Close httplib2 connections.
create(parent, body=None, requestId=None, reviewId=None, x__xgafv=None)
Creates and initiates an asynchronous multi-agent review for a document. Returns a google.longrunning.Operation. When the operation completes, the `response` field contains a `Review` and the `metadata` field contains `CreateReviewMetadata`.
Retrieves a specific review execution result.
list(parent, filter=None, orderBy=None, pageSize=None, pageToken=None, x__xgafv=None)
Lists all review execution runs for a document.
list_next(previous_request, previous_response)
Retrieves the next page of results.
close()
Close httplib2 connections.
create(parent, body=None, requestId=None, reviewId=None, x__xgafv=None)
Creates and initiates an asynchronous multi-agent review for a document. Returns a google.longrunning.Operation. When the operation completes, the `response` field contains a `Review` and the `metadata` field contains `CreateReviewMetadata`.
Args:
parent: string, Required. The parent Document resource name where this review will be created. (required)
body: object, The request body.
The object takes the form of:
{ # An evaluation run of a document.
"createTime": "A String", # Output only. Timestamp when this review attempt was initiated.
"endTime": "A String", # Output only. Timestamp when the review reached a terminal state.
"name": "A String", # Identifier. Resource name in format `documents/{document}/reviews/{review}`.
"progressPercent": 42, # Output only. Estimated completion progress percentage of the review in [0, 100].
"result": { # Encapsulates the synthesized output or failure details of a single review execution. # Output only. Review output (markdown, errors, and future modalities).
"anchoredComments": [ # Output only. Structured review comments anchored to specific locations in the document. At most 300 anchored comments are returned per review.
{ # A structured review comment anchored to a specific location in the document.
"bodyMarkdown": "A String", # Output only. Detailed markdown explanation of the review comment.
"citationReport": { # Structured citation verification report for a single bibliography reference. # Output only. Optional structured citation verification report when this comment corresponds to a bibliography reference.
"citationKey": "A String", # Output only. Generated BibTeX citation key (e.g., "smith2023deep").
"entryType": "A String", # Output only. BibTeX entry type (e.g., "article", "inproceedings", "misc").
"extractedMetadata": { # Structured bibliographic metadata for an extracted or retrieved work. # Output only. Metadata parsed from the paper's bibliography entry.
"authors": [ # Output only. Ordered list of authors.
{ # Author name components.
"familyName": "A String", # Output only. Author family name / surname (or organization name).
"givenName": "A String", # Output only. Author given name / initials.
},
],
"doi": "A String", # Output only. Digital Object Identifier (DOI).
"journal": "A String", # Output only. Journal, conference, or venue name.
"pages": "A String", # Output only. Page range or article number.
"publicationDate": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # Output only. Publication date (month and day left as 0 if just year).
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"source": "A String", # Output only. Source database for retrieved metadata (e.g., "openalex", "crossref"). Empty on `extracted_metadata`.
"title": "A String", # Output only. Work title.
"urls": [ # Output only. URLs associated with the reference.
"A String",
],
"volume": "A String", # Output only. Volume identifier.
},
"fieldComparisons": [ # Output only. Per-field comparisons (populated only when `retrieved_metadata` is present).
{ # Per-field comparison result between extracted and retrieved metadata.
"detail": "A String", # Output only. Human-readable comparison detail (e.g., "extracted=2023, found=2024 (diff=1)").
"fieldKey": "A String", # Output only. Field key ("title", "authors", "year", "journal", "volume", "pages", "doi").
"match": True or False, # Output only. Whether the extracted and retrieved values matched.
},
],
"finalVerdict": "A String", # Output only. Final combined verdict after database lookup and search grounding.
"firstAuthorFamilyNameMatch": True or False, # Output only. Whether the first author's family name matched between extracted and retrieved metadata.
"groundingUrls": [ # Output only. Web sources surfaced during Google Search grounding.
{ # Web source URL surfaced during Google Search grounding verification.
"title": "A String", # Output only. Source page title or domain.
"url": "A String", # Output only. Source URL.
},
],
"lookupVerdict": "A String", # Output only. Verdict from scholarly database lookup (OpenAlex / Crossref) before search grounding.
"rawReference": "A String", # Output only. Verbatim reference string extracted from the paper's bibliography.
"refNum": 42, # Output only. 1-indexed bibliography reference number in the paper.
"retrievedBibtex": "A String", # Output only. Formatted BibTeX entry for the verified `retrieved_metadata` when present. Empty when `retrieved_metadata` is absent.
"retrievedMetadata": { # Structured bibliographic metadata for an extracted or retrieved work. # Output only. Metadata retrieved from OpenAlex / Crossref. Populated only when the retrieved work's title matches the extracted title. Omitted when no candidate matches the title so unrelated papers are never displayed as candidates.
"authors": [ # Output only. Ordered list of authors.
{ # Author name components.
"familyName": "A String", # Output only. Author family name / surname (or organization name).
"givenName": "A String", # Output only. Author given name / initials.
},
],
"doi": "A String", # Output only. Digital Object Identifier (DOI).
"journal": "A String", # Output only. Journal, conference, or venue name.
"pages": "A String", # Output only. Page range or article number.
"publicationDate": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # Output only. Publication date (month and day left as 0 if just year).
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"source": "A String", # Output only. Source database for retrieved metadata (e.g., "openalex", "crossref"). Empty on `extracted_metadata`.
"title": "A String", # Output only. Work title.
"urls": [ # Output only. URLs associated with the reference.
"A String",
],
"volume": "A String", # Output only. Volume identifier.
},
"searchMethod": "A String", # Output only. Strategy that produced the scholarly database match (e.g., "doi", "title", "title_author", "autocomplete"). Empty when no title-matching candidate was found.
"searchRationale": "A String", # Output only. Explanation from the Google Search grounding verification step (when run).
"searchVerdict": "A String", # Output only. Verdict from Google Search grounding verification (when run).
},
"commentId": "A String", # Output only. Unique identifier for the comment within the review.
"location": { # A location targeting either a PDF page region/quote or text lines in the document. # Output only. Polymorphic location in the document where this comment is anchored.
"pdf": { # Location anchor within a PDF document. # Output only. Location within a rendered PDF document.
"boundingBoxes": [ # Output only. Normalized bounding boxes [0.0, 1.0] relative to page width and height. At most 50 bounding boxes are returned per anchored span.
{ # Bounding box in normalized [0.0, 1.0] page coordinates (origin top-left).
"bottom": 3.14, # Output only. Bottom coordinate in [0.0, 1.0].
"left": 3.14, # Output only. Left coordinate in [0.0, 1.0].
"right": 3.14, # Output only. Right coordinate in [0.0, 1.0].
"top": 3.14, # Output only. Top coordinate in [0.0, 1.0].
},
],
"pageNumber": 42, # Output only. 1-indexed page number within the PDF document.
"quoteSelector": { # W3C Web Annotation TextQuoteSelector for resilient text anchoring (see https://www.w3.org/TR/annotation-model/#text-quote-selector for details). # Output only. W3C Web Annotation TextQuoteSelector (https://www.w3.org/TR/annotation-model/#text-quote-selector) for exact text span highlighting.
"exact": "A String", # Output only. Verbatim substring extracted from the document character stream.
"prefix": "A String", # Output only. Characters immediately preceding `exact` for disambiguation.
"suffix": "A String", # Output only. Characters immediately following `exact` for disambiguation.
},
},
"text": { # Location anchor within a plain-text, Markdown, or LaTeX source document. # Output only. Location within a plain-text, Markdown, or LaTeX source document.
"firstColumn": 42, # Output only. Optional 1-indexed inclusive first column offset within `first_line`.
"firstLine": 42, # Output only. 1-indexed inclusive first line number.
"lastColumn": 42, # Output only. Optional 1-indexed inclusive last column offset within `last_line`.
"lastLine": 42, # Output only. 1-indexed inclusive last line number.
"quotedLinePreview": "A String", # Output only. Verbatim snippet of the anchored source line(s).
},
},
"severity": "A String", # Output only. Severity classification of the comment.
"suggestedEdit": "A String", # Output only. Optional suggested replacement text or edit for the anchored span.
"summary": "A String", # Output only. Short one-line summary of the review comment.
},
],
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Output only. Failure status details if review execution failed.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"reviewMarkdown": "A String", # Output only. Synthesized review report markdown.
},
"runConfig": { # Configuration options for the multi-agent document review execution pipeline. # Optional. Run configuration parameters used for this review.
"geminiApiKey": "A String", # Optional. Input only. Developer Bring-Your-Own-Key Gemini API key. When provided, requests are billed to the caller's Gemini API project. Input only; forwarded to the asynchronous review runner in the task payload and never persisted in database records or returned in review resources (see companion field `gemini_api_key_set`, AIP-147).
"geminiApiKeySet": True or False, # Output only. Indicates whether a developer Bring-Your-Own-Key Gemini API key was provided for this review run.
"model": "A String", # Optional. The Gemini model identifier to use for the review. If omitted, the server uses its default model. Unsupported values return INVALID_ARGUMENT.
"thinkingLevel": "A String", # Optional. Reasoning effort level for model calls in the review pipeline. Defaults to `THINKING_LEVEL_MEDIUM` when omitted or `THINKING_LEVEL_UNSPECIFIED`. Non-`THINKING_LEVEL_MEDIUM` thinking levels require `gemini_api_key` when calling `CreateReview`; otherwise `CreateReview` returns `INVALID_ARGUMENT`.
"topology": "A String", # Optional. Review execution topology profile to use.
"userPrompt": "A String", # Optional. User-provided guidance, focus areas, or custom evaluation instructions passed to the review agents.
},
"startTime": "A String", # Output only. Timestamp when the worker started evaluation.
"state": "A String", # Output only. Current review lifecycle state.
}
requestId: string, Optional. Idempotency identifier for network retry safety (AIP-155). Must be a valid UUID4 string.
reviewId: string, Optional. The ID to use for the review, which will become the final component of the review's resource name. If not provided, a unique server-generated UUID will be assigned.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}
get(name, x__xgafv=None)
Retrieves a specific review execution result.
Args:
name: string, Required. The resource name of the review to retrieve. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # An evaluation run of a document.
"createTime": "A String", # Output only. Timestamp when this review attempt was initiated.
"endTime": "A String", # Output only. Timestamp when the review reached a terminal state.
"name": "A String", # Identifier. Resource name in format `documents/{document}/reviews/{review}`.
"progressPercent": 42, # Output only. Estimated completion progress percentage of the review in [0, 100].
"result": { # Encapsulates the synthesized output or failure details of a single review execution. # Output only. Review output (markdown, errors, and future modalities).
"anchoredComments": [ # Output only. Structured review comments anchored to specific locations in the document. At most 300 anchored comments are returned per review.
{ # A structured review comment anchored to a specific location in the document.
"bodyMarkdown": "A String", # Output only. Detailed markdown explanation of the review comment.
"citationReport": { # Structured citation verification report for a single bibliography reference. # Output only. Optional structured citation verification report when this comment corresponds to a bibliography reference.
"citationKey": "A String", # Output only. Generated BibTeX citation key (e.g., "smith2023deep").
"entryType": "A String", # Output only. BibTeX entry type (e.g., "article", "inproceedings", "misc").
"extractedMetadata": { # Structured bibliographic metadata for an extracted or retrieved work. # Output only. Metadata parsed from the paper's bibliography entry.
"authors": [ # Output only. Ordered list of authors.
{ # Author name components.
"familyName": "A String", # Output only. Author family name / surname (or organization name).
"givenName": "A String", # Output only. Author given name / initials.
},
],
"doi": "A String", # Output only. Digital Object Identifier (DOI).
"journal": "A String", # Output only. Journal, conference, or venue name.
"pages": "A String", # Output only. Page range or article number.
"publicationDate": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # Output only. Publication date (month and day left as 0 if just year).
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"source": "A String", # Output only. Source database for retrieved metadata (e.g., "openalex", "crossref"). Empty on `extracted_metadata`.
"title": "A String", # Output only. Work title.
"urls": [ # Output only. URLs associated with the reference.
"A String",
],
"volume": "A String", # Output only. Volume identifier.
},
"fieldComparisons": [ # Output only. Per-field comparisons (populated only when `retrieved_metadata` is present).
{ # Per-field comparison result between extracted and retrieved metadata.
"detail": "A String", # Output only. Human-readable comparison detail (e.g., "extracted=2023, found=2024 (diff=1)").
"fieldKey": "A String", # Output only. Field key ("title", "authors", "year", "journal", "volume", "pages", "doi").
"match": True or False, # Output only. Whether the extracted and retrieved values matched.
},
],
"finalVerdict": "A String", # Output only. Final combined verdict after database lookup and search grounding.
"firstAuthorFamilyNameMatch": True or False, # Output only. Whether the first author's family name matched between extracted and retrieved metadata.
"groundingUrls": [ # Output only. Web sources surfaced during Google Search grounding.
{ # Web source URL surfaced during Google Search grounding verification.
"title": "A String", # Output only. Source page title or domain.
"url": "A String", # Output only. Source URL.
},
],
"lookupVerdict": "A String", # Output only. Verdict from scholarly database lookup (OpenAlex / Crossref) before search grounding.
"rawReference": "A String", # Output only. Verbatim reference string extracted from the paper's bibliography.
"refNum": 42, # Output only. 1-indexed bibliography reference number in the paper.
"retrievedBibtex": "A String", # Output only. Formatted BibTeX entry for the verified `retrieved_metadata` when present. Empty when `retrieved_metadata` is absent.
"retrievedMetadata": { # Structured bibliographic metadata for an extracted or retrieved work. # Output only. Metadata retrieved from OpenAlex / Crossref. Populated only when the retrieved work's title matches the extracted title. Omitted when no candidate matches the title so unrelated papers are never displayed as candidates.
"authors": [ # Output only. Ordered list of authors.
{ # Author name components.
"familyName": "A String", # Output only. Author family name / surname (or organization name).
"givenName": "A String", # Output only. Author given name / initials.
},
],
"doi": "A String", # Output only. Digital Object Identifier (DOI).
"journal": "A String", # Output only. Journal, conference, or venue name.
"pages": "A String", # Output only. Page range or article number.
"publicationDate": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # Output only. Publication date (month and day left as 0 if just year).
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"source": "A String", # Output only. Source database for retrieved metadata (e.g., "openalex", "crossref"). Empty on `extracted_metadata`.
"title": "A String", # Output only. Work title.
"urls": [ # Output only. URLs associated with the reference.
"A String",
],
"volume": "A String", # Output only. Volume identifier.
},
"searchMethod": "A String", # Output only. Strategy that produced the scholarly database match (e.g., "doi", "title", "title_author", "autocomplete"). Empty when no title-matching candidate was found.
"searchRationale": "A String", # Output only. Explanation from the Google Search grounding verification step (when run).
"searchVerdict": "A String", # Output only. Verdict from Google Search grounding verification (when run).
},
"commentId": "A String", # Output only. Unique identifier for the comment within the review.
"location": { # A location targeting either a PDF page region/quote or text lines in the document. # Output only. Polymorphic location in the document where this comment is anchored.
"pdf": { # Location anchor within a PDF document. # Output only. Location within a rendered PDF document.
"boundingBoxes": [ # Output only. Normalized bounding boxes [0.0, 1.0] relative to page width and height. At most 50 bounding boxes are returned per anchored span.
{ # Bounding box in normalized [0.0, 1.0] page coordinates (origin top-left).
"bottom": 3.14, # Output only. Bottom coordinate in [0.0, 1.0].
"left": 3.14, # Output only. Left coordinate in [0.0, 1.0].
"right": 3.14, # Output only. Right coordinate in [0.0, 1.0].
"top": 3.14, # Output only. Top coordinate in [0.0, 1.0].
},
],
"pageNumber": 42, # Output only. 1-indexed page number within the PDF document.
"quoteSelector": { # W3C Web Annotation TextQuoteSelector for resilient text anchoring (see https://www.w3.org/TR/annotation-model/#text-quote-selector for details). # Output only. W3C Web Annotation TextQuoteSelector (https://www.w3.org/TR/annotation-model/#text-quote-selector) for exact text span highlighting.
"exact": "A String", # Output only. Verbatim substring extracted from the document character stream.
"prefix": "A String", # Output only. Characters immediately preceding `exact` for disambiguation.
"suffix": "A String", # Output only. Characters immediately following `exact` for disambiguation.
},
},
"text": { # Location anchor within a plain-text, Markdown, or LaTeX source document. # Output only. Location within a plain-text, Markdown, or LaTeX source document.
"firstColumn": 42, # Output only. Optional 1-indexed inclusive first column offset within `first_line`.
"firstLine": 42, # Output only. 1-indexed inclusive first line number.
"lastColumn": 42, # Output only. Optional 1-indexed inclusive last column offset within `last_line`.
"lastLine": 42, # Output only. 1-indexed inclusive last line number.
"quotedLinePreview": "A String", # Output only. Verbatim snippet of the anchored source line(s).
},
},
"severity": "A String", # Output only. Severity classification of the comment.
"suggestedEdit": "A String", # Output only. Optional suggested replacement text or edit for the anchored span.
"summary": "A String", # Output only. Short one-line summary of the review comment.
},
],
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Output only. Failure status details if review execution failed.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"reviewMarkdown": "A String", # Output only. Synthesized review report markdown.
},
"runConfig": { # Configuration options for the multi-agent document review execution pipeline. # Optional. Run configuration parameters used for this review.
"geminiApiKey": "A String", # Optional. Input only. Developer Bring-Your-Own-Key Gemini API key. When provided, requests are billed to the caller's Gemini API project. Input only; forwarded to the asynchronous review runner in the task payload and never persisted in database records or returned in review resources (see companion field `gemini_api_key_set`, AIP-147).
"geminiApiKeySet": True or False, # Output only. Indicates whether a developer Bring-Your-Own-Key Gemini API key was provided for this review run.
"model": "A String", # Optional. The Gemini model identifier to use for the review. If omitted, the server uses its default model. Unsupported values return INVALID_ARGUMENT.
"thinkingLevel": "A String", # Optional. Reasoning effort level for model calls in the review pipeline. Defaults to `THINKING_LEVEL_MEDIUM` when omitted or `THINKING_LEVEL_UNSPECIFIED`. Non-`THINKING_LEVEL_MEDIUM` thinking levels require `gemini_api_key` when calling `CreateReview`; otherwise `CreateReview` returns `INVALID_ARGUMENT`.
"topology": "A String", # Optional. Review execution topology profile to use.
"userPrompt": "A String", # Optional. User-provided guidance, focus areas, or custom evaluation instructions passed to the review agents.
},
"startTime": "A String", # Output only. Timestamp when the worker started evaluation.
"state": "A String", # Output only. Current review lifecycle state.
}
list(parent, filter=None, orderBy=None, pageSize=None, pageToken=None, x__xgafv=None)
Lists all review execution runs for a document.
Args:
parent: string, Required. The parent Document resource name. (required)
filter: string, Optional. Custom filter expressions are not currently supported; non-empty values return INVALID_ARGUMENT.
orderBy: string, Optional. Custom order_by expressions are not currently supported; non-empty values return INVALID_ARGUMENT.
pageSize: integer, Optional. The maximum number of reviews to return in a single page. The server may return fewer than this value. If unspecified, at most 50 reviews will be returned. The maximum value is 100; values above 100 will be coerced to 100.
pageToken: string, Optional. A page token received from a previous `ListReviews` call.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response message for listing Review resources.
"nextPageToken": "A String", # A token to retrieve the next page of results, or empty if no further pages exist.
"reviews": [ # The list of Review resources.
{ # An evaluation run of a document.
"createTime": "A String", # Output only. Timestamp when this review attempt was initiated.
"endTime": "A String", # Output only. Timestamp when the review reached a terminal state.
"name": "A String", # Identifier. Resource name in format `documents/{document}/reviews/{review}`.
"progressPercent": 42, # Output only. Estimated completion progress percentage of the review in [0, 100].
"result": { # Encapsulates the synthesized output or failure details of a single review execution. # Output only. Review output (markdown, errors, and future modalities).
"anchoredComments": [ # Output only. Structured review comments anchored to specific locations in the document. At most 300 anchored comments are returned per review.
{ # A structured review comment anchored to a specific location in the document.
"bodyMarkdown": "A String", # Output only. Detailed markdown explanation of the review comment.
"citationReport": { # Structured citation verification report for a single bibliography reference. # Output only. Optional structured citation verification report when this comment corresponds to a bibliography reference.
"citationKey": "A String", # Output only. Generated BibTeX citation key (e.g., "smith2023deep").
"entryType": "A String", # Output only. BibTeX entry type (e.g., "article", "inproceedings", "misc").
"extractedMetadata": { # Structured bibliographic metadata for an extracted or retrieved work. # Output only. Metadata parsed from the paper's bibliography entry.
"authors": [ # Output only. Ordered list of authors.
{ # Author name components.
"familyName": "A String", # Output only. Author family name / surname (or organization name).
"givenName": "A String", # Output only. Author given name / initials.
},
],
"doi": "A String", # Output only. Digital Object Identifier (DOI).
"journal": "A String", # Output only. Journal, conference, or venue name.
"pages": "A String", # Output only. Page range or article number.
"publicationDate": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # Output only. Publication date (month and day left as 0 if just year).
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"source": "A String", # Output only. Source database for retrieved metadata (e.g., "openalex", "crossref"). Empty on `extracted_metadata`.
"title": "A String", # Output only. Work title.
"urls": [ # Output only. URLs associated with the reference.
"A String",
],
"volume": "A String", # Output only. Volume identifier.
},
"fieldComparisons": [ # Output only. Per-field comparisons (populated only when `retrieved_metadata` is present).
{ # Per-field comparison result between extracted and retrieved metadata.
"detail": "A String", # Output only. Human-readable comparison detail (e.g., "extracted=2023, found=2024 (diff=1)").
"fieldKey": "A String", # Output only. Field key ("title", "authors", "year", "journal", "volume", "pages", "doi").
"match": True or False, # Output only. Whether the extracted and retrieved values matched.
},
],
"finalVerdict": "A String", # Output only. Final combined verdict after database lookup and search grounding.
"firstAuthorFamilyNameMatch": True or False, # Output only. Whether the first author's family name matched between extracted and retrieved metadata.
"groundingUrls": [ # Output only. Web sources surfaced during Google Search grounding.
{ # Web source URL surfaced during Google Search grounding verification.
"title": "A String", # Output only. Source page title or domain.
"url": "A String", # Output only. Source URL.
},
],
"lookupVerdict": "A String", # Output only. Verdict from scholarly database lookup (OpenAlex / Crossref) before search grounding.
"rawReference": "A String", # Output only. Verbatim reference string extracted from the paper's bibliography.
"refNum": 42, # Output only. 1-indexed bibliography reference number in the paper.
"retrievedBibtex": "A String", # Output only. Formatted BibTeX entry for the verified `retrieved_metadata` when present. Empty when `retrieved_metadata` is absent.
"retrievedMetadata": { # Structured bibliographic metadata for an extracted or retrieved work. # Output only. Metadata retrieved from OpenAlex / Crossref. Populated only when the retrieved work's title matches the extracted title. Omitted when no candidate matches the title so unrelated papers are never displayed as candidates.
"authors": [ # Output only. Ordered list of authors.
{ # Author name components.
"familyName": "A String", # Output only. Author family name / surname (or organization name).
"givenName": "A String", # Output only. Author given name / initials.
},
],
"doi": "A String", # Output only. Digital Object Identifier (DOI).
"journal": "A String", # Output only. Journal, conference, or venue name.
"pages": "A String", # Output only. Page range or article number.
"publicationDate": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # Output only. Publication date (month and day left as 0 if just year).
"day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
"month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
"year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
},
"source": "A String", # Output only. Source database for retrieved metadata (e.g., "openalex", "crossref"). Empty on `extracted_metadata`.
"title": "A String", # Output only. Work title.
"urls": [ # Output only. URLs associated with the reference.
"A String",
],
"volume": "A String", # Output only. Volume identifier.
},
"searchMethod": "A String", # Output only. Strategy that produced the scholarly database match (e.g., "doi", "title", "title_author", "autocomplete"). Empty when no title-matching candidate was found.
"searchRationale": "A String", # Output only. Explanation from the Google Search grounding verification step (when run).
"searchVerdict": "A String", # Output only. Verdict from Google Search grounding verification (when run).
},
"commentId": "A String", # Output only. Unique identifier for the comment within the review.
"location": { # A location targeting either a PDF page region/quote or text lines in the document. # Output only. Polymorphic location in the document where this comment is anchored.
"pdf": { # Location anchor within a PDF document. # Output only. Location within a rendered PDF document.
"boundingBoxes": [ # Output only. Normalized bounding boxes [0.0, 1.0] relative to page width and height. At most 50 bounding boxes are returned per anchored span.
{ # Bounding box in normalized [0.0, 1.0] page coordinates (origin top-left).
"bottom": 3.14, # Output only. Bottom coordinate in [0.0, 1.0].
"left": 3.14, # Output only. Left coordinate in [0.0, 1.0].
"right": 3.14, # Output only. Right coordinate in [0.0, 1.0].
"top": 3.14, # Output only. Top coordinate in [0.0, 1.0].
},
],
"pageNumber": 42, # Output only. 1-indexed page number within the PDF document.
"quoteSelector": { # W3C Web Annotation TextQuoteSelector for resilient text anchoring (see https://www.w3.org/TR/annotation-model/#text-quote-selector for details). # Output only. W3C Web Annotation TextQuoteSelector (https://www.w3.org/TR/annotation-model/#text-quote-selector) for exact text span highlighting.
"exact": "A String", # Output only. Verbatim substring extracted from the document character stream.
"prefix": "A String", # Output only. Characters immediately preceding `exact` for disambiguation.
"suffix": "A String", # Output only. Characters immediately following `exact` for disambiguation.
},
},
"text": { # Location anchor within a plain-text, Markdown, or LaTeX source document. # Output only. Location within a plain-text, Markdown, or LaTeX source document.
"firstColumn": 42, # Output only. Optional 1-indexed inclusive first column offset within `first_line`.
"firstLine": 42, # Output only. 1-indexed inclusive first line number.
"lastColumn": 42, # Output only. Optional 1-indexed inclusive last column offset within `last_line`.
"lastLine": 42, # Output only. 1-indexed inclusive last line number.
"quotedLinePreview": "A String", # Output only. Verbatim snippet of the anchored source line(s).
},
},
"severity": "A String", # Output only. Severity classification of the comment.
"suggestedEdit": "A String", # Output only. Optional suggested replacement text or edit for the anchored span.
"summary": "A String", # Output only. Short one-line summary of the review comment.
},
],
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # Output only. Failure status details if review execution failed.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"reviewMarkdown": "A String", # Output only. Synthesized review report markdown.
},
"runConfig": { # Configuration options for the multi-agent document review execution pipeline. # Optional. Run configuration parameters used for this review.
"geminiApiKey": "A String", # Optional. Input only. Developer Bring-Your-Own-Key Gemini API key. When provided, requests are billed to the caller's Gemini API project. Input only; forwarded to the asynchronous review runner in the task payload and never persisted in database records or returned in review resources (see companion field `gemini_api_key_set`, AIP-147).
"geminiApiKeySet": True or False, # Output only. Indicates whether a developer Bring-Your-Own-Key Gemini API key was provided for this review run.
"model": "A String", # Optional. The Gemini model identifier to use for the review. If omitted, the server uses its default model. Unsupported values return INVALID_ARGUMENT.
"thinkingLevel": "A String", # Optional. Reasoning effort level for model calls in the review pipeline. Defaults to `THINKING_LEVEL_MEDIUM` when omitted or `THINKING_LEVEL_UNSPECIFIED`. Non-`THINKING_LEVEL_MEDIUM` thinking levels require `gemini_api_key` when calling `CreateReview`; otherwise `CreateReview` returns `INVALID_ARGUMENT`.
"topology": "A String", # Optional. Review execution topology profile to use.
"userPrompt": "A String", # Optional. User-provided guidance, focus areas, or custom evaluation instructions passed to the review agents.
},
"startTime": "A String", # Output only. Timestamp when the worker started evaluation.
"state": "A String", # Output only. Current review lifecycle state.
},
],
}
list_next(previous_request, previous_response)
Retrieves the next page of results. Args: previous_request: The request for the previous page. (required) previous_response: The response from the request for the previous page. (required) Returns: A request object that you can call 'execute()' on to request the next page. Returns None if there are no more items in the collection.