ultimate-pi 0.15.0 → 0.17.0

package/.pi/extensions/lib/plan-debate-round-status.ts

@@ -7,12 +7,15 @@ import { access } from "node:fs/promises";
 import { join } from "node:path";
 import { capsForDebate } from "./debate-bus-core.js";
 import {
-	type PlanDebateFocus,
+	type PlanDebateRoundFocus,
 	readDebateRoundFocus,
 } from "./plan-debate-focus.js";
 import { planDebateIdForRun } from "./plan-debate-id.js";
 import { laneArtifactPath } from "./plan-debate-lane.js";
-import { lanesForRound } from "./plan-debate-lanes.js";
+import {
+	lanesForConsolidatedRound,
+	lanesForRound,
+} from "./plan-debate-lanes.js";
 import {
 	getMessengerRoundState,
 	loadMessengerState,
@@ -40,26 +43,32 @@ export interface RoundStatusResult {
 	dialogue: { ok: boolean; errors: string[] };
 	unresolved_claim_ids: string[];
 	exchange_count: number;
-	debate_round_focus?: PlanDebateFocus | null;
+	debate_round_focus?: PlanDebateRoundFocus | null;
 }
 
 export async function getPlanDebateRoundStatus(
 	runDir: string,
 	roundIndex: number,
 	runId?: string,
-	opts?: { debate_round_focus?: PlanDebateFocus },
+	opts?: { debate_round_focus?: PlanDebateRoundFocus },
 ): Promise<RoundStatusResult> {
+	const messengerState = await loadMessengerState(runDir);
+	const consolidated =
+		messengerState?.review_gate_mode === "consolidated" && roundIndex === 1;
 	const focus =
 		opts?.debate_round_focus ??
+		(consolidated ? ("all" as PlanDebateRoundFocus) : null) ??
 		(await readDebateRoundFocus(runDir, roundIndex));
 	const missing: string[] = [];
-	for (const lane of lanesForRound(roundIndex, focus)) {
+	const laneList = consolidated
+		? lanesForConsolidatedRound()
+		: lanesForRound(roundIndex, focus);
+	for (const lane of laneList) {
 		const rel = laneArtifactPath(lane, roundIndex);
 		if (!(await exists(join(runDir, rel)))) {
 			missing.push(rel);
 		}
 	}
-	const messengerState = await loadMessengerState(runDir);
 	const profile = messengerState?.debate_profile;
 	const caps = capsForDebate(
 		runId ? planDebateIdForRun(runId) : `plan-${runId ?? "unknown"}`,
@@ -73,7 +82,9 @@ export async function getPlanDebateRoundStatus(
 	if (!dialogue.ok) {
 		missing.push(...dialogue.errors.map((e) => `messenger: ${e}`));
 	}
-	const reviewRound = `artifacts/review-round-r${roundIndex}.yaml`;
+	const reviewRound = consolidated
+		? "artifacts/review-round-consolidated.yaml"
+		: `artifacts/review-round-r${roundIndex}.yaml`;
 	const reviewRoundOnDisk = await exists(join(runDir, reviewRound));
 
 	let next_tool: string | undefined;

package/.pi/extensions/lib/plan-messenger.ts

@@ -63,6 +63,8 @@ export interface MessengerState {
 	rounds: Record<string, MessengerRoundState>;
 	debate_profile?: DebateProfile;
 	required_focuses?: PlanDebateFocus[];
+	/** consolidated = single Review Gate round; threaded = per-focus rounds */
+	review_gate_mode?: "consolidated" | "threaded";
 }
 
 function messengerRoot(runDir: string): string {
@@ -84,6 +86,7 @@ export async function initPlanMessenger(
 		debateId: string;
 		debate_profile?: DebateProfile;
 		required_focuses?: PlanDebateFocus[];
+		review_gate_mode?: "consolidated" | "threaded";
 	},
 ): Promise<string> {
 	const root = messengerRoot(runDir);
@@ -97,6 +100,7 @@ export async function initPlanMessenger(
 		rounds: {},
 		debate_profile: opts.debate_profile,
 		required_focuses: opts.required_focuses,
+		review_gate_mode: opts.review_gate_mode,
 	};
 	await writeFile(
 		join(root, "state.json"),

package/.pi/extensions/lib/plan-review-gate.ts

@@ -0,0 +1,51 @@
+/**
+ * Consolidated vs threaded Review Gate strategy for plan-phase debate.
+ */
+
+import type {
+	DebateEligibilityResult,
+	PlanReviewGateStrategy,
+} from "./plan-debate-eligibility.js";
+import type { PlanDebateFocus } from "./plan-debate-focus.js";
+
+export type { PlanReviewGateStrategy };
+
+export const CONSOLIDATED_REVIEW_ROUND = 1;
+export const CONSOLIDATED_REVIEW_ARTIFACT =
+	"artifacts/review-round-consolidated.yaml";
+
+export function planReviewGateStrategyFromEligibility(
+	eligibility: DebateEligibilityResult,
+): PlanReviewGateStrategy {
+	return (
+		eligibility.review_gate_strategy ?? {
+			mode: eligibility.profile === "fast" ? "consolidated" : "threaded",
+			profile: eligibility.profile,
+			required_focuses: [...eligibility.required_focuses],
+			min_focus_rounds: eligibility.min_focus_rounds,
+			max_rounds: eligibility.max_rounds,
+			max_exchanges_per_round: eligibility.max_exchanges_per_round,
+			round_token_cap: eligibility.round_token_cap,
+			debate_global_cap: eligibility.debate_global_cap,
+			rationale: [...eligibility.rationale],
+		}
+	);
+}
+
+export function isConsolidatedReviewStrategy(
+	strategy: PlanReviewGateStrategy,
+): boolean {
+	return strategy.mode === "consolidated";
+}
+
+/** Focus areas covered in a single consolidated review round (spec + quality gate). */
+export const CONSOLIDATED_REVIEW_FOCUS_AREAS: readonly PlanDebateFocus[] = [
+	"spec",
+	"quality",
+];
+
+export function consolidatedReviewFocusesSatisfied(
+	covered: readonly string[],
+): boolean {
+	return CONSOLIDATED_REVIEW_FOCUS_AREAS.every((f) => covered.includes(f));
+}

package/.pi/extensions/trace-recorder.ts

@@ -235,6 +235,7 @@ export default function traceRecorder(pi: ExtensionAPI) {
 		if (shouldEmitStarted) {
 			captureHarnessEvent(sessionId, "harness_run_started", {
 				harness_run_id: runId,
+				run_id: runId,
 				harness_plan_id: activeRun.planId,
 				harness_phase: activeRun.phase,
 				pi_session_id: sessionId,

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

@@ -1,8 +1,8 @@
 {
 	"schema_version": "1.0.0",
 	"package": "ultimate-pi",
-	"package_version": "0.14.0",
-	"generated_at": "2026-05-19T10:53:28.359Z",
+	"package_version": "0.15.0",
+	"generated_at": "2026-05-19T12:56:13.369Z",
 	"agents": {
 		"pi-pi/agent-expert": {
 			"path": ".pi/agents/pi-pi/agent-expert.md",
@@ -46,23 +46,23 @@
 		},
 		"harness/adversary": {
 			"path": ".pi/agents/harness/adversary.md",
-			"sha256": "dd2ef87139cb175d795f4d7bde78dca1a181d2e42c3c3bd0d48832cf5069aa29"
+			"sha256": "560c7571ab91478bde1271e9ae6c3a112c3e1d28e1a261c5450fd1d00f9f89af"
 		},
 		"harness/evaluator": {
 			"path": ".pi/agents/harness/evaluator.md",
-			"sha256": "2b8039fd79f9177fdafd5319a53a96812719d4f1f68e2de70632030142649cfe"
+			"sha256": "a4667d3efb305ba2fe79118e3d7d2b0de5e0369637af040d1238161d75cd28ac"
 		},
 		"harness/executor": {
 			"path": ".pi/agents/harness/executor.md",
-			"sha256": "b549e9fc802ba23857a1bc6b2ff36f3c169e708fe5ec13857b3bcfe841384f1f"
+			"sha256": "6baffcc3d89954494ce3ae439175686a39928b6a543a0a451da27475094b1712"
 		},
 		"harness/incident-recorder": {
 			"path": ".pi/agents/harness/incident-recorder.md",
-			"sha256": "d7577c911a9e6c9607eb64f76337aab85c4eb9a92e7cd917eb8d989ef3cd1de5"
+			"sha256": "d42fa45de1a2fe3842d075c6f319315266588942e314f1b650caabac39bdc29a"
 		},
 		"harness/meta-optimizer": {
 			"path": ".pi/agents/harness/meta-optimizer.md",
-			"sha256": "a4eed88084c7cfb5ace3edc72b72d7ead4134b3eae0d444b391decfe2640a632"
+			"sha256": "cbaab35367126796b7136389a02ab41b4fd1fe7098cf83be562d7b7493ccc297"
 		},
 		"harness/sentrux-bootstrap": {
 			"path": ".pi/agents/harness/sentrux-bootstrap.md",
@@ -70,63 +70,63 @@
 		},
 		"harness/tie-breaker": {
 			"path": ".pi/agents/harness/tie-breaker.md",
-			"sha256": "68f02b86e95927f06d7f963e1f61f193159bbef1ba4558d90c84d5457d62b3f7"
+			"sha256": "1c54c1c3274291dea1ea8826563a7ad4fe1d9c4302984e907bfcd22cfc4f5eba"
 		},
 		"harness/trace-librarian": {
 			"path": ".pi/agents/harness/trace-librarian.md",
-			"sha256": "03b499a948b8467f1cfe2b4e63190feb7b8b9d96461055638e774253b9b6b2d4"
+			"sha256": "336b3f3f6141cef8750ab18d29bbe454caf26973830a86afe099d9e4ad8b0abe"
 		},
 		"harness/planning/decompose": {
 			"path": ".pi/agents/harness/planning/decompose.md",
-			"sha256": "5c3b983772d013741d50f39945bc77f178aa338aecab56b93c09216d72192c69"
+			"sha256": "0919dafa1d1cd008d513c28524c1e7218867586a138982dccf01db5270c42c73"
 		},
 		"harness/planning/execution-plan-author": {
 			"path": ".pi/agents/harness/planning/execution-plan-author.md",
-			"sha256": "16f8800c50bcaf1b82ed9138889c8a0e538ee6a139aeae129ccd20cec2ec25f7"
+			"sha256": "55ece0f1ee14abd17fe7b3e478b548240f637eacbfc2a34758e98d3878dc82fd"
 		},
 		"harness/planning/hypothesis-validator": {
 			"path": ".pi/agents/harness/planning/hypothesis-validator.md",
-			"sha256": "9e68ec5d6aef96a3666c30227c3cbddf1aaed1182fdc94dbbd21ad3d48315ff2"
+			"sha256": "36f0baa7796229f21bd02faf5e70402c7bf054289eab557a25bfbe3cb7781de7"
 		},
 		"harness/planning/hypothesis": {
 			"path": ".pi/agents/harness/planning/hypothesis.md",
-			"sha256": "b20c527d15c2243cd5d3a8f16cea6d44bdfd16e01915d42f3b830bf9938e5f8b"
+			"sha256": "e83d5c4faaee8d32af4a5f22c9917b70a173f3e22d7c0f182b361706f2309171"
 		},
 		"harness/planning/implementation-researcher": {
 			"path": ".pi/agents/harness/planning/implementation-researcher.md",
-			"sha256": "dbd1c4fc74d538b110d406febfd4603eebea77d82e8b367df4596ac7ff6e54cc"
+			"sha256": "653f320b5d51bb331774246687f24a75347b406bba4e6dfd2968d6e5d4cc8bb3"
 		},
 		"harness/planning/plan-adversary": {
 			"path": ".pi/agents/harness/planning/plan-adversary.md",
-			"sha256": "7c14eaab65f356003ee2ff380f5d4e620170b5126daa67c3d226b12342f47bd2"
+			"sha256": "3241d7ec939dc29e0af64690b99e9f74b209f40b0daa4a2a1f9ff86f99f94a8d"
 		},
 		"harness/planning/plan-evaluator": {
 			"path": ".pi/agents/harness/planning/plan-evaluator.md",
-			"sha256": "846575abe9df3e7e5be812c0c474989c1a9de8074a7884d77b9d3dd423643480"
+			"sha256": "71660ab58bfcfdfae56c873140d4ea5946ae30cd5719c96afeabfd02b1d1f81d"
 		},
 		"harness/planning/review-integrator": {
 			"path": ".pi/agents/harness/planning/review-integrator.md",
-			"sha256": "bed43f3f049c279ac50a24bcffac1bbe46a8605d89c9cc6d0c3c6a87d488b1b8"
+			"sha256": "cf3f0dbe81274ec9ef0ff2e0c170e8dc929b20be65492d0ee9a80d985acf6d71"
 		},
 		"harness/planning/scout-graphify": {
 			"path": ".pi/agents/harness/planning/scout-graphify.md",
-			"sha256": "7f385d5bda2fe04b9da52cb4cb9247324efd345579b483d3ad55a6abefad50d5"
+			"sha256": "6e2bda8ad38311810c9916d9dab311873bc776e4b8832bb0e574136e45e1255e"
 		},
 		"harness/planning/scout-semantic": {
 			"path": ".pi/agents/harness/planning/scout-semantic.md",
-			"sha256": "36bd424ebd422bda82bd447b22f591f99f32ec897ea43f385586119da5c26caa"
+			"sha256": "416e518d8204a55b26dc53da1f750865c6f09ee2c7f343b41e7c08da3230c089"
 		},
 		"harness/planning/scout-structure": {
 			"path": ".pi/agents/harness/planning/scout-structure.md",
-			"sha256": "e67b7cd75519e5ae36e1bb5f49ca158888c28d365465863aee50a9b2e8e5b7d7"
+			"sha256": "76c42a15cc74cf1de2cf861cb0146c865c205f69cce7b9605d41893b19600029"
 		},
 		"harness/planning/sprint-contract-auditor": {
 			"path": ".pi/agents/harness/planning/sprint-contract-auditor.md",
-			"sha256": "d915274dc9b5addae5499bc2390b348eddeb8f133b526a816e23d0d19a2618bf"
+			"sha256": "12cb5e6b53dcc19ace62e8e4c152d96440717df53a182e76216dd2327410df4d"
 		},
 		"harness/planning/stack-researcher": {
 			"path": ".pi/agents/harness/planning/stack-researcher.md",
-			"sha256": "fa228920abe2b66d4d8921c4a5d85593e3019a24bbe9ae512ed9149f235e3536"
+			"sha256": "ce546ef3aca19da7f334f07cef8f510b79068bffeb7f276c428f3e6236bbe96b"
 		}
 	}
 }

package/.pi/harness/docs/adrs/0037-subagent-submit-tools.md

@@ -0,0 +1,31 @@
+# ADR 0037: Subagent submit tools (replace JSON prose contracts)
+
+**Status:** Accepted  
+**Date:** 2026-05-19
+
+## Context
+
+Harness plan/execute agents used fenced JSON in `finalOutput`, requiring the parent orchestrator to parse prose and call `write_harness_yaml`. This was fragile (truncated parallel summaries, invalid JSON, double-hop writes).
+
+Planning agents set `extensions: false` and subprocess spawn used `--no-extensions`, so harness tools were unavailable in children.
+
+## Decision
+
+1. **Option A — subprocess-only extension bundle:** vendored spawn passes `--no-extensions -e .pi/extensions/harness-subagent-submit.ts` for `harness/*` agents with `extensions: false`.
+2. **Scoped `submit_*` tools** per agent, validated against `.pi/harness/specs/*.schema.json` (Ajv) and written deterministically under `HARNESS_RUN_DIR`.
+3. **Parent gates** via `harness_artifact_ready` (file existence) instead of parsing subprocess JSON.
+4. **Debate lanes:** `tool_result` hook prefers last `submit_*` in `details.results[].messages`; skips `finalOutput` auto-apply when submit present (`HARNESS_SUBMIT_TOOLS` default on).
+5. **Parent** blocks all `submit_*`; keeps `write_harness_yaml` for merges and debate round submission only.
+
+## Consequences
+
+- Agent frontmatter lists one terminal `submit_*` tool per role.
+- `HarnessSpawnContext` must include `run_id` / `run_dir`; bridge sets `HARNESS_RUN_ID`, `HARNESS_RUN_DIR`, `HARNESS_AGENT_ID` on spawn.
+- `parseHarnessAgentJson` retained for migration/tests; hot path is tool args.
+- See ADR 0038 for budget telemetry-only default.
+
+## References
+
+- `.pi/extensions/harness-subagent-submit.ts`
+- `.pi/extensions/lib/harness-subagent-submit-registry.ts`
+- `.pi/harness/specs/plan-scout-findings.schema.json`

package/.pi/harness/docs/adrs/0038-budget-telemetry-only.md

@@ -0,0 +1,23 @@
+# ADR 0038: Budget enforcement telemetry-only (default)
+
+**Status:** Accepted  
+**Date:** 2026-05-19
+
+## Context
+
+Token and debate caps emitted `harness-budget-exhausted`, which set `budgetExhausted` in the live widget and blocked flows even when `HARNESS_BUDGET_HARD_STOP` was false. `max_rounds` and messenger exchange limits in `validatePlanDebateGate` also hard-failed approval.
+
+## Decision
+
+- **`HARNESS_BUDGET_ENFORCE` default `off`:** phase/debate caps log `harness-budget-soft-limit` and `harness-budget-telemetry` only; `harness-budget-exhausted` is emitted only when enforce is on **and** hard-stop flags are set.
+- **UI:** `budgetExhausted` / blocked substate only when blocking exhaustion events qualify.
+- **Debate:** `capsForDebate` uses sentinel caps when enforce is off; `max_rounds` gate errors become warnings.
+- **CLI:** `--budget` on harness prompts is reserved/no-op until a real budget story ships.
+
+Re-enable: `HARNESS_BUDGET_ENFORCE=1` plus `HARNESS_BUDGET_HARD_STOP` / `HARNESS_DEBATE_HARD_STOP` as needed.
+
+## Consequences
+
+- Long debates and large plans are not blocked by soft token telemetry.
+- Quality gates (`min_focus_rounds`, required focuses, `review_gate_ready`) remain enforced.
+- PostHog should prefer `harness_budget_telemetry` over exhausted for dashboards until enforce returns.

package/.pi/harness/docs/adrs/README.md

@@ -22,6 +22,8 @@ Team-shared ADRs for the ultimate-pi harness live under `.pi/harness/docs/adrs/`
 | [0034](0034-darwin-plan-research-pipeline.md) | Darwin plan research pipeline | Accepted |
 | [0035](0035-plan-phase-review-gate.md) | Plan-phase Review Gate | Accepted |
 | [0036](0036-implementation-research-and-selective-debate.md) | Implementation research and selective debate | Accepted |
+| [0037](0037-subagent-submit-tools.md) | Subagent submit tools (subprocess extension) | Accepted |
+| [0038](0038-budget-telemetry-only.md) | Budget caps telemetry-only by default | Accepted |
 
 ## Template
 

package/.pi/harness/evals/smoke/fixtures/plan-phase/minimal-med-fast/artifacts/implementation-research.yaml

@@ -0,0 +1,28 @@
+schema_version: "1.0.0"
+problem_framing: Validate harness plan-phase with fixture-driven smoke
+sub_problems:
+  - DAG validation
+  - Debate gate coverage
+internal_references:
+  - path: .pi/harness/evals/smoke/smoke-harness-plan.mjs
+    relevance: Existing smoke pattern
+    reuse_signal: high
+external_references: []
+solution_patterns:
+  - name: fixture-driven gate
+    provenance: in-repo smoke
+    fit: Validates plan pipeline without live agents
+    tradeoffs:
+      pros: [Deterministic CI]
+      cons: []
+    risks: []
+similar_implementations: []
+recommended_approach:
+  summary: Extend minimal-med fixture with implementation artifact
+  recommended_approach_confidence: high
+  confidence_rationale: Reuses established smoke-harness-plan pattern
+  evidence_refs:
+    - .pi/harness/evals/smoke/smoke-harness-plan.mjs
+    - .pi/scripts/validate-plan-dag.mjs
+anti_patterns: []
+open_questions: []

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

@@ -0,0 +1,25 @@
+schema_version: "1.0.0"
+round_index: 1
+debate_round_focus: all
+round_summary: Consolidated review gate for fast profile fixture
+validation_summary: Spec and quality checks pass in one round
+adversary_summary: No blockers
+disputes: []
+recommended_packet_patches: []
+review_gate_ready: true
+participants:
+  - PlanEvaluatorAgent
+  - PlanAdversaryAgent
+  - SprintContractAuditorAgent
+  - ReviewIntegratorAgent
+claims:
+  - consolidated review gate ready
+rebuttals: []
+evidence_refs: []
+token_usage:
+  per_agent:
+    PlanEvaluatorAgent: 120
+    PlanAdversaryAgent: 100
+    SprintContractAuditorAgent: 80
+  round_total: 300
+consensus_delta: 0.1

package/.pi/harness/evals/smoke/fixtures/plan-phase/minimal-med-fast/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: Consolidated debate round recorded (fast profile)
+  - 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-fast/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-fast/research-brief.yaml

@@ -0,0 +1,62 @@
+decomposition:
+  schema_version: "1.0.0"
+  problem_restatement: Light-profile smoke for two-focus debate
+hypothesis:
+  schema_version: "1.0.0"
+  primary:
+    claim: Light debate covers spec and quality only
+    mechanism: Eligibility profile light with min_focus_rounds 2
+    prediction: planDebateOutcomeComplete passes with two rounds
+    experiment: Run smoke-harness-plan.mjs --fixture minimal-low-light
+implementation:
+  schema_version: "1.0.0"
+  problem_framing: Low-risk fixture for selective debate
+  sub_problems: [spec coverage, quality coverage]
+  internal_references:
+    - path: test/plan-debate-eligibility.test.mjs
+      relevance: Eligibility unit tests
+      reuse_signal: high
+  external_references: []
+  solution_patterns:
+    - name: light profile gate
+      provenance: ADR-0036
+      fit: Reduces debate cost on trivial tasks
+      tradeoffs:
+        pros: [Fewer rounds]
+        cons: []
+      risks: []
+  similar_implementations:
+    - name: minimal-med four-focus fixture
+      what_it_solves: Full debate coverage
+      gap_vs_us: Light uses two focuses only
+  recommended_approach:
+    summary: Two review rounds with spec then quality
+    recommended_approach_confidence: high
+    confidence_rationale: Deterministic fixture aligned with eligibility rules
+    evidence_refs:
+      - .pi/extensions/lib/plan-debate-eligibility.ts
+      - test/plan-debate-eligibility.test.mjs
+  anti_patterns: []
+  open_questions: []
+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 light smoke task