@tangle-network/agent-app 0.1.14 → 0.2.0

package/dist/eval-campaign/index.d.ts

@@ -0,0 +1,75 @@
+import { JudgeVerdict } from '@tangle-network/agent-eval';
+export { EnsembleAggregate, JudgeVerdict, RunRecord, aggregateJudgeVerdicts } from '@tangle-network/agent-eval';
+import { Scenario, JudgeConfig } from '@tangle-network/agent-eval/campaign';
+export { CampaignResult, DispatchContext, Gate, ImprovementDriver, JudgeConfig, JudgeDimension, JudgeScore, LabeledScenarioStore, MutableSurface, Mutator, Scenario, defaultProductionGate, evolutionaryDriver, gepaDriver, paretoSignificanceGate, runCampaign } from '@tangle-network/agent-eval/campaign';
+export { SelfImproveBudget, SelfImproveOptions, SelfImproveResult, selfImprove } from '@tangle-network/agent-eval/contract';
+
+/**
+ * Eval-campaign — the app-shell's curated surface for a product's
+ * self-improvement loop, NOT a reimplementation.
+ *
+ * The loop ENGINE lives in `@tangle-network/agent-eval` (a peer dependency):
+ * `selfImprove` already owns the whole cycle — train/holdout split, the GEPA
+ * driver, the held-out production gate, durable provenance + hosted ingest, and
+ * every default. A product should NOT hand-roll `runImprovementLoop` +
+ * `emitLoopProvenance` around it (that is the boilerplate this surface exists to
+ * delete). It should call `selfImprove` with three things it actually owns:
+ * scenarios, an `agent` dispatch, and a `judge`.
+ *
+ * This module adds the one piece `selfImprove` does not own and which every
+ * multi-model product re-hand-rolls — the ensemble judge:
+ *
+ *   {@link buildEnsembleJudge} — turn a per-rubric `scoreOne` into a
+ *   `JudgeConfig` that fans out N uncorrelated judge calls and reduces them via
+ *   the substrate's `aggregateJudgeVerdicts` (survivor-mean, inter-rater spread,
+ *   fail-loud on all-failed). A product writes its rubric + one judge call; the
+ *   fan-out, partial-failure handling, and composite are the scaffold's.
+ *
+ * Everything else is a curated re-export so a product has ONE eval import:
+ * `selfImprove` + the gates + the drivers + the types. See
+ * `.claude/skills/eval-campaign/SKILL.md` for the wiring contract.
+ */
+
+/** Config for {@link buildEnsembleJudge}. `D` = the rubric's dimension union. */
+interface EnsembleJudgeConfig<TArtifact, TScenario extends Scenario, D extends string> {
+    /** Judge name — appears in traces and scorecards. */
+    name: string;
+    /** Stable-ordered rubric dimensions. Drives the `JudgeDimension` list AND the
+     *  reducer keys, so a judge that omits a dimension scores it 0 (never silently
+     *  dropped). */
+    rubric: readonly D[];
+    /**
+     * Score ONE artifact on the rubric → a raw per-dimension verdict. Called
+     * `judgeReps` times per artifact; vary the model by `rep` for an uncorrelated
+     * ensemble (judges that share a base model share its bias). Return
+     * `{ model, perDimension: null }` to record a judge failure WITHOUT killing
+     * the ensemble; throw only on an unrecoverable error (the whole rep is then
+     * treated as a failed judge).
+     */
+    scoreOne: (input: {
+        artifact: TArtifact;
+        scenario: TScenario;
+        signal: AbortSignal;
+        rep: number;
+    }) => Promise<JudgeVerdict<D>>;
+    /** Independent judge calls per artifact, reduced by `aggregateJudgeVerdicts`.
+     *  Default 1. Raise (with model variety in `scoreOne`) for inter-rater bands. */
+    judgeReps?: number;
+    /** Per-dimension composite weights. Default: uniform over `rubric`. A partial
+     *  map selects-and-weights exactly the named dimensions. */
+    weights?: Partial<Record<D, number>>;
+    /** Optional human-readable dimension descriptions. Default: the key itself. */
+    describe?: (dim: D) => string;
+}
+/**
+ * Build a `JudgeConfig` whose `score()` fans out `judgeReps` independent
+ * `scoreOne` calls and reduces them with the substrate's
+ * `aggregateJudgeVerdicts`. A single judge call failing does NOT fail the cell
+ * (it is recorded and dropped); only ALL judges failing throws — which the
+ * campaign records as a failed cell, never a silent zero.
+ *
+ * Pass the result straight to `selfImprove({ judge })` (or `runCampaign`).
+ */
+declare function buildEnsembleJudge<TArtifact, TScenario extends Scenario, D extends string>(cfg: EnsembleJudgeConfig<TArtifact, TScenario, D>): JudgeConfig<TArtifact, TScenario>;
+
+export { type EnsembleJudgeConfig, buildEnsembleJudge };

package/dist/eval-campaign/index.js

@@ -0,0 +1,47 @@
+// src/eval-campaign/index.ts
+import {
+  aggregateJudgeVerdicts
+} from "@tangle-network/agent-eval";
+import { aggregateJudgeVerdicts as aggregateJudgeVerdicts2 } from "@tangle-network/agent-eval";
+import {
+  defaultProductionGate,
+  evolutionaryDriver,
+  gepaDriver,
+  paretoSignificanceGate,
+  runCampaign
+} from "@tangle-network/agent-eval/campaign";
+import { selfImprove } from "@tangle-network/agent-eval/contract";
+function buildEnsembleJudge(cfg) {
+  const reps = cfg.judgeReps ?? 1;
+  if (reps < 1) {
+    throw new Error(`buildEnsembleJudge: judgeReps must be >= 1 (got ${reps})`);
+  }
+  if (cfg.rubric.length === 0) {
+    throw new Error("buildEnsembleJudge: rubric is empty");
+  }
+  return {
+    name: cfg.name,
+    dimensions: cfg.rubric.map((key) => ({ key, description: cfg.describe?.(key) ?? key })),
+    async score({ artifact, scenario, signal }) {
+      const settled = await Promise.allSettled(
+        Array.from({ length: reps }, (_, rep) => cfg.scoreOne({ artifact, scenario, signal, rep }))
+      );
+      const verdicts = settled.map(
+        (r, rep) => r.status === "fulfilled" ? r.value : { model: `${cfg.name}-rep${rep}`, perDimension: null, rationale: String(r.reason) }
+      );
+      const agg = aggregateJudgeVerdicts(verdicts, cfg.rubric, cfg.weights);
+      return { composite: agg.composite, dimensions: agg.perDimension, notes: agg.rationale };
+    }
+  };
+}
+export {
+  aggregateJudgeVerdicts2 as aggregateJudgeVerdicts,
+  buildEnsembleJudge,
+  defaultProductionGate,
+  evolutionaryDriver,
+  gepaDriver,
+  paretoSignificanceGate,
+  runCampaign,
+  selfImprove
+};
+//# sourceMappingURL=index.js.map

package/dist/eval-campaign/index.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../../src/eval-campaign/index.ts"],"sourcesContent":["/**\n * Eval-campaign — the app-shell's curated surface for a product's\n * self-improvement loop, NOT a reimplementation.\n *\n * The loop ENGINE lives in `@tangle-network/agent-eval` (a peer dependency):\n * `selfImprove` already owns the whole cycle — train/holdout split, the GEPA\n * driver, the held-out production gate, durable provenance + hosted ingest, and\n * every default. A product should NOT hand-roll `runImprovementLoop` +\n * `emitLoopProvenance` around it (that is the boilerplate this surface exists to\n * delete). It should call `selfImprove` with three things it actually owns:\n * scenarios, an `agent` dispatch, and a `judge`.\n *\n * This module adds the one piece `selfImprove` does not own and which every\n * multi-model product re-hand-rolls — the ensemble judge:\n *\n *   {@link buildEnsembleJudge} — turn a per-rubric `scoreOne` into a\n *   `JudgeConfig` that fans out N uncorrelated judge calls and reduces them via\n *   the substrate's `aggregateJudgeVerdicts` (survivor-mean, inter-rater spread,\n *   fail-loud on all-failed). A product writes its rubric + one judge call; the\n *   fan-out, partial-failure handling, and composite are the scaffold's.\n *\n * Everything else is a curated re-export so a product has ONE eval import:\n * `selfImprove` + the gates + the drivers + the types. See\n * `.claude/skills/eval-campaign/SKILL.md` for the wiring contract.\n */\n\nimport {\n  aggregateJudgeVerdicts,\n  type JudgeVerdict,\n} from '@tangle-network/agent-eval'\nimport type {\n  JudgeConfig,\n  JudgeScore,\n  Scenario,\n} from '@tangle-network/agent-eval/campaign'\n\n/** Config for {@link buildEnsembleJudge}. `D` = the rubric's dimension union. */\nexport interface EnsembleJudgeConfig<TArtifact, TScenario extends Scenario, D extends string> {\n  /** Judge name — appears in traces and scorecards. */\n  name: string\n  /** Stable-ordered rubric dimensions. Drives the `JudgeDimension` list AND the\n   *  reducer keys, so a judge that omits a dimension scores it 0 (never silently\n   *  dropped). */\n  rubric: readonly D[]\n  /**\n   * Score ONE artifact on the rubric → a raw per-dimension verdict. Called\n   * `judgeReps` times per artifact; vary the model by `rep` for an uncorrelated\n   * ensemble (judges that share a base model share its bias). Return\n   * `{ model, perDimension: null }` to record a judge failure WITHOUT killing\n   * the ensemble; throw only on an unrecoverable error (the whole rep is then\n   * treated as a failed judge).\n   */\n  scoreOne: (input: {\n    artifact: TArtifact\n    scenario: TScenario\n    signal: AbortSignal\n    rep: number\n  }) => Promise<JudgeVerdict<D>>\n  /** Independent judge calls per artifact, reduced by `aggregateJudgeVerdicts`.\n   *  Default 1. Raise (with model variety in `scoreOne`) for inter-rater bands. */\n  judgeReps?: number\n  /** Per-dimension composite weights. Default: uniform over `rubric`. A partial\n   *  map selects-and-weights exactly the named dimensions. */\n  weights?: Partial<Record<D, number>>\n  /** Optional human-readable dimension descriptions. Default: the key itself. */\n  describe?: (dim: D) => string\n}\n\n/**\n * Build a `JudgeConfig` whose `score()` fans out `judgeReps` independent\n * `scoreOne` calls and reduces them with the substrate's\n * `aggregateJudgeVerdicts`. A single judge call failing does NOT fail the cell\n * (it is recorded and dropped); only ALL judges failing throws — which the\n * campaign records as a failed cell, never a silent zero.\n *\n * Pass the result straight to `selfImprove({ judge })` (or `runCampaign`).\n */\nexport function buildEnsembleJudge<TArtifact, TScenario extends Scenario, D extends string>(\n  cfg: EnsembleJudgeConfig<TArtifact, TScenario, D>,\n): JudgeConfig<TArtifact, TScenario> {\n  const reps = cfg.judgeReps ?? 1\n  if (reps < 1) {\n    throw new Error(`buildEnsembleJudge: judgeReps must be >= 1 (got ${reps})`)\n  }\n  if (cfg.rubric.length === 0) {\n    throw new Error('buildEnsembleJudge: rubric is empty')\n  }\n  return {\n    name: cfg.name,\n    dimensions: cfg.rubric.map((key) => ({ key, description: cfg.describe?.(key) ?? key })),\n    async score({ artifact, scenario, signal }): Promise<JudgeScore> {\n      const settled = await Promise.allSettled(\n        Array.from({ length: reps }, (_, rep) => cfg.scoreOne({ artifact, scenario, signal, rep })),\n      )\n      const verdicts: JudgeVerdict<D>[] = settled.map((r, rep) =>\n        r.status === 'fulfilled'\n          ? r.value\n          : { model: `${cfg.name}-rep${rep}`, perDimension: null, rationale: String(r.reason) },\n      )\n      // Throws iff EVERY rep failed → the campaign records a failed cell.\n      const agg = aggregateJudgeVerdicts(verdicts, cfg.rubric, cfg.weights)\n      return { composite: agg.composite, dimensions: agg.perDimension, notes: agg.rationale }\n    },\n  }\n}\n\n// ── Curated re-exports — the one eval import for a product loop ──────────────\n// The loop engine + gates + drivers + the ensemble reducer, so a product wires\n// its self-improvement loop from a single module instead of reaching across\n// three agent-eval subpaths. All DOWNWARD imports (agent-app consumes the\n// substrate); the layering rule is preserved.\n\nexport { aggregateJudgeVerdicts } from '@tangle-network/agent-eval'\nexport type {\n  EnsembleAggregate,\n  JudgeVerdict,\n  RunRecord,\n} from '@tangle-network/agent-eval'\nexport {\n  defaultProductionGate,\n  evolutionaryDriver,\n  gepaDriver,\n  paretoSignificanceGate,\n  runCampaign,\n} from '@tangle-network/agent-eval/campaign'\nexport type {\n  CampaignResult,\n  DispatchContext,\n  Gate,\n  ImprovementDriver,\n  JudgeConfig,\n  JudgeDimension,\n  JudgeScore,\n  LabeledScenarioStore,\n  MutableSurface,\n  Mutator,\n  Scenario,\n} from '@tangle-network/agent-eval/campaign'\nexport { selfImprove } from '@tangle-network/agent-eval/contract'\nexport type {\n  SelfImproveBudget,\n  SelfImproveOptions,\n  SelfImproveResult,\n} from '@tangle-network/agent-eval/contract'\n"],"mappings":";AA0BA;AAAA,EACE;AAAA,OAEK;AAmFP,SAAS,0BAAAA,+BAA8B;AAMvC;AAAA,EACE;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,OACK;AAcP,SAAS,mBAAmB;AA7DrB,SAAS,mBACd,KACmC;AACnC,QAAM,OAAO,IAAI,aAAa;AAC9B,MAAI,OAAO,GAAG;AACZ,UAAM,IAAI,MAAM,mDAAmD,IAAI,GAAG;AAAA,EAC5E;AACA,MAAI,IAAI,OAAO,WAAW,GAAG;AAC3B,UAAM,IAAI,MAAM,qCAAqC;AAAA,EACvD;AACA,SAAO;AAAA,IACL,MAAM,IAAI;AAAA,IACV,YAAY,IAAI,OAAO,IAAI,CAAC,SAAS,EAAE,KAAK,aAAa,IAAI,WAAW,GAAG,KAAK,IAAI,EAAE;AAAA,IACtF,MAAM,MAAM,EAAE,UAAU,UAAU,OAAO,GAAwB;AAC/D,YAAM,UAAU,MAAM,QAAQ;AAAA,QAC5B,MAAM,KAAK,EAAE,QAAQ,KAAK,GAAG,CAAC,GAAG,QAAQ,IAAI,SAAS,EAAE,UAAU,UAAU,QAAQ,IAAI,CAAC,CAAC;AAAA,MAC5F;AACA,YAAM,WAA8B,QAAQ;AAAA,QAAI,CAAC,GAAG,QAClD,EAAE,WAAW,cACT,EAAE,QACF,EAAE,OAAO,GAAG,IAAI,IAAI,OAAO,GAAG,IAAI,cAAc,MAAM,WAAW,OAAO,EAAE,MAAM,EAAE;AAAA,MACxF;AAEA,YAAM,MAAM,uBAAuB,UAAU,IAAI,QAAQ,IAAI,OAAO;AACpE,aAAO,EAAE,WAAW,IAAI,WAAW,YAAY,IAAI,cAAc,OAAO,IAAI,UAAU;AAAA,IACxF;AAAA,EACF;AACF;","names":["aggregateJudgeVerdicts"]}

package/dist/index.js

@@ -1,3 +1,10 @@
+import {
+  addSecurityHeaders,
+  checkRateLimit,
+  extractRequestContext,
+  parseJsonObjectBody,
+  requireString
+} from "./chunk-CN75FIPT.js";
 import {
   DEFAULT_REDACTION_PATTERNS,
   buildRedactedDocument,
@@ -6,6 +13,11 @@ import {
   redactForIngestion,
   revealSpan
 } from "./chunk-5RMIUJDI.js";
+import {
+  createKnowledgeLoop,
+  createReviewerDecider,
+  reviewCandidate
+} from "./chunk-EEPJGZJW.js";
 import {
   DEFAULT_HARNESS,
   KNOWN_HARNESSES,
@@ -65,13 +77,6 @@ import {
   invokeIntegrationHub,
   resolveIntegrationAction
 } from "./chunk-L2TG5DBW.js";
-import {
-  addSecurityHeaders,
-  checkRateLimit,
-  extractRequestContext,
-  parseJsonObjectBody,
-  requireString
-} from "./chunk-CN75FIPT.js";
 import {
   DEFAULT_APP_TOOL_PATHS,
   DEFAULT_HEADER_NAMES,
@@ -123,11 +128,6 @@ import {
   buildKnowledgeRequirements,
   deriveSignals
 } from "./chunk-ZXNXAQAH.js";
-import {
-  createKnowledgeLoop,
-  createReviewerDecider,
-  reviewCandidate
-} from "./chunk-EEPJGZJW.js";
 export {
   APP_TOOL_NAMES,
   DEFAULT_APP_TOOL_PATHS,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-app",
-  "version": "0.1.14",
+  "version": "0.2.0",
   "packageManager": "pnpm@10.33.4",
   "description": "Application-shell framework for Tangle agent products: a bounded tool loop, the structured agent→app tool side channel, integration-hub client, per-workspace billing, and crypto — composed over the Tangle agent substrate through typed seams.",
   "keywords": [
@@ -61,6 +61,11 @@
       "import": "./dist/eval/index.js",
       "default": "./dist/eval/index.js"
     },
+    "./eval-campaign": {
+      "types": "./dist/eval-campaign/index.d.ts",
+      "import": "./dist/eval-campaign/index.js",
+      "default": "./dist/eval-campaign/index.js"
+    },
     "./knowledge": {
       "types": "./dist/knowledge/index.d.ts",
       "import": "./dist/knowledge/index.js",
@@ -131,7 +136,7 @@
     "typecheck": "tsc --noEmit"
   },
   "devDependencies": {
-    "@tangle-network/agent-eval": "^0.70.0",
+    "@tangle-network/agent-eval": "^0.82.0",
     "@tangle-network/agent-integrations": "^0.32.0",
     "@tangle-network/agent-knowledge": "^1.5.2",
     "@types/node": "^25.6.0",
@@ -140,7 +145,7 @@
     "vitest": "^3.0.0"
   },
   "peerDependencies": {
-    "@tangle-network/agent-eval": ">=0.50.0",
+    "@tangle-network/agent-eval": ">=0.82.0",
     "@tangle-network/agent-integrations": ">=0.32.0",
     "@tangle-network/agent-knowledge": ">=1.5.0",
     "@tangle-network/agent-runtime": ">=0.21.0"