Bulk Task Completion

batch-complete — Bulk Complete or Cancel Items

Close out a feature subtree, cancel an abandoned workstream, or clean up stale items in one operation. Handles gate checks, active-item warnings, and reports exactly what succeeded and what was skipped.

Step 1 — Identify Scope

Resolve $ARGUMENTS to a UUID via query_items search (operation="search", query=$ARGUMENTS, limit=5); if ambiguous, present matches via AskUserQuestion.

If $ARGUMENTS is empty, classify the request from conversation context:

• Feature subtree: user mentions completing "everything under" a named item → search for that item, use rootId
• Specific items: user lists names or IDs → collect each UUID, use itemIds
• Cleanup: user wants to clear old/stale items → search by status or title fragment, collect UUIDs, use itemIds

If scope still cannot be determined, ask via AskUserQuestion: "Which item (or items) do you want to complete? Provide a root UUID, a title fragment, or a list of item IDs."

Step 2 — Preview Impact

Before executing, show the user what will happen. Call:

query_items(operation="overview", itemId="<rootId>")

Parse the child counts by role and present a preview table. Use the trigger chosen (or likely to be chosen) to set the action label — trigger="complete" shows "will be completed"; trigger="cancel" shows "will be cancelled":

◆ Impact Preview — "Auth System Feature"  [trigger: complete]
  ○ queue:    3 items (will be completed)
  ◉ work:     1 item  (active — will be force-completed)
  ◉ review:   1 item  (active — will be force-completed)
  ✓ terminal: 2 items (already done — will be skipped)

◆ Impact Preview — "Auth System Feature"  [trigger: cancel]
  ○ queue:    3 items (will be cancelled)
  ◉ work:     1 item  (active — will be force-cancelled)
  ◉ review:   1 item  (active — will be force-cancelled)
  ✓ terminal: 2 items (already done — will be skipped)

For itemIds path (no root item): call query_items(operation="get", itemId="<uuid>") on each item and build the same role-grouped preview table from the individual results. For large lists (10+ items), use query_items(operation="search") with filters instead of individual get calls.

If any items are in work or review, warn the user that active work will be force-completed (gate checks still apply). Use AskUserQuestion with three options:

◆ 2 items are currently active (work or review).
  How would you like to proceed?
  1. Proceed — complete everything including active items
  2. Cancel active items instead — use trigger="cancel" (bypasses gates)
  3. Abort — leave everything as-is

Wait for the user's choice before continuing. Record whether to use trigger="complete" or trigger="cancel".

Step 3 — Gate Check

Skip this step if trigger="cancel" was already chosen in Step 2 — cancel bypasses all gates, so gate checking is unnecessary.

For trigger="complete", gate previewing is best-effort. complete_tree performs the definitive gate check during execution and reports any failures in its response. A lightweight pre-check is still useful to surface issues before committing — call get_context on each child from Step 2's results rather than on the root item (the root itself is not completed by complete_tree, only its descendants are):

get_context(itemId="<child-uuid>")   ← repeat for each child listed in Step 2

If any child's gate status shows missing required notes, display them:

⊘ Gate Warnings (preview — definitive check runs at execution):
  "Implement login" — missing: implementation-notes (work, required)
  "Write tests" — missing: session-tracking (work, required)

Then offer three options via AskUserQuestion:

◆ Some items have unfilled required notes and will be skipped by the gate.
  What would you like to do?
  1. Fill notes first — use manage_notes(operation="upsert") to fill each item's required notes, then return here
  2. Use cancel trigger — bypasses all gates, marks items as "cancelled"
  3. Proceed anyway — gated items will be skipped, others will complete

Call get_context(itemId=...) to retrieve guidanceKey for items with missing notes, then resolve its text via query_items(operation="schema", itemId=...). Use the guidance as authoring instructions before filling.

Wait for the user's choice. If they choose option 2, switch to trigger="cancel" for the execution step.

If complete_tree reports gate failures in Step 4, fill the missing notes and rerun complete_tree — items already in terminal are silently skipped on subsequent runs.

Step 4 — Execute

Call complete_tree with the chosen trigger:

Feature subtree (rootId):

complete_tree(rootId="<uuid>", trigger="complete")

Specific items (itemIds):

complete_tree(itemIds=["<uuid-1>", "<uuid-2>", "<uuid-3>"], trigger="complete")

Cancel variant (bypasses gates):

complete_tree(rootId="<uuid>", trigger="cancel")

Parse the response and present results:

✓ Batch Complete — "Auth System Feature"
  ✓ Design API schema — completed
  ✓ Set up database — completed
  ⊘ Implement login — skipped (gate: missing implementation-notes)
  ✓ Write unit tests — completed
  — Integration tests — skipped (dependency on "Implement login")

  Summary: 3/5 completed | 1 gate failure | 1 dependency skip

Use these symbols:

• ✓ — applied: true (completed or cancelled)
• ⊘ — gate failure (gateErrors present)
• — — skipped due to dependency on a failed item

Step 5 — Cleanup (Optional)

If the user wants to delete the completed items after finishing (to fully archive a workstream), confirm via AskUserQuestion:

◆ Delete all items under "Auth System Feature" after completing?
  This cannot be undone.
  1. Yes, delete them
  2. No, keep them in terminal state

If confirmed, delete with:

manage_items(operation="delete", itemIds=["<root-uuid>"], recursive=true)

Report what was deleted:

✓ Deleted: "Auth System Feature" and all 5 descendants