specweave 3.1.0 → 3.1.2

package/plugins/specweave/hooks/run.mjs

@@ -31,6 +31,17 @@ function hasActiveAutoSession(data) {
   }
   return false;
 }
+// `specweave task done`/`skip` writes ~/.specweave/close-pending/<session>.json
+// when an increment's last task turns terminal; Stop then reminds that session
+// once to verify and close it. Only that session spawns the worker: every
+// other stop stays on the fast path.
+function hasClosePendingFor(data) {
+  const session = typeof data.session_id === 'string' ? data.session_id : '';
+  if (!/^[A-Za-z0-9._-]{1,128}$/.test(session) || session === '.' || session === '..') return false;
+  if (data.stop_hook_active === true) return false;
+  try { return existsSync(path.join(homedir(), '.specweave', 'close-pending', `${session}.json`)); }
+  catch { return false; }
+}
 // PreToolUse fast path. Ordinary edits and ordinary shell commands must not
 // spawn a worker, resolve npm or import the CLI. Write|Edit only matter inside
 // `.specweave/increments/`; Bash only matters when the project opted into the
@@ -100,7 +111,7 @@ process.stdin.on('end',()=>{
   catch {return finish({},'invalid_input');}
   if(!['session-start','pre-tool-use','pre-compact','stop'].includes(event))return finish({});
   if(process.env.SPECWEAVE_DISABLE_HOOKS === '1')return finish({});
-  if(event === 'stop' && !hasActiveAutoSession(data))return finish({});
+  if(event === 'stop' && !hasActiveAutoSession(data) && !hasClosePendingFor(data))return finish({});
   if(event === 'pre-tool-use' && skipPreToolUse(data))return finish({});
   const env={...process.env};
   child=spawn(process.execPath,[worker,event],{env,detached:process.platform !== 'win32',stdio:['pipe','pipe','pipe']});

package/plugins/specweave/skills/do/SKILL.md

@@ -72,8 +72,15 @@ merge and close; do not implement.
 
 ## Finish without asking
 
-When `task next` has nothing left, run sw-done: verify, review, complete.
-"All tasks are done, should I close?" is the anti-pattern.
+When `task next` has nothing left, run sw-done: verify, review, complete, in the same
+session. "All tasks are done, should I close?" is the anti-pattern.
+
+Plan for it from the start: a progress checklist or status you keep for the user ends
+with "Verify and close 0042", not with "merge" or "release". Work that shipped through
+a PR still gets `specweave task done T-03 --evidence "<commit sha>"` first, or the ledger
+never shows it finished. A session never ends with every task done and the increment
+still open; if a close gate stops you (verify fails, a manual check only the user can
+do), say which one in your report. A lane agent leaves the close to its lead.
 
 ## Stopping early
 

package/plugins/specweave/skills/handoff/SKILL.md

@@ -52,7 +52,8 @@ or a `Waits on: ...` line in the increment's `handoff.md`; a `wait` with the not
 
 On the other side, "pick up all" is `specweave pickup --all`: the newest index,
 actionable increments first, then the ones waiting on a person. Start each topic with
-its resume prompt, then `specweave pickup <id>`.
+its resume prompt, then `specweave pickup <id>` and sw-do, which closes each one
+whose tasks all end up done.
 
 ## Your hand-written handoff is kept
 
@@ -93,7 +94,8 @@ account", run `specweave pickup`. It fetches the last handoff, moves this branch
 forward to it and applies the handed-off edits (only on a clean tree), then prints the
 increment, the next task with its acceptance criteria and any notes. If it reports
 uncommitted changes or a diverged branch, do what it says; never discard the user's
-edits. Then continue with sw-do.
+edits. Then continue with sw-do, which closes the increment through sw-done once its
+last task is done.
 
 Several sessions can hand off in one project (each increment's handoff, and a session
 that hit the limit in a worktree or with several increments active). `specweave handoff
@@ -130,4 +132,5 @@ git push -u origin HEAD
 ```
 
 To pick up by hand: `git fetch origin`, check out that branch, read its `handoff.md`,
-and continue at the first task in spec.md with no `done` line in the ledger.
+and continue at the first task in spec.md with no `done` line in the ledger. When none
+is left, close it as sw-done says.

package/plugins/specweave/skills/increment/SKILL.md

@@ -108,3 +108,7 @@ Files that change and in what order, decisions, rejected alternatives, risks.
 
 Show the ACs and tasks. Unless the user asked to review the plan first, carry on with
 sw-do (one agent, or parallel lanes for three or more disjoint groups of tasks).
+Opening an increment makes closing it part of the same job: any plan or checklist you
+show ends with "Verify and close 0042", and sw-do closes it through sw-done once the last
+task is done. When the plan waits for the user's review, say the increment stays open
+until they answer.

package/src/templates/AGENTS.md.template

@@ -8,12 +8,12 @@ This project uses SpecWeave. Plan increments in `.specweave/increments/NNNN-slug
 ## The loop
 
 1. `specweave pickup`: applies the latest handoff and prints the open increment, next task and ACs, other claims, branch state, notes and project memory.
-2. New work needing ACs or handoff: `specweave create-increment "title"`, then fill spec.md. First ask the user only their critical decisions, one at a time with a recommended answer, and record them under `## Decisions` (sw-increment). If an open increment owns the files, add ACs and tasks there. Small fixes need no increment.
+2. New work needing ACs or handoff: `specweave create-increment "title"`, then fill spec.md. First ask the user only their critical decisions, one at a time with a recommended answer, and record them under `## Decisions` (sw-increment). If an open increment owns the files, add ACs and tasks there. Small fixes need no increment. Close what you open: its plan ends with "Verify and close NNNN".
 3. `specweave task claim T-NN`, edit only that task's Files, commit as `NNNN: what changed`, then `specweave task done T-NN --run "<its Test>"`.
-4. `specweave verify`, a review in a fresh session for anything that ships, then `specweave complete NNNN`.
-5. Before stopping or switching tools/accounts: `specweave handoff --reason "<why>"`.
+4. When the last task is done or skipped, without asking: `specweave verify`, a fresh-context review (subagent or new session) for anything that ships, `specweave complete NNNN`. PR-shipped work needs `task done` first.
+5. Stopping with tasks left, or switching tools: `specweave handoff --reason "<why>"`.
 
-**Handoff.** When the user says "hand off", "out of tokens" or "switching accounts", or "[Usage limit reached" appears (outside SpecWithCode), run `specweave handoff --reason "<why>"`; tell them to say "pick up" in the other tool. "[Usage limit approaching" or usage heads-ups mean keep working; say so. When the user says "pick up", run `specweave pickup`; continue its task, passing any given id/title. Take the newest handoff if several; say which.
+**Handoff.** When the user says "hand off", "out of tokens" or "switching accounts", or "[Usage limit reached" appears (outside SpecWithCode), run `specweave handoff --reason "<why>"`; tell them to say "pick up" in the other tool. "[Usage limit approaching" or usage heads-ups mean keep working; say so. When the user says "pick up", run `specweave pickup`; continue through step 4, passing any given id/title. Take the newest handoff if several; say which.
 
 Tasks in spec.md: `### T-01 Title`, then `- AC: AC-01 | Files: src/a.ts, tests/e2e/a.test.ts | Test: npm test -- e2e/a`. An AC is met when its tasks are done. Leave notes with `specweave note "<text>"`. Skills: `.agents/skills/sw-*` and `.claude/skills/sw-*`; other tools: `npx vskill install anton-abyzov/specweave/sw-do`.
 <!-- /SECTION -->