@tangle-network/agent-app 0.43.12 → 0.43.13

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -89,7 +89,7 @@ if (result.gate.decision === 'ship') await ship(result.winnerSurface)
89
89
  | `baselineSurface` | — (required) | the surface the loop optimizes; start `''` |
90
90
  | `mutationPrimitives` | gepaProposer's own | your optimization levers (additive directives) |
91
91
  | `proposer` | `gepaProposer` | pass `evolutionaryProposer({ mutator })` for blind addendum rotation |
92
- | `gate` | `defaultProductionGate` (Δ 0.05) | `paretoSignificanceGate` for multi-objective; tune `deltaThreshold` for your rubric scale . To prove a held-out lift is real CONTENT and not just added prompt/mount FOOTPRINT, compose `neutralizationGate` (agent-eval >= 0.107.0, from `@tangle-network/agent-eval/campaign`) — a footprint-matched placebo arm. It needs `ctx.neutralizedJudgeScores` from `runImprovementLoop({ neutralize })`; `selfImprove`/this scaffold do not surface that option yet, so wire it at the `runImprovementLoop` level or re-export it in the scaffold first. |
92
+ | `gate` | `defaultProductionGate` (Δ 0.05) | `paretoSignificanceGate` for multi-objective; tune `deltaThreshold` for your rubric scale. To prove a held-out lift is real CONTENT and not just added prompt/mount FOOTPRINT, compose `neutralizationGate` (agent-eval >= 0.107.0, from `@tangle-network/agent-eval/campaign`) — a footprint-matched placebo arm. It needs `ctx.neutralizedJudgeScores` from `runImprovementLoop({ neutralize })`; `selfImprove`/this scaffold do not surface that option yet, so wire it at the `runImprovementLoop` level or re-export it in the scaffold first. |
93
93
  | `budget` | 3 gens × pop 2, 0.25 holdout | `budget.reps` (replicates → tighter CIs), `budget.promoteTopK`, `budget.holdoutScenarios` (explicit split), `budget.dollars` (cost cap) |
94
94
  | `expectUsage` | **`'assert'`** | the fail-loud backend-integrity guard. Leave at `'assert'` for real runs (a stub cell throws); set `'off'` ONLY for a deterministic offline/replay run |
95
95
  | `labeledStore` | off | capture every artifact + judge score (the dataset you ship + few-shot corpus); set `captureSource` (default `'eval-run'`) |
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@tangle-network/agent-app",
3
- "version": "0.43.12",
3
+ "version": "0.43.13",
4
4
  "packageManager": "pnpm@10.33.4",
5
5
  "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.",
6
6
  "keywords": [