|
+
not watch. A prompt tells the agent what to do, but a prompt is not a guarantee.
|
|
211
|
+
With the gates on, Claude Code runs the check each time the agent tries to stop. The
|
|
212
|
+
agent cannot stop until the problem is gone.
|
|
213
|
+
|
|
214
|
+
**Before you turn them on.** An older project can have specs marked done with no
|
|
215
|
+
accepted review. The check sends each one back for a review. To see them first, say:
|
|
216
|
+
|
|
217
|
+
```text
|
|
218
|
+
Run Joycraft's gate check with `node .joycraft/runtime/gate.mjs check` and show me
|
|
219
|
+
what it names. Change nothing yet.
|
|
220
|
+
```
|
|
221
|
+
|
|
222
|
+
Do this also after you update an older project to 1.4.1, because session end now
|
|
223
|
+
runs the same check.
|
|
224
|
+
|
|
225
|
+
**Turn them on.** Say:
|
|
226
|
+
|
|
227
|
+
```text
|
|
228
|
+
Turn on Joycraft's gates.
|
|
229
|
+
```
|
|
230
|
+
|
|
231
|
+
The agent shows you the change to `.claude/settings.json` on a page. It writes the
|
|
232
|
+
change only on your yes. The change adds one Stop hook and no other line. Setup
|
|
233
|
+
also offers the gates one time.
|
|
234
|
+
|
|
235
|
+
**Turn them off.** Say:
|
|
236
|
+
|
|
237
|
+
```text
|
|
238
|
+
Turn off Joycraft's gates.
|
|
239
|
+
```
|
|
240
|
+
|
|
241
|
+
The agent removes Joycraft's hook. Your own hooks stay. If you remove Joycraft from
|
|
242
|
+
the project, the agent removes this hook first.
|
|
243
|
+
|
|
244
|
+
**What the gates do not do.**
|
|
245
|
+
|
|
246
|
+
- The hook is for Claude Code only for now. On the other agents, the session-end
|
|
247
|
+
skill runs the check. That step is an instruction, so the agent can still skip it.
|
|
248
|
+
- There is no CI check. Joycraft does not check your pull requests.
|
|
249
|
+
- The hook is not a sandbox. A shell command can still change the queue file. The
|
|
250
|
+
check finds the result at the next stop.
|
|
251
|
+
|
|
252
|
+
**A fourth review is refused.** On every agent, one spec gets at most three
|
|
253
|
+
reviews. A round is one set of reviewed inputs, so a new review of the same code
|
|
254
|
+
does not count again. Reviewer startup prints the round and refuses a fourth
|
|
255
|
+
review. The agent then records `## Decision needed` in the spec and asks you.
|
|
256
|
+
|
|
196
257
|
## Answering questions: the decision page
|
|
197
258
|
|
|
198
259
|
When the agent needs you to choose between options, it asks in your question
|
|
@@ -235,8 +296,9 @@ project:
|
|
|
235
296
|
|
|
236
297
|
All of it lives in your repository. Joycraft collects no data and does not call an AI
|
|
237
298
|
model itself. Its only network use is the version check below. Joycraft adds no
|
|
238
|
-
agent hooks and changes no agent settings
|
|
239
|
-
|
|
299
|
+
agent hooks and changes no agent settings, except the gate hook that you turn on
|
|
300
|
+
([The gates](#the-gates-no-spec-is-done-without-an-accepted-review)). A command
|
|
301
|
+
after an archive runs only if you asked for one.
|
|
240
302
|
|
|
241
303
|
## Updates
|
|
242
304
|
|
|
@@ -270,20 +332,24 @@ Check for a Joycraft update.
|
|
|
270
332
|
"Tested" means: we installed Joycraft in a test project, one agent built a spec, and
|
|
271
333
|
a second, separate agent checked it and passed it.
|
|
272
334
|
|
|
273
|
-
##
|
|
335
|
+
## Everything else: ask your agent
|
|
274
336
|
|
|
275
|
-
|
|
337
|
+
You never need to run a Joycraft command yourself. Each of these is a short prompt
|
|
338
|
+
in [Prompts](docs/prompts.md):
|
|
276
339
|
|
|
277
|
-
|
|
278
|
-
|
|
279
|
-
|
|
280
|
-
|
|
281
|
-
|
|
282
|
-
|
|
283
|
-
|
|
340
|
+
| You want to | Say |
|
|
341
|
+
|---|---|
|
|
342
|
+
| Update Joycraft | "Check for a Joycraft update." |
|
|
343
|
+
| Check the install | "Check my Joycraft install." |
|
|
344
|
+
| Change a setting | "Keep Joycraft's specs in working/features." |
|
|
345
|
+
| Connect your wiki | "Link our wiki and keep it up to date." |
|
|
346
|
+
| Clean up | "Clean up the docs and the workspace." |
|
|
347
|
+
| Turn the gates on | "Turn on Joycraft's gates." |
|
|
348
|
+
| Turn the gates off | "Turn off Joycraft's gates." |
|
|
349
|
+
| Undo the 1.0 upgrade | "Undo this project's upgrade to Joycraft 1.0." |
|
|
350
|
+
| Remove Joycraft | "Remove Joycraft from this project." |
|
|
284
351
|
|
|
285
|
-
|
|
286
|
-
outside a terminal, a command shows its plan and stops. It never waits for input.
|
|
352
|
+
The CLI commands behind them are in the [install guide](docs/install.md#cli-reference).
|
|
287
353
|
|
|
288
354
|
More: [Install guide](docs/install.md) · [Migrating from 0.7](docs/migrating-from-0.7.md) ·
|
|
289
355
|
[Prompts](docs/prompts.md) · [Changelog](CHANGELOG.md) · [Security](SECURITY.md) ·
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "joycraft",
|
|
3
|
-
"version": "1.
|
|
3
|
+
"version": "1.4.1",
|
|
4
4
|
"description": "Install and update Joycraft, a skill bundle and runtime for agent-led software work, in any project",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"bin": {
|
|
@@ -13,8 +13,8 @@
|
|
|
13
13
|
"payload"
|
|
14
14
|
],
|
|
15
15
|
"joycraft": {
|
|
16
|
-
"release": "1.
|
|
17
|
-
"summary": "
|
|
16
|
+
"release": "1.4.1",
|
|
17
|
+
"summary": "Gates: say \"Turn on Joycraft's gates\" and Claude Code cannot stop while a spec is done without an accepted review; session end runs the same check on every agent, and a fourth review is refused.",
|
|
18
18
|
"autoSafeEligible": false
|
|
19
19
|
},
|
|
20
20
|
"scripts": {
|
|
@@ -20,16 +20,15 @@ node .joycraft/runtime/context/cli.mjs --query "<current request>"
|
|
|
20
20
|
Narrow discovery with `--paths docs/context src/relevant-area` when the relevant
|
|
21
21
|
area is known. Retrieval excludes `docs/archive/` unless historical material is
|
|
22
22
|
specifically needed; add `--history` to inspect it as reading context, never as
|
|
23
|
-
current authority.
|
|
24
|
-
installed; otherwise they come in local-search order. Read `.joycraft/references/context.md` for output
|
|
23
|
+
current authority. Results come in local-search order. Read `.joycraft/references/context.md` for output
|
|
25
24
|
and failure details.
|
|
26
25
|
|
|
27
|
-
Read useful
|
|
28
|
-
reading order; low scores do not remove files or define task scope. Check omitted
|
|
29
|
-
|
|
26
|
+
Read useful source files and follow their relevant links. Local scores guide
|
|
27
|
+
reading order; low scores do not remove files or define task scope. Check omitted
|
|
28
|
+
and unreadable reasons.
|
|
30
29
|
Refine the query or paths when local keyword matching misses a known dependency.
|
|
31
30
|
When the requested change has an unclear state, data, or responsibility seam,
|
|
32
|
-
trace the actual counterpart sources beyond the
|
|
31
|
+
trace the actual counterpart sources beyond the result list: for example, the
|
|
33
32
|
owner alongside its callers, readers, writers, or persistence boundary. Add
|
|
34
33
|
discovered sources to the work's declared inputs and report any unresolved
|
|
35
34
|
coverage. Read `.joycraft/references/architecture.md` only for that
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: joycraft-entry
|
|
3
|
-
description: Start any Joycraft work. After Joycraft is installed,
|
|
4
|
-
compatibility: Setup
|
|
3
|
+
description: Start any Joycraft work. After Joycraft is installed, when asked to "set up Joycraft", "check the context map", change Joycraft settings or remove Joycraft, read the project, interview the user and build the context map in AGENTS.md; then turn a repair, feature, or mixed request into a context-backed brief and the next useful action.
|
|
4
|
+
compatibility: Setup helpers require Node.js 22+ and the installed .joycraft runtime only when used; ordinary brief and context navigation has no project-stack prerequisite.
|
|
5
5
|
---
|
|
6
6
|
|
|
7
7
|
Run `node .joycraft/runtime/update-check.mjs check` first, once per session. If it
|
|
@@ -24,7 +24,7 @@ alone does not start a full setup.
|
|
|
24
24
|
|
|
25
25
|
Read existing project instructions first. During an upgrade, inspect the installed
|
|
26
26
|
manifest’s `legacyConflicts` and reconcile competing old skill discovery before
|
|
27
|
-
|
|
27
|
+
choosing skills; preserved custom content is not a completed migration.
|
|
28
28
|
On a bare project, offer the
|
|
29
29
|
[kickoff](../../../.joycraft/references/setup.md#kickoff-for-a-new-project)
|
|
30
30
|
in one line before any brief or scaffold, and run it when the user asks for it on
|
|
@@ -49,7 +49,7 @@ scope or a consequential choice.
|
|
|
49
49
|
|
|
50
50
|
When an unclear state, data, or responsibility boundary could change the work,
|
|
51
51
|
do focused discovery before splitting it: inspect the actual owner and its
|
|
52
|
-
callers, readers, writers, or other coupled counterpart.
|
|
52
|
+
callers, readers, writers, or other coupled counterpart. Search can point to
|
|
53
53
|
sources, but does not replace that trace. Keep settled product behavior in the
|
|
54
54
|
brief; record only durable, source-backed navigation in the project's existing
|
|
55
55
|
context homes. Read `.joycraft/references/architecture.md` for this
|
|
@@ -103,6 +103,15 @@ with no options.
|
|
|
103
103
|
`node .joycraft/runtime/config.mjs` and use its `paths` wherever Joycraft guidance
|
|
104
104
|
says `docs/features`, `docs/archive` or `docs/context`.
|
|
105
105
|
|
|
106
|
+
**Change settings when asked.** When the user asks to move Joycraft's folders, run
|
|
107
|
+
something after a feature is archived (such as a wiki sync), map code to a context
|
|
108
|
+
page, connect their wiki, see their settings or remove Joycraft, follow
|
|
109
|
+
[settings](../../../.joycraft/references/settings.md). The user never edits
|
|
110
|
+
`joycraft.yaml` or runs a Joycraft command by hand.
|
|
111
|
+
|
|
112
|
+
**Gates by request.** When the user asks to turn Joycraft's gates on or off, or
|
|
113
|
+
what they do, follow [gates](../../../.joycraft/references/gates.md).
|
|
114
|
+
|
|
106
115
|
**Show documents as pages.** A brief, plan, spec set or review that the user must
|
|
107
116
|
read or approve is also rendered, never left as Markdown in chat: the decision
|
|
108
117
|
artifact for a brief, an HTML page for anything else. Show it as
|
|
@@ -126,20 +135,6 @@ existing direct path when it fits the request. Do not turn routine data entry
|
|
|
126
135
|
into a code-spec factory or create per-record plans when an approved batch tool
|
|
127
136
|
already owns the operation. Preserve its validation, approval and readback rules.
|
|
128
137
|
|
|
129
|
-
When a native hook adds routing advice to the prompt, use it to select relevant
|
|
130
|
-
skills. Keep all expressed goals even when a classifier misses a signal. Do not
|
|
131
|
-
repeat a live routing call when the hook already provided current advice.
|
|
132
|
-
Routing does not approve scope, answer a decision, or establish evidence.
|
|
133
|
-
|
|
134
138
|
Use `joycraft-context` when you need to find relevant project files beyond the
|
|
135
|
-
context map. Its deterministic search
|
|
136
|
-
|
|
137
|
-
failures, read `.joycraft/references/hooks-runtime.md`. Treat unavailable
|
|
138
|
-
checks as unavailable, never as approval. For a denial, compare its cited scope
|
|
139
|
-
with the current task and the actual human question/answer. Repair missing
|
|
140
|
-
source delivery once through the documented binding flow, then resume understood
|
|
141
|
-
authorized work. Do not ask for the same permission again, move a chat answer to
|
|
142
|
-
a different document as an enforcement workaround, weaken a gate, or wrap a
|
|
143
|
-
denied command. Ask the host for the legitimate correction when needed.
|
|
144
|
-
If native hooks are absent and routing is materially uncertain, the explicit adapter in `.joycraft/references/routing.md` remains available.
|
|
145
|
-
When requested setup includes native hooks, use [Codex hook installation](../../../.joycraft/references/hooks-install.md) or [Claude Code hook installation](../../../.joycraft/references/hooks-claude.md) for the active host. Installation and project setup do not establish host trust or execution.
|
|
139
|
+
context map. Its deterministic search provides pointers; read the selected
|
|
140
|
+
source before relying on it.
|
|
@@ -30,10 +30,7 @@ For normal native execution, the host launches the selected worker first. The
|
|
|
30
30
|
child bootstraps from its actual root, then runs `dispatch-start.mjs --role
|
|
31
31
|
implementer` with its actual native identity before any tasked edit or mutation.
|
|
32
32
|
The coordinator runs that start itself only when it is the implementer actor.
|
|
33
|
-
Use the returned packet only when `ready` is true.
|
|
34
|
-
workflow can be ready; unavailable hook status is not a new permission gate for
|
|
35
|
-
all work. When startup returns unenforced, hold only that claimed enforced task,
|
|
36
|
-
report why, and continue unrelated authorized or manual/disabled workflow.
|
|
33
|
+
Use the returned packet only when `ready` is true.
|
|
37
34
|
|
|
38
35
|
If existing independent reports reveal a possible recurring failure, follow [recurring failure guidance](../../../.joycraft/references/recurring-failures.md) before carrying it forward: inspect the current scoped sources and actual counterpart path or journey, then provide any proposed lesson as exact inputs through the existing dispatch flow. A verified repair may establish its local project fact; a broader method benefit remains pending later reuse.
|
|
39
36
|
|
|
@@ -77,9 +74,9 @@ It needs actual host session/agent identity and available current authority
|
|
|
77
74
|
as described in [dispatch guidance](../../../.joycraft/references/dispatch.md).
|
|
78
75
|
Write its packet or subject beneath a confirmed Git-ignored project-local
|
|
79
76
|
directory, not among reviewed sources.
|
|
80
|
-
If
|
|
81
|
-
|
|
82
|
-
|
|
77
|
+
If a separate review context/capability is unavailable, leave the spec
|
|
78
|
+
`in-review`; do not invent an ID to continue. This holds the claimed review,
|
|
79
|
+
not unrelated authorized work.
|
|
83
80
|
|
|
84
81
|
When a recorded tool breaks during a run (the dev server does not start, a
|
|
85
82
|
port is taken, the browser or simulator crashes), repair it with what the user
|
|
@@ -101,9 +98,10 @@ Only the guarded completion path can move an `in-review` spec to `done`. Use its
|
|
|
101
98
|
|
|
102
99
|
When a current independent review is `FAIL` or `UNVERIFIED`, first fix
|
|
103
100
|
straightforward failures within the existing authorization and obtain a fresh
|
|
104
|
-
review. A spec gets at most three reviews
|
|
105
|
-
|
|
106
|
-
|
|
101
|
+
review. A spec gets at most three reviews: reviewer startup prints
|
|
102
|
+
`reviewRound` and refuses a fourth. Settled briefs and checked specs should make
|
|
103
|
+
this rare. If startup refuses a review, or a second FAIL on the same criterion
|
|
104
|
+
or a "decision needed" finding still occurs, send no
|
|
107
105
|
further fix and never amend acceptance yourself: note it under `## Decision
|
|
108
106
|
needed` in the spec, leave it `in-review`, and continue independent ready work. An owner can explicitly accept the
|
|
109
107
|
current findings and their stated limits through `accept-owner`; that is a
|
|
@@ -8,11 +8,6 @@ compatibility: Requires Node.js 22+ and the installed .joycraft runtime for the
|
|
|
8
8
|
|
|
9
9
|
Use this skill when pausing or finishing an authorized queue session.
|
|
10
10
|
|
|
11
|
-
On Claude `SessionEnd`, write only the local session summary and deduplicate the
|
|
12
|
-
transition record. Do not call an API or archive from that hook. On other hosts,
|
|
13
|
-
use their metrics/manual or portable summary path when available; never infer a
|
|
14
|
-
Claude lifecycle event from a generic session boundary.
|
|
15
|
-
|
|
16
11
|
Read each touched queue and report the real state of every affected spec: `todo`, `in-review`, or `done`. `done` must have either an accepted PASS report receipt or a completion-helper owner-acceptance record bound to a current failed or unverified report; a commit, PASS command, or implementer assertion is not acceptance. Keep blocked or failed dependency branches explicit while identifying independent ready work that can continue next.
|
|
17
12
|
|
|
18
13
|
If the session stops or restarts a concurrent run, report its recorded
|
|
@@ -20,8 +15,7 @@ coordinator ownership, captured refs, known worker trees, leases, locks, and
|
|
|
20
15
|
runtime processes. Release only resources demonstrably owned by that run;
|
|
21
16
|
retain ambiguous merges, locks, processes, and trees for diagnosis. Do not
|
|
22
17
|
force local state to a remote tip. Start a replacement only from the durable
|
|
23
|
-
run journal and a newly printed dispatch plan.
|
|
24
|
-
project/native runtime boundary; it does not enforce lifecycle behavior.
|
|
18
|
+
run journal and a newly printed dispatch plan.
|
|
25
19
|
|
|
26
20
|
For each completed spec, report the implementation revision, independent reviewer session ID, report and receipt paths, actual commands and outcomes, visual inspection status where required, and known limitations. For owner-accepted work, also report the owner-acceptance record and its inherited limits as `done, owner-accepted with <limits>`; preserve the original `FAIL` or `UNVERIFIED` report rather than calling it PASS or verified. List each spec completed under a feature waiver as `done, waived by the user: "<instruction>"`, with any report's real verdict; never call it reviewed or verified.
|
|
27
21
|
|
|
@@ -29,12 +23,13 @@ If a completion operation failed or was interrupted, do not declare success or h
|
|
|
29
23
|
|
|
30
24
|
Leave enough project-relative paths and next actions for another session to resume the autonomous ready authorized queue without recreating settled context or decisions.
|
|
31
25
|
|
|
32
|
-
Before ending
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
26
|
+
Before ending, run `node .joycraft/runtime/status.mjs --fix` (repairs lagging
|
|
27
|
+
frontmatter of accepted specs, lists features ready to archive) and
|
|
28
|
+
`node .joycraft/runtime/gate.mjs check`. Do the step each gate message names,
|
|
29
|
+
such as a completing command. Tell the user each message you could not clear.
|
|
30
|
+
Then preview `node .joycraft/runtime/worktrees.mjs prune` and apply it with
|
|
31
|
+
`--apply`: it removes only clean, integrated trees of done specs and keeps the
|
|
32
|
+
rest with their reason. Report kept trees and their size from `list`.
|
|
38
33
|
When this session coordinated a queue and no work on it remains, release the
|
|
39
34
|
lease with `node .joycraft/runtime/coordinator.mjs release --queue <queue> --session <your-session-id>`. See [worker isolation](../../../.joycraft/references/worktrees.md)
|
|
40
35
|
when the session used parallel mutable workers.
|
|
@@ -6,12 +6,6 @@ compatibility: The optional shared evidence validator requires Node.js 22+ and t
|
|
|
6
6
|
|
|
7
7
|
# Useful testing evidence
|
|
8
8
|
|
|
9
|
-
Use any post-edit hook findings as candidate gaps to inspect against the active
|
|
10
|
-
requirements and relevant tests. A flag is not proof of a defect, and no flag is
|
|
11
|
-
not proof of coverage. Keep valid gaps visible until a useful assertion or
|
|
12
|
-
observed interaction resolves them; missing tests during intermediate edits do
|
|
13
|
-
not require stopping understood implementation.
|
|
14
|
-
|
|
15
9
|
Read the active requirements and relevant existing tests. Choose the smallest
|
|
16
10
|
boundary that can establish each claim: real function inputs for arithmetic,
|
|
17
11
|
composed transitions for stateful behavior, rendered interaction for UI behavior.
|
|
@@ -29,10 +29,9 @@ prepare a source packet for a manual boundary, but it must not bind the child
|
|
|
29
29
|
using the parent's identity. After launch, the reviewer child bootstraps at its
|
|
30
30
|
actual root and runs `dispatch-start.mjs --role reviewer` with its own actual
|
|
31
31
|
native identity, which captures the subject, preflights delivery, writes the
|
|
32
|
-
bounded packet
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
result holds only the claimed review, not unrelated work.
|
|
32
|
+
bounded packet. If the real ID or a separate reviewer context is unavailable,
|
|
33
|
+
leave the spec `in-review`; do not manufacture either. This holds only the
|
|
34
|
+
claimed review, not unrelated work.
|
|
36
35
|
Reviewer startup output also carries `trace`, the spec's criteria with the tests
|
|
37
36
|
tagged `[AC:<criterion-id>]` (`node .joycraft/runtime/trace.mjs --queue <queue> --spec <id>`
|
|
38
37
|
produces the same). Report untraced criteria as findings; a missing tag alone is
|
|
@@ -44,10 +43,8 @@ Dispatch `collaboration.spawn_agent` with `fork_turns: "none"` and the packet's
|
|
|
44
43
|
|
|
45
44
|
When already dispatched as the independent reviewer, perform the review directly; do not recursively dispatch another reviewer. Read the parent brief, spec, queue entry, declared criteria and exact verification inputs. Use the supplied subject, set independence truthfully, and do not self-certify implementation from your own context.
|
|
46
45
|
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
score or clean hook receipt cannot establish acceptance. Check changed tests for
|
|
50
|
-
weakened assertions that could hide the requested behavior.
|
|
46
|
+
Check changed tests for weakened assertions that could hide the requested
|
|
47
|
+
behavior.
|
|
51
48
|
|
|
52
49
|
Review scope as well as behavior: determine whether the listed inputs and criteria cover the requested work, including relevant newly changed files. For a cross-boundary change, inspect the combined observable behavior across the relevant producer, consumer, state or storage boundary; separate green helpers, snapshots, or assertion counts do not establish that behavior. If a material counterpart or owning decision/context source was omitted, report the scope gap and require its exact path to be added before a fresh current review subject is prepared. Preserve the snapshot's implementation revision as provenance while checking its current bound inputs. A changed, missing, or renamed input makes the subject stale; do not substitute a newer HEAD as its identity.
|
|
53
50
|
|
|
@@ -79,10 +79,8 @@ subject or provide the reviewer with an intended verdict or implementer reasonin
|
|
|
79
79
|
Update only affected accepted facts in their owning reference, reconciling them
|
|
80
80
|
at session end before any eligible archival. Active choices remain in their
|
|
81
81
|
brief; rationale links to that choice; proposals stay marked as proposals.
|
|
82
|
-
References describe and navigate the project. They
|
|
83
|
-
|
|
84
|
-
extra live classification calls merely to maintain a map. Retrieval scores and
|
|
85
|
-
this procedure do not certify exhaustive discovery.
|
|
82
|
+
References describe and navigate the project. They do not grant permission.
|
|
83
|
+
Retrieval scores and this procedure do not certify exhaustive discovery.
|
|
86
84
|
|
|
87
85
|
Keep task context bounded to relevant sources. When evaluating the change,
|
|
88
86
|
record newly delivered input bytes, repeated reads/provider calls, human
|
|
@@ -43,19 +43,17 @@ and a snippet of at most 1,800 UTF-8 bytes around the first matching line.
|
|
|
43
43
|
Snippets include source line numbers and whether they are partial. Large files
|
|
44
44
|
are never described as searched or ranked. Read those separately when needed.
|
|
45
45
|
|
|
46
|
-
Every selected candidate is retained, including a zero-scored file
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
`batches` records candidate IDs, returned model, usage and elapsed time for each
|
|
56
|
-
successful call. `omitted`, `unreadable`, and `unranked` explain files that were
|
|
57
|
-
not scored. Hashes bind the result to the bytes read, not future edits. Open the
|
|
46
|
+
Every selected candidate is retained, including a zero-scored file; there is no
|
|
47
|
+
candidate cap or score cutoff. A keyword search can miss paraphrases or
|
|
48
|
+
dependencies; this result never claims exhaustive context. Refine and follow
|
|
49
|
+
relevant links.
|
|
50
|
+
|
|
51
|
+
The JSON `references` come in local-search order: local score, then path.
|
|
52
|
+
`status` is `local-search-only`, and `unranked` lists each candidate with the
|
|
53
|
+
reason `scoring-disabled`. `omitted` and `unreadable` explain files that were
|
|
54
|
+
not read. Hashes bind the result to the bytes read, not future edits. Open the
|
|
58
55
|
current source before relying on it; a bounded snippet is not the full file.
|
|
56
|
+
Invalid inputs or an unavailable Git inventory exit nonzero.
|
|
59
57
|
|
|
60
58
|
For an unclear state, data, or responsibility boundary, use the result as a
|
|
61
59
|
starting point and inspect the actual coupled sources as well: the owner and its
|
|
@@ -63,28 +61,7 @@ callers, readers, writers, or persistence boundary as applicable. Add discovered
|
|
|
63
61
|
paths to the brief/spec verification inputs before dispatch, and state any
|
|
64
62
|
unresolved coverage. Read `architecture.md` for focused examples. This expands
|
|
65
63
|
source discovery only when the seam matters; it does not make the context map a
|
|
66
|
-
second source of product decisions or a
|
|
67
|
-
|
|
68
|
-
Live scoring is the default. `.joycraft/hooks-config.json` supplies
|
|
69
|
-
`enabled`, `timeoutMs`, and Keychain service `JEV_API_KEY`; `--keychain-service` overrides it. The
|
|
70
|
-
shared `.joycraft/runtime/hooks/judge.mjs` primitive uses an existing
|
|
71
|
-
environment credential first, then the configured macOS Keychain service.
|
|
72
|
-
Credentials are never saved in the config, command arguments, result or project.
|
|
73
|
-
No dotenv file, transcript, or whole-project model dump is used.
|
|
74
|
-
The shared redactor removes recognizable credential patterns from outgoing
|
|
75
|
-
query/snippet strings before the Jev call; content hashes still identify the
|
|
76
|
-
original local bytes. Pattern redaction cannot identify arbitrary secret text.
|
|
77
|
-
Setting `enabled: false` selects explicit `local-search-only` output without
|
|
78
|
-
credential lookup; each candidate is marked unranked with `scoring-disabled`.
|
|
79
|
-
|
|
80
|
-
Missing credentials, malformed provider output or an outage stop further model
|
|
81
|
-
calls for that invocation. All selected references remain available in local
|
|
82
|
-
order where unranked; previously successful scores retain their provenance.
|
|
83
|
-
`status: incomplete-provider-ranking`, `provenance: local-search-fallback` and
|
|
84
|
-
`fallbackReason` make this explicit. Exit success means a usable result exists,
|
|
85
|
-
not that every candidate was scored; inspect `status` and `scoredCount`.
|
|
86
|
-
Invalid inputs or an unavailable Git inventory exit nonzero. Provider scores
|
|
87
|
-
advise reading order and never approve intent, authorize work or certify evidence.
|
|
64
|
+
second source of product decisions or a prohibition.
|
|
88
65
|
|
|
89
66
|
Treat only the context homes as current authority. `docs/features/` is working
|
|
90
67
|
material that can be stale until its feature is archived, and `docs/archive/` is
|