{ "schema": "varexis-public-evidence-record/0.3", "generated_at_utc": "2026-10-30T12:29:00.575278+00:00", "record_id": "VXI-EXT-ICE08-LANGFUSE-USAGE-BUCKETS-OVERLAP-DOUBLE-COUNT-01-v1", "record_kind": "external_reference", "title": "Can cached input tokens be counted both within input and in a separate Langfuse usage bucket", "system": "Langfuse", "evidence_family": "vendor_evidence_review", "index_status": "PUBLIC_SAFE_SOURCE_REVIEW", "evidence_state": "PRIMARY_DOCUMENTATION_REVIEW_ONLY", "canonical_question": "Can cached input tokens be counted both within input and in a separate Langfuse usage bucket?", "near_questions": [ "Should cached tokens be subtracted from the input bucket?", "Why can inferred Langfuse cost exceed provider cost?", "Are usage-detail keys independent additive buckets?", "Does overlapping usage alter an explicitly ingested cost?" ], "supported_claims": [ { "claim": "Langfuse treats usage keys as non-overlapping buckets. Overlapping counts can double-count usage and inferred cost; directly ingested cost values are not recalculated by that overlap.", "reliance": "DOCUMENTED_CAPABILITY_ONLY" } ], "not_demonstrated_claims": [ "Reconcile bucket definitions before accepting totals or alleging duplicate billing.", "Buyer implementation, live runtime enforcement, settled payment, verified deletion or certification are not established.", "No expanded capabilities or licences for existing INDEX executables." ], "public_summary": "Langfuse treats usage keys as non-overlapping buckets. Overlapping counts can double-count usage and inferred cost; directly ingested cost values are not recalculated by that overlap.", "related_record_ids": [], "source_review": { "source_type": "official_external_documentation", "source_title": "Token & Cost Tracking - Langfuse", "source_url": "https://langfuse.com/docs/observability/features/token-and-cost-tracking", "checked_on": "2026-10-30", "candidate_record_id": "VXI-EXT-ICE08-LANGFUSE-USAGE-BUCKETS-OVERLAP-DOUBLE-COUNT-01-v1", "candidate_record_sha256": "e882a04bde0f2c23038875a0dd62ee533c3646d44c85c92ade903190cf4fb03d", "method": "Primary documentation reviewed for the published bounded statement.", "deployment_tested_by_varexis": false, "revalidation": "The delivered snapshot preserves the review date shown. Recheck current primary documentation and deployment context before relying on present applicability; payment does not trigger fresh research." }, "answer_policy": { "classification": "DOCUMENTED_WITH_DEPLOYMENT_BOUNDARY", "bounded_answer": "Langfuse treats usage keys as non-overlapping buckets. Overlapping counts can double-count usage and inferred cost; directly ingested cost values are not recalculated by that overlap.", "required_buyer_context": "provider token fields; normalized usage buckets; inferred versus ingested cost. Buyer deployment not inspected.", "missing_evidence": "A broader claim needs evidence matching the intended use. Payment does not upgrade the evidence state." }, "private_boundary": "Raw logs, thresholds, private paths, source code, protected mechanisms and reconstruction-level details are excluded from public and paid delivery.", "decision_profile": { "schema": "varexis-vendor-evidence-review/1", "review_status": "documentation_review_only", "checked_on": "2026-10-30", "claim_to_check": "Can cached input tokens be counted both within input and in a separate Langfuse usage bucket?", "documented_statement": { "status": "documented", "statement": "Langfuse treats usage keys as non-overlapping buckets. Overlapping counts can double-count usage and inferred cost; directly ingested cost values are not recalculated by that overlap.", "source_ids": [ "langfuse-cost" ] }, "review_inference": { "status": "review_inference", "statement": "Can cached input tokens be counted both within input and in a separate Langfuse usage bucket? Use the stated boundary to identify missing scope, source or outcome evidence before closing the review. Telemetry normalization overlap differs from interpreting provider cache prices. This is an operational review inference, not an observed deployment outcome.", "source_ids": [ "langfuse-cost" ] }, "buyer_evidence_required": [ "provider token fields", "normalized usage buckets", "inferred versus ingested cost" ], "review_condition": { "status": "varexis_review_policy", "statement": "Reconcile bucket definitions before accepting totals or alleging duplicate billing." }, "unknowns": "The buyer implementation, effective authority, source-data completeness and actual business outcomes were not inspected.", "unknown_finding": { "status": "unknown", "statement": "No buyer deployment or transaction was observed." }, "evidence_sources": [ { "source_id": "langfuse-cost", "url": "https://langfuse.com/docs/observability/features/token-and-cost-tracking", "final_url": "https://langfuse.com/docs/observability/features/token-and-cost-tracking", "captured_at_utc": "2026-10-30T12:14:29.193750+00:00", "status": 200, "content_type": "text/html; charset=utf-8", "bytes": 698022, "sha256": "44889fccebbf7fab268e0c72ade2952343ef4158ef8ea042873077bb8a059b86", "title": "Token & Cost Tracking - Langfuse", "publisher": "Langfuse", "checked_on": "2026-10-30", "capture_status": 200, "claim_review_completed": true, "hash_basis": "SHA-256 of captured HTTP response-body bytes; not a signature or factual guarantee.", "version_context": "Official SDK/service documentation captured 2026-10-30. Rolling documentation, not a pinned implementation release; recheck current version and configuration before reliance.", "rights_disposition": "Original bounded paraphrase with source attribution. Captured source body remains private; no source-body redistribution. Vendor documentation rights, code licences and marks are not transferred.", "reviewed_sections": [ "Model definitions and prices", "Usage types are mutually exclusive buckets", "Adding custom model definitions", "Troubleshooting" ] } ], "observed_deployment": false, "commercial_reliance_boundary": "Documentation supports only the stated boundary. Existing licensed checkers analyse supported supplied declarations locally; they do not inspect provider accounts, verify live behaviour, enforce decisions or certify compliance.", "paid_value": { "decision_context": "Can cached input tokens be counted both within input and in a separate Langfuse usage bucket? Use the stated boundary to identify missing scope, source or outcome evidence before closing the review.", "free": "Complete source review, questions, provenance and limitations; free to read and save locally.", "single_request": "Unavailable for this publication-only record; historical saved retrieval is unchanged.", "evidence_receipt": "Unavailable for this publication-only record; no paid retrieval entitlement is added.", "excluded": [ "Fresh source research", "Native provider integration or schema support", "Live inspection or runtime enforcement", "Payment settlement or verified deletion", "Certification or expanded licences" ], "integrity": "Hashes identify content versions; they do not prove factual truth or provide a signature." }, "revalidation": { "trigger": "Recheck current primary documentation and the applicable API, service, account and configuration before reliance. No ongoing monitoring is included.", "specific_watch": "Usage types are mutually exclusive buckets" }, "buyer_relevance": "Can cached input tokens be counted both within input and in a separate Langfuse usage bucket? Use the stated boundary to identify missing scope, source or outcome evidence before closing the review.", "refusal_conditions": [ "Reconcile bucket definitions before accepting totals or alleging duplicate billing.", "Do not infer deployment conformance, authority or successful outcomes from source documentation." ], "decision_context": { "operator": "Agent platform operator or cost reviewer", "scenario": "Can cached input tokens be counted both within input and in a separate Langfuse usage bucket?", "consequence": "Use the stated boundary to identify missing scope, source or outcome evidence before closing the review.", "confidence": "High for captured documentation; applicability and deployed behaviour unverified." }, "novelty_review": { "candidate_id": "ICE08-038", "disposition": "EXTENSION", "nearest_record_id": "VXI-EXT-PROCUREMENT-OPENAI-PROMPT-CACHE-USAGE-RATE-DISTINCTION-01-v1", "nearest_record_url": "/varexis-index/records/openai-prompt-cache-usage-rate-distinction.json", "nearest_record_sha256": "6ac7d43909197cc01de1f490e1d10b504ba5b62e3c66f56784eb9fdb77e6096f", "material_distinction": "Telemetry normalization overlap differs from interpreting provider cache prices.", "review_status": "PASS: implementing-agent source and duplication review" }, "optional_selection": { "guide_id": "agent-run-cost-trace-evidence", "guide_url": "/index-guides/agent-run-cost-trace-evidence", "guide_manifest": "/varexis-index/decision-guides.json", "checker": { "product_id": "agent-audit-coverage", "price_gbp_excluding_vat": 79, "purchase_url": "/index-access?route=agentic_pack_audit_coverage_v1", "licence_scope": "Existing separate internal-use licence; subscriptions do not include the executable.", "benefit": "Optional local analysis of supported supplied declarations only; no native provider integration or verification is added." }, "boundary": "Optional Audit Coverage only reconciles supported supplied event-chain declarations. It does not connect to these providers, calculate model charges, verify live permissions, export traces or enforce budgets." }, "exact_access": { "endpoint": "/mcp/catalogue", "tool": "get_publication_record", "arguments": { "record_id": "VXI-EXT-ICE08-LANGFUSE-USAGE-BUCKETS-OVERLAP-DOUBLE-COUNT-01-v1" }, "record_url": "/varexis-index/records/langfuse-usage-buckets-overlap-double-count.json", "original_mcp_search": false, "paid_saved_retrieval": false } }, "niche": { "niche_id": "ice08-audit", "label": "Audit, Provenance & Evidence Accountability", "classification_id": "audit", "classification_label": "Audit, Provenance & Evidence Accountability", "topic_id": "audit", "buyer_intent": "Can cached input tokens be counted both within input and in a separate Langfuse usage bucket? Use the stated boundary to identify missing scope, source or outcome evidence before closing the review.", "comparison_role": "supplementary_discovery" }, "paid_access_note": "The full published answer and boundaries are free. Paid access saves the selected route and source versions, with an unsigned receipt when purchased. Preview coverage before paying. Fresh research, bespoke assessment and protected evidence are excluded.", "service_route": { "request_guide": "/varexis-index/request.html", "request_workflow": "/varexis-index/request-workflow.json", "service_id": "single_request", "service_routes_url": "/varexis-index/service-routes.json", "payment_required": true, "availability_endpoint": "/api/index/capabilities", "operational_status": "AUTOMATIC_SERVICE_CAPABILITIES_GATED", "checkout_url": "/index-access" }, "authority_boundary": "VAREXIS-INDEX informs evidence reliance. It does not provide advice, certification, deployment authority, security assurance, production approval, or guarantee.", "human_page": "/varexis-index/catalog.html#langfuse-usage-buckets-overlap-double-count", "machine_readable_record": "/varexis-index/records/langfuse-usage-buckets-overlap-double-count.json" }