Docs menu

Tools

run_lint

The findings, each with its citation and the date it was last checked.

reads Lint an app against the law

What it does

Step 2, and the one that returns findings. Pass the activities and jurisdictions set_profile validated.

It costs three upstream requests for any number of declared jurisdictions: the manifest of the LexLint law library and its two published NDJSON files, filtered to your declaration in memory once all three have arrived, rather than fetched one jurisdiction at a time. On a key whose law library has not moved since an earlier lint, the manifest request revalidates as an unmetered 304 and the other two are served from that key's own cache, so a repeat lint against an unchanged law library can cost as few as zero metered requests.

Put together, one full lint from a cold cache, check_access, set_profile, run_lint, costs five upstream requests, however many jurisdictions you declare: at the free tier's 50 requests a day, that is ten full lints a day even before a warm cache makes some of them cheaper.

Not sure which slug to use? Search by name at https://ungovr.org/atlas and read the slug off the entity's URL. The page at https://ungovr.org/urn translates between a URN, a slug, and other government identifiers.

Each finding carries severity, jurisdiction, summary, citation, as_of_date, stale, and confidence. Where LexLint holds a page on the instrument, the finding also carries note_url: show the citation as a link to it. It is null when there is no such page, and it is never something to construct, since the address is a stored code rather than a form of the citation. A finding about a specific instrument also carries lifecycle: what its status and dates mean read as of now, as one of new, recent, in_force, imminent, proposed, blocked or unknown, with a detail line such as in force in 47 days. It is computed per call, not stored, so a countdown is correct on the day you read it. An instrument that has been repealed, superseded or withdrawn carries no band, because it is not reported at all: it binds nobody, and there is nothing for your code to do about it. Unknown argument names and unknown activity values are refused with an error rather than silently ignored, so a typo cannot produce a falsely clean run.

Parameters

NameTypeRequiredWhat it takes
activitiesstring[]yesWhat the app does, from the profile set_profile returned. Allowed: crawls_web, trains_models, generates_content, deploys_chatbot, deploys_companion_chatbot, deploys_mental_health_chatbot, automated_outreach, places_automated_calls, sends_automated_texts, sends_commercial_email, sends_faxes, high_risk_decisions, processes_voice, processes_biometrics, processes_personal_data, processes_deidentified_data, publishes_adult_content, operates_social_platform, serves_minors, operates_app_store, ships_mobile_app, ships_consumer_interface, relies_on_digital_identity, collects_e_signatures, ships_encryption, serves_sanctioned_destination, aggregates_content, distributes_software_product, handles_health_records, provides_financial_services, operates_essential_service, is_listed_company, provides_telecom_services, provides_cloud_services, provides_general_purpose_ai_model, is_frontier_developer, serves_education_institutions, serves_k12_schools, serves_higher_education, statutory_requests, records_calls, records_text_chat, tracks_devices, is_bank, is_lender, is_insurer, is_securities_firm, is_payment_provider, is_crypto_asset_provider, employment_decisions, credit_decisions, insurance_decisions, housing_decisions, education_decisions, health_care_decisions, public_services_decisions, justice_decisions, generates_text, generates_images, generates_video, generates_audio
activities_left_outstring[]noActivities the developer was asked about and said this software does not do. Today it answers processes_personal_data: unsent, a declaration naming any activity its code settles is matched as if it processes personal data, with an info coverage line, until the developer answers. It also answers the two chatbot kinds: deploys_chatbot with neither declared nor left out is matched as if it is both, with an info coverage line. And it answers the two model-provider roles: trains_models with a role neither declared nor left out is asked about it, with an info coverage line counting the laws that bind it. Left out, serves_education_institutions says no school, college or university runs or buys this software, so serves_minors no longer brings school law in. And it answers the eight decision domains: high_risk_decisions does not reach a domain left out, so a decision that fits none, such as fraud screening, leaves all eight out. From the profile set_profile returned.
jurisdictionsstring[]yesJurisdiction slugs from the profile set_profile returned, lowercase, "/"-separated (e.g. "us", "us/ca", "eu", "kr"). A slug is the jurisdiction's UnGovr Atlas path: California is https://ungovr.org/us/ca and its Atlas ID is urn:ungovr:us/ca. Its ISO 3166 code, US-CA, is accepted too. A deeper or unresearched path resolves to the nearest jurisdiction whose law reaches it, and to none for a place with its own legal system, and the jurisdictions whose law is researched are listed at https://lexlint.io/law for the developer to check; name every jurisdiction the app operates in: one left off is unlinted, not passed.
public_sectorstring[]noIs this software run by a public body (body), sold to or run for public bodies (supplier), both, or neither (none)? Ask the developer every time the profile is declared; never infer it from the code. Omitted, duties binding only public bodies are reported as the caller's, and run_lint counts them in a coverage line. body: A public body runs this software. supplier: You sell this software to public bodies or run it for them.
public_sector_functionsstring[]noWhich kinds of public body run or buy this software. Ask only when public_sector is body or supplier, and never infer it from the code. One or more of: general (a general-purpose public body, such as a city hall, a state department or a federal agency), law_enforcement (police and sheriffs), corrections (prisons, jails, parole and probation), prosecution_courts (courts, prosecutors and public defenders), public_education (public schools, school districts and public universities), public_health (health departments and public hospitals), elections (election offices), public_benefits (agencies deciding welfare, unemployment or Medicaid eligibility), emergency_services (911 centers, fire and emergency medical services). A duty that binds only another kind is reported as someone else's; a duty that binds every public body always reaches you. Omitted, every public-body duty reaches you, and run_lint counts the ones that bind a single kind in a coverage line.
regulated_sectorobjectnoWhose duty a financial-law row is. Is this software run by a bank, insurer or other regulated financial entity (body), supplied to one (supplier), or neither (none)? {"financial": "supplier"}. Ask when provides_financial_services or a license class (is_bank, is_lender, is_insurer, is_securities_firm, is_payment_provider, is_crypto_asset_provider) is declared; never infer it. It routes and never matches, so a supplier still declares the classes of its customers. Omitted, the entity's duties are reported as the caller's, and run_lint counts them in a coverage line. For education: is this software run by a school, district, college or university, public or private (body), supplied to one (supplier), or neither (none)? {"education": "supplier"}. Ask when serves_education_institutions, serves_k12_schools or serves_higher_education is declared. Omitted, public_sector body or supplier with public_sector_functions naming public_education answers it.
rolesobjectnoWhich role this software's maker holds, keyed by axis: ai_system (provider, deployer, importer, distributor, product_manufacturer, authorised_representative) and personal_data (controller, processor). Each is the position under each regime's own law, whatever it calls it, such as Colorado's developer (provider), or the CCPA's business or India's data fiduciary (controller). {"ai_system": ["provider"], "personal_data": ["processor"]}; "none" alone when asked and no regime gives it one. Ask the developer; never infer it from the code. Omitted, an axis routes nothing and run_lint counts the duties a role would move in a coverage line.
flowsobject[]noWhere this software stores or sends personal data across a border, one entry per route: [{"from": "eu", "to": "us", "data": "personal", "basis": "contract_clauses"}]. from and to are jurisdiction slugs, as jurisdictions takes them; data is personal or sensitive; basis is the transfer mechanism the route relies on: adequacy, contract_clauses, binding_rules, certification, authority_approval, consent, derogation, unknown. [] when asked and no personal data leaves the jurisdiction it was collected in. Ask the developer; never infer it from the code. Each cross-border transfer finding then names the declared flows that leave its jurisdiction. No finding is dropped or downgraded on a flow.
derivedbooleannotrue adds derived findings: the records an app holds to meet the deadlines the matched laws set, inferred by LexLint and traced to each law. false leaves them out; omitted, the server default applies.
client_versionstringnoThe LexLint plugin version you are running, from your SKILL.md, exactly as check_access takes it. Send it on every lint: a run that skips the preflight otherwise learns nothing about its own staleness. Omitted, update_available comes back null, which means LexLint learned nothing, never that you are current.
briefbooleannoSend true when you will show these findings to a person and have no LexLint procedure loaded. Each finding then comes back as one line to print: its summary and first duty clipped to 160 characters, with the citation, note_url, in_force, owed and kind; the full text of any law is one get_law call away. Leave it out when you write lexlint.yml: brief findings drop fields the manifest keeps.

Result fields

FieldTypeWhat it carries
lintstringOne-line verdict: counts by severity, then the verdict itself. The passing state is "no basic issues found", never "compliant".
activitiesstring[]The declared activities this run was evaluated against, de-duplicated.
jurisdictionsstring[]The declared jurisdiction slugs this run was evaluated against, normalized.
findingsobject[]Every finding, one per instrument per jurisdiction. Group these into work items before showing them; eight jurisdictions produce a list nobody reads.
noticestringThe standing disclaimer. Not legal advice, not a certification, not authorization to access any system.
docsstringWhere the full documentation lives.
corpus_built_atstring or nullWhen the bulk export this run read was built. Null on the per-slug request path, which reads no manifest and so has no build stamp: null means "not reported here", never "not built".
run_atstringThe instant this run was judged at, ISO 8601. Not the same question as corpus_built_at: a finding's kind, severity, staleness and certainty rung move with the clock as well as with the law library, so an instrument becomes a live obligation the moment its effective_date passes, against a law library that has not moved. Send it back on upload_lint_run's compact form, which rebuilds this run at this instant.
freshness_window_daysinteger or nullThe law library's re-read cadence in days, as the export publishes it. Not a staleness threshold: no finding is judged or marked against it. Null when the law library states none.
derivedbooleanThe derived answer this call sent, echoed. Absent when none was sent.
briefbooleanPresent, and true, when the call sent brief: each instrument finding is then one line, and fields it would otherwise carry (detail, why, matched_by, basis, lifecycle, the rest of requires) are not sent. Absent there means not sent, never empty.
replaystringQuote this when you report a problem with a run, and LexLint can reproduce it exactly: the bundle, the law library build, the instant the run was judged at, and a digest of the declaration. Nothing about the run is stored to make it work.
declaration_sensitivityobjectThe finding ids that rest on exactly one declared activity, keyed by that activity in declared order: strike a value the developer doubts and these are the findings that go with it. Show it grouped by activity after the findings. A declared activity nothing rests on alone is absent, and {} means no finding rests on one value. Posture findings rest on crawls_web, which is what draws them; the untagged-activity coverage finding rests on the activity it names; other coverage findings rest on no single value. A value the lint set for you, serves_education_institutions from public_education, is keyed after the declared ones: leave it out to strike it.
client_versionstring or nullThe client_version this call sent back, normalized. Null when none was sent.
latest_versionstringThe newest published LexLint bundle, as the server knows it.
update_availableboolean or nullThree-valued: true means a newer LexLint plugin is published. Null means LexLint learned nothing about your version, which is NOT the same as being current.
update_commandstring or nullThe plugin update command, shown to the developer and not run by the assistant. Present only when update_available is true.
lint_procedure_urlstring or nullA link to show the developer: the written LexLint procedure for the lint loop. Set only for a caller that sent X-API-Key and no bundle version; null for a bundle session, which already holds it, and for a signed-in caller.
lint_procedure_noticestring or nullWhy lint_procedure_url is set and what that procedure holds, for the developer. Null with it.
tested_model_familiesstring[]Which model families LexLint's procedure is exercised against, as lowercase tokens. Nothing about your model is sent to LexLint.
model_noticestringLexLint's advisory to the developer on models outside tested_model_families. Not a gate: the lint runs either way.

Example request

{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "run_lint", "arguments": { "activities": [ "crawls_web", "trains_models" ], "jurisdictions": [ "eu", "us/ca" ] } } }