projectstore-claude 0.30.11 → 0.30.13

package/node_modules/projectstore/.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "name": "projectstore",
       "displayName": "projectstore",
       "description": "📚 Your agent runs the project through a verified loop: task → artifact (ADR · spec · epic · story) → adversarial critic → backlog → planner → reviewer → done. Plain markdown in an Obsidian-friendly vault, every write approved by you — and any model can pick the project up tomorrow.",
-      "version": "0.30.11",
+      "version": "0.30.13",
       "author": {
         "name": "Evgenii Konev",
         "email": "ekonev@smartandpoint.com",

package/node_modules/projectstore/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "projectstore",
   "displayName": "projectstore",
-  "version": "0.30.11",
+  "version": "0.30.13",
   "description": "Your agent runs the project through a verified loop: task → artifact (ADR / spec / epic / story) → adversarial critic → backlog → planner → reviewer → done. Plain markdown in git — any model can pick the project up tomorrow.",
   "author": {
     "name": "Evgenii Konev @ SmartAndPoint",

package/node_modules/projectstore/agents/planner.md

@@ -85,8 +85,17 @@ generic best practice — cite the real files and patterns you found.
 8. **Proposed `code_refs`** — the paths/globs this epic (and story) will own once
    implemented, ready for `/projectstore:codemap set`. You PROPOSE; the command
    writes after approval.
+9. **Open questions** — at most five decisions the user must make that the
+   code and the vault cannot answer, the one that changes the plan most
+   first. One per line:
+   `Q<n>. <the question> Options: (a) … (b) … Recommend (b): <why>`, with two to four options. The
+   recommendation is one of the options, so it can be recorded as the answer
+   when the user skips the question. "None" is the normal case. With more than
+   five, return five, say how many you left out, and say the story is
+   probably too big: suggest how to split it. You ask the user nothing; the
+   plan step puts these to the user in one round.
 
 Rules: be concrete and cite real paths / symbols; if the task is ambiguous or has
-two plausible homes, say so and recommend one with the tradeoff. No code
+two plausible homes, say so in Open questions (item 9) and recommend one with the tradeoff. No code
 generation beyond tiny illustrative snippets. You are read-only — never write
 code or vault files.

package/node_modules/projectstore/agents/reviewer.md

@@ -46,6 +46,17 @@ that is a 🔴 finding: the story is covered by a spec, new or existing, and
 `no_spec` is removed before it closes. There is no way to silence this.
 Otherwise check that the reason still matches what the diff did.
 
+**An Independent test line.** A story may carry one optional line under
+Description, `**Independent test:**` (translated as Unabhängiger Test, Prueba
+independiente, Test indépendant, Независимая проверка or 独立测试; in any
+locale, the bold line right under the Description comment): one sentence on how the story is checked on its own. It is filled when
+text follows the label outside the comment. When it is filled, the matrix gets
+one line for it: `— evidence:` with the command run and what was seen, or
+`not run — <why>` (it needs a host, a network, a release or a person: name
+which). With neither, that is a 🟡 should-fix, never a 🔴: the line is a hint,
+not a gate, and it never holds a story open. With no line, or only its
+placeholder, say nothing about it.
+
 ## Phase 0 — Pre-commitment
 From the story + file list, predict the 3-5 most likely gaps ("AC #3 needs an
 error path the diff doesn't touch"; "touches a cache — invalidation risk"). Write
@@ -97,7 +108,9 @@ say so plainly.
    Format each evidence value so it can be persisted verbatim into the story
    file at close: `— evidence: <test | command | file:line>` (a test may be
    named by its contract token, `[example#3]`, which doctor checks) — the close gate
-   (`/projectstore:story close`) copies your matrix into the checkboxes.
+   (`/projectstore:story close`) copies your matrix into the checkboxes. A
+   filled Independent test line gets its own line here, so the close can copy
+   it into the Final Summary's tests executed.
 3. **Findings** — severity-rated: `🔴 blocker` / `🟡 should-fix` / `🟢 nit`; each
    with file:line, confidence, why it matters, and a specific fix.
 4. **Proposed `code_refs`** — computed, not recalled: run

package/node_modules/projectstore/commands/story.md

@@ -50,6 +50,13 @@ the two cannot collide).
    line with `variant: test` before the preview, the way `--spec` fills
    `specs:`. The critic then reviews the story against `story.test`.
 
+3b. **The Independent test line** (optional, under Description; its label is
+   translated in each locale). When the conversation already says how this
+   story is checked on its own (a command to run and what to see), write
+   that sentence in place of the line's comment. Otherwise leave the
+   placeholder as it is and invent nothing: it is a hint, not a gate. Quote
+   the line in the preview.
+
 4. **Preview**: path + first ~25 lines.
 
 5. **Approval** via AskUserQuestion: Yes / Edit / No.
@@ -58,8 +65,9 @@ the two cannot collide).
 
 6. **Post-approval race re-check** (Layer 1): re-run `draft.mjs story <epic-id> "<title>"` (the same stripped arguments as step 3) and re-read its `collision` field — an exact-name `test -e` cannot see normalized cross-era collisions (`story-006-foo.md` vs `story-foo.md`). If `collision` is non-null, surface it as a topic collision (`"<identity>" already exists as <with>`), and ask: extend the existing story, pick a different slug (`-2` is a deliberate distinct identity), or cancel. Render `warnings` entries as `⚠️` lines in the preview too.
 
-7. **On Yes** (path free): Write the file you previewed, with the step-2 and
-   step-3a edits (`specs:`, `variant: test`), not the re-run's raw draft.
+7. **On Yes** (path free): Write the file you previewed, with the step-2,
+   step-3a and step-3b edits (`specs:`, `variant: test`, the Independent test
+   line), not the re-run's raw draft.
 
 8. **Suggest next**: "Now decompose the work in the `Decomposition` section, or run `/projectstore:kanban` to refresh the board. Before implementation: `/projectstore:story plan <story>`."
 
@@ -92,15 +100,39 @@ the two cannot collide).
    `plan_updated_at` / `closed_at` — stamped unconditionally; the
    `lifecycle_gates` key gates checks, never data).
 
+2a. **(plan only) Open questions, one round.** Before writing the plan,
+   collect the open questions: the planner's "Open questions" when it ran,
+   else your own; do not start the planner here. Keep only decisions the
+   user must make; skip what the conversation, or an earlier
+   `### Clarifications` in this plan, already settled. None is the normal
+   case: then ask nothing and write nothing. Keep at most five, the one that
+   changes the plan most first; with more, keep five, say how many were
+   dropped, and suggest splitting the story; when the planner says it left questions out, say so in the same round, with its split suggestion. Each question has two to four
+   options and one recommended option. Put them to the user in one round:
+   one call of AskUserQuestion for up to four questions; with five, or where
+   the harness has no question tool, one plain-text message with the
+   questions numbered. Ask once per gate run: the Edit in step 4 and the
+   re-check in step 5 never ask again. A skipped question, or every question
+   of a dismissed call, takes its recommendation, marked `(assumed)`. Record
+   the round under `### Clarifications`, last in the plan: a line with
+   today's date, then one bullet per question with its answer; a later plan
+   run appends its own dated line to the same subsection. An answer that changes a
+   contract of the covering spec says which one, and the spec is amended
+   the way it records its other amendments before the code is written.
+
 3. **Fill the section content** in the returned `content` before preview:
    - `plan` — write the Implementation Plan. When the story's `specs:` names a
      covering spec, the plan is a THIN ROUTE through that spec's behavioral
      contracts: which contracts, in what order, which files. Consult the
-     planner agent's output if one ran. Do not restate the spec.
+     planner agent's output if one ran. Do not restate the spec. End the plan
+     with the step 2a round, when there was one.
    - `close` — write the Final Summary (what changed / why / tests executed /
      risks & follow-ups), and update the Acceptance Criteria checkboxes with
      evidence suffixes: `- [x] <criterion> — evidence: <test | command | file:line>`.
      Check a box ONLY with real evidence (reviewer output, test run, command).
+     When the story's Independent test line is filled, in the Final Summary's
+     tests executed, say whether the Independent test ran and how (the command
+     and what was seen), or why not; the story closes either way.
 
 4. **Preview** path + notes + the changed sections. **Approval** via
    AskUserQuestion: Yes / Edit / No.

package/node_modules/projectstore/docs/contracts-and-tests.md

@@ -104,6 +104,23 @@ the ones a production vault hits.
 The story has `variant: test` in its frontmatter and follows every other
 story rule: the plan and close gates, evidence, the board.
 
+## A story with no spec: the Independent test line
+
+Most stories have no covering spec, so no scenario tells them how they are
+checked. The story template has one optional line under Description for
+that: one sentence on how the story is checked on its own, a command to run
+and what to see.
+
+```markdown
+**Independent test:** run `npm test` with a fixture vault whose index has a
+stale row, and see doctor report the folder.
+```
+
+It is a hint, not a gate. `/projectstore:story` fills it only when the
+conversation already says how; otherwise the placeholder stays, or you delete
+it. When the line is filled, the reviewer reports whether that test ran, and
+the close reports it in the Final Summary. Doctor never reads it.
+
 ## A contract no test can cover
 
 Some contracts are checked on a real host after install, or by a person.

package/node_modules/projectstore/package.json

@@ -1,6 +1,6 @@
 {
   "name": "projectstore",
-  "version": "0.30.11",
+  "version": "0.30.13",
   "description": "Your agent runs the project through a verified loop: task → artifact (ADR / spec / epic / story) → adversarial critic → backlog → planner → reviewer → done. Plain markdown in git — any model can pick the project up tomorrow.",
   "keywords": [
     "project-management",

package/node_modules/projectstore/templates/de/story.md.tmpl

@@ -34,6 +34,8 @@ plan_updated_at: null
 
 <!-- Welches Problem löst diese Story? Wer ist der Nutzer? -->
 
+**Unabhängiger Test:** <!-- Optional. Ein Satz dazu, wie diese Story für sich geprüft wird: ein Kommando und was man sieht. Lösche die Zeile, wenn es keinen gibt. -->
+
 ## Zerlegung
 
 <!-- Granulare Checkliste konkreter Aufgaben. Jeder Punkt klein genug für eine Sitzung. -->

package/node_modules/projectstore/templates/en/story.md.tmpl

@@ -34,6 +34,8 @@ plan_updated_at: null
 
 <!-- What problem does this story solve? Who is the user? -->
 
+**Independent test:** <!-- Optional. One sentence on how this story is checked on its own: a command to run and what to see. Delete the line if there is none. -->
+
 ## Decomposition
 
 <!-- Granular checklist of concrete tasks. Each item should be small enough to complete in a session. -->

package/node_modules/projectstore/templates/es/story.md.tmpl

@@ -34,6 +34,8 @@ plan_updated_at: null
 
 <!-- ¿Qué problema resuelve esta historia? ¿Quién es el usuario? -->
 
+**Prueba independiente:** <!-- Opcional. Una frase sobre cómo se comprueba esta historia por sí sola: un comando y lo que se ve. Borra la línea si no hay ninguna. -->
+
 ## Descomposición
 
 <!-- Checklist granular de tareas concretas. Cada punto, lo bastante pequeño para cerrarlo en una sesión. -->

package/node_modules/projectstore/templates/fr/story.md.tmpl

@@ -34,6 +34,8 @@ plan_updated_at: null
 
 <!-- Quel problème cette story résout-elle ? Qui est l'utilisateur ? -->
 
+**Test indépendant :** <!-- Facultatif. Une phrase sur la façon de vérifier cette story seule : une commande à lancer et ce qu'on voit. Supprime la ligne s'il n'y en a pas. -->
+
 ## Décomposition
 
 <!-- Checklist granulaire de tâches concrètes. Chaque point assez petit pour tenir dans une session. -->

package/node_modules/projectstore/templates/ru/story.md.tmpl

@@ -34,6 +34,8 @@ plan_updated_at: null
 
 <!-- Какую проблему решает эта история? Кто пользователь? -->
 
+**Независимая проверка:** <!-- Необязательно. Одно предложение о том, как проверить эту стори отдельно: какую команду запустить и что увидеть. Удали строку, если такой проверки нет. -->
+
 ## Декомпозиция
 
 <!-- Гранулярный чеклист конкретных задач. Каждый пункт — достаточно мал, чтобы закрыть за одну сессию. -->

package/node_modules/projectstore/templates/zh/story.md.tmpl

@@ -34,6 +34,8 @@ plan_updated_at: null
 
 <!-- 这个 story 解决什么问题？用户是谁？ -->
 
+**独立测试：** <!-- 可选。一句话说明如何单独验证这个 story：运行什么命令、看到什么结果。没有就删掉这一行。 -->
+
 ## 任务分解
 
 <!-- 具体任务的细颗粒清单。每一条都小到能在一次会话内做完。 -->

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "projectstore-claude",
-  "version": "0.30.11",
+  "version": "0.30.13",
   "description": "projectstore for Claude Code: the core pinned and bundled, the harness fixed. A release artifact; the way in is npx projectstore setup",
   "keywords": [
     "projectstore",
@@ -37,7 +37,7 @@
     "README.md"
   ],
   "dependencies": {
-    "projectstore": "=0.30.11"
+    "projectstore": "=0.30.13"
   },
   "bundleDependencies": [
     "projectstore"