ultimate-pi 0.11.0 → 0.13.0

package/.pi/agents/harness/planning/plan-adversary.md

@@ -1,50 +1,18 @@
 ---
-description: Plan adversary (pre-approval) — edge cases and acceptance gaps on a draft PlanPacket.
-tools: read, grep, find, ls, bash
-disallowed_tools: write, edit, ask_user, approve_plan, create_plan, Agent
+description: Plan-phase adversarial verification on ExecutionPlan.
+tools: read, grep, find, ls
+disallowed_tools: write, edit, bash, ask_user, approve_plan, create_plan, subagent
 extensions: false
-thinking: high
-max_turns: 15
-inherit_context: false
+thinking: medium
+max_turns: 12
 ---
 
-You are the **Harness plan adversary (pre-approval)**. Not the post-run `harness/adversary`.
+You are **plan-adversary** — break the plan with reproducible counterexamples.
 
-## Mission
+Engage failed/warn checks from the same round's `plan-evaluator` first, then independent attacks. Cite `work_item_id` / `phase_id`.
 
-Pressure-test a **draft** `PlanPacket` for **execution risk** before the user approves. Surface edge cases, failure modes, and missing acceptance checks tied to hypothesis-derived `acceptance_checks`. Read-only — no mutations.
+## Output
 
-Do **not** re-score DARWIN novelty or duplicate hypothesis-eval work.
+Valid **YAML only** — `PlanAdversaryBrief` (`.pi/harness/specs/plan-adversary-brief.schema.json`).
 
-## Input
-
-The spawn prompt includes:
-
-- `HarnessSpawnContext`
-- Draft `PlanPacket` JSON
-- Scout lane summaries (graphify, structure, semantic)
-
-## Process
-
-1. Assume the plan has hidden gaps until you justify `recommendation: proceed`.
-2. Tie every finding to evidence (paths, APIs, or scout findings) — no speculation without a probe path.
-3. Propose concrete `mitigations` the parent can merge into scope, assumptions, or `acceptance_checks`.
-4. Empty arrays are allowed when no material gaps exist; say so in `human_summary`.
-
-## Output (required JSON block)
-
-Match `PlanAdversaryBrief` (`.pi/harness/specs/plan-adversary-brief.schema.json`):
-
-```json
-{
-  "schema_version": "1.0.0",
-  "edge_cases": ["…"],
-  "failure_modes": ["…"],
-  "acceptance_gaps": ["…"],
-  "mitigations": ["…"],
-  "recommendation": "proceed",
-  "human_summary": "…"
-}
-```
-
-Use `"recommendation": "revise"` when scope or acceptance must change before execution.
+Bus label: `PlanAdversarysubagent`.

package/.pi/agents/harness/planning/plan-evaluator.md

@@ -0,0 +1,18 @@
+---
+description: Plan-phase Validation Checks evaluator (neutral pass/fail).
+tools: read, grep, find, ls
+disallowed_tools: write, edit, bash, ask_user, approve_plan, create_plan, subagent
+extensions: false
+thinking: medium
+max_turns: 12
+---
+
+You are **plan-evaluator** — score ExecutionPlan against Validation Checks (not an advocate).
+
+Parent passes `debate_round_focus`: `spec` | `wbs` | `schedule` | `quality`.
+
+## Output
+
+Valid **YAML only** — `PlanValidationTurn` (`.pi/harness/specs/plan-validation-turn.schema.json`). Fail if `dag_validation.status === "fail"`.
+
+Bus label: `PlanEvaluatorsubagent`.

package/.pi/agents/harness/planning/review-integrator.md

@@ -0,0 +1,23 @@
+---
+description: Plan-phase Review Gate integrator (round → debate bus).
+tools: read, grep, find, ls
+disallowed_tools: write, edit, bash, ask_user, approve_plan, create_plan, subagent
+extensions: false
+thinking: medium
+max_turns: 10
+---
+
+You are **review-integrator** — merge evaluator, adversary, sprint audit, and hypothesis-validator outputs into a Review Gate draft.
+
+## Output
+
+Valid **YAML only** — `PlanReviewRoundDraft` (`.pi/harness/specs/plan-review-round-draft.schema.json`) with:
+
+- `round_summary`, `validation_summary`, `adversary_summary`
+- `disputes[]`, `recommended_packet_patches[]` (JSON Pointer paths)
+- `review_gate_ready` boolean
+- `participants`, `claims`, `rebuttals`, `evidence_refs`, `token_usage`, `severity_scores`
+
+Parent runs `buildPlanReviewRoundEnvelope` → `/harness-debate-round`.
+
+Bus label: `ReviewIntegratorsubagent`.

package/.pi/agents/harness/planning/scout-graphify.md

@@ -1,11 +1,10 @@
 ---
 description: Plan-phase scout — graphify graph and wiki navigation (read-only).
-tools: read, grep, find, ls, bash
-disallowed_tools: write, edit, ask_user, approve_plan, create_plan, Agent
+tools: read, bash, ls
+disallowed_tools: write, edit, ask_user, approve_plan, create_plan, subagent, grep, find
 extensions: false
-thinking: medium
-max_turns: 12
-inherit_context: false
+thinking: low
+max_turns: 6
 ---
 
 You are the **Harness planning scout (graphify lane)**.
@@ -16,6 +15,8 @@ Explore the codebase via graphify for the task in `HarnessSpawnContext`. You do
 
 Findings should feed **constraints, prior art, and tensions** for the decompose agent (existing patterns, god nodes, surprising connections).
 
+**Lane contract:** you own **relationships and architecture** (`graphify query`, `explain`, `path`). `scout-semantic` owns implementation-by-meaning via `ccc search` — do not duplicate semantic chunk search here.
+
 ## Spawn context
 
 Read `HarnessSpawnContext` in the spawn prompt (`task_summary`, `mode`, `plan_packet_path`, `risk_level`, `quick`). For `mode: revise`, read the existing plan at `plan_packet_path` first and focus findings on what changed or is at risk.
@@ -25,11 +26,18 @@ Read `HarnessSpawnContext` in the spawn prompt (`task_summary`, `mode`, `plan_pa
 1. Read `graphify-out/GRAPH_REPORT.md` when present; use `graphify query`, `graphify path`, or `graphify explain` for the task (read-only CLI only).
 2. If `graphify-out/` is missing, say so in `findings` and `open_questions` — do not run `graphify update` or installs.
 3. Do not read `.pi/harness/specs/*.schema.json` from disk.
+4. **Stop early** — target ≤6 tool calls when possible.
 
 ## Bash guardrails
 
 Read-only only: no `graphify update`, `graphify extract`, `pip install`, redirects (`>`, `>>`), or file creation. Allowed: `graphify query`, `graphify path`, `graphify explain`, `ls`, `cat`, `head`.
 
+## Output limits
+
+- `findings`: at most **8** bullets, each ≤2 sentences
+- `key_paths`: at most **10** absolute paths
+- `open_questions`: at most **5** items
+
 ## Output (required JSON block)
 
 End with one fenced `json` block:

package/.pi/agents/harness/planning/scout-semantic.md

@@ -1,18 +1,19 @@
 ---
-description: Plan-phase scout — ck semantic code search (read-only).
-tools: read, grep, find, ls, bash
-disallowed_tools: write, edit, ask_user, approve_plan, create_plan, Agent
+description: Plan-phase scout — CocoIndex semantic code search (read-only).
+tools: read, bash, ls
+disallowed_tools: write, edit, ask_user, approve_plan, create_plan, subagent, grep, find
 extensions: false
-thinking: medium
-max_turns: 12
-inherit_context: false
+thinking: low
+max_turns: 6
 ---
 
 You are the **Harness planning scout (semantic lane)**.
 
 ## Mission
 
-Find conceptually related code via ck semantic search for the task in `HarnessSpawnContext`. You do **not** build the PlanPacket or mutate files.
+Find conceptually related **implementation** via CocoIndex (`ccc search`) for the task in `HarnessSpawnContext`. You do **not** build the PlanPacket or mutate files.
+
+**Lane contract:** `scout-graphify` owns relationships, callers, and communities. You own **meaning** — functions, classes, and chunks that implement the task.
 
 ## Spawn context
 
@@ -20,13 +21,24 @@ Read `HarnessSpawnContext` in the spawn prompt. For `mode: revise`, bias searche
 
 ## Process
 
-1. Use `ck search` or `ck query` (or project-documented ck CLI) with task-focused queries.
-2. If ck is unavailable, set `status: partial` and document in `findings`.
-3. Cap output — prefer the top 5–10 most relevant paths.
+1. Run **2–3** task-focused queries: `ccc search "<query>" --limit 5` (add `--path` when spawn context names a directory).
+2. The harness runs incremental `ccc index` before scouts spawn — **do not** run `ccc index`, `ccc init`, or `ccc search --refresh`.
+3. If `ccc` is missing or the index is empty: `status: partial` and document in `findings`.
+4. **Stop early** — top **5** most relevant paths only.
 
 ## Bash guardrails
 
-Read-only only: no installs, index rebuilds that mutate disk, or redirects.
+Read-only only: no installs, indexing, daemon control, or redirects.
+
+**Allowed:** `ccc search`, `ccc status`, `ls`, `head`, `cat`, `sed -n` (read slices).
+
+**Forbidden:** `ccc index`, `ccc init`, `ccc reset`, `ccc daemon`, `ccc search --refresh`, package installs.
+
+## Output limits
+
+- `findings`: at most **6** bullets
+- `key_paths`: at most **8** absolute paths
+- `open_questions`: at most **4** items
 
 ## Output (required JSON block)
 

package/.pi/agents/harness/planning/scout-structure.md

@@ -1,11 +1,10 @@
 ---
 description: Plan-phase scout — ast-grep structural code search (read-only).
-tools: read, grep, find, ls, bash
-disallowed_tools: write, edit, ask_user, approve_plan, create_plan, Agent
+tools: read, bash, ls
+disallowed_tools: write, edit, ask_user, approve_plan, create_plan, subagent, grep, find
 extensions: false
-thinking: medium
-max_turns: 12
-inherit_context: false
+thinking: low
+max_turns: 6
 ---
 
 You are the **Harness planning scout (structure lane)**.
@@ -22,14 +21,21 @@ Read `HarnessSpawnContext` in the spawn prompt. For `mode: revise`, read the exi
 
 ## Process
 
-1. Run `sg -p '…'` with patterns tied to the task (handlers, types, exports, call sites).
+1. Run `sg -p '…'` with patterns tied to the task (handlers, types, exports, call sites). **Do not use `find` or `grep`.**
 2. Prefer absolute paths in `key_paths`.
 3. If `sg` is not on PATH, set `status: partial` and note the tooling gap in `findings`.
+4. **Stop early** — target ≤6 tool calls when possible.
 
 ## Bash guardrails
 
 Read-only only: no installs, redirects, or mutating git/npm commands.
 
+## Output limits
+
+- `findings`: at most **8** bullets
+- `key_paths`: at most **10** absolute paths
+- `open_questions`: at most **5** items
+
 ## Output (required JSON block)
 
 ```json

package/.pi/agents/harness/planning/sprint-contract-auditor.md

@@ -0,0 +1,18 @@
+---
+description: Plan-phase ADR-020 sprint contract auditor.
+tools: read, grep, find, ls
+disallowed_tools: write, edit, bash, ask_user, approve_plan, create_plan, subagent
+extensions: false
+thinking: medium
+max_turns: 10
+---
+
+You are **sprint-contract-auditor** — ADR-020 Sprint Contract, Done Criteria Types, checkpoints, Keep Quality Left.
+
+Required on debate **round 4**; optional spot-check round 2 if done_criteria sparse.
+
+## Output
+
+Valid **YAML only** — `PlanSprintAuditTurn` (`.pi/harness/specs/plan-sprint-audit-turn.schema.json`).
+
+Bus label: `SprintContractAuditorsubagent`.

package/.pi/agents/harness/planning/stack-researcher.md

@@ -0,0 +1,24 @@
+---
+description: Plan-phase stack research (ctx7 + web, read-only file writes via parent).
+tools: read, grep, find, ls, bash, web_search, web_fetch
+disallowed_tools: write, edit, ask_user, approve_plan, create_plan, subagent
+extensions: false
+thinking: medium
+max_turns: 14
+---
+
+You are **stack-researcher** — evidence-backed stack recommendations for harness planning.
+
+## Mission
+
+Produce `PlanStackBrief` with ranked options. For brownfield tasks, always include **extend current stack** as one ranked option.
+
+## Protocol
+
+1. **Libraries / APIs:** `ctx7 library` → `ctx7 docs` (read context7-cli skill). Cite library IDs in `evidence_refs`.
+2. **Comparisons / landscape:** `web_search` + `web_fetch` (`.web/` artifacts).
+3. **Greenfield:** ≥3 distinct options with pros/cons/risks.
+
+## Output
+
+Return valid **YAML only** (no fences) matching `PlanStackBrief` (`.pi/harness/specs/plan-stack-brief.schema.json`). Parent writes `artifacts/stack.yaml`.

package/.pi/agents/harness/tie-breaker.md

@@ -5,7 +5,6 @@ extensions: false
 disallowed_tools: ask_user
 thinking: high
 max_turns: 15
-inherit_context: false
 ---
 
 You are the Harness Tie-Breaker.

package/.pi/agents/harness/trace-librarian.md

@@ -4,7 +4,6 @@ tools: read, grep, find, ls
 extensions: false
 thinking: medium
 max_turns: 20
-inherit_context: false
 ---
 
 You are the Harness Trace Librarian.

package/.pi/extensions/debate-orchestrator.ts

@@ -14,16 +14,20 @@
  * }
  */
 
-import { appendFile, mkdir, readFile, writeFile } from "node:fs/promises";
+import { appendFile, mkdir, writeFile } from "node:fs/promises";
 import { join } from "node:path";
 import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
+import {
+	type DebateParticipant,
+	debatePhaseFromId,
+	isPlanDebateId,
+	PLAN_DEBATE_PARTICIPANTS,
+	POST_EXECUTE_DEBATE_PARTICIPANTS,
+} from "../lib/debate-orchestrator-types.js";
 import { getRunIdFromSession } from "../lib/harness-run-context.js";
 
-type DebateParticipant =
-	| "EvaluatorAgent"
-	| "AdversaryAgent"
-	| "TieBreakerAgent";
 type PolicyDecision = "pass" | "conditional_pass" | "block" | "human_required";
+type DebatePhase = "plan" | "post_execute";
 
 interface RoundPayload {
 	participants: DebateParticipant[];
@@ -46,11 +50,13 @@ interface RoundPayload {
 interface DebateState {
 	run_id: string;
 	debate_id: string;
+	debate_phase: DebatePhase;
 	round_count: number;
 	budget_used: number;
 	max_rounds: number;
 	round_token_cap: number;
 	debate_global_cap: number;
+	last_review_gate_ready?: boolean;
 }
 
 interface BusEnvelope<T = unknown> {
@@ -104,46 +110,39 @@ function getRunId(ctx: {
 	);
 }
 
-async function readRoundCapsFromSchema(): Promise<{
+const PLAN_BUDGET = {
+	max_rounds: 4,
+	round_token_cap: 2000,
+	debate_global_cap: 12000,
+} as const;
+
+const AGGRESSIVE_BUDGET = {
+	max_rounds: 6,
+	round_token_cap: 2500,
+	debate_global_cap: 35000,
+} as const;
+
+function capsForDebate(debateId: string): {
+	name: "plan" | "aggressive";
 	max_rounds: number;
 	round_token_cap: number;
 	debate_global_cap: number;
-}> {
-	try {
-		const roundSchemaPath = join(
-			process.cwd(),
-			".pi",
-			"harness",
-			"specs",
-			"round-result.schema.json",
+} {
+	if (isPlanDebateId(debateId)) {
+		return { name: "plan", ...PLAN_BUDGET };
+	}
+	return { name: "aggressive", ...AGGRESSIVE_BUDGET };
+}
+
+function participantAllowed(participant: string, phase: DebatePhase): boolean {
+	if (phase === "plan") {
+		return (PLAN_DEBATE_PARTICIPANTS as readonly string[]).includes(
+			participant,
 		);
-		const parsed = JSON.parse(await readFile(roundSchemaPath, "utf-8")) as {
-			properties?: {
-				budget_profile?: {
-					properties?: {
-						max_rounds?: { const?: number };
-						round_token_cap?: { const?: number };
-						debate_global_cap?: { const?: number };
-					};
-				};
-			};
-		};
-		return {
-			max_rounds: Number(
-				parsed?.properties?.budget_profile?.properties?.max_rounds?.const ?? 6,
-			),
-			round_token_cap: Number(
-				parsed?.properties?.budget_profile?.properties?.round_token_cap
-					?.const ?? 2500,
-			),
-			debate_global_cap: Number(
-				parsed?.properties?.budget_profile?.properties?.debate_global_cap
-					?.const ?? 35000,
-			),
-		};
-	} catch {
-		return { max_rounds: 6, round_token_cap: 2500, debate_global_cap: 35000 };
 	}
+	return (POST_EXECUTE_DEBATE_PARTICIPANTS as readonly string[]).includes(
+		participant,
+	);
 }
 
 async function writeDebateEvent(
@@ -197,13 +196,18 @@ export default function debateOrchestrator(pi: ExtensionAPI) {
 	let lastSeverity = defaultSeverity();
 
 	async function openDebate(runId: string, debateId: string): Promise<void> {
-		const caps = await readRoundCapsFromSchema();
+		const caps = capsForDebate(debateId);
+		const debate_phase = debatePhaseFromId(debateId);
 		state = {
 			run_id: runId,
 			debate_id: debateId,
+			debate_phase,
 			round_count: 0,
 			budget_used: 0,
-			...caps,
+			max_rounds: caps.max_rounds,
+			round_token_cap: caps.round_token_cap,
+			debate_global_cap: caps.debate_global_cap,
+			last_review_gate_ready: false,
 		};
 		pi.appendEntry("harness-debate-state", state);
 		const envelope: BusEnvelope = {
@@ -216,7 +220,8 @@ export default function debateOrchestrator(pi: ExtensionAPI) {
 			},
 			payload: {
 				opened_at: nowIso(),
-				budget_profile: "aggressive",
+				debate_phase,
+				budget_profile: caps.name,
 			},
 		};
 		pi.appendEntry("harness-debate-envelope", envelope);
@@ -267,6 +272,15 @@ export default function debateOrchestrator(pi: ExtensionAPI) {
 			return { ok: false, reason: "debate id mismatch" };
 		}
 
+		for (const p of envelope.payload.participants ?? []) {
+			if (!participantAllowed(p, state.debate_phase)) {
+				return {
+					ok: false,
+					reason: `participant ${p} invalid for debate_phase=${state.debate_phase}`,
+				};
+			}
+		}
+
 		const nextRound = state.round_count + 1;
 		if (nextRound > state.max_rounds) {
 			await emitBudgetExhausted("max_rounds_reached");
@@ -310,6 +324,11 @@ export default function debateOrchestrator(pi: ExtensionAPI) {
 			};
 		}
 
+		const profileName =
+			state.debate_phase === "plan"
+				? ("plan" as const)
+				: ("aggressive" as const);
+
 		const roundRecord = {
 			schema_version: "1.0.0",
 			contract_version: "1.0.0",
@@ -322,7 +341,7 @@ export default function debateOrchestrator(pi: ExtensionAPI) {
 			evidence_refs: envelope.payload.evidence_refs,
 			token_usage: envelope.payload.token_usage,
 			budget_profile: {
-				name: "aggressive",
+				name: profileName,
 				max_rounds: state.max_rounds,
 				round_token_cap: state.round_token_cap,
 				debate_global_cap: state.debate_global_cap,
@@ -354,12 +373,20 @@ export default function debateOrchestrator(pi: ExtensionAPI) {
 			),
 		);
 		const decision = decidePolicy(lastSeverity, evidenceScore);
+		const planPhase = state.debate_phase === "plan";
+		const evaluatorPassed = planPhase
+			? Boolean(state.last_review_gate_ready)
+			: true;
+		const debateComplete = planPhase
+			? state.round_count >= state.max_rounds
+			: state.round_count > 0;
 
 		const consensus = {
 			schema_version: "1.0.0",
 			contract_version: "1.0.0",
 			run_id: state.run_id,
 			debate_id: state.debate_id,
+			debate_phase: state.debate_phase,
 			round_count: state.round_count,
 			budget_used: state.budget_used,
 			severity_scores: lastSeverity,
@@ -371,15 +398,25 @@ export default function debateOrchestrator(pi: ExtensionAPI) {
 			},
 			confidence_weights: WEIGHTS,
 			evidence_refs: [],
-			strict_gate_prerequisites: {
-				plan_gate_passed: true,
-				execution_completed: true,
-				evaluator_passed: true,
-				adversarial_debate_completed: state.round_count > 0,
-				severity_policy_ok: decision !== "block",
-				benchmark_delta_checks_passed: false,
-				rollback_artifacts_generated: false,
-			},
+			strict_gate_prerequisites: planPhase
+				? {
+						plan_gate_passed: false,
+						execution_completed: false,
+						evaluator_passed: evaluatorPassed,
+						adversarial_debate_completed: debateComplete,
+						severity_policy_ok: decision !== "block",
+						benchmark_delta_checks_passed: false,
+						rollback_artifacts_generated: false,
+					}
+				: {
+						plan_gate_passed: true,
+						execution_completed: true,
+						evaluator_passed: true,
+						adversarial_debate_completed: debateComplete,
+						severity_policy_ok: decision !== "block",
+						benchmark_delta_checks_passed: false,
+						rollback_artifacts_generated: false,
+					},
 			policy_decision: decision,
 			rationale,
 		};

package/.pi/extensions/harness-plan-approval.ts

@@ -236,7 +236,7 @@ export default function harnessPlanApproval(pi: ExtensionAPI) {
 		name: "create_plan",
 		label: "Create Plan",
 		description:
-			"Write the approved PlanPacket to plan-packet.json for this harness run. Call only after approve_plan (Approve). Do not use write/edit.",
+			"Write the approved PlanPacket to plan-packet.yaml for this harness run. Call only after approve_plan (Approve). Do not use write/edit.",
 		promptSnippet: CREATE_PLAN_SNIPPET,
 		promptGuidelines: CREATE_PLAN_GUIDELINES,
 		parameters: CreatePlanParamsSchema,
@@ -298,7 +298,7 @@ export default function harnessPlanApproval(pi: ExtensionAPI) {
 			return new Text(
 				theme.fg(
 					"success",
-					`Wrote ${details?.plan_path ?? "plan-packet.json"}`,
+					`Wrote ${details?.plan_path ?? "plan-packet.yaml"}`,
 				),
 				0,
 				0,