@themoltnet/pi-extension 0.31.2 → 0.32.0

package/dist/index.js

@@ -14226,6 +14226,86 @@ var PRODUCER_TASK_TYPES = new Set([
 	"render_pack",
 	"run_eval"
 ]);
+function isNonEmptyString(value) {
+	return typeof value === "string" && value.length > 0;
+}
+function criterionWeight(criterion, index) {
+	if (typeof criterion.weight === "number") return criterion.weight;
+	if (typeof criterion.max_score === "number") return criterion.max_score / 100;
+	if (typeof criterion.maxScore === "number") return criterion.maxScore / 100;
+	throw new TaskBuildError([{
+		field: `successCriteria/rubric/criteria/${index}/weight`,
+		message: "criterion is missing weight or max_score"
+	}]);
+}
+/**
+* Normalize authoring-time rubric criteria to canonical MoltNet rubric
+* criteria. Accepts `{id,title,description,weight}` and
+* `{name,description,max_score}` style inputs, strips authoring-only fields,
+* and fills a default scoring mode.
+*/
+function normalizeRubricCriteria(criteria, options) {
+	const errors = [];
+	const normalized = criteria.map((criterion, index) => {
+		const id = criterion.id ?? criterion.name;
+		const description = criterion.description ?? criterion.title;
+		if (!isNonEmptyString(id)) errors.push({
+			field: `successCriteria/rubric/criteria/${index}/id`,
+			message: "criterion is missing id or name"
+		});
+		if (!isNonEmptyString(description)) errors.push({
+			field: `successCriteria/rubric/criteria/${index}/description`,
+			message: "criterion is missing description or title"
+		});
+		return {
+			id: id ?? "",
+			description: description ?? "",
+			weight: criterionWeight(criterion, index),
+			scoring: criterion.scoring ?? options?.scoring ?? "llm_score"
+		};
+	});
+	if (errors.length > 0) throw new TaskBuildError(errors);
+	return normalized;
+}
+/**
+* Build a canonical `SuccessCriteria` envelope from rubric/checklist-style
+* criteria. This keeps rubrics readable at the authoring boundary while
+* preserving the strict task schema on the wire.
+*/
+function buildRubricSuccessCriteria(options) {
+	const rubric = {
+		rubricId: options.rubricId,
+		version: options.version ?? "v1",
+		criteria: normalizeRubricCriteria(options.criteria, { scoring: options.scoring }),
+		...options.contentHash ? { contentHash: options.contentHash } : {},
+		...options.preamble ? { preamble: options.preamble } : {},
+		...options.scope ? { scope: options.scope } : {}
+	};
+	const weightError = validateRubricWeights(rubric);
+	if (weightError) throw new TaskBuildError([{
+		field: "successCriteria/rubric/criteria",
+		message: weightError
+	}]);
+	return {
+		version: 1,
+		rubric
+	};
+}
+function resolveJudgeEvalAttemptTarget(target) {
+	if ("judgeEvalTarget" in target && typeof target.judgeEvalTarget === "function") return target.judgeEvalTarget();
+	if ("targetTaskId" in target) return {
+		targetTaskId: target.targetTaskId,
+		targetAttemptN: target.targetAttemptN
+	};
+	if ("taskId" in target) return {
+		targetTaskId: target.taskId,
+		targetAttemptN: target.accepted?.attemptN ?? target.attemptN ?? 1
+	};
+	throw new TaskBuildError([{
+		field: "target",
+		message: "judge_eval_attempt target is missing task id"
+	}]);
+}
 /**
 * Fluent, network-free builder for a `tasks.create` body. Encodes the
 * non-obvious task schema (context arrays, success-criteria gates,
@@ -14676,6 +14756,20 @@ function buildJudgeEvalAttempt(input) {
 	return buildTask("judge_eval_attempt", input);
 }
 /**
+* Build a `judge_eval_attempt` task from an accepted `run_eval` result (or a
+* small target tuple) plus human-friendly rubric criteria.
+*
+* @param target - A `TaskResultReader` or `{targetTaskId,targetAttemptN}` tuple.
+* @param options - Rubric metadata and eval/checklist-style criteria.
+* @returns A typed {@link TaskBuilder}.
+*/
+function buildJudgeEvalAttemptForRunEval(target, options) {
+	return buildJudgeEvalAttempt({
+		...resolveJudgeEvalAttemptTarget(target),
+		successCriteria: buildRubricSuccessCriteria(options)
+	});
+}
+/**
 * Build a `pr_review` task. Requires `subject` + `successCriteria`. Note the
 * rubric criteria must use `boolean` scoring for this task type.
 *
@@ -14713,7 +14807,9 @@ var TaskResultReader = class {
 	accepted;
 	/** Token / cost usage for the accepted attempt, if reported. */
 	usage;
+	/** Task id for the task whose accepted attempt is being read. */
 	taskId;
+	/** CID of the accepted attempt output. */
 	outputCid;
 	constructor(task, attempt) {
 		const errors = [];
@@ -14806,6 +14902,19 @@ var TaskResultReader = class {
 		};
 	}
 	/**
+	* Return the target tuple required by `judge_eval_attempt`.
+	*
+	* This intentionally uses the accepted attempt number, not merely the
+	* attempt object passed to the reader, so a downstream judge is pinned to
+	* the producer output that the task accepted.
+	*/
+	judgeEvalTarget() {
+		return {
+			targetTaskId: this.taskId,
+			targetAttemptN: this.accepted.attemptN
+		};
+	}
+	/**
 	* Build a `TaskRef` that anchors a downstream task to this accepted output
 	* and points at one persistent task artifact by CID.
 	*
@@ -14943,6 +15052,7 @@ function createTasksNamespace(context) {
 		buildAssessBrief,
 		buildJudgePack,
 		buildJudgeEvalAttempt,
+		buildJudgeEvalAttemptForRunEval,
 		buildPrReview,
 		async readResult(taskOrId) {
 			const task = typeof taskOrId === "string" ? unwrapResult(await getTask({
@@ -26317,7 +26427,8 @@ async function executePiTask(claimedTask, reporter, opts) {
 					const message = err instanceof Error ? err.message : String(err);
 					reporterError = {
 						code: "reporter_failed",
-						message
+						message,
+						retryable: true
 					};
 					process.stderr.write(`[reporter] ${message}\n`);
 				}
@@ -26527,9 +26638,11 @@ async function executePiTask(claimedTask, reporter, opts) {
 				retryable: false
 			}
 		};
-		const status = runError || llmAbort || parseError || reporterError ? "failed" : "completed";
-		const errorCode = runError?.code ?? parseError?.code ?? reporterError?.code ?? (llmAbort ? "llm_api_error" : void 0);
-		const errorMessage = runError?.message ?? parseError?.message ?? reporterError?.message ?? (llmAbort ? llmErrorMessage ?? "LLM API error during turn" : void 0);
+		const reporterErrorSnapshot = reporterError;
+		const status = runError || llmAbort || parseError || reporterErrorSnapshot ? "failed" : "completed";
+		const errorCode = runError?.code ?? parseError?.code ?? reporterErrorSnapshot?.code ?? (llmAbort ? "llm_api_error" : void 0);
+		const errorMessage = runError?.message ?? parseError?.message ?? reporterErrorSnapshot?.message ?? (llmAbort ? llmErrorMessage ?? "LLM API error during turn" : void 0);
+		const errorRetryable = reporterErrorSnapshot && errorCode === reporterErrorSnapshot.code && errorMessage === reporterErrorSnapshot.message ? reporterErrorSnapshot.retryable ?? false : false;
 		return {
 			taskId: task.id,
 			attemptN,
@@ -26541,7 +26654,7 @@ async function executePiTask(claimedTask, reporter, opts) {
 			...errorCode && errorMessage ? { error: {
 				code: errorCode,
 				message: errorMessage,
-				retryable: false
+				retryable: errorRetryable
 			} } : {}
 		};
 	} catch (err) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@themoltnet/pi-extension",
-  "version": "0.31.2",
+  "version": "0.32.0",
   "type": "module",
   "description": "MoltNet pi extension — sandboxed tool execution in Gondolin VMs with MoltNet identity and persistent memory",
   "keywords": [
@@ -36,8 +36,8 @@
     "@earendil-works/gondolin": "^0.9.1",
     "@opentelemetry/api": "^1.9.0",
     "typebox": "^1.2.8",
-    "@themoltnet/sdk": "0.117.0",
-    "@themoltnet/agent-runtime": "0.33.2"
+    "@themoltnet/agent-runtime": "0.34.0",
+    "@themoltnet/sdk": "0.118.0"
   },
   "peerDependencies": {
     "@earendil-works/pi-coding-agent": ">=0.74.0",