Previous value: -"Results per page. Default 25; positive integers above 100 clamp to 100 with a notice unless OPENALEX_CLAMP_PER_PAGE=false restores rejection. A budget-cut page returns fewer (`omitted`)."New value: +"Results per page. Default 25; a larger value returns at most 100 and says so (rejected instead on a server set to OPENALEX_CLAMP_PER_PAGE=false)."

Removed value: -9007199254740991

Previous value: -"OpenAlex work field names to return. Always returned: id, display_name. Defaults to the curated works select if omitted. `author_list` returns each author in authorship order as `{id, display_name, orcid}` (`orcid` null when absent), a compact alternative to `authorships`, which also carries institutions and affiliations; neither the default nor `[\"*\"]` includes it. Large projections may be cut to fit the response budget (`omitted`, `windows`)."New value: +"OpenAlex work field names to return. Always returned: id, display_name. Defaults to the curated works select if omitted. `author_list` returns each author in authorship order as `{id, display_name, orcid}` (`orcid` null when absent), a compact alternative to `authorships`, which also carries institutions and affiliations; neither the default nor `[\"*\"]` includes it. A wide projection on a large page makes a large response, so name the fields you need."

Previous value: -"Machine-readable failure mode. Declared by this tool: `unmatched_quote_in_filter_value`: A filter value sent unquoted has an unmatched double quote. `rate_limited`: OpenAlex throttled the request for exceeding its per-second ceiling (HTTP 429). `upstream_budget_exhausted`: The OpenAlex daily usage budget is spent (HTTP 429). `upstream_plan_required`: A filter is one OpenAlex serves only on a paid plan — created_date, updated_date, or a from_/to_ form of either (HTTP 429 \"Plan upgrade required\"). `upstream_timeout`: OpenAlex did not respond within the request deadline. `upstream_unavailable`: OpenAlex was unreachable or unusable — HTTP 503, a connection failure, or a body that was empty, HTML, or unparseable JSON. `upstream_unauthorized`: OpenAlex rejected the API key (HTTP 401). `upstream_forbidden`: OpenAlex denied access to the requested resource (HTTP 403). `comma_in_filter_value`: A filter value contains a comma, which collides with the OpenAlex filter separator, on a field that takes no phrase. Free-text search filters (any `.search` key, such as title.search or abstract.search.exact) and fields matched as whole text (display_name, awards.funder_display_name, awards.funder_award_id, authorships.institutions.geo.city, authorships.institutions.geo.region, raw_affiliation_strings, biblio fields) are exempt: a comma there is sent quoted, as part of the phrase. `invalid_country_code`: A country filter (a key ending in country_code, country_codes, or countries) holds a segment that cannot be a country code, such as a misspelled name, an unassigned number, \"unknown\", or two codes joined by a space (\"DE US\"). `mixed_and_or_in_filter_value`: A filter value puts \"|\" (OR) beside an AND operator — a \"+\", or a space on a field where words mean AND (on a country field a space is always part of a country name, and inside a language name it is part of the name). OpenAlex splits the value on \"|\" first and drops every alternative that ANDs more than one value, so no single value can carry both. `quote_in_filter_value`: A filter value sent to OpenAlex double-quoted holds a double quote inside its outer pair — a value the server quotes (a multi-word value on a field matched as whole text, or a value holding a comma on such a field or on a free-text search filter), or one the caller wrapped in double quotes on any filter but a free-text search. `upstream_invalid_params`: OpenAlex rejected an invalid filter, select, or sort field name (HTTP 400). `upstream_invalid_id_value`: An entity-ID filter received a value that is not an OpenAlex ID — usually a name (HTTP 400). `upstream_sort_requires_search`: sort=-relevance_score was used but the citation-graph query has no active search (HTTP 400). `upstream_invalid_params_other`: OpenAlex rejected the request (HTTP 400) for a reason other than an invalid field name. `reserved_filter_key`: filters contains cites/cited_by/related_to, or an alias of one such as cited_works — the direction parameter reserves those keys. `id_type_mismatch`: seed_id is a native OpenAlex ID of another entity type — an author, source, institution, topic, publisher, funder, or concept ID rather than a work ID. `id_dot_segment`: seed_id holds a `.` or `..` path segment, written plainly or percent-encoded. `entity_not_found`: OpenAlex has no work matching the seed_id. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `unmatched_quote_in_filter_value`: A filter value sent unquoted has an unmatched double quote. `rate_limited`: OpenAlex throttled the request for exceeding its per-second ceiling (HTTP 429). `upstream_budget_exhausted`: The OpenAlex daily usage budget is spent (HTTP 429). `upstream_plan_required`: A filter is one OpenAlex serves only on a paid plan — created_date, updated_date, or a from_/to_ form of either (HTTP 429 \"Plan upgrade required\"). `upstream_timeout`: OpenAlex did not respond within the request deadline. `upstream_unavailable`: OpenAlex was unreachable or unusable — HTTP 503, a connection failure, or a body that was empty, HTML, or unparseable JSON. `upstream_unauthorized`: OpenAlex rejected the API key (HTTP 401). `upstream_forbidden`: OpenAlex denied access to the requested resource (HTTP 403). `comma_in_filter_value`: A filter value contains a comma, which collides with the OpenAlex filter separator, on a field that takes no phrase. Free-text search filters (any `.search` key, such as title.search or abstract.search.exact) and fields matched as whole text (display_name, awards.funder_display_name, awards.funder_award_id, authorships.institutions.geo.city, authorships.institutions.geo.region, raw_affiliation_strings, biblio fields) are exempt: a comma there is sent quoted, as part of the phrase. `invalid_country_code`: A country filter (a key ending in country_code, country_codes, or countries) holds a segment that cannot be a country code, such as a misspelled name, an unassigned number, \"unknown\", or two codes joined by a space (\"DE US\"). `mixed_and_or_in_filter_value`: A filter value puts \"|\" (OR) beside an AND operator — a \"+\", or a space on a field where words mean AND (on a country field a space is always part of a country name, and inside a language name it is part of the name). OpenAlex splits the value on \"|\" first and drops every alternative that ANDs more than one value, so no single value can carry both. `quote_in_filter_value`: A filter value sent to OpenAlex double-quoted holds a double quote inside its outer pair — a value the server quotes (a multi-word value on a field matched as whole text, or a value holding a comma on such a field or on a free-text search filter), or one the caller wrapped in double quotes on any filter but a free-text search. `upstream_invalid_params`: OpenAlex rejected an invalid filter, select, or sort field name (HTTP 400). `upstream_invalid_id_value`: An entity-ID filter received a value that is not an OpenAlex ID — usually a name (HTTP 400). `upstream_sort_requires_search`: sort=-relevance_score was used but the citation-graph query has no active search (HTTP 400). `upstream_invalid_params_other`: OpenAlex rejected the request (HTTP 400) for a reason other than an invalid field name. `reserved_filter_key`: filters contains cites/cited_by/related_to, or an alias of one such as cited_works — the direction parameter reserves those keys. `id_type_mismatch`: seed_id is a native OpenAlex ID of another entity type — an author, source, institution, topic, publisher, funder, award, or concept ID rather than a work ID. `id_dot_segment`: seed_id holds a `.` or `..` path segment, written plainly or percent-encoded. `entity_not_found`: OpenAlex has no work matching the seed_id. `response_too_large`: The response's structuredContent or content[] text would exceed 8,000,000 bytes — a wide `select` on a large page. A page is never shortened to fit. Other values are possible when a failure originates below the handler."

Previous value: -[
-  "unmatched_quote_in_filter_value",
-  "rate_limited",
-  "upstream_budget_exhausted",
-  "upstream_plan_required",
-  "upstream_timeout",
-  "upstream_unavailable",
-  "upstream_unauthorized",
-  "upstream_forbidden",
-  "comma_in_filter_value",
-  "invalid_country_code",
-  "mixed_and_or_in_filter_value",
-  "quote_in_filter_value",
-  "upstream_invalid_params",
-  "upstream_invalid_id_value",
-  "upstream_sort_requires_search",
-  "upstream_invalid_params_other",
-  "reserved_filter_key",
-  "id_type_mismatch",
-  "id_dot_segment",
-  "entity_not_found"
-]New value: +[
+  "unmatched_quote_in_filter_value",
+  "rate_limited",
+  "upstream_budget_exhausted",
+  "upstream_plan_required",
+  "upstream_timeout",
+  "upstream_unavailable",
+  "upstream_unauthorized",
+  "upstream_forbidden",
+  "comma_in_filter_value",
+  "invalid_country_code",
+  "mixed_and_or_in_filter_value",
+  "quote_in_filter_value",
+  "upstream_invalid_params",
+  "upstream_invalid_id_value",
+  "upstream_sort_requires_search",
+  "upstream_invalid_params_other",
+  "reserved_filter_key",
+  "id_type_mismatch",
+  "id_dot_segment",
+  "entity_not_found",
+  "response_too_large"
+]

Previous value: -"Cursor for next page. null if no more results. Continues after the full upstream page, `omitted` works included."New value: +"Cursor for the next page; pass it back unchanged as `cursor`. null when no further page exists, except on a final page that exactly fills `per_page`: OpenAlex still returns a cursor there, and it leads to an empty page."

Previous value: -"Page size OpenAlex echoed for this request — the applied per_page after clamping, not the number of records returned. A short or exhausted page carries fewer records than this, as does a page the response budget cut (`omitted`)."New value: +"Page size OpenAlex echoed for this request — the applied per_page after clamping, not the number of records returned. A short or exhausted page carries fewer records than this."

Previous value: -"Guidance notice. Set when per_page was clamped (requested and applied sizes), when no edges are returned — a first call suggests verifying the seed_id, broadening filters, or trying a different direction; a cursor continuation says the walk is already past its last edge — when the response budget cut works, windowed an array, or ran over, and when a work carries exactly 100 authorships or author_list entries (possibly capped). Absent otherwise."New value: +"Guidance notice. Set when per_page was clamped (requested and applied sizes), when no edges are returned — a first call suggests verifying the seed_id, broadening filters, or trying a different direction; a cursor continuation says the walk is already past its last edge — and when a work carries exactly 100 authorships or author_list entries (possibly capped). Absent otherwise."

Removed value: -{
-  "additionalProperties": false,
-  "description": "Present when the response budget cut whole records from the page end; pagination continues after the full upstream page.",
-  "properties": {
-    "ids": {
-      "description": "Bare IDs of the records left out, in page order (a keyword keeps its URL).",
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    "next": {
-      "additionalProperties": false,
-      "description": "One call returning those records as a set, in OpenAlex's order, not page order. Budgeted too, so it may carry its own `omitted`.",
-      "properties": {
-        "arguments": {
-          "additionalProperties": {},
-          "description": "Arguments to pass as-is.",
-          "properties": {},
-          "type": "object"
-        },
-        "tool": {
-          "const": "openalex_search_entities",
-          "description": "Tool to call.",
-          "type": "string"
-        }
-      },
-      "required": [
-        "tool",
-        "arguments"
-      ],
-      "type": "object"
-    }
-  },
-  "required": [
-    "ids",
-    "next"
-  ],
-  "type": "object"
-}

Removed value: -{
-  "description": "True when even the least this call can return — the first record's non-array fields (its arrays windowed to empty), or one `slice` element — exceeds the budget.",
-  "type": "boolean"
-}

Previous value: -"Works on the citation graph in this direction. Text values are plain text — HTML entities decoded, HTML/JATS/MathML markup removed — except identifier and URL fields such as `id`, `doi`, `ids`, and `*_url`, returned exactly as OpenAlex stores them; an abstract arrives reconstructed as `abstract`, and a selected `author_list` as one `{id, display_name, orcid}` entry per author. Works cut by the response budget are in `omitted`; partial or possibly capped arrays are in `windows`."New value: +"Works on the citation graph in this direction. Text values are plain text — HTML entities decoded, HTML/JATS/MathML markup removed — except identifier and URL fields such as `id`, `doi`, `ids`, and `*_url`, returned exactly as OpenAlex stores them; an abstract arrives reconstructed as `abstract`, and a selected `author_list` as one `{id, display_name, orcid}` entry per author. Possibly capped author arrays are in `windows`."

Previous value: -"Arrays windowed to fit the budget, paged by `slice`, or possibly capped at 100 list authors or 5,000 stored singleton authors. A `slice` call always carries its window, even for a whole array. `next` is null at the stored-array end, including a possibly capped singleton."New value: +"Author arrays possibly capped at 100 on a list record or 5,000 stored on a singleton, and the window of every `slice` call — present even when the slice holds the whole array. A slice window's `next` repeats its `slice.limit` from the following offset; `next` is null at the stored-array end, including a possibly capped singleton."

Previous value: -"An array returned in part."New value: +"An array returned in part, or possibly in part."

Previous value: -"Additional filters to narrow the graph, same syntax as openalex_search_entities. Example: publication_year=\">2020\", is_oa=\"true\". Country fields take ISO 3166-1 alpha-2 codes (\"DE\") and `language` takes ISO 639-1 codes (\"en\"); alpha-3, numeric, ISO 639-2, and English-name forms are converted — a multi-word name is one value, so \"South Korea|Japan\" ORs two countries — and a value that cannot be a country code is rejected. A multi-word value on a field matched as whole text (display_name, awards.funder_display_name, authorships.institutions.geo.city, raw_affiliation_strings) matches as one phrase (\"National Science Foundation\"; a comma, as in \"University of California, Berkeley\", is part of it, and it cannot contain a double quote of its own), \"!\" and \"|\" included, but cannot be ANDed with \"+\" in the same field. A value mixing \"|\" with an AND operator — a \"+\", or a space on a field where words mean AND — is rejected, since OpenAlex drops every \"|\" alternative that ANDs more than one value; put the AND in a second key instead. Do not include cites/cited_by/related_to, nor an alias of one such as cited_works — those keys are set by the `direction` parameter."New value: +"Additional filter record object to narrow the graph, using the same value syntax as openalex_search_entities; native string input is unavailable here. Example: publication_year=\">2020\", is_oa=\"true\". Country fields take ISO 3166-1 alpha-2 codes (\"DE\") and `language` takes ISO 639-1 codes (\"en\"); alpha-3, numeric, ISO 639-2, and English-name forms are converted — a multi-word name is one value, so \"South Korea|Japan\" ORs two countries — and a value that cannot be a country code is rejected. A multi-word value on a field matched as whole text (display_name, awards.funder_display_name, authorships.institutions.geo.city, raw_affiliation_strings) matches as one phrase (\"National Science Foundation\"; a comma, as in \"University of California, Berkeley\", is part of it, and it cannot contain a double quote of its own), \"!\" and \"|\" included, but cannot be ANDed with \"+\" in the same field. A value sent unquoted must have paired double quotes; balanced search phrases remain valid. Filters are checked before the seed lookup. A value mixing \"|\" with an AND operator — a \"+\", or a space on a field where words mean AND — is rejected, since OpenAlex drops every \"|\" alternative that ANDs more than one value; put the AND in a second key instead. Do not include cites/cited_by/related_to, nor an alias of one such as cited_works — those keys are set by the `direction` parameter."

Previous value: -"Results per page (1-100). Default 25. A budget-cut page returns fewer (`omitted`)."New value: +"Results per page. Default 25; positive integers above 100 clamp to 100 with a notice unless OPENALEX_CLAMP_PER_PAGE=false restores rejection. A budget-cut page returns fewer (`omitted`)."

Previous value: -100New value: +9007199254740991

Previous value: -"Machine-readable failure mode. Declared by this tool: `rate_limited`: OpenAlex throttled the request for exceeding its per-second ceiling (HTTP 429). `upstream_budget_exhausted`: The OpenAlex daily usage budget is spent (HTTP 429). `upstream_plan_required`: A filter is one OpenAlex serves only on a paid plan — created_date, updated_date, or a from_/to_ form of either (HTTP 429 \"Plan upgrade required\"). `upstream_timeout`: OpenAlex did not respond within the request deadline. `upstream_unavailable`: OpenAlex was unreachable or unusable — HTTP 503, a connection failure, or a body that was empty, HTML, or unparseable JSON. `upstream_unauthorized`: OpenAlex rejected the API key (HTTP 401). `upstream_forbidden`: OpenAlex denied access to the requested resource (HTTP 403). `comma_in_filter_value`: A filter value contains a comma, which collides with the OpenAlex filter separator, on a field that takes no phrase. Free-text search filters (any `.search` key, such as title.search or abstract.search.exact) and fields matched as whole text (display_name, awards.funder_display_name, awards.funder_award_id, authorships.institutions.geo.city, authorships.institutions.geo.region, raw_affiliation_strings, biblio fields) are exempt: a comma there is sent quoted, as part of the phrase. `invalid_country_code`: A country filter (a key ending in country_code, country_codes, or countries) holds a segment that cannot be a country code, such as a misspelled name, an unassigned number, \"unknown\", or two codes joined by a space (\"DE US\"). `mixed_and_or_in_filter_value`: A filter value puts \"|\" (OR) beside an AND operator — a \"+\", or a space on a field where words mean AND (on a country field a space is always part of a country name, and inside a language name it is part of the name). OpenAlex splits the value on \"|\" first and drops every alternative that ANDs more than one value, so no single value can carry both. `quote_in_filter_value`: A filter value sent to OpenAlex double-quoted holds a double quote inside its outer pair — a value the server quotes (a multi-word value on a field matched as whole text, or a value holding a comma on such a field or on a free-text search filter), or one the caller wrapped in double quotes on any filter but a free-text search. `upstream_invalid_params`: OpenAlex rejected an invalid filter, select, or sort field name (HTTP 400). `upstream_invalid_id_value`: An entity-ID filter received a value that is not an OpenAlex ID — usually a name (HTTP 400). `upstream_sort_requires_search`: sort=-relevance_score was used but the citation-graph query has no active search (HTTP 400). `upstream_invalid_params_other`: OpenAlex rejected the request (HTTP 400) for a reason other than an invalid field name. `reserved_filter_key`: filters contains cites/cited_by/related_to, or an alias of one such as cited_works — the direction parameter reserves those keys. `id_type_mismatch`: seed_id is a native OpenAlex ID of another entity type — an author, source, institution, topic, publisher, funder, or concept ID rather than a work ID. `id_dot_segment`: seed_id holds a `.` or `..` path segment, written plainly or percent-encoded. `entity_not_found`: OpenAlex has no work matching the seed_id. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `unmatched_quote_in_filter_value`: A filter value sent unquoted has an unmatched double quote. `rate_limited`: OpenAlex throttled the request for exceeding its per-second ceiling (HTTP 429). `upstream_budget_exhausted`: The OpenAlex daily usage budget is spent (HTTP 429). `upstream_plan_required`: A filter is one OpenAlex serves only on a paid plan — created_date, updated_date, or a from_/to_ form of either (HTTP 429 \"Plan upgrade required\"). `upstream_timeout`: OpenAlex did not respond within the request deadline. `upstream_unavailable`: OpenAlex was unreachable or unusable — HTTP 503, a connection failure, or a body that was empty, HTML, or unparseable JSON. `upstream_unauthorized`: OpenAlex rejected the API key (HTTP 401). `upstream_forbidden`: OpenAlex denied access to the requested resource (HTTP 403). `comma_in_filter_value`: A filter value contains a comma, which collides with the OpenAlex filter separator, on a field that takes no phrase. Free-text search filters (any `.search` key, such as title.search or abstract.search.exact) and fields matched as whole text (display_name, awards.funder_display_name, awards.funder_award_id, authorships.institutions.geo.city, authorships.institutions.geo.region, raw_affiliation_strings, biblio fields) are exempt: a comma there is sent quoted, as part of the phrase. `invalid_country_code`: A country filter (a key ending in country_code, country_codes, or countries) holds a segment that cannot be a country code, such as a misspelled name, an unassigned number, \"unknown\", or two codes joined by a space (\"DE US\"). `mixed_and_or_in_filter_value`: A filter value puts \"|\" (OR) beside an AND operator — a \"+\", or a space on a field where words mean AND (on a country field a space is always part of a country name, and inside a language name it is part of the name). OpenAlex splits the value on \"|\" first and drops every alternative that ANDs more than one value, so no single value can carry both. `quote_in_filter_value`: A filter value sent to OpenAlex double-quoted holds a double quote inside its outer pair — a value the server quotes (a multi-word value on a field matched as whole text, or a value holding a comma on such a field or on a free-text search filter), or one the caller wrapped in double quotes on any filter but a free-text search. `upstream_invalid_params`: OpenAlex rejected an invalid filter, select, or sort field name (HTTP 400). `upstream_invalid_id_value`: An entity-ID filter received a value that is not an OpenAlex ID — usually a name (HTTP 400). `upstream_sort_requires_search`: sort=-relevance_score was used but the citation-graph query has no active search (HTTP 400). `upstream_invalid_params_other`: OpenAlex rejected the request (HTTP 400) for a reason other than an invalid field name. `reserved_filter_key`: filters contains cites/cited_by/related_to, or an alias of one such as cited_works — the direction parameter reserves those keys. `id_type_mismatch`: seed_id is a native OpenAlex ID of another entity type — an author, source, institution, topic, publisher, funder, or concept ID rather than a work ID. `id_dot_segment`: seed_id holds a `.` or `..` path segment, written plainly or percent-encoded. `entity_not_found`: OpenAlex has no work matching the seed_id. Other values are possible when a failure originates below the handler."

Previous value: -[
-  "rate_limited",
-  "upstream_budget_exhausted",
-  "upstream_plan_required",
-  "upstream_timeout",
-  "upstream_unavailable",
-  "upstream_unauthorized",
-  "upstream_forbidden",
-  "comma_in_filter_value",
-  "invalid_country_code",
-  "mixed_and_or_in_filter_value",
-  "quote_in_filter_value",
-  "upstream_invalid_params",
-  "upstream_invalid_id_value",
-  "upstream_sort_requires_search",
-  "upstream_invalid_params_other",
-  "reserved_filter_key",
-  "id_type_mismatch",
-  "id_dot_segment",
-  "entity_not_found"
-]New value: +[
+  "unmatched_quote_in_filter_value",
+  "rate_limited",
+  "upstream_budget_exhausted",
+  "upstream_plan_required",
+  "upstream_timeout",
+  "upstream_unavailable",
+  "upstream_unauthorized",
+  "upstream_forbidden",
+  "comma_in_filter_value",
+  "invalid_country_code",
+  "mixed_and_or_in_filter_value",
+  "quote_in_filter_value",
+  "upstream_invalid_params",
+  "upstream_invalid_id_value",
+  "upstream_sort_requires_search",
+  "upstream_invalid_params_other",
+  "reserved_filter_key",
+  "id_type_mismatch",
+  "id_dot_segment",
+  "entity_not_found"
+]

Previous value: -"Page size OpenAlex echoed for this request — the requested per_page, not the number of records returned. A short or exhausted page carries fewer records than this, as does a page the response budget cut (`omitted`)."New value: +"Page size OpenAlex echoed for this request — the applied per_page after clamping, not the number of records returned. A short or exhausted page carries fewer records than this, as does a page the response budget cut (`omitted`)."

Previous value: -"Guidance notice. Set when no edges are returned — a first call suggests verifying the seed_id, broadening filters, or trying a different direction; a `cursor` continuation says the walk is already past its last edge instead — when the response budget cut works, windowed an array, or ran over, and when a work carries exactly 100 authorships or author_list entries (possibly capped). Absent otherwise."New value: +"Guidance notice. Set when per_page was clamped (requested and applied sizes), when no edges are returned — a first call suggests verifying the seed_id, broadening filters, or trying a different direction; a cursor continuation says the walk is already past its last edge — when the response budget cut works, windowed an array, or ran over, and when a work carries exactly 100 authorships or author_list entries (possibly capped). Absent otherwise."

Previous value: -"Arrays returned in part — windowed to fit the budget, paged by `slice`, or a possibly capped 100-entry `authorships` or `author_list` — each with its continuation. A `slice` call always carries its window, even for a whole array; otherwise absent when every array is whole."New value: +"Arrays windowed to fit the budget, paged by `slice`, or possibly capped at 100 list authors or 5,000 stored singleton authors. A `slice` call always carries its window, even for a whole array. `next` is null at the stored-array end, including a possibly capped singleton."

Previous value: -"True for exactly 100 `authorships` or `author_list` entries on a list record (OpenAlex's cap): the list may be longer."New value: +"True for exactly 100 authorships or author_list entries on a list record, or 5,000 on a singleton lookup: the byline may be longer than the returned array."

Previous value: -"Array length as returned to this call."New value: +"Stored array length returned to this call, not a complete byline total."

Previous value: -"Additional filters to narrow the graph, same syntax as openalex_search_entities. Example: publication_year=\">2020\", is_oa=\"true\". Do not include cites/cited_by/related_to, nor an alias of one such as cited_works — those keys are set by the `direction` parameter."New value: +"Additional filters to narrow the graph, same syntax as openalex_search_entities. Example: publication_year=\">2020\", is_oa=\"true\". Country fields take ISO 3166-1 alpha-2 codes (\"DE\") and `language` takes ISO 639-1 codes (\"en\"); alpha-3, numeric, ISO 639-2, and English-name forms are converted — a multi-word name is one value, so \"South Korea|Japan\" ORs two countries — and a value that cannot be a country code is rejected. A multi-word value on a field matched as whole text (display_name, awards.funder_display_name, authorships.institutions.geo.city, raw_affiliation_strings) matches as one phrase (\"National Science Foundation\"; a comma, as in \"University of California, Berkeley\", is part of it, and it cannot contain a double quote of its own), \"!\" and \"|\" included, but cannot be ANDed with \"+\" in the same field. A value mixing \"|\" with an AND operator — a \"+\", or a space on a field where words mean AND — is rejected, since OpenAlex drops every \"|\" alternative that ANDs more than one value; put the AND in a second key instead. Do not include cites/cited_by/related_to, nor an alias of one such as cited_works — those keys are set by the `direction` parameter."

Previous value: -"Seed work identifier. Accepts OpenAlex ID (\"W2741809807\"), DOI (\"10.1038/nature12373\" or full URL), or PMID (\"12345678\" or \"https://pubmed.ncbi.nlm.nih.gov/12345678\"). A PMCID is recognized too, bare or as a PubMed Central URL, but OpenAlex indexes no PMCIDs, so it resolves nothing — pass the work's PMID or DOI instead. Use openalex_resolve_name first if you only have a title."New value: +"Seed work identifier. Accepts OpenAlex work ID (\"W2741809807\", or its OpenAlex record-page or API URL such as \"https://openalex.org/works/W2741809807\"), DOI (\"10.1038/nature12373\" or full URL), or PMID (\"12345678\" or \"https://pubmed.ncbi.nlm.nih.gov/12345678\"). A PMCID is recognized too, bare or as a PubMed Central URL, but OpenAlex indexes no PMCIDs, so it resolves nothing — pass the work's PMID or DOI instead. Use openalex_resolve_name first if you only have a title."

Previous value: -"OpenAlex work field names to return. Always returned: id, display_name. Defaults to the curated works select if omitted. Large projections may be cut to fit the response budget (`omitted`, `windows`)."New value: +"OpenAlex work field names to return. Always returned: id, display_name. Defaults to the curated works select if omitted. `author_list` returns each author in authorship order as `{id, display_name, orcid}` (`orcid` null when absent), a compact alternative to `authorships`, which also carries institutions and affiliations; neither the default nor `[\"*\"]` includes it. Large projections may be cut to fit the response budget (`omitted`, `windows`)."

Previous value: -"USD this call spent, covering both upstream requests — the seed validation lookup (unbilled) and the graph page itself."New value: +"USD this call spent, covering both upstream requests — the seed validation lookup and the graph page itself. The seed lookup is unbilled unless seed_id carries characters past the identifier itself (`W2741809807#x` still resolves to W2741809807), which OpenAlex bills like one list request."

Previous value: -"Machine-readable failure mode. Declared by this tool: `rate_limited`: OpenAlex throttled the request for exceeding its per-second ceiling (HTTP 429). `upstream_budget_exhausted`: The OpenAlex daily usage budget is spent (HTTP 429). `upstream_timeout`: OpenAlex did not respond within the request deadline. `upstream_unavailable`: OpenAlex was unreachable or unusable — HTTP 503, a connection failure, or a body that was empty, HTML, or unparseable JSON. `upstream_unauthorized`: OpenAlex rejected the API key (HTTP 401). `upstream_forbidden`: OpenAlex denied access to the requested resource (HTTP 403). `comma_in_filter_value`: A filter value contains a comma, which collides with the OpenAlex filter separator. `upstream_invalid_params`: OpenAlex rejected an invalid filter or sort field name (HTTP 400). `upstream_invalid_id_value`: An entity-ID filter received a value that is not an OpenAlex ID — usually a name (HTTP 400). `upstream_sort_requires_search`: sort=-relevance_score was used but the citation-graph query has no active search (HTTP 400). `upstream_invalid_params_other`: OpenAlex rejected the request (HTTP 400) for a reason other than an invalid field name. `reserved_filter_key`: filters contains cites/cited_by/related_to, or an alias of one such as cited_works — the direction parameter reserves those keys. `entity_not_found`: OpenAlex has no work matching the seed_id. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `rate_limited`: OpenAlex throttled the request for exceeding its per-second ceiling (HTTP 429). `upstream_budget_exhausted`: The OpenAlex daily usage budget is spent (HTTP 429). `upstream_plan_required`: A filter is one OpenAlex serves only on a paid plan — created_date, updated_date, or a from_/to_ form of either (HTTP 429 \"Plan upgrade required\"). `upstream_timeout`: OpenAlex did not respond within the request deadline. `upstream_unavailable`: OpenAlex was unreachable or unusable — HTTP 503, a connection failure, or a body that was empty, HTML, or unparseable JSON. `upstream_unauthorized`: OpenAlex rejected the API key (HTTP 401). `upstream_forbidden`: OpenAlex denied access to the requested resource (HTTP 403). `comma_in_filter_value`: A filter value contains a comma, which collides with the OpenAlex filter separator, on a field that takes no phrase. Free-text search filters (any `.search` key, such as title.search or abstract.search.exact) and fields matched as whole text (display_name, awards.funder_display_name, awards.funder_award_id, authorships.institutions.geo.city, authorships.institutions.geo.region, raw_affiliation_strings, biblio fields) are exempt: a comma there is sent quoted, as part of the phrase. `invalid_country_code`: A country filter (a key ending in country_code, country_codes, or countries) holds a segment that cannot be a country code, such as a misspelled name, an unassigned number, \"unknown\", or two codes joined by a space (\"DE US\"). `mixed_and_or_in_filter_value`: A filter value puts \"|\" (OR) beside an AND operator — a \"+\", or a space on a field where words mean AND (on a country field a space is always part of a country name, and inside a language name it is part of the name). OpenAlex splits the value on \"|\" first and drops every alternative that ANDs more than one value, so no single value can carry both. `quote_in_filter_value`: A filter value sent to OpenAlex double-quoted holds a double quote inside its outer pair — a value the server quotes (a multi-word value on a field matched as whole text, or a value holding a comma on such a field or on a free-text search filter), or one the caller wrapped in double quotes on any filter but a free-text search. `upstream_invalid_params`: OpenAlex rejected an invalid filter, select, or sort field name (HTTP 400). `upstream_invalid_id_value`: An entity-ID filter received a value that is not an OpenAlex ID — usually a name (HTTP 400). `upstream_sort_requires_search`: sort=-relevance_score was used but the citation-graph query has no active search (HTTP 400). `upstream_invalid_params_other`: OpenAlex rejected the request (HTTP 400) for a reason other than an invalid field name. `reserved_filter_key`: filters contains cites/cited_by/related_to, or an alias of one such as cited_works — the direction parameter reserves those keys. `id_type_mismatch`: seed_id is a native OpenAlex ID of another entity type — an author, source, institution, topic, publisher, funder, or concept ID rather than a work ID. `id_dot_segment`: seed_id holds a `.` or `..` path segment, written plainly or percent-encoded. `entity_not_found`: OpenAlex has no work matching the seed_id. Other values are possible when a failure originates below the handler."

Previous value: -[
-  "rate_limited",
-  "upstream_budget_exhausted",
-  "upstream_timeout",
-  "upstream_unavailable",
-  "upstream_unauthorized",
-  "upstream_forbidden",
-  "comma_in_filter_value",
-  "upstream_invalid_params",
-  "upstream_invalid_id_value",
-  "upstream_sort_requires_search",
-  "upstream_invalid_params_other",
-  "reserved_filter_key",
-  "entity_not_found"
-]New value: +[
+  "rate_limited",
+  "upstream_budget_exhausted",
+  "upstream_plan_required",
+  "upstream_timeout",
+  "upstream_unavailable",
+  "upstream_unauthorized",
+  "upstream_forbidden",
+  "comma_in_filter_value",
+  "invalid_country_code",
+  "mixed_and_or_in_filter_value",
+  "quote_in_filter_value",
+  "upstream_invalid_params",
+  "upstream_invalid_id_value",
+  "upstream_sort_requires_search",
+  "upstream_invalid_params_other",
+  "reserved_filter_key",
+  "id_type_mismatch",
+  "id_dot_segment",
+  "entity_not_found"
+]

Previous value: -"Guidance notice. Set when no edges are returned — a first call suggests verifying the seed_id, broadening filters, or trying a different direction; a `cursor` continuation says the walk is already past its last edge instead — when the response budget cut works, windowed an array, or ran over, and when a work carries exactly 100 authorships (possibly capped). Absent otherwise."New value: +"Guidance notice. Set when no edges are returned — a first call suggests verifying the seed_id, broadening filters, or trying a different direction; a `cursor` continuation says the walk is already past its last edge instead — when the response budget cut works, windowed an array, or ran over, and when a work carries exactly 100 authorships or author_list entries (possibly capped). Absent otherwise."

Previous value: -"Works on the citation graph in this direction. Text values are plain text — HTML entities decoded, HTML/JATS/MathML markup removed — except identifier and URL fields such as `id`, `doi`, `ids`, and `*_url`, returned exactly as OpenAlex stores them. Works cut by the response budget are in `omitted`; partial or possibly capped arrays are in `windows`."New value: +"Works on the citation graph in this direction. Text values are plain text — HTML entities decoded, HTML/JATS/MathML markup removed — except identifier and URL fields such as `id`, `doi`, `ids`, and `*_url`, returned exactly as OpenAlex stores them; an abstract arrives reconstructed as `abstract`, and a selected `author_list` as one `{id, display_name, orcid}` entry per author. Works cut by the response budget are in `omitted`; partial or possibly capped arrays are in `windows`."

Previous value: -"Arrays returned in part — windowed to fit the budget, paged by `slice`, or 100 possibly capped authorships — each with its continuation. A `slice` call always carries its window, even for a whole array; otherwise absent when every array is whole."New value: +"Arrays returned in part — windowed to fit the budget, paged by `slice`, or a possibly capped 100-entry `authorships` or `author_list` — each with its continuation. A `slice` call always carries its window, even for a whole array; otherwise absent when every array is whole."

Previous value: -"True for exactly 100 authorships on a list record (OpenAlex's cap): the list may be longer."New value: +"True for exactly 100 `authorships` or `author_list` entries on a list record (OpenAlex's cap): the list may be longer."

Previous value: -"Results per page (1-100). Default 25."New value: +"Results per page (1-100). Default 25. A budget-cut page returns fewer (`omitted`)."

Previous value: -"OpenAlex work field names to return. Always returned: id, display_name. Defaults to the curated works select if omitted."New value: +"OpenAlex work field names to return. Always returned: id, display_name. Defaults to the curated works select if omitted. Large projections may be cut to fit the response budget (`omitted`, `windows`)."

Previous value: -"Cursor for next page. null if no more results."New value: +"Cursor for next page. null if no more results. Continues after the full upstream page, `omitted` works included."

Previous value: -"Page size OpenAlex echoed for this request — the requested per_page, not the number of records returned. A short or exhausted page carries fewer records than this."New value: +"Page size OpenAlex echoed for this request — the requested per_page, not the number of records returned. A short or exhausted page carries fewer records than this, as does a page the response budget cut (`omitted`)."

Previous value: -"Guidance when no edges are returned. A first call suggests verifying the seed_id, broadening filters, or trying a different direction; a `cursor` continuation says the walk is already past its last edge instead. Absent when results are present."New value: +"Guidance notice. Set when no edges are returned — a first call suggests verifying the seed_id, broadening filters, or trying a different direction; a `cursor` continuation says the walk is already past its last edge instead — when the response budget cut works, windowed an array, or ran over, and when a work carries exactly 100 authorships (possibly capped). Absent otherwise."

Added value: +{
+  "additionalProperties": false,
+  "description": "Present when the response budget cut whole records from the page end; pagination continues after the full upstream page.",
+  "properties": {
+    "ids": {
+      "description": "Bare IDs of the records left out, in page order (a keyword keeps its URL).",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "next": {
+      "additionalProperties": false,
+      "description": "One call returning those records as a set, in OpenAlex's order, not page order. Budgeted too, so it may carry its own `omitted`.",
+      "properties": {
+        "arguments": {
+          "additionalProperties": {},
+          "description": "Arguments to pass as-is.",
+          "properties": {},
+          "type": "object"
+        },
+        "tool": {
+          "const": "openalex_search_entities",
+          "description": "Tool to call.",
+          "type": "string"
+        }
+      },
+      "required": [
+        "tool",
+        "arguments"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "ids",
+    "next"
+  ],
+  "type": "object"
+}

Added value: +{
+  "description": "True when even the least this call can return — the first record's non-array fields (its arrays windowed to empty), or one `slice` element — exceeds the budget.",
+  "type": "boolean"
+}

Previous value: -"Works on the citation graph in this direction. Text values are plain text — HTML entities decoded, HTML/JATS/MathML markup removed."New value: +"Works on the citation graph in this direction. Text values are plain text — HTML entities decoded, HTML/JATS/MathML markup removed — except identifier and URL fields such as `id`, `doi`, `ids`, and `*_url`, returned exactly as OpenAlex stores them. Works cut by the response budget are in `omitted`; partial or possibly capped arrays are in `windows`."

Added value: +{
+  "description": "Arrays returned in part — windowed to fit the budget, paged by `slice`, or 100 possibly capped authorships — each with its continuation. A `slice` call always carries its window, even for a whole array; otherwise absent when every array is whole.",
+  "items": {
+    "additionalProperties": false,
+    "description": "An array returned in part.",
+    "properties": {
+      "field": {
+        "description": "Array field.",
+        "type": "string"
+      },
+      "id": {
+        "description": "Bare ID of the record.",
+        "type": "string"
+      },
+      "next": {
+        "anyOf": [
+          {
+            "additionalProperties": false,
+            "properties": {
+              "arguments": {
+                "additionalProperties": {},
+                "description": "Arguments to pass as-is.",
+                "properties": {},
+                "type": "object"
+              },
+              "tool": {
+                "const": "openalex_search_entities",
+                "description": "Tool to call.",
+                "type": "string"
+              }
+            },
+            "required": [
+              "tool",
+              "arguments"
+            ],
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "`id` + `slice` call for the next elements; null at the array end."
+      },
+      "offset": {
+        "description": "Index of the first element shown.",
+        "type": "number"
+      },
+      "possibly_capped": {
+        "description": "True for exactly 100 authorships on a list record (OpenAlex's cap): the list may be longer.",
+        "type": "boolean"
+      },
+      "shown": {
+        "description": "Elements shown.",
+        "type": "number"
+      },
+      "total": {
+        "description": "Array length as returned to this call.",
+        "type": "number"
+      }
+    },
+    "required": [
+      "id",
+      "field",
+      "offset",
+      "shown",
+      "total",
+      "possibly_capped",
+      "next"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Previous value: -"Works on the citation graph in this direction."New value: +"Works on the citation graph in this direction. Text values are plain text — HTML entities decoded, HTML/JATS/MathML markup removed."

Previous value: -"Pagination cursor from a previous response. Pass to get the next page."New value: +"Pagination cursor from a previous response. Pass to get the next page. Omit it on the first call — an empty string is rejected, since a supplied-but-blank cursor is a caller mistake rather than a request for the first page."

Added value: +1

Previous value: -"Additional filters to narrow the graph, same syntax as openalex_search_entities. Example: publication_year=\">2020\", is_oa=\"true\". Do not include cites/cited_by/related_to — those are set by the `direction` parameter."New value: +"Additional filters to narrow the graph, same syntax as openalex_search_entities. Example: publication_year=\">2020\", is_oa=\"true\". Do not include cites/cited_by/related_to, nor an alias of one such as cited_works — those keys are set by the `direction` parameter."

Previous value: -"Machine-readable failure mode. Declared by this tool: `rate_limited`: OpenAlex throttled the request for exceeding its per-second ceiling (HTTP 429). `upstream_budget_exhausted`: The OpenAlex daily usage budget is spent (HTTP 429). `upstream_timeout`: OpenAlex did not respond within the request deadline. `upstream_unavailable`: OpenAlex was unreachable or unusable — HTTP 503, a connection failure, or a body that was empty, HTML, or unparseable JSON. `upstream_unauthorized`: OpenAlex rejected the API key (HTTP 401). `upstream_forbidden`: OpenAlex denied access to the requested resource (HTTP 403). `comma_in_filter_value`: A filter value contains a comma, which collides with the OpenAlex filter separator. `upstream_invalid_params`: OpenAlex rejected an invalid filter or sort field name (HTTP 400). `upstream_invalid_id_value`: An entity-ID filter received a value that is not an OpenAlex ID — usually a name (HTTP 400). `upstream_sort_requires_search`: sort=-relevance_score was used but the citation-graph query has no active search (HTTP 400). `upstream_invalid_params_other`: OpenAlex rejected the request (HTTP 400) for a reason other than an invalid field name. `reserved_filter_key`: filters contains cites/cited_by/related_to — the direction parameter reserves those keys. `entity_not_found`: OpenAlex has no work matching the seed_id. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `rate_limited`: OpenAlex throttled the request for exceeding its per-second ceiling (HTTP 429). `upstream_budget_exhausted`: The OpenAlex daily usage budget is spent (HTTP 429). `upstream_timeout`: OpenAlex did not respond within the request deadline. `upstream_unavailable`: OpenAlex was unreachable or unusable — HTTP 503, a connection failure, or a body that was empty, HTML, or unparseable JSON. `upstream_unauthorized`: OpenAlex rejected the API key (HTTP 401). `upstream_forbidden`: OpenAlex denied access to the requested resource (HTTP 403). `comma_in_filter_value`: A filter value contains a comma, which collides with the OpenAlex filter separator. `upstream_invalid_params`: OpenAlex rejected an invalid filter or sort field name (HTTP 400). `upstream_invalid_id_value`: An entity-ID filter received a value that is not an OpenAlex ID — usually a name (HTTP 400). `upstream_sort_requires_search`: sort=-relevance_score was used but the citation-graph query has no active search (HTTP 400). `upstream_invalid_params_other`: OpenAlex rejected the request (HTTP 400) for a reason other than an invalid field name. `reserved_filter_key`: filters contains cites/cited_by/related_to, or an alias of one such as cited_works — the direction parameter reserves those keys. `entity_not_found`: OpenAlex has no work matching the seed_id. Other values are possible when a failure originates below the handler."

Previous value: -"Records on this page."New value: +"Page size OpenAlex echoed for this request — the requested per_page, not the number of records returned. A short or exhausted page carries fewer records than this."

Previous value: -"Recovery guidance when no edges are returned — suggests verifying the seed_id, broadening filters, or trying a different direction. Absent when results are present."New value: +"Guidance when no edges are returned. A first call suggests verifying the seed_id, broadening filters, or trying a different direction; a `cursor` continuation says the walk is already past its last edge instead. Absent when results are present."

Previous value: -"Seed work identifier. Accepts OpenAlex ID (\"W2741809807\"), DOI (\"10.1038/nature12373\" or full URL), PMID (\"12345678\" or \"https://pubmed.ncbi.nlm.nih.gov/12345678\"), or PMCID. Use openalex_resolve_name first if you only have a title."New value: +"Seed work identifier. Accepts OpenAlex ID (\"W2741809807\"), DOI (\"10.1038/nature12373\" or full URL), or PMID (\"12345678\" or \"https://pubmed.ncbi.nlm.nih.gov/12345678\"). A PMCID is recognized too, bare or as a PubMed Central URL, but OpenAlex indexes no PMCIDs, so it resolves nothing — pass the work's PMID or DOI instead. Use openalex_resolve_name first if you only have a title."

Previous value: -"Seed work identifier. Accepts OpenAlex ID (\"W2741809807\"), DOI (\"10.1038/nature12373\" or full URL), PMID, or PMCID. Use openalex_resolve_name first if you only have a title."New value: +"Seed work identifier. Accepts OpenAlex ID (\"W2741809807\"), DOI (\"10.1038/nature12373\" or full URL), PMID (\"12345678\" or \"https://pubmed.ncbi.nlm.nih.gov/12345678\"), or PMCID. Use openalex_resolve_name first if you only have a title."

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

Added value: +[
+  "string",
+  "null"
+]

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

Added value: +[
+  "string",
+  "null"
+]

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Added value: +false

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "meta",
+      "results",
+      "echo",
+      "totalCount"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `rate_limited`: OpenAlex throttled the request for exceeding its per-second ceiling (HTTP 429). `upstream_budget_exhausted`: The OpenAlex daily usage budget is spent (HTTP 429). `upstream_timeout`: OpenAlex did not respond within the request deadline. `upstream_unavailable`: OpenAlex was unreachable or unusable — HTTP 503, a connection failure, or a body that was empty, HTML, or unparseable JSON. `upstream_unauthorized`: OpenAlex rejected the API key (HTTP 401). `upstream_forbidden`: OpenAlex denied access to the requested resource (HTTP 403). `comma_in_filter_value`: A filter value contains a comma, which collides with the OpenAlex filter separator. `upstream_invalid_params`: OpenAlex rejected an invalid filter or sort field name (HTTP 400). `upstream_invalid_id_value`: An entity-ID filter received a value that is not an OpenAlex ID — usually a name (HTTP 400). `upstream_sort_requires_search`: sort=-relevance_score was used but the citation-graph query has no active search (HTTP 400). `upstream_invalid_params_other`: OpenAlex rejected the request (HTTP 400) for a reason other than an invalid field name. `reserved_filter_key`: filters contains cites/cited_by/related_to — the direction parameter reserves those keys. `entity_not_found`: OpenAlex has no work matching the seed_id. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "rate_limited",
+            "upstream_budget_exhausted",
+            "upstream_timeout",
+            "upstream_unavailable",
+            "upstream_unauthorized",
+            "upstream_forbidden",
+            "comma_in_filter_value",
+            "upstream_invalid_params",
+            "upstream_invalid_id_value",
+            "upstream_sort_requires_search",
+            "upstream_invalid_params_other",
+            "reserved_filter_key",
+            "entity_not_found"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

Removed value: -[
-  "meta",
-  "results",
-  "echo",
-  "totalCount"
-]

Added value: +{
+  "description": "USD left in the prepaid balance — a separate pool OpenAlex draws on only after the daily allowance runs out, and which the daily reset does not refill. Add it to `remainingUsd` for the full spendable amount. Absent when the account holds no prepaid balance.",
+  "type": "number"
+}

Added value: +{
+  "additionalProperties": false,
+  "description": "What this call cost against the OpenAlex daily budget and what is left of it. Price a full walk before committing to it: `totalCount` ÷ `per_page` × `costUsd` against `remainingUsd`. Absent when OpenAlex omitted the accounting headers.",
+  "properties": {
+    "costUsd": {
+      "description": "USD this call spent, covering both upstream requests — the seed validation lookup (unbilled) and the graph page itself.",
+      "type": "number"
+    },
+    "remainingUsd": {
+      "description": "USD left in today's OpenAlex budget after this call.",
+      "type": "number"
+    },
+    "resetsInSeconds": {
+      "description": "Seconds until the daily budget refills (midnight UTC).",
+      "type": "number"
+    }
+  },
+  "required": [
+    "costUsd",
+    "remainingUsd",
+    "resetsInSeconds"
+  ],
+  "type": "object"
+}

Previous value: -"Sort field. Prefix with \"-\" for descending. Common: \"cited_by_count\", \"-publication_date\". Default is OpenAlex relevance."New value: +"Sort field. Prefix with \"-\" for descending. Comma-separate for a multi-key sort, applied left to right, with the \"-\" prefix set per key (\"-publication_year,cited_by_count\" sorts by year descending, then citations ascending). Common: \"cited_by_count\", \"-publication_date\". Default is OpenAlex relevance."

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

Previous value: -"Work title."New value: +"Work title. null when OpenAlex holds no title for the record (paratext works and other untitled entries) — use `id` to identify it."

Removed value: -"string"

Added value: +{
+  "description": "Total edges from seed_id in this direction across all pages.",
+  "type": "number"
+}

Removed value: -{
-  "description": "Total edges from seed_id in this direction across all pages.",
-  "type": "number"
-}

Previous value: -[
-  "meta",
-  "results",
-  "echo",
-  "totalEdges"
-]New value: +[
+  "meta",
+  "results",
+  "echo",
+  "totalCount"
+]

Previous value: -"Compact echo of seed_id, direction, filters, sort — useful when no edges are returned so callers see what was actually queried."New value: +"Compact echo of seed_id, direction, filters, sort — surfaces what was actually queried when no edges are returned."

Added value: +{
+  "description": "Compact echo of seed_id, direction, filters, sort — useful when no edges are returned so callers see what was actually queried.",
+  "type": "string"
+}

Removed value: -{
-  "description": "Compact echo of seed_id, direction, filters, sort — useful when empty.",
-  "type": "string"
-}

Previous value: -[
-  "count",
-  "per_page",
-  "next_cursor",
-  "echo"
-]New value: +[
+  "count",
+  "per_page",
+  "next_cursor"
+]

Added value: +{
+  "description": "Recovery guidance when no edges are returned — suggests verifying the seed_id, broadening filters, or trying a different direction. Absent when results are present.",
+  "type": "string"
+}

Added value: +{
+  "description": "Total edges from seed_id in this direction across all pages.",
+  "type": "number"
+}

Previous value: -[
-  "meta",
-  "results"
-]New value: +[
+  "meta",
+  "results",
+  "echo",
+  "totalEdges"
+]

Previous value: -"Additional filters to narrow the graph, same syntax as openalex_search_entities. Example: publication_year=\">2020\", is_oa=\"true\". The direction filter is added automatically — do not pass cites/cited_by/related_to here."New value: +"Additional filters to narrow the graph, same syntax as openalex_search_entities. Example: publication_year=\">2020\", is_oa=\"true\". Do not include cites/cited_by/related_to — those are set by the `direction` parameter."