ultimate-pi 0.11.0 → 0.13.0

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",

package/.pi/harness/evals/smoke/smoke-harness-plan.mjs

@@ -0,0 +1,88 @@
+#!/usr/bin/env node
+/**
+ * smoke-harness-plan — fixture validation for plan-phase pipeline (CI).
+ * Usage: node .pi/harness/evals/smoke/smoke-harness-plan.mjs --fixture
+ */
+
+import { access, cp, mkdir, readFile, rm } from "node:fs/promises";
+import { constants } from "node:fs";
+import { dirname, join, resolve } from "node:path";
+import { fileURLToPath } from "node:url";
+import { parse as parseYaml } from "yaml";
+import { validateExecutionPlan } from "../../../scripts/validate-plan-dag.mjs";
+
+const ROOT = join(dirname(fileURLToPath(import.meta.url)), "..", "..", "..", "..");
+const FIXTURE_DIR = join(dirname(fileURLToPath(import.meta.url)), "fixtures", "plan-phase");
+
+function fail(msg) {
+	console.error(`smoke-harness-plan: FAIL: ${msg}`);
+	process.exit(1);
+}
+
+function ok(msg) {
+	console.log(`  ✓ ${msg}`);
+}
+
+async function runFixture() {
+	const fixtureRoot = join(FIXTURE_DIR, "minimal-med");
+	try {
+		await access(fixtureRoot, constants.R_OK);
+	} catch {
+		fail(`missing fixture ${fixtureRoot}`);
+	}
+
+	const packetPath = join(fixtureRoot, "plan-packet.yaml");
+	const raw = await readFile(packetPath, "utf-8");
+	const packet = parseYaml(raw);
+	if (packet.contract_version !== "1.1.0") {
+		fail("fixture contract_version must be 1.1.0");
+	}
+	if (!packet.execution_plan) fail("fixture missing execution_plan");
+
+	const { status, errors } = validateExecutionPlan(packet, fixtureRoot);
+	if (status !== "pass") {
+		fail(`DAG validation failed: ${errors.join("; ")}`);
+	}
+	ok("fixture plan-packet.yaml DAG pass");
+
+	const reviewPath = join(fixtureRoot, "plan-review.md");
+	await access(reviewPath, constants.R_OK);
+	ok("plan-review.md present");
+
+	const debateRounds = ["review-round-r1.yaml", "review-round-r4.yaml"];
+	for (const name of debateRounds) {
+		const p = join(fixtureRoot, "artifacts", name);
+		await access(p, constants.R_OK);
+		const draft = parseYaml(await readFile(p, "utf-8"));
+		if (!draft.schema_version) fail(`${name} missing schema_version`);
+	}
+	ok("debate round YAML artifacts present");
+
+	const researchPath = join(fixtureRoot, "research-brief.yaml");
+	const research = parseYaml(await readFile(researchPath, "utf-8"));
+	if (!research.decomposition || !research.hypothesis) {
+		fail("research-brief.yaml missing decomposition/hypothesis");
+	}
+	ok("research-brief.yaml structure");
+
+	console.log("smoke-harness-plan: all fixture checks passed");
+}
+
+async function main() {
+	const args = process.argv.slice(2);
+	if (args.includes("--fixture")) {
+		await runFixture();
+		return;
+	}
+	if (args.includes("--live")) {
+		console.log(
+			"smoke-harness-plan: --live requires manual /harness-plan run; skipping in CI",
+		);
+		return;
+	}
+	fail("Usage: smoke-harness-plan.mjs --fixture | --live");
+}
+
+main().catch((err) => {
+	fail(err instanceof Error ? err.message : String(err));
+});

package/.pi/harness/specs/harness-posthog-event.schema.json

@@ -24,7 +24,12 @@
 				"harness_drift_report",
 				"harness_eval_verdict",
 				"harness_sentrux_signal",
-				"harness_observation"
+				"harness_observation",
+				"harness_subagent_spawned",
+				"harness_subagent_completed",
+				"harness_subagent_result_wait",
+				"harness_subagent_setup",
+				"harness_blackboard_op"
 			]
 		},
 		"distinct_id": {

package/.pi/harness/specs/plan-execution-plan-brief.schema.json

@@ -0,0 +1,13 @@
+{
+	"$schema": "https://json-schema.org/draft/2020-12/schema",
+	"$id": "https://ultimate-pi.local/.pi/harness/specs/plan-execution-plan-brief.schema.json",
+	"title": "PlanExecutionPlanBrief",
+	"type": "object",
+	"additionalProperties": false,
+	"required": ["schema_version", "execution_plan"],
+	"properties": {
+		"schema_version": { "type": "string", "const": "1.0.0" },
+		"execution_plan": { "$ref": "plan-execution-plan.schema.json" },
+		"human_summary": { "type": "string" }
+	}
+}

package/.pi/harness/specs/plan-execution-plan.schema.json

@@ -0,0 +1,255 @@
+{
+	"$schema": "https://json-schema.org/draft/2020-12/schema",
+	"$id": "https://ultimate-pi.local/.pi/harness/specs/plan-execution-plan.schema.json",
+	"title": "ExecutionPlan",
+	"type": "object",
+	"additionalProperties": false,
+	"required": [
+		"schema_version",
+		"phases",
+		"work_items",
+		"sprint_contract",
+		"wbs_dictionary",
+		"risk_register",
+		"schedule_metadata",
+		"dag_validation"
+	],
+	"properties": {
+		"schema_version": { "type": "string", "const": "1.0.0" },
+		"phases": {
+			"type": "array",
+			"minItems": 1,
+			"items": { "$ref": "#/$defs/phase" }
+		},
+		"work_items": {
+			"type": "array",
+			"minItems": 1,
+			"items": { "$ref": "#/$defs/work_item" }
+		},
+		"sprint_contract": { "$ref": "#/$defs/sprint_contract" },
+		"wbs_dictionary": {
+			"type": "array",
+			"items": { "$ref": "#/$defs/wbs_entry" }
+		},
+		"risk_register": {
+			"type": "array",
+			"items": { "$ref": "#/$defs/risk" }
+		},
+		"schedule_metadata": { "$ref": "#/$defs/schedule_metadata" },
+		"dag_validation": { "$ref": "#/$defs/dag_validation" }
+	},
+	"$defs": {
+		"phase": {
+			"type": "object",
+			"additionalProperties": false,
+			"required": [
+				"phase_id",
+				"name",
+				"objective",
+				"entry_criteria",
+				"exit_criteria",
+				"milestone",
+				"work_item_ids"
+			],
+			"properties": {
+				"phase_id": { "type": "string", "minLength": 1 },
+				"name": { "type": "string", "minLength": 1 },
+				"objective": { "type": "string", "minLength": 1 },
+				"entry_criteria": {
+					"type": "array",
+					"minItems": 1,
+					"items": { "type": "string", "minLength": 1 }
+				},
+				"exit_criteria": {
+					"type": "array",
+					"minItems": 1,
+					"items": { "type": "string", "minLength": 1 }
+				},
+				"milestone": { "type": "string", "minLength": 1 },
+				"work_item_ids": {
+					"type": "array",
+					"minItems": 1,
+					"items": { "type": "string", "minLength": 1 }
+				}
+			}
+		},
+		"work_item": {
+			"type": "object",
+			"additionalProperties": false,
+			"required": [
+				"work_item_id",
+				"phase_id",
+				"title",
+				"description",
+				"depends_on",
+				"files",
+				"parallel_safe",
+				"done_criteria",
+				"acceptance_check_ids"
+			],
+			"properties": {
+				"work_item_id": { "type": "string", "minLength": 1 },
+				"phase_id": { "type": "string", "minLength": 1 },
+				"title": { "type": "string", "minLength": 1 },
+				"description": { "type": "string", "minLength": 1 },
+				"depends_on": {
+					"type": "array",
+					"items": { "type": "string", "minLength": 1 }
+				},
+				"files": {
+					"type": "array",
+					"items": { "type": "string", "minLength": 1 }
+				},
+				"parallel_safe": { "type": "boolean" },
+				"non_code": { "type": "boolean" },
+				"done_criteria": { "$ref": "#/$defs/done_criteria" },
+				"acceptance_check_ids": {
+					"type": "array",
+					"minItems": 1,
+					"items": { "type": "string", "minLength": 1 }
+				}
+			}
+		},
+		"done_criteria": {
+			"type": "object",
+			"additionalProperties": false,
+			"required": ["type", "spec"],
+			"properties": {
+				"type": {
+					"type": "string",
+					"enum": ["command", "test", "lint", "manual", "artifact"]
+				},
+				"spec": { "type": "string", "minLength": 1 }
+			}
+		},
+		"sprint_contract": {
+			"type": "object",
+			"additionalProperties": false,
+			"required": [
+				"in_scope",
+				"out_of_scope",
+				"definition_of_done",
+				"assumptions",
+				"external_dependencies"
+			],
+			"properties": {
+				"in_scope": {
+					"type": "array",
+					"items": { "type": "string", "minLength": 1 }
+				},
+				"out_of_scope": {
+					"type": "array",
+					"items": { "type": "string", "minLength": 1 }
+				},
+				"definition_of_done": { "type": "string", "minLength": 1 },
+				"assumptions": {
+					"type": "array",
+					"items": { "type": "string", "minLength": 1 }
+				},
+				"external_dependencies": {
+					"type": "array",
+					"items": { "type": "string", "minLength": 1 }
+				}
+			}
+		},
+		"wbs_entry": {
+			"type": "object",
+			"additionalProperties": false,
+			"required": [
+				"work_item_id",
+				"deliverable",
+				"owner_role",
+				"inputs",
+				"outputs"
+			],
+			"properties": {
+				"work_item_id": { "type": "string", "minLength": 1 },
+				"deliverable": { "type": "string", "minLength": 1 },
+				"owner_role": {
+					"type": "string",
+					"enum": ["executor", "human", "research"]
+				},
+				"inputs": {
+					"type": "array",
+					"items": { "type": "string", "minLength": 1 }
+				},
+				"outputs": {
+					"type": "array",
+					"items": { "type": "string", "minLength": 1 }
+				}
+			}
+		},
+		"risk": {
+			"type": "object",
+			"additionalProperties": false,
+			"required": [
+				"risk_id",
+				"description",
+				"likelihood",
+				"impact",
+				"mitigation",
+				"linked_work_item_ids"
+			],
+			"properties": {
+				"risk_id": { "type": "string", "minLength": 1 },
+				"description": { "type": "string", "minLength": 1 },
+				"likelihood": {
+					"type": "string",
+					"enum": ["low", "med", "high"]
+				},
+				"impact": {
+					"type": "string",
+					"enum": ["low", "med", "high"]
+				},
+				"mitigation": { "type": "string", "minLength": 1 },
+				"linked_work_item_ids": {
+					"type": "array",
+					"items": { "type": "string", "minLength": 1 }
+				}
+			}
+		},
+		"schedule_metadata": {
+			"type": "object",
+			"additionalProperties": false,
+			"required": [
+				"critical_path_work_item_ids",
+				"parallel_groups",
+				"schedule_baseline_note"
+			],
+			"properties": {
+				"critical_path_work_item_ids": {
+					"type": "array",
+					"items": { "type": "string", "minLength": 1 }
+				},
+				"parallel_groups": {
+					"type": "array",
+					"items": {
+						"type": "array",
+						"items": { "type": "string", "minLength": 1 }
+					}
+				},
+				"schedule_baseline_note": { "type": "string", "minLength": 1 }
+			}
+		},
+		"dag_validation": {
+			"type": "object",
+			"additionalProperties": false,
+			"required": ["status", "topological_order", "cycles", "conflicts"],
+			"properties": {
+				"status": { "type": "string", "enum": ["pass", "fail"] },
+				"topological_order": {
+					"type": "array",
+					"items": { "type": "string", "minLength": 1 }
+				},
+				"cycles": {
+					"type": "array",
+					"items": { "type": "array", "items": { "type": "string" } }
+				},
+				"conflicts": {
+					"type": "array",
+					"items": { "type": "string", "minLength": 1 }
+				}
+			}
+		}
+	}
+}