@dtlabs/ai-toolkit 0.16.0 → 0.16.2

package/CHANGELOG.md

@@ -1,4 +1,20 @@
 ## 0.1.4 (2026-07-21)
+## [0.16.2](https://github.com/dtlab-tech/ai-toolkit/compare/v0.16.1...v0.16.2) (2026-10-02)
+
+
+### Bug Fixes
+
+* **gaia-generate-work-breakdown:** forbid citing an AC outside its owning phase ([525e2ce](https://github.com/dtlab-tech/ai-toolkit/commit/525e2cef928dafb8b80470b572d214b85aecb1dc))
+* **gaia-generate-work-breakdown:** forbid citing an AC outside its owning phase ([5376d67](https://github.com/dtlab-tech/ai-toolkit/commit/5376d67a67140d5b46e507f2092e389d362ce723))
+
+## [0.16.1](https://github.com/dtlab-tech/ai-toolkit/compare/v0.16.0...v0.16.1) (2026-10-02)
+
+
+### Bug Fixes
+
+* **wb-validate:** require groupingRationale only when outputCount > 1 ([e3cb71a](https://github.com/dtlab-tech/ai-toolkit/commit/e3cb71a7f38fbd974c70f3dbdd99223a6aa05048))
+* **wb-validate:** require groupingRationale only when outputCount > 1 ([7406fbe](https://github.com/dtlab-tech/ai-toolkit/commit/7406fbe336304c2ebcd012fc6a6b1b4980121a64))
+
 ## [0.16.0](https://github.com/dtlab-tech/ai-toolkit/compare/v0.15.1...v0.16.0) (2026-10-02)
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dtlabs/ai-toolkit",
-  "version": "0.16.0",
+  "version": "0.16.2",
   "description": "AI Toolkit — reusable agents and procedures for developers to build AI-powered applications.",
   "files": [
     "docs/",

package/src/claude/agents/gaia-generate-work-breakdown.md

@@ -128,7 +128,7 @@ Decomposition strategy by domain:
 | `domain` | string | One of: `BE`, `FE`, `DB`, `DevOps`, `INFRA`, `TEST` |
 | `agentType` | string | One of: `developer-backend`, `developer-frontend`, `developer-testing`, `review-solution` (deprecated: `developer-database` — maps to `developer-backend`) |
 | `dependsOn` | array of strings | Task IDs this task depends on; may be empty `[]`; all IDs must be defined within this same JSON |
-| `acceptanceCriteria` | array of strings | AC IDs from Requirements that this task covers; may be empty `[]` |
+| `acceptanceCriteria` | array of strings | AC IDs from Requirements scoped to this task's own phase that this task covers; may be empty `[]`. Never an AC owned by a different phase (see Guidelines) |
 | `verification` | object | `{ "commands": ["..."] }` — one or more shell commands that verify the task output; array must be non-empty |
 | `estimate` | object | `{ "agentMinutes": N, "tokens": N }` — target ≤ 15 minutes; positive integers |
 | `outputCount` | integer | Number of distinct outputs; must be ≥ 1 |
@@ -339,7 +339,7 @@ Do NOT guess or invent task decompositions when the source is unclear. Ask first
 - **Cross-phase dependencies are expected** — US tasks may depend on INFRA tasks; cross-US task dependencies are also valid
 - **INFRA phase first** (if present), then US phases in priority order (Must before Should before Could)
 - **Within a phase, order tasks by layer dependency** (DB → BE → FE → TEST); independent tasks within the same layer may be listed in any order
-- **acceptanceCriteria** must list AC IDs from the Requirements that this task covers; leave empty `[]` if the task covers no AC directly (e.g., pure infrastructure setup)
+- **acceptanceCriteria** must list only AC IDs whose Requirements AC-table scope ("Related UC") matches this task's own phase, or that are marked cross-cutting ("All UCs"/multiple UCs including this phase's). **Never cite an AC owned by a different phase on this task, even when this task is prerequisite or contributing work for it** — an INFRA task that lays groundwork for an AC verified in a later US does not "cover" that AC; leave `acceptanceCriteria` empty `[]` on that task instead (e.g., pure infrastructure setup, or groundwork for an AC owned elsewhere). If an AC is genuinely cross-cutting, reflect that in the AC's own "Related UC" column, not by citing it from an unrelated task.
 - **schemaVersion must be exactly 2** — do not omit it, do not use any other value
 - **No pipes, CR, or LF** in `phase.title`, `task.title`, or `commit.subject` — these characters break CSV generation
-- **Traceability**: every UC must map to a US phase; every Must-priority AC must be covered by at least one task's `acceptanceCriteria`
+- **Traceability**: every UC must map to a US phase; every Must-priority AC must be covered by at least one task's `acceptanceCriteria` **within that AC's own owning US phase** (per its "Related UC" scope) — not by a task in an earlier or later phase, even one that contributes toward satisfying it eventually

package/src/claude/scripts/wb-validate.js

@@ -359,7 +359,7 @@ for (const phase of phases) {
 
     const topLevelFields = [
       'id', 'title', 'outcome', 'domain', 'agentType', 'dependsOn',
-      'acceptanceCriteria', 'outputCount', 'groupingRationale', 'commit',
+      'acceptanceCriteria', 'outputCount', 'commit',
     ]
     for (const field of topLevelFields) {
       if (task[field] == null) {
@@ -374,6 +374,20 @@ for (const phase of phases) {
       }
     }
 
+    // groupingRationale is required only when outputCount > 1 (the generator agent's own
+    // contract: a single-output task has nothing to justify grouping, so it emits null) —
+    // null is the documented, correct value there, not a missing field.
+    if (task.outputCount > 1 && task.groupingRationale == null) {
+      report.errors.push({
+        category: ERRORS.MISSING_FIELD,
+        severity: 'error',
+        taskId,
+        field: 'groupingRationale',
+        message: `Task "${taskId}" has outputCount > 1 but is missing required field "groupingRationale"`,
+        details: { taskId, field: 'groupingRationale' },
+      })
+    }
+
     // Nested: verification.commands — existence and array type only; emptiness checked later
     if (task.verification == null || task.verification.commands == null) {
       report.errors.push({