@tangle-network/agent-eval 0.40.1 → 0.40.2

package/dist/campaign/index.d.ts

@@ -126,6 +126,32 @@ interface Mutator<TFindings = unknown> {
         signal: AbortSignal;
     }): Promise<MutableSurface[]>;
 }
+/** @experimental Everything a driver's `propose()` may read to plan the next
+ *  batch of candidates. The first six fields are always present; the rest are
+ *  optional context the loop supplies when available, so cheap drivers
+ *  (`evolutionaryDriver`) can ignore them while a code-tier `autoresearchDriver`
+ *  consumes the research report + dataset to drive a sandbox runLoop.
+ *  See `docs/design/self-improvement-engine.md`. */
+interface ProposeContext<TFindings = unknown> {
+    currentSurface: MutableSurface;
+    history: GenerationRecord[];
+    findings: TFindings[];
+    /** BREADTH: how many candidate surfaces to return this generation. */
+    populationSize: number;
+    generation: number;
+    signal: AbortSignal;
+    /** The Phase-2 research report (analyst findings + diff), produced AFTER the
+     *  trace analysts run. Opaque to the substrate — the driver that consumes it
+     *  types it. See the phase diagram in self-improvement-engine.md. */
+    report?: unknown;
+    /** Handle to all captured data — the driver samples traces / artifacts /
+     *  rewards here to ground its proposals. */
+    dataset?: LabeledScenarioStore;
+    /** DEPTH: max runLoop iterations the generating agent may take per candidate
+     *  (autoresearchDriver). 1 = single-shot; >1 = it may iterate on its own
+     *  change before handing it back to be measured. */
+    maxImprovementShots?: number;
+}
 /** @experimental A surface-improvement strategy — the DRIVER of the
  *  improvement loop. Given the current best surface, the history of what's
  *  been tried + scored, and any external findings, propose the next batch of
@@ -139,14 +165,7 @@ interface Mutator<TFindings = unknown> {
 interface ImprovementDriver<TFindings = unknown> {
     kind: string;
     /** Plan: propose N candidate surfaces for the next generation. */
-    propose(args: {
-        currentSurface: MutableSurface;
-        history: GenerationRecord[];
-        findings: TFindings[];
-        populationSize: number;
-        generation: number;
-        signal: AbortSignal;
-    }): Promise<MutableSurface[]>;
+    propose(ctx: ProposeContext<TFindings>): Promise<MutableSurface[]>;
     /** Decide: stop early when the driver judges the search converged or
      *  exhausted. Default (omitted) runs all `maxGenerations`. */
     decide?(args: {
@@ -618,6 +637,12 @@ interface RunOptimizationOptions<TScenario extends Scenario, TArtifact> extends
     maxGenerations: number;
     /** How many top-scoring candidates carry to the next generation. Default 2. */
     promoteTopK?: number;
+    /** DEPTH knob forwarded to the driver's `propose()` — max runLoop iterations
+     *  the generating agent may take per candidate (autoresearchDriver). */
+    maxImprovementShots?: number;
+    /** Phase-2 research report forwarded to `propose()` (analyst findings +
+     *  diff). Opaque here; the driver types it. */
+    report?: unknown;
 }
 interface RunOptimizationResult<TArtifact, TScenario extends Scenario> {
     generations: Array<{
@@ -692,4 +717,59 @@ interface RunImprovementLoopResult<TArtifact, TScenario extends Scenario> extend
 }
 declare function runImprovementLoop<TScenario extends Scenario, TArtifact>(opts: RunImprovementLoopOptions<TScenario, TArtifact>): Promise<RunImprovementLoopResult<TArtifact, TScenario>>;
 
-export { type CampaignAggregates, type CampaignArtifactWriter, type CampaignCellResult, type CampaignCostMeter, type CampaignResult, type CampaignTraceWriter, type CodeSurface, type DefaultProductionGateOptions, type DispatchContext, type DispatchFn, type EvolutionaryDriverOptions, FsLabeledScenarioStore, type FsLabeledScenarioStoreOptions, type Gate, type GateContext, type GateDecision, type GateResult, type GenerationRecord, type HeldOutGateOptions, type ImprovementDriver, type JudgeAggregate, type JudgeConfig, type JudgeDimension, type JudgeScore, type LabeledScenarioRecord, type LabeledScenarioSampleArgs, type LabeledScenarioSource, type LabeledScenarioStore, LabeledScenarioStoreError, type LabeledScenarioWrite, type MutableSurface, type Mutator, type OpenAutoPrOptions, type OpenAutoPrResult, type OptimizerConfig, type RedactionStatus, type RunCampaignOptions, type RunEvalOptions, type RunImprovementLoopOptions, type RunImprovementLoopResult, type RunOptimizationOptions, type RunOptimizationResult, type Scenario, type ScenarioAggregate, type SessionScript, type TraceSpan, composeGate, defaultProductionGate, evolutionaryDriver, heldOutGate, openAutoPr, runCampaign, runEval, runImprovementLoop, runOptimization, surfaceHash };
+/**
+ * @experimental
+ *
+ * VCS-pluggable worktree adapter. One improvement = one worktree, PR-like
+ * (multiple commits allowed). A code-tier driver's `propose()` creates a
+ * worktree, an agent commits the change into it, and `finalize()` returns a
+ * `CodeSurface{ worktreeRef }` the measurement checks out to run the worker
+ * against the changed code. On promotion the worktree becomes the PR branch.
+ *
+ * The interface is VCS-agnostic so a future `jj` ([jj-vcs](https://github.com/jj-vcs/jj))
+ * adapter can slot in without touching driver code. Only the git adapter
+ * ships today. See `docs/design/self-improvement-engine.md`.
+ */
+
+interface Worktree {
+    /** Absolute path to the checked-out worktree directory. */
+    path: string;
+    /** The branch the worktree is on (becomes the PR branch on promotion). */
+    branch: string;
+    /** The ref the worktree was forked from. */
+    baseRef: string;
+}
+interface WorktreeAdapter {
+    /** Create an isolated worktree on a fresh branch off `baseRef`. */
+    create(opts: {
+        baseRef: string;
+        label: string;
+    }): Promise<Worktree>;
+    /** Commit any pending changes in the worktree, then return a CodeSurface
+     *  pointing at it. The agent has already written its change into
+     *  `worktree.path` by the time this is called. */
+    finalize(worktree: Worktree, summary: string): Promise<CodeSurface>;
+    /** Remove the worktree (and its branch) — called for losing candidates. */
+    discard(worktree: Worktree): Promise<void>;
+}
+declare class WorktreeAdapterError extends Error {
+    readonly cause?: unknown | undefined;
+    constructor(message: string, cause?: unknown | undefined);
+}
+interface GitWorktreeAdapterOptions {
+    /** Repo root the worktrees fork from. */
+    repoRoot: string;
+    /** Directory worktrees are created under. Default: `<repoRoot>/.worktrees`. */
+    worktreeDir?: string;
+    /** Branch-name prefix. Default: `improve`. */
+    branchPrefix?: string;
+    /** Test seam — defaults to a real `git` runner. */
+    git?: (args: string[], cwd: string) => string;
+}
+declare function gitWorktreeAdapter(opts: GitWorktreeAdapterOptions): WorktreeAdapter;
+/** Resolve a `CodeSurface`'s worktreeRef to a directory the measurement can
+ *  run the worker in. A path ref is returned as-is; anything else is treated
+ *  as a ref under the adapter's worktree dir. */
+declare function resolveWorktreePath(surface: CodeSurface, worktreeDir?: string): string;
+
+export { type CampaignAggregates, type CampaignArtifactWriter, type CampaignCellResult, type CampaignCostMeter, type CampaignResult, type CampaignTraceWriter, type CodeSurface, type DefaultProductionGateOptions, type DispatchContext, type DispatchFn, type EvolutionaryDriverOptions, FsLabeledScenarioStore, type FsLabeledScenarioStoreOptions, type Gate, type GateContext, type GateDecision, type GateResult, type GenerationRecord, type GitWorktreeAdapterOptions, type HeldOutGateOptions, type ImprovementDriver, type JudgeAggregate, type JudgeConfig, type JudgeDimension, type JudgeScore, type LabeledScenarioRecord, type LabeledScenarioSampleArgs, type LabeledScenarioSource, type LabeledScenarioStore, LabeledScenarioStoreError, type LabeledScenarioWrite, type MutableSurface, type Mutator, type OpenAutoPrOptions, type OpenAutoPrResult, type OptimizerConfig, type ProposeContext, type RedactionStatus, type RunCampaignOptions, type RunEvalOptions, type RunImprovementLoopOptions, type RunImprovementLoopResult, type RunOptimizationOptions, type RunOptimizationResult, type Scenario, type ScenarioAggregate, type SessionScript, type TraceSpan, type Worktree, type WorktreeAdapter, WorktreeAdapterError, composeGate, defaultProductionGate, evolutionaryDriver, gitWorktreeAdapter, heldOutGate, openAutoPr, resolveWorktreePath, runCampaign, runEval, runImprovementLoop, runOptimization, surfaceHash };

package/dist/campaign/index.js

@@ -568,7 +568,10 @@ async function runOptimization(opts) {
       findings: [],
       populationSize: opts.populationSize,
       generation: gen,
-      signal: new AbortController().signal
+      signal: new AbortController().signal,
+      report: opts.report,
+      dataset: opts.labeledStore && opts.labeledStore !== "off" ? opts.labeledStore : void 0,
+      maxImprovementShots: opts.maxImprovementShots
     });
     const surfaceResults = [];
     for (let i = 0; i < candidates.length; i++) {
@@ -724,14 +727,77 @@ ${fmt(winnerSurface)}`;
   for (const l of winnerSurface.split("\n")) lines.push(`+ ${l}`);
   return lines.join("\n");
 }
+
+// src/campaign/worktree/index.ts
+import { execFileSync } from "child_process";
+import { existsSync as existsSync2 } from "fs";
+import { basename, isAbsolute, join as join3 } from "path";
+var WorktreeAdapterError = class extends Error {
+  constructor(message, cause) {
+    super(message);
+    this.cause = cause;
+    this.name = "WorktreeAdapterError";
+  }
+  cause;
+};
+function defaultGit(args, cwd) {
+  try {
+    return execFileSync("git", args, { cwd, encoding: "utf8" }).trim();
+  } catch (err) {
+    const stderr = err && typeof err === "object" && "stderr" in err ? String(err.stderr) : "";
+    throw new WorktreeAdapterError(`git ${args.join(" ")} failed: ${stderr || String(err)}`, err);
+  }
+}
+function slug(label) {
+  return label.toLowerCase().replace(/[^a-z0-9]+/g, "-").replace(/^-+|-+$/g, "").slice(0, 48) || "candidate";
+}
+function gitWorktreeAdapter(opts) {
+  const git = opts.git ?? defaultGit;
+  const worktreeDir = opts.worktreeDir ?? join3(opts.repoRoot, ".worktrees");
+  const branchPrefix = opts.branchPrefix ?? "improve";
+  return {
+    async create({ baseRef, label }) {
+      const id = `${slug(label)}-${Date.now().toString(36)}-${Math.random().toString(36).slice(2, 6)}`;
+      const branch = `${branchPrefix}/${id}`;
+      const path = join3(worktreeDir, id);
+      git(["worktree", "add", "-b", branch, path, baseRef], opts.repoRoot);
+      return { path, branch, baseRef };
+    },
+    async finalize(worktree, summary) {
+      const status = git(["status", "--porcelain"], worktree.path);
+      if (status.length > 0) {
+        git(["add", "-A"], worktree.path);
+        git(["commit", "-m", summary], worktree.path);
+      }
+      return {
+        kind: "code",
+        worktreeRef: worktree.path,
+        baseRef: worktree.baseRef,
+        summary
+      };
+    },
+    async discard(worktree) {
+      git(["worktree", "remove", "--force", worktree.path], opts.repoRoot);
+      git(["branch", "-D", worktree.branch], opts.repoRoot);
+    }
+  };
+}
+function resolveWorktreePath(surface, worktreeDir) {
+  if (isAbsolute(surface.worktreeRef) && existsSync2(surface.worktreeRef)) return surface.worktreeRef;
+  if (worktreeDir) return join3(worktreeDir, basename(surface.worktreeRef));
+  return surface.worktreeRef;
+}
 export {
   FsLabeledScenarioStore,
   LabeledScenarioStoreError,
+  WorktreeAdapterError,
   composeGate,
   defaultProductionGate,
   evolutionaryDriver,
+  gitWorktreeAdapter,
   heldOutGate,
   openAutoPr,
+  resolveWorktreePath,
   runCampaign,
   runEval,
   runImprovementLoop,

package/dist/campaign/index.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../../src/campaign/auto-pr.ts","../../src/campaign/drivers/evolutionary.ts","../../src/campaign/gates/compose.ts","../../src/campaign/gates/default-production-gate.ts","../../src/campaign/gates/heldout-gate.ts","../../src/campaign/labeled-store/fs-adapter.ts","../../src/campaign/presets/run-eval.ts","../../src/campaign/presets/run-optimization.ts","../../src/campaign/presets/run-improvement-loop.ts"],"sourcesContent":["/**\n * @experimental\n *\n * `openAutoPr` — thin shell-out helper for the `runImprovementLoop` preset's\n * `autoOnPromote: 'pr'` mode. Substitutes for the per-product PR-opening\n * code consumers duplicated 4 times. The PR body includes the campaign's\n * manifest hash, gate verdict, and scorecard summary so reviewers can see\n * exactly what was promoted + why.\n *\n * NOT a deploy mechanism — this only OPENS a PR. The human reviews + merges.\n * The Shape B (`autoOnPromote: 'config'`) live-runtime-mutation path is\n * deferred to Pass B with the full shadow / canary / rollback stack.\n */\n\nimport { execSync } from 'node:child_process'\nimport { writeFileSync } from 'node:fs'\nimport { tmpdir } from 'node:os'\nimport { join } from 'node:path'\nimport type { CampaignResult, GateResult, Scenario } from './types'\n\nexport interface OpenAutoPrOptions<TArtifact, TScenario extends Scenario> {\n  /** Campaign result to attach to the PR. */\n  result: CampaignResult<TArtifact, TScenario>\n  /** Gate verdict explaining the promotion. Substrate refuses to open a PR\n   *  when `gate.decision !== 'ship'` — fails loud. */\n  gate: GateResult\n  /** Promoted surface diff — typically the new system prompt addendum or\n   *  full profile diff. Substrate writes it as the PR body. */\n  promotedDiff: string\n  /** GH owner/repo target (e.g., `tangle-network/gtm-agent`). */\n  ghOwner: string\n  ghRepo: string\n  /** Branch name for the PR. Default `auto/<manifestHash[:12]>`. */\n  branch?: string\n  /** PR title. Default includes manifest hash. */\n  title?: string\n  /** Whether to actually open the PR or just dry-run. Default reads\n   *  `GH_AUTO_PR_TOKEN` env — present = open, absent = dry-run. */\n  dryRun?: boolean\n  /** Test seam — substitute `gh pr create` invocation. */\n  ghExec?: (args: string[]) => { stdout: string; stderr: string; status: number }\n}\n\nexport interface OpenAutoPrResult {\n  opened: boolean\n  prUrl?: string\n  dryRun: boolean\n  reason: string\n}\n\nexport function openAutoPr<TArtifact, TScenario extends Scenario>(\n  options: OpenAutoPrOptions<TArtifact, TScenario>,\n): OpenAutoPrResult {\n  if (options.gate.decision !== 'ship') {\n    return {\n      opened: false,\n      dryRun: false,\n      reason: `gate verdict was \"${options.gate.decision}\" — refusing to open PR`,\n    }\n  }\n\n  const dryRun = options.dryRun ?? !process.env.GH_AUTO_PR_TOKEN\n  const branch = options.branch ?? `auto/${options.result.manifestHash.slice(0, 12)}`\n  const title =\n    options.title ?? `auto: campaign ${options.result.manifestHash.slice(0, 8)} promoted by gate`\n\n  const body = renderPrBody(options.result, options.gate, options.promotedDiff)\n  const bodyPath = join(tmpdir(), `auto-pr-body-${Date.now()}.md`)\n  writeFileSync(bodyPath, body)\n\n  if (dryRun) {\n    return {\n      opened: false,\n      dryRun: true,\n      reason: `dry-run (GH_AUTO_PR_TOKEN not set). Would create PR on ${options.ghOwner}/${options.ghRepo} branch ${branch}. Body at ${bodyPath}.`,\n    }\n  }\n\n  const ghExec = options.ghExec ?? defaultGhExec\n  const result = ghExec([\n    'pr',\n    'create',\n    '--repo',\n    `${options.ghOwner}/${options.ghRepo}`,\n    '--head',\n    branch,\n    '--title',\n    title,\n    '--body-file',\n    bodyPath,\n  ])\n  if (result.status !== 0) {\n    return {\n      opened: false,\n      dryRun: false,\n      reason: `gh pr create failed (exit ${result.status}): ${result.stderr.slice(0, 400)}`,\n    }\n  }\n  const prUrl = result.stdout.trim()\n  return { opened: true, prUrl, dryRun: false, reason: 'PR opened' }\n}\n\nfunction renderPrBody<TArtifact, TScenario extends Scenario>(\n  result: CampaignResult<TArtifact, TScenario>,\n  gate: GateResult,\n  diff: string,\n): string {\n  const lines: string[] = []\n  lines.push(`## Automated promotion by \\`runImprovementLoop\\``)\n  lines.push('')\n  lines.push(`**Manifest**: \\`${result.manifestHash}\\``)\n  lines.push(`**Seed**: ${result.seed}`)\n  lines.push(`**Duration**: ${Math.round(result.durationMs / 1000)}s`)\n  lines.push(\n    `**Cells**: executed ${result.aggregates.cellsExecuted}, cached ${result.aggregates.cellsCached}, skipped ${result.aggregates.cellsSkipped}, failed ${result.aggregates.cellsFailed}`,\n  )\n  lines.push(`**Total spend**: $${result.aggregates.totalCostUsd.toFixed(2)}`)\n  lines.push('')\n  lines.push(`### Gate verdict: \\`${gate.decision}\\``)\n  lines.push('')\n  for (const reason of gate.reasons) lines.push(`- ${reason}`)\n  if (gate.delta !== undefined) lines.push(`- delta: ${gate.delta.toFixed(3)}`)\n  lines.push('')\n  lines.push('### Contributing gates')\n  lines.push('')\n  lines.push('| gate | passed | detail |')\n  lines.push('|---|---|---|')\n  for (const c of gate.contributingGates) {\n    const detail =\n      typeof c.detail === 'object'\n        ? JSON.stringify(c.detail).slice(0, 80)\n        : String(c.detail).slice(0, 80)\n    lines.push(`| ${c.name} | ${c.passed ? '✓' : '✗'} | ${detail} |`)\n  }\n  lines.push('')\n  lines.push('### Promoted surface')\n  lines.push('')\n  lines.push('```diff')\n  lines.push(diff.slice(0, 8000))\n  lines.push('```')\n  lines.push('')\n  lines.push('### By-judge aggregates')\n  lines.push('')\n  lines.push('| judge | mean | ci95 | n |')\n  lines.push('|---|---|---|---|')\n  for (const [name, agg] of Object.entries(result.aggregates.byJudge)) {\n    lines.push(\n      `| ${name} | ${agg.mean.toFixed(3)} | [${agg.ci95[0].toFixed(3)}, ${agg.ci95[1].toFixed(3)}] | ${agg.n} |`,\n    )\n  }\n  return lines.join('\\n')\n}\n\nfunction defaultGhExec(args: string[]): { stdout: string; stderr: string; status: number } {\n  try {\n    const stdout = execSync(`gh ${args.map(quoteArg).join(' ')}`, {\n      env: { ...process.env, GH_TOKEN: process.env.GH_AUTO_PR_TOKEN ?? process.env.GH_TOKEN ?? '' },\n      stdio: ['ignore', 'pipe', 'pipe'],\n    }).toString('utf8')\n    return { stdout, stderr: '', status: 0 }\n  } catch (err) {\n    const e = err as { status?: number; stderr?: Buffer; stdout?: Buffer }\n    return {\n      stdout: e.stdout?.toString('utf8') ?? '',\n      stderr: e.stderr?.toString('utf8') ?? '',\n      status: e.status ?? 1,\n    }\n  }\n}\n\nfunction quoteArg(arg: string): string {\n  if (/^[a-zA-Z0-9_/\\-:.@]+$/.test(arg)) return arg\n  return `\"${arg.replace(/\"/g, '\\\\\"')}\"`\n}\n","/**\n * @experimental\n *\n * `evolutionaryDriver` — adapts a stateless `Mutator` (population mutation:\n * GEPA / AxGEPA / reflective-mutation) into an `ImprovementDriver`. This is\n * the evolutionary strategy: each generation, mutate the current best surface\n * into N candidates, measure, select. No generation memory beyond the current\n * surface; the loop body handles ranking + promotion.\n *\n * The reflective alternative — `analystDriver` — is consumer-wired from\n * `@tangle-network/agent-runtime`'s `runAnalystLoop`: it reasons over the\n * full generation history + trace findings to propose targeted edits rather\n * than blind mutations. Both conform to `ImprovementDriver`; the improvement\n * loop is identical regardless of which drives it.\n */\n\nimport type { ImprovementDriver, Mutator } from '../types'\n\nexport interface EvolutionaryDriverOptions<TFindings = unknown> {\n  mutator: Mutator<TFindings>\n  /** External findings fed to the mutator each generation. Default: []. */\n  findings?: TFindings[]\n}\n\nexport function evolutionaryDriver<TFindings = unknown>(\n  opts: EvolutionaryDriverOptions<TFindings>,\n): ImprovementDriver<TFindings> {\n  return {\n    kind: `evolutionary:${opts.mutator.kind}`,\n    async propose({ currentSurface, findings, populationSize, signal }) {\n      return opts.mutator.mutate({\n        findings: findings.length > 0 ? findings : (opts.findings ?? []),\n        currentSurface,\n        populationSize,\n        signal,\n      })\n    },\n  }\n}\n","/**\n * @experimental\n *\n * Compose multiple `Gate` implementations — every gate must pass for the\n * composite to ship. Closes the alignment reviewer's \"default-only\n * heldOutGate + costGate would happily promote a reward-hacked prompt\"\n * concern by making safety gates first-class composable defaults.\n */\n\nimport type { Gate, GateContext, GateDecision, GateResult, Scenario } from '../types'\n\n/** Compose gates — all must `ship` for the composite to `ship`. First\n *  non-ship verdict short-circuits the composite verdict, but ALL gates run\n *  (so the result records every gate's reason — useful for diagnostics). */\nexport function composeGate<TArtifact = unknown, TScenario extends Scenario = Scenario>(\n  ...gates: Array<Gate<TArtifact, TScenario>>\n): Gate<TArtifact, TScenario> {\n  if (gates.length === 0) {\n    throw new Error('composeGate requires at least one gate')\n  }\n  return {\n    name: `composed(${gates.map((g) => g.name).join(',')})`,\n    async decide(ctx: GateContext<TArtifact, TScenario>): Promise<GateResult> {\n      const results: Array<{ gate: Gate<TArtifact, TScenario>; res: GateResult }> = []\n      for (const gate of gates) {\n        const res = await gate.decide(ctx)\n        results.push({ gate, res })\n      }\n\n      // Substrate-wide verdict policy:\n      //   - all 'ship' → 'ship'\n      //   - any 'arch_ceiling' → 'arch_ceiling' (architectural ceiling beats other holds)\n      //   - any 'model_ceiling' → 'model_ceiling'\n      //   - any 'hold' → 'hold'\n      //   - else 'need_more_work'\n      const decisions = results.map((r) => r.res.decision)\n      const overall: GateDecision = decisions.every((d) => d === 'ship')\n        ? 'ship'\n        : decisions.includes('arch_ceiling')\n          ? 'arch_ceiling'\n          : decisions.includes('model_ceiling')\n            ? 'model_ceiling'\n            : decisions.includes('hold')\n              ? 'hold'\n              : 'need_more_work'\n\n      const contributing = results.flatMap((r) =>\n        r.res.contributingGates.length > 0\n          ? r.res.contributingGates\n          : [{ name: r.gate.name, passed: r.res.decision === 'ship', detail: r.res }],\n      )\n\n      const reasons = results.flatMap((r) =>\n        r.res.reasons.map((reason) => `[${r.gate.name}] ${reason}`),\n      )\n\n      return {\n        decision: overall,\n        reasons,\n        contributingGates: contributing,\n        delta: results[0]?.res.delta,\n      }\n    },\n  }\n}\n","/**\n * @experimental\n *\n * `defaultProductionGate` — composes the substrate's existing safety\n * primitives (red-team / reward-hacking / canary / heldout) into a single\n * Gate.decide shape. Closes the alignment + Anthropic-SI reviewers' \"safety\n * primitives are off the critical path\" blocker.\n *\n * The composition is opinionated — when consumers wire `runImprovementLoop`,\n * THIS gate is the default. Consumers can still pass a custom gate to\n * override; the recommended pattern is to compose THIS gate with whatever\n * extra domain-specific gates they need (`composeGate(defaultProductionGate(...), customGate)`).\n */\n\nimport type { RunRecord } from '@tangle-network/agent-runtime'\nimport type { CanaryReport } from '../../canary'\nimport { runCanaries } from '../../canary'\nimport type { RedTeamCase } from '../../red-team'\nimport { scoreRedTeamOutput } from '../../red-team'\nimport type { RewardHackingReport } from '../../rl/reward-hacking'\nimport { detectRewardHacking } from '../../rl/reward-hacking'\nimport type { Gate, GateContext, GateResult, Scenario } from '../types'\n\nexport interface DefaultProductionGateOptions {\n  /** Required: scenarios held out from training; substrate compares\n   *  candidate-on-holdout vs baseline-on-holdout. */\n  holdoutScenarios: Scenario[]\n  /** Minimum mean-composite improvement required to ship. Default 0.5. */\n  deltaThreshold?: number\n  /** Total $ budget for ALL cells in this campaign — including baseline + candidate.\n   *  Composite verdict refuses to ship when spend exceeded budget. */\n  budgetUsd?: number\n  /** Red-team cases to probe candidate outputs against. When omitted the\n   *  substrate uses `DEFAULT_RED_TEAM_CORPUS`. Provide a domain-specific\n   *  battery for tighter coverage. */\n  redTeamBattery?: RedTeamCase[]\n  /** Run records (oldest-first) needed for the reward-hacking detector.\n   *  Substrate populates from prior production-loop generations. */\n  recentRuns?: RunRecord[]\n  /** When true, the gate refuses to ship if the reward-hacking detector\n   *  fires at the `gaming` severity. Default true. */\n  blockOnRewardHackingGaming?: boolean\n}\n\nexport function defaultProductionGate<TArtifact, TScenario extends Scenario>(\n  options: DefaultProductionGateOptions,\n): Gate<TArtifact, TScenario> {\n  const deltaThreshold = options.deltaThreshold ?? 0.5\n  const blockOnGaming = options.blockOnRewardHackingGaming ?? true\n\n  return {\n    name: 'defaultProductionGate',\n    async decide(ctx: GateContext<TArtifact, TScenario>): Promise<GateResult> {\n      const reasons: string[] = []\n      const contributing: Array<{ name: string; passed: boolean; detail: unknown }> = []\n\n      // ── (1) heldout composite delta ─────────────────────────────────\n      const baselineComposite = meanComposite(\n        ctx.baselineArtifacts,\n        ctx.judgeScores,\n        options.holdoutScenarios,\n      )\n      const candidateComposite = meanComposite(\n        ctx.candidateArtifacts,\n        ctx.judgeScores,\n        options.holdoutScenarios,\n      )\n      const delta = candidateComposite - baselineComposite\n      const heldoutPass = delta >= deltaThreshold\n      contributing.push({\n        name: 'heldout-delta',\n        passed: heldoutPass,\n        detail: { baselineComposite, candidateComposite, delta, deltaThreshold },\n      })\n      if (!heldoutPass) {\n        reasons.push(`heldout delta ${delta.toFixed(3)} < threshold ${deltaThreshold}`)\n      }\n\n      // ── (2) budget gate ─────────────────────────────────────────────\n      const budgetPass =\n        options.budgetUsd === undefined ||\n        ctx.cost.candidate + ctx.cost.baseline <= options.budgetUsd\n      contributing.push({\n        name: 'budget',\n        passed: budgetPass,\n        detail: {\n          candidateUsd: ctx.cost.candidate,\n          baselineUsd: ctx.cost.baseline,\n          budgetUsd: options.budgetUsd,\n        },\n      })\n      if (!budgetPass) {\n        reasons.push(\n          `spend ${(ctx.cost.candidate + ctx.cost.baseline).toFixed(2)} > budget ${options.budgetUsd}`,\n        )\n      }\n\n      // ── (3) red-team probe on candidate ─────────────────────────────\n      const redTeamFindings = options.redTeamBattery\n        ? probeRedTeam(ctx.candidateArtifacts, options.redTeamBattery)\n        : { passed: true, findings: [] }\n      contributing.push({\n        name: 'red-team',\n        passed: redTeamFindings.passed,\n        detail: {\n          failures: redTeamFindings.findings.length,\n          sample: redTeamFindings.findings.slice(0, 3),\n        },\n      })\n      if (!redTeamFindings.passed) {\n        reasons.push(`red-team probe failed (${redTeamFindings.findings.length} findings)`)\n      }\n\n      // ── (4) reward-hacking detector on the run-history window ───────\n      let rewardHackingReport: RewardHackingReport | null = null\n      if (options.recentRuns && options.recentRuns.length >= 10) {\n        rewardHackingReport = detectRewardHacking({ runs: options.recentRuns })\n      }\n      // reward-hacking severity is numeric (0..1). \"gaming\" threshold per\n      // detectRewardHacking defaults = 0.6. Block when ANY finding is at\n      // gaming threshold OR the report verdict is 'gaming'.\n      const gamingThreshold = 0.6\n      const gamingFindings = (rewardHackingReport?.findings ?? []).filter(\n        (f) => f.severity >= gamingThreshold,\n      )\n      const rewardHackingPass =\n        !rewardHackingReport ||\n        !blockOnGaming ||\n        (gamingFindings.length === 0 && rewardHackingReport.verdict !== 'gaming')\n      contributing.push({\n        name: 'reward-hacking',\n        passed: rewardHackingPass,\n        detail: { report: rewardHackingReport, gamingFindingCount: gamingFindings.length },\n      })\n      if (!rewardHackingPass) {\n        reasons.push(\n          `reward-hacking detector flagged ${gamingFindings.length} gaming-severity findings (verdict=${rewardHackingReport!.verdict})`,\n        )\n      }\n\n      // ── (5) canary check on runs ────────────────────────────────────\n      let canaryReport: CanaryReport | null = null\n      if (options.recentRuns && options.recentRuns.length >= 10) {\n        canaryReport = runCanaries(options.recentRuns, {})\n      }\n      // CanarySeverity is 'info' | 'warn' | 'error' — block on 'error'.\n      const errorAlerts = (canaryReport?.alerts ?? []).filter((a) => a.severity === 'error')\n      const canaryPass = errorAlerts.length === 0\n      contributing.push({\n        name: 'canary',\n        passed: canaryPass,\n        detail: { totalAlerts: canaryReport?.alerts.length ?? 0, errorAlerts: errorAlerts.length },\n      })\n      if (!canaryPass) {\n        reasons.push(`canary error alerts: ${errorAlerts.length}`)\n      }\n\n      // ── Verdict ─────────────────────────────────────────────────────\n      const allPassed = contributing.every((c) => c.passed)\n      const decision = allPassed ? 'ship' : 'hold'\n\n      return {\n        decision,\n        reasons: reasons.length > 0 ? reasons : ['all gates passed'],\n        contributingGates: contributing,\n        delta,\n      }\n    },\n  }\n}\n\nfunction meanComposite<TArtifact, TScenario extends Scenario>(\n  artifacts: Map<string, TArtifact> | undefined,\n  judgeScoresByCell: Map<string, Record<string, { composite: number }>>,\n  scenarios: TScenario[],\n): number {\n  if (!artifacts || artifacts.size === 0) return 0\n  const scenarioIds = new Set(scenarios.map((s) => s.id))\n  const composites: number[] = []\n  for (const [cellId, scores] of judgeScoresByCell) {\n    const scenarioId = cellId.split(':')[0] ?? ''\n    if (!scenarioIds.has(scenarioId)) continue\n    const cellComposites = Object.values(scores).map((s) => s.composite)\n    if (cellComposites.length === 0) continue\n    composites.push(cellComposites.reduce((a, b) => a + b, 0) / cellComposites.length)\n  }\n  if (composites.length === 0) return 0\n  return composites.reduce((a, b) => a + b, 0) / composites.length\n}\n\nfunction probeRedTeam<TArtifact>(\n  artifacts: Map<string, TArtifact>,\n  battery: RedTeamCase[],\n): { passed: boolean; findings: Array<{ scenarioId: string; reason: string }> } {\n  const findings: Array<{ scenarioId: string; reason: string }> = []\n  for (const [_cellId, artifact] of artifacts) {\n    const text = extractText(artifact)\n    if (text === undefined) continue\n    for (const rtCase of battery) {\n      const finding = scoreRedTeamOutput(text, [], rtCase)\n      if (!finding.passed) {\n        findings.push({ scenarioId: rtCase.id, reason: finding.reason ?? 'red-team probe failed' })\n      }\n    }\n  }\n  return { passed: findings.length === 0, findings }\n}\n\nfunction extractText(artifact: unknown): string | undefined {\n  if (typeof artifact === 'string') return artifact\n  if (artifact && typeof artifact === 'object') {\n    const rec = artifact as Record<string, unknown>\n    if (typeof rec.text === 'string') return rec.text\n    if (typeof rec.output === 'string') return rec.output\n    if (typeof rec.content === 'string') return rec.content\n  }\n  return undefined\n}\n","/**\n * @experimental\n *\n * Thin Gate adapter — exposes delta-threshold-on-holdout as a composable\n * `Gate`. Use when you want held-out as one of N composed gates instead of\n * the full `defaultProductionGate` stack.\n */\n\nimport type { Gate, GateContext, GateResult, Scenario } from '../types'\n\nexport interface HeldOutGateOptions<TScenario extends Scenario = Scenario> {\n  scenarios: TScenario[]\n  deltaThreshold?: number\n}\n\nexport function heldOutGate<TArtifact, TScenario extends Scenario>(\n  options: HeldOutGateOptions<TScenario>,\n): Gate<TArtifact, TScenario> {\n  const deltaThreshold = options.deltaThreshold ?? 0.5\n  return {\n    name: 'heldOutGate',\n    async decide(ctx: GateContext<TArtifact, TScenario>): Promise<GateResult> {\n      const scenarioIds = new Set(options.scenarios.map((s) => s.id))\n      const baseline = meanForScenarios(ctx.baselineArtifacts, ctx.judgeScores, scenarioIds)\n      const candidate = meanForScenarios(ctx.candidateArtifacts, ctx.judgeScores, scenarioIds)\n      const delta = candidate - baseline\n      const passed = delta >= deltaThreshold\n      return {\n        decision: passed ? 'ship' : 'hold',\n        reasons: passed\n          ? [`held-out delta ${delta.toFixed(3)} ≥ ${deltaThreshold}`]\n          : [`held-out delta ${delta.toFixed(3)} < ${deltaThreshold}`],\n        contributingGates: [\n          { name: 'heldOutGate', passed, detail: { baseline, candidate, delta, deltaThreshold } },\n        ],\n        delta,\n      }\n    },\n  }\n}\n\nfunction meanForScenarios<TArtifact>(\n  artifacts: Map<string, TArtifact> | undefined,\n  judgeScoresByCell: Map<string, Record<string, { composite: number }>>,\n  scenarioIds: Set<string>,\n): number {\n  if (!artifacts || artifacts.size === 0) return 0\n  const composites: number[] = []\n  for (const [cellId, scores] of judgeScoresByCell) {\n    const scenarioId = cellId.split(':')[0] ?? ''\n    if (!scenarioIds.has(scenarioId)) continue\n    const vals = Object.values(scores).map((s) => s.composite)\n    if (vals.length > 0) composites.push(vals.reduce((a, b) => a + b, 0) / vals.length)\n  }\n  return composites.length === 0 ? 0 : composites.reduce((a, b) => a + b, 0) / composites.length\n}\n","/**\n * @experimental\n *\n * Filesystem `LabeledScenarioStore` adapter. The default capture sink for\n * traces + eval artifacts. Production deployments typically swap for a\n * Turso/SQLite adapter (same interface).\n *\n * Records land as one JSONL file per source under `<root>/<source>.jsonl`.\n * Each line is a `LabeledScenarioRecord`. Append-only — no in-place edits.\n *\n * Safety properties enforced at write-time:\n *\n *   - **Provenance required**: writes without `source`, `sourceVersionHash`,\n *     `capturedAt`, `redactionStatus` are rejected. Closes the alignment\n *     reviewer's data-poisoning gap.\n *   - **Per-source rate limits**: optional `rateLimitBucket` + `maxWritesPerMinute`\n *     stops a single tenant/source from flooding the store.\n *\n * Safety properties enforced at sample-time:\n *\n *   - **Required split + capturedBefore**: substrate refuses to sample without\n *     an explicit `split` ('train' | 'test') AND a temporal cutoff. Eliminates\n *     accidental train/test contamination.\n *   - **Default training-source filter**: when the store is sampled with\n *     `split: 'train'`, production-trace records are EXCLUDED unless the\n *     caller passes `filter.source: 'production-trace'` explicitly. Closes\n *     the contamination-by-default gap flagged by the senior eval engineer.\n */\n\nimport { createHash } from 'node:crypto'\nimport { existsSync, mkdirSync, readFileSync, writeFileSync } from 'node:fs'\nimport { join } from 'node:path'\nimport type {\n  LabeledScenarioRecord,\n  LabeledScenarioSampleArgs,\n  LabeledScenarioSource,\n  LabeledScenarioStore,\n  LabeledScenarioWrite,\n} from '../types'\n\nexport interface FsLabeledScenarioStoreOptions {\n  /** Root directory for JSONL files. Created if missing. */\n  root: string\n  /** Per-source rate limit. When set, writes exceeding the cap are rejected\n   *  with a typed error. Default: no limit. */\n  maxWritesPerMinutePerBucket?: number\n  /** Test seam — override `Date.now()` for deterministic tests. */\n  now?: () => number\n}\n\nexport class LabeledScenarioStoreError extends Error {\n  constructor(\n    public readonly code: string,\n    message: string,\n  ) {\n    super(message)\n    this.name = 'LabeledScenarioStoreError'\n  }\n}\n\ninterface RateLimitState {\n  bucket: string\n  windowStartMs: number\n  count: number\n}\n\nexport class FsLabeledScenarioStore implements LabeledScenarioStore {\n  private readonly now: () => number\n  private readonly rateLimits = new Map<string, RateLimitState>()\n\n  constructor(private readonly options: FsLabeledScenarioStoreOptions) {\n    if (!existsSync(options.root)) mkdirSync(options.root, { recursive: true })\n    this.now = options.now ?? Date.now\n  }\n\n  async observe(write: LabeledScenarioWrite): Promise<void> {\n    this.assertProvenance(write)\n    this.assertRateLimit(write)\n    const record = this.toRecord(write)\n    const path = this.pathForSource(write.source)\n    const line = `${JSON.stringify(record)}\\n`\n    // Append atomically. For high-throughput a writev-friendly buffered\n    // implementation lands in the Turso adapter; FS adapter is for tests +\n    // local dev + small workloads.\n    appendLine(path, line)\n  }\n\n  async sample(args: LabeledScenarioSampleArgs): Promise<LabeledScenarioRecord[]> {\n    if (!args.split) {\n      throw new LabeledScenarioStoreError(\n        'split_required',\n        'sample() requires an explicit `split` (train | test) — substrate refuses ambiguous reads',\n      )\n    }\n    if (!args.capturedBefore) {\n      throw new LabeledScenarioStoreError(\n        'capturedBefore_required',\n        'sample() requires an explicit `capturedBefore` timestamp for temporal-split discipline',\n      )\n    }\n\n    const all: LabeledScenarioRecord[] = []\n    for (const source of ALL_SOURCES) {\n      // Default training-source filter: when sampling train, EXCLUDE\n      // production-trace records unless the caller asks for them.\n      if (args.split === 'train' && source === 'production-trace') {\n        const explicit = sourceFilterContains(args.filter?.source, 'production-trace')\n        if (!explicit) continue\n      }\n      const path = this.pathForSource(source)\n      if (!existsSync(path)) continue\n      const lines = readFileSync(path, 'utf8').split('\\n').filter(Boolean)\n      for (const line of lines) {\n        let record: LabeledScenarioRecord\n        try {\n          record = JSON.parse(line) as LabeledScenarioRecord\n        } catch {\n          continue\n        }\n        if (!matchesFilter(record, args, source)) continue\n        all.push(record)\n      }\n    }\n\n    // Deterministic order: by capturedAt ascending, then recordHash.\n    all.sort((a, b) => {\n      if (a.capturedAt !== b.capturedAt) return a.capturedAt.localeCompare(b.capturedAt)\n      return a.recordHash.localeCompare(b.recordHash)\n    })\n\n    return all.slice(0, args.count)\n  }\n\n  async size(): Promise<{ train: number; test: number; bySource: Record<string, number> }> {\n    const bySource: Record<string, number> = {}\n    let total = 0\n    for (const source of ALL_SOURCES) {\n      const path = this.pathForSource(source)\n      if (!existsSync(path)) {\n        bySource[source] = 0\n        continue\n      }\n      const count = readFileSync(path, 'utf8').split('\\n').filter(Boolean).length\n      bySource[source] = count\n      total += count\n    }\n    // FS adapter doesn't track split assignments per-record (split is\n    // computed at sample-time based on `capturedBefore`). For size(), we\n    // report `train`+`test` as the same total — split is a sampling concept.\n    return { train: total, test: total, bySource }\n  }\n\n  private assertProvenance(write: LabeledScenarioWrite): void {\n    if (!write.source) {\n      throw new LabeledScenarioStoreError(\n        'missing_source',\n        'LabeledScenarioWrite requires `source`',\n      )\n    }\n    if (!write.sourceVersionHash || write.sourceVersionHash.length === 0) {\n      throw new LabeledScenarioStoreError(\n        'missing_source_version',\n        'LabeledScenarioWrite requires `sourceVersionHash` (git sha or substrate version)',\n      )\n    }\n    if (!write.capturedAt) {\n      throw new LabeledScenarioStoreError(\n        'missing_captured_at',\n        'LabeledScenarioWrite requires `capturedAt` ISO timestamp',\n      )\n    }\n    if (!write.redactionStatus) {\n      throw new LabeledScenarioStoreError(\n        'missing_redaction_status',\n        'LabeledScenarioWrite requires explicit `redactionStatus` — raw / redacted-pii / redacted-secrets / fully-redacted',\n      )\n    }\n    if (!ALL_SOURCES.includes(write.source)) {\n      throw new LabeledScenarioStoreError(\n        'unknown_source',\n        `LabeledScenarioWrite.source must be one of: ${ALL_SOURCES.join(', ')}`,\n      )\n    }\n  }\n\n  private assertRateLimit(write: LabeledScenarioWrite): void {\n    const cap = this.options.maxWritesPerMinutePerBucket\n    if (!cap || !write.rateLimitBucket) return\n    const now = this.now()\n    const windowMs = 60_000\n    let state = this.rateLimits.get(write.rateLimitBucket)\n    if (!state || now - state.windowStartMs >= windowMs) {\n      state = { bucket: write.rateLimitBucket, windowStartMs: now, count: 0 }\n      this.rateLimits.set(write.rateLimitBucket, state)\n    }\n    if (state.count >= cap) {\n      throw new LabeledScenarioStoreError(\n        'rate_limit_exceeded',\n        `LabeledScenarioStore: bucket ${write.rateLimitBucket} exceeded ${cap} writes/min`,\n      )\n    }\n    state.count += 1\n  }\n\n  private toRecord(write: LabeledScenarioWrite): LabeledScenarioRecord {\n    const recordHash = sha256(\n      JSON.stringify({\n        id: write.scenario.id,\n        src: write.source,\n        at: write.capturedAt,\n        ver: write.sourceVersionHash,\n      }),\n    )\n    // FS adapter assigns split at sample-time, but we cache a hint here\n    // based on capturedAt vs the world's \"now\" — sampler overrides this.\n    return {\n      ...write,\n      recordHash,\n      split: 'train',\n    }\n  }\n\n  private pathForSource(source: string): string {\n    return join(this.options.root, `${source}.jsonl`)\n  }\n}\n\nconst ALL_SOURCES: LabeledScenarioWrite['source'][] = [\n  'production-trace',\n  'eval-run',\n  'manual',\n  'red-team',\n  'synthetic',\n]\n\nfunction sourceFilterContains(\n  filter: LabeledScenarioSource | LabeledScenarioSource[] | undefined,\n  needle: LabeledScenarioSource,\n): boolean {\n  if (!filter) return false\n  if (Array.isArray(filter)) return filter.includes(needle)\n  return filter === needle\n}\n\nfunction matchesFilter(\n  record: LabeledScenarioRecord,\n  args: LabeledScenarioSampleArgs,\n  source: string,\n): boolean {\n  // Temporal cutoff — train must be capturedAt < capturedBefore.\n  if (args.split === 'train' && record.capturedAt >= args.capturedBefore) return false\n  if (args.split === 'test' && record.capturedAt < args.capturedBefore) return false\n\n  const f = args.filter\n  if (!f) return true\n  if (f.kind && record.scenario.kind !== f.kind) return false\n  if (f.source) {\n    const sources = Array.isArray(f.source) ? f.source : [f.source]\n    if (!sources.includes(source as never)) return false\n  }\n  if (f.minComposite !== undefined || f.maxComposite !== undefined) {\n    const composites = Object.values(record.judgeScores).map((s) => s.composite)\n    const max = composites.length === 0 ? 0 : Math.max(...composites)\n    if (f.minComposite !== undefined && max < f.minComposite) return false\n    if (f.maxComposite !== undefined && max > f.maxComposite) return false\n  }\n  return true\n}\n\nfunction sha256(input: string): string {\n  return createHash('sha256').update(input).digest('hex').slice(0, 16)\n}\n\nfunction appendLine(path: string, line: string): void {\n  if (existsSync(path)) {\n    const existing = readFileSync(path, 'utf8')\n    writeFileSync(path, existing + line)\n  } else {\n    writeFileSync(path, line)\n  }\n}\n","/**\n * @experimental\n *\n * `runEval` — the simplest preset over `runCampaign`. No optimizer, no\n * gate, no auto-PR. Just: run scenarios through dispatch, score with\n * judges, return CampaignResult.\n *\n * The 80% case for consumers who want a scorecard, not an improvement loop.\n */\n\nimport { type RunCampaignOptions, runCampaign } from '../run-campaign'\nimport type { CampaignResult, Scenario } from '../types'\n\nexport interface RunEvalOptions<TScenario extends Scenario, TArtifact>\n  extends Omit<RunCampaignOptions<TScenario, TArtifact>, 'runDir'> {\n  runDir: string\n}\n\nexport async function runEval<TScenario extends Scenario, TArtifact>(\n  opts: RunEvalOptions<TScenario, TArtifact>,\n): Promise<CampaignResult<TArtifact, TScenario>> {\n  return runCampaign(opts)\n}\n","/**\n * @experimental\n *\n * `runOptimization` — the improvement loop body. Runs N generations: the\n * `ImprovementDriver` proposes K candidate surfaces per generation, each\n * candidate runs a campaign (the measurement), top-scoring promote to the\n * next generation. Driver-agnostic — the same loop runs an evolutionary\n * population mutator (`evolutionaryDriver`) or a reflective analyst\n * (`analystDriver`); they differ only in how `propose()` picks candidates.\n *\n * This is `runLoop`'s shape (plan → measure → decide) specialized to surface\n * improvement: `driver.propose` = plan, `runCampaign` = the measurement (which\n * runs the worker behind `dispatch`), the mean-composite ranking = the\n * validator, `driver.decide` = the stop check.\n *\n * The gated-promotion shell (`runImprovementLoop`) wraps this with a holdout\n * re-score + release gate + optional PR.\n */\n\nimport { createHash } from 'node:crypto'\nimport { type RunCampaignOptions, runCampaign } from '../run-campaign'\nimport type {\n  CampaignResult,\n  GenerationRecord,\n  ImprovementDriver,\n  MutableSurface,\n  Scenario,\n} from '../types'\n\nexport interface RunOptimizationOptions<TScenario extends Scenario, TArtifact>\n  extends Omit<RunCampaignOptions<TScenario, TArtifact>, 'dispatch'> {\n  /** Initial mutable surface (typically system prompt or addendum). */\n  baselineSurface: MutableSurface\n  /** Dispatcher that takes the CURRENT surface + scenario → artifact. */\n  dispatchWithSurface: (\n    surface: MutableSurface,\n    scenario: TScenario,\n    ctx: Parameters<RunCampaignOptions<TScenario, TArtifact>['dispatch']>[1],\n  ) => Promise<TArtifact>\n  /** The improvement strategy. Wrap a population `Mutator` via\n   *  `evolutionaryDriver({ mutator })`, or pass a reflective `analystDriver`. */\n  driver: ImprovementDriver\n  populationSize: number\n  maxGenerations: number\n  /** How many top-scoring candidates carry to the next generation. Default 2. */\n  promoteTopK?: number\n}\n\nexport interface RunOptimizationResult<TArtifact, TScenario extends Scenario> {\n  generations: Array<{\n    record: GenerationRecord\n    surfaces: Array<{\n      surfaceHash: string\n      surface: MutableSurface\n      campaign: CampaignResult<TArtifact, TScenario>\n    }>\n  }>\n  winnerSurface: MutableSurface\n  winnerSurfaceHash: string\n  baselineCampaign: CampaignResult<TArtifact, TScenario>\n}\n\nexport async function runOptimization<TScenario extends Scenario, TArtifact>(\n  opts: RunOptimizationOptions<TScenario, TArtifact>,\n): Promise<RunOptimizationResult<TArtifact, TScenario>> {\n  const promoteTopK = opts.promoteTopK ?? 2\n\n  // Baseline run\n  const baselineCampaign = await runCampaign<TScenario, TArtifact>({\n    ...opts,\n    dispatch: (scenario, ctx) => opts.dispatchWithSurface(opts.baselineSurface, scenario, ctx),\n    runDir: `${opts.runDir}/baseline`,\n  })\n\n  const generations: RunOptimizationResult<TArtifact, TScenario>['generations'] = []\n  const history: GenerationRecord[] = []\n  let currentSurfaces: MutableSurface[] = [opts.baselineSurface]\n  let winnerSurface = opts.baselineSurface\n  let winnerSurfaceHash = surfaceHash(opts.baselineSurface)\n  let winnerComposite = meanComposite(baselineCampaign)\n\n  for (let gen = 0; gen < opts.maxGenerations; gen++) {\n    // Decide: the driver may stop early based on accumulated history.\n    if (opts.driver.decide?.({ history }).stop) break\n\n    // Plan: the driver proposes N candidates from the current best surface,\n    // the accumulated generation history, and any external findings.\n    const candidates = await opts.driver.propose({\n      currentSurface: currentSurfaces[0] ?? opts.baselineSurface,\n      history,\n      findings: [],\n      populationSize: opts.populationSize,\n      generation: gen,\n      signal: new AbortController().signal,\n    })\n\n    // Run each candidate as its own campaign.\n    const surfaceResults: Array<{\n      surfaceHash: string\n      surface: MutableSurface\n      campaign: CampaignResult<TArtifact, TScenario>\n      composite: number\n    }> = []\n    for (let i = 0; i < candidates.length; i++) {\n      const surface = candidates[i] as MutableSurface\n      const hash = surfaceHash(surface)\n      const campaign = await runCampaign<TScenario, TArtifact>({\n        ...opts,\n        dispatch: (scenario, ctx) => opts.dispatchWithSurface(surface, scenario, ctx),\n        runDir: `${opts.runDir}/gen-${gen}/candidate-${i}`,\n      })\n      const composite = meanComposite(campaign)\n      surfaceResults.push({ surfaceHash: hash, surface, campaign, composite })\n    }\n\n    // Rank, promote top-K.\n    surfaceResults.sort((a, b) => b.composite - a.composite)\n    const promoted = surfaceResults.slice(0, promoteTopK)\n    currentSurfaces = promoted.map((p) => p.surface)\n    const top = surfaceResults[0]\n    if (top && top.composite > winnerComposite) {\n      winnerSurface = top.surface\n      winnerSurfaceHash = top.surfaceHash\n      winnerComposite = top.composite\n    }\n\n    const record: GenerationRecord = {\n      generationIndex: gen,\n      candidates: surfaceResults.map((s) => ({\n        surfaceHash: s.surfaceHash,\n        composite: s.composite,\n        ci95: [s.composite, s.composite] as [number, number],\n      })),\n      promoted: promoted.map((p) => p.surfaceHash),\n    }\n    history.push(record)\n    generations.push({\n      record,\n      surfaces: surfaceResults.map((s) => ({\n        surfaceHash: s.surfaceHash,\n        surface: s.surface,\n        campaign: s.campaign,\n      })),\n    })\n  }\n\n  return {\n    generations,\n    winnerSurface,\n    winnerSurfaceHash,\n    baselineCampaign,\n  }\n}\n\nexport function surfaceHash(surface: MutableSurface): string {\n  // Prompt/tool surfaces (string) hash by content; code surfaces hash by the\n  // worktree + base ref pair (the content lives in git, not in the string).\n  const material =\n    typeof surface === 'string'\n      ? surface\n      : JSON.stringify({\n          kind: surface.kind,\n          worktreeRef: surface.worktreeRef,\n          baseRef: surface.baseRef ?? null,\n        })\n  return createHash('sha256').update(material).digest('hex').slice(0, 16)\n}\n\nfunction meanComposite<TArtifact, TScenario extends Scenario>(\n  campaign: CampaignResult<TArtifact, TScenario>,\n): number {\n  const composites: number[] = []\n  for (const cell of campaign.cells) {\n    const cellComposites = Object.values(cell.judgeScores).map((s) => s.composite)\n    if (cellComposites.length > 0) {\n      composites.push(cellComposites.reduce((a, b) => a + b, 0) / cellComposites.length)\n    }\n  }\n  return composites.length === 0 ? 0 : composites.reduce((a, b) => a + b, 0) / composites.length\n}\n","/**\n * @experimental\n *\n * `runImprovementLoop` — the gated-promotion shell around the improvement\n * loop body (`runOptimization`). Drives candidate surfaces via the\n * `ImprovementDriver`, re-scores the winner against the baseline on a\n * holdout set, runs the release gate, and optionally opens a PR.\n *\n * Role vocabulary (see docs/design/loop-taxonomy.md):\n *   - DRIVER     = the `ImprovementDriver` (evolutionary GEPA mutator OR\n *                  reflective analyst). Proposes candidate SURFACES — the\n *                  worker's system prompt / tool config — NOT conversation\n *                  turns.\n *   - MEASUREMENT= `runCampaign`. Scores one surface by running the worker\n *                  (via `dispatch`) over scenarios and judging the output.\n *   - WORKER     = the agent harness in the sandbox, invoked behind the\n *                  topology-opaque `dispatch` seam — never referenced here.\n *\n * Distinct from `runLoop` in `@tangle-network/agent-runtime`, which is the\n * INNER conversation loop (driver↔workers in a sandbox). `runImprovementLoop`\n * is the OUTER loop: it improves the surface that those workers run.\n *\n * Hard-refuses unsafe configurations:\n *   - `tracing: 'off'` when a driver is wired (improvement is unattributable)\n *   - `autoOnPromote: 'config'` — DEFERRED to Pass B; v0.40 only ships\n *     `'pr'` and `'none'`.\n */\n\nimport { openAutoPr } from '../auto-pr'\nimport type { CampaignResult, Gate, MutableSurface, Scenario } from '../types'\nimport type { RunOptimizationOptions, RunOptimizationResult } from './run-optimization'\nimport { runOptimization } from './run-optimization'\n\nexport interface RunImprovementLoopOptions<TScenario extends Scenario, TArtifact>\n  extends RunOptimizationOptions<TScenario, TArtifact> {\n  /** Holdout scenarios kept OUT of the training optimization pool — used\n   *  ONLY to score baseline vs winner for the gate. */\n  holdoutScenarios: TScenario[]\n  /** Promotion gate. Substrate strongly recommends `defaultProductionGate`\n   *  for production wiring (composes red-team / reward-hacking / canary /\n   *  heldout). */\n  gate: Gate<TArtifact, TScenario>\n  /** What to do when the gate ships:\n   *   - `'pr'`: open a PR via `openAutoPr`\n   *   - `'none'`: just report — caller decides what to do with the winner\n   *  v0.40 does NOT support `'config'` (live-runtime self-mutation) —\n   *  deferred to Pass B behind safety stack. */\n  autoOnPromote: 'pr' | 'none'\n  /** GH owner / repo for the auto-PR. Required when autoOnPromote === 'pr'. */\n  ghOwner?: string\n  ghRepo?: string\n  /** Optional render override — substrate writes a diff-shaped surface; pass\n   *  a function to format the promoted surface differently. */\n  renderPromotedDiff?: (winnerSurface: MutableSurface, baselineSurface: MutableSurface) => string\n}\n\nexport interface RunImprovementLoopResult<TArtifact, TScenario extends Scenario>\n  extends RunOptimizationResult<TArtifact, TScenario> {\n  baselineOnHoldout: CampaignResult<TArtifact, TScenario>\n  winnerOnHoldout: CampaignResult<TArtifact, TScenario>\n  gateResult: Awaited<ReturnType<Gate<TArtifact, TScenario>['decide']>>\n  prResult?: ReturnType<typeof openAutoPr>\n}\n\nexport async function runImprovementLoop<TScenario extends Scenario, TArtifact>(\n  opts: RunImprovementLoopOptions<TScenario, TArtifact>,\n): Promise<RunImprovementLoopResult<TArtifact, TScenario>> {\n  // ── Safety pre-flight ─────────────────────────────────────────────\n  // biome-ignore lint/suspicious/noExplicitAny: Pass A reserved field for Pass B Shape B\n  if ((opts as any).autoOnPromote === 'config') {\n    throw new Error(\n      \"runImprovementLoop: autoOnPromote='config' is deferred to Pass B (requires shadow deploy + rollback + ensemble judges). Use 'pr' or 'none' in v0.40.\",\n    )\n  }\n  // Refuse tracing=off whenever a driver is wired. An improvement loop\n  // without traces is unattributable — its candidate surfaces cannot be\n  // cited back to the spans that motivated them, and the dataset flywheel\n  // (LabeledScenarioStore) that GEPA optimizes against goes unfed.\n  if (opts.tracing === 'off' && opts.driver) {\n    throw new Error(\n      \"runImprovementLoop: tracing='off' is forbidden when a driver is wired. The improvement loop without traces is unattributable; candidate surfaces cannot be cited back to spans and the optimization dataset goes unfed.\",\n    )\n  }\n  if (opts.autoOnPromote === 'pr' && (!opts.ghOwner || !opts.ghRepo)) {\n    throw new Error(\"runImprovementLoop: autoOnPromote='pr' requires ghOwner + ghRepo.\")\n  }\n\n  // ── (1) optimization loop produces a winner ────────────────────────\n  const optimization = await runOptimization(opts)\n\n  // ── (2) baseline + winner re-scored on the holdout set ─────────────\n  const { runCampaign } = await import('../run-campaign')\n\n  const baselineOnHoldout = await runCampaign<TScenario, TArtifact>({\n    ...opts,\n    scenarios: opts.holdoutScenarios,\n    dispatch: (scenario, ctx) => opts.dispatchWithSurface(opts.baselineSurface, scenario, ctx),\n    runDir: `${opts.runDir}/holdout-baseline`,\n  })\n\n  const winnerOnHoldout = await runCampaign<TScenario, TArtifact>({\n    ...opts,\n    scenarios: opts.holdoutScenarios,\n    dispatch: (scenario, ctx) =>\n      opts.dispatchWithSurface(optimization.winnerSurface, scenario, ctx),\n    runDir: `${opts.runDir}/holdout-winner`,\n  })\n\n  // ── (3) gate verdict ───────────────────────────────────────────────\n  const candidateArtifacts = new Map<string, TArtifact>()\n  const baselineArtifacts = new Map<string, TArtifact>()\n  const judgeScores = new Map<\n    string,\n    Record<string, { composite: number; dimensions: Record<string, number>; notes: string }>\n  >()\n  for (const cell of winnerOnHoldout.cells) {\n    candidateArtifacts.set(cell.cellId, cell.artifact)\n    judgeScores.set(cell.cellId, cell.judgeScores)\n  }\n  for (const cell of baselineOnHoldout.cells) {\n    baselineArtifacts.set(cell.cellId, cell.artifact)\n    const prior = judgeScores.get(cell.cellId) ?? {}\n    judgeScores.set(cell.cellId, { ...prior, ...cell.judgeScores })\n  }\n\n  const gateResult = await opts.gate.decide({\n    candidateArtifacts,\n    baselineArtifacts,\n    judgeScores,\n    scenarios: opts.holdoutScenarios,\n    cost: {\n      candidate: winnerOnHoldout.aggregates.totalCostUsd,\n      baseline: baselineOnHoldout.aggregates.totalCostUsd,\n    },\n    signal: new AbortController().signal,\n  })\n\n  // ── (4) auto-PR when gate ships ────────────────────────────────────\n  let prResult: ReturnType<typeof openAutoPr> | undefined\n  if (opts.autoOnPromote === 'pr' && gateResult.decision === 'ship') {\n    const render = opts.renderPromotedDiff ?? defaultRenderDiff\n    const promotedDiff = render(optimization.winnerSurface, opts.baselineSurface)\n    prResult = openAutoPr({\n      result: winnerOnHoldout,\n      gate: gateResult,\n      promotedDiff,\n      ghOwner: opts.ghOwner!,\n      ghRepo: opts.ghRepo!,\n    })\n  }\n\n  return {\n    ...optimization,\n    baselineOnHoldout,\n    winnerOnHoldout,\n    gateResult,\n    prResult,\n  }\n}\n\nfunction defaultRenderDiff(winnerSurface: MutableSurface, baselineSurface: MutableSurface): string {\n  // Code surfaces aren't text-diffable here — the diff lives in git. Render\n  // the worktree/base refs + summary so the PR body points at the change.\n  if (typeof winnerSurface !== 'string' || typeof baselineSurface !== 'string') {\n    const fmt = (s: MutableSurface): string =>\n      typeof s === 'string'\n        ? '(prompt surface)'\n        : `worktree=${s.worktreeRef}${s.baseRef ? ` base=${s.baseRef}` : ''}${s.summary ? `\\n${s.summary}` : ''}`\n    return `--- baseline\\n${fmt(baselineSurface)}\\n+++ winner\\n${fmt(winnerSurface)}`\n  }\n  const lines: string[] = []\n  lines.push('--- baseline')\n  lines.push('+++ winner')\n  for (const l of baselineSurface.split('\\n')) lines.push(`- ${l}`)\n  for (const l of winnerSurface.split('\\n')) lines.push(`+ ${l}`)\n  return lines.join('\\n')\n}\n"],"mappings":";;;;;;;;;;;;;;;;AAcA,SAAS,gBAAgB;AACzB,SAAS,qBAAqB;AAC9B,SAAS,cAAc;AACvB,SAAS,YAAY;AAiCd,SAAS,WACd,SACkB;AAClB,MAAI,QAAQ,KAAK,aAAa,QAAQ;AACpC,WAAO;AAAA,MACL,QAAQ;AAAA,MACR,QAAQ;AAAA,MACR,QAAQ,qBAAqB,QAAQ,KAAK,QAAQ;AAAA,IACpD;AAAA,EACF;AAEA,QAAM,SAAS,QAAQ,UAAU,CAAC,QAAQ,IAAI;AAC9C,QAAM,SAAS,QAAQ,UAAU,QAAQ,QAAQ,OAAO,aAAa,MAAM,GAAG,EAAE,CAAC;AACjF,QAAM,QACJ,QAAQ,SAAS,kBAAkB,QAAQ,OAAO,aAAa,MAAM,GAAG,CAAC,CAAC;AAE5E,QAAM,OAAO,aAAa,QAAQ,QAAQ,QAAQ,MAAM,QAAQ,YAAY;AAC5E,QAAM,WAAW,KAAK,OAAO,GAAG,gBAAgB,KAAK,IAAI,CAAC,KAAK;AAC/D,gBAAc,UAAU,IAAI;AAE5B,MAAI,QAAQ;AACV,WAAO;AAAA,MACL,QAAQ;AAAA,MACR,QAAQ;AAAA,MACR,QAAQ,0DAA0D,QAAQ,OAAO,IAAI,QAAQ,MAAM,WAAW,MAAM,aAAa,QAAQ;AAAA,IAC3I;AAAA,EACF;AAEA,QAAM,SAAS,QAAQ,UAAU;AACjC,QAAM,SAAS,OAAO;AAAA,IACpB;AAAA,IACA;AAAA,IACA;AAAA,IACA,GAAG,QAAQ,OAAO,IAAI,QAAQ,MAAM;AAAA,IACpC;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,EACF,CAAC;AACD,MAAI,OAAO,WAAW,GAAG;AACvB,WAAO;AAAA,MACL,QAAQ;AAAA,MACR,QAAQ;AAAA,MACR,QAAQ,6BAA6B,OAAO,MAAM,MAAM,OAAO,OAAO,MAAM,GAAG,GAAG,CAAC;AAAA,IACrF;AAAA,EACF;AACA,QAAM,QAAQ,OAAO,OAAO,KAAK;AACjC,SAAO,EAAE,QAAQ,MAAM,OAAO,QAAQ,OAAO,QAAQ,YAAY;AACnE;AAEA,SAAS,aACP,QACA,MACA,MACQ;AACR,QAAM,QAAkB,CAAC;AACzB,QAAM,KAAK,kDAAkD;AAC7D,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,mBAAmB,OAAO,YAAY,IAAI;AACrD,QAAM,KAAK,aAAa,OAAO,IAAI,EAAE;AACrC,QAAM,KAAK,iBAAiB,KAAK,MAAM,OAAO,aAAa,GAAI,CAAC,GAAG;AACnE,QAAM;AAAA,IACJ,uBAAuB,OAAO,WAAW,aAAa,YAAY,OAAO,WAAW,WAAW,aAAa,OAAO,WAAW,YAAY,YAAY,OAAO,WAAW,WAAW;AAAA,EACrL;AACA,QAAM,KAAK,qBAAqB,OAAO,WAAW,aAAa,QAAQ,CAAC,CAAC,EAAE;AAC3E,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,uBAAuB,KAAK,QAAQ,IAAI;AACnD,QAAM,KAAK,EAAE;AACb,aAAW,UAAU,KAAK,QAAS,OAAM,KAAK,KAAK,MAAM,EAAE;AAC3D,MAAI,KAAK,UAAU,OAAW,OAAM,KAAK,YAAY,KAAK,MAAM,QAAQ,CAAC,CAAC,EAAE;AAC5E,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,wBAAwB;AACnC,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,4BAA4B;AACvC,QAAM,KAAK,eAAe;AAC1B,aAAW,KAAK,KAAK,mBAAmB;AACtC,UAAM,SACJ,OAAO,EAAE,WAAW,WAChB,KAAK,UAAU,EAAE,MAAM,EAAE,MAAM,GAAG,EAAE,IACpC,OAAO,EAAE,MAAM,EAAE,MAAM,GAAG,EAAE;AAClC,UAAM,KAAK,KAAK,EAAE,IAAI,MAAM,EAAE,SAAS,WAAM,QAAG,MAAM,MAAM,IAAI;AAAA,EAClE;AACA,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,sBAAsB;AACjC,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,SAAS;AACpB,QAAM,KAAK,KAAK,MAAM,GAAG,GAAI,CAAC;AAC9B,QAAM,KAAK,KAAK;AAChB,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,yBAAyB;AACpC,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,6BAA6B;AACxC,QAAM,KAAK,mBAAmB;AAC9B,aAAW,CAAC,MAAM,GAAG,KAAK,OAAO,QAAQ,OAAO,WAAW,OAAO,GAAG;AACnE,UAAM;AAAA,MACJ,KAAK,IAAI,MAAM,IAAI,KAAK,QAAQ,CAAC,CAAC,OAAO,IAAI,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC,KAAK,IAAI,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC,OAAO,IAAI,CAAC;AAAA,IACxG;AAAA,EACF;AACA,SAAO,MAAM,KAAK,IAAI;AACxB;AAEA,SAAS,cAAc,MAAoE;AACzF,MAAI;AACF,UAAM,SAAS,SAAS,MAAM,KAAK,IAAI,QAAQ,EAAE,KAAK,GAAG,CAAC,IAAI;AAAA,MAC5D,KAAK,EAAE,GAAG,QAAQ,KAAK,UAAU,QAAQ,IAAI,oBAAoB,QAAQ,IAAI,YAAY,GAAG;AAAA,MAC5F,OAAO,CAAC,UAAU,QAAQ,MAAM;AAAA,IAClC,CAAC,EAAE,SAAS,MAAM;AAClB,WAAO,EAAE,QAAQ,QAAQ,IAAI,QAAQ,EAAE;AAAA,EACzC,SAAS,KAAK;AACZ,UAAM,IAAI;AACV,WAAO;AAAA,MACL,QAAQ,EAAE,QAAQ,SAAS,MAAM,KAAK;AAAA,MACtC,QAAQ,EAAE,QAAQ,SAAS,MAAM,KAAK;AAAA,MACtC,QAAQ,EAAE,UAAU;AAAA,IACtB;AAAA,EACF;AACF;AAEA,SAAS,SAAS,KAAqB;AACrC,MAAI,wBAAwB,KAAK,GAAG,EAAG,QAAO;AAC9C,SAAO,IAAI,IAAI,QAAQ,MAAM,KAAK,CAAC;AACrC;;;ACrJO,SAAS,mBACd,MAC8B;AAC9B,SAAO;AAAA,IACL,MAAM,gBAAgB,KAAK,QAAQ,IAAI;AAAA,IACvC,MAAM,QAAQ,EAAE,gBAAgB,UAAU,gBAAgB,OAAO,GAAG;AAClE,aAAO,KAAK,QAAQ,OAAO;AAAA,QACzB,UAAU,SAAS,SAAS,IAAI,WAAY,KAAK,YAAY,CAAC;AAAA,QAC9D;AAAA,QACA;AAAA,QACA;AAAA,MACF,CAAC;AAAA,IACH;AAAA,EACF;AACF;;;ACxBO,SAAS,eACX,OACyB;AAC5B,MAAI,MAAM,WAAW,GAAG;AACtB,UAAM,IAAI,MAAM,wCAAwC;AAAA,EAC1D;AACA,SAAO;AAAA,IACL,MAAM,YAAY,MAAM,IAAI,CAAC,MAAM,EAAE,IAAI,EAAE,KAAK,GAAG,CAAC;AAAA,IACpD,MAAM,OAAO,KAA6D;AACxE,YAAM,UAAwE,CAAC;AAC/E,iBAAW,QAAQ,OAAO;AACxB,cAAM,MAAM,MAAM,KAAK,OAAO,GAAG;AACjC,gBAAQ,KAAK,EAAE,MAAM,IAAI,CAAC;AAAA,MAC5B;AAQA,YAAM,YAAY,QAAQ,IAAI,CAAC,MAAM,EAAE,IAAI,QAAQ;AACnD,YAAM,UAAwB,UAAU,MAAM,CAAC,MAAM,MAAM,MAAM,IAC7D,SACA,UAAU,SAAS,cAAc,IAC/B,iBACA,UAAU,SAAS,eAAe,IAChC,kBACA,UAAU,SAAS,MAAM,IACvB,SACA;AAEV,YAAM,eAAe,QAAQ;AAAA,QAAQ,CAAC,MACpC,EAAE,IAAI,kBAAkB,SAAS,IAC7B,EAAE,IAAI,oBACN,CAAC,EAAE,MAAM,EAAE,KAAK,MAAM,QAAQ,EAAE,IAAI,aAAa,QAAQ,QAAQ,EAAE,IAAI,CAAC;AAAA,MAC9E;AAEA,YAAM,UAAU,QAAQ;AAAA,QAAQ,CAAC,MAC/B,EAAE,IAAI,QAAQ,IAAI,CAAC,WAAW,IAAI,EAAE,KAAK,IAAI,KAAK,MAAM,EAAE;AAAA,MAC5D;AAEA,aAAO;AAAA,QACL,UAAU;AAAA,QACV;AAAA,QACA,mBAAmB;AAAA,QACnB,OAAO,QAAQ,CAAC,GAAG,IAAI;AAAA,MACzB;AAAA,IACF;AAAA,EACF;AACF;;;ACpBO,SAAS,sBACd,SAC4B;AAC5B,QAAM,iBAAiB,QAAQ,kBAAkB;AACjD,QAAM,gBAAgB,QAAQ,8BAA8B;AAE5D,SAAO;AAAA,IACL,MAAM;AAAA,IACN,MAAM,OAAO,KAA6D;AACxE,YAAM,UAAoB,CAAC;AAC3B,YAAM,eAA0E,CAAC;AAGjF,YAAM,oBAAoB;AAAA,QACxB,IAAI;AAAA,QACJ,IAAI;AAAA,QACJ,QAAQ;AAAA,MACV;AACA,YAAM,qBAAqB;AAAA,QACzB,IAAI;AAAA,QACJ,IAAI;AAAA,QACJ,QAAQ;AAAA,MACV;AACA,YAAM,QAAQ,qBAAqB;AACnC,YAAM,cAAc,SAAS;AAC7B,mBAAa,KAAK;AAAA,QAChB,MAAM;AAAA,QACN,QAAQ;AAAA,QACR,QAAQ,EAAE,mBAAmB,oBAAoB,OAAO,eAAe;AAAA,MACzE,CAAC;AACD,UAAI,CAAC,aAAa;AAChB,gBAAQ,KAAK,iBAAiB,MAAM,QAAQ,CAAC,CAAC,gBAAgB,cAAc,EAAE;AAAA,MAChF;AAGA,YAAM,aACJ,QAAQ,cAAc,UACtB,IAAI,KAAK,YAAY,IAAI,KAAK,YAAY,QAAQ;AACpD,mBAAa,KAAK;AAAA,QAChB,MAAM;AAAA,QACN,QAAQ;AAAA,QACR,QAAQ;AAAA,UACN,cAAc,IAAI,KAAK;AAAA,UACvB,aAAa,IAAI,KAAK;AAAA,UACtB,WAAW,QAAQ;AAAA,QACrB;AAAA,MACF,CAAC;AACD,UAAI,CAAC,YAAY;AACf,gBAAQ;AAAA,UACN,UAAU,IAAI,KAAK,YAAY,IAAI,KAAK,UAAU,QAAQ,CAAC,CAAC,aAAa,QAAQ,SAAS;AAAA,QAC5F;AAAA,MACF;AAGA,YAAM,kBAAkB,QAAQ,iBAC5B,aAAa,IAAI,oBAAoB,QAAQ,cAAc,IAC3D,EAAE,QAAQ,MAAM,UAAU,CAAC,EAAE;AACjC,mBAAa,KAAK;AAAA,QAChB,MAAM;AAAA,QACN,QAAQ,gBAAgB;AAAA,QACxB,QAAQ;AAAA,UACN,UAAU,gBAAgB,SAAS;AAAA,UACnC,QAAQ,gBAAgB,SAAS,MAAM,GAAG,CAAC;AAAA,QAC7C;AAAA,MACF,CAAC;AACD,UAAI,CAAC,gBAAgB,QAAQ;AAC3B,gBAAQ,KAAK,0BAA0B,gBAAgB,SAAS,MAAM,YAAY;AAAA,MACpF;AAGA,UAAI,sBAAkD;AACtD,UAAI,QAAQ,cAAc,QAAQ,WAAW,UAAU,IAAI;AACzD,8BAAsB,oBAAoB,EAAE,MAAM,QAAQ,WAAW,CAAC;AAAA,MACxE;AAIA,YAAM,kBAAkB;AACxB,YAAM,kBAAkB,qBAAqB,YAAY,CAAC,GAAG;AAAA,QAC3D,CAAC,MAAM,EAAE,YAAY;AAAA,MACvB;AACA,YAAM,oBACJ,CAAC,uBACD,CAAC,iBACA,eAAe,WAAW,KAAK,oBAAoB,YAAY;AAClE,mBAAa,KAAK;AAAA,QAChB,MAAM;AAAA,QACN,QAAQ;AAAA,QACR,QAAQ,EAAE,QAAQ,qBAAqB,oBAAoB,eAAe,OAAO;AAAA,MACnF,CAAC;AACD,UAAI,CAAC,mBAAmB;AACtB,gBAAQ;AAAA,UACN,mCAAmC,eAAe,MAAM,sCAAsC,oBAAqB,OAAO;AAAA,QAC5H;AAAA,MACF;AAGA,UAAI,eAAoC;AACxC,UAAI,QAAQ,cAAc,QAAQ,WAAW,UAAU,IAAI;AACzD,uBAAe,YAAY,QAAQ,YAAY,CAAC,CAAC;AAAA,MACnD;AAEA,YAAM,eAAe,cAAc,UAAU,CAAC,GAAG,OAAO,CAAC,MAAM,EAAE,aAAa,OAAO;AACrF,YAAM,aAAa,YAAY,WAAW;AAC1C,mBAAa,KAAK;AAAA,QAChB,MAAM;AAAA,QACN,QAAQ;AAAA,QACR,QAAQ,EAAE,aAAa,cAAc,OAAO,UAAU,GAAG,aAAa,YAAY,OAAO;AAAA,MAC3F,CAAC;AACD,UAAI,CAAC,YAAY;AACf,gBAAQ,KAAK,wBAAwB,YAAY,MAAM,EAAE;AAAA,MAC3D;AAGA,YAAM,YAAY,aAAa,MAAM,CAAC,MAAM,EAAE,MAAM;AACpD,YAAM,WAAW,YAAY,SAAS;AAEtC,aAAO;AAAA,QACL;AAAA,QACA,SAAS,QAAQ,SAAS,IAAI,UAAU,CAAC,kBAAkB;AAAA,QAC3D,mBAAmB;AAAA,QACnB;AAAA,MACF;AAAA,IACF;AAAA,EACF;AACF;AAEA,SAAS,cACP,WACA,mBACA,WACQ;AACR,MAAI,CAAC,aAAa,UAAU,SAAS,EAAG,QAAO;AAC/C,QAAM,cAAc,IAAI,IAAI,UAAU,IAAI,CAAC,MAAM,EAAE,EAAE,CAAC;AACtD,QAAM,aAAuB,CAAC;AAC9B,aAAW,CAAC,QAAQ,MAAM,KAAK,mBAAmB;AAChD,UAAM,aAAa,OAAO,MAAM,GAAG,EAAE,CAAC,KAAK;AAC3C,QAAI,CAAC,YAAY,IAAI,UAAU,EAAG;AAClC,UAAM,iBAAiB,OAAO,OAAO,MAAM,EAAE,IAAI,CAAC,MAAM,EAAE,SAAS;AACnE,QAAI,eAAe,WAAW,EAAG;AACjC,eAAW,KAAK,eAAe,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,eAAe,MAAM;AAAA,EACnF;AACA,MAAI,WAAW,WAAW,EAAG,QAAO;AACpC,SAAO,WAAW,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,WAAW;AAC5D;AAEA,SAAS,aACP,WACA,SAC8E;AAC9E,QAAM,WAA0D,CAAC;AACjE,aAAW,CAAC,SAAS,QAAQ,KAAK,WAAW;AAC3C,UAAM,OAAO,YAAY,QAAQ;AACjC,QAAI,SAAS,OAAW;AACxB,eAAW,UAAU,SAAS;AAC5B,YAAM,UAAU,mBAAmB,MAAM,CAAC,GAAG,MAAM;AACnD,UAAI,CAAC,QAAQ,QAAQ;AACnB,iBAAS,KAAK,EAAE,YAAY,OAAO,IAAI,QAAQ,QAAQ,UAAU,wBAAwB,CAAC;AAAA,MAC5F;AAAA,IACF;AAAA,EACF;AACA,SAAO,EAAE,QAAQ,SAAS,WAAW,GAAG,SAAS;AACnD;AAEA,SAAS,YAAY,UAAuC;AAC1D,MAAI,OAAO,aAAa,SAAU,QAAO;AACzC,MAAI,YAAY,OAAO,aAAa,UAAU;AAC5C,UAAM,MAAM;AACZ,QAAI,OAAO,IAAI,SAAS,SAAU,QAAO,IAAI;AAC7C,QAAI,OAAO,IAAI,WAAW,SAAU,QAAO,IAAI;AAC/C,QAAI,OAAO,IAAI,YAAY,SAAU,QAAO,IAAI;AAAA,EAClD;AACA,SAAO;AACT;;;AC1MO,SAAS,YACd,SAC4B;AAC5B,QAAM,iBAAiB,QAAQ,kBAAkB;AACjD,SAAO;AAAA,IACL,MAAM;AAAA,IACN,MAAM,OAAO,KAA6D;AACxE,YAAM,cAAc,IAAI,IAAI,QAAQ,UAAU,IAAI,CAAC,MAAM,EAAE,EAAE,CAAC;AAC9D,YAAM,WAAW,iBAAiB,IAAI,mBAAmB,IAAI,aAAa,WAAW;AACrF,YAAM,YAAY,iBAAiB,IAAI,oBAAoB,IAAI,aAAa,WAAW;AACvF,YAAM,QAAQ,YAAY;AAC1B,YAAM,SAAS,SAAS;AACxB,aAAO;AAAA,QACL,UAAU,SAAS,SAAS;AAAA,QAC5B,SAAS,SACL,CAAC,kBAAkB,MAAM,QAAQ,CAAC,CAAC,WAAM,cAAc,EAAE,IACzD,CAAC,kBAAkB,MAAM,QAAQ,CAAC,CAAC,MAAM,cAAc,EAAE;AAAA,QAC7D,mBAAmB;AAAA,UACjB,EAAE,MAAM,eAAe,QAAQ,QAAQ,EAAE,UAAU,WAAW,OAAO,eAAe,EAAE;AAAA,QACxF;AAAA,QACA;AAAA,MACF;AAAA,IACF;AAAA,EACF;AACF;AAEA,SAAS,iBACP,WACA,mBACA,aACQ;AACR,MAAI,CAAC,aAAa,UAAU,SAAS,EAAG,QAAO;AAC/C,QAAM,aAAuB,CAAC;AAC9B,aAAW,CAAC,QAAQ,MAAM,KAAK,mBAAmB;AAChD,UAAM,aAAa,OAAO,MAAM,GAAG,EAAE,CAAC,KAAK;AAC3C,QAAI,CAAC,YAAY,IAAI,UAAU,EAAG;AAClC,UAAM,OAAO,OAAO,OAAO,MAAM,EAAE,IAAI,CAAC,MAAM,EAAE,SAAS;AACzD,QAAI,KAAK,SAAS,EAAG,YAAW,KAAK,KAAK,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,KAAK,MAAM;AAAA,EACpF;AACA,SAAO,WAAW,WAAW,IAAI,IAAI,WAAW,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,WAAW;AAC1F;;;AC1BA,SAAS,kBAAkB;AAC3B,SAAS,YAAY,WAAW,cAAc,iBAAAA,sBAAqB;AACnE,SAAS,QAAAC,aAAY;AAmBd,IAAM,4BAAN,cAAwC,MAAM;AAAA,EACnD,YACkB,MAChB,SACA;AACA,UAAM,OAAO;AAHG;AAIhB,SAAK,OAAO;AAAA,EACd;AAAA,EALkB;AAMpB;AAQO,IAAM,yBAAN,MAA6D;AAAA,EAIlE,YAA6B,SAAwC;AAAxC;AAC3B,QAAI,CAAC,WAAW,QAAQ,IAAI,EAAG,WAAU,QAAQ,MAAM,EAAE,WAAW,KAAK,CAAC;AAC1E,SAAK,MAAM,QAAQ,OAAO,KAAK;AAAA,EACjC;AAAA,EAH6B;AAAA,EAHZ;AAAA,EACA,aAAa,oBAAI,IAA4B;AAAA,EAO9D,MAAM,QAAQ,OAA4C;AACxD,SAAK,iBAAiB,KAAK;AAC3B,SAAK,gBAAgB,KAAK;AAC1B,UAAM,SAAS,KAAK,SAAS,KAAK;AAClC,UAAM,OAAO,KAAK,cAAc,MAAM,MAAM;AAC5C,UAAM,OAAO,GAAG,KAAK,UAAU,MAAM,CAAC;AAAA;AAItC,eAAW,MAAM,IAAI;AAAA,EACvB;AAAA,EAEA,MAAM,OAAO,MAAmE;AAC9E,QAAI,CAAC,KAAK,OAAO;AACf,YAAM,IAAI;AAAA,QACR;AAAA,QACA;AAAA,MACF;AAAA,IACF;AACA,QAAI,CAAC,KAAK,gBAAgB;AACxB,YAAM,IAAI;AAAA,QACR;AAAA,QACA;AAAA,MACF;AAAA,IACF;AAEA,UAAM,MAA+B,CAAC;AACtC,eAAW,UAAU,aAAa;AAGhC,UAAI,KAAK,UAAU,WAAW,WAAW,oBAAoB;AAC3D,cAAM,WAAW,qBAAqB,KAAK,QAAQ,QAAQ,kBAAkB;AAC7E,YAAI,CAAC,SAAU;AAAA,MACjB;AACA,YAAM,OAAO,KAAK,cAAc,MAAM;AACtC,UAAI,CAAC,WAAW,IAAI,EAAG;AACvB,YAAM,QAAQ,aAAa,MAAM,MAAM,EAAE,MAAM,IAAI,EAAE,OAAO,OAAO;AACnE,iBAAW,QAAQ,OAAO;AACxB,YAAI;AACJ,YAAI;AACF,mBAAS,KAAK,MAAM,IAAI;AAAA,QAC1B,QAAQ;AACN;AAAA,QACF;AACA,YAAI,CAAC,cAAc,QAAQ,MAAM,MAAM,EAAG;AAC1C,YAAI,KAAK,MAAM;AAAA,MACjB;AAAA,IACF;AAGA,QAAI,KAAK,CAAC,GAAG,MAAM;AACjB,UAAI,EAAE,eAAe,EAAE,WAAY,QAAO,EAAE,WAAW,cAAc,EAAE,UAAU;AACjF,aAAO,EAAE,WAAW,cAAc,EAAE,UAAU;AAAA,IAChD,CAAC;AAED,WAAO,IAAI,MAAM,GAAG,KAAK,KAAK;AAAA,EAChC;AAAA,EAEA,MAAM,OAAmF;AACvF,UAAM,WAAmC,CAAC;AAC1C,QAAI,QAAQ;AACZ,eAAW,UAAU,aAAa;AAChC,YAAM,OAAO,KAAK,cAAc,MAAM;AACtC,UAAI,CAAC,WAAW,IAAI,GAAG;AACrB,iBAAS,MAAM,IAAI;AACnB;AAAA,MACF;AACA,YAAM,QAAQ,aAAa,MAAM,MAAM,EAAE,MAAM,IAAI,EAAE,OAAO,OAAO,EAAE;AACrE,eAAS,MAAM,IAAI;AACnB,eAAS;AAAA,IACX;AAIA,WAAO,EAAE,OAAO,OAAO,MAAM,OAAO,SAAS;AAAA,EAC/C;AAAA,EAEQ,iBAAiB,OAAmC;AAC1D,QAAI,CAAC,MAAM,QAAQ;AACjB,YAAM,IAAI;AAAA,QACR;AAAA,QACA;AAAA,MACF;AAAA,IACF;AACA,QAAI,CAAC,MAAM,qBAAqB,MAAM,kBAAkB,WAAW,GAAG;AACpE,YAAM,IAAI;AAAA,QACR;AAAA,QACA;AAAA,MACF;AAAA,IACF;AACA,QAAI,CAAC,MAAM,YAAY;AACrB,YAAM,IAAI;AAAA,QACR;AAAA,QACA;AAAA,MACF;AAAA,IACF;AACA,QAAI,CAAC,MAAM,iBAAiB;AAC1B,YAAM,IAAI;AAAA,QACR;AAAA,QACA;AAAA,MACF;AAAA,IACF;AACA,QAAI,CAAC,YAAY,SAAS,MAAM,MAAM,GAAG;AACvC,YAAM,IAAI;AAAA,QACR;AAAA,QACA,+CAA+C,YAAY,KAAK,IAAI,CAAC;AAAA,MACvE;AAAA,IACF;AAAA,EACF;AAAA,EAEQ,gBAAgB,OAAmC;AACzD,UAAM,MAAM,KAAK,QAAQ;AACzB,QAAI,CAAC,OAAO,CAAC,MAAM,gBAAiB;AACpC,UAAM,MAAM,KAAK,IAAI;AACrB,UAAM,WAAW;AACjB,QAAI,QAAQ,KAAK,WAAW,IAAI,MAAM,eAAe;AACrD,QAAI,CAAC,SAAS,MAAM,MAAM,iBAAiB,UAAU;AACnD,cAAQ,EAAE,QAAQ,MAAM,iBAAiB,eAAe,KAAK,OAAO,EAAE;AACtE,WAAK,WAAW,IAAI,MAAM,iBAAiB,KAAK;AAAA,IAClD;AACA,QAAI,MAAM,SAAS,KAAK;AACtB,YAAM,IAAI;AAAA,QACR;AAAA,QACA,gCAAgC,MAAM,eAAe,aAAa,GAAG;AAAA,MACvE;AAAA,IACF;AACA,UAAM,SAAS;AAAA,EACjB;AAAA,EAEQ,SAAS,OAAoD;AACnE,UAAM,aAAa;AAAA,MACjB,KAAK,UAAU;AAAA,QACb,IAAI,MAAM,SAAS;AAAA,QACnB,KAAK,MAAM;AAAA,QACX,IAAI,MAAM;AAAA,QACV,KAAK,MAAM;AAAA,MACb,CAAC;AAAA,IACH;AAGA,WAAO;AAAA,MACL,GAAG;AAAA,MACH;AAAA,MACA,OAAO;AAAA,IACT;AAAA,EACF;AAAA,EAEQ,cAAc,QAAwB;AAC5C,WAAOA,MAAK,KAAK,QAAQ,MAAM,GAAG,MAAM,QAAQ;AAAA,EAClD;AACF;AAEA,IAAM,cAAgD;AAAA,EACpD;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AACF;AAEA,SAAS,qBACP,QACA,QACS;AACT,MAAI,CAAC,OAAQ,QAAO;AACpB,MAAI,MAAM,QAAQ,MAAM,EAAG,QAAO,OAAO,SAAS,MAAM;AACxD,SAAO,WAAW;AACpB;AAEA,SAAS,cACP,QACA,MACA,QACS;AAET,MAAI,KAAK,UAAU,WAAW,OAAO,cAAc,KAAK,eAAgB,QAAO;AAC/E,MAAI,KAAK,UAAU,UAAU,OAAO,aAAa,KAAK,eAAgB,QAAO;AAE7E,QAAM,IAAI,KAAK;AACf,MAAI,CAAC,EAAG,QAAO;AACf,MAAI,EAAE,QAAQ,OAAO,SAAS,SAAS,EAAE,KAAM,QAAO;AACtD,MAAI,EAAE,QAAQ;AACZ,UAAM,UAAU,MAAM,QAAQ,EAAE,MAAM,IAAI,EAAE,SAAS,CAAC,EAAE,MAAM;AAC9D,QAAI,CAAC,QAAQ,SAAS,MAAe,EAAG,QAAO;AAAA,EACjD;AACA,MAAI,EAAE,iBAAiB,UAAa,EAAE,iBAAiB,QAAW;AAChE,UAAM,aAAa,OAAO,OAAO,OAAO,WAAW,EAAE,IAAI,CAAC,MAAM,EAAE,SAAS;AAC3E,UAAM,MAAM,WAAW,WAAW,IAAI,IAAI,KAAK,IAAI,GAAG,UAAU;AAChE,QAAI,EAAE,iBAAiB,UAAa,MAAM,EAAE,aAAc,QAAO;AACjE,QAAI,EAAE,iBAAiB,UAAa,MAAM,EAAE,aAAc,QAAO;AAAA,EACnE;AACA,SAAO;AACT;AAEA,SAAS,OAAO,OAAuB;AACrC,SAAO,WAAW,QAAQ,EAAE,OAAO,KAAK,EAAE,OAAO,KAAK,EAAE,MAAM,GAAG,EAAE;AACrE;AAEA,SAAS,WAAW,MAAc,MAAoB;AACpD,MAAI,WAAW,IAAI,GAAG;AACpB,UAAM,WAAW,aAAa,MAAM,MAAM;AAC1C,IAAAD,eAAc,MAAM,WAAW,IAAI;AAAA,EACrC,OAAO;AACL,IAAAA,eAAc,MAAM,IAAI;AAAA,EAC1B;AACF;;;ACtQA,eAAsB,QACpB,MAC+C;AAC/C,SAAO,YAAY,IAAI;AACzB;;;ACHA,SAAS,cAAAE,mBAAkB;AA2C3B,eAAsB,gBACpB,MACsD;AACtD,QAAM,cAAc,KAAK,eAAe;AAGxC,QAAM,mBAAmB,MAAM,YAAkC;AAAA,IAC/D,GAAG;AAAA,IACH,UAAU,CAAC,UAAU,QAAQ,KAAK,oBAAoB,KAAK,iBAAiB,UAAU,GAAG;AAAA,IACzF,QAAQ,GAAG,KAAK,MAAM;AAAA,EACxB,CAAC;AAED,QAAM,cAA0E,CAAC;AACjF,QAAM,UAA8B,CAAC;AACrC,MAAI,kBAAoC,CAAC,KAAK,eAAe;AAC7D,MAAI,gBAAgB,KAAK;AACzB,MAAI,oBAAoB,YAAY,KAAK,eAAe;AACxD,MAAI,kBAAkBC,eAAc,gBAAgB;AAEpD,WAAS,MAAM,GAAG,MAAM,KAAK,gBAAgB,OAAO;AAElD,QAAI,KAAK,OAAO,SAAS,EAAE,QAAQ,CAAC,EAAE,KAAM;AAI5C,UAAM,aAAa,MAAM,KAAK,OAAO,QAAQ;AAAA,MAC3C,gBAAgB,gBAAgB,CAAC,KAAK,KAAK;AAAA,MAC3C;AAAA,MACA,UAAU,CAAC;AAAA,MACX,gBAAgB,KAAK;AAAA,MACrB,YAAY;AAAA,MACZ,QAAQ,IAAI,gBAAgB,EAAE;AAAA,IAChC,CAAC;AAGD,UAAM,iBAKD,CAAC;AACN,aAAS,IAAI,GAAG,IAAI,WAAW,QAAQ,KAAK;AAC1C,YAAM,UAAU,WAAW,CAAC;AAC5B,YAAM,OAAO,YAAY,OAAO;AAChC,YAAM,WAAW,MAAM,YAAkC;AAAA,QACvD,GAAG;AAAA,QACH,UAAU,CAAC,UAAU,QAAQ,KAAK,oBAAoB,SAAS,UAAU,GAAG;AAAA,QAC5E,QAAQ,GAAG,KAAK,MAAM,QAAQ,GAAG,cAAc,CAAC;AAAA,MAClD,CAAC;AACD,YAAM,YAAYA,eAAc,QAAQ;AACxC,qBAAe,KAAK,EAAE,aAAa,MAAM,SAAS,UAAU,UAAU,CAAC;AAAA,IACzE;AAGA,mBAAe,KAAK,CAAC,GAAG,MAAM,EAAE,YAAY,EAAE,SAAS;AACvD,UAAM,WAAW,eAAe,MAAM,GAAG,WAAW;AACpD,sBAAkB,SAAS,IAAI,CAAC,MAAM,EAAE,OAAO;AAC/C,UAAM,MAAM,eAAe,CAAC;AAC5B,QAAI,OAAO,IAAI,YAAY,iBAAiB;AAC1C,sBAAgB,IAAI;AACpB,0BAAoB,IAAI;AACxB,wBAAkB,IAAI;AAAA,IACxB;AAEA,UAAM,SAA2B;AAAA,MAC/B,iBAAiB;AAAA,MACjB,YAAY,eAAe,IAAI,CAAC,OAAO;AAAA,QACrC,aAAa,EAAE;AAAA,QACf,WAAW,EAAE;AAAA,QACb,MAAM,CAAC,EAAE,WAAW,EAAE,SAAS;AAAA,MACjC,EAAE;AAAA,MACF,UAAU,SAAS,IAAI,CAAC,MAAM,EAAE,WAAW;AAAA,IAC7C;AACA,YAAQ,KAAK,MAAM;AACnB,gBAAY,KAAK;AAAA,MACf;AAAA,MACA,UAAU,eAAe,IAAI,CAAC,OAAO;AAAA,QACnC,aAAa,EAAE;AAAA,QACf,SAAS,EAAE;AAAA,QACX,UAAU,EAAE;AAAA,MACd,EAAE;AAAA,IACJ,CAAC;AAAA,EACH;AAEA,SAAO;AAAA,IACL;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,EACF;AACF;AAEO,SAAS,YAAY,SAAiC;AAG3D,QAAM,WACJ,OAAO,YAAY,WACf,UACA,KAAK,UAAU;AAAA,IACb,MAAM,QAAQ;AAAA,IACd,aAAa,QAAQ;AAAA,IACrB,SAAS,QAAQ,WAAW;AAAA,EAC9B,CAAC;AACP,SAAOC,YAAW,QAAQ,EAAE,OAAO,QAAQ,EAAE,OAAO,KAAK,EAAE,MAAM,GAAG,EAAE;AACxE;AAEA,SAASD,eACP,UACQ;AACR,QAAM,aAAuB,CAAC;AAC9B,aAAW,QAAQ,SAAS,OAAO;AACjC,UAAM,iBAAiB,OAAO,OAAO,KAAK,WAAW,EAAE,IAAI,CAAC,MAAM,EAAE,SAAS;AAC7E,QAAI,eAAe,SAAS,GAAG;AAC7B,iBAAW,KAAK,eAAe,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,eAAe,MAAM;AAAA,IACnF;AAAA,EACF;AACA,SAAO,WAAW,WAAW,IAAI,IAAI,WAAW,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,WAAW;AAC1F;;;ACnHA,eAAsB,mBACpB,MACyD;AAGzD,MAAK,KAAa,kBAAkB,UAAU;AAC5C,UAAM,IAAI;AAAA,MACR;AAAA,IACF;AAAA,EACF;AAKA,MAAI,KAAK,YAAY,SAAS,KAAK,QAAQ;AACzC,UAAM,IAAI;AAAA,MACR;AAAA,IACF;AAAA,EACF;AACA,MAAI,KAAK,kBAAkB,SAAS,CAAC,KAAK,WAAW,CAAC,KAAK,SAAS;AAClE,UAAM,IAAI,MAAM,mEAAmE;AAAA,EACrF;AAGA,QAAM,eAAe,MAAM,gBAAgB,IAAI;AAG/C,QAAM,EAAE,aAAAE,aAAY,IAAI,MAAM,OAAO,6BAAiB;AAEtD,QAAM,oBAAoB,MAAMA,aAAkC;AAAA,IAChE,GAAG;AAAA,IACH,WAAW,KAAK;AAAA,IAChB,UAAU,CAAC,UAAU,QAAQ,KAAK,oBAAoB,KAAK,iBAAiB,UAAU,GAAG;AAAA,IACzF,QAAQ,GAAG,KAAK,MAAM;AAAA,EACxB,CAAC;AAED,QAAM,kBAAkB,MAAMA,aAAkC;AAAA,IAC9D,GAAG;AAAA,IACH,WAAW,KAAK;AAAA,IAChB,UAAU,CAAC,UAAU,QACnB,KAAK,oBAAoB,aAAa,eAAe,UAAU,GAAG;AAAA,IACpE,QAAQ,GAAG,KAAK,MAAM;AAAA,EACxB,CAAC;AAGD,QAAM,qBAAqB,oBAAI,IAAuB;AACtD,QAAM,oBAAoB,oBAAI,IAAuB;AACrD,QAAM,cAAc,oBAAI,IAGtB;AACF,aAAW,QAAQ,gBAAgB,OAAO;AACxC,uBAAmB,IAAI,KAAK,QAAQ,KAAK,QAAQ;AACjD,gBAAY,IAAI,KAAK,QAAQ,KAAK,WAAW;AAAA,EAC/C;AACA,aAAW,QAAQ,kBAAkB,OAAO;AAC1C,sBAAkB,IAAI,KAAK,QAAQ,KAAK,QAAQ;AAChD,UAAM,QAAQ,YAAY,IAAI,KAAK,MAAM,KAAK,CAAC;AAC/C,gBAAY,IAAI,KAAK,QAAQ,EAAE,GAAG,OAAO,GAAG,KAAK,YAAY,CAAC;AAAA,EAChE;AAEA,QAAM,aAAa,MAAM,KAAK,KAAK,OAAO;AAAA,IACxC;AAAA,IACA;AAAA,IACA;AAAA,IACA,WAAW,KAAK;AAAA,IAChB,MAAM;AAAA,MACJ,WAAW,gBAAgB,WAAW;AAAA,MACtC,UAAU,kBAAkB,WAAW;AAAA,IACzC;AAAA,IACA,QAAQ,IAAI,gBAAgB,EAAE;AAAA,EAChC,CAAC;AAGD,MAAI;AACJ,MAAI,KAAK,kBAAkB,QAAQ,WAAW,aAAa,QAAQ;AACjE,UAAM,SAAS,KAAK,sBAAsB;AAC1C,UAAM,eAAe,OAAO,aAAa,eAAe,KAAK,eAAe;AAC5E,eAAW,WAAW;AAAA,MACpB,QAAQ;AAAA,MACR,MAAM;AAAA,MACN;AAAA,MACA,SAAS,KAAK;AAAA,MACd,QAAQ,KAAK;AAAA,IACf,CAAC;AAAA,EACH;AAEA,SAAO;AAAA,IACL,GAAG;AAAA,IACH;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,EACF;AACF;AAEA,SAAS,kBAAkB,eAA+B,iBAAyC;AAGjG,MAAI,OAAO,kBAAkB,YAAY,OAAO,oBAAoB,UAAU;AAC5E,UAAM,MAAM,CAAC,MACX,OAAO,MAAM,WACT,qBACA,YAAY,EAAE,WAAW,GAAG,EAAE,UAAU,SAAS,EAAE,OAAO,KAAK,EAAE,GAAG,EAAE,UAAU;AAAA,EAAK,EAAE,OAAO,KAAK,EAAE;AAC3G,WAAO;AAAA,EAAiB,IAAI,eAAe,CAAC;AAAA;AAAA,EAAiB,IAAI,aAAa,CAAC;AAAA,EACjF;AACA,QAAM,QAAkB,CAAC;AACzB,QAAM,KAAK,cAAc;AACzB,QAAM,KAAK,YAAY;AACvB,aAAW,KAAK,gBAAgB,MAAM,IAAI,EAAG,OAAM,KAAK,KAAK,CAAC,EAAE;AAChE,aAAW,KAAK,cAAc,MAAM,IAAI,EAAG,OAAM,KAAK,KAAK,CAAC,EAAE;AAC9D,SAAO,MAAM,KAAK,IAAI;AACxB;","names":["writeFileSync","join","createHash","meanComposite","createHash","runCampaign"]}
+{"version":3,"sources":["../../src/campaign/auto-pr.ts","../../src/campaign/drivers/evolutionary.ts","../../src/campaign/gates/compose.ts","../../src/campaign/gates/default-production-gate.ts","../../src/campaign/gates/heldout-gate.ts","../../src/campaign/labeled-store/fs-adapter.ts","../../src/campaign/presets/run-eval.ts","../../src/campaign/presets/run-optimization.ts","../../src/campaign/presets/run-improvement-loop.ts","../../src/campaign/worktree/index.ts"],"sourcesContent":["/**\n * @experimental\n *\n * `openAutoPr` — thin shell-out helper for the `runImprovementLoop` preset's\n * `autoOnPromote: 'pr'` mode. Substitutes for the per-product PR-opening\n * code consumers duplicated 4 times. The PR body includes the campaign's\n * manifest hash, gate verdict, and scorecard summary so reviewers can see\n * exactly what was promoted + why.\n *\n * NOT a deploy mechanism — this only OPENS a PR. The human reviews + merges.\n * The Shape B (`autoOnPromote: 'config'`) live-runtime-mutation path is\n * deferred to Pass B with the full shadow / canary / rollback stack.\n */\n\nimport { execSync } from 'node:child_process'\nimport { writeFileSync } from 'node:fs'\nimport { tmpdir } from 'node:os'\nimport { join } from 'node:path'\nimport type { CampaignResult, GateResult, Scenario } from './types'\n\nexport interface OpenAutoPrOptions<TArtifact, TScenario extends Scenario> {\n  /** Campaign result to attach to the PR. */\n  result: CampaignResult<TArtifact, TScenario>\n  /** Gate verdict explaining the promotion. Substrate refuses to open a PR\n   *  when `gate.decision !== 'ship'` — fails loud. */\n  gate: GateResult\n  /** Promoted surface diff — typically the new system prompt addendum or\n   *  full profile diff. Substrate writes it as the PR body. */\n  promotedDiff: string\n  /** GH owner/repo target (e.g., `tangle-network/gtm-agent`). */\n  ghOwner: string\n  ghRepo: string\n  /** Branch name for the PR. Default `auto/<manifestHash[:12]>`. */\n  branch?: string\n  /** PR title. Default includes manifest hash. */\n  title?: string\n  /** Whether to actually open the PR or just dry-run. Default reads\n   *  `GH_AUTO_PR_TOKEN` env — present = open, absent = dry-run. */\n  dryRun?: boolean\n  /** Test seam — substitute `gh pr create` invocation. */\n  ghExec?: (args: string[]) => { stdout: string; stderr: string; status: number }\n}\n\nexport interface OpenAutoPrResult {\n  opened: boolean\n  prUrl?: string\n  dryRun: boolean\n  reason: string\n}\n\nexport function openAutoPr<TArtifact, TScenario extends Scenario>(\n  options: OpenAutoPrOptions<TArtifact, TScenario>,\n): OpenAutoPrResult {\n  if (options.gate.decision !== 'ship') {\n    return {\n      opened: false,\n      dryRun: false,\n      reason: `gate verdict was \"${options.gate.decision}\" — refusing to open PR`,\n    }\n  }\n\n  const dryRun = options.dryRun ?? !process.env.GH_AUTO_PR_TOKEN\n  const branch = options.branch ?? `auto/${options.result.manifestHash.slice(0, 12)}`\n  const title =\n    options.title ?? `auto: campaign ${options.result.manifestHash.slice(0, 8)} promoted by gate`\n\n  const body = renderPrBody(options.result, options.gate, options.promotedDiff)\n  const bodyPath = join(tmpdir(), `auto-pr-body-${Date.now()}.md`)\n  writeFileSync(bodyPath, body)\n\n  if (dryRun) {\n    return {\n      opened: false,\n      dryRun: true,\n      reason: `dry-run (GH_AUTO_PR_TOKEN not set). Would create PR on ${options.ghOwner}/${options.ghRepo} branch ${branch}. Body at ${bodyPath}.`,\n    }\n  }\n\n  const ghExec = options.ghExec ?? defaultGhExec\n  const result = ghExec([\n    'pr',\n    'create',\n    '--repo',\n    `${options.ghOwner}/${options.ghRepo}`,\n    '--head',\n    branch,\n    '--title',\n    title,\n    '--body-file',\n    bodyPath,\n  ])\n  if (result.status !== 0) {\n    return {\n      opened: false,\n      dryRun: false,\n      reason: `gh pr create failed (exit ${result.status}): ${result.stderr.slice(0, 400)}`,\n    }\n  }\n  const prUrl = result.stdout.trim()\n  return { opened: true, prUrl, dryRun: false, reason: 'PR opened' }\n}\n\nfunction renderPrBody<TArtifact, TScenario extends Scenario>(\n  result: CampaignResult<TArtifact, TScenario>,\n  gate: GateResult,\n  diff: string,\n): string {\n  const lines: string[] = []\n  lines.push(`## Automated promotion by \\`runImprovementLoop\\``)\n  lines.push('')\n  lines.push(`**Manifest**: \\`${result.manifestHash}\\``)\n  lines.push(`**Seed**: ${result.seed}`)\n  lines.push(`**Duration**: ${Math.round(result.durationMs / 1000)}s`)\n  lines.push(\n    `**Cells**: executed ${result.aggregates.cellsExecuted}, cached ${result.aggregates.cellsCached}, skipped ${result.aggregates.cellsSkipped}, failed ${result.aggregates.cellsFailed}`,\n  )\n  lines.push(`**Total spend**: $${result.aggregates.totalCostUsd.toFixed(2)}`)\n  lines.push('')\n  lines.push(`### Gate verdict: \\`${gate.decision}\\``)\n  lines.push('')\n  for (const reason of gate.reasons) lines.push(`- ${reason}`)\n  if (gate.delta !== undefined) lines.push(`- delta: ${gate.delta.toFixed(3)}`)\n  lines.push('')\n  lines.push('### Contributing gates')\n  lines.push('')\n  lines.push('| gate | passed | detail |')\n  lines.push('|---|---|---|')\n  for (const c of gate.contributingGates) {\n    const detail =\n      typeof c.detail === 'object'\n        ? JSON.stringify(c.detail).slice(0, 80)\n        : String(c.detail).slice(0, 80)\n    lines.push(`| ${c.name} | ${c.passed ? '✓' : '✗'} | ${detail} |`)\n  }\n  lines.push('')\n  lines.push('### Promoted surface')\n  lines.push('')\n  lines.push('```diff')\n  lines.push(diff.slice(0, 8000))\n  lines.push('```')\n  lines.push('')\n  lines.push('### By-judge aggregates')\n  lines.push('')\n  lines.push('| judge | mean | ci95 | n |')\n  lines.push('|---|---|---|---|')\n  for (const [name, agg] of Object.entries(result.aggregates.byJudge)) {\n    lines.push(\n      `| ${name} | ${agg.mean.toFixed(3)} | [${agg.ci95[0].toFixed(3)}, ${agg.ci95[1].toFixed(3)}] | ${agg.n} |`,\n    )\n  }\n  return lines.join('\\n')\n}\n\nfunction defaultGhExec(args: string[]): { stdout: string; stderr: string; status: number } {\n  try {\n    const stdout = execSync(`gh ${args.map(quoteArg).join(' ')}`, {\n      env: { ...process.env, GH_TOKEN: process.env.GH_AUTO_PR_TOKEN ?? process.env.GH_TOKEN ?? '' },\n      stdio: ['ignore', 'pipe', 'pipe'],\n    }).toString('utf8')\n    return { stdout, stderr: '', status: 0 }\n  } catch (err) {\n    const e = err as { status?: number; stderr?: Buffer; stdout?: Buffer }\n    return {\n      stdout: e.stdout?.toString('utf8') ?? '',\n      stderr: e.stderr?.toString('utf8') ?? '',\n      status: e.status ?? 1,\n    }\n  }\n}\n\nfunction quoteArg(arg: string): string {\n  if (/^[a-zA-Z0-9_/\\-:.@]+$/.test(arg)) return arg\n  return `\"${arg.replace(/\"/g, '\\\\\"')}\"`\n}\n","/**\n * @experimental\n *\n * `evolutionaryDriver` — adapts a stateless `Mutator` (population mutation:\n * GEPA / AxGEPA / reflective-mutation) into an `ImprovementDriver`. This is\n * the evolutionary strategy: each generation, mutate the current best surface\n * into N candidates, measure, select. No generation memory beyond the current\n * surface; the loop body handles ranking + promotion.\n *\n * The reflective alternative — `analystDriver` — is consumer-wired from\n * `@tangle-network/agent-runtime`'s `runAnalystLoop`: it reasons over the\n * full generation history + trace findings to propose targeted edits rather\n * than blind mutations. Both conform to `ImprovementDriver`; the improvement\n * loop is identical regardless of which drives it.\n */\n\nimport type { ImprovementDriver, Mutator } from '../types'\n\nexport interface EvolutionaryDriverOptions<TFindings = unknown> {\n  mutator: Mutator<TFindings>\n  /** External findings fed to the mutator each generation. Default: []. */\n  findings?: TFindings[]\n}\n\nexport function evolutionaryDriver<TFindings = unknown>(\n  opts: EvolutionaryDriverOptions<TFindings>,\n): ImprovementDriver<TFindings> {\n  return {\n    kind: `evolutionary:${opts.mutator.kind}`,\n    async propose({ currentSurface, findings, populationSize, signal }) {\n      return opts.mutator.mutate({\n        findings: findings.length > 0 ? findings : (opts.findings ?? []),\n        currentSurface,\n        populationSize,\n        signal,\n      })\n    },\n  }\n}\n","/**\n * @experimental\n *\n * Compose multiple `Gate` implementations — every gate must pass for the\n * composite to ship. Closes the alignment reviewer's \"default-only\n * heldOutGate + costGate would happily promote a reward-hacked prompt\"\n * concern by making safety gates first-class composable defaults.\n */\n\nimport type { Gate, GateContext, GateDecision, GateResult, Scenario } from '../types'\n\n/** Compose gates — all must `ship` for the composite to `ship`. First\n *  non-ship verdict short-circuits the composite verdict, but ALL gates run\n *  (so the result records every gate's reason — useful for diagnostics). */\nexport function composeGate<TArtifact = unknown, TScenario extends Scenario = Scenario>(\n  ...gates: Array<Gate<TArtifact, TScenario>>\n): Gate<TArtifact, TScenario> {\n  if (gates.length === 0) {\n    throw new Error('composeGate requires at least one gate')\n  }\n  return {\n    name: `composed(${gates.map((g) => g.name).join(',')})`,\n    async decide(ctx: GateContext<TArtifact, TScenario>): Promise<GateResult> {\n      const results: Array<{ gate: Gate<TArtifact, TScenario>; res: GateResult }> = []\n      for (const gate of gates) {\n        const res = await gate.decide(ctx)\n        results.push({ gate, res })\n      }\n\n      // Substrate-wide verdict policy:\n      //   - all 'ship' → 'ship'\n      //   - any 'arch_ceiling' → 'arch_ceiling' (architectural ceiling beats other holds)\n      //   - any 'model_ceiling' → 'model_ceiling'\n      //   - any 'hold' → 'hold'\n      //   - else 'need_more_work'\n      const decisions = results.map((r) => r.res.decision)\n      const overall: GateDecision = decisions.every((d) => d === 'ship')\n        ? 'ship'\n        : decisions.includes('arch_ceiling')\n          ? 'arch_ceiling'\n          : decisions.includes('model_ceiling')\n            ? 'model_ceiling'\n            : decisions.includes('hold')\n              ? 'hold'\n              : 'need_more_work'\n\n      const contributing = results.flatMap((r) =>\n        r.res.contributingGates.length > 0\n          ? r.res.contributingGates\n          : [{ name: r.gate.name, passed: r.res.decision === 'ship', detail: r.res }],\n      )\n\n      const reasons = results.flatMap((r) =>\n        r.res.reasons.map((reason) => `[${r.gate.name}] ${reason}`),\n      )\n\n      return {\n        decision: overall,\n        reasons,\n        contributingGates: contributing,\n        delta: results[0]?.res.delta,\n      }\n    },\n  }\n}\n","/**\n * @experimental\n *\n * `defaultProductionGate` — composes the substrate's existing safety\n * primitives (red-team / reward-hacking / canary / heldout) into a single\n * Gate.decide shape. Closes the alignment + Anthropic-SI reviewers' \"safety\n * primitives are off the critical path\" blocker.\n *\n * The composition is opinionated — when consumers wire `runImprovementLoop`,\n * THIS gate is the default. Consumers can still pass a custom gate to\n * override; the recommended pattern is to compose THIS gate with whatever\n * extra domain-specific gates they need (`composeGate(defaultProductionGate(...), customGate)`).\n */\n\nimport type { RunRecord } from '@tangle-network/agent-runtime'\nimport type { CanaryReport } from '../../canary'\nimport { runCanaries } from '../../canary'\nimport type { RedTeamCase } from '../../red-team'\nimport { scoreRedTeamOutput } from '../../red-team'\nimport type { RewardHackingReport } from '../../rl/reward-hacking'\nimport { detectRewardHacking } from '../../rl/reward-hacking'\nimport type { Gate, GateContext, GateResult, Scenario } from '../types'\n\nexport interface DefaultProductionGateOptions {\n  /** Required: scenarios held out from training; substrate compares\n   *  candidate-on-holdout vs baseline-on-holdout. */\n  holdoutScenarios: Scenario[]\n  /** Minimum mean-composite improvement required to ship. Default 0.5. */\n  deltaThreshold?: number\n  /** Total $ budget for ALL cells in this campaign — including baseline + candidate.\n   *  Composite verdict refuses to ship when spend exceeded budget. */\n  budgetUsd?: number\n  /** Red-team cases to probe candidate outputs against. When omitted the\n   *  substrate uses `DEFAULT_RED_TEAM_CORPUS`. Provide a domain-specific\n   *  battery for tighter coverage. */\n  redTeamBattery?: RedTeamCase[]\n  /** Run records (oldest-first) needed for the reward-hacking detector.\n   *  Substrate populates from prior production-loop generations. */\n  recentRuns?: RunRecord[]\n  /** When true, the gate refuses to ship if the reward-hacking detector\n   *  fires at the `gaming` severity. Default true. */\n  blockOnRewardHackingGaming?: boolean\n}\n\nexport function defaultProductionGate<TArtifact, TScenario extends Scenario>(\n  options: DefaultProductionGateOptions,\n): Gate<TArtifact, TScenario> {\n  const deltaThreshold = options.deltaThreshold ?? 0.5\n  const blockOnGaming = options.blockOnRewardHackingGaming ?? true\n\n  return {\n    name: 'defaultProductionGate',\n    async decide(ctx: GateContext<TArtifact, TScenario>): Promise<GateResult> {\n      const reasons: string[] = []\n      const contributing: Array<{ name: string; passed: boolean; detail: unknown }> = []\n\n      // ── (1) heldout composite delta ─────────────────────────────────\n      const baselineComposite = meanComposite(\n        ctx.baselineArtifacts,\n        ctx.judgeScores,\n        options.holdoutScenarios,\n      )\n      const candidateComposite = meanComposite(\n        ctx.candidateArtifacts,\n        ctx.judgeScores,\n        options.holdoutScenarios,\n      )\n      const delta = candidateComposite - baselineComposite\n      const heldoutPass = delta >= deltaThreshold\n      contributing.push({\n        name: 'heldout-delta',\n        passed: heldoutPass,\n        detail: { baselineComposite, candidateComposite, delta, deltaThreshold },\n      })\n      if (!heldoutPass) {\n        reasons.push(`heldout delta ${delta.toFixed(3)} < threshold ${deltaThreshold}`)\n      }\n\n      // ── (2) budget gate ─────────────────────────────────────────────\n      const budgetPass =\n        options.budgetUsd === undefined ||\n        ctx.cost.candidate + ctx.cost.baseline <= options.budgetUsd\n      contributing.push({\n        name: 'budget',\n        passed: budgetPass,\n        detail: {\n          candidateUsd: ctx.cost.candidate,\n          baselineUsd: ctx.cost.baseline,\n          budgetUsd: options.budgetUsd,\n        },\n      })\n      if (!budgetPass) {\n        reasons.push(\n          `spend ${(ctx.cost.candidate + ctx.cost.baseline).toFixed(2)} > budget ${options.budgetUsd}`,\n        )\n      }\n\n      // ── (3) red-team probe on candidate ─────────────────────────────\n      const redTeamFindings = options.redTeamBattery\n        ? probeRedTeam(ctx.candidateArtifacts, options.redTeamBattery)\n        : { passed: true, findings: [] }\n      contributing.push({\n        name: 'red-team',\n        passed: redTeamFindings.passed,\n        detail: {\n          failures: redTeamFindings.findings.length,\n          sample: redTeamFindings.findings.slice(0, 3),\n        },\n      })\n      if (!redTeamFindings.passed) {\n        reasons.push(`red-team probe failed (${redTeamFindings.findings.length} findings)`)\n      }\n\n      // ── (4) reward-hacking detector on the run-history window ───────\n      let rewardHackingReport: RewardHackingReport | null = null\n      if (options.recentRuns && options.recentRuns.length >= 10) {\n        rewardHackingReport = detectRewardHacking({ runs: options.recentRuns })\n      }\n      // reward-hacking severity is numeric (0..1). \"gaming\" threshold per\n      // detectRewardHacking defaults = 0.6. Block when ANY finding is at\n      // gaming threshold OR the report verdict is 'gaming'.\n      const gamingThreshold = 0.6\n      const gamingFindings = (rewardHackingReport?.findings ?? []).filter(\n        (f) => f.severity >= gamingThreshold,\n      )\n      const rewardHackingPass =\n        !rewardHackingReport ||\n        !blockOnGaming ||\n        (gamingFindings.length === 0 && rewardHackingReport.verdict !== 'gaming')\n      contributing.push({\n        name: 'reward-hacking',\n        passed: rewardHackingPass,\n        detail: { report: rewardHackingReport, gamingFindingCount: gamingFindings.length },\n      })\n      if (!rewardHackingPass) {\n        reasons.push(\n          `reward-hacking detector flagged ${gamingFindings.length} gaming-severity findings (verdict=${rewardHackingReport!.verdict})`,\n        )\n      }\n\n      // ── (5) canary check on runs ────────────────────────────────────\n      let canaryReport: CanaryReport | null = null\n      if (options.recentRuns && options.recentRuns.length >= 10) {\n        canaryReport = runCanaries(options.recentRuns, {})\n      }\n      // CanarySeverity is 'info' | 'warn' | 'error' — block on 'error'.\n      const errorAlerts = (canaryReport?.alerts ?? []).filter((a) => a.severity === 'error')\n      const canaryPass = errorAlerts.length === 0\n      contributing.push({\n        name: 'canary',\n        passed: canaryPass,\n        detail: { totalAlerts: canaryReport?.alerts.length ?? 0, errorAlerts: errorAlerts.length },\n      })\n      if (!canaryPass) {\n        reasons.push(`canary error alerts: ${errorAlerts.length}`)\n      }\n\n      // ── Verdict ─────────────────────────────────────────────────────\n      const allPassed = contributing.every((c) => c.passed)\n      const decision = allPassed ? 'ship' : 'hold'\n\n      return {\n        decision,\n        reasons: reasons.length > 0 ? reasons : ['all gates passed'],\n        contributingGates: contributing,\n        delta,\n      }\n    },\n  }\n}\n\nfunction meanComposite<TArtifact, TScenario extends Scenario>(\n  artifacts: Map<string, TArtifact> | undefined,\n  judgeScoresByCell: Map<string, Record<string, { composite: number }>>,\n  scenarios: TScenario[],\n): number {\n  if (!artifacts || artifacts.size === 0) return 0\n  const scenarioIds = new Set(scenarios.map((s) => s.id))\n  const composites: number[] = []\n  for (const [cellId, scores] of judgeScoresByCell) {\n    const scenarioId = cellId.split(':')[0] ?? ''\n    if (!scenarioIds.has(scenarioId)) continue\n    const cellComposites = Object.values(scores).map((s) => s.composite)\n    if (cellComposites.length === 0) continue\n    composites.push(cellComposites.reduce((a, b) => a + b, 0) / cellComposites.length)\n  }\n  if (composites.length === 0) return 0\n  return composites.reduce((a, b) => a + b, 0) / composites.length\n}\n\nfunction probeRedTeam<TArtifact>(\n  artifacts: Map<string, TArtifact>,\n  battery: RedTeamCase[],\n): { passed: boolean; findings: Array<{ scenarioId: string; reason: string }> } {\n  const findings: Array<{ scenarioId: string; reason: string }> = []\n  for (const [_cellId, artifact] of artifacts) {\n    const text = extractText(artifact)\n    if (text === undefined) continue\n    for (const rtCase of battery) {\n      const finding = scoreRedTeamOutput(text, [], rtCase)\n      if (!finding.passed) {\n        findings.push({ scenarioId: rtCase.id, reason: finding.reason ?? 'red-team probe failed' })\n      }\n    }\n  }\n  return { passed: findings.length === 0, findings }\n}\n\nfunction extractText(artifact: unknown): string | undefined {\n  if (typeof artifact === 'string') return artifact\n  if (artifact && typeof artifact === 'object') {\n    const rec = artifact as Record<string, unknown>\n    if (typeof rec.text === 'string') return rec.text\n    if (typeof rec.output === 'string') return rec.output\n    if (typeof rec.content === 'string') return rec.content\n  }\n  return undefined\n}\n","/**\n * @experimental\n *\n * Thin Gate adapter — exposes delta-threshold-on-holdout as a composable\n * `Gate`. Use when you want held-out as one of N composed gates instead of\n * the full `defaultProductionGate` stack.\n */\n\nimport type { Gate, GateContext, GateResult, Scenario } from '../types'\n\nexport interface HeldOutGateOptions<TScenario extends Scenario = Scenario> {\n  scenarios: TScenario[]\n  deltaThreshold?: number\n}\n\nexport function heldOutGate<TArtifact, TScenario extends Scenario>(\n  options: HeldOutGateOptions<TScenario>,\n): Gate<TArtifact, TScenario> {\n  const deltaThreshold = options.deltaThreshold ?? 0.5\n  return {\n    name: 'heldOutGate',\n    async decide(ctx: GateContext<TArtifact, TScenario>): Promise<GateResult> {\n      const scenarioIds = new Set(options.scenarios.map((s) => s.id))\n      const baseline = meanForScenarios(ctx.baselineArtifacts, ctx.judgeScores, scenarioIds)\n      const candidate = meanForScenarios(ctx.candidateArtifacts, ctx.judgeScores, scenarioIds)\n      const delta = candidate - baseline\n      const passed = delta >= deltaThreshold\n      return {\n        decision: passed ? 'ship' : 'hold',\n        reasons: passed\n          ? [`held-out delta ${delta.toFixed(3)} ≥ ${deltaThreshold}`]\n          : [`held-out delta ${delta.toFixed(3)} < ${deltaThreshold}`],\n        contributingGates: [\n          { name: 'heldOutGate', passed, detail: { baseline, candidate, delta, deltaThreshold } },\n        ],\n        delta,\n      }\n    },\n  }\n}\n\nfunction meanForScenarios<TArtifact>(\n  artifacts: Map<string, TArtifact> | undefined,\n  judgeScoresByCell: Map<string, Record<string, { composite: number }>>,\n  scenarioIds: Set<string>,\n): number {\n  if (!artifacts || artifacts.size === 0) return 0\n  const composites: number[] = []\n  for (const [cellId, scores] of judgeScoresByCell) {\n    const scenarioId = cellId.split(':')[0] ?? ''\n    if (!scenarioIds.has(scenarioId)) continue\n    const vals = Object.values(scores).map((s) => s.composite)\n    if (vals.length > 0) composites.push(vals.reduce((a, b) => a + b, 0) / vals.length)\n  }\n  return composites.length === 0 ? 0 : composites.reduce((a, b) => a + b, 0) / composites.length\n}\n","/**\n * @experimental\n *\n * Filesystem `LabeledScenarioStore` adapter. The default capture sink for\n * traces + eval artifacts. Production deployments typically swap for a\n * Turso/SQLite adapter (same interface).\n *\n * Records land as one JSONL file per source under `<root>/<source>.jsonl`.\n * Each line is a `LabeledScenarioRecord`. Append-only — no in-place edits.\n *\n * Safety properties enforced at write-time:\n *\n *   - **Provenance required**: writes without `source`, `sourceVersionHash`,\n *     `capturedAt`, `redactionStatus` are rejected. Closes the alignment\n *     reviewer's data-poisoning gap.\n *   - **Per-source rate limits**: optional `rateLimitBucket` + `maxWritesPerMinute`\n *     stops a single tenant/source from flooding the store.\n *\n * Safety properties enforced at sample-time:\n *\n *   - **Required split + capturedBefore**: substrate refuses to sample without\n *     an explicit `split` ('train' | 'test') AND a temporal cutoff. Eliminates\n *     accidental train/test contamination.\n *   - **Default training-source filter**: when the store is sampled with\n *     `split: 'train'`, production-trace records are EXCLUDED unless the\n *     caller passes `filter.source: 'production-trace'` explicitly. Closes\n *     the contamination-by-default gap flagged by the senior eval engineer.\n */\n\nimport { createHash } from 'node:crypto'\nimport { existsSync, mkdirSync, readFileSync, writeFileSync } from 'node:fs'\nimport { join } from 'node:path'\nimport type {\n  LabeledScenarioRecord,\n  LabeledScenarioSampleArgs,\n  LabeledScenarioSource,\n  LabeledScenarioStore,\n  LabeledScenarioWrite,\n} from '../types'\n\nexport interface FsLabeledScenarioStoreOptions {\n  /** Root directory for JSONL files. Created if missing. */\n  root: string\n  /** Per-source rate limit. When set, writes exceeding the cap are rejected\n   *  with a typed error. Default: no limit. */\n  maxWritesPerMinutePerBucket?: number\n  /** Test seam — override `Date.now()` for deterministic tests. */\n  now?: () => number\n}\n\nexport class LabeledScenarioStoreError extends Error {\n  constructor(\n    public readonly code: string,\n    message: string,\n  ) {\n    super(message)\n    this.name = 'LabeledScenarioStoreError'\n  }\n}\n\ninterface RateLimitState {\n  bucket: string\n  windowStartMs: number\n  count: number\n}\n\nexport class FsLabeledScenarioStore implements LabeledScenarioStore {\n  private readonly now: () => number\n  private readonly rateLimits = new Map<string, RateLimitState>()\n\n  constructor(private readonly options: FsLabeledScenarioStoreOptions) {\n    if (!existsSync(options.root)) mkdirSync(options.root, { recursive: true })\n    this.now = options.now ?? Date.now\n  }\n\n  async observe(write: LabeledScenarioWrite): Promise<void> {\n    this.assertProvenance(write)\n    this.assertRateLimit(write)\n    const record = this.toRecord(write)\n    const path = this.pathForSource(write.source)\n    const line = `${JSON.stringify(record)}\\n`\n    // Append atomically. For high-throughput a writev-friendly buffered\n    // implementation lands in the Turso adapter; FS adapter is for tests +\n    // local dev + small workloads.\n    appendLine(path, line)\n  }\n\n  async sample(args: LabeledScenarioSampleArgs): Promise<LabeledScenarioRecord[]> {\n    if (!args.split) {\n      throw new LabeledScenarioStoreError(\n        'split_required',\n        'sample() requires an explicit `split` (train | test) — substrate refuses ambiguous reads',\n      )\n    }\n    if (!args.capturedBefore) {\n      throw new LabeledScenarioStoreError(\n        'capturedBefore_required',\n        'sample() requires an explicit `capturedBefore` timestamp for temporal-split discipline',\n      )\n    }\n\n    const all: LabeledScenarioRecord[] = []\n    for (const source of ALL_SOURCES) {\n      // Default training-source filter: when sampling train, EXCLUDE\n      // production-trace records unless the caller asks for them.\n      if (args.split === 'train' && source === 'production-trace') {\n        const explicit = sourceFilterContains(args.filter?.source, 'production-trace')\n        if (!explicit) continue\n      }\n      const path = this.pathForSource(source)\n      if (!existsSync(path)) continue\n      const lines = readFileSync(path, 'utf8').split('\\n').filter(Boolean)\n      for (const line of lines) {\n        let record: LabeledScenarioRecord\n        try {\n          record = JSON.parse(line) as LabeledScenarioRecord\n        } catch {\n          continue\n        }\n        if (!matchesFilter(record, args, source)) continue\n        all.push(record)\n      }\n    }\n\n    // Deterministic order: by capturedAt ascending, then recordHash.\n    all.sort((a, b) => {\n      if (a.capturedAt !== b.capturedAt) return a.capturedAt.localeCompare(b.capturedAt)\n      return a.recordHash.localeCompare(b.recordHash)\n    })\n\n    return all.slice(0, args.count)\n  }\n\n  async size(): Promise<{ train: number; test: number; bySource: Record<string, number> }> {\n    const bySource: Record<string, number> = {}\n    let total = 0\n    for (const source of ALL_SOURCES) {\n      const path = this.pathForSource(source)\n      if (!existsSync(path)) {\n        bySource[source] = 0\n        continue\n      }\n      const count = readFileSync(path, 'utf8').split('\\n').filter(Boolean).length\n      bySource[source] = count\n      total += count\n    }\n    // FS adapter doesn't track split assignments per-record (split is\n    // computed at sample-time based on `capturedBefore`). For size(), we\n    // report `train`+`test` as the same total — split is a sampling concept.\n    return { train: total, test: total, bySource }\n  }\n\n  private assertProvenance(write: LabeledScenarioWrite): void {\n    if (!write.source) {\n      throw new LabeledScenarioStoreError(\n        'missing_source',\n        'LabeledScenarioWrite requires `source`',\n      )\n    }\n    if (!write.sourceVersionHash || write.sourceVersionHash.length === 0) {\n      throw new LabeledScenarioStoreError(\n        'missing_source_version',\n        'LabeledScenarioWrite requires `sourceVersionHash` (git sha or substrate version)',\n      )\n    }\n    if (!write.capturedAt) {\n      throw new LabeledScenarioStoreError(\n        'missing_captured_at',\n        'LabeledScenarioWrite requires `capturedAt` ISO timestamp',\n      )\n    }\n    if (!write.redactionStatus) {\n      throw new LabeledScenarioStoreError(\n        'missing_redaction_status',\n        'LabeledScenarioWrite requires explicit `redactionStatus` — raw / redacted-pii / redacted-secrets / fully-redacted',\n      )\n    }\n    if (!ALL_SOURCES.includes(write.source)) {\n      throw new LabeledScenarioStoreError(\n        'unknown_source',\n        `LabeledScenarioWrite.source must be one of: ${ALL_SOURCES.join(', ')}`,\n      )\n    }\n  }\n\n  private assertRateLimit(write: LabeledScenarioWrite): void {\n    const cap = this.options.maxWritesPerMinutePerBucket\n    if (!cap || !write.rateLimitBucket) return\n    const now = this.now()\n    const windowMs = 60_000\n    let state = this.rateLimits.get(write.rateLimitBucket)\n    if (!state || now - state.windowStartMs >= windowMs) {\n      state = { bucket: write.rateLimitBucket, windowStartMs: now, count: 0 }\n      this.rateLimits.set(write.rateLimitBucket, state)\n    }\n    if (state.count >= cap) {\n      throw new LabeledScenarioStoreError(\n        'rate_limit_exceeded',\n        `LabeledScenarioStore: bucket ${write.rateLimitBucket} exceeded ${cap} writes/min`,\n      )\n    }\n    state.count += 1\n  }\n\n  private toRecord(write: LabeledScenarioWrite): LabeledScenarioRecord {\n    const recordHash = sha256(\n      JSON.stringify({\n        id: write.scenario.id,\n        src: write.source,\n        at: write.capturedAt,\n        ver: write.sourceVersionHash,\n      }),\n    )\n    // FS adapter assigns split at sample-time, but we cache a hint here\n    // based on capturedAt vs the world's \"now\" — sampler overrides this.\n    return {\n      ...write,\n      recordHash,\n      split: 'train',\n    }\n  }\n\n  private pathForSource(source: string): string {\n    return join(this.options.root, `${source}.jsonl`)\n  }\n}\n\nconst ALL_SOURCES: LabeledScenarioWrite['source'][] = [\n  'production-trace',\n  'eval-run',\n  'manual',\n  'red-team',\n  'synthetic',\n]\n\nfunction sourceFilterContains(\n  filter: LabeledScenarioSource | LabeledScenarioSource[] | undefined,\n  needle: LabeledScenarioSource,\n): boolean {\n  if (!filter) return false\n  if (Array.isArray(filter)) return filter.includes(needle)\n  return filter === needle\n}\n\nfunction matchesFilter(\n  record: LabeledScenarioRecord,\n  args: LabeledScenarioSampleArgs,\n  source: string,\n): boolean {\n  // Temporal cutoff — train must be capturedAt < capturedBefore.\n  if (args.split === 'train' && record.capturedAt >= args.capturedBefore) return false\n  if (args.split === 'test' && record.capturedAt < args.capturedBefore) return false\n\n  const f = args.filter\n  if (!f) return true\n  if (f.kind && record.scenario.kind !== f.kind) return false\n  if (f.source) {\n    const sources = Array.isArray(f.source) ? f.source : [f.source]\n    if (!sources.includes(source as never)) return false\n  }\n  if (f.minComposite !== undefined || f.maxComposite !== undefined) {\n    const composites = Object.values(record.judgeScores).map((s) => s.composite)\n    const max = composites.length === 0 ? 0 : Math.max(...composites)\n    if (f.minComposite !== undefined && max < f.minComposite) return false\n    if (f.maxComposite !== undefined && max > f.maxComposite) return false\n  }\n  return true\n}\n\nfunction sha256(input: string): string {\n  return createHash('sha256').update(input).digest('hex').slice(0, 16)\n}\n\nfunction appendLine(path: string, line: string): void {\n  if (existsSync(path)) {\n    const existing = readFileSync(path, 'utf8')\n    writeFileSync(path, existing + line)\n  } else {\n    writeFileSync(path, line)\n  }\n}\n","/**\n * @experimental\n *\n * `runEval` — the simplest preset over `runCampaign`. No optimizer, no\n * gate, no auto-PR. Just: run scenarios through dispatch, score with\n * judges, return CampaignResult.\n *\n * The 80% case for consumers who want a scorecard, not an improvement loop.\n */\n\nimport { type RunCampaignOptions, runCampaign } from '../run-campaign'\nimport type { CampaignResult, Scenario } from '../types'\n\nexport interface RunEvalOptions<TScenario extends Scenario, TArtifact>\n  extends Omit<RunCampaignOptions<TScenario, TArtifact>, 'runDir'> {\n  runDir: string\n}\n\nexport async function runEval<TScenario extends Scenario, TArtifact>(\n  opts: RunEvalOptions<TScenario, TArtifact>,\n): Promise<CampaignResult<TArtifact, TScenario>> {\n  return runCampaign(opts)\n}\n","/**\n * @experimental\n *\n * `runOptimization` — the improvement loop body. Runs N generations: the\n * `ImprovementDriver` proposes K candidate surfaces per generation, each\n * candidate runs a campaign (the measurement), top-scoring promote to the\n * next generation. Driver-agnostic — the same loop runs an evolutionary\n * population mutator (`evolutionaryDriver`) or a reflective analyst\n * (`analystDriver`); they differ only in how `propose()` picks candidates.\n *\n * This is `runLoop`'s shape (plan → measure → decide) specialized to surface\n * improvement: `driver.propose` = plan, `runCampaign` = the measurement (which\n * runs the worker behind `dispatch`), the mean-composite ranking = the\n * validator, `driver.decide` = the stop check.\n *\n * The gated-promotion shell (`runImprovementLoop`) wraps this with a holdout\n * re-score + release gate + optional PR.\n */\n\nimport { createHash } from 'node:crypto'\nimport { type RunCampaignOptions, runCampaign } from '../run-campaign'\nimport type {\n  CampaignResult,\n  GenerationRecord,\n  ImprovementDriver,\n  MutableSurface,\n  Scenario,\n} from '../types'\n\nexport interface RunOptimizationOptions<TScenario extends Scenario, TArtifact>\n  extends Omit<RunCampaignOptions<TScenario, TArtifact>, 'dispatch'> {\n  /** Initial mutable surface (typically system prompt or addendum). */\n  baselineSurface: MutableSurface\n  /** Dispatcher that takes the CURRENT surface + scenario → artifact. */\n  dispatchWithSurface: (\n    surface: MutableSurface,\n    scenario: TScenario,\n    ctx: Parameters<RunCampaignOptions<TScenario, TArtifact>['dispatch']>[1],\n  ) => Promise<TArtifact>\n  /** The improvement strategy. Wrap a population `Mutator` via\n   *  `evolutionaryDriver({ mutator })`, or pass a reflective `analystDriver`. */\n  driver: ImprovementDriver\n  populationSize: number\n  maxGenerations: number\n  /** How many top-scoring candidates carry to the next generation. Default 2. */\n  promoteTopK?: number\n  /** DEPTH knob forwarded to the driver's `propose()` — max runLoop iterations\n   *  the generating agent may take per candidate (autoresearchDriver). */\n  maxImprovementShots?: number\n  /** Phase-2 research report forwarded to `propose()` (analyst findings +\n   *  diff). Opaque here; the driver types it. */\n  report?: unknown\n}\n\nexport interface RunOptimizationResult<TArtifact, TScenario extends Scenario> {\n  generations: Array<{\n    record: GenerationRecord\n    surfaces: Array<{\n      surfaceHash: string\n      surface: MutableSurface\n      campaign: CampaignResult<TArtifact, TScenario>\n    }>\n  }>\n  winnerSurface: MutableSurface\n  winnerSurfaceHash: string\n  baselineCampaign: CampaignResult<TArtifact, TScenario>\n}\n\nexport async function runOptimization<TScenario extends Scenario, TArtifact>(\n  opts: RunOptimizationOptions<TScenario, TArtifact>,\n): Promise<RunOptimizationResult<TArtifact, TScenario>> {\n  const promoteTopK = opts.promoteTopK ?? 2\n\n  // Baseline run\n  const baselineCampaign = await runCampaign<TScenario, TArtifact>({\n    ...opts,\n    dispatch: (scenario, ctx) => opts.dispatchWithSurface(opts.baselineSurface, scenario, ctx),\n    runDir: `${opts.runDir}/baseline`,\n  })\n\n  const generations: RunOptimizationResult<TArtifact, TScenario>['generations'] = []\n  const history: GenerationRecord[] = []\n  let currentSurfaces: MutableSurface[] = [opts.baselineSurface]\n  let winnerSurface = opts.baselineSurface\n  let winnerSurfaceHash = surfaceHash(opts.baselineSurface)\n  let winnerComposite = meanComposite(baselineCampaign)\n\n  for (let gen = 0; gen < opts.maxGenerations; gen++) {\n    // Decide: the driver may stop early based on accumulated history.\n    if (opts.driver.decide?.({ history }).stop) break\n\n    // Plan: the driver proposes N candidates from the current best surface,\n    // the accumulated generation history, and any external findings.\n    const candidates = await opts.driver.propose({\n      currentSurface: currentSurfaces[0] ?? opts.baselineSurface,\n      history,\n      findings: [],\n      populationSize: opts.populationSize,\n      generation: gen,\n      signal: new AbortController().signal,\n      report: opts.report,\n      dataset: opts.labeledStore && opts.labeledStore !== 'off' ? opts.labeledStore : undefined,\n      maxImprovementShots: opts.maxImprovementShots,\n    })\n\n    // Run each candidate as its own campaign.\n    const surfaceResults: Array<{\n      surfaceHash: string\n      surface: MutableSurface\n      campaign: CampaignResult<TArtifact, TScenario>\n      composite: number\n    }> = []\n    for (let i = 0; i < candidates.length; i++) {\n      const surface = candidates[i] as MutableSurface\n      const hash = surfaceHash(surface)\n      const campaign = await runCampaign<TScenario, TArtifact>({\n        ...opts,\n        dispatch: (scenario, ctx) => opts.dispatchWithSurface(surface, scenario, ctx),\n        runDir: `${opts.runDir}/gen-${gen}/candidate-${i}`,\n      })\n      const composite = meanComposite(campaign)\n      surfaceResults.push({ surfaceHash: hash, surface, campaign, composite })\n    }\n\n    // Rank, promote top-K.\n    surfaceResults.sort((a, b) => b.composite - a.composite)\n    const promoted = surfaceResults.slice(0, promoteTopK)\n    currentSurfaces = promoted.map((p) => p.surface)\n    const top = surfaceResults[0]\n    if (top && top.composite > winnerComposite) {\n      winnerSurface = top.surface\n      winnerSurfaceHash = top.surfaceHash\n      winnerComposite = top.composite\n    }\n\n    const record: GenerationRecord = {\n      generationIndex: gen,\n      candidates: surfaceResults.map((s) => ({\n        surfaceHash: s.surfaceHash,\n        composite: s.composite,\n        ci95: [s.composite, s.composite] as [number, number],\n      })),\n      promoted: promoted.map((p) => p.surfaceHash),\n    }\n    history.push(record)\n    generations.push({\n      record,\n      surfaces: surfaceResults.map((s) => ({\n        surfaceHash: s.surfaceHash,\n        surface: s.surface,\n        campaign: s.campaign,\n      })),\n    })\n  }\n\n  return {\n    generations,\n    winnerSurface,\n    winnerSurfaceHash,\n    baselineCampaign,\n  }\n}\n\nexport function surfaceHash(surface: MutableSurface): string {\n  // Prompt/tool surfaces (string) hash by content; code surfaces hash by the\n  // worktree + base ref pair (the content lives in git, not in the string).\n  const material =\n    typeof surface === 'string'\n      ? surface\n      : JSON.stringify({\n          kind: surface.kind,\n          worktreeRef: surface.worktreeRef,\n          baseRef: surface.baseRef ?? null,\n        })\n  return createHash('sha256').update(material).digest('hex').slice(0, 16)\n}\n\nfunction meanComposite<TArtifact, TScenario extends Scenario>(\n  campaign: CampaignResult<TArtifact, TScenario>,\n): number {\n  const composites: number[] = []\n  for (const cell of campaign.cells) {\n    const cellComposites = Object.values(cell.judgeScores).map((s) => s.composite)\n    if (cellComposites.length > 0) {\n      composites.push(cellComposites.reduce((a, b) => a + b, 0) / cellComposites.length)\n    }\n  }\n  return composites.length === 0 ? 0 : composites.reduce((a, b) => a + b, 0) / composites.length\n}\n","/**\n * @experimental\n *\n * `runImprovementLoop` — the gated-promotion shell around the improvement\n * loop body (`runOptimization`). Drives candidate surfaces via the\n * `ImprovementDriver`, re-scores the winner against the baseline on a\n * holdout set, runs the release gate, and optionally opens a PR.\n *\n * Role vocabulary (see docs/design/loop-taxonomy.md):\n *   - DRIVER     = the `ImprovementDriver` (evolutionary GEPA mutator OR\n *                  reflective analyst). Proposes candidate SURFACES — the\n *                  worker's system prompt / tool config — NOT conversation\n *                  turns.\n *   - MEASUREMENT= `runCampaign`. Scores one surface by running the worker\n *                  (via `dispatch`) over scenarios and judging the output.\n *   - WORKER     = the agent harness in the sandbox, invoked behind the\n *                  topology-opaque `dispatch` seam — never referenced here.\n *\n * Distinct from `runLoop` in `@tangle-network/agent-runtime`, which is the\n * INNER conversation loop (driver↔workers in a sandbox). `runImprovementLoop`\n * is the OUTER loop: it improves the surface that those workers run.\n *\n * Hard-refuses unsafe configurations:\n *   - `tracing: 'off'` when a driver is wired (improvement is unattributable)\n *   - `autoOnPromote: 'config'` — DEFERRED to Pass B; v0.40 only ships\n *     `'pr'` and `'none'`.\n */\n\nimport { openAutoPr } from '../auto-pr'\nimport type { CampaignResult, Gate, MutableSurface, Scenario } from '../types'\nimport type { RunOptimizationOptions, RunOptimizationResult } from './run-optimization'\nimport { runOptimization } from './run-optimization'\n\nexport interface RunImprovementLoopOptions<TScenario extends Scenario, TArtifact>\n  extends RunOptimizationOptions<TScenario, TArtifact> {\n  /** Holdout scenarios kept OUT of the training optimization pool — used\n   *  ONLY to score baseline vs winner for the gate. */\n  holdoutScenarios: TScenario[]\n  /** Promotion gate. Substrate strongly recommends `defaultProductionGate`\n   *  for production wiring (composes red-team / reward-hacking / canary /\n   *  heldout). */\n  gate: Gate<TArtifact, TScenario>\n  /** What to do when the gate ships:\n   *   - `'pr'`: open a PR via `openAutoPr`\n   *   - `'none'`: just report — caller decides what to do with the winner\n   *  v0.40 does NOT support `'config'` (live-runtime self-mutation) —\n   *  deferred to Pass B behind safety stack. */\n  autoOnPromote: 'pr' | 'none'\n  /** GH owner / repo for the auto-PR. Required when autoOnPromote === 'pr'. */\n  ghOwner?: string\n  ghRepo?: string\n  /** Optional render override — substrate writes a diff-shaped surface; pass\n   *  a function to format the promoted surface differently. */\n  renderPromotedDiff?: (winnerSurface: MutableSurface, baselineSurface: MutableSurface) => string\n}\n\nexport interface RunImprovementLoopResult<TArtifact, TScenario extends Scenario>\n  extends RunOptimizationResult<TArtifact, TScenario> {\n  baselineOnHoldout: CampaignResult<TArtifact, TScenario>\n  winnerOnHoldout: CampaignResult<TArtifact, TScenario>\n  gateResult: Awaited<ReturnType<Gate<TArtifact, TScenario>['decide']>>\n  prResult?: ReturnType<typeof openAutoPr>\n}\n\nexport async function runImprovementLoop<TScenario extends Scenario, TArtifact>(\n  opts: RunImprovementLoopOptions<TScenario, TArtifact>,\n): Promise<RunImprovementLoopResult<TArtifact, TScenario>> {\n  // ── Safety pre-flight ─────────────────────────────────────────────\n  // biome-ignore lint/suspicious/noExplicitAny: Pass A reserved field for Pass B Shape B\n  if ((opts as any).autoOnPromote === 'config') {\n    throw new Error(\n      \"runImprovementLoop: autoOnPromote='config' is deferred to Pass B (requires shadow deploy + rollback + ensemble judges). Use 'pr' or 'none' in v0.40.\",\n    )\n  }\n  // Refuse tracing=off whenever a driver is wired. An improvement loop\n  // without traces is unattributable — its candidate surfaces cannot be\n  // cited back to the spans that motivated them, and the dataset flywheel\n  // (LabeledScenarioStore) that GEPA optimizes against goes unfed.\n  if (opts.tracing === 'off' && opts.driver) {\n    throw new Error(\n      \"runImprovementLoop: tracing='off' is forbidden when a driver is wired. The improvement loop without traces is unattributable; candidate surfaces cannot be cited back to spans and the optimization dataset goes unfed.\",\n    )\n  }\n  if (opts.autoOnPromote === 'pr' && (!opts.ghOwner || !opts.ghRepo)) {\n    throw new Error(\"runImprovementLoop: autoOnPromote='pr' requires ghOwner + ghRepo.\")\n  }\n\n  // ── (1) optimization loop produces a winner ────────────────────────\n  const optimization = await runOptimization(opts)\n\n  // ── (2) baseline + winner re-scored on the holdout set ─────────────\n  const { runCampaign } = await import('../run-campaign')\n\n  const baselineOnHoldout = await runCampaign<TScenario, TArtifact>({\n    ...opts,\n    scenarios: opts.holdoutScenarios,\n    dispatch: (scenario, ctx) => opts.dispatchWithSurface(opts.baselineSurface, scenario, ctx),\n    runDir: `${opts.runDir}/holdout-baseline`,\n  })\n\n  const winnerOnHoldout = await runCampaign<TScenario, TArtifact>({\n    ...opts,\n    scenarios: opts.holdoutScenarios,\n    dispatch: (scenario, ctx) =>\n      opts.dispatchWithSurface(optimization.winnerSurface, scenario, ctx),\n    runDir: `${opts.runDir}/holdout-winner`,\n  })\n\n  // ── (3) gate verdict ───────────────────────────────────────────────\n  const candidateArtifacts = new Map<string, TArtifact>()\n  const baselineArtifacts = new Map<string, TArtifact>()\n  const judgeScores = new Map<\n    string,\n    Record<string, { composite: number; dimensions: Record<string, number>; notes: string }>\n  >()\n  for (const cell of winnerOnHoldout.cells) {\n    candidateArtifacts.set(cell.cellId, cell.artifact)\n    judgeScores.set(cell.cellId, cell.judgeScores)\n  }\n  for (const cell of baselineOnHoldout.cells) {\n    baselineArtifacts.set(cell.cellId, cell.artifact)\n    const prior = judgeScores.get(cell.cellId) ?? {}\n    judgeScores.set(cell.cellId, { ...prior, ...cell.judgeScores })\n  }\n\n  const gateResult = await opts.gate.decide({\n    candidateArtifacts,\n    baselineArtifacts,\n    judgeScores,\n    scenarios: opts.holdoutScenarios,\n    cost: {\n      candidate: winnerOnHoldout.aggregates.totalCostUsd,\n      baseline: baselineOnHoldout.aggregates.totalCostUsd,\n    },\n    signal: new AbortController().signal,\n  })\n\n  // ── (4) auto-PR when gate ships ────────────────────────────────────\n  let prResult: ReturnType<typeof openAutoPr> | undefined\n  if (opts.autoOnPromote === 'pr' && gateResult.decision === 'ship') {\n    const render = opts.renderPromotedDiff ?? defaultRenderDiff\n    const promotedDiff = render(optimization.winnerSurface, opts.baselineSurface)\n    prResult = openAutoPr({\n      result: winnerOnHoldout,\n      gate: gateResult,\n      promotedDiff,\n      ghOwner: opts.ghOwner!,\n      ghRepo: opts.ghRepo!,\n    })\n  }\n\n  return {\n    ...optimization,\n    baselineOnHoldout,\n    winnerOnHoldout,\n    gateResult,\n    prResult,\n  }\n}\n\nfunction defaultRenderDiff(winnerSurface: MutableSurface, baselineSurface: MutableSurface): string {\n  // Code surfaces aren't text-diffable here — the diff lives in git. Render\n  // the worktree/base refs + summary so the PR body points at the change.\n  if (typeof winnerSurface !== 'string' || typeof baselineSurface !== 'string') {\n    const fmt = (s: MutableSurface): string =>\n      typeof s === 'string'\n        ? '(prompt surface)'\n        : `worktree=${s.worktreeRef}${s.baseRef ? ` base=${s.baseRef}` : ''}${s.summary ? `\\n${s.summary}` : ''}`\n    return `--- baseline\\n${fmt(baselineSurface)}\\n+++ winner\\n${fmt(winnerSurface)}`\n  }\n  const lines: string[] = []\n  lines.push('--- baseline')\n  lines.push('+++ winner')\n  for (const l of baselineSurface.split('\\n')) lines.push(`- ${l}`)\n  for (const l of winnerSurface.split('\\n')) lines.push(`+ ${l}`)\n  return lines.join('\\n')\n}\n","/**\n * @experimental\n *\n * VCS-pluggable worktree adapter. One improvement = one worktree, PR-like\n * (multiple commits allowed). A code-tier driver's `propose()` creates a\n * worktree, an agent commits the change into it, and `finalize()` returns a\n * `CodeSurface{ worktreeRef }` the measurement checks out to run the worker\n * against the changed code. On promotion the worktree becomes the PR branch.\n *\n * The interface is VCS-agnostic so a future `jj` ([jj-vcs](https://github.com/jj-vcs/jj))\n * adapter can slot in without touching driver code. Only the git adapter\n * ships today. See `docs/design/self-improvement-engine.md`.\n */\n\nimport { execFileSync } from 'node:child_process'\nimport { existsSync } from 'node:fs'\nimport { basename, isAbsolute, join } from 'node:path'\nimport type { CodeSurface } from '../types'\n\nexport interface Worktree {\n  /** Absolute path to the checked-out worktree directory. */\n  path: string\n  /** The branch the worktree is on (becomes the PR branch on promotion). */\n  branch: string\n  /** The ref the worktree was forked from. */\n  baseRef: string\n}\n\nexport interface WorktreeAdapter {\n  /** Create an isolated worktree on a fresh branch off `baseRef`. */\n  create(opts: { baseRef: string; label: string }): Promise<Worktree>\n  /** Commit any pending changes in the worktree, then return a CodeSurface\n   *  pointing at it. The agent has already written its change into\n   *  `worktree.path` by the time this is called. */\n  finalize(worktree: Worktree, summary: string): Promise<CodeSurface>\n  /** Remove the worktree (and its branch) — called for losing candidates. */\n  discard(worktree: Worktree): Promise<void>\n}\n\nexport class WorktreeAdapterError extends Error {\n  constructor(\n    message: string,\n    readonly cause?: unknown,\n  ) {\n    super(message)\n    this.name = 'WorktreeAdapterError'\n  }\n}\n\nexport interface GitWorktreeAdapterOptions {\n  /** Repo root the worktrees fork from. */\n  repoRoot: string\n  /** Directory worktrees are created under. Default: `<repoRoot>/.worktrees`. */\n  worktreeDir?: string\n  /** Branch-name prefix. Default: `improve`. */\n  branchPrefix?: string\n  /** Test seam — defaults to a real `git` runner. */\n  git?: (args: string[], cwd: string) => string\n}\n\nfunction defaultGit(args: string[], cwd: string): string {\n  try {\n    return execFileSync('git', args, { cwd, encoding: 'utf8' }).trim()\n  } catch (err) {\n    const stderr =\n      err && typeof err === 'object' && 'stderr' in err\n        ? String((err as { stderr: unknown }).stderr)\n        : ''\n    throw new WorktreeAdapterError(`git ${args.join(' ')} failed: ${stderr || String(err)}`, err)\n  }\n}\n\n/** Slugify a label into a branch-safe segment. */\nfunction slug(label: string): string {\n  return (\n    label\n      .toLowerCase()\n      .replace(/[^a-z0-9]+/g, '-')\n      .replace(/^-+|-+$/g, '')\n      .slice(0, 48) || 'candidate'\n  )\n}\n\nexport function gitWorktreeAdapter(opts: GitWorktreeAdapterOptions): WorktreeAdapter {\n  const git = opts.git ?? defaultGit\n  const worktreeDir = opts.worktreeDir ?? join(opts.repoRoot, '.worktrees')\n  const branchPrefix = opts.branchPrefix ?? 'improve'\n\n  return {\n    async create({ baseRef, label }) {\n      const id = `${slug(label)}-${Date.now().toString(36)}-${Math.random().toString(36).slice(2, 6)}`\n      const branch = `${branchPrefix}/${id}`\n      const path = join(worktreeDir, id)\n      git(['worktree', 'add', '-b', branch, path, baseRef], opts.repoRoot)\n      return { path, branch, baseRef }\n    },\n\n    async finalize(worktree, summary) {\n      // Stage + commit any pending changes the agent left in the worktree.\n      // A no-op commit is refused by git, so only commit when the tree is dirty.\n      const status = git(['status', '--porcelain'], worktree.path)\n      if (status.length > 0) {\n        git(['add', '-A'], worktree.path)\n        git(['commit', '-m', summary], worktree.path)\n      }\n      return {\n        kind: 'code',\n        worktreeRef: worktree.path,\n        baseRef: worktree.baseRef,\n        summary,\n      }\n    },\n\n    async discard(worktree) {\n      // Remove the worktree, then delete its branch. Force-remove because the\n      // worktree may hold uncommitted experiment state we're discarding.\n      git(['worktree', 'remove', '--force', worktree.path], opts.repoRoot)\n      git(['branch', '-D', worktree.branch], opts.repoRoot)\n    },\n  }\n}\n\n/** Resolve a `CodeSurface`'s worktreeRef to a directory the measurement can\n *  run the worker in. A path ref is returned as-is; anything else is treated\n *  as a ref under the adapter's worktree dir. */\nexport function resolveWorktreePath(surface: CodeSurface, worktreeDir?: string): string {\n  if (isAbsolute(surface.worktreeRef) && existsSync(surface.worktreeRef)) return surface.worktreeRef\n  if (worktreeDir) return join(worktreeDir, basename(surface.worktreeRef))\n  return surface.worktreeRef\n}\n"],"mappings":";;;;;;;;;;;;;;;;AAcA,SAAS,gBAAgB;AACzB,SAAS,qBAAqB;AAC9B,SAAS,cAAc;AACvB,SAAS,YAAY;AAiCd,SAAS,WACd,SACkB;AAClB,MAAI,QAAQ,KAAK,aAAa,QAAQ;AACpC,WAAO;AAAA,MACL,QAAQ;AAAA,MACR,QAAQ;AAAA,MACR,QAAQ,qBAAqB,QAAQ,KAAK,QAAQ;AAAA,IACpD;AAAA,EACF;AAEA,QAAM,SAAS,QAAQ,UAAU,CAAC,QAAQ,IAAI;AAC9C,QAAM,SAAS,QAAQ,UAAU,QAAQ,QAAQ,OAAO,aAAa,MAAM,GAAG,EAAE,CAAC;AACjF,QAAM,QACJ,QAAQ,SAAS,kBAAkB,QAAQ,OAAO,aAAa,MAAM,GAAG,CAAC,CAAC;AAE5E,QAAM,OAAO,aAAa,QAAQ,QAAQ,QAAQ,MAAM,QAAQ,YAAY;AAC5E,QAAM,WAAW,KAAK,OAAO,GAAG,gBAAgB,KAAK,IAAI,CAAC,KAAK;AAC/D,gBAAc,UAAU,IAAI;AAE5B,MAAI,QAAQ;AACV,WAAO;AAAA,MACL,QAAQ;AAAA,MACR,QAAQ;AAAA,MACR,QAAQ,0DAA0D,QAAQ,OAAO,IAAI,QAAQ,MAAM,WAAW,MAAM,aAAa,QAAQ;AAAA,IAC3I;AAAA,EACF;AAEA,QAAM,SAAS,QAAQ,UAAU;AACjC,QAAM,SAAS,OAAO;AAAA,IACpB;AAAA,IACA;AAAA,IACA;AAAA,IACA,GAAG,QAAQ,OAAO,IAAI,QAAQ,MAAM;AAAA,IACpC;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,EACF,CAAC;AACD,MAAI,OAAO,WAAW,GAAG;AACvB,WAAO;AAAA,MACL,QAAQ;AAAA,MACR,QAAQ;AAAA,MACR,QAAQ,6BAA6B,OAAO,MAAM,MAAM,OAAO,OAAO,MAAM,GAAG,GAAG,CAAC;AAAA,IACrF;AAAA,EACF;AACA,QAAM,QAAQ,OAAO,OAAO,KAAK;AACjC,SAAO,EAAE,QAAQ,MAAM,OAAO,QAAQ,OAAO,QAAQ,YAAY;AACnE;AAEA,SAAS,aACP,QACA,MACA,MACQ;AACR,QAAM,QAAkB,CAAC;AACzB,QAAM,KAAK,kDAAkD;AAC7D,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,mBAAmB,OAAO,YAAY,IAAI;AACrD,QAAM,KAAK,aAAa,OAAO,IAAI,EAAE;AACrC,QAAM,KAAK,iBAAiB,KAAK,MAAM,OAAO,aAAa,GAAI,CAAC,GAAG;AACnE,QAAM;AAAA,IACJ,uBAAuB,OAAO,WAAW,aAAa,YAAY,OAAO,WAAW,WAAW,aAAa,OAAO,WAAW,YAAY,YAAY,OAAO,WAAW,WAAW;AAAA,EACrL;AACA,QAAM,KAAK,qBAAqB,OAAO,WAAW,aAAa,QAAQ,CAAC,CAAC,EAAE;AAC3E,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,uBAAuB,KAAK,QAAQ,IAAI;AACnD,QAAM,KAAK,EAAE;AACb,aAAW,UAAU,KAAK,QAAS,OAAM,KAAK,KAAK,MAAM,EAAE;AAC3D,MAAI,KAAK,UAAU,OAAW,OAAM,KAAK,YAAY,KAAK,MAAM,QAAQ,CAAC,CAAC,EAAE;AAC5E,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,wBAAwB;AACnC,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,4BAA4B;AACvC,QAAM,KAAK,eAAe;AAC1B,aAAW,KAAK,KAAK,mBAAmB;AACtC,UAAM,SACJ,OAAO,EAAE,WAAW,WAChB,KAAK,UAAU,EAAE,MAAM,EAAE,MAAM,GAAG,EAAE,IACpC,OAAO,EAAE,MAAM,EAAE,MAAM,GAAG,EAAE;AAClC,UAAM,KAAK,KAAK,EAAE,IAAI,MAAM,EAAE,SAAS,WAAM,QAAG,MAAM,MAAM,IAAI;AAAA,EAClE;AACA,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,sBAAsB;AACjC,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,SAAS;AACpB,QAAM,KAAK,KAAK,MAAM,GAAG,GAAI,CAAC;AAC9B,QAAM,KAAK,KAAK;AAChB,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,yBAAyB;AACpC,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,6BAA6B;AACxC,QAAM,KAAK,mBAAmB;AAC9B,aAAW,CAAC,MAAM,GAAG,KAAK,OAAO,QAAQ,OAAO,WAAW,OAAO,GAAG;AACnE,UAAM;AAAA,MACJ,KAAK,IAAI,MAAM,IAAI,KAAK,QAAQ,CAAC,CAAC,OAAO,IAAI,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC,KAAK,IAAI,KAAK,CAAC,EAAE,QAAQ,CAAC,CAAC,OAAO,IAAI,CAAC;AAAA,IACxG;AAAA,EACF;AACA,SAAO,MAAM,KAAK,IAAI;AACxB;AAEA,SAAS,cAAc,MAAoE;AACzF,MAAI;AACF,UAAM,SAAS,SAAS,MAAM,KAAK,IAAI,QAAQ,EAAE,KAAK,GAAG,CAAC,IAAI;AAAA,MAC5D,KAAK,EAAE,GAAG,QAAQ,KAAK,UAAU,QAAQ,IAAI,oBAAoB,QAAQ,IAAI,YAAY,GAAG;AAAA,MAC5F,OAAO,CAAC,UAAU,QAAQ,MAAM;AAAA,IAClC,CAAC,EAAE,SAAS,MAAM;AAClB,WAAO,EAAE,QAAQ,QAAQ,IAAI,QAAQ,EAAE;AAAA,EACzC,SAAS,KAAK;AACZ,UAAM,IAAI;AACV,WAAO;AAAA,MACL,QAAQ,EAAE,QAAQ,SAAS,MAAM,KAAK;AAAA,MACtC,QAAQ,EAAE,QAAQ,SAAS,MAAM,KAAK;AAAA,MACtC,QAAQ,EAAE,UAAU;AAAA,IACtB;AAAA,EACF;AACF;AAEA,SAAS,SAAS,KAAqB;AACrC,MAAI,wBAAwB,KAAK,GAAG,EAAG,QAAO;AAC9C,SAAO,IAAI,IAAI,QAAQ,MAAM,KAAK,CAAC;AACrC;;;ACrJO,SAAS,mBACd,MAC8B;AAC9B,SAAO;AAAA,IACL,MAAM,gBAAgB,KAAK,QAAQ,IAAI;AAAA,IACvC,MAAM,QAAQ,EAAE,gBAAgB,UAAU,gBAAgB,OAAO,GAAG;AAClE,aAAO,KAAK,QAAQ,OAAO;AAAA,QACzB,UAAU,SAAS,SAAS,IAAI,WAAY,KAAK,YAAY,CAAC;AAAA,QAC9D;AAAA,QACA;AAAA,QACA;AAAA,MACF,CAAC;AAAA,IACH;AAAA,EACF;AACF;;;ACxBO,SAAS,eACX,OACyB;AAC5B,MAAI,MAAM,WAAW,GAAG;AACtB,UAAM,IAAI,MAAM,wCAAwC;AAAA,EAC1D;AACA,SAAO;AAAA,IACL,MAAM,YAAY,MAAM,IAAI,CAAC,MAAM,EAAE,IAAI,EAAE,KAAK,GAAG,CAAC;AAAA,IACpD,MAAM,OAAO,KAA6D;AACxE,YAAM,UAAwE,CAAC;AAC/E,iBAAW,QAAQ,OAAO;AACxB,cAAM,MAAM,MAAM,KAAK,OAAO,GAAG;AACjC,gBAAQ,KAAK,EAAE,MAAM,IAAI,CAAC;AAAA,MAC5B;AAQA,YAAM,YAAY,QAAQ,IAAI,CAAC,MAAM,EAAE,IAAI,QAAQ;AACnD,YAAM,UAAwB,UAAU,MAAM,CAAC,MAAM,MAAM,MAAM,IAC7D,SACA,UAAU,SAAS,cAAc,IAC/B,iBACA,UAAU,SAAS,eAAe,IAChC,kBACA,UAAU,SAAS,MAAM,IACvB,SACA;AAEV,YAAM,eAAe,QAAQ;AAAA,QAAQ,CAAC,MACpC,EAAE,IAAI,kBAAkB,SAAS,IAC7B,EAAE,IAAI,oBACN,CAAC,EAAE,MAAM,EAAE,KAAK,MAAM,QAAQ,EAAE,IAAI,aAAa,QAAQ,QAAQ,EAAE,IAAI,CAAC;AAAA,MAC9E;AAEA,YAAM,UAAU,QAAQ;AAAA,QAAQ,CAAC,MAC/B,EAAE,IAAI,QAAQ,IAAI,CAAC,WAAW,IAAI,EAAE,KAAK,IAAI,KAAK,MAAM,EAAE;AAAA,MAC5D;AAEA,aAAO;AAAA,QACL,UAAU;AAAA,QACV;AAAA,QACA,mBAAmB;AAAA,QACnB,OAAO,QAAQ,CAAC,GAAG,IAAI;AAAA,MACzB;AAAA,IACF;AAAA,EACF;AACF;;;ACpBO,SAAS,sBACd,SAC4B;AAC5B,QAAM,iBAAiB,QAAQ,kBAAkB;AACjD,QAAM,gBAAgB,QAAQ,8BAA8B;AAE5D,SAAO;AAAA,IACL,MAAM;AAAA,IACN,MAAM,OAAO,KAA6D;AACxE,YAAM,UAAoB,CAAC;AAC3B,YAAM,eAA0E,CAAC;AAGjF,YAAM,oBAAoB;AAAA,QACxB,IAAI;AAAA,QACJ,IAAI;AAAA,QACJ,QAAQ;AAAA,MACV;AACA,YAAM,qBAAqB;AAAA,QACzB,IAAI;AAAA,QACJ,IAAI;AAAA,QACJ,QAAQ;AAAA,MACV;AACA,YAAM,QAAQ,qBAAqB;AACnC,YAAM,cAAc,SAAS;AAC7B,mBAAa,KAAK;AAAA,QAChB,MAAM;AAAA,QACN,QAAQ;AAAA,QACR,QAAQ,EAAE,mBAAmB,oBAAoB,OAAO,eAAe;AAAA,MACzE,CAAC;AACD,UAAI,CAAC,aAAa;AAChB,gBAAQ,KAAK,iBAAiB,MAAM,QAAQ,CAAC,CAAC,gBAAgB,cAAc,EAAE;AAAA,MAChF;AAGA,YAAM,aACJ,QAAQ,cAAc,UACtB,IAAI,KAAK,YAAY,IAAI,KAAK,YAAY,QAAQ;AACpD,mBAAa,KAAK;AAAA,QAChB,MAAM;AAAA,QACN,QAAQ;AAAA,QACR,QAAQ;AAAA,UACN,cAAc,IAAI,KAAK;AAAA,UACvB,aAAa,IAAI,KAAK;AAAA,UACtB,WAAW,QAAQ;AAAA,QACrB;AAAA,MACF,CAAC;AACD,UAAI,CAAC,YAAY;AACf,gBAAQ;AAAA,UACN,UAAU,IAAI,KAAK,YAAY,IAAI,KAAK,UAAU,QAAQ,CAAC,CAAC,aAAa,QAAQ,SAAS;AAAA,QAC5F;AAAA,MACF;AAGA,YAAM,kBAAkB,QAAQ,iBAC5B,aAAa,IAAI,oBAAoB,QAAQ,cAAc,IAC3D,EAAE,QAAQ,MAAM,UAAU,CAAC,EAAE;AACjC,mBAAa,KAAK;AAAA,QAChB,MAAM;AAAA,QACN,QAAQ,gBAAgB;AAAA,QACxB,QAAQ;AAAA,UACN,UAAU,gBAAgB,SAAS;AAAA,UACnC,QAAQ,gBAAgB,SAAS,MAAM,GAAG,CAAC;AAAA,QAC7C;AAAA,MACF,CAAC;AACD,UAAI,CAAC,gBAAgB,QAAQ;AAC3B,gBAAQ,KAAK,0BAA0B,gBAAgB,SAAS,MAAM,YAAY;AAAA,MACpF;AAGA,UAAI,sBAAkD;AACtD,UAAI,QAAQ,cAAc,QAAQ,WAAW,UAAU,IAAI;AACzD,8BAAsB,oBAAoB,EAAE,MAAM,QAAQ,WAAW,CAAC;AAAA,MACxE;AAIA,YAAM,kBAAkB;AACxB,YAAM,kBAAkB,qBAAqB,YAAY,CAAC,GAAG;AAAA,QAC3D,CAAC,MAAM,EAAE,YAAY;AAAA,MACvB;AACA,YAAM,oBACJ,CAAC,uBACD,CAAC,iBACA,eAAe,WAAW,KAAK,oBAAoB,YAAY;AAClE,mBAAa,KAAK;AAAA,QAChB,MAAM;AAAA,QACN,QAAQ;AAAA,QACR,QAAQ,EAAE,QAAQ,qBAAqB,oBAAoB,eAAe,OAAO;AAAA,MACnF,CAAC;AACD,UAAI,CAAC,mBAAmB;AACtB,gBAAQ;AAAA,UACN,mCAAmC,eAAe,MAAM,sCAAsC,oBAAqB,OAAO;AAAA,QAC5H;AAAA,MACF;AAGA,UAAI,eAAoC;AACxC,UAAI,QAAQ,cAAc,QAAQ,WAAW,UAAU,IAAI;AACzD,uBAAe,YAAY,QAAQ,YAAY,CAAC,CAAC;AAAA,MACnD;AAEA,YAAM,eAAe,cAAc,UAAU,CAAC,GAAG,OAAO,CAAC,MAAM,EAAE,aAAa,OAAO;AACrF,YAAM,aAAa,YAAY,WAAW;AAC1C,mBAAa,KAAK;AAAA,QAChB,MAAM;AAAA,QACN,QAAQ;AAAA,QACR,QAAQ,EAAE,aAAa,cAAc,OAAO,UAAU,GAAG,aAAa,YAAY,OAAO;AAAA,MAC3F,CAAC;AACD,UAAI,CAAC,YAAY;AACf,gBAAQ,KAAK,wBAAwB,YAAY,MAAM,EAAE;AAAA,MAC3D;AAGA,YAAM,YAAY,aAAa,MAAM,CAAC,MAAM,EAAE,MAAM;AACpD,YAAM,WAAW,YAAY,SAAS;AAEtC,aAAO;AAAA,QACL;AAAA,QACA,SAAS,QAAQ,SAAS,IAAI,UAAU,CAAC,kBAAkB;AAAA,QAC3D,mBAAmB;AAAA,QACnB;AAAA,MACF;AAAA,IACF;AAAA,EACF;AACF;AAEA,SAAS,cACP,WACA,mBACA,WACQ;AACR,MAAI,CAAC,aAAa,UAAU,SAAS,EAAG,QAAO;AAC/C,QAAM,cAAc,IAAI,IAAI,UAAU,IAAI,CAAC,MAAM,EAAE,EAAE,CAAC;AACtD,QAAM,aAAuB,CAAC;AAC9B,aAAW,CAAC,QAAQ,MAAM,KAAK,mBAAmB;AAChD,UAAM,aAAa,OAAO,MAAM,GAAG,EAAE,CAAC,KAAK;AAC3C,QAAI,CAAC,YAAY,IAAI,UAAU,EAAG;AAClC,UAAM,iBAAiB,OAAO,OAAO,MAAM,EAAE,IAAI,CAAC,MAAM,EAAE,SAAS;AACnE,QAAI,eAAe,WAAW,EAAG;AACjC,eAAW,KAAK,eAAe,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,eAAe,MAAM;AAAA,EACnF;AACA,MAAI,WAAW,WAAW,EAAG,QAAO;AACpC,SAAO,WAAW,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,WAAW;AAC5D;AAEA,SAAS,aACP,WACA,SAC8E;AAC9E,QAAM,WAA0D,CAAC;AACjE,aAAW,CAAC,SAAS,QAAQ,KAAK,WAAW;AAC3C,UAAM,OAAO,YAAY,QAAQ;AACjC,QAAI,SAAS,OAAW;AACxB,eAAW,UAAU,SAAS;AAC5B,YAAM,UAAU,mBAAmB,MAAM,CAAC,GAAG,MAAM;AACnD,UAAI,CAAC,QAAQ,QAAQ;AACnB,iBAAS,KAAK,EAAE,YAAY,OAAO,IAAI,QAAQ,QAAQ,UAAU,wBAAwB,CAAC;AAAA,MAC5F;AAAA,IACF;AAAA,EACF;AACA,SAAO,EAAE,QAAQ,SAAS,WAAW,GAAG,SAAS;AACnD;AAEA,SAAS,YAAY,UAAuC;AAC1D,MAAI,OAAO,aAAa,SAAU,QAAO;AACzC,MAAI,YAAY,OAAO,aAAa,UAAU;AAC5C,UAAM,MAAM;AACZ,QAAI,OAAO,IAAI,SAAS,SAAU,QAAO,IAAI;AAC7C,QAAI,OAAO,IAAI,WAAW,SAAU,QAAO,IAAI;AAC/C,QAAI,OAAO,IAAI,YAAY,SAAU,QAAO,IAAI;AAAA,EAClD;AACA,SAAO;AACT;;;AC1MO,SAAS,YACd,SAC4B;AAC5B,QAAM,iBAAiB,QAAQ,kBAAkB;AACjD,SAAO;AAAA,IACL,MAAM;AAAA,IACN,MAAM,OAAO,KAA6D;AACxE,YAAM,cAAc,IAAI,IAAI,QAAQ,UAAU,IAAI,CAAC,MAAM,EAAE,EAAE,CAAC;AAC9D,YAAM,WAAW,iBAAiB,IAAI,mBAAmB,IAAI,aAAa,WAAW;AACrF,YAAM,YAAY,iBAAiB,IAAI,oBAAoB,IAAI,aAAa,WAAW;AACvF,YAAM,QAAQ,YAAY;AAC1B,YAAM,SAAS,SAAS;AACxB,aAAO;AAAA,QACL,UAAU,SAAS,SAAS;AAAA,QAC5B,SAAS,SACL,CAAC,kBAAkB,MAAM,QAAQ,CAAC,CAAC,WAAM,cAAc,EAAE,IACzD,CAAC,kBAAkB,MAAM,QAAQ,CAAC,CAAC,MAAM,cAAc,EAAE;AAAA,QAC7D,mBAAmB;AAAA,UACjB,EAAE,MAAM,eAAe,QAAQ,QAAQ,EAAE,UAAU,WAAW,OAAO,eAAe,EAAE;AAAA,QACxF;AAAA,QACA;AAAA,MACF;AAAA,IACF;AAAA,EACF;AACF;AAEA,SAAS,iBACP,WACA,mBACA,aACQ;AACR,MAAI,CAAC,aAAa,UAAU,SAAS,EAAG,QAAO;AAC/C,QAAM,aAAuB,CAAC;AAC9B,aAAW,CAAC,QAAQ,MAAM,KAAK,mBAAmB;AAChD,UAAM,aAAa,OAAO,MAAM,GAAG,EAAE,CAAC,KAAK;AAC3C,QAAI,CAAC,YAAY,IAAI,UAAU,EAAG;AAClC,UAAM,OAAO,OAAO,OAAO,MAAM,EAAE,IAAI,CAAC,MAAM,EAAE,SAAS;AACzD,QAAI,KAAK,SAAS,EAAG,YAAW,KAAK,KAAK,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,KAAK,MAAM;AAAA,EACpF;AACA,SAAO,WAAW,WAAW,IAAI,IAAI,WAAW,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,WAAW;AAC1F;;;AC1BA,SAAS,kBAAkB;AAC3B,SAAS,YAAY,WAAW,cAAc,iBAAAA,sBAAqB;AACnE,SAAS,QAAAC,aAAY;AAmBd,IAAM,4BAAN,cAAwC,MAAM;AAAA,EACnD,YACkB,MAChB,SACA;AACA,UAAM,OAAO;AAHG;AAIhB,SAAK,OAAO;AAAA,EACd;AAAA,EALkB;AAMpB;AAQO,IAAM,yBAAN,MAA6D;AAAA,EAIlE,YAA6B,SAAwC;AAAxC;AAC3B,QAAI,CAAC,WAAW,QAAQ,IAAI,EAAG,WAAU,QAAQ,MAAM,EAAE,WAAW,KAAK,CAAC;AAC1E,SAAK,MAAM,QAAQ,OAAO,KAAK;AAAA,EACjC;AAAA,EAH6B;AAAA,EAHZ;AAAA,EACA,aAAa,oBAAI,IAA4B;AAAA,EAO9D,MAAM,QAAQ,OAA4C;AACxD,SAAK,iBAAiB,KAAK;AAC3B,SAAK,gBAAgB,KAAK;AAC1B,UAAM,SAAS,KAAK,SAAS,KAAK;AAClC,UAAM,OAAO,KAAK,cAAc,MAAM,MAAM;AAC5C,UAAM,OAAO,GAAG,KAAK,UAAU,MAAM,CAAC;AAAA;AAItC,eAAW,MAAM,IAAI;AAAA,EACvB;AAAA,EAEA,MAAM,OAAO,MAAmE;AAC9E,QAAI,CAAC,KAAK,OAAO;AACf,YAAM,IAAI;AAAA,QACR;AAAA,QACA;AAAA,MACF;AAAA,IACF;AACA,QAAI,CAAC,KAAK,gBAAgB;AACxB,YAAM,IAAI;AAAA,QACR;AAAA,QACA;AAAA,MACF;AAAA,IACF;AAEA,UAAM,MAA+B,CAAC;AACtC,eAAW,UAAU,aAAa;AAGhC,UAAI,KAAK,UAAU,WAAW,WAAW,oBAAoB;AAC3D,cAAM,WAAW,qBAAqB,KAAK,QAAQ,QAAQ,kBAAkB;AAC7E,YAAI,CAAC,SAAU;AAAA,MACjB;AACA,YAAM,OAAO,KAAK,cAAc,MAAM;AACtC,UAAI,CAAC,WAAW,IAAI,EAAG;AACvB,YAAM,QAAQ,aAAa,MAAM,MAAM,EAAE,MAAM,IAAI,EAAE,OAAO,OAAO;AACnE,iBAAW,QAAQ,OAAO;AACxB,YAAI;AACJ,YAAI;AACF,mBAAS,KAAK,MAAM,IAAI;AAAA,QAC1B,QAAQ;AACN;AAAA,QACF;AACA,YAAI,CAAC,cAAc,QAAQ,MAAM,MAAM,EAAG;AAC1C,YAAI,KAAK,MAAM;AAAA,MACjB;AAAA,IACF;AAGA,QAAI,KAAK,CAAC,GAAG,MAAM;AACjB,UAAI,EAAE,eAAe,EAAE,WAAY,QAAO,EAAE,WAAW,cAAc,EAAE,UAAU;AACjF,aAAO,EAAE,WAAW,cAAc,EAAE,UAAU;AAAA,IAChD,CAAC;AAED,WAAO,IAAI,MAAM,GAAG,KAAK,KAAK;AAAA,EAChC;AAAA,EAEA,MAAM,OAAmF;AACvF,UAAM,WAAmC,CAAC;AAC1C,QAAI,QAAQ;AACZ,eAAW,UAAU,aAAa;AAChC,YAAM,OAAO,KAAK,cAAc,MAAM;AACtC,UAAI,CAAC,WAAW,IAAI,GAAG;AACrB,iBAAS,MAAM,IAAI;AACnB;AAAA,MACF;AACA,YAAM,QAAQ,aAAa,MAAM,MAAM,EAAE,MAAM,IAAI,EAAE,OAAO,OAAO,EAAE;AACrE,eAAS,MAAM,IAAI;AACnB,eAAS;AAAA,IACX;AAIA,WAAO,EAAE,OAAO,OAAO,MAAM,OAAO,SAAS;AAAA,EAC/C;AAAA,EAEQ,iBAAiB,OAAmC;AAC1D,QAAI,CAAC,MAAM,QAAQ;AACjB,YAAM,IAAI;AAAA,QACR;AAAA,QACA;AAAA,MACF;AAAA,IACF;AACA,QAAI,CAAC,MAAM,qBAAqB,MAAM,kBAAkB,WAAW,GAAG;AACpE,YAAM,IAAI;AAAA,QACR;AAAA,QACA;AAAA,MACF;AAAA,IACF;AACA,QAAI,CAAC,MAAM,YAAY;AACrB,YAAM,IAAI;AAAA,QACR;AAAA,QACA;AAAA,MACF;AAAA,IACF;AACA,QAAI,CAAC,MAAM,iBAAiB;AAC1B,YAAM,IAAI;AAAA,QACR;AAAA,QACA;AAAA,MACF;AAAA,IACF;AACA,QAAI,CAAC,YAAY,SAAS,MAAM,MAAM,GAAG;AACvC,YAAM,IAAI;AAAA,QACR;AAAA,QACA,+CAA+C,YAAY,KAAK,IAAI,CAAC;AAAA,MACvE;AAAA,IACF;AAAA,EACF;AAAA,EAEQ,gBAAgB,OAAmC;AACzD,UAAM,MAAM,KAAK,QAAQ;AACzB,QAAI,CAAC,OAAO,CAAC,MAAM,gBAAiB;AACpC,UAAM,MAAM,KAAK,IAAI;AACrB,UAAM,WAAW;AACjB,QAAI,QAAQ,KAAK,WAAW,IAAI,MAAM,eAAe;AACrD,QAAI,CAAC,SAAS,MAAM,MAAM,iBAAiB,UAAU;AACnD,cAAQ,EAAE,QAAQ,MAAM,iBAAiB,eAAe,KAAK,OAAO,EAAE;AACtE,WAAK,WAAW,IAAI,MAAM,iBAAiB,KAAK;AAAA,IAClD;AACA,QAAI,MAAM,SAAS,KAAK;AACtB,YAAM,IAAI;AAAA,QACR;AAAA,QACA,gCAAgC,MAAM,eAAe,aAAa,GAAG;AAAA,MACvE;AAAA,IACF;AACA,UAAM,SAAS;AAAA,EACjB;AAAA,EAEQ,SAAS,OAAoD;AACnE,UAAM,aAAa;AAAA,MACjB,KAAK,UAAU;AAAA,QACb,IAAI,MAAM,SAAS;AAAA,QACnB,KAAK,MAAM;AAAA,QACX,IAAI,MAAM;AAAA,QACV,KAAK,MAAM;AAAA,MACb,CAAC;AAAA,IACH;AAGA,WAAO;AAAA,MACL,GAAG;AAAA,MACH;AAAA,MACA,OAAO;AAAA,IACT;AAAA,EACF;AAAA,EAEQ,cAAc,QAAwB;AAC5C,WAAOA,MAAK,KAAK,QAAQ,MAAM,GAAG,MAAM,QAAQ;AAAA,EAClD;AACF;AAEA,IAAM,cAAgD;AAAA,EACpD;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AACF;AAEA,SAAS,qBACP,QACA,QACS;AACT,MAAI,CAAC,OAAQ,QAAO;AACpB,MAAI,MAAM,QAAQ,MAAM,EAAG,QAAO,OAAO,SAAS,MAAM;AACxD,SAAO,WAAW;AACpB;AAEA,SAAS,cACP,QACA,MACA,QACS;AAET,MAAI,KAAK,UAAU,WAAW,OAAO,cAAc,KAAK,eAAgB,QAAO;AAC/E,MAAI,KAAK,UAAU,UAAU,OAAO,aAAa,KAAK,eAAgB,QAAO;AAE7E,QAAM,IAAI,KAAK;AACf,MAAI,CAAC,EAAG,QAAO;AACf,MAAI,EAAE,QAAQ,OAAO,SAAS,SAAS,EAAE,KAAM,QAAO;AACtD,MAAI,EAAE,QAAQ;AACZ,UAAM,UAAU,MAAM,QAAQ,EAAE,MAAM,IAAI,EAAE,SAAS,CAAC,EAAE,MAAM;AAC9D,QAAI,CAAC,QAAQ,SAAS,MAAe,EAAG,QAAO;AAAA,EACjD;AACA,MAAI,EAAE,iBAAiB,UAAa,EAAE,iBAAiB,QAAW;AAChE,UAAM,aAAa,OAAO,OAAO,OAAO,WAAW,EAAE,IAAI,CAAC,MAAM,EAAE,SAAS;AAC3E,UAAM,MAAM,WAAW,WAAW,IAAI,IAAI,KAAK,IAAI,GAAG,UAAU;AAChE,QAAI,EAAE,iBAAiB,UAAa,MAAM,EAAE,aAAc,QAAO;AACjE,QAAI,EAAE,iBAAiB,UAAa,MAAM,EAAE,aAAc,QAAO;AAAA,EACnE;AACA,SAAO;AACT;AAEA,SAAS,OAAO,OAAuB;AACrC,SAAO,WAAW,QAAQ,EAAE,OAAO,KAAK,EAAE,OAAO,KAAK,EAAE,MAAM,GAAG,EAAE;AACrE;AAEA,SAAS,WAAW,MAAc,MAAoB;AACpD,MAAI,WAAW,IAAI,GAAG;AACpB,UAAM,WAAW,aAAa,MAAM,MAAM;AAC1C,IAAAD,eAAc,MAAM,WAAW,IAAI;AAAA,EACrC,OAAO;AACL,IAAAA,eAAc,MAAM,IAAI;AAAA,EAC1B;AACF;;;ACtQA,eAAsB,QACpB,MAC+C;AAC/C,SAAO,YAAY,IAAI;AACzB;;;ACHA,SAAS,cAAAE,mBAAkB;AAiD3B,eAAsB,gBACpB,MACsD;AACtD,QAAM,cAAc,KAAK,eAAe;AAGxC,QAAM,mBAAmB,MAAM,YAAkC;AAAA,IAC/D,GAAG;AAAA,IACH,UAAU,CAAC,UAAU,QAAQ,KAAK,oBAAoB,KAAK,iBAAiB,UAAU,GAAG;AAAA,IACzF,QAAQ,GAAG,KAAK,MAAM;AAAA,EACxB,CAAC;AAED,QAAM,cAA0E,CAAC;AACjF,QAAM,UAA8B,CAAC;AACrC,MAAI,kBAAoC,CAAC,KAAK,eAAe;AAC7D,MAAI,gBAAgB,KAAK;AACzB,MAAI,oBAAoB,YAAY,KAAK,eAAe;AACxD,MAAI,kBAAkBC,eAAc,gBAAgB;AAEpD,WAAS,MAAM,GAAG,MAAM,KAAK,gBAAgB,OAAO;AAElD,QAAI,KAAK,OAAO,SAAS,EAAE,QAAQ,CAAC,EAAE,KAAM;AAI5C,UAAM,aAAa,MAAM,KAAK,OAAO,QAAQ;AAAA,MAC3C,gBAAgB,gBAAgB,CAAC,KAAK,KAAK;AAAA,MAC3C;AAAA,MACA,UAAU,CAAC;AAAA,MACX,gBAAgB,KAAK;AAAA,MACrB,YAAY;AAAA,MACZ,QAAQ,IAAI,gBAAgB,EAAE;AAAA,MAC9B,QAAQ,KAAK;AAAA,MACb,SAAS,KAAK,gBAAgB,KAAK,iBAAiB,QAAQ,KAAK,eAAe;AAAA,MAChF,qBAAqB,KAAK;AAAA,IAC5B,CAAC;AAGD,UAAM,iBAKD,CAAC;AACN,aAAS,IAAI,GAAG,IAAI,WAAW,QAAQ,KAAK;AAC1C,YAAM,UAAU,WAAW,CAAC;AAC5B,YAAM,OAAO,YAAY,OAAO;AAChC,YAAM,WAAW,MAAM,YAAkC;AAAA,QACvD,GAAG;AAAA,QACH,UAAU,CAAC,UAAU,QAAQ,KAAK,oBAAoB,SAAS,UAAU,GAAG;AAAA,QAC5E,QAAQ,GAAG,KAAK,MAAM,QAAQ,GAAG,cAAc,CAAC;AAAA,MAClD,CAAC;AACD,YAAM,YAAYA,eAAc,QAAQ;AACxC,qBAAe,KAAK,EAAE,aAAa,MAAM,SAAS,UAAU,UAAU,CAAC;AAAA,IACzE;AAGA,mBAAe,KAAK,CAAC,GAAG,MAAM,EAAE,YAAY,EAAE,SAAS;AACvD,UAAM,WAAW,eAAe,MAAM,GAAG,WAAW;AACpD,sBAAkB,SAAS,IAAI,CAAC,MAAM,EAAE,OAAO;AAC/C,UAAM,MAAM,eAAe,CAAC;AAC5B,QAAI,OAAO,IAAI,YAAY,iBAAiB;AAC1C,sBAAgB,IAAI;AACpB,0BAAoB,IAAI;AACxB,wBAAkB,IAAI;AAAA,IACxB;AAEA,UAAM,SAA2B;AAAA,MAC/B,iBAAiB;AAAA,MACjB,YAAY,eAAe,IAAI,CAAC,OAAO;AAAA,QACrC,aAAa,EAAE;AAAA,QACf,WAAW,EAAE;AAAA,QACb,MAAM,CAAC,EAAE,WAAW,EAAE,SAAS;AAAA,MACjC,EAAE;AAAA,MACF,UAAU,SAAS,IAAI,CAAC,MAAM,EAAE,WAAW;AAAA,IAC7C;AACA,YAAQ,KAAK,MAAM;AACnB,gBAAY,KAAK;AAAA,MACf;AAAA,MACA,UAAU,eAAe,IAAI,CAAC,OAAO;AAAA,QACnC,aAAa,EAAE;AAAA,QACf,SAAS,EAAE;AAAA,QACX,UAAU,EAAE;AAAA,MACd,EAAE;AAAA,IACJ,CAAC;AAAA,EACH;AAEA,SAAO;AAAA,IACL;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,EACF;AACF;AAEO,SAAS,YAAY,SAAiC;AAG3D,QAAM,WACJ,OAAO,YAAY,WACf,UACA,KAAK,UAAU;AAAA,IACb,MAAM,QAAQ;AAAA,IACd,aAAa,QAAQ;AAAA,IACrB,SAAS,QAAQ,WAAW;AAAA,EAC9B,CAAC;AACP,SAAOC,YAAW,QAAQ,EAAE,OAAO,QAAQ,EAAE,OAAO,KAAK,EAAE,MAAM,GAAG,EAAE;AACxE;AAEA,SAASD,eACP,UACQ;AACR,QAAM,aAAuB,CAAC;AAC9B,aAAW,QAAQ,SAAS,OAAO;AACjC,UAAM,iBAAiB,OAAO,OAAO,KAAK,WAAW,EAAE,IAAI,CAAC,MAAM,EAAE,SAAS;AAC7E,QAAI,eAAe,SAAS,GAAG;AAC7B,iBAAW,KAAK,eAAe,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,eAAe,MAAM;AAAA,IACnF;AAAA,EACF;AACA,SAAO,WAAW,WAAW,IAAI,IAAI,WAAW,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI,WAAW;AAC1F;;;AC5HA,eAAsB,mBACpB,MACyD;AAGzD,MAAK,KAAa,kBAAkB,UAAU;AAC5C,UAAM,IAAI;AAAA,MACR;AAAA,IACF;AAAA,EACF;AAKA,MAAI,KAAK,YAAY,SAAS,KAAK,QAAQ;AACzC,UAAM,IAAI;AAAA,MACR;AAAA,IACF;AAAA,EACF;AACA,MAAI,KAAK,kBAAkB,SAAS,CAAC,KAAK,WAAW,CAAC,KAAK,SAAS;AAClE,UAAM,IAAI,MAAM,mEAAmE;AAAA,EACrF;AAGA,QAAM,eAAe,MAAM,gBAAgB,IAAI;AAG/C,QAAM,EAAE,aAAAE,aAAY,IAAI,MAAM,OAAO,6BAAiB;AAEtD,QAAM,oBAAoB,MAAMA,aAAkC;AAAA,IAChE,GAAG;AAAA,IACH,WAAW,KAAK;AAAA,IAChB,UAAU,CAAC,UAAU,QAAQ,KAAK,oBAAoB,KAAK,iBAAiB,UAAU,GAAG;AAAA,IACzF,QAAQ,GAAG,KAAK,MAAM;AAAA,EACxB,CAAC;AAED,QAAM,kBAAkB,MAAMA,aAAkC;AAAA,IAC9D,GAAG;AAAA,IACH,WAAW,KAAK;AAAA,IAChB,UAAU,CAAC,UAAU,QACnB,KAAK,oBAAoB,aAAa,eAAe,UAAU,GAAG;AAAA,IACpE,QAAQ,GAAG,KAAK,MAAM;AAAA,EACxB,CAAC;AAGD,QAAM,qBAAqB,oBAAI,IAAuB;AACtD,QAAM,oBAAoB,oBAAI,IAAuB;AACrD,QAAM,cAAc,oBAAI,IAGtB;AACF,aAAW,QAAQ,gBAAgB,OAAO;AACxC,uBAAmB,IAAI,KAAK,QAAQ,KAAK,QAAQ;AACjD,gBAAY,IAAI,KAAK,QAAQ,KAAK,WAAW;AAAA,EAC/C;AACA,aAAW,QAAQ,kBAAkB,OAAO;AAC1C,sBAAkB,IAAI,KAAK,QAAQ,KAAK,QAAQ;AAChD,UAAM,QAAQ,YAAY,IAAI,KAAK,MAAM,KAAK,CAAC;AAC/C,gBAAY,IAAI,KAAK,QAAQ,EAAE,GAAG,OAAO,GAAG,KAAK,YAAY,CAAC;AAAA,EAChE;AAEA,QAAM,aAAa,MAAM,KAAK,KAAK,OAAO;AAAA,IACxC;AAAA,IACA;AAAA,IACA;AAAA,IACA,WAAW,KAAK;AAAA,IAChB,MAAM;AAAA,MACJ,WAAW,gBAAgB,WAAW;AAAA,MACtC,UAAU,kBAAkB,WAAW;AAAA,IACzC;AAAA,IACA,QAAQ,IAAI,gBAAgB,EAAE;AAAA,EAChC,CAAC;AAGD,MAAI;AACJ,MAAI,KAAK,kBAAkB,QAAQ,WAAW,aAAa,QAAQ;AACjE,UAAM,SAAS,KAAK,sBAAsB;AAC1C,UAAM,eAAe,OAAO,aAAa,eAAe,KAAK,eAAe;AAC5E,eAAW,WAAW;AAAA,MACpB,QAAQ;AAAA,MACR,MAAM;AAAA,MACN;AAAA,MACA,SAAS,KAAK;AAAA,MACd,QAAQ,KAAK;AAAA,IACf,CAAC;AAAA,EACH;AAEA,SAAO;AAAA,IACL,GAAG;AAAA,IACH;AAAA,IACA;AAAA,IACA;AAAA,IACA;AAAA,EACF;AACF;AAEA,SAAS,kBAAkB,eAA+B,iBAAyC;AAGjG,MAAI,OAAO,kBAAkB,YAAY,OAAO,oBAAoB,UAAU;AAC5E,UAAM,MAAM,CAAC,MACX,OAAO,MAAM,WACT,qBACA,YAAY,EAAE,WAAW,GAAG,EAAE,UAAU,SAAS,EAAE,OAAO,KAAK,EAAE,GAAG,EAAE,UAAU;AAAA,EAAK,EAAE,OAAO,KAAK,EAAE;AAC3G,WAAO;AAAA,EAAiB,IAAI,eAAe,CAAC;AAAA;AAAA,EAAiB,IAAI,aAAa,CAAC;AAAA,EACjF;AACA,QAAM,QAAkB,CAAC;AACzB,QAAM,KAAK,cAAc;AACzB,QAAM,KAAK,YAAY;AACvB,aAAW,KAAK,gBAAgB,MAAM,IAAI,EAAG,OAAM,KAAK,KAAK,CAAC,EAAE;AAChE,aAAW,KAAK,cAAc,MAAM,IAAI,EAAG,OAAM,KAAK,KAAK,CAAC,EAAE;AAC9D,SAAO,MAAM,KAAK,IAAI;AACxB;;;AClKA,SAAS,oBAAoB;AAC7B,SAAS,cAAAC,mBAAkB;AAC3B,SAAS,UAAU,YAAY,QAAAC,aAAY;AAuBpC,IAAM,uBAAN,cAAmC,MAAM;AAAA,EAC9C,YACE,SACS,OACT;AACA,UAAM,OAAO;AAFJ;AAGT,SAAK,OAAO;AAAA,EACd;AAAA,EAJW;AAKb;AAaA,SAAS,WAAW,MAAgB,KAAqB;AACvD,MAAI;AACF,WAAO,aAAa,OAAO,MAAM,EAAE,KAAK,UAAU,OAAO,CAAC,EAAE,KAAK;AAAA,EACnE,SAAS,KAAK;AACZ,UAAM,SACJ,OAAO,OAAO,QAAQ,YAAY,YAAY,MAC1C,OAAQ,IAA4B,MAAM,IAC1C;AACN,UAAM,IAAI,qBAAqB,OAAO,KAAK,KAAK,GAAG,CAAC,YAAY,UAAU,OAAO,GAAG,CAAC,IAAI,GAAG;AAAA,EAC9F;AACF;AAGA,SAAS,KAAK,OAAuB;AACnC,SACE,MACG,YAAY,EACZ,QAAQ,eAAe,GAAG,EAC1B,QAAQ,YAAY,EAAE,EACtB,MAAM,GAAG,EAAE,KAAK;AAEvB;AAEO,SAAS,mBAAmB,MAAkD;AACnF,QAAM,MAAM,KAAK,OAAO;AACxB,QAAM,cAAc,KAAK,eAAeA,MAAK,KAAK,UAAU,YAAY;AACxE,QAAM,eAAe,KAAK,gBAAgB;AAE1C,SAAO;AAAA,IACL,MAAM,OAAO,EAAE,SAAS,MAAM,GAAG;AAC/B,YAAM,KAAK,GAAG,KAAK,KAAK,CAAC,IAAI,KAAK,IAAI,EAAE,SAAS,EAAE,CAAC,IAAI,KAAK,OAAO,EAAE,SAAS,EAAE,EAAE,MAAM,GAAG,CAAC,CAAC;AAC9F,YAAM,SAAS,GAAG,YAAY,IAAI,EAAE;AACpC,YAAM,OAAOA,MAAK,aAAa,EAAE;AACjC,UAAI,CAAC,YAAY,OAAO,MAAM,QAAQ,MAAM,OAAO,GAAG,KAAK,QAAQ;AACnE,aAAO,EAAE,MAAM,QAAQ,QAAQ;AAAA,IACjC;AAAA,IAEA,MAAM,SAAS,UAAU,SAAS;AAGhC,YAAM,SAAS,IAAI,CAAC,UAAU,aAAa,GAAG,SAAS,IAAI;AAC3D,UAAI,OAAO,SAAS,GAAG;AACrB,YAAI,CAAC,OAAO,IAAI,GAAG,SAAS,IAAI;AAChC,YAAI,CAAC,UAAU,MAAM,OAAO,GAAG,SAAS,IAAI;AAAA,MAC9C;AACA,aAAO;AAAA,QACL,MAAM;AAAA,QACN,aAAa,SAAS;AAAA,QACtB,SAAS,SAAS;AAAA,QAClB;AAAA,MACF;AAAA,IACF;AAAA,IAEA,MAAM,QAAQ,UAAU;AAGtB,UAAI,CAAC,YAAY,UAAU,WAAW,SAAS,IAAI,GAAG,KAAK,QAAQ;AACnE,UAAI,CAAC,UAAU,MAAM,SAAS,MAAM,GAAG,KAAK,QAAQ;AAAA,IACtD;AAAA,EACF;AACF;AAKO,SAAS,oBAAoB,SAAsB,aAA8B;AACtF,MAAI,WAAW,QAAQ,WAAW,KAAKD,YAAW,QAAQ,WAAW,EAAG,QAAO,QAAQ;AACvF,MAAI,YAAa,QAAOC,MAAK,aAAa,SAAS,QAAQ,WAAW,CAAC;AACvE,SAAO,QAAQ;AACjB;","names":["writeFileSync","join","createHash","meanComposite","createHash","runCampaign","existsSync","join"]}

package/dist/openapi.json

@@ -2,7 +2,7 @@
   "openapi": "3.1.0",
   "info": {
     "title": "@tangle-network/agent-eval — wire protocol",
-    "version": "0.40.1",
+    "version": "0.40.2",
     "description": "HTTP and stdio RPC interface to agent-eval. The TypeScript runtime is the source of truth; this spec is the contract that cross-language clients (Python, Rust, Go) generate from.\n\nWire-protocol version: 1.0.0. Bumps on breaking changes to request/response schemas.",
     "contact": {
       "name": "Tangle Network",

package/docs/design/self-improvement-engine.md

@@ -0,0 +1,130 @@
+# The self-improvement engine
+
+How the pieces compose into a closed loop that improves an agent over time.
+This builds on [`loop-taxonomy.md`](./loop-taxonomy.md) (the role vocabulary)
+— read that first. Here we describe the *engine*: the phases, the data flow,
+and where each existing primitive plugs in.
+
+## The closed loop, by phase
+
+```
+PHASE 1 — RUN
+  driver ↔ workers (sandbox) over scenarios
+  → traces emitted → TraceStore + LabeledScenarioStore (the dataset)
+  Every run feeds the dataset regardless of why it ran (see the flywheel
+  section in loop-taxonomy.md). This is the only source of improvement signal.
+
+PHASE 2 — ANALYZE                                  ← the research report is born here
+  trace analysts run over the accumulated traces
+  (today: runAnalystLoop steps 2–4 in agent-runtime)
+    - run the analyst registry over traces → findings
+    - persist findings to the ledger
+    - diff the new findings vs the baseline → research report
+  Output: a research report = { findings, diff } grounded in real traces.
+
+PHASE 3 — PROPOSE
+  ImprovementDriver.propose(input) → MutableSurface[]
+  input carries:
+    - currentSurface      the current best surface (prompt string or CodeSurface)
+    - history             prior generations + their scores
+    - report              the Phase-2 research report (findings + diff)
+    - traces              all traces (read access) — "all the data"
+    - dataset             the LabeledScenarioStore handle
+    - populationSize      BREADTH: how many candidate surfaces to return
+    - maxImprovementShots DEPTH: how many runLoop iterations each candidate
+                          generation may take (1..MAX_IMPROVEMENT_SHOTS)
+  For the code-tier (autoresearch) driver, propose() runs a FULL sandbox
+  runLoop: a driver↔worker(s) loop that reads report+traces+codebase and
+  produces the improvement as commits in ONE worktree per candidate.
+  Output: CodeSurface{ worktreeRef }[] (or string[] for prompt-tier).
+
+PHASE 4 — MEASURE
+  each candidate → runCampaign on the holdout set
+  (checks out the candidate's worktree, runs the worker against the changed
+   code/prompt, judges, scores). The measurement is driver-agnostic.
+
+PHASE 5 — GATE + PROMOTE
+  defaultProductionGate(winner vs baseline on holdout) → ship | hold | …
+  on ship → open a PR from the winning worktree (one worktree = one PR).
+
+  ↺ loop back to PHASE 1 with the promoted surface as the new baseline.
+```
+
+The improvement loop body (`runOptimization`) owns Phases 3–4; the gated
+shell (`runImprovementLoop`) adds Phase 5. Phases 1–2 are upstream — the
+run that produces traces, and the analysts that turn traces into a report.
+
+## `propose()` — the plan step, recursively agentic
+
+`propose()` does NOT run the worker and does NOT measure. It returns N
+candidate surfaces to measure next. *How* it produces them is per-driver and
+spans a cost spectrum:
+
+| Driver | `propose()` mechanism | Sandbox? | Output |
+|---|---|---|---|
+| `evolutionaryDriver` | mutate current surface text into N variants | no | `string[]` |
+| `analystDriver` (reflective) | LLM reads the report → drafts edits | LLM call | `string[]` / `CodeSurface[]` |
+| `autoresearchDriver` (code-tier) | **full sandbox runLoop** (≤ `maxImprovementShots`) reads report+traces+codebase → commits in one worktree | **yes** | `CodeSurface[]` |
+
+The recursion: generating *one* candidate (autoresearch `propose`) is itself a
+driver↔worker-in-a-sandbox loop, nested inside the *measurement* of that
+candidate (Phase 4), nested inside the improvement loop. "A loop whose step
+contains a loop."
+
+Two knobs, not one:
+- **`populationSize`** — breadth: how many candidates `propose()` returns.
+- **`maxImprovementShots`** — depth: how many runLoop iterations the
+  generating agent gets per candidate (N=1 → single-shot; N>1 → it can
+  iterate on its own change before handing it back to be measured).
+
+## Package boundaries (respecting the leaf direction)
+
+agent-eval is the leaf (imports nothing upstream). agent-runtime imports it.
+So:
+
+| Piece | Package | Why |
+|---|---|---|
+| `ImprovementDriver` contract | agent-eval | the shared interface; everyone implements it |
+| widened `propose()` input (report/traces/dataset) | agent-eval | part of the contract |
+| `evolutionaryDriver` | agent-eval | pure: dataset → surface, no sandbox |
+| **VCS-pluggable worktree adapter** | agent-eval | pure git/FS, no sandbox; produces `CodeSurface` |
+| `runOptimization` / `runImprovementLoop` | agent-eval | driver-agnostic loop body + gated shell |
+| `defaultProductionGate` | agent-eval | measurement-side safety |
+| **`autoresearchDriver`** (sandbox-spawning `propose`) | agent-runtime | needs the sandbox SDK + `runLoop` |
+| `analystDriver` (wraps the improvement adapter) | agent-runtime | depends on `runAnalystLoop` machinery |
+| trace analysts / `runAnalystLoop` (Phase 2) | agent-runtime | runs agents to analyze |
+
+## The worktree adapter (VCS-pluggable)
+
+One improvement = one worktree, PR-like (multiple commits allowed). The
+adapter abstracts the VCS so the driver code is VCS-agnostic:
+
+```ts
+interface WorktreeAdapter {
+  create(opts: { baseRef: string; label: string }): Promise<Worktree>
+  // ... agent commits into worktree.path ...
+  finalize(wt: Worktree, summary: string): Promise<CodeSurface>  // → { kind:'code', worktreeRef, baseRef, summary }
+  discard(wt: Worktree): Promise<void>
+}
+```
+
+- **git** impl ships first (`git worktree add` / branch / commit).
+- **jj** ([jj-vcs](https://github.com/jj-vcs/jj)) is a candidate second impl —
+  not built now; the interface exists so it can slot in without touching
+  driver code.
+
+The measurement (Phase 4) consumes a `CodeSurface` by checking out
+`worktreeRef` before running the worker; on promotion (Phase 5) the worktree
+becomes the PR branch.
+
+## Build sequence
+
+1. **agent-eval 0.40.2**: widen `propose()` input (additive optional
+   `report` / `traces` / `dataset` / `maxImprovementShots`); add the
+   VCS-pluggable worktree adapter with a git impl; multi-sink trace fan-out
+   helper.
+2. **agent-runtime 0.25.0**: `analystDriver` (wraps the improvement adapter,
+   fed the Phase-2 report); `autoresearchDriver` (sandbox runLoop `propose`);
+   default-on multi-sink tracing in `handleChatTurn`.
+3. Wire one consumer end-to-end (Phase 4 of the broader rollout), prove it,
+   then fan out.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-eval",
-  "version": "0.40.1",
+  "version": "0.40.2",
   "description": "Substrate for self-improving agents: traces, verifiable rewards, preferences, GEPA / reflective mutation, auto-research, replay, sequential anytime-valid stats, and release gates.",
   "homepage": "https://github.com/tangle-network/agent-eval#readme",
   "repository": {