@dtlabs/ai-toolkit 0.6.0 → 0.7.0

package/.claude/agents/developer-testing.md

@@ -78,7 +78,7 @@ Follow all conventions EXACTLY.
 4. **Create test project/file** if it doesn't exist (following project conventions)
 5. **Write test helpers** (custom factories, builders, mocks) if needed
 6. **Implement tests** following AAA pattern
-7. **Verify** by running the test command from AGENTS.md
+7. **Syntax check only (optional)** — you MAY run a build to confirm the test files compile (e.g. `dotnet build`, `npx tsc --noEmit`). **Do NOT run the test suite** (`dotnet test`, `npm test`, etc.) — the orchestrator runs the full suite once, after all agents finish. Running it here duplicates a multi-minute build per agent and contends for build artifacts.
 
 ---
 
@@ -102,13 +102,13 @@ When all assigned tasks are complete, return a **structured summary** to the orc
 Tasks completed: [list]
 Files created:   [list with path only]
 Files modified:  [list with path only]
-Test result:     ✅ N/N passed / ❌ N failed — [failing test names if any]
+Build check:     ✅ compiles / ❌ compile error — [first error line if any] / ⏭️ not run
 Notes:           [blocking issues, skipped cases, TODO items]
 ─────────────────────────────────────────────
 ```
 
 - **Never dump test code** into the summary
-- If tests FAILED, include only the failing test names and first error line
+- Do NOT report test-run results — you do not run the suite; the orchestrator runs it once after all agents finish. Report only whether the test files compile.
 
 ---
 
@@ -119,4 +119,4 @@ Notes:           [blocking issues, skipped cases, TODO items]
 - **No testing of trivial code** — getters/setters, data classes, config files
 - **Mock external dependencies** — databases, HTTP clients, file systems
 - **Use the project's preferred mocking approach** — as defined in AGENTS.md
-- **After implementation**: run the test command to verify all tests pass
+- **Do NOT run the test suite** — the orchestrator runs the full suite once, after every agent has finished writing its files. A build for a quick syntax check is fine; running the tests here wastes minutes on a duplicate build and can lock build artifacts.

package/.claude/workflows/pm-phase3.js

@@ -4,6 +4,7 @@ export const meta = {
   phases: [
     { title: 'Parse',          detail: 'Parse Work Breakdown into structured implementation phases' },
     { title: 'Implementation', detail: 'Dispatch developer agents per US, review, commit' },
+    { title: 'Test',           detail: 'Single test run after all phases complete' },
     { title: 'Remediation',    detail: 'Fix OPEN issues from Issues Register' },
     { title: 'PR',             detail: 'Push branch, create PR, update registry' },
     { title: 'Actuals',        detail: 'Write Token-Estimate and Effort-Estimate actuals' },
@@ -237,6 +238,16 @@ const executePhase = async (implPhase) => {
   }
 
   phasesDone++
+
+  // Persist the cumulative token ledger to disk after every completed phase.
+  // budget.spent() is an in-memory counter — if the workflow is stopped (manual
+  // stop, crash, timeout) before the Actuals phase, all token data would be lost.
+  // Writing the full ledger here means the file always reflects real consumption
+  // up to the last completed phase, recoverable manually or by a resumed run.
+  await agent(
+    `Write the following JSON to ${featureDir}/${prefix}-token-ledger.json (overwrite the file if it exists):\n${JSON.stringify(tokenLedger, null, 2)}`,
+    { label: `persist-ledger:${implPhase.phase_id}`, phase: 'Implementation', model: 'haiku' }
+  )
 }
 
 // Execute waves: phases in the same wave run in parallel, waves are sequential
@@ -267,6 +278,28 @@ issuesPath = issuesResult?.path || ''
 issuesOpen = issuesResult?.open_count || 0
 log(`Implementation complete — ${phasesDone} phases, ${usPassed.length} US passed, ${usEscalated.length} escalated, ${issuesOpen} open issues`)
 
+// ── Final test run ────────────────────────────────────────────────────────────
+// Developer agents no longer run the test suite themselves (they do a syntax-check
+// build at most). Running the suite once here, after all files are written, replaces
+// N parallel per-agent test runs — cutting ~1h of duplicated builds and artifact
+// contention down to a single centralized run with one consolidated failure report.
+phase('Test')
+
+const beforeTest = budget.spent()
+await agent(
+  `Run the full test suite in the repository root and report the result.
+
+1. Read AGENTS.md in the repository root to find the exact test command for this project.
+2. Run that command (e.g. \`dotnet test --no-restore --logger "console;verbosity=normal"\`, \`npm test\`).
+3. Report the outcome: total passed/failed, and for any failures the test name and first error line.
+
+Do NOT fix failing tests — only report them.`,
+  { label: 'final-test-run', phase: 'Test', model: 'haiku' }
+)
+const testTokens = budget.spent() - beforeTest
+tokenLedger.push({ agent: 'final-test-run', model: 'haiku', phase_delta_tokens: testTokens })
+log(`Test run complete — ${testTokens} tokens`)
+
 // ── Remediation ───────────────────────────────────────────────────────────────
 phase('Remediation')
 
@@ -381,6 +414,30 @@ log(`PR done: ${prResult.pr_url} — ${prTokens} tokens`)
 // ── Actuals ───────────────────────────────────────────────────────────────────
 phase('Actuals')
 
+// Fallback: merge in any ledger entries that were persisted to disk but are missing
+// from the in-memory ledger (e.g. this is a resumed run and earlier phases ran in a
+// previous, interrupted invocation). The in-memory ledger has priority for entries
+// present in both — it reflects the most recent measurements.
+const persistedLedgerRaw = await agent(
+  `Read ${featureDir}/${prefix}-token-ledger.json and return its contents as a raw JSON string, nothing else. If the file does not exist, return exactly "[]".`,
+  { label: 'read-ledger', phase: 'Actuals', model: 'haiku' }
+)
+try {
+  const persisted = JSON.parse(typeof persistedLedgerRaw === 'string' ? persistedLedgerRaw.trim() : '[]')
+  if (Array.isArray(persisted)) {
+    const seen = new Set(tokenLedger.map(e => e.agent))
+    for (const entry of persisted) {
+      if (entry && entry.agent && !seen.has(entry.agent)) {
+        tokenLedger.push(entry)
+        seen.add(entry.agent)
+        log(`Recovered ledger entry from disk: ${entry.agent} (${entry.phase_delta_tokens} tokens)`)
+      }
+    }
+  }
+} catch (e) {
+  log(`Could not parse persisted token ledger — using in-memory ledger only`)
+}
+
 const totalPhase3Tokens = tokenLedger.reduce((s, e) => s + (e.phase_delta_tokens || 0), 0)
 
 const ACTUALS_SCHEMA = {

package/CHANGELOG.md

@@ -1,4 +1,13 @@
 ## 0.1.4 (2026-07-21)
+## [0.7.0](https://github.com/dtlab-tech/ai-toolkit/compare/v0.6.0...v0.7.0) (2026-07-29)
+
+
+### Features
+
+* **pipeline:** centralized test run + persistent token ledger + validation report fix + smarter define-feature ([c9fad6e](https://github.com/dtlab-tech/ai-toolkit/commit/c9fad6e4e5dfe25823df1d6534b4e597baa97001))
+* **pm-phase3:** add centralized test run phase to streamline testing process ([972fac5](https://github.com/dtlab-tech/ai-toolkit/commit/972fac55d0754743859a7d75379a41acd49a890d))
+* **pm-phase3:** persist token ledger to disk after every phase ([b6ad681](https://github.com/dtlab-tech/ai-toolkit/commit/b6ad6814770fae31cda60f25298dab9b2739eeaa))
+
 ## [0.6.0](https://github.com/dtlab-tech/ai-toolkit/compare/v0.5.0...v0.6.0) (2026-07-29)
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dtlabs/ai-toolkit",
-  "version": "0.6.0",
+  "version": "0.7.0",
   "description": "AI Toolkit — reusable agents and procedures for developers to build AI-powered applications.",
   "files": [
     "docs/",