feat(confidence-engine): add serializeFocusedInvestigationEvidence evidence serializer and deterministic test

Apparatus-level pure serialization function that preserves all five
focused-deconstruction arrays (observations, uncertainties, assumptions,
relationships, possibleFollowUpQuestions) plus exact inputs and execution
metadata from the existing checkpoint — without modifying production code.

Deterministic verification: syntax check pass, 79/79 assertions pass
(including 28 new evidence-ser tests), zero live calls.

Experiment 4's missing structured output cannot be reconstructed (never
persisted by the apparatus). No new semantic evidence produced.
This commit is contained in:
2026-10-09 14:25:26 +01:00
parent 7fd05745e8
commit 7d7a9e8d29
4 changed files with 205 additions and 2 deletions
+64 -1
View File
@@ -520,4 +520,67 @@ async function composeDeepInvestigationCheckpoint({ situationGraph, previousQues
};
}
module.exports = { runLiveExperiment, extractLiveExperimentCheckpoint, _extractReasoningState, composeDeepInvestigationCheckpoint };
/**
* Serialize a completed deep-investigation checkpoint into the durable
* focused-deconstruction evidence record.
*
* Pure function — no side effects, no I/O, no model calls. Intended for
* deterministic test fixtures and external audit tools that need a stable
* JSON-serializable representation of the five deconstruction arrays plus
* exact input values and execution metadata.
*
* @param {object} checkpoint — returned from composeDeepInvestigationCheckpoint()
* @param {object} identity — { experimentId, scenarioId, targetNodeId, evidenceDesignation }
* - experimentId: unique identifier for the experiment run
* - scenarioId: identifier for the scenario (e.g. "HS-03C")
* - targetNodeId: the situationGraph node that was selected as focus
* - evidenceDesignation: "synthetic" or "real-user" (or any string)
* @param {object} [metadata] — optional execution metadata from the apparatus
* - modelName, providerGenerateCalls, modelElapsedMs, endToEndElapsedMs, success
* Any missing field is set to null (never fabricated).
* @returns {object} JSON-serializable evidence record per fixed contract
*/
function serializeFocusedInvestigationEvidence(checkpoint, identity, metadata) {
/* ── Extract the five structured deconstruction arrays ────────────── */
const contributions = Array.isArray(checkpoint?.postEpisodeContributions)
? checkpoint.postEpisodeContributions
: [];
// There should be exactly one contribution per focused-investigation run;
// if multiple exist (episode path with accumulated contributions),
// take the first one that carries the deconstruction arrays.
const deconContribution = contributions.find(
(c) => Array.isArray(c?.observations) && Array.isArray(c?.uncertainties)
) || contributions[0] || {};
return {
/* ── Identity (supplied by caller, not derived) ─────────────────── */
experimentId: identity.experimentId ?? null,
scenarioId: identity.scenarioId ?? null,
targetNodeId: identity.targetNodeId ?? null,
evidenceDesignation: identity.evidenceDesignation ?? null,
/* ── Exact focused-investigation inputs (from checkpoint) ──────── */
canonicalTargetDescription: checkpoint.focusedInvestigationInput?.targetDescription ?? "",
actualQuestion: checkpoint.focusedInvestigationInput?.question ?? "",
exactAnswer: checkpoint.focusedInvestigationInput?.answer ?? "",
/* ── Structured model output (preserved verbatim, no transformation) ─── */
observations: deconContribution.observations ?? null,
uncertainties: deconContribution.uncertainties ?? null,
assumptions: deconContribution.assumptions ?? null,
relationships: deconContribution.relationships ?? null,
possibleFollowUpQuestions: deconContribution.possibleFollowUpQuestions ?? null,
/* ── Execution metadata (supplied by caller; null when not exposed) ─ */
modelName: metadata?.modelName ?? null,
providerGenerateCalls: metadata?.providerGenerateCalls ?? null,
modelElapsedMs: metadata?.modelElapsedMs ?? null,
endToEndElapsedMs: metadata?.endToEndElapsedMs ?? null,
executionStatus: (metadata?.success !== undefined)
? (metadata.success === true ? "completed" : "failed")
: null,
};
}
module.exports = { runLiveExperiment, extractLiveExperimentCheckpoint, _extractReasoningState, composeDeepInvestigationCheckpoint, serializeFocusedInvestigationEvidence };