> ## Documentation Index > Fetch the complete documentation index at: https://vaquill.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # List contract reviews in a matter > Every review in this matter, newest first. A listed review carries its status, its findings summary and its timestamps. The fields that describe what was ASKED FOR (`contractType`, `userSide`, `playbookId`, `jurisdiction`, `round`) are absent from a list and present on a `GET` by id: they live alongside the contract text, and returning them per row would mean pulling every contract in the page across the wire. ## OpenAPI ````yaml https://api.vaquill.ai/workspace/openapi/v1.json get /v1/matters/{matterId}/reviews openapi: 3.1.0 info: title: Vaquill Legal Workspace API description: >- Organization-scoped API for driving your legal workspace from your own backend: matters, documents, drafting, review, compare and matrices. **Authentication**: `Authorization: Bearer vq_ws_...`. Credentials are issued by an organization owner from the automation console at `/automation` and are shown once. The organization is resolved from the credential and can never be named in a request, so there is no `organizationId` field anywhere in this API and sending one is refused. This is NOT the Vaquill Data API. That one holds a `vq_key_` credential and serves the public legal corpus; the two share no credential, host or endpoint, and sending a `vq_key_` here is refused with an error naming the other product. ## Long-running work Anything that costs real work answers `202` with an **operation**. Poll `GET /v1/operations/{operationId}` until `status` is `succeeded`, `failed` or `cancelled`, honouring `Retry-After` between polls. There are no webhooks, so polling is the only completion signal. The five statuses are `queued`, `running`, `succeeded`, `failed`, `cancelled`, and there is no sixth: every capability reports through the same envelope. Send an `Idempotency-Key` on any launch. A retry with the same key and the same body returns the FIRST operation rather than starting a second billable job, which is what makes recovering from a timeout free. ## Identifiers Every public id is `_<32 lowercase hex>`, for example `mat_9f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6`. The prefix names the resource type. Ids are opaque: take them from responses rather than building them, and never pass a bare database uuid. ## Lists Every collection answers `{data, pagination}`, never a bare array. Page with `limit` and `offset`, and read `pagination.total` to size a job before running it. `pagination.hasMore` is the reliable signal that rows remain. ## Errors Errors are RFC 9457 problem documents (`application/problem+json`), including for a wrong path and a wrong method. Branch on `type`; it is the stable identifier and it resolves to a page describing the failure. `title` and `detail` are written for people and may be reworded at any time. Every response carries `X-Request-ID`, and every error repeats it as `requestId`: quote it when contacting support. A `404` is returned identically for a resource that does not exist, one belonging to another organization, and one outside your installation's matter allowlist. That is deliberate, so the status code cannot be used to discover which ids exist elsewhere. ## Rate limits Limits are per credential and are set by what an operation COSTS rather than by its HTTP method, so a `GET` that runs a retrieval is not a read. Each operation's tier is fixed; a `429` carries `Retry-After`. | Tier | Per minute | Per hour | Per day | |---|---|---|---| | `poll` | 120 | 3000 | 30000 | | `read` | 60 | 1200 | 15000 | | `write` | 30 | 600 | 5000 | | `launch` | 10 | 200 | 2000 | | `download` | 20 | 300 | 3000 | | `upload` | 5 | 100 | 500 | ## Scopes A credential carries an explicit scope set, chosen when it is issued. A call outside them is `403` with `insufficient-scope`, naming the scopes the operation needed. Read and run are separate throughout, so a credential can be allowed to read results without being allowed to spend money producing them. `chronology:read`, `chronology:write`, `clients:read`, `clients:write`, `compare:read`, `compare:run`, `compliance:read`, `compliance:run`, `credentials:rotate`, `documents:download`, `documents:read`, `documents:write`, `drafting:read`, `drafting:run`, `exports:create`, `exports:read`, `facts:read`, `facts:run`, `matrices:read`, `matrices:run`, `matrices:write`, `matters:read`, `matters:write`, `nda:read`, `nda:run`, `operations:read`, `playbooks:read`, `playbooks:run`, `playbooks:write`, `research:read`, `research:run`, `review:read`, `review:run`, `summaries:read`, `summaries:run`, `webhooks:read`, `webhooks:write`, `workflows:read`, `workflows:run`, `workflows:write` version: 1.0.0 servers: - url: https://api.vaquill.ai/workspace description: Vaquill Legal Workspace API (production) - url: /workspace description: Vaquill Legal Workspace API (relative to the mount) security: - WorkspaceAuth: [] tags: - name: Operations description: >- The one job envelope. Every long-running call answers `202` with an operation, and polling this resource is the only way to learn it finished: there are no webhooks. Five statuses, no synonyms. - name: Clients description: The people and companies matters are filed under. Synchronous CRUD. - name: Matters description: >- The unit of work everything else hangs off. A matter scopes documents, drafts, reviews, comparisons and matrices, and it is what a credential's access is checked against. - name: Folders description: >- Organization inside and across matters. The same folders the web app shows, so one created here appears in the customer's browser. - name: Documents description: >- Files in a matter: their metadata, their ingested text, and the original bytes. A document is only usable by retrieval, drafting and review once its status is `succeeded`. - name: Uploads description: >- Getting files in. One presigned multipart flow at every size, with the bytes going straight to storage and never through this API. Initiate, PUT each part, then complete. - name: Research description: >- Asking legal questions and getting grounded, cited answers. This API does NOT stream: an ask answers `202` and you poll the operation, then read the answer off the message it points at. Conversation state is kept here, so you hold a chat id rather than replaying a transcript. Also covers the matter settings behind an answer, the skills you can ask through, and the standalone web-research tools. - name: Drafting description: >- Generating, revising and exporting draft documents. Bodies come out as sections and go in as markdown; the editor's own format is never on the wire. Rendered files come from the export route. - name: Playbooks description: >- The organization's negotiating positions, per contract type, and the starter templates to build them from. A playbook is the input a contract review is measured against. - name: Reviews description: >- Reviewing one contract against a playbook: clause analysis, redlines, flags, liability exposure and a reported sign-off gate. Export applies the redlines as native Word tracked changes. - name: Facts description: >- The cross-document fact ledger for a matter: what every document in it asserts, coalesced and cited back to its source passages. - name: Matter summary description: >- A citation-backed summary of everything filed to a matter, generated on demand and readable claim by claim. - name: Chronology description: >- The dated events across a matter's documents, as one timeline, with duplicate and date-conflict flags. - name: NDA triage description: >- Screening one inbound NDA against ten standard criteria and, where you name one, your own NDA playbook. Answers `green`, `yellow` or `red` with the reasoning per criterion, plus a report you can forward. - name: Compliance description: >- Checking one document against one regulation's requirement checklist: a verdict per requirement with the article it comes from, the gaps, and what to do about them. Only regulations with a real checklist behind them are accepted. - name: Comparisons description: >- Diffing two documents in a matter into structural changes, with a substantive-versus-cosmetic judgment and a downloadable redline. - name: Matrices description: >- Spreadsheet-style extraction across many documents: rows are documents, columns are questions, cells are answers with verified citations. Building a grid is free; running it is what costs. - name: Workflows description: >- Multi-step analyses from a fixed catalogue. Read a definition to learn what documents and inputs it takes, launch a run inside a matter, then download the artifacts it produces. externalDocs: description: Getting started guide and error reference url: https://vaquill.ai/docs/workspace-api paths: /v1/matters/{matterId}/reviews: get: tags: - Reviews summary: List contract reviews in a matter description: >- Every review in this matter, newest first. A listed review carries its status, its findings summary and its timestamps. The fields that describe what was ASKED FOR (`contractType`, `userSide`, `playbookId`, `jurisdiction`, `round`) are absent from a list and present on a `GET` by id: they live alongside the contract text, and returning them per row would mean pulling every contract in the page across the wire. operationId: reviews.list parameters: - name: matterId in: path required: true schema: type: string title: Matterid description: >- `mat_` identifier of the matter to work inside. Everything in this API hangs off a matter, and the matter in the path is what the authorization boundary is checked against. Take it from `GET /v1/matters`. - name: limit in: query required: false schema: type: integer maximum: 200 minimum: 1 description: How many rows to return, 1 to 200. Defaults to 50. default: 50 title: Limit description: How many rows to return, 1 to 200. Defaults to 50. - name: offset in: query required: false schema: type: integer minimum: 0 description: >- How many rows to skip before returning any. Combine with `limit` to page: `offset=0`, then `offset=50`, and so on. Offsets are positional, not stable, so a set that changes while you page can show a row twice or not at all. default: 0 title: Offset description: >- How many rows to skip before returning any. Combine with `limit` to page: `offset=0`, then `offset=50`, and so on. Offsets are positional, not stable, so a set that changes while you page can show a row twice or not at all. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/Page_Review_' example: data: - id: rev_9f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 matterId: mat_9f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 status: succeeded contractType: msa userSide: buyer playbookId: value jurisdiction: US round: 1 summary: >- Twelve substantive changes, seven of them in the liability and indemnity sections. overallRisk: yellow businessImpactSummary: >- Two changes shift risk toward us; the rest are housekeeping. approvalGate: required: false level: partner dealBreakerCount: 1 reasons: - clauseName: Limitation of Liability approvalLevel: partner isDealBreaker: false note: 'Escalated to GC: deal value over $1M.' summary: >- Twelve substantive changes, seven of them in the liability and indemnity sections. liabilityExposure: exposureLevel: yellow verdict: >- Liability is capped at fees paid in the preceding twelve months. capStatus: capped capAmount: Fees paid in the preceding twelve months capQuote: >- shall not exceed the fees paid in the preceding twelve months grounding: verified capScope: aggregate capAdequate: false mutualCap: false consequentialDamagesExcluded: false uncappedCarveouts: - Indemnity for IP infringement - Confidentiality breach supercap: Two times fees for data-security breaches indemnityExposure: Uncapped for third-party IP claims. insuranceRequired: $5M commercial general liability claimTimeBar: Claims must be brought within 12 months. counterpartyMatch: name: Acme Corporation vendor: Acme Corporation flexibility: limited negotiationStrategyNote: >- This paper is rarely amended below the enterprise tier; lead with the liability cap. counterpartyRedlinesCount: 4 clauses: - clauseName: Limitation of Liability clauseType: limitation_of_liability sectionReference: '8.2' currentLanguage: Supplier's total liability shall be unlimited. severity: yellow analysis: >- The clause is uncapped and departs from the playbook's standard position. riskDescription: >- Unlimited liability for a breach we cannot fully control. playbookPosition: >- Cap liability at fees paid in the preceding twelve months. approvalLevel: partner isDealBreaker: false redlines: - clauseName: Limitation of Liability sectionReference: '8.2' currentLanguage: Supplier's total liability shall be unlimited. proposedLanguage: >- Supplier's total liability shall not exceed the fees paid in the preceding twelve months. rationale: >- Our standard position caps liability at fees paid in the preceding 12 months. priority: must_have fallbackPosition: Two times fees paid in the preceding twelve months. grounding: verified approvalLevel: partner isDealBreaker: false nature: substantive negotiationPriorities: - tier: 1 tierLabel: Must have items: - Cap liability - Remove uncapped indemnity missingClauses: - Force Majeure flags: - clauseName: Limitation of Liability sectionReference: '8.2' observation: >- The counterparty entity name differs from the one on the signature block. parseWarning: >- Two clauses could not be parsed and are omitted from the findings. deep: clausesReviewed: 1 redlinesKept: 1 clearedAsCompliant: 1 clauseLimit: 40 clausesTruncated: false createdAt: '2026-08-19T14:32:10Z' completedAt: '2026-08-19T14:32:10Z' pagination: limit: 50 offset: 0 total: 128 hasMore: false '401': description: >- The credential is missing, malformed, unknown, revoked or expired. `type` is `invalid-credential`, or `wrong-product-credential` when a `vq_key_` Data API key was sent to this API. headers: X-Request-ID: description: >- The id of this request. The same value appears as `requestId` in the body. Quote it when contacting support. schema: type: string examples: - req_5f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 WWW-Authenticate: description: RFC 9110 authentication challenge. schema: type: string content: application/problem+json: schema: $ref: '#/components/schemas/Problem' '403': description: >- The credential does not carry a scope this operation requires (`insufficient-scope`), or the organization's installation is suspended (`installation-inactive`). headers: X-Request-ID: description: >- The id of this request. The same value appears as `requestId` in the body. Quote it when contacting support. schema: type: string examples: - req_5f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 WWW-Authenticate: description: RFC 9110 authentication challenge. schema: type: string content: application/problem+json: schema: $ref: '#/components/schemas/Problem' '404': description: >- The resource does not exist, is not this organization's, or is outside this installation's matter allowlist. The three are deliberately indistinguishable, so the status code cannot be used to discover which ids exist in another organization. Each resource has its own `type`. headers: X-Request-ID: description: >- The id of this request. The same value appears as `requestId` in the body. Quote it when contacting support. schema: type: string examples: - req_5f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 content: application/problem+json: schema: $ref: '#/components/schemas/Problem' '422': description: >- The request does not match the published schema. `errors` names each rejected field and why. The submitted value is never echoed back. headers: X-Request-ID: description: >- The id of this request. The same value appears as `requestId` in the body. Quote it when contacting support. schema: type: string examples: - req_5f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 content: application/problem+json: schema: $ref: '#/components/schemas/ValidationProblem' '429': description: Too many requests for this credential's tier. Honour `Retry-After`. headers: X-Request-ID: description: >- The id of this request. The same value appears as `requestId` in the body. Quote it when contacting support. schema: type: string examples: - req_5f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 Retry-After: description: Seconds to wait before retrying. schema: type: integer content: application/problem+json: schema: $ref: '#/components/schemas/Problem' '500': description: >- An unexpected error on our side. The body carries a stable `type` and the request id and nothing else; the cause is in our logs. headers: X-Request-ID: description: >- The id of this request. The same value appears as `requestId` in the body. Quote it when contacting support. schema: type: string examples: - req_5f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 content: application/problem+json: schema: $ref: '#/components/schemas/Problem' '503': description: >- A dependency this request needs is unavailable, so nothing was done. Retryable. Authentication fails closed rather than admitting the request, so this is never a statement about your credential. headers: X-Request-ID: description: >- The id of this request. The same value appears as `requestId` in the body. Quote it when contacting support. schema: type: string examples: - req_5f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 content: application/problem+json: schema: $ref: '#/components/schemas/Problem' components: schemas: Page_Review_: properties: data: items: $ref: '#/components/schemas/Review' type: array title: Data description: The rows in this window, in the collection's default order. pagination: $ref: '#/components/schemas/Pagination' description: Where this window sits in the full result set. additionalProperties: false type: object required: - data - pagination title: Page[Review] Problem: type: object title: Problem description: >- An RFC 9457 problem document. Branch on `type`, which is stable; `title` and `detail` are written for people and may be reworded. Some problems carry extra members (`requiredScopes`, `limit`, `expectedVersion`), which is why this object is open. required: - type - title - status - detail - instance properties: type: type: string format: uri description: >- The stable identifier for this error, and the one field to branch on. Resolves to a page describing it. examples: - https://vaquill.ai/docs/workspace-api/errors/insufficient-scope title: type: string description: A short human-readable summary. examples: - Insufficient scope status: type: integer description: The HTTP status code, repeated. examples: - 403 detail: type: string description: >- What went wrong on this specific request. May be reworded at any time. examples: - >- This credential carries matters:read. This operation needs matters:write. instance: type: string description: The path this problem occurred on. examples: - /workspace/v1/matters/mat_9f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 requestId: type: string description: >- The id of this request, identical to the `X-Request-ID` response header. Quote it when contacting support. examples: - req_5f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 additionalProperties: true ValidationProblem: type: object title: ValidationProblem description: >- A problem document for a schema rejection. `errors` lists the fields that were refused. The value you submitted is deliberately not echoed, so a validation failure cannot copy your content into an error response or into either side's logs. required: - type - title - status - detail - instance - errors properties: type: type: string format: uri description: >- The stable identifier for this error, and the one field to branch on. Resolves to a page describing it. examples: - https://vaquill.ai/docs/workspace-api/errors/insufficient-scope title: type: string description: A short human-readable summary. examples: - Insufficient scope status: type: integer description: The HTTP status code, repeated. examples: - 403 detail: type: string description: >- What went wrong on this specific request. May be reworded at any time. examples: - >- This credential carries matters:read. This operation needs matters:write. instance: type: string description: The path this problem occurred on. examples: - /workspace/v1/matters/mat_9f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 requestId: type: string description: >- The id of this request, identical to the `X-Request-ID` response header. Quote it when contacting support. examples: - req_5f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 errors: type: array description: One entry per rejected field. items: type: object required: - location - message - type properties: location: type: string description: >- Dotted path to the rejected field, for example `body.contentMarkdown`. message: type: string description: Why it was rejected. type: type: string description: The validation rule that failed. additionalProperties: true Review: properties: id: type: string title: Id description: Public identifier, `rev_` followed by 32 hex characters. examples: - rev_9f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 matterId: type: string title: Matterid description: '`mat_` identifier of the matter this review belongs to.' examples: - mat_9f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 status: $ref: '#/components/schemas/OperationStatus' description: >- Review status, using the same five public values as an operation. While `queued` or `running`, every findings list is empty and the scalar fields are absent. That is the truthful shape of a review that has not happened yet, not an error. examples: - succeeded contractType: anyOf: - type: string - type: 'null' title: Contracttype description: Contract type the review ran as, echoed from the request. examples: - msa userSide: anyOf: - type: string - type: 'null' title: Userside description: Which side the review argued for, echoed from the request. examples: - buyer playbookId: anyOf: - type: string - type: 'null' title: Playbookid description: >- The playbook the review actually ran against. Absent when it ran against the built-in defaults, so the two cases can be told apart after the fact. examples: - pbk_9f2c8b1e4a7d43c9b6e0f1a2c3d4e5f6 jurisdiction: anyOf: - type: string - type: 'null' title: Jurisdiction description: Jurisdiction the review ran under. examples: - US round: type: integer title: Round description: Negotiation round this review was run for. default: 1 examples: - 1 summary: type: string title: Summary description: Prose summary of the review's conclusions. default: '' examples: - >- Twelve substantive changes, seven of them in the liability and indemnity sections. overallRisk: anyOf: - type: string - type: 'null' title: Overallrisk description: 'Overall risk rating for the contract: `green`, `yellow` or `red`.' examples: - yellow businessImpactSummary: anyOf: - type: string - type: 'null' title: Businessimpactsummary description: What the findings mean commercially, in plain language. examples: - Two changes shift risk toward us; the rest are housekeeping. approvalGate: anyOf: - $ref: '#/components/schemas/ReviewApprovalGate' - type: 'null' description: >- Whether a human should sign this off before it goes out. Reported, never enforced. liabilityExposure: anyOf: - $ref: '#/components/schemas/ReviewLiabilityExposure' - type: 'null' description: >- How much you are on the hook for: caps, carve-outs, indemnities and insurance. counterpartyMatch: anyOf: - $ref: '#/components/schemas/ReviewCounterpartyMatch' - type: 'null' description: >- Set when a known counterparty paper was recognized, which means the findings include counterparty-specific redlines layered on the general analysis. clauses: items: $ref: '#/components/schemas/ReviewClause' type: array title: Clauses description: >- Every clause analyzed, with its severity against the playbook position. redlines: items: $ref: '#/components/schemas/ReviewRedline' type: array title: Redlines description: >- Proposed edits, ready to send to counterparty counsel. Check each one's `grounding` before applying it automatically. negotiationPriorities: items: $ref: '#/components/schemas/ReviewNegotiationPriority' type: array title: Negotiationpriorities description: What to raise first and what to trade, in tiers. missingClauses: items: type: string type: array title: Missingclauses description: >- Standard clauses ABSENT from the contract. The one finding that cannot be expressed as a clause analysis, because there is no clause to analyze. examples: - - Force Majeure flags: items: $ref: '#/components/schemas/ReviewFlag' type: array title: Flags description: >- Things the reviewer noticed and deliberately did not redline: a wrong entity name, an odd schedule entry, a real ambiguity. Confirm these with a human before signing. parseWarning: anyOf: - type: string - type: 'null' title: Parsewarning description: >- Set when the model's output only partly parsed, which means the findings may be incomplete. Present is the difference between acting on the findings and asking a human first. examples: - Two clauses could not be parsed and are omitted from the findings. deep: anyOf: - $ref: '#/components/schemas/ReviewDeepMeta' - type: 'null' description: >- What the deep verification pass did. Absent on a standard review, which is the signal that no verification ran rather than that it found nothing. createdAt: type: string format: date-time title: Createdat description: When the review was created (RFC 3339). examples: - '2026-08-19T14:32:10Z' completedAt: anyOf: - type: string format: date-time - type: 'null' title: Completedat description: When the review reached a terminal status (RFC 3339). examples: - '2026-08-19T14:32:10Z' additionalProperties: false type: object required: - id - matterId - status - createdAt title: Review description: 'One contract review: its findings, or its progress toward them.' Pagination: properties: limit: type: integer title: Limit description: The `limit` that was applied to this request. examples: - 50 offset: type: integer title: Offset description: The `offset` that was applied to this request. examples: - 0 total: type: integer title: Total description: >- Total rows matching the filter, not the number returned in `data`. Use it to size a job before running it. examples: - 128 hasMore: type: boolean title: Hasmore description: >- True when rows remain beyond this window. Derived from `offset + len(data) < total`, so a full final page correctly reports `false` rather than sending you after an empty page. examples: - false additionalProperties: false type: object required: - limit - offset - total - hasMore title: Pagination description: >- Where the caller is, and whether there is more. `total` is the count of rows matching the filter, not the count returned, so a caller can size a job before running it. OperationStatus: type: string enum: - queued - running - succeeded - failed - cancelled title: OperationStatus description: >- The public five. There is no sixth, and there are no synonyms. Internal vocabularies spell terminal success `completed`, `ready`, `extracted`, `succeeded` and `fresh`; terminal failure `failed` and `error`; queued `pending`, `queued` and `draft`. All of that is collapsed here by `app.workspace_api.adapters.status_map`, which refuses to guess. ReviewApprovalGate: properties: required: type: boolean title: Required description: >- Whether a human should sign this off before it goes to the counterparty. REPORTED, never enforced: it does not block the review or the export. Implement the gate on your side using this field. default: false examples: - false level: anyOf: - type: string - type: 'null' title: Level description: >- The highest sign-off any gating clause needs: `manager`, `partner` or `gc`. Absent when `required` is false. examples: - partner dealBreakerCount: type: integer title: Dealbreakercount description: How many clauses sit at or below the walk-away floor. default: 0 examples: - 1 reasons: items: $ref: '#/components/schemas/ReviewApprovalReason' type: array title: Reasons description: Which clauses drive the gate, and why each one does. summary: type: string title: Summary description: One-line explanation of the gate, suitable to show a reviewer. default: '' examples: - >- Twelve substantive changes, seven of them in the liability and indemnity sections. additionalProperties: false type: object title: ReviewApprovalGate description: >- Whether a human has to sign this off before it goes to the counterparty. **Reported, never enforced.** The gate is computed deterministically from the playbook's own `approvalLevel` and `dealBreaker` on clauses that actually deviated, and it is published as a fact about the result. It does not block the review, it does not block the export, and the operation reaches a terminal status either way. That is the same decision the acting-user header already carries (docs 07.3): we record what we know and build no enforcement machinery we cannot honour. Enforcing would mean an approval workflow, an enrolled approver directory and a state a review can sit in indefinitely, which is precisely the "do not let it hang" failure the handoff for this track warned about. A caller that wants a gate has everything it needs to implement one: `required` says whether, `level` says who, and `reasons` says why. ReviewLiabilityExposure: properties: exposureLevel: type: string title: Exposurelevel description: >- Overall liability exposure from your side: `green`, `yellow` or `red`. examples: - yellow verdict: type: string title: Verdict description: Plain-language summary of the liability position. default: '' examples: - Liability is capped at fees paid in the preceding twelve months. capStatus: anyOf: - type: string - type: 'null' title: Capstatus description: >- Whether liability is capped: `capped`, `uncapped`, `partial` or `not_addressed`. Null when it could not be determined. examples: - capped capAmount: anyOf: - type: string - type: 'null' title: Capamount description: >- The cap as written, as a string rather than a number since contracts express it in many forms (a figure, a multiple of fees, a formula). examples: - Fees paid in the preceding twelve months capQuote: anyOf: - type: string - type: 'null' title: Capquote description: >- The verbatim contract sentence the cap claim is drawn from, so a headline number can be checked against the source rather than trusted. examples: - shall not exceed the fees paid in the preceding twelve months grounding: anyOf: - type: string - type: 'null' title: Grounding description: >- `verified` when `capQuote` is a literal span of the contract, `unverified` when it could not be found. Same meaning as on a redline. examples: - verified capScope: anyOf: - type: string - type: 'null' title: Capscope description: >- What the cap applies across: `per_claim`, `aggregate`, `both` or `unclear`. examples: - aggregate capAdequate: anyOf: - type: boolean - type: 'null' title: Capadequate description: >- Whether the cap is meaningful against plausible harm and deal value. A cap tied to fees paid to date is inadequate even though a cap exists. examples: - false mutualCap: anyOf: - type: boolean - type: 'null' title: Mutualcap description: Whether the cap applies to both sides equally. examples: - false consequentialDamagesExcluded: anyOf: - type: boolean - type: 'null' title: Consequentialdamagesexcluded description: Whether consequential and indirect damages are excluded. examples: - false uncappedCarveouts: items: type: string type: array title: Uncappedcarveouts description: >- Categories of liability that sit OUTSIDE the cap, for example indemnity or confidentiality breaches. examples: - - Indemnity for IP infringement - Confidentiality breach supercap: anyOf: - type: string - type: 'null' title: Supercap description: >- A raised cap that applies to specific categories, when the contract sets one. examples: - Two times fees for data-security breaches indemnityExposure: anyOf: - type: string - type: 'null' title: Indemnityexposure description: What you are indemnifying the counterparty for. examples: - Uncapped for third-party IP claims. insuranceRequired: anyOf: - type: string - type: 'null' title: Insurancerequired description: Insurance the contract requires you to carry. examples: - $5M commercial general liability claimTimeBar: anyOf: - type: string - type: 'null' title: Claimtimebar description: Any deadline for bringing a claim under the contract. examples: - Claims must be brought within 12 months. additionalProperties: false type: object required: - exposureLevel title: ReviewLiabilityExposure description: >- How much the reviewer is on the hook for, in one panel. Every field is nullable and stays nullable. This is assembled defensively from LLM output about contract language that may not exist: a contract with no liability clause has no cap, and `null` is the true answer rather than a zero that reads as "capped at nothing". ReviewCounterpartyMatch: properties: name: type: string title: Name description: Name of the recognized counterparty paper. examples: - Acme Corporation vendor: type: string title: Vendor description: The vendor whose standard form this is. examples: - Acme Corporation flexibility: type: string title: Flexibility description: >- How negotiable this paper is in practice: `rigid`, `limited` or `standard`. examples: - limited negotiationStrategyNote: type: string title: Negotiationstrategynote description: How to approach negotiating against this specific paper. examples: - >- This paper is rarely amended below the enterprise tier; lead with the liability cap. counterpartyRedlinesCount: type: integer title: Counterpartyredlinescount description: >- How many redlines the counterparty overlay contributed on top of the general analysis. A non-zero value means the findings are tuned to this specific paper. default: 0 examples: - 4 additionalProperties: false type: object required: - name - vendor - flexibility - negotiationStrategyNote title: ReviewCounterpartyMatch description: >- A known counterparty paper was recognised in the contract text. Published so a caller knows the findings include counterparty-specific redlines layered on top of the general analysis, which changes how the result should be read. The catalogue slug and the phrases that matched are NOT published: they are our detection internals, and neither is actionable. ReviewClause: properties: clauseName: type: string title: Clausename description: >- Human-readable name of the clause, for example 'Limitation of Liability'. examples: - Limitation of Liability clauseType: type: string title: Clausetype description: >- Clause-type slug the analysis matched, the same key a playbook's `positions` map uses. examples: - limitation_of_liability sectionReference: anyOf: - type: string - type: 'null' title: Sectionreference description: Where the clause sits in the contract, for example `8.2`. examples: - '8.2' currentLanguage: type: string title: Currentlanguage description: >- The exact quote from the contract this analysis is about. Empty when the finding is that the clause is ABSENT, which is the one case with nothing to quote. default: '' examples: - Supplier's total liability shall be unlimited. severity: type: string title: Severity description: >- How far the clause deviates from the playbook position: `green`, `yellow` or `red`. Published as a plain string so a new level cannot break your client. examples: - yellow analysis: type: string title: Analysis description: What the reviewer concluded about this clause. examples: - >- The clause is uncapped and departs from the playbook's standard position. riskDescription: anyOf: - type: string - type: 'null' title: Riskdescription description: What could go wrong if the clause stands as written. examples: - Unlimited liability for a breach we cannot fully control. playbookPosition: anyOf: - type: string - type: 'null' title: Playbookposition description: The playbook position this clause was measured against. examples: - Cap liability at fees paid in the preceding twelve months. approvalLevel: anyOf: - type: string - type: 'null' title: Approvallevel description: >- Sign-off a deviation on this clause needs: `none`, `manager`, `partner` or `gc`. Computed server-side by matching the clause to its playbook position, never asserted by the model. Only meaningful when `severity` is not green. examples: - partner isDealBreaker: type: boolean title: Isdealbreaker description: True when the clause is at or below the playbook's walk-away floor. default: false examples: - false additionalProperties: false type: object required: - clauseName - clauseType - severity - analysis title: ReviewClause description: One clause, as analyzed against the playbook position for its type. ReviewRedline: properties: clauseName: type: string title: Clausename description: Which clause this edit applies to. examples: - Limitation of Liability sectionReference: anyOf: - type: string - type: 'null' title: Sectionreference description: Where the clause sits in the contract, for example `8.2`. examples: - '8.2' currentLanguage: type: string title: Currentlanguage description: >- The text to be replaced, as it stands in the contract. Empty for an insertion. default: '' examples: - Supplier's total liability shall be unlimited. proposedLanguage: type: string title: Proposedlanguage description: The replacement text to send to the counterparty. examples: - >- Supplier's total liability shall not exceed the fees paid in the preceding twelve months. rationale: type: string title: Rationale description: >- Why this edit is being proposed. Suitable to put in a margin comment. examples: - >- Our standard position caps liability at fees paid in the preceding 12 months. priority: type: string title: Priority description: >- How hard to push for this edit: `must_have`, `should_have` or `nice_to_have`. examples: - must_have fallbackPosition: anyOf: - type: string - type: 'null' title: Fallbackposition description: >- What to retreat to if this edit is rejected, taken from the playbook's fallback ladder. examples: - Two times fees paid in the preceding twelve months. grounding: type: string title: Grounding description: >- Whether `currentLanguage` was found verbatim in the contract. `verified` means it was. `unverified` means it was NOT, so the edit may be misanchored. `insertion` means there is nothing to anchor because the clause is missing. An integration applying redlines automatically must stop and ask a human on `unverified`. default: verified examples: - verified approvalLevel: anyOf: - type: string - type: 'null' title: Approvallevel description: >- Sign-off this edit needs before it goes out: `none`, `manager`, `partner` or `gc`. examples: - partner isDealBreaker: type: boolean title: Isdealbreaker description: >- True when the clause this edit addresses is at or below the walk-away floor. default: false examples: - false nature: anyOf: - type: string - type: 'null' title: Nature description: >- `substantive` or `housekeeping`. Absent means unclassified, on a review produced before the pipeline classified this. Absent is NOT the same as `housekeeping`. examples: - substantive additionalProperties: false type: object required: - clauseName - proposedLanguage - rationale - priority title: ReviewRedline description: One proposed edit, ready to send to counterparty counsel. ReviewNegotiationPriority: properties: tier: type: integer title: Tier description: >- Priority tier: 1 is must-have and covers deal breakers, 2 is should-have, 3 is nice-to-have. examples: - 1 tierLabel: type: string title: Tierlabel description: Human-readable name for the tier. examples: - Must have items: items: type: string type: array title: Items description: What to raise at this tier, in order. examples: - - Cap liability - Remove uncapped indemnity additionalProperties: false type: object required: - tier - tierLabel - items title: ReviewNegotiationPriority description: >- One tier of the negotiation plan: what to raise first, and what to trade. ReviewFlag: properties: clauseName: type: string title: Clausename description: Which clause or part of the contract the observation is about. examples: - Limitation of Liability sectionReference: anyOf: - type: string - type: 'null' title: Sectionreference description: Where it sits in the contract. examples: - '8.2' observation: type: string title: Observation description: >- What the reviewer noticed. These are things a human should confirm before signing, not edits, which makes them the most important field here for a caller automating the review away. examples: - >- The counterparty entity name differs from the one on the signature block. additionalProperties: false type: object required: - clauseName - observation title: ReviewFlag description: >- Something the reviewer noticed and deliberately did NOT redline. A wrong entity name, an odd schedule entry, a real ambiguity. These are not edits; they are things a human should confirm before signing, which makes them the most important thing on this surface for a caller that is otherwise automating the review away. ReviewDeepMeta: properties: clausesReviewed: type: integer title: Clausesreviewed description: How many first-pass flagged clauses the deep pass verified. examples: - 1 redlinesKept: type: integer title: Redlineskept description: How many survived verification and are in `redlines`. examples: - 1 clearedAsCompliant: type: integer title: Clearedascompliant description: >- How many first-pass flags the deep pass cleared as already compliant, and therefore dropped. Fewer false positives is the point of running deep. examples: - 1 clauseLimit: type: integer title: Clauselimit description: >- The ceiling on how many flagged clauses a deep review verifies, currently 40. default: 40 examples: - 40 clausesTruncated: type: boolean title: Clausestruncated description: >- True when the deep pass hit its 40-clause ceiling, which means first-pass flags beyond it were NOT verified and are NOT in `redlines`. Treat the review as covering the first 40 findings only. A boolean rather than a count because the number dropped is not recorded anywhere upstream. default: false examples: - false additionalProperties: false type: object required: - clausesReviewed - redlinesKept - clearedAsCompliant title: ReviewDeepMeta description: >- What the deep verification pass did, present only when one ran. Absent on a standard review, which is the honest signal that no verification happened rather than a zeroed object implying one found nothing. `estimatedCostUsd` is dropped on the way through. It is our spend and our model choice, and it is on the list of things a published DTO always drops. ReviewApprovalReason: properties: clauseName: type: string title: Clausename description: The clause driving this part of the gate. examples: - Limitation of Liability approvalLevel: anyOf: - type: string - type: 'null' title: Approvallevel description: Sign-off this clause requires. examples: - partner isDealBreaker: type: boolean title: Isdealbreaker description: True when this clause is at or below the walk-away floor. default: false examples: - false note: anyOf: - type: string - type: 'null' title: Note description: >- Set when a conditional rule RAISED this clause's sign-off, for example 'Escalated to GC: deal value over $1M'. Absent when the level came straight from the playbook position. examples: - 'Escalated to GC: deal value over $1M.' additionalProperties: false type: object required: - clauseName title: ReviewApprovalReason description: One clause driving the review-level sign-off gate. securitySchemes: WorkspaceAuth: type: http scheme: bearer bearerFormat: vq_ws_* description: >- Workspace credential issued from the automation console at `/automation`. Send it as `Authorization: Bearer vq_ws_...`. This is NOT a Data API key: a `vq_key_` credential is refused here and names the other product in the error. ````