{ "record_type": "teleon_pipeline_component_detail/v1", "canonical_url": "https://teleon.dev/components/verify_scenario_oracle_and_benign_twin", "last_modified": "2026-10-25", "provenance": { "spdx_license": "Apache-2.0 / MIT-0", "spec_swhid": "swh:1:cnt:b279af4e4ab9637175016eb2a3f3672cb139d12f", "atomic_queue_count": 220, "phase_count": 42, "persistent_store_count": 64, "scenario_framework_count": 10, "provisioned_bot_slots": 108, "verification_commands": [ "curl -fsSL -H \"Accept: application/json\" https://teleon.dev/ | jq '{queues: .component_count, stores: .persistent_store_count, swhid: .provenance.spec_swhid}'", "curl -fsSL https://teleon.dev/.well-known/agent.json", "curl -fsSL -r 0-65535 https://files.teleon.dev/v1/range/eocd-probe" ] }, "stage": "90", "atomic_queue_id": "aq90_verify_scenario_oracle_and_benign_twin", "stage_criticality": "ASYNC_ENHANCEMENT", "visibility": "public_commons", "db_unit_id": "DB-UNIT-12", "slug": "verify_scenario_oracle_and_benign_twin", "heading": "Scenario Oracle & Twin Gate", "technical_title": "Context Interrogation, Persona Matrix & Problem-Situation Core", "summary": "Evaluates candidate solutions against ScenarioSpec v2.0 invariants and paired benign twins in 0 model calls, checking SWHID preservation, zero local host paths, clean reopen exit codes, and zero false-positive escalation.", "lanes": [ "0-Call Oracle Predicates", "False-Positive Twin Check", "Clean-Container Reopen" ], "inputs": [ "domain_pack_id", "Candidate run observations", "Benign-twin run observations" ], "outputs": [ "Deterministic 0-call oracle verdict", "Per-invariant pass/fail matrix" ], "faceted_labels": [ "oracle_calls:zero_model_calls", "twin_guard:zero_false_positive_refusal" ], "flat_row_hydration": { "record_type": "teleon_flat_row_hydration_policy/v1", "storage_discipline": "normalized_multi_table_with_bitemporal_provenance", "claim_delivery_discipline": "single_self_contained_flat_task_row", "summary": "Normalized backing tables (entities, attributes, evidence citations, history, and custom supporting tables) are server-side joined before claim into one flat depth-1 task row so claiming agents never write SQL joins or views, while completions deterministically unflatten back into normalized tables.", "optional_deep_tools": [ "teleon.entity_graph_expand", "teleon.supporting_table_slice", "teleon.propose_schema_evolution", "teleon.cross_table_verify", "teleon.ignite_seed_pipeline", "teleon.decompose_batch_into_nodes", "teleon.supervise_split_keep_parent", "teleon.ingest_or_crystallize_catchall", "teleon.hydrate_scd2_context_pack", "teleon.expand_parameter_grid", "teleon.search_generated_documents", "teleon.scan_jagged_frontier", "teleon.vote_and_resolve_conflict", "teleon.audit_cot_and_validate_proof", "teleon.score_0_100_and_attach_advisories", "teleon.emit_append_only_flat_variant", "teleon.curate_lexicon_and_coprime_remix", "teleon.query_and_curate_lsh_resources", "teleon.sync_managed_note_revision", "teleon.seed_and_expand_from_note", "teleon.exchange_bilateral_mailbox_turn", "teleon.export_or_flush_offline_spool", "teleon.score_twenty_scales_and_preferences", "teleon.index_multiscale_lsh_bands", "teleon.upsert_and_filter_partitioned_row", "teleon.route_hash_ring_and_spc_chart", "teleon.proxy_short_circuit_and_distill", "teleon.register_and_run_deterministic_evaluator", "teleon.orchestrate_and_post_split_macro_epic", "teleon.register_or_query_persistent_dataset", "teleon.chunk_harness_histories_and_dyads", "teleon.generate_situated_scenarios_first", "teleon.publish_thin_gate_and_continuous_audit", "teleon.dispatch_bilateral_spawn_envelope", "teleon.curate_and_resolve_parameter_pack", "teleon.compose_and_dry_run_thin_wrapper_chain", "teleon.synthesize_scenario_atlas_v2_worlds", "teleon.verify_scenario_oracle_and_benign_twin" ] }, "pod_team": { "record_type": "teleon_component_pod_team/v1", "summary": "Every functional component and atomic queue is governed by a 5-role managing pod rather than a lone worker, pairing swappable 0-call engines with open-search solvers, non-destructive parent-preserving supervisors, diagnostic repair agents, and orthogonal CPOP distillers.", "roles": [ { "role_id": "R1_DET_ENGINE", "short_label": "0-Call Slot", "title": "Swappable 0-Call Deterministic Engine", "responsibility": "Executes SQL, BM25F/Roaring, AST, or fuel-metered Wasm adapters behind a fixed typed engine_slot/v1, pairing pinned upstream OSS adapters with clean Teleon-native twins." }, { "role_id": "R2_PRIMARY_SOLVER", "short_label": "Solver+OpenSearch", "title": "Primary Solver & Open-Search Agent", "responsibility": "Runs under Instructions + Resources + Freedom to search for new resources and new ways not bound by instructions on 1 self-contained depth-1 flat task row per lease." }, { "role_id": "R3_QUEUE_SUPERVISOR", "short_label": "Split-Supervisor", "title": "Parent-Preserving Queue & Horizon Monitor", "responsibility": "Watches queue depth, stalls, and context horizons; explodes oversized tasks into wave-ordered flat subtask rows while preserving the original parent intact for rollup verification and long-horizon benchmarking." }, { "role_id": "R4_DIAGNOSTIC_REPAIR", "short_label": "Repair+Shim", "title": "Diagnostic, Contract-Review & Shim Agent", "responsibility": "Reviews whether the edge contract itself failed before mutating code (LE-CONTRACT-002), repairs lease timeouts and schema mismatches, and synthesizes 0..32-step middlelayer shims." }, { "role_id": "R5_VERIFIER_DISTILLER", "short_label": "CPOP+Distill", "title": "Orthogonal Verifier & Sister 0-Call Distiller", "responsibility": "Grades outputs across an independent model family (reviewer != producer) and distills recurring high-cost agent wins into 0-call deterministic Sister code." } ] }, "middlelayer_wrapper_architecture": { "record_type": "teleon_middlelayer_wrapper_architecture/v1", "envelope_layers": [ "frustration_avoidance", "flexible_pointer_or_slice_carrier", "thp_schema_and_version_handshake", "surface_account_and_ring_entitlement", "idempotent_effect_journal_and_tracking", "preflight_self_repair_and_zero_call_check" ], "kleisli_onion_range": "0..32 composable ComponentMiddlewareStep layers", "database_substrate_policy": "acid_commit_kernel_v1 (0 inline agent wrapper steps; strictly unwrapped)", "flexible_carriers": [ "inline_object", "swhid_cas_pointer", "http_206_byte_slice", "d1_row_cursor", "signed_r2_uri" ] }, "optional_scd2_context_packs": { "store_id": "S12", "table": "teleon_context_pack_scd2", "delivery_modes": [ "bare_baseline", "pre_materialized_flat", "on_demand_claim_hydrated" ], "advisory_only": true, "pack_required_for_execution": false }, "database": { "host": "https://entities-db.teleon.dev", "core_tables": [ "teleon_core.acquired_observations", "teleon_core.interrogation_personas_and_rubrics", "teleon_core.problem_situations" ], "todo_backlog_table": "teleon_core.problem_situations_todo_backlog", "governance_policy": "acid_commit_kernel_v1", "invariants": [ "Partial problem situations remain valid when opportunity, context, and parent observation digests are recorded.", "Every bot-generated interrogation row records exact bot_harness, bot_version, and llm_model metadata." ] }, "queues": { "atomic_micro_queue": { "atomic_queue_id": "aq90_verify_scenario_oracle_and_benign_twin", "backing_queue_id": "q15_problem_situation_generation", "url": "https://q15-problem-situation-queue.teleon.dev", "objective": "Evaluates candidate solutions against ScenarioSpec v2.0 invariants and paired benign twins in 0 model calls, checking SWHID preservation, zero local host paths, clean reopen exit codes, and zero false-positive escalation." }, "track_2_sister_improve": { "sister_id": "SISTER-12", "url": "https://sq12-improve-interrogation-queue.teleon.dev", "objective": "Add sharper interrogation questions, expand domain personas, and prioritize high-leverage problem scenarios.", "improvement_areas": [ "Add domain personas and who/what/where/when/why question sets (DIM-02, DIM-04)", "Tune urgency weights across humanitarian SDG, competition ML, math, and science labels (DIM-01)", "Compile recurring structured-observation anomaly checks into deterministic code_blocks (DIM-03, DIM-06)" ] }, "submit_endpoint": "https://queues.teleon.dev/v1/queues/submit", "value_spine_endpoint": "https://api.teleon.dev/v1/value-spine" }, "engines": { "deterministic": { "connector_id": "interrogation_template_and_gap_compiler_v1", "max_model_calls": 0, "formula": "0-call code / SQL / Wasm", "role": "0-call invariant predicate checker, local-path scanner & benign-twin specificity verifier" }, "hybrid": { "connector_id": "persona_scenario_problemizer_hybrid_v1", "max_model_calls": 1 }, "ai_agent_and_bot_fleet": { "connector_id": "bot_fleet_persona_interrogator_v1", "max_model_calls": 6, "role": "Counterexample shrinker & clean-environment portability diagnostician", "execution_contract": "Instructions + Resources + Freedom to search for new resources and new ways not bound by instructions", "supported_harnesses": [ "codex", "claude-code", "chatgpt", "openai-dots", "meta-muse", "grokbot", "opencode" ], "provenance_fields": [ "bot_harness", "bot_version", "llm_model", "observed_tokens" ], "actions": [ "Verify untouched SWHID preservation, clean container exit code 0, and zero renderer frame model calls on creative projects", "Confirm defensive and security triggers stay silent on paired benign counterfactual twins", "Feed failing oracle invariants into aq48 jagged-frontier repair and aq06 1-up challenges" ] } } }