ultimate-pi 0.11.0 → 0.12.0

package/.pi/extensions/review-integrity.ts

@@ -1,9 +1,8 @@
 /**
  * review-integrity — enforce evaluator/adversary isolation from executor session.
  *
- * Parent orchestrators spawn review agents in isolated subagent sessions.
- * Direct review tools in the executor session are blocked; Agent/get_subagent_result
- * for harness review agents remain allowed.
+ * Parent orchestrators spawn review agents in isolated subprocesses via `subagent`.
+ * Direct review tools in the executor session are blocked.
  */
 
 import { appendFile, mkdir } from "node:fs/promises";
@@ -15,12 +14,6 @@ type HarnessPhase = "plan" | "execute" | "evaluate" | "adversary" | "merge";
 const INCIDENTS_DIR = join(process.cwd(), ".pi", "harness", "incidents");
 const INCIDENT_FILE = join(INCIDENTS_DIR, "review-integrity.jsonl");
 
-const ORCHESTRATION_TOOLS = new Set([
-	"Agent",
-	"get_subagent_result",
-	"steer_subagent",
-]);
-
 const REVIEW_SUBAGENT_TYPES = new Set([
 	"harness/evaluator",
 	"harness/adversary",
@@ -104,15 +97,45 @@ function restoreState(ctx: {
 	};
 }
 
-function subagentTypeFromInput(
+function agentsFromSubagentInput(
 	input: Record<string, unknown> | undefined,
-): string {
-	if (!input) return "";
-	const direct = input.subagent_type;
-	if (typeof direct === "string") return direct;
-	const nested = input as { subagentType?: string };
-	if (typeof nested.subagentType === "string") return nested.subagentType;
-	return "";
+): string[] {
+	if (!input) return [];
+	const names: string[] = [];
+	if (typeof input.agent === "string") names.push(input.agent);
+	const tasks = input.tasks;
+	if (Array.isArray(tasks)) {
+		for (const t of tasks) {
+			if (
+				t &&
+				typeof t === "object" &&
+				typeof (t as { agent?: string }).agent === "string"
+			) {
+				names.push((t as { agent: string }).agent);
+			}
+		}
+	}
+	const chain = input.chain;
+	if (Array.isArray(chain)) {
+		for (const c of chain) {
+			if (
+				c &&
+				typeof c === "object" &&
+				typeof (c as { agent?: string }).agent === "string"
+			) {
+				names.push((c as { agent: string }).agent);
+			}
+		}
+	}
+	const agg = input.aggregator;
+	if (
+		agg &&
+		typeof agg === "object" &&
+		typeof (agg as { agent?: string }).agent === "string"
+	) {
+		names.push((agg as { agent: string }).agent);
+	}
+	return names;
 }
 
 async function appendIncident(payload: Record<string, unknown>): Promise<void> {
@@ -178,26 +201,26 @@ export default function reviewIntegrity(pi: ExtensionAPI) {
 				customType: "harness-review-integrity-hint",
 				display: true,
 				content: [
-					"Review phase in executor session: spawn harness/evaluator or harness/adversary via Agent (isolated subagent context).",
-					"Do not run review checks directly in this session — use get_subagent_result after spawn.",
+					"Review phase in executor session: spawn harness/evaluator or harness/adversary via subagent (isolated subprocess).",
+					"Do not run review checks directly in this session.",
 				].join("\n"),
 			},
 		};
 	});
 
 	pi.on("tool_call", async (event, ctx) => {
-		if (event.toolName === "Agent") {
-			const subagentType = subagentTypeFromInput(
+		if (event.toolName === "subagent") {
+			const agents = agentsFromSubagentInput(
 				event.input as Record<string, unknown> | undefined,
 			);
-			if (subagentType === EXECUTOR_SUBAGENT_TYPE) {
+			if (agents.includes(EXECUTOR_SUBAGENT_TYPE)) {
 				state.executorSessionId = ctx.sessionManager.getSessionId();
 				state.violationActive = false;
 				state.updatedAt = nowIso();
 				persist();
 				return undefined;
 			}
-			if (REVIEW_SUBAGENT_TYPES.has(subagentType)) {
+			if (agents.some((a) => REVIEW_SUBAGENT_TYPES.has(a))) {
 				state.violationActive = false;
 				state.updatedAt = nowIso();
 				persist();
@@ -207,10 +230,6 @@ export default function reviewIntegrity(pi: ExtensionAPI) {
 
 		if (!state.violationActive) return undefined;
 
-		if (ORCHESTRATION_TOOLS.has(event.toolName)) {
-			return undefined;
-		}
-
 		await appendIncident({
 			type: "review_integrity_violation",
 			session_id: ctx.sessionManager.getSessionId(),
@@ -218,13 +237,13 @@ export default function reviewIntegrity(pi: ExtensionAPI) {
 			reason:
 				"direct tool use in review phase while sharing executor session context",
 			mitigation:
-				"spawn harness/evaluator or harness/adversary via Agent instead",
+				"spawn harness/evaluator or harness/adversary via subagent instead",
 		});
 
 		return {
 			block: true,
 			reason:
-				"review-integrity: tool blocked in review phase — spawn an isolated review subagent via Agent.",
+				"review-integrity: tool blocked in review phase — spawn an isolated review subagent via subagent.",
 		};
 	});
 

package/.pi/harness/agents.manifest.json

@@ -1,8 +1,8 @@
 {
 	"schema_version": "1.0.0",
 	"package": "ultimate-pi",
-	"package_version": "0.10.1",
-	"generated_at": "2026-05-17T17:48:22.826Z",
+	"package_version": "0.11.0",
+	"generated_at": "2026-05-18T09:43:44.563Z",
 	"agents": {
 		"pi-pi/agent-expert": {
 			"path": ".pi/agents/pi-pi/agent-expert.md",
@@ -46,27 +46,23 @@
 		},
 		"harness/adversary": {
 			"path": ".pi/agents/harness/adversary.md",
-			"sha256": "b965f90610ca942d08b656f1aee839266d08a92beb174b8761dd5e840694a899"
+			"sha256": "dd2ef87139cb175d795f4d7bde78dca1a181d2e42c3c3bd0d48832cf5069aa29"
 		},
 		"harness/evaluator": {
 			"path": ".pi/agents/harness/evaluator.md",
-			"sha256": "6c0de777a10de26dba4a6feb5641495fa5c2d31072a8b0e597a5ecc9921f129f"
+			"sha256": "2b8039fd79f9177fdafd5319a53a96812719d4f1f68e2de70632030142649cfe"
 		},
 		"harness/executor": {
 			"path": ".pi/agents/harness/executor.md",
-			"sha256": "5af3ec2be4d64a738834e36d480a36c2bee4359e8cd5a2e1aac49be4cff79589"
+			"sha256": "b549e9fc802ba23857a1bc6b2ff36f3c169e708fe5ec13857b3bcfe841384f1f"
 		},
 		"harness/incident-recorder": {
 			"path": ".pi/agents/harness/incident-recorder.md",
-			"sha256": "2de405f77b62dde38f331665bff220a3ef131c3c1cd42eebee364000fc83352b"
+			"sha256": "d7577c911a9e6c9607eb64f76337aab85c4eb9a92e7cd917eb8d989ef3cd1de5"
 		},
 		"harness/meta-optimizer": {
 			"path": ".pi/agents/harness/meta-optimizer.md",
-			"sha256": "ef2fb950e18e3a6439e91a68f764fc7ec922cd2d6b35de8f656f376854974d04"
-		},
-		"harness/planner": {
-			"path": ".pi/agents/harness/planner.md",
-			"sha256": "648b9e4c56a6c0f983ae990238952579bb4745af81eb6c79add5325ea4929c91"
+			"sha256": "a4eed88084c7cfb5ace3edc72b72d7ead4134b3eae0d444b391decfe2640a632"
 		},
 		"harness/sentrux-bootstrap": {
 			"path": ".pi/agents/harness/sentrux-bootstrap.md",
@@ -74,43 +70,59 @@
 		},
 		"harness/tie-breaker": {
 			"path": ".pi/agents/harness/tie-breaker.md",
-			"sha256": "651f50b9e2c7903c542700e94908b1fcd026ebed12aa1f1d6ec481df3567e34f"
+			"sha256": "68f02b86e95927f06d7f963e1f61f193159bbef1ba4558d90c84d5457d62b3f7"
 		},
 		"harness/trace-librarian": {
 			"path": ".pi/agents/harness/trace-librarian.md",
-			"sha256": "d63fe08a2ea0466c0fd89fff4da03ac1d9d3580c306381cee251c89d4e8fdb97"
+			"sha256": "03b499a948b8467f1cfe2b4e63190feb7b8b9d96461055638e774253b9b6b2d4"
 		},
 		"harness/planning/decompose": {
 			"path": ".pi/agents/harness/planning/decompose.md",
-			"sha256": "a4f33869759ebdc049e77b344ae050be5ede08ea9a92216b8599cc7d2f14c052"
+			"sha256": "1b3f85d956d2e203ec87045a731c47f8b40f75b63fce8916fda91cefc39244a8"
+		},
+		"harness/planning/execution-plan-author": {
+			"path": ".pi/agents/harness/planning/execution-plan-author.md",
+			"sha256": "a69fb2e8bda9336e71ce9536071f9c8a2f4abd9d9d88930c6a8be29bdc9c5f62"
 		},
-		"harness/planning/hypothesis-eval": {
-			"path": ".pi/agents/harness/planning/hypothesis-eval.md",
-			"sha256": "7a05e2f746bf79f20096cbfb12aaee31a0717e660680b44cb285ea967b3141e5"
+		"harness/planning/hypothesis-validator": {
+			"path": ".pi/agents/harness/planning/hypothesis-validator.md",
+			"sha256": "f75312439c441ccee72692d41f44b6e733df08e06c89e930740fc256bed3ba02"
 		},
 		"harness/planning/hypothesis": {
 			"path": ".pi/agents/harness/planning/hypothesis.md",
-			"sha256": "7f2af6dda328d6cc1279dbff20a46b1d93aacfda9d57857cc6117685f8a585dd"
+			"sha256": "b20c527d15c2243cd5d3a8f16cea6d44bdfd16e01915d42f3b830bf9938e5f8b"
 		},
 		"harness/planning/plan-adversary": {
 			"path": ".pi/agents/harness/planning/plan-adversary.md",
-			"sha256": "4beceb8c4181f82b7eb006d87392c0adb4c7ce41992193790888e7298c1b7594"
+			"sha256": "685926c638ae1377361d7cafda5e400be19cb3880510d8f6d389a5876647575f"
+		},
+		"harness/planning/plan-evaluator": {
+			"path": ".pi/agents/harness/planning/plan-evaluator.md",
+			"sha256": "44fd52389d7e43dd5093653cba9694900561318ee5f00e3bc05c3ecef5d43621"
 		},
-		"harness/planning/planner": {
-			"path": ".pi/agents/harness/planning/planner.md",
-			"sha256": "570c501c976e26d79a36814787eb03fab6aa97f79cc895af319dc717648a2a65"
+		"harness/planning/review-integrator": {
+			"path": ".pi/agents/harness/planning/review-integrator.md",
+			"sha256": "d0e8214539d0a78b9e5add70e61dd4e4de36def64172cda18d9b70727e7600ca"
 		},
 		"harness/planning/scout-graphify": {
 			"path": ".pi/agents/harness/planning/scout-graphify.md",
-			"sha256": "76a66a3dc8bce60a91ed30ffdc683fb1eab0692006b0ee80fbdc67b11b374b61"
+			"sha256": "b59916a26afccfe105e29c0bd8637ac54275e8afef1c6cc88a58bd05b0325473"
 		},
 		"harness/planning/scout-semantic": {
 			"path": ".pi/agents/harness/planning/scout-semantic.md",
-			"sha256": "99aedca25fd81000d3bb532e0191ce9e1a87b84ab4039f089734f3a0d24ba44b"
+			"sha256": "47b7ea3e65b20a65e6d0ff11b6d5daff59b47a9ed618b8a3b6282f2eb0460572"
 		},
 		"harness/planning/scout-structure": {
 			"path": ".pi/agents/harness/planning/scout-structure.md",
-			"sha256": "83fd09e5eccd77b27d9de464d7e32536d9a762469e021b86b0ca665942bb40af"
+			"sha256": "e67b7cd75519e5ae36e1bb5f49ca158888c28d365465863aee50a9b2e8e5b7d7"
+		},
+		"harness/planning/sprint-contract-auditor": {
+			"path": ".pi/agents/harness/planning/sprint-contract-auditor.md",
+			"sha256": "f613a4fa937d76936fa01155d4e7956a81878f300100f99f6a78915b0af6f7c7"
+		},
+		"harness/planning/stack-researcher": {
+			"path": ".pi/agents/harness/planning/stack-researcher.md",
+			"sha256": "90e2ff1348f54bebc8c0392407bf1bb4d794c942fd8d6f342d80b191c945b34e"
 		}
 	}
 }

package/.pi/harness/docs/adrs/0032-harness-command-orchestration.md

@@ -5,14 +5,14 @@
 
 ## Context
 
-Harness slash prompts duplicated logic already defined in `harness/*` agents. Commands did not invoke the `Agent` tool. Review docs told users to fork a new Pi session even though subagents already provide isolated context.
+Harness slash prompts duplicated logic already defined in `harness/*` agents. The in-process `Agent` / `createAgentSession` stack was heavy and unstable. Review docs told users to fork a new Pi session even though subprocess subagents already provide isolation.
 
 ## Decision
 
 1. **Slash commands** (prompt templates) are orchestrators: spawn `harness/*` agents once, perform policy-gated writes, emit handoff blocks. Command identity is captured on Pi **`input`** as `harness-turn` (raw `/harness-*`), not from expanded prompt markdown.
 2. **Agents** perform multi-turn reads and emit structured JSON drafts. **Planning** (`harness/planning/*`) scouts and plan-adversary are read-only; parent orchestrator runs `ask_user`, `approve_plan`, and `create_plan` (see ADR 0033).
 3. **HarnessSpawnContext** is injected in `[HarnessRunContext]`; orchestrator copies it into spawn prompts. Subagents do not receive `[HarnessActivePlan]` injection.
-4. **Review isolation** uses `Agent` spawn with `inherit_context: false`. `review-integrity` allows `Agent` / `get_subagent_result` for evaluator/adversary/tie-breaker.
+4. **Review isolation** uses native `subagent` (vendored pi-subagents: isolated `pi --mode json` subprocess). `review-integrity` allows `subagent` when `agent` is evaluator/adversary/tie-breaker; bridge blocks plan-phase mutating spawns and nested `subagent` in children.
 5. **Subagent policy** blocks mutating tools for read-only phase agents; `ask_user` bridged for evaluator/adversary/tie-breaker only (not planning scouts).
 6. **Parent** owns plan-phase `ask_user`, `approve_plan`, and `create_plan` per ADR 0033.
 
@@ -32,6 +32,7 @@ Harness slash prompts duplicated logic already defined in `harness/*` agents. Co
 
 - `.pi/prompts/harness-*.md`
 - `.pi/agents/harness/*.md`
-- `.pi/extensions/lib/harness-subagents/harness-subagent-policy.ts`
+- `vendor/pi-subagents/src/subagents.ts`, `.pi/extensions/lib/harness-subagents-bridge.ts`
+- `.pi/extensions/lib/harness-subagent-policy.ts`
 - `.pi/extensions/review-integrity.ts`
 - `.pi/lib/harness-agent-output.ts`

package/.pi/harness/docs/adrs/0033-parent-orchestrated-planning.md

@@ -5,7 +5,7 @@
 
 ## Context
 
-`/harness-plan` delegated the full plan lifecycle to a single `harness/planner` subagent. Plans and approval UI were largely invisible in the parent transcript until `get_subagent_result`, and the orchestrator could not call `ask_user` / `approve_plan` / `create_plan` directly.
+`/harness-plan` previously delegated the full plan lifecycle to a single `harness/planner` subagent. Plans and approval UI were largely invisible in the parent transcript until subprocess completion, and the orchestrator could not call `ask_user` / `approve_plan` / `create_plan` directly.
 
 ## Decision
 

package/.pi/harness/docs/adrs/0035-plan-phase-review-gate.md

@@ -0,0 +1,27 @@
+# ADR-0035: Plan-phase Review Gate and YAML artifacts
+
+## Status
+
+Accepted (2026-05-18)
+
+## Context
+
+`/harness-plan` produced thin PlanPackets (scope + bullets). Post-execute adversarial review (`/harness-critic`) ran too late. Graphify corpus (Structured Planning, ADR-020, Generator–Evaluator) defines WBS, validation, and review gate before baseline.
+
+## Decision
+
+1. **PlanPacket 1.1.0** — required `execution_plan` (phases, work_items, sprint_contract, dag_validation).
+2. **YAML on disk** — `plan-packet.yaml`, `research-brief.yaml`, `run-context.yaml`, `artifacts/*.yaml`. JSON Schema unchanged; instances validated after YAML parse.
+3. **Review Gate agents** — `stack-researcher`, `execution-plan-author`, debate: `hypothesis-validator`, `plan-evaluator`, `plan-adversary`, `sprint-contract-auditor`, `review-integrator`.
+4. **Debate bus** — `debate_id=plan-<run_id>`, plan budget profile (4 rounds, 12k cap), plan-phase consensus prerequisites.
+5. **No legacy JSON** plan paths; no pre-debate standalone `hypothesis-eval`.
+
+## Consequences
+
+- Positive: PM-grade plans, deterministic DAG gate, blind hypothesis eval in debate R1.
+- Negative: Higher spawn/token cost; `harness-verify` and smoke fixtures must use `.yaml`.
+
+## References
+
+- [ADR-0033](0033-parent-orchestrated-planning.md), [ADR-0034](0034-darwin-plan-research-pipeline.md)
+- `raw/decisions/adr-020.md`, `raw/modules/structured-planning.md`

package/.pi/harness/evals/smoke/fixtures/plan-phase/minimal-med/artifacts/review-round-r1.yaml

@@ -0,0 +1,25 @@
+schema_version: "1.0.0"
+round_index: 1
+debate_round_focus: spec
+round_summary: Spec round passed for fixture
+validation_summary: All spec checks pass
+adversary_summary: No blocking adversarial findings
+disputes: []
+recommended_packet_patches: []
+review_gate_ready: true
+participants:
+  - PlanEvaluatorAgent
+  - PlanAdversaryAgent
+  - HypothesisValidatorAgent
+  - ReviewIntegratorAgent
+claims:
+  - spec validation complete
+rebuttals: []
+evidence_refs: []
+token_usage:
+  per_agent:
+    PlanEvaluatorAgent: 100
+    PlanAdversaryAgent: 100
+    ReviewIntegratorAgent: 50
+  round_total: 250
+consensus_delta: 0.1

package/.pi/harness/evals/smoke/fixtures/plan-phase/minimal-med/artifacts/review-round-r4.yaml

@@ -0,0 +1,26 @@
+schema_version: "1.0.0"
+round_index: 4
+debate_round_focus: quality
+round_summary: Quality and sprint contract round passed
+validation_summary: Sprint contract complete
+adversary_summary: No gaps
+disputes: []
+recommended_packet_patches: []
+review_gate_ready: true
+participants:
+  - PlanEvaluatorAgent
+  - PlanAdversaryAgent
+  - SprintContractAuditorAgent
+  - ReviewIntegratorAgent
+claims:
+  - review gate ready
+rebuttals: []
+evidence_refs: []
+token_usage:
+  per_agent:
+    PlanEvaluatorAgent: 120
+    PlanAdversaryAgent: 110
+    SprintContractAuditorAgent: 90
+    ReviewIntegratorAgent: 60
+  round_total: 380
+consensus_delta: 0.15

package/.pi/harness/evals/smoke/fixtures/plan-phase/minimal-med/artifacts/sprint-audit-r4.yaml

@@ -0,0 +1,5 @@
+schema_version: "1.0.0"
+round_index: 4
+gaps: []
+recommendation: proceed
+human_summary: Sprint contract satisfies ADR-020 for fixture

package/.pi/harness/evals/smoke/fixtures/plan-phase/minimal-med/plan-packet.yaml

@@ -0,0 +1,196 @@
+schema_version: "1.0.0"
+contract_version: "1.1.0"
+plan_id: plan-smoke-fixture-001
+task_id: task-smoke-001
+scope: Smoke fixture for plan-phase harness validation with execution_plan and debate artifacts.
+assumptions:
+  - Fixture only; no live agent run
+risk_level: med
+acceptance_checks:
+  - id: AC-1
+    description: DAG validation passes
+  - id: AC-2
+    description: Four debate rounds recorded
+  - id: AC-3
+    description: Stack brief present in research-brief
+  - id: AC-4
+    description: Sprint contract complete
+  - id: AC-5
+    description: plan-review.md renders
+rollback_plan:
+  revert_commit_ready: true
+  rollback_artifacts:
+    revert_command: git revert HEAD
+    revert_branch: main
+    patch_bundle: .pi/harness/runs/smoke-fixture/patch.bundle
+execution_plan:
+  schema_version: "1.0.0"
+  phases:
+    - phase_id: P1
+      name: Foundation
+      objective: Establish baseline and verify harness wiring
+      entry_criteria:
+        - Fixture loaded
+      exit_criteria:
+        - AC-1 satisfied
+      milestone: M1-baseline
+      work_item_ids: [WI-1, WI-2, WI-3]
+    - phase_id: P2
+      name: Build
+      objective: Implement core changes
+      entry_criteria:
+        - M1-baseline complete
+      exit_criteria:
+        - AC-2 satisfied
+      milestone: M2-build
+      work_item_ids: [WI-4, WI-5, WI-6]
+    - phase_id: P3
+      name: Verify
+      objective: Quality gate and documentation
+      entry_criteria:
+        - M2-build complete
+      exit_criteria:
+        - AC-5 satisfied
+      milestone: M3-ship
+      work_item_ids: [WI-7, WI-8]
+  work_items:
+    - work_item_id: WI-1
+      phase_id: P1
+      title: Load fixture packet
+      description: Read plan-packet.yaml from fixture directory
+      depends_on: []
+      files:
+        - .pi/harness/evals/smoke/fixtures/plan-phase/minimal-med/plan-packet.yaml
+      parallel_safe: true
+      done_criteria:
+        type: manual
+        spec: Fixture packet readable
+      acceptance_check_ids: [AC-1]
+    - work_item_id: WI-2
+      phase_id: P1
+      title: Run DAG validator
+      description: Execute validate-plan-dag.mjs
+      depends_on: [WI-1]
+      files:
+        - .pi/scripts/validate-plan-dag.mjs
+      parallel_safe: false
+      done_criteria:
+        type: command
+        spec: node .pi/scripts/validate-plan-dag.mjs --packet plan-packet.yaml
+      acceptance_check_ids: [AC-1]
+    - work_item_id: WI-3
+      phase_id: P1
+      title: Lint harness-yaml
+      description: Ensure YAML helpers parse fixture
+      depends_on: [WI-1]
+      files:
+        - .pi/lib/harness-yaml.ts
+      parallel_safe: true
+      done_criteria:
+        type: lint
+        spec: npm test
+      acceptance_check_ids: [AC-1]
+    - work_item_id: WI-4
+      phase_id: P2
+      title: Debate round 1-2 artifacts
+      description: Validate review-round YAML
+      depends_on: [WI-2]
+      files:
+        - .pi/harness/evals/smoke/fixtures/plan-phase/minimal-med/artifacts/review-round-r1.yaml
+      parallel_safe: false
+      done_criteria:
+        type: artifact
+        spec: artifacts/review-round-r1.yaml exists
+      acceptance_check_ids: [AC-2]
+    - work_item_id: WI-5
+      phase_id: P2
+      title: Debate round 3-4 artifacts
+      description: Validate final review round
+      depends_on: [WI-4]
+      files:
+        - .pi/harness/evals/smoke/fixtures/plan-phase/minimal-med/artifacts/review-round-r4.yaml
+      parallel_safe: false
+      done_criteria:
+        type: artifact
+        spec: artifacts/review-round-r4.yaml exists
+      acceptance_check_ids: [AC-2]
+    - work_item_id: WI-6
+      phase_id: P2
+      title: Stack research merge
+      description: research-brief includes stack section
+      depends_on: [WI-2]
+      files: []
+      non_code: true
+      parallel_safe: true
+      done_criteria:
+        type: manual
+        spec: research-brief.yaml contains stack key
+      acceptance_check_ids: [AC-3]
+    - work_item_id: WI-7
+      phase_id: P3
+      title: Sprint contract audit
+      description: R4 sprint audit artifact
+      depends_on: [WI-5]
+      files:
+        - .pi/harness/evals/smoke/fixtures/plan-phase/minimal-med/artifacts/sprint-audit-r4.yaml
+      parallel_safe: false
+      done_criteria:
+        type: artifact
+        spec: sprint-audit-r4.yaml present
+      acceptance_check_ids: [AC-4]
+    - work_item_id: WI-8
+      phase_id: P3
+      title: Render plan-review
+      description: Human-readable plan review markdown
+      depends_on: [WI-7]
+      files:
+        - .pi/harness/evals/smoke/fixtures/plan-phase/minimal-med/plan-review.md
+      parallel_safe: false
+      done_criteria:
+        type: manual
+        spec: plan-review.md non-empty
+      acceptance_check_ids: [AC-5]
+  sprint_contract:
+    in_scope:
+      - Fixture validation only
+    out_of_scope:
+      - Production deploy
+    definition_of_done: All smoke checks green
+    assumptions:
+      - CI environment has node
+    external_dependencies: []
+  wbs_dictionary:
+    - work_item_id: WI-1
+      deliverable: Fixture packet loaded
+      owner_role: executor
+      inputs: []
+      outputs: [parsed packet]
+  risk_register:
+    - risk_id: R1
+      description: DAG validator false negative
+      likelihood: low
+      impact: high
+      mitigation: Unit tests on validate-plan-dag.mjs
+      linked_work_item_ids: [WI-2]
+    - risk_id: R2
+      description: Debate cap misconfiguration
+      likelihood: med
+      impact: med
+      mitigation: debate-orchestrator plan profile tests
+      linked_work_item_ids: [WI-4]
+    - risk_id: R3
+      description: YAML parse drift
+      likelihood: low
+      impact: med
+      mitigation: harness-yaml strict parse
+      linked_work_item_ids: [WI-3]
+  schedule_metadata:
+    critical_path_work_item_ids: [WI-1, WI-2, WI-4, WI-5, WI-7, WI-8]
+    parallel_groups:
+      - [WI-1, WI-3]
+    schedule_baseline_note: Fixture topological order; no calendar dates
+  dag_validation:
+    status: pass
+    topological_order: [WI-1, WI-2, WI-3, WI-4, WI-5, WI-6, WI-7, WI-8]
+    cycles: []
+    conflicts: []

package/.pi/harness/evals/smoke/fixtures/plan-phase/minimal-med/plan-review.md

@@ -0,0 +1,14 @@
+# Plan review (fixture)
+
+plan_id: plan-smoke-fixture-001
+
+## Execution plan
+
+Phases: P1 Foundation → P2 Build → P3 Verify
+
+Critical path: WI-1 → WI-2 → WI-4 → WI-5 → WI-7 → WI-8
+
+## Debate
+
+- Round 1 (spec): review_gate_ready
+- Round 4 (quality): review_gate_ready

package/.pi/harness/evals/smoke/fixtures/plan-phase/minimal-med/research-brief.yaml

@@ -0,0 +1,32 @@
+decomposition:
+  schema_version: "1.0.0"
+  problem_restatement: Validate plan-phase YAML and debate pipeline
+hypothesis:
+  schema_version: "1.0.0"
+  primary:
+    claim: Fixture-driven smoke covers DAG and debate
+    mechanism: Static artifacts plus validate-plan-dag.mjs
+    prediction: CI passes without live agents
+    experiment: Run smoke-harness-plan.mjs --fixture
+stack:
+  schema_version: "1.0.0"
+  problem_framing: Node harness tooling
+  constraints: []
+  options:
+    - name: extend current stack
+      category: brownfield
+      fit_summary: Use existing ultimate-pi harness
+      tradeoffs:
+        pros: [No new deps]
+        cons: []
+      risks: []
+      evidence_refs: []
+      recommendation_rank: 1
+  recommended_primary: extend current stack
+  rationale: Fixture validates in-repo harness
+eval:
+  schema_version: "1.0.0"
+  revision_recommended: false
+  relevance:
+    passes: true
+    rationale: Hypothesis matches smoke task

package/.pi/harness/evals/smoke/run-context.fixture.json

@@ -5,7 +5,7 @@
 	"project_root": "/tmp/ultimate-pi-smoke",
 	"phase": "plan",
 	"plan_id": null,
-	"plan_packet_path": "/tmp/ultimate-pi-smoke/.pi/harness/runs/smoke-session-1/plan-packet.json",
+	"plan_packet_path": "/tmp/ultimate-pi-smoke/.pi/harness/runs/smoke-session-1/plan-packet.yaml",
 	"plan_ready": false,
 	"task_summary": "smoke task",
 	"status": "active",