{ "record_type": "teleon_pipeline_component_detail/v1", "canonical_url": "https://teleon.dev/components/find_entities_and_leads", "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": "13", "atomic_queue_id": "aq13_entity_find", "stage_criticality": "ASYNC_ENHANCEMENT", "visibility": "public_commons", "db_unit_id": "DB-UNIT-01", "slug": "find_entities_and_leads", "heading": "Find Entities & Leads", "technical_title": "Content-Addressed Entities & Merkle Payload Core", "summary": "Discovers candidate people, organizations, places, leads, or domain things matching a target brief and resolves canonical IDs.", "lanes": [ "People & Orgs", "Places & Things", "Canonical Dedup" ], "inputs": [ "Target entity criteria", "Exclusion fingerprints" ], "outputs": [ "Canonical entity stub", "Discovery provenance URL" ], "faceted_labels": [ "entity:person|org|place|lead|repo|thing", "dedup:canonical_key" ], "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.teleon_entities", "teleon_core.teleon_executable_payloads", "teleon_core.teleon_annotation_revisions" ], "todo_backlog_table": "teleon_core.entities_cas_todo_backlog", "governance_policy": "acid_commit_kernel_v1", "invariants": [ "Never rewrite immutable swh:1:cnt digests; append bitemporal annotation revisions instead.", "Prefer HTTP Range slices (<= 64 KiB) over full repository downloads." ] }, "queues": { "atomic_micro_queue": { "atomic_queue_id": "aq13_entity_find", "backing_queue_id": "q03_seed_intake", "url": "https://q03-seed-queue.teleon.dev", "objective": "Discovers candidate people, organizations, places, leads, or domain things matching a target brief and resolves canonical IDs." }, "track_2_sister_improve": { "sister_id": "SISTER-01", "url": "https://sq01-improve-cas-queue.teleon.dev", "objective": "Tune chunk boundaries, add AST language grammars, and shrink byte-slice token overhead.", "improvement_areas": [ "Tune FastCDC chunk target size per language grammar", "Add AST symbol-slicing code_blocks for new file formats (WGSL, USD, Typst)", "Expand provenance and license synonym mappings" ] }, "submit_endpoint": "https://queues.teleon.dev/v1/queues/submit", "value_spine_endpoint": "https://api.teleon.dev/v1/value-spine" }, "engines": { "deterministic": { "connector_id": "cas_fastcdc_swhid_ingestor_v1", "max_model_calls": 0, "formula": "0-call code / SQL / Wasm", "role": "Domain/URL canonicalizer & dedup matcher" }, "hybrid": { "connector_id": "cas_license_boundary_disambiguator_v1", "max_model_calls": 1 }, "ai_agent_and_bot_fleet": { "connector_id": "cas_unstructured_bundle_extractor_v1", "max_model_calls": 6, "role": "Multi-source entity & lead scout", "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": [ "Discover net-new organizations, maintainers, places, or domain artifacts", "Normalize domains, handles, and identifiers to prevent duplicate entity rows", "Hand discovered stubs automatically to aq14_entity_enrich" ] } } }