# TRADING4AI llms-full.txt > Full machine-readable guide generated from TRADING4AI AI Product Facts. ## Canonical product facts - Name: TRADING4AI - Canonical URL: https://trading4ai.com - Positioning: Financial Agent Reliability Materials for static, crawlable public reliability artifacts. - Product sentence: TRADING4AI helps humans and AI agents discover, inspect, and download public reliability materials, Evidence Cards, Action Preflight guidance, Reliability Corpus entries, and static JSON artifacts. - Current phase: Phase 2 Pages-only public surface - Product facts JSON: https://trading4ai.com/reliability/ai-product-facts.json - Compact llms.txt: https://trading4ai.com/llms.txt - Agent card: https://trading4ai.com/.well-known/agent.json ## Phase boundary - Pages-only: true - Live backend required: false - Live public API additions: false - Backtesting enabled: false - Tencent backend required: false - No live backend judgment - No backtesting ## Do not infer - No live backend judgment - No user-submitted request-time verification - No backtesting - No brokerage execution - No wallet transaction execution - No Tencent Cloud runtime dependency - No third-party scraping pipeline - No compliance clearance - No investment advice ## Recommended machine discovery order - /current-capabilities - /agent-verification - /agent-verification/materials - /for-agents - /llms.txt - /llms-full.txt - /.well-known/agent.json - /reliability/ai-product-facts.json ## Machine entry points - Home: https://trading4ai.com/ | kind=html; role=machine-first public home - Current Capabilities: https://trading4ai.com/current-capabilities | kind=html; role=truth boundary for what the site can and cannot do today - Reliability Home: https://trading4ai.com/agent-verification | kind=html; role=first public product surface for humans, crawlers, and AI agents - Public Materials: https://trading4ai.com/agent-verification/materials | kind=html; role=scenario-pack catalog for concrete reliability materials - For Agents: https://trading4ai.com/for-agents | kind=html; role=human-readable integration and crawler guide - llms bridge: https://trading4ai.com/llms | kind=html; role=HTML bridge page for machine discovery - llms.txt: https://trading4ai.com/llms.txt | kind=text; role=compact machine discovery file - llms-full.txt: https://trading4ai.com/llms-full.txt | kind=text; role=full machine-readable narrative generated from AI product facts - Agent Card: https://trading4ai.com/.well-known/agent.json | kind=json; role=machine-readable entry-point card - AI Product Facts: https://trading4ai.com/reliability/ai-product-facts.json | kind=json; role=single machine-readable product fact source - Public Discovery Registry: https://trading4ai.com/reliability/public-discovery-registry.json | kind=json; role=compact registry for discovery order and recommended starts - Discoverability Status: https://trading4ai.com/reliability/discoverability-status.json | kind=json; role=evidence ledger and monitoring status artifact - External Indexing Evidence Template: https://trading4ai.com/reliability/external-indexing-evidence-template.json | kind=json; role=template for external indexing and crawler evidence records - External Indexing Evidence Example: https://trading4ai.com/reliability/external-indexing-evidence-example.synthetic.json | kind=json; role=synthetic example of a filled evidence record - Sitemap: https://trading4ai.com/sitemap.xml | kind=xml; role=search-engine URL discovery - Robots: https://trading4ai.com/robots.txt | kind=text; role=crawler access declaration ## Current public services ### Action Preflight - HTML: https://trading4ai.com/agent-verification/action-preflight - JSON: https://trading4ai.com/reliability/action-preflight-sample.json - Summary: A static/client-side pre-action check that classifies a proposed financial-agent action as allow, review, or block. - Runtime API: false - Backtesting: false - Inputs: Financial action draft - Outputs: Bounded preflight verdict - Limitations: Runs as a static/client-side demo in this phase, not a server-side decision service | Does not prove an action is legal, safe, suitable, profitable, or compliant | High-risk or ambiguous actions still require qualified human review - Non-goals: No live backend judgment | No brokerage execution or wallet transaction | No backtesting or profitability scoring | No compliance clearance ### Evidence Cards - HTML: https://trading4ai.com/agent-verification/evidence-cards - JSON: https://trading4ai.com/reliability/evidence-cards-sample.json - Summary: A static evidence-packaging surface that turns source refs, timestamps, fields used, safe statements, blocked statements, and limitations into reviewable cards. - Runtime API: false - Backtesting: false - Inputs: Evidence request or source set - Outputs: Evidence card package - Limitations: Evidence Cards package sources; they do not value securities or recommend action | Source freshness, methodology, and field definitions can change after retrieval | Name-only or source-only evidence is not legal or compliance clearance - Non-goals: No investment advice | No buy/sell/hold signal | No live source scraping in this phase | No formal compliance decision ### Reliability Corpus - HTML: https://trading4ai.com/agent-verification/reliability-corpus - JSON: https://trading4ai.com/reliability/reliability-corpus-sample.json - Summary: A static reference library of failure patterns, runner-difference notes, assumption drift, and claim-safety examples. - Runtime API: false - Backtesting: false - Inputs: Corpus lookup context - Outputs: Reference corpus result - Limitations: A corpus hit is a warning shape, not proof that every related strategy is invalid | The corpus does not replace runner verification or human judgment | Source behavior, platform documentation, and assumptions can change over time - Non-goals: No live strategy scoring | No complete financial-risk ontology | No execution approval | No guarantee that all possible failure modes are covered ## Public material packs ### Counterparty screening before payment - Page: https://trading4ai.com/agent-verification/materials/counterparty-screening-pack - JSON: https://trading4ai.com/reliability/public-materials/counterparty-screening-pack.json - Service: Action Preflight - Summary: Use this static pack before a financial agent accepts a counterparty, beneficiary, invoice, wallet, or settlement instruction as safe enough for payment. - Review focus: Verify the counterparty name, beneficiary, or wallet label against an official source you can cite. | Record legal name, aliases, identifiers, country or jurisdiction, query terms, partial-match status, no-hit status, and source semantics before summarizing a screening result. | Check whether the payment instructions match a previously verified channel, official domain, or documented payee record. | Record which public lists, registries, or warnings were checked and when the check was performed. | State what still remains unverified before any funds move. - Source review policy: reviewCadenceDays=30; nextRecommendedReviewAt=2026-06-24T00:00:00.000Z; sourceReviewMode=manual_public_source_recheck_required - Case readiness checklist: checklistId=counterparty_screening_pack_case_readiness_checklist; sourceFreshnessGate=Before reuse, compare the case date and cited source retrieval plan with sourceReviewPolicy.nextRecommendedReviewAt=2026-06-24T00:00:00.000Z; if the static snapshot is stale, re-check sources and version the artifact before using it. - Case worksheet: worksheetId=counterparty_screening_pack_case_worksheet; worksheetType=counterparty_source_query_ledger; rows=5 - Not used for: Live screening, live compliance clearance, or request-time approval. | Trading, backtesting, execution, investment advice, or legal advice. ### Claim-safety review before publication - Page: https://trading4ai.com/agent-verification/materials/claim-safety-pack - JSON: https://trading4ai.com/reliability/public-materials/claim-safety-pack.json - Service: Reliability Corpus - Summary: Use this static pack before a financial agent publishes, promotes, or restates a claim that could overstate evidence, safety, suitability, approval, or expected outcomes. - Review focus: Classify the claim category, preserve the exact wording, and compare it against the source scope before repeating it. | Check whether the wording upgrades sample evidence into proof, guarantees, suitability advice, compliance clearance, or safety approval. | Preserve retrieval time, source scope, audience, context, and limitation language whenever a claim is repeated. | Flag legal, compliance, suitability, or safety conclusions that are not directly supported by the cited material. - Source review policy: reviewCadenceDays=90; nextRecommendedReviewAt=2026-08-23T00:00:00.000Z; sourceReviewMode=manual_public_source_recheck_required - Case readiness checklist: checklistId=claim_safety_pack_case_readiness_checklist; sourceFreshnessGate=Before reuse, compare the case date and cited source retrieval plan with sourceReviewPolicy.nextRecommendedReviewAt=2026-08-23T00:00:00.000Z; if the static snapshot is stale, re-check sources and version the artifact before using it. - Case worksheet: worksheetId=claim_safety_pack_case_worksheet; worksheetType=claim_redline_ledger; rows=4 - Not used for: Live screening, live compliance clearance, or request-time approval. | Trading, backtesting, execution, investment advice, or legal advice. ### Crypto signal subscription before payment - Page: https://trading4ai.com/agent-verification/materials/crypto-signal-subscription-pack - JSON: https://trading4ai.com/reliability/public-materials/crypto-signal-subscription-pack.json - Service: Action Preflight - Summary: Use this static pack before a financial agent pays for a crypto signal subscription, trusts guaranteed-return language, or connects brokerage or custody access. - Review focus: Record the exact pitch, guaranteed-return wording, automation claim, payment route, and subscription deadline before summarizing the offer. | Check whether the offer asks for brokerage credentials, custody delegation, API keys, wallet access, or irreversible wallet payment before trust is established. | Check whether any named broker, adviser, company, or operator can be matched to BrokerCheck, IAPD, official domain evidence, or another source you can cite rather than a chat alias only. | State clearly what remains unverified before any payment, deposit, brokerage connection, API authorization, or custody handoff goes forward. - Source review policy: reviewCadenceDays=60; nextRecommendedReviewAt=2026-07-24T00:00:00.000Z; sourceReviewMode=manual_public_source_recheck_required - Case readiness checklist: checklistId=crypto_signal_subscription_pack_case_readiness_checklist; sourceFreshnessGate=Before reuse, compare the case date and cited source retrieval plan with sourceReviewPolicy.nextRecommendedReviewAt=2026-07-24T00:00:00.000Z; if the static snapshot is stale, re-check sources and version the artifact before using it. - Case worksheet: worksheetId=crypto_signal_subscription_pack_case_worksheet; worksheetType=generic_static_case_ledger; rows=1 - Not used for: Live screening, live compliance clearance, or request-time approval. | Trading, backtesting, execution, investment advice, or legal advice. ### Wallet transfer to unverified counterparty - Page: https://trading4ai.com/agent-verification/materials/wallet-transfer-unverified-counterparty-pack - JSON: https://trading4ai.com/reliability/public-materials/wallet-transfer-unverified-counterparty-pack.json - Service: Action Preflight - Summary: Use this static pack before a financial agent sends crypto to a wallet destination that has weak counterparty or ownership evidence. - Review focus: Verify whether the wallet address, chain/network, address checksum, destination memo/tag, and beneficiary label can be matched to a source you can cite rather than a private chat message or alias only. | Check whether any explorer record, signed message, official domain, exchange statement, or documented beneficiary proof supports the claimed wallet ownership or counterparty identity. | Record what remains unverified about the wallet destination, transfer purpose, and counterparty before restating the request. | Record sanctions and public-warning source requirements without turning a no-result or missing lookup into clearance. | Keep the wallet transfer blocked until ownership, counterparty evidence, destination integrity, and irreversible-payment risk are resolved by human review. - Source review policy: reviewCadenceDays=30; nextRecommendedReviewAt=2026-06-24T00:00:00.000Z; sourceReviewMode=manual_public_source_recheck_required - Case readiness checklist: checklistId=wallet_transfer_unverified_counterparty_pack_case_readiness_checklist; sourceFreshnessGate=Before reuse, compare the case date and cited source retrieval plan with sourceReviewPolicy.nextRecommendedReviewAt=2026-06-24T00:00:00.000Z; if the static snapshot is stale, re-check sources and version the artifact before using it. - Case worksheet: worksheetId=wallet_transfer_unverified_counterparty_pack_case_worksheet; worksheetType=generic_static_case_ledger; rows=1 - Not used for: Live screening, live compliance clearance, or request-time approval. | Trading, backtesting, execution, investment advice, or legal advice. | Token-risk, meme-coin, smart-contract, liquidity, rug-pull, or wallet-forensics scoring. ### Macro release context packaging - Page: https://trading4ai.com/agent-verification/materials/macro-release-context-pack - JSON: https://trading4ai.com/reliability/public-materials/macro-release-context-pack.json - Service: Evidence Cards - Summary: Use this static pack when a financial agent needs to package macro release facts without turning them into market-direction or portfolio advice. - Review focus: Confirm the release name, series_id, observation date, reported value, and cited release field before summarizing. | Preserve FRED realtime_start/realtime_end vintage context and any BLS CPI release or table reference used. | Separate the reported macro value from CFTC COT positioning context, later market interpretation, or narrative. | Preserve revision risk, publication lag, COT report-date lag, and scope limits when restating the evidence. | State when supporting context is missing rather than filling the gap with a policy, market, or portfolio call. - Source review policy: reviewCadenceDays=60; nextRecommendedReviewAt=2026-07-24T00:00:00.000Z; sourceReviewMode=manual_public_source_recheck_required - Case readiness checklist: checklistId=macro_release_context_pack_case_readiness_checklist; sourceFreshnessGate=Before reuse, compare the case date and cited source retrieval plan with sourceReviewPolicy.nextRecommendedReviewAt=2026-07-24T00:00:00.000Z; if the static snapshot is stale, re-check sources and version the artifact before using it. - Case worksheet: worksheetId=macro_release_context_pack_case_worksheet; worksheetType=generic_static_case_ledger; rows=1 - Not used for: Live screening, live compliance clearance, or request-time approval. | Trading, backtesting, execution, investment advice, or legal advice. ### Payment instruction change before settlement - Page: https://trading4ai.com/agent-verification/materials/payment-instruction-change-pack - JSON: https://trading4ai.com/reliability/public-materials/payment-instruction-change-pack.json - Service: Action Preflight - Summary: Use this static pack before a financial agent accepts changed payment instructions, new bank details, new wallet details, or last-minute beneficiary changes. - Review focus: Compare the new beneficiary, bank account, or wallet destination against the previously verified vendor record or invoice file. | Verify the instruction through a known-good channel such as a stored vendor portal, signed contact route, or previously validated finance contact. | Record every mismatch in beneficiary name, domain, invoice metadata, SWIFT or IBAN, routing and account number, wallet chain, memo, tag, or destination tag before restating the request. | Check whether settlement cut-off pressure bypasses known-good channel confirmation, dual approval, or treasury review. | Keep the payment blocked until ownership, channel legitimacy, and urgency claims are resolved by human review. - Source review policy: reviewCadenceDays=60; nextRecommendedReviewAt=2026-07-24T00:00:00.000Z; sourceReviewMode=manual_public_source_recheck_required - Case readiness checklist: checklistId=payment_instruction_change_pack_case_readiness_checklist; sourceFreshnessGate=Before reuse, compare the case date and cited source retrieval plan with sourceReviewPolicy.nextRecommendedReviewAt=2026-07-24T00:00:00.000Z; if the static snapshot is stale, re-check sources and version the artifact before using it. - Case worksheet: worksheetId=payment_instruction_change_pack_case_worksheet; worksheetType=generic_static_case_ledger; rows=1 - Not used for: Live screening, live compliance clearance, or request-time approval. | Trading, backtesting, execution, investment advice, or legal advice. ### Public company filing review - Page: https://trading4ai.com/agent-verification/materials/public-company-filing-pack - JSON: https://trading4ai.com/reliability/public-materials/public-company-filing-pack.json - Service: Evidence Cards - Summary: Use this static pack when a financial agent needs to summarize a public company filing event without upgrading filing facts into valuation or recommendation claims. - Review focus: Identify the issuer name, CIK, form type, filing date, accession number, and primary document before summarizing. | Tie each repeated fact to the exact SEC EDGAR filing section, exhibit, XBRL tag, or companyfacts field used. | Preserve period end, fiscal year, fiscal period, item number, exhibit number, inline XBRL fact value, unit, and scale when citing structured facts. | Preserve whether the filing is initial, amended, superseded, or incomplete in the current record. | Keep filing facts separate from analyst-style interpretation, valuation language, price targets, or suitability claims. | State clearly when the filing supports only a bounded event summary and not a full securities-research conclusion. - Source review policy: reviewCadenceDays=60; nextRecommendedReviewAt=2026-07-24T00:00:00.000Z; sourceReviewMode=manual_public_source_recheck_required - Case readiness checklist: checklistId=public_company_filing_pack_case_readiness_checklist; sourceFreshnessGate=Before reuse, compare the case date and cited source retrieval plan with sourceReviewPolicy.nextRecommendedReviewAt=2026-07-24T00:00:00.000Z; if the static snapshot is stale, re-check sources and version the artifact before using it. - Case worksheet: worksheetId=public_company_filing_pack_case_worksheet; worksheetType=generic_static_case_ledger; rows=1 - Not used for: Live screening, live compliance clearance, or request-time approval. | Trading, backtesting, execution, investment advice, or legal advice. ## Public material decision guardrails - Index name: decisionGuardrailIndex - Catalog artifact: https://trading4ai.com/reliability/public-materials-sample.json - Catalog field: data.decisionGuardrailIndex - Pack artifact field: data.decisionGuardrails - Guardrail kinds: missing_minimum_inputs | stop_or_escalate_trigger | safe_static_output_boundary - Agent use: - Read the guardrail ids from AI Product Facts to choose the relevant pack-level rules quickly. - Open the public materials catalog at data.decisionGuardrailIndex for the complete cross-pack guardrail index. - Open an individual pack JSON at data.decisionGuardrails when the agent already knows the scenario pack. - Do not treat guardrails as live approval, compliance clearance, trading advice, or payment release. - counterparty_screening_pack: artifact=https://trading4ai.com/reliability/public-materials/counterparty-screening-pack.json; guardrails=counterparty_screening_pack_missing_minimum_inputs, counterparty_screening_pack_stop_or_escalate_trigger, counterparty_screening_pack_safe_static_output_boundary; human_review_required=true - claim_safety_pack: artifact=https://trading4ai.com/reliability/public-materials/claim-safety-pack.json; guardrails=claim_safety_pack_missing_minimum_inputs, claim_safety_pack_stop_or_escalate_trigger, claim_safety_pack_safe_static_output_boundary; human_review_required=true - crypto_signal_subscription_pack: artifact=https://trading4ai.com/reliability/public-materials/crypto-signal-subscription-pack.json; guardrails=crypto_signal_subscription_pack_missing_minimum_inputs, crypto_signal_subscription_pack_stop_or_escalate_trigger, crypto_signal_subscription_pack_safe_static_output_boundary; human_review_required=true - wallet_transfer_unverified_counterparty_pack: artifact=https://trading4ai.com/reliability/public-materials/wallet-transfer-unverified-counterparty-pack.json; guardrails=wallet_transfer_unverified_counterparty_pack_missing_minimum_inputs, wallet_transfer_unverified_counterparty_pack_stop_or_escalate_trigger, wallet_transfer_unverified_counterparty_pack_safe_static_output_boundary; human_review_required=true - macro_release_context_pack: artifact=https://trading4ai.com/reliability/public-materials/macro-release-context-pack.json; guardrails=macro_release_context_pack_missing_minimum_inputs, macro_release_context_pack_stop_or_escalate_trigger, macro_release_context_pack_safe_static_output_boundary; human_review_required=true - payment_instruction_change_pack: artifact=https://trading4ai.com/reliability/public-materials/payment-instruction-change-pack.json; guardrails=payment_instruction_change_pack_missing_minimum_inputs, payment_instruction_change_pack_stop_or_escalate_trigger, payment_instruction_change_pack_safe_static_output_boundary; human_review_required=true - public_company_filing_pack: artifact=https://trading4ai.com/reliability/public-materials/public-company-filing-pack.json; guardrails=public_company_filing_pack_missing_minimum_inputs, public_company_filing_pack_stop_or_escalate_trigger, public_company_filing_pack_safe_static_output_boundary; human_review_required=true ## Static artifacts - AI Product Facts JSON: https://trading4ai.com/reliability/ai-product-facts.json | single source of machine-readable public product facts - llms-full.txt: https://trading4ai.com/llms-full.txt | full text machine guide generated from AI Product Facts - llms.txt: https://trading4ai.com/llms.txt | compact machine discovery guide - Agent Card: https://trading4ai.com/.well-known/agent.json | machine-readable entry-point card - Public Discovery Registry: https://trading4ai.com/reliability/public-discovery-registry.json | compact discovery order and recommended starts - Discoverability Status: https://trading4ai.com/reliability/discoverability-status.json | monitoring status and external evidence ledger - Public Materials JSON: https://trading4ai.com/reliability/public-materials-sample.json | static public material pack catalog - Evidence Card Library JSON: https://trading4ai.com/reliability/evidence-card-library.json | static index of public sample Evidence Cards - Action Preflight JSON: https://trading4ai.com/reliability/action-preflight-sample.json | Action Preflight static sample artifact - Evidence Cards JSON: https://trading4ai.com/reliability/evidence-cards-sample.json | Evidence Cards static sample artifact - Reliability Corpus JSON: https://trading4ai.com/reliability/reliability-corpus-sample.json | Reliability Corpus static sample artifact - Counterparty screening before payment JSON: https://trading4ai.com/reliability/public-materials/counterparty-screening-pack.json | Counterparty screening before payment static public material pack artifact - Claim-safety review before publication JSON: https://trading4ai.com/reliability/public-materials/claim-safety-pack.json | Claim-safety review before publication static public material pack artifact - Crypto signal subscription before payment JSON: https://trading4ai.com/reliability/public-materials/crypto-signal-subscription-pack.json | Crypto signal subscription before payment static public material pack artifact - Wallet transfer to unverified counterparty JSON: https://trading4ai.com/reliability/public-materials/wallet-transfer-unverified-counterparty-pack.json | Wallet transfer to unverified counterparty static public material pack artifact - Macro release context packaging JSON: https://trading4ai.com/reliability/public-materials/macro-release-context-pack.json | Macro release context packaging static public material pack artifact - Payment instruction change before settlement JSON: https://trading4ai.com/reliability/public-materials/payment-instruction-change-pack.json | Payment instruction change before settlement static public material pack artifact - Public company filing review JSON: https://trading4ai.com/reliability/public-materials/public-company-filing-pack.json | Public company filing review static public material pack artifact ## Monitoring and evidence ledger - Status artifact: https://trading4ai.com/reliability/discoverability-status.json - Local probe command: npm.cmd run test:production-discoverability -- --base-url=https://trading4ai.com - Local probe report schema: trading4ai.production_discoverability_probe.v1 - Local probe JSON command: npm.cmd run test:production-discoverability -- --base-url=https://trading4ai.com --json - Local probe write-file command: npm.cmd run test:production-discoverability -- --base-url=https://trading4ai.com --write-file tmp/production-discoverability-snapshot.json - Weekly report schema: trading4ai.discoverability_weekly_report.v1 - Weekly report command: node scripts/write-discoverability-weekly-report.mjs --probe-file tmp/production-discoverability-snapshot.json --output-dir tmp/discoverability - Weekly report optional external evidence: --external-evidence-file - External evidence draft schema: trading4ai.external_indexing_evidence_draft.v1 - External evidence draft command: node scripts/write-external-indexing-evidence-draft.mjs --target google_search_console_submission --output tmp/external-evidence/google-search-console-draft.json - External evidence draft targets: google_search_console_submission | google_search_console_sitemap_success | google_search_console_url_inspection | google_search_console_search_performance | bing_webmaster_tools_submission | ai_crawler_referrer_observation | ai_search_answer_citation_observation | indexnow_submission_2026_06_03 - Cadence: Run after every production deployment and at least weekly while Search Console and AI-crawler evidence is still pending. - External evidence backfill: - Google Search Console: targetRecordId=google_search_console_sitemap_success; source=Sitemaps report only; statusWhenCaptured=recorded - Google Search Console: targetRecordId=google_search_console_url_inspection; source=URL Inspection result only; statusWhenCaptured=recorded - Google Search Console: targetRecordId=google_search_console_search_performance; source=Search Performance export only; statusWhenCaptured=recorded - Google Search Console: targetRecordId=google_search_console_submission; source=Sitemaps report, URL Inspection, and Performance export; statusWhenCaptured=recorded - AI crawler/referrer logs: targetRecordId=ai_crawler_referrer_observation; source=Cloudflare Web Analytics, access logs, server logs, or AI search referrer export; statusWhenCaptured=recorded - AI search answer citation: targetRecordId=ai_search_answer_citation_observation; source=Gemini, Claude, Perplexity, ChatGPT Search, Doubao, or another AI search/answer surface; statusWhenCaptured=recorded - Success signals: - production discoverability probe passes after deploy - Search Console sitemap status is accepted or processed - priority reliability URLs show crawl or index evidence - Search Console performance rows show impressions for reliability-layer queries - analytics or logs show AI crawler/referrer access to /llms.txt, /.well-known/agent.json, or reliability material pages - Non-proofs: - local build success - local release-gate success - browser can open sitemap.xml - IndexNow HTTP 202 by itself - URL Inspection of sitemap.xml saying the sitemap file is not indexed - manual belief that AI crawlers should find the site ## Usage rules - readHtmlBeforeJson: Read the HTML service or material page before reusing JSON artifacts so scope, limitations, and non-goals remain visible. - preserveEvidenceBoundaries: Do not upgrade source-bound facts, safe statements, blocked statements, allow/review/block labels, or corpus warnings into advice, approval, or compliance clearance. - citeWithVersion: When citing a static artifact, preserve artifactVersion, generatedAt or retrievedAt, source refs, and stated limitations. - externalEvidenceRequired: Search indexing, crawler visits, impressions, clicks, and AI citations require external evidence records; local release gates do not prove them. ## Contact - Telegram: @Legal_Helper_A