ultimate-pi 0.16.0 → 0.17.0

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

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

@@ -1,7 +1,7 @@
 #!/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 [minimal-med|minimal-low-light]
+ * Usage: node .pi/harness/evals/smoke/smoke-harness-plan.mjs --fixture [minimal-med|minimal-low-light|minimal-med-fast]
  */
 
 import { access, readFile } from "node:fs/promises";
@@ -26,16 +26,23 @@ async function scanFocusCoverage(fixtureRoot, requiredFocus) {
 	let last_round_index = 0;
 	const { readdir } = await import("node:fs/promises");
 	const files = (await readdir(art)).filter((f) =>
-		/^review-round-r\d+\.yaml$/i.test(f),
+		/^review-round(?:-r\d+|-consolidated)\.yaml$/i.test(f),
 	);
 	for (const name of files.sort()) {
-		const m = /^review-round-r(\d+)\.yaml$/i.exec(name);
+		const consolidated = /^review-round-consolidated\.yaml$/i.test(name);
+		const m = consolidated
+			? ["review-round-consolidated.yaml", "1"]
+			: /^review-round-r(\d+)\.yaml$/i.exec(name);
 		if (!m) continue;
-		const roundIndex = Number(m[1]);
+		const roundIndex = consolidated ? 1 : Number(m[1]);
 		if (roundIndex > last_round_index) last_round_index = roundIndex;
 		const draft = parseYaml(await readFile(join(art, name), "utf-8"));
 		const focus = String(draft.debate_round_focus ?? "").trim();
-		if (requiredFocus.includes(focus)) covered.add(focus);
+		if (focus === "all") {
+			for (const f of requiredFocus) covered.add(f);
+		} else if (requiredFocus.includes(focus)) {
+			covered.add(focus);
+		}
 		if (roundIndex === last_round_index) {
 			last_review_gate_ready = draft.review_gate_ready === true;
 		}
@@ -110,22 +117,33 @@ async function runFixture(name) {
 	ok("research-brief.yaml structure");
 
 	const isLight = name === "minimal-low-light";
-	const requiredFocus = isLight ? ["spec", "quality"] : ["spec", "wbs", "schedule", "quality"];
-	const debateRounds = isLight
-		? ["review-round-r1.yaml", "review-round-r2.yaml"]
-		: [
-				"review-round-r1.yaml",
-				"review-round-r2.yaml",
-				"review-round-r3.yaml",
-				"review-round-r4.yaml",
-			];
+	const isFast = name === "minimal-med-fast";
+	const requiredFocus =
+		isLight || isFast
+			? ["spec", "quality"]
+			: ["spec", "wbs", "schedule", "quality"];
+	const debateRounds = isFast
+		? ["review-round-consolidated.yaml"]
+		: isLight
+			? ["review-round-r1.yaml", "review-round-r2.yaml"]
+			: [
+					"review-round-r1.yaml",
+					"review-round-r2.yaml",
+					"review-round-r3.yaml",
+					"review-round-r4.yaml",
+				];
 	const seenFocus = new Set();
 	for (const fileName of debateRounds) {
 		const p = join(fixtureRoot, "artifacts", fileName);
 		await access(p, constants.R_OK);
 		const draft = parseYaml(await readFile(p, "utf-8"));
 		if (!draft.schema_version) fail(`${fileName} missing schema_version`);
-		if (draft.debate_round_focus) seenFocus.add(draft.debate_round_focus);
+		const f = String(draft.debate_round_focus ?? "").trim();
+		if (f === "all") {
+			for (const req of requiredFocus) seenFocus.add(req);
+		} else if (f) {
+			seenFocus.add(f);
+		}
 	}
 	for (const focus of requiredFocus) {
 		if (!seenFocus.has(focus)) {
@@ -135,7 +153,7 @@ async function runFixture(name) {
 	ok(`debate round YAML artifacts (${requiredFocus.length} focuses)`);
 
 	const coverage = await scanFocusCoverage(fixtureRoot, requiredFocus);
-	const minRounds = isLight ? 2 : 4;
+	const minRounds = isFast ? 1 : isLight ? 2 : 4;
 	if (!planOutcomeComplete(coverage, requiredFocus, minRounds)) {
 		fail("debate outcome incomplete for fixture coverage");
 	}
@@ -144,6 +162,9 @@ async function runFixture(name) {
 	if (isLight && packet.risk_level !== "low") {
 		fail("minimal-low-light fixture must use risk_level low");
 	}
+	if (isFast && packet.risk_level !== "med") {
+		fail("minimal-med-fast fixture must use risk_level med");
+	}
 
 	console.log(`smoke-harness-plan: all ${name} fixture checks passed`);
 }
@@ -161,7 +182,9 @@ async function main() {
 		);
 		return;
 	}
-	fail("Usage: smoke-harness-plan.mjs --fixture [minimal-med|minimal-low-light] | --live");
+	fail(
+		"Usage: smoke-harness-plan.mjs --fixture [minimal-med|minimal-low-light|minimal-med-fast] | --live",
+	);
 }
 
 main().catch((err) => {

package/.pi/harness/specs/plan-review-round-draft.schema.json

@@ -16,7 +16,7 @@
 		"round_index": { "type": "integer", "minimum": 1, "maximum": 12 },
 		"debate_round_focus": {
 			"type": "string",
-			"enum": ["spec", "wbs", "schedule", "quality"]
+			"enum": ["spec", "wbs", "schedule", "quality", "all"]
 		},
 		"round_summary": { "type": "string", "minLength": 1 },
 		"validation_summary": { "type": "string" },

package/.pi/model-router.example.json

@@ -1,7 +1,7 @@
 {
 	"defaultProfile": "auto",
 	"debug": false,
-	"classifierModel": "opencode-go/qwen3.6-plus",
+	"classifierModel": "openai/gpt-5.4-nano",
 	"phaseBias": 0.5,
 	"maxSessionBudget": 1.0,
 	"largeContextThreshold": 100000,
@@ -16,12 +16,21 @@
 	"profiles": {
 		"auto": {
 			"high": {
-				"model": "opencode-go/deepseek-v4-pro",
+				"model": "openai/gpt-5.5",
 				"thinking": "high",
-				"fallbacks": ["opencode-go/qwen3.6-plus"]
+				"fallbacks": ["openai/gpt-5.4-nano"]
+			},
+			"medium": { "model": "openai/gpt-5.5", "thinking": "medium" },
+			"low": { "model": "openai/gpt-5.5", "thinking": "low" }
+		},
+		"opencode-go": {
+			"high": {
+				"model": "opencode-go/qwen3.6-plus",
+				"thinking": "high",
+				"fallbacks": ["opencode-go/deepseek-v4-flash"]
 			},
 			"medium": { "model": "opencode-go/qwen3.6-plus", "thinking": "medium" },
-			"low": { "model": "opencode-go/deepseek-v4-flash", "thinking": "low" }
+			"low": { "model": "opencode-go/qwen3.6-plus", "thinking": "low" }
 		}
 	}
 }

package/.pi/prompts/harness-plan.md

@@ -138,11 +138,16 @@ harness_debate_open({ debate_profile, required_focuses })
 
 Profiles:
 
-| Profile | Focuses required | min_focus_rounds |
-|---------|------------------|------------------|
-| full | spec, wbs, schedule, quality | 4 |
-| standard | all four | 4 |
-| light | spec, quality only | 2 |
+| Profile | Review gate | Focuses required | min_focus_rounds |
+|---------|-------------|------------------|------------------|
+| full | threaded (4 rounds) | spec, wbs, schedule, quality | 4 |
+| standard | threaded (4 rounds) | all four | 4 |
+| light | threaded (2 rounds) | spec, quality only | 2 |
+| fast | **consolidated** (1 round) | spec, quality | 1 |
+
+Med/low non-fork plans with clear stack and no implementation `open_questions` default to **fast** (consolidated). Escalate to threaded rounds only when integrator sets `review_gate_ready: false` or records blockers.
+
+`--quick`: skip scout-semantic; cap web research (≤2 searches, ≤3 fetches); prefer **fast** eligibility when DAG passes; use consolidated Review Gate when profile is fast.
 
 ## Phase 5 — Review Gate debate (profile-aware, pi-messenger, even with `--quick`)
 
@@ -153,13 +158,26 @@ Profiles:
 
 ### Focus coverage (required before consensus)
 
-Each required focus must appear in a submitted `review-round-rN.yaml` (`debate_round_focus`). Monotonic `round_index` (cap from profile). Consensus only when:
+Each required focus must appear in submitted review artifacts (`review-round-rN.yaml` or `review-round-consolidated.yaml` with `debate_round_focus: all`). Monotonic `round_index` (cap from profile). Consensus only when:
 
 - all **required** focuses covered, **and**
 - last round `review_gate_ready: true`, **and**
 - `validate-plan-dag.mjs` still passes (re-run after patches).
 
-### Per-round state machine
+### Consolidated state machine (`review_gate_mode: consolidated`, profile fast)
+
+```
+round_index := 1
+debate_round_focus := all
+spawn hypothesis-validator (blind)
+WHILE NOT ready_for_integrator (harness_debate_round_status round_index=1):
+  follow next_tool (validation-turn, adversary-brief, sprint-audit in parallel-friendly order; one subagent per batch)
+spawn review-integrator → write artifacts/review-round-consolidated.yaml → harness_debate_submit_round
+IF review_gate_ready false OR blockers: escalate — threaded round per missing focus (spec/wbs/schedule/quality)
+harness_debate_focus_coverage → harness_debate_consensus
+```
+
+### Threaded state machine (standard/full/light)
 
 ```
 round_index := next uncovered required focus

package/.pi/prompts/harness-setup.md

@@ -327,7 +327,7 @@ sentrux plugin add-standard 2>/dev/null || echo "Plugins already installed or fa
 
 ## Step 3 — Pi Extension Packages
 
-Bundled extensions load from the installed `ultimate-pi` package. **Per-turn model routing** comes from a **vendored** fork of [`yeliu84/pi-model-router`](https://github.com/yeliu84/pi-model-router) in `vendor/pi-model-router/`, wired through [`.pi/extensions/pi-model-router-harness.ts`](.pi/extensions/pi-model-router-harness.ts). The harness **gates** activation on `.pi/model-router.json` (Step **3.5** below) so `router/auto` and built-in tiers such as `openai/gpt-5.4-pro` cannot load prematurely. Attribution: see [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md) and `vendor/pi-model-router/UPSTREAM_PIN.md`. Maintainer refresh: `npm run vendor:sync-router`.
+Bundled extensions load from the installed `ultimate-pi` package. **Session-locked model routing** comes from a **vendored** fork of [`yeliu84/pi-model-router`](https://github.com/yeliu84/pi-model-router) in `vendor/pi-model-router/`, wired through [`.pi/extensions/pi-model-router-harness.ts`](.pi/extensions/pi-model-router-harness.ts). The router picks **one concrete model** when the session starts (from the first user prompt + system prompt complexity), then changes **thinking level only** each turn. The harness **gates** activation on `.pi/model-router.json` (Step **3.5** below) so `router/auto` cannot load prematurely. Attribution: see [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md) and `vendor/pi-model-router/UPSTREAM_PIN.md`. Maintainer refresh: `npm run vendor:sync-router`.
 
 Optionally install the companion lockfile used in development:
 
@@ -381,9 +381,9 @@ If generation prints "No authenticated Pi providers": warn in report — user sh
 
 Do NOT block setup. If no config is written, `harness-sync-model-router.mjs` clears a premature `defaultProvider: "router"` in `.pi/settings.json`.
 
-**Router onboarding** — The vendored extension starts only after `.pi/model-router.json` appears. Running the script above prepares that file plus optional Pi defaults (**`router` / `auto`**) via `harness-sync-model-router.mjs` when `defaultProvider` was unset—then **`/reload`**.
+**Router onboarding** — The vendored extension starts only after `.pi/model-router.json` appears. Running the script above prepares that file plus optional Pi defaults (**`router` / `auto`**, or whatever `defaultProfile` is) via `harness-sync-model-router.mjs` when `defaultProvider` was unset—then **`/reload`**. Generated profiles use **one model SKU per profile**; high/medium/low tiers differ in **thinking** only. Subagents resolve their subprocess model from the **agent system prompt** complexity (same lock rules).
 
-Manual override: **`/router profile auto`** anytime after reload if they changed defaults.
+Manual override: **`/router profile auto`** or **`/router profile opencode-go`** anytime after reload if they changed defaults.
 
 ## Step 3.6 — Harness agents (package-resolved)
 
@@ -677,7 +677,7 @@ Output summary table:
 | sentrux | ✓/✗ | CLI + plugins; rules via Step 4.2 bootstrap |
 | Sentrux rules.toml | ✓/✗ | `.sentrux/rules.toml` synced from manifest |
 | pi extensions | ✓/✗ | 4 packages |
-| model router | ✓/✗ | Package + config verified, activation via `/router profile auto` |
+| model router | ✓/✗ | Package + config verified, activation via `/router profile auto` (or `opencode-go`) |
 | `.env` | ✓/✗/ask | Created / keys appended / user declined |
 
 | .gitignore | ✓/✗ | entries added (incl. `.env`) |