1fe56e9b6f
First Wave M / Phase B piece (GATING): read-only backend that makes the calibrated-learning / serving-discipline loop inspectable — 'the engine earns the right to guess', ADR-0175. The workbench computes NONE of these numbers: - GET /calibration/classes — per-class gold-tether view from the persisted practice arena ledger (evals/gsm8k_math/practice/v1/report.json per_class). Each class's reliability_floor is the engine's own one-sided Wilson conservative_floor (via ClassTally.reliability); PROPOSE (θ=0.85) / SERVE (θ=0.99) license verdicts come from core.reliability_gate.license_for. Failures-first ordering. A test proves the reader's floor equals a direct conservative_floor() call — no re-implementation. - GET /serving/metrics — the live correct/refused/wrong counts read unchanged from the committed train_sample + holdout_dev report.json (currently 4/46/0 and 5/495/0 — wrong=0). Never re-runs a lane. Honest current state: the committed practice ledger's three classes (additive/divisive/multiplicative) are all below N_MIN=10, so none has earned a license yet — the reader shows exactly that, no fake green light. - workbench/calibration.py: pure readers; imports core.reliability_gate; EvidenceUnavailableError -> 501 (fail-closed) when the artifact is absent. - schemas + TS mirrors (CalibrationClass, ServingMetrics); both snapshots regenerated (deterministic); both drift gates pass. - trust boundary: read-only over committed artifacts + engine-owned derivation; no execution, no mutation, no license ever changed. Verified: 30 Python tests (incl. the no-reimplementation proof + fail-closed), 390 vitest, both schema drift gates, snapshots deterministic.
287 lines
5.1 KiB
JSON
287 lines
5.1 KiB
JSON
{
|
|
"ArtifactDetail": [
|
|
"content_type",
|
|
"content"
|
|
],
|
|
"ArtifactRef": [
|
|
"artifact_id",
|
|
"kind",
|
|
"path",
|
|
"digest",
|
|
"created_at"
|
|
],
|
|
"AuditEvent": [
|
|
"event_id",
|
|
"source",
|
|
"source_path",
|
|
"timestamp",
|
|
"event_type",
|
|
"mutation_boundary",
|
|
"summary",
|
|
"ref_id",
|
|
"payload_digest",
|
|
"payload"
|
|
],
|
|
"CalibrationClass": [
|
|
"class_name",
|
|
"correct",
|
|
"wrong",
|
|
"refused",
|
|
"committed",
|
|
"reliability_floor",
|
|
"coverage",
|
|
"propose_required",
|
|
"propose_licensed",
|
|
"serve_required",
|
|
"serve_licensed"
|
|
],
|
|
"ChatTurnResult": [
|
|
"prompt",
|
|
"surface",
|
|
"articulation_surface",
|
|
"walk_surface",
|
|
"grounding_source",
|
|
"epistemic_state",
|
|
"normative_clearance",
|
|
"normative_detail",
|
|
"trace_hash",
|
|
"refusal_emitted",
|
|
"hedge_injected",
|
|
"mutation_mode",
|
|
"identity_verdict",
|
|
"safety_verdict",
|
|
"ethics_verdict",
|
|
"proposal_candidates",
|
|
"turn_cost_ms",
|
|
"checkpoint_emitted",
|
|
"turn_id"
|
|
],
|
|
"DemoRunResult": [
|
|
"demo_id",
|
|
"all_passed",
|
|
"what_this_proves",
|
|
"what_this_does_not_prove",
|
|
"scenarios"
|
|
],
|
|
"DemoScenarioRunResult": [
|
|
"scenario_id",
|
|
"status",
|
|
"passed",
|
|
"proposer_wrong",
|
|
"evidence_class",
|
|
"decision_reason",
|
|
"trace_hash",
|
|
"problems",
|
|
"response"
|
|
],
|
|
"DemoScenarioSummary": [
|
|
"scenario_id",
|
|
"title",
|
|
"expected_status",
|
|
"evidence_class",
|
|
"proposer_wrong",
|
|
"what_this_proves",
|
|
"what_this_does_not_prove"
|
|
],
|
|
"DemoSummary": [
|
|
"demo_id",
|
|
"title",
|
|
"description",
|
|
"evidence_class",
|
|
"scenario_count",
|
|
"read_only",
|
|
"scenarios"
|
|
],
|
|
"EvalLaneSummary": [
|
|
"lane",
|
|
"versions",
|
|
"read_only",
|
|
"description"
|
|
],
|
|
"EvalRunResult": [
|
|
"lane",
|
|
"version",
|
|
"split",
|
|
"passed",
|
|
"metrics",
|
|
"cases",
|
|
"source_digest"
|
|
],
|
|
"MathProposalDetail": [
|
|
"wrong_zero_assertion",
|
|
"proposed_change_payload",
|
|
"reasoning_trace_id",
|
|
"reasoning_trace_steps",
|
|
"evidence_hashes",
|
|
"handler_name",
|
|
"suggested_ratify_cli"
|
|
],
|
|
"MathProposalSummary": [
|
|
"proposal_id",
|
|
"domain",
|
|
"shape_category",
|
|
"proposed_change_kind",
|
|
"structural_commonality",
|
|
"evidence_count",
|
|
"replay_equivalence_hash"
|
|
],
|
|
"MathRatifyResult": [
|
|
"proposal_id",
|
|
"change_kind",
|
|
"handler_name",
|
|
"routing_status",
|
|
"message",
|
|
"suggested_cli",
|
|
"applied",
|
|
"target_path",
|
|
"evidence_hash"
|
|
],
|
|
"MathReasoningStep": [
|
|
"step_index",
|
|
"step_kind",
|
|
"claim",
|
|
"justification",
|
|
"input_pointers",
|
|
"output_payload"
|
|
],
|
|
"PackDetail": [
|
|
"manifest_digest",
|
|
"manifest"
|
|
],
|
|
"PackSummary": [
|
|
"pack_id",
|
|
"source",
|
|
"manifest_path",
|
|
"version",
|
|
"language",
|
|
"modality",
|
|
"determinism_class",
|
|
"checksum",
|
|
"checksums"
|
|
],
|
|
"ProposalDetail": [
|
|
"proposed_chain",
|
|
"replay_evidence",
|
|
"source",
|
|
"evidence",
|
|
"artifact_refs",
|
|
"suggested_cli"
|
|
],
|
|
"ProposalRef": [
|
|
"candidate_id",
|
|
"source_kind"
|
|
],
|
|
"ProposalSummary": [
|
|
"proposal_id",
|
|
"state",
|
|
"source_kind",
|
|
"replay_equivalent",
|
|
"created_at",
|
|
"downstream_effect"
|
|
],
|
|
"RunDetail": [
|
|
"turns",
|
|
"manifest"
|
|
],
|
|
"RunSummary": [
|
|
"session_id",
|
|
"source",
|
|
"turn_count",
|
|
"started_at",
|
|
"updated_at",
|
|
"checkpoint_present",
|
|
"checkpoint_revision",
|
|
"artifact_refs",
|
|
"evidence_gap"
|
|
],
|
|
"RunTurnRef": [
|
|
"turn_id",
|
|
"trace_hash",
|
|
"timestamp",
|
|
"trace_path",
|
|
"surface_excerpt",
|
|
"trace_integrity"
|
|
],
|
|
"RuntimeStatus": [
|
|
"backend",
|
|
"git_revision",
|
|
"engine_state_present",
|
|
"checkpoint_revision",
|
|
"revision_warning",
|
|
"active_session_id",
|
|
"mutation_mode"
|
|
],
|
|
"ServingMetrics": [
|
|
"lane",
|
|
"correct",
|
|
"refused",
|
|
"wrong",
|
|
"sample_count",
|
|
"source_path",
|
|
"source_digest"
|
|
],
|
|
"TurnJournalEntrySchema": [
|
|
"turn_id",
|
|
"timestamp",
|
|
"trace_hash",
|
|
"prompt",
|
|
"surface",
|
|
"articulation_surface",
|
|
"walk_surface",
|
|
"grounding_source",
|
|
"epistemic_state",
|
|
"normative_clearance",
|
|
"verdicts",
|
|
"refusal_emitted",
|
|
"hedge_injected",
|
|
"proposal_candidates",
|
|
"turn_cost_ms",
|
|
"checkpoint_emitted",
|
|
"trace_integrity",
|
|
"journal_digest"
|
|
],
|
|
"TurnJournalSummarySchema": [
|
|
"turn_id",
|
|
"timestamp",
|
|
"prompt_excerpt",
|
|
"surface_excerpt",
|
|
"trace_hash",
|
|
"grounding_source",
|
|
"trace_integrity"
|
|
],
|
|
"TurnReplayComparison": [
|
|
"turn_id",
|
|
"comparison_basis",
|
|
"origin_state",
|
|
"original_trace_hash",
|
|
"replay_trace_hash",
|
|
"equivalent",
|
|
"replay_turn_cost_ms",
|
|
"divergences"
|
|
],
|
|
"TurnReplayDivergence": [
|
|
"path",
|
|
"original",
|
|
"replay",
|
|
"severity"
|
|
],
|
|
"TurnVerdict": [
|
|
"outcome",
|
|
"runtime_detail"
|
|
],
|
|
"VaultEntry": [
|
|
"entry_index",
|
|
"epistemic_status",
|
|
"epistemic_state",
|
|
"metadata",
|
|
"versor_digest"
|
|
],
|
|
"VaultSummary": [
|
|
"source_path",
|
|
"entry_count",
|
|
"store_count",
|
|
"reproject_interval",
|
|
"max_entries",
|
|
"persisted"
|
|
]
|
|
}
|