Previous value: -"Files and websites available to the planned Study (one question block, at most 100). With multiple assets, map every question explicitly (use [] for no assets); an asset no question uses is shown with every question. Give each scoped file a stable id. Remote URLs are copied into durable Minds storage before the draft is saved. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."New value: +"Files and websites available to the planned Study (one question block, at most 100). With multiple assets, map every question explicitly (use [] for no assets); an asset no question uses is shown with every question. Give each scoped file a stable id. Remote URLs are copied into durable Minds storage before the draft is saved. Pass a fetchable HTTP(S) URL, or an existing Minds workspace upload under chat/<userId>/ (that storage path or its /api/uploads/chat/ URL; request the signed upload with folder \"chat\"). MCP cannot read a local path, and a file the user attached in the chat client is NOT reachable either unless that client also exposes a public URL for it — most do not. When it is not: send the file CONTENTS to import_audience_sources (UTF-8 text, Markdown, CSV, JSON), which takes contents rather than paths. A PDF or image with no public URL has no MCP route at all — it must be uploaded in the Minds app first; say so instead of retrying. Study tools import external file URLs into durable Minds storage before saving or running. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."

Previous value: -"Storage path of a file already uploaded to Minds. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."New value: +"Storage path of a file already uploaded to Minds. Pass a fetchable HTTP(S) URL, or an existing Minds workspace upload under chat/<userId>/ (that storage path or its /api/uploads/chat/ URL; request the signed upload with folder \"chat\"). MCP cannot read a local path, and a file the user attached in the chat client is NOT reachable either unless that client also exposes a public URL for it — most do not. When it is not: send the file CONTENTS to import_audience_sources (UTF-8 text, Markdown, CSV, JSON), which takes contents rather than paths. A PDF or image with no public URL has no MCP route at all — it must be uploaded in the Minds app first; say so instead of retrying. Study tools import external file URLs into durable Minds storage before saving or running. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."

Previous value: -"Fetchable HTTP(S), signed, or Minds workspace upload URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."New value: +"Fetchable HTTP(S), signed, or Minds workspace upload URL. Pass a fetchable HTTP(S) URL, or an existing Minds workspace upload under chat/<userId>/ (that storage path or its /api/uploads/chat/ URL; request the signed upload with folder \"chat\"). MCP cannot read a local path, and a file the user attached in the chat client is NOT reachable either unless that client also exposes a public URL for it — most do not. When it is not: send the file CONTENTS to import_audience_sources (UTF-8 text, Markdown, CSV, JSON), which takes contents rather than paths. A PDF or image with no public URL has no MCP route at all — it must be uploaded in the Minds app first; say so instead of retrying. Study tools import external file URLs into durable Minds storage before saving or running. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."

Previous value: -"The one main source this study is about. When Minds must evaluate pasted text, use kind prompt and put the exact respondent-visible material in content. Keep research objectives, requested questions, and planner-only instructions in request. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."New value: +"The one main source this study is about. When Minds must evaluate pasted text, use kind prompt and put the exact respondent-visible material in content. Keep research objectives, requested questions, and planner-only instructions in request. Pass a fetchable HTTP(S) URL, or an existing Minds workspace upload under chat/<userId>/ (that storage path or its /api/uploads/chat/ URL; request the signed upload with folder \"chat\"). MCP cannot read a local path, and a file the user attached in the chat client is NOT reachable either unless that client also exposes a public URL for it — most do not. When it is not: send the file CONTENTS to import_audience_sources (UTF-8 text, Markdown, CSV, JSON), which takes contents rather than paths. A PDF or image with no public URL has no MCP route at all — it must be uploaded in the Minds app first; say so instead of retrying. Study tools import external file URLs into durable Minds storage before saving or running. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."

Previous value: -"Fetchable source URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."New value: +"Fetchable source URL. Pass a fetchable HTTP(S) URL, or an existing Minds workspace upload under chat/<userId>/ (that storage path or its /api/uploads/chat/ URL; request the signed upload with folder \"chat\"). MCP cannot read a local path, and a file the user attached in the chat client is NOT reachable either unless that client also exposes a public URL for it — most do not. When it is not: send the file CONTENTS to import_audience_sources (UTF-8 text, Markdown, CSV, JSON), which takes contents rather than paths. A PDF or image with no public URL has no MCP route at all — it must be uploaded in the Minds app first; say so instead of retrying. Study tools import external file URLs into durable Minds storage before saving or running. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."

Previous value: -"Files and websites available to the planned Study (one question block, at most 100). With multiple assets, every question needs an explicit assignment and every asset must be used by at least one question. Use [] for no assets. Give each scoped file a stable id. Remote URLs are copied into durable Minds storage before the draft is saved. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."New value: +"Files and websites available to the planned Study (one question block, at most 100). With multiple assets, map every question explicitly (use [] for no assets); an asset no question uses is shown with every question. Give each scoped file a stable id. Remote URLs are copied into durable Minds storage before the draft is saved. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."

Previous value: -"Question-to-file mapping. Multi-asset blocks require every question to be mapped, using [] for no assets; every asset must appear on at least one question. Each question at most once; every referenced attachment id must resolve."New value: +"Question-to-file mapping. In multi-asset blocks map every question, using [] for no assets; an omitted question receives every asset and an asset on no question is shown with every question. Each question at most once; every referenced attachment id must resolve."

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "label": {
+        "type": "string"
+      },
+      "value": {
+        "type": "number"
+      }
+    },
+    "required": [
+      "label",
+      "value"
+    ],
+    "type": "object"
+  },
+  "maxItems": 100,
+  "minItems": 2,
+  "type": "array"
+}

Removed value: -100

Removed value: --100

Previous value: -"integer"New value: +"number"

Previous value: -"Explicit response-format edits, one entry per question. Each entry needs questionId (from the latest draft) plus the type the question actually calls for: categorical for one choice, multiselect for several (with maxSelections), ranking when every Mind orders all categoricalOptions, scale with an inclusive integer scaleRange, and qualitative only for a genuinely open answer. Use this to correct an item whose options ended up inside its text."New value: +"Explicit response-format edits, one entry per question. Each entry needs questionId (from the latest draft) plus the type the question actually calls for: categorical for one choice, multiselect for several (with maxSelections), ranking when every Mind orders all categoricalOptions, scale with an inclusive finite numeric scaleRange, and qualitative only for a genuinely open answer. Use this to correct an item whose options ended up inside its text."

Removed value: -1

Added value: +{
+  "description": "Exhaustive allowed scale answers in authored order, each with its literal label and numeric value. Omit for an unenumerated range; never fill missing intermediate points.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "label": {
+        "type": "string"
+      },
+      "value": {
+        "type": "number"
+      }
+    },
+    "required": [
+      "label",
+      "value"
+    ],
+    "type": "object"
+  },
+  "maxItems": 100,
+  "minItems": 2,
+  "type": "array"
+}

Previous value: -"Inclusive integer response range as [minimum, maximum]; required for scale responses."New value: +"Inclusive finite numeric response bounds as [minimum, maximum], only when specified. Numeric responses may be unbounded. Fractional and wide ranges retain their authored values."

Removed value: -100

Removed value: --100

Previous value: -"integer"New value: +"number"

Previous value: -"Exact execution contract for this item. Pick by what the question asks of a respondent: a fixed set of choices is categorical (exactly one) or multiselect (several, with maxSelections); putting every option in order is ranking; a numeric judgement is scale with an inclusive integer scaleRange; only a genuinely open answer in the respondent's own words is qualitative. categorical, multiselect and ranking all carry the choices in categoricalOptions, which keep their exact labels and order even with attachments; files are evidence and do not generate replacement A/B options."New value: +"Exact execution contract for this item. Pick by what the question asks of a respondent: a fixed set of choices is categorical (exactly one) or multiselect (several, with maxSelections); putting every option in order is ranking; a numeric judgement is scale with an inclusive finite numeric scaleRange; only a genuinely open answer in the respondent's own words is qualitative. categorical, multiselect and ranking all carry the choices in categoricalOptions, which keep their exact labels and order even with attachments; files are evidence and do not generate replacement A/B options."

Removed value: -1

Added value: +{
+  "description": "Exhaustive allowed scale answers in authored order, each with its literal label and numeric value. Omit for an unenumerated range; never fill missing intermediate points.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "label": {
+        "type": "string"
+      },
+      "value": {
+        "type": "number"
+      }
+    },
+    "required": [
+      "label",
+      "value"
+    ],
+    "type": "object"
+  },
+  "maxItems": 100,
+  "minItems": 2,
+  "type": "array"
+}

Previous value: -"Inclusive integer response range as [minimum, maximum]; required for scale responses."New value: +"Inclusive finite numeric response bounds as [minimum, maximum], only when specified. Numeric responses may be unbounded. Fractional and wide ranges retain their authored values."

Removed value: -100

Removed value: --100

Previous value: -"integer"New value: +"number"

Added value: +{
+  "items": {
+    "maxLength": 500,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 100,
+  "minItems": 1,
+  "type": "array"
+}

Added value: +{
+  "items": {
+    "maxLength": 500,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 100,
+  "minItems": 1,
+  "type": "array"
+}

Previous value: -"Routing: ask this item only of respondents whose own answer to an earlier categorical or multiselect item (questionId) matched. Give exactly one of answerIn or answerNotIn with that item's exact option labels. Respondents not asked are recorded as not asked and excluded from this item's results."New value: +"Routing: ask this item only of respondents whose own answer to an earlier item (questionId) matched. Give exactly one of: answerIn or answerNotIn with an earlier categorical or multiselect item's exact option labels; or categoryIn or categoryNotIn for an earlier open (qualitative) item, whose answers are coded into the categories named for it (one frame per item, at most 12) once it has been answered; an answer fitting none of them counts as none. Scale and ranking items cannot gate. Respondents not asked are recorded as not asked and excluded from this item's results."

Added value: +{
+  "items": {
+    "maxLength": 500,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 100,
+  "minItems": 1,
+  "type": "array"
+}

Added value: +{
+  "items": {
+    "maxLength": 500,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 100,
+  "minItems": 1,
+  "type": "array"
+}

Previous value: -"Exact respondent-visible question text, including any anchors or labels. Stored as given. Answer options do NOT belong here: list them in response.categoricalOptions instead. A question whose text spells out its choices but is typed qualitative is answered as free text, every Mind converges on the same most likely wording, and the chart shows one option at 100%. State the options here only as a respondent would read them, and always carry the same options in response.categoricalOptions so the contract and the wording agree."New value: +"Exact respondent-visible question text, including any anchors or labels. Stored as given. Answer options do NOT belong here: list them in response.categoricalOptions instead. A question whose text spells out its choices but is typed qualitative is answered as free text, every Mind converges on the same most likely wording, and the chart shows one option at 100%. State the options here only as a respondent would read them, and always carry the same options in response.categoricalOptions so the contract and the wording agree. Skip and filter instructions (\"No -> go to Q12\", \"only if Q3 = Yes\") do not belong in the text either: transcribe each as askIf. A jump from an answer of item G to item N gives every item between G and N answerNotIn [that answer]; a filter gives answerIn. Tell the person about any instruction you cannot map to exact items and options instead of guessing it."

Previous value: -"Save exact edits to draftPlanId and revision without a model call. Preserves method configuration, source policy, item IDs and exact wording. Questions are the complete selected instrument in module order; method-specific batteries are read-only. Cannot combine with planner inputs."New value: +"Save exact edits to draftPlanId and revision without a model call. Preserves method configuration, source policy, item IDs and exact wording. Questions are the complete selected instrument in module order, including each item's askIf (omitted means none); method-specific batteries are read-only. Cannot combine with planner inputs."

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "answerIn": {
+      "items": {
+        "maxLength": 500,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 100,
+      "minItems": 1,
+      "type": "array"
+    },
+    "answerNotIn": {
+      "items": {
+        "maxLength": 500,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 100,
+      "minItems": 1,
+      "type": "array"
+    },
+    "questionId": {
+      "maxLength": 80,
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "questionId"
+  ],
+  "type": "object"
+}

Previous value: -"Explicit response-format edits, one entry per question. Each entry needs questionId (from the latest draft) plus type qualitative, categorical, multiselect, ranking (every Mind orders all categoricalOptions), or scale with an inclusive integer scaleRange."New value: +"Explicit response-format edits, one entry per question. Each entry needs questionId (from the latest draft) plus the type the question actually calls for: categorical for one choice, multiselect for several (with maxSelections), ranking when every Mind orders all categoricalOptions, scale with an inclusive integer scaleRange, and qualitative only for a genuinely open answer. Use this to correct an item whose options ended up inside its text."

Added value: +{
+  "additionalProperties": false,
+  "description": "Routing: ask this item only of respondents whose own answer to an earlier categorical or multiselect item (questionId) matched. Give exactly one of answerIn or answerNotIn with that item's exact option labels. Respondents not asked are recorded as not asked and excluded from this item's results.",
+  "properties": {
+    "answerIn": {
+      "items": {
+        "maxLength": 500,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 100,
+      "minItems": 1,
+      "type": "array"
+    },
+    "answerNotIn": {
+      "items": {
+        "maxLength": 500,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 100,
+      "minItems": 1,
+      "type": "array"
+    },
+    "questionId": {
+      "maxLength": 80,
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "questionId"
+  ],
+  "type": "object"
+}

Previous value: -"Exact execution contract for this item: type qualitative, categorical (with categoricalOptions), multiselect, ranking (with categoricalOptions every Mind puts in order), or scale (with inclusive integer scaleRange). Supplied categoricalOptions keep their exact labels and order even with attachments; files are evidence and do not generate replacement A/B options."New value: +"Exact execution contract for this item. Pick by what the question asks of a respondent: a fixed set of choices is categorical (exactly one) or multiselect (several, with maxSelections); putting every option in order is ranking; a numeric judgement is scale with an inclusive integer scaleRange; only a genuinely open answer in the respondent's own words is qualitative. categorical, multiselect and ranking all carry the choices in categoricalOptions, which keep their exact labels and order even with attachments; files are evidence and do not generate replacement A/B options."

Previous value: -"Exact respondent-visible question text, including any anchors or labels. Stored as given."New value: +"Exact respondent-visible question text, including any anchors or labels. Stored as given. Answer options do NOT belong here: list them in response.categoricalOptions instead. A question whose text spells out its choices but is typed qualitative is answered as free text, every Mind converges on the same most likely wording, and the chart shows one option at 100%. State the options here only as a respondent would read them, and always carry the same options in response.categoricalOptions so the contract and the wording agree."

Previous value: -[
-  "qualitative",
-  "categorical",
-  "multiselect",
-  "scale"
-]New value: +[
+  "qualitative",
+  "categorical",
+  "multiselect",
+  "ranking",
+  "scale"
+]

Previous value: -"Explicit response-format edits, one entry per question. Each entry needs questionId (from the latest draft) plus type qualitative, categorical, multiselect, or scale with an inclusive integer scaleRange."New value: +"Explicit response-format edits, one entry per question. Each entry needs questionId (from the latest draft) plus type qualitative, categorical, multiselect, ranking (every Mind orders all categoricalOptions), or scale with an inclusive integer scaleRange."

Previous value: -"Predefined answer choices; only valid for categorical or multiselect responses."New value: +"Predefined answer choices; only valid for categorical, multiselect or ranking responses. A ranking orders all of them."

Previous value: -[
-  "qualitative",
-  "categorical",
-  "multiselect",
-  "scale"
-]New value: +[
+  "qualitative",
+  "categorical",
+  "multiselect",
+  "ranking",
+  "scale"
+]

Previous value: -"Exact execution contract for this item: type qualitative, categorical (with categoricalOptions), multiselect, or scale (with inclusive integer scaleRange). Supplied categoricalOptions keep their exact labels and order even with attachments; files are evidence and do not generate replacement A/B options."New value: +"Exact execution contract for this item: type qualitative, categorical (with categoricalOptions), multiselect, ranking (with categoricalOptions every Mind puts in order), or scale (with inclusive integer scaleRange). Supplied categoricalOptions keep their exact labels and order even with attachments; files are evidence and do not generate replacement A/B options."

Previous value: -"Predefined answer choices; only valid for categorical or multiselect responses."New value: +"Predefined answer choices; only valid for categorical, multiselect or ranking responses. A ranking orders all of them."

Previous value: -[
-  "qualitative",
-  "categorical",
-  "multiselect",
-  "scale"
-]New value: +[
+  "qualitative",
+  "categorical",
+  "multiselect",
+  "ranking",
+  "scale"
+]

Removed value: -{
-  "description": "Answers to the draft confirmation questions.",
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "answer": {
-        "description": "The user's answer to that confirmation question.",
-        "type": "string"
-      },
-      "questionId": {
-        "description": "Confirmation question ID from the latest draft.",
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "questionId",
-      "answer"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}

Removed value: -{
-  "description": "Files and websites available to the planned Study (one question block, at most 100). With multiple assets, every question needs an explicit assignment and every asset must be used by at least one question. Use [] for no assets. Give each scoped file a stable id. Remote URLs are copied into durable Minds storage before the draft is saved. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset.",
-  "items": {
-    "properties": {
-      "id": {
-        "description": "Stable asset ID used by questionAttachments to assign this file to specific planned questions.",
-        "maxLength": 255,
-        "minLength": 1,
-        "type": "string"
-      },
-      "kind": {
-        "const": "website",
-        "description": "Use website for a page to read as a website rather than download as a file.",
-        "type": "string"
-      },
-      "mimeType": {
-        "maxLength": 255,
-        "type": "string"
-      },
-      "name": {
-        "description": "File name visible in the Study.",
-        "minLength": 1,
-        "type": "string"
-      },
-      "path": {
-        "description": "Storage path of a file already uploaded to Minds. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset.",
-        "minLength": 1,
-        "type": "string"
-      },
-      "type": {
-        "description": "MIME type when known.",
-        "minLength": 1,
-        "type": "string"
-      },
-      "url": {
-        "description": "Fetchable HTTP(S), signed, or Minds workspace upload URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset.",
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "type": "object"
-  },
-  "maxItems": 100,
-  "type": "array"
-}

Added value: +{
+  "description": "Revising an existing draft: which draft and revision, and how it should change. Omit for a new draft.",
+  "properties": {
+    "answers": {
+      "description": "Answers to the draft confirmation questions.",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "answer": {
+            "description": "The user's answer to that confirmation question.",
+            "type": "string"
+          },
+          "questionId": {
+            "description": "Confirmation question ID from the latest draft.",
+            "minLength": 1,
+            "type": "string"
+          }
+        },
+        "required": [
+          "questionId",
+          "answer"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "edits": {
+      "additionalProperties": false,
+      "description": "Save exact edits to draftPlanId and revision without a model call. Preserves method configuration, source policy, item IDs and exact wording. Questions are the complete selected instrument in module order; method-specific batteries are read-only. Cannot combine with planner inputs.",
+      "properties": {
+        "objective": {
+          "maxLength": 2000,
+          "minLength": 1,
+          "type": "string"
+        },
+        "promptContent": {
+          "maxLength": 20000,
+          "type": "string"
+        },
+        "questions": {
+          "items": {
+            "additionalProperties": false,
+            "properties": {
+              "attachmentIds": {
+                "items": {
+                  "maxLength": 255,
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "maxItems": 50,
+                "type": "array"
+              },
+              "id": {
+                "maxLength": 80,
+                "minLength": 1,
+                "pattern": "^[a-z0-9_-]+$",
+                "type": "string"
+              },
+              "moduleId": {
+                "maxLength": 120,
+                "minLength": 1,
+                "type": "string"
+              },
+              "response": {
+                "additionalProperties": false,
+                "properties": {
+                  "categoricalOptions": {
+                    "items": {
+                      "minLength": 1,
+                      "type": "string"
+                    },
+                    "maxItems": 100,
+                    "minItems": 2,
+                    "type": "array"
+                  },
+                  "maxSelections": {
+                    "maximum": 100,
+                    "minimum": 1,
+                    "type": "integer"
+                  },
+                  "scaleRange": {
+                    "items": {
+                      "maximum": 100,
+                      "minimum": -100,
+                      "type": "integer"
+                    },
+                    "maxItems": 2,
+                    "minItems": 2,
+                    "type": "array"
+                  },
+                  "type": {
+                    "enum": [
+                      "qualitative",
+                      "categorical",
+                      "multiselect",
+                      "scale"
+                    ],
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "type"
+                ],
+                "type": "object"
+              },
+              "text": {
+                "maxLength": 2000,
+                "minLength": 1,
+                "type": "string"
+              }
+            },
+            "required": [
+              "id",
+              "moduleId",
+              "text",
+              "response"
+            ],
+            "type": "object"
+          },
+          "maxItems": 200,
+          "minItems": 1,
+          "type": "array"
+        }
+      },
+      "type": "object"
+    },
+    "id": {
+      "description": "Existing draft ID to revise after the user answers a confirmation question.",
+      "format": "uuid",
+      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
+      "type": "string"
+    },
+    "loadLatest": {
+      "description": "Read the latest saved revision of draftPlanId, without generating, saving or executing. Do not combine with edits or planner inputs.",
+      "type": "boolean"
+    },
+    "questionResponses": {
+      "description": "Explicit response-format edits, one entry per question. Each entry needs questionId (from the latest draft) plus type qualitative, categorical, multiselect, or scale with an inclusive integer scaleRange.",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "categoricalOptions": {
+            "description": "Predefined answer choices; only valid for categorical or multiselect responses.",
+            "items": {
+              "minLength": 1,
+              "type": "string"
+            },
+            "maxItems": 100,
+            "minItems": 2,
+            "type": "array"
+          },
+          "maxSelections": {
+            "description": "Maximum choices a respondent may select; only valid for multiselect responses.",
+            "maximum": 100,
+            "minimum": 1,
+            "type": "integer"
+          },
+          "questionId": {
+            "description": "Question ID from the latest draft plan.",
+            "maxLength": 80,
+            "minLength": 1,
+            "type": "string"
+          },
+          "scaleRange": {
+            "description": "Inclusive integer response range as [minimum, maximum]; required for scale responses.",
+            "items": {
+              "maximum": 100,
+              "minimum": -100,
+              "type": "integer"
+            },
+            "maxItems": 2,
+            "minItems": 2,
+            "type": "array"
+          },
+          "type": {
+            "enum": [
+              "qualitative",
+              "categorical",
+              "multiselect",
+              "scale"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "questionId",
+          "type"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "refinement": {
+      "description": "How the user wants the existing draft changed.",
+      "type": "string"
+    },
+    "revision": {
+      "description": "Current draft revision; required with draftPlanId.",
+      "exclusiveMinimum": 0,
+      "maximum": 9007199254740991,
+      "type": "integer"
+    }
+  },
+  "type": "object"
+}

Removed value: -{
-  "description": "Existing draft ID to revise after the user answers a confirmation question.",
-  "format": "uuid",
-  "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
-  "type": "string"
-}

Removed value: -{
-  "additionalProperties": false,
-  "description": "Save exact edits to draftPlanId and revision without a model call. Preserves method configuration, source policy, item IDs and exact wording. Questions are the complete selected instrument in module order; method-specific batteries are read-only. Cannot combine with planner inputs.",
-  "properties": {
-    "objective": {
-      "maxLength": 2000,
-      "minLength": 1,
-      "type": "string"
-    },
-    "promptContent": {
-      "maxLength": 20000,
-      "type": "string"
-    },
-    "questions": {
-      "items": {
-        "additionalProperties": false,
-        "properties": {
-          "attachmentIds": {
-            "items": {
-              "maxLength": 255,
-              "minLength": 1,
-              "type": "string"
-            },
-            "maxItems": 50,
-            "type": "array"
-          },
-          "id": {
-            "maxLength": 80,
-            "minLength": 1,
-            "pattern": "^[a-z0-9_-]+$",
-            "type": "string"
-          },
-          "moduleId": {
-            "maxLength": 120,
-            "minLength": 1,
-            "type": "string"
-          },
-          "response": {
-            "additionalProperties": false,
-            "properties": {
-              "categoricalOptions": {
-                "items": {
-                  "minLength": 1,
-                  "type": "string"
-                },
-                "maxItems": 100,
-                "minItems": 2,
-                "type": "array"
-              },
-              "maxSelections": {
-                "maximum": 100,
-                "minimum": 1,
-                "type": "integer"
-              },
-              "scaleRange": {
-                "items": {
-                  "maximum": 100,
-                  "minimum": -100,
-                  "type": "integer"
-                },
-                "maxItems": 2,
-                "minItems": 2,
-                "type": "array"
-              },
-              "type": {
-                "enum": [
-                  "qualitative",
-                  "categorical",
-                  "multiselect",
-                  "scale"
-                ],
-                "type": "string"
-              }
-            },
-            "required": [
-              "type"
-            ],
-            "type": "object"
-          },
-          "text": {
-            "maxLength": 2000,
-            "minLength": 1,
-            "type": "string"
-          }
-        },
-        "required": [
-          "id",
-          "moduleId",
-          "text",
-          "response"
-        ],
-        "type": "object"
-      },
-      "maxItems": 200,
-      "minItems": 1,
-      "type": "array"
-    }
-  },
-  "type": "object"
-}

Removed value: -{
-  "description": "Read the latest saved revision of draftPlanId, without generating, saving or executing. Do not combine with edits or planner inputs.",
-  "type": "boolean"
-}

Removed value: -{
-  "description": "Experimental per-Mind treatment assignments stored in the exact draft revision. Each Mind may appear once; unlisted Minds use sourcePolicy. Use only for a preregistered source-policy experiment.",
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "mindId": {
-        "description": "Exact Mind UUID in the Study cohort.",
-        "format": "uuid",
-        "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
-        "type": "string"
-      },
-      "sourcePolicy": {
-        "description": "Request-scoped evidence treatment for this Mind.",
-        "enum": [
-          "request_only",
-          "auto"
-        ],
-        "type": "string"
-      }
-    },
-    "required": [
-      "mindId",
-      "sourcePolicy"
-    ],
-    "type": "object"
-  },
-  "maxItems": 2000,
-  "type": "array"
-}

Removed value: -{
-  "description": "Study ID (UUID; legacy wire field name: panelId). Omit both panelId and panelName only to continue the active Study from this MCP session.",
-  "format": "uuid",
-  "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
-  "type": "string"
-}

Removed value: -{
-  "description": "Study name for fuzzy matching (legacy wire field name: panelName). Omit both panelName and panelId only to continue the active Study from this MCP session.",
-  "type": "string"
-}

Added value: +{
+  "description": "Evidence policy and language stored in the draft revision and reviewed before execution.",
+  "properties": {
+    "mindSourcePolicyOverrides": {
+      "description": "Experimental per-Mind treatment assignments stored in the exact draft revision. Each Mind may appear once; unlisted Minds use sourcePolicy. Use only for a preregistered source-policy experiment.",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "mindId": {
+            "description": "Exact Mind UUID in the Study cohort.",
+            "format": "uuid",
+            "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
+            "type": "string"
+          },
+          "sourcePolicy": {
+            "description": "Request-scoped evidence treatment for this Mind.",
+            "enum": [
+              "request_only",
+              "auto"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "mindId",
+          "sourcePolicy"
+        ],
+        "type": "object"
+      },
+      "maxItems": 2000,
+      "type": "array"
+    },
+    "sourcePolicy": {
+      "description": "Evidence policy stored in the draft and reviewed before execution. Defaults to request_only for a controlled Study. Use auto only for an explicitly designed experiment that should allow relevant Mind-knowledge retrieval; response-mode rules still control live web search.",
+      "enum": [
+        "request_only",
+        "auto"
+      ],
+      "type": "string"
+    },
+    "studyLocale": {
+      "description": "Language for the plan, questions, responses, labels, and summary. Set this explicitly when the user requests a language.",
+      "enum": [
+        "en",
+        "es",
+        "fr",
+        "de",
+        "zh",
+        "tr",
+        "ar",
+        "ja",
+        "ko"
+      ],
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Removed value: -{
-  "description": "Question-to-file mapping. Multi-asset blocks require every question to be mapped, using [] for no assets; every asset must appear on at least one question. Each question at most once; every referenced attachment id must resolve.",
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "attachmentIds": {
-        "description": "Stable ids from attachments that this question alone receives (at most 20).",
-        "items": {
-          "maxLength": 255,
-          "minLength": 1,
-          "type": "string"
-        },
-        "maxItems": 20,
-        "type": "array"
-      },
-      "questionNumber": {
-        "description": "One-based question position in the returned plan, across modules in order.",
-        "maximum": 9007199254740991,
-        "minimum": 1,
-        "type": "integer"
-      }
-    },
-    "required": [
-      "questionNumber",
-      "attachmentIds"
-    ],
-    "type": "object"
-  },
-  "minItems": 1,
-  "type": "array"
-}

Removed value: -{
-  "description": "Explicit response-format edits, one entry per question. Each entry needs questionId (from the latest draft) plus type qualitative, categorical, multiselect, or scale with an inclusive integer scaleRange.",
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "categoricalOptions": {
-        "description": "Predefined answer choices; only valid for categorical or multiselect responses.",
-        "items": {
-          "minLength": 1,
-          "type": "string"
-        },
-        "maxItems": 100,
-        "minItems": 2,
-        "type": "array"
-      },
-      "maxSelections": {
-        "description": "Maximum choices a respondent may select; only valid for multiselect responses.",
-        "maximum": 100,
-        "minimum": 1,
-        "type": "integer"
-      },
-      "questionId": {
-        "description": "Question ID from the latest draft plan.",
-        "maxLength": 80,
-        "minLength": 1,
-        "type": "string"
-      },
-      "scaleRange": {
-        "description": "Inclusive integer response range as [minimum, maximum]; required for scale responses.",
-        "items": {
-          "maximum": 100,
-          "minimum": -100,
-          "type": "integer"
-        },
-        "maxItems": 2,
-        "minItems": 2,
-        "type": "array"
-      },
-      "type": {
-        "enum": [
-          "qualitative",
-          "categorical",
-          "multiselect",
-          "scale"
-        ],
-        "type": "string"
-      }
-    },
-    "required": [
-      "questionId",
-      "type"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}

Removed value: -{
-  "description": "How the user wants the existing draft changed.",
-  "type": "string"
-}

Removed value: -{
-  "description": "Current draft revision; required with draftPlanId.",
-  "exclusiveMinimum": 0,
-  "maximum": 9007199254740991,
-  "type": "integer"
-}

Removed value: -{
-  "description": "The one main source this study is about. When Minds must evaluate pasted text, use kind prompt and put the exact respondent-visible material in content. Keep research objectives, requested questions, and planner-only instructions in request. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset.",
-  "properties": {
-    "content": {
-      "description": "Exact respondent-visible pasted text. Use only with kind prompt when Minds must evaluate a concept, message, description, or other text. Do not include planner-only instructions.",
-      "maxLength": 20000,
-      "minLength": 1,
-      "type": "string"
-    },
-    "kind": {
-      "enum": [
-        "prompt",
-        "website",
-        "image",
-        "video",
-        "document",
-        "questionnaire",
-        "other"
-      ],
-      "type": "string"
-    },
-    "label": {
-      "minLength": 1,
-      "type": "string"
-    },
-    "mimeType": {
-      "type": "string"
-    },
-    "url": {
-      "description": "Fetchable source URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset.",
-      "minLength": 1,
-      "type": "string"
-    }
-  },
-  "required": [
-    "kind",
-    "label"
-  ],
-  "type": "object"
-}

Removed value: -{
-  "description": "Evidence policy stored in the draft and reviewed before execution. Defaults to request_only for a controlled Study. Use auto only for an explicitly designed experiment that should allow relevant Mind-knowledge retrieval; response-mode rules still control live web search.",
-  "enum": [
-    "request_only",
-    "auto"
-  ],
-  "type": "string"
-}

Added value: +{
+  "description": "Respondent-visible material for the planned block, and how it is assigned to questions.",
+  "properties": {
+    "attachments": {
+      "description": "Files and websites available to the planned Study (one question block, at most 100). With multiple assets, every question needs an explicit assignment and every asset must be used by at least one question. Use [] for no assets. Give each scoped file a stable id. Remote URLs are copied into durable Minds storage before the draft is saved. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset.",
+      "items": {
+        "properties": {
+          "id": {
+            "description": "Stable asset ID used by questionAttachments to assign this file to specific planned questions.",
+            "maxLength": 255,
+            "minLength": 1,
+            "type": "string"
+          },
+          "kind": {
+            "const": "website",
+            "description": "Use website for a page to read as a website rather than download as a file.",
+            "type": "string"
+          },
+          "mimeType": {
+            "maxLength": 255,
+            "type": "string"
+          },
+          "name": {
+            "description": "File name visible in the Study.",
+            "minLength": 1,
+            "type": "string"
+          },
+          "path": {
+            "description": "Storage path of a file already uploaded to Minds. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset.",
+            "minLength": 1,
+            "type": "string"
+          },
+          "type": {
+            "description": "MIME type when known.",
+            "minLength": 1,
+            "type": "string"
+          },
+          "url": {
+            "description": "Fetchable HTTP(S), signed, or Minds workspace upload URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset.",
+            "minLength": 1,
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "maxItems": 100,
+      "type": "array"
+    },
+    "questionAttachments": {
+      "description": "Question-to-file mapping. Multi-asset blocks require every question to be mapped, using [] for no assets; every asset must appear on at least one question. Each question at most once; every referenced attachment id must resolve.",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "attachmentIds": {
+            "description": "Stable ids from attachments that this question alone receives (at most 20).",
+            "items": {
+              "maxLength": 255,
+              "minLength": 1,
+              "type": "string"
+            },
+            "maxItems": 20,
+            "type": "array"
+          },
+          "questionNumber": {
+            "description": "One-based question position in the returned plan, across modules in order.",
+            "maximum": 9007199254740991,
+            "minimum": 1,
+            "type": "integer"
+          }
+        },
+        "required": [
+          "questionNumber",
+          "attachmentIds"
+        ],
+        "type": "object"
+      },
+      "minItems": 1,
+      "type": "array"
+    },
+    "source": {
+      "description": "The one main source this study is about. When Minds must evaluate pasted text, use kind prompt and put the exact respondent-visible material in content. Keep research objectives, requested questions, and planner-only instructions in request. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset.",
+      "properties": {
+        "content": {
+          "description": "Exact respondent-visible pasted text. Use only with kind prompt when Minds must evaluate a concept, message, description, or other text. Do not include planner-only instructions.",
+          "maxLength": 20000,
+          "minLength": 1,
+          "type": "string"
+        },
+        "kind": {
+          "enum": [
+            "prompt",
+            "website",
+            "image",
+            "video",
+            "document",
+            "questionnaire",
+            "other"
+          ],
+          "type": "string"
+        },
+        "label": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "mimeType": {
+          "type": "string"
+        },
+        "url": {
+          "description": "Fetchable source URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset.",
+          "minLength": 1,
+          "type": "string"
+        }
+      },
+      "required": [
+        "kind",
+        "label"
+      ],
+      "type": "object"
+    },
+    "suggestQuestionStimuli": {
+      "description": "Default true. Lets the planner assign each attached file or website to one or more questions (attachmentIds on those questions). Pass false to leave questions unassigned unless questionAttachments names them.",
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "Which Study the plan belongs to. Omit entirely to continue the active Study from this MCP session.",
+  "properties": {
+    "id": {
+      "description": "Study ID (UUID). Omit with studyName to continue the active Study.",
+      "format": "uuid",
+      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
+      "type": "string"
+    },
+    "name": {
+      "description": "Study name to fuzzy-match among the newest 1,000 visible Studies; use studyId for older records. Omit with studyId to continue the active Study.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Removed value: -{
-  "description": "Study ID (UUID). Omit with studyName to continue the active Study.",
-  "format": "uuid",
-  "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
-  "type": "string"
-}

Removed value: -{
-  "description": "Language for the plan, questions, responses, labels, and summary. Set this explicitly when the user requests a language.",
-  "enum": [
-    "en",
-    "es",
-    "fr",
-    "de",
-    "zh",
-    "tr",
-    "ar",
-    "ja",
-    "ko"
-  ],
-  "type": "string"
-}

Removed value: -{
-  "description": "Study name to fuzzy-match among the newest 1,000 visible Studies; use studyId for older records. Omit with studyId to continue the active Study.",
-  "type": "string"
-}

Removed value: -{
-  "description": "Default true. Lets the planner assign each attached file or website to one or more questions (attachmentIds on those questions). Pass false to leave questions unassigned unless questionAttachments names them.",
-  "type": "boolean"
-}

Previous value: -"Study name for fuzzy matching. Omit with studyId to continue the active Study."New value: +"Study name to fuzzy-match among the newest 1,000 visible Studies; use studyId for older records. Omit with studyId to continue the active Study."

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "draftPlanId": {
+      "description": "Draft plan to confirm with run_study_questions."
+    },
+    "draftReview": {
+      "description": "The saved draft as reviewed: questions, methods, outputs and confirmation choices."
+    },
+    "nextAction": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "What to do next: show the draft and wait for explicit confirmation."
+    },
+    "revision": {
+      "description": "Draft revision to confirm."
+    },
+    "studyId": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Study the plan belongs to."
+    }
+  },
+  "type": "object"
+}

Previous value: -"Files and websites available to the planned Study. With multiple assets, every question needs an explicit assignment and every asset must be used by at least one question. Use [] for no assets. Give each scoped file a stable id. Remote URLs are copied into durable Minds storage before the draft is saved. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."New value: +"Files and websites available to the planned Study (one question block, at most 100). With multiple assets, every question needs an explicit assignment and every asset must be used by at least one question. Use [] for no assets. Give each scoped file a stable id. Remote URLs are copied into durable Minds storage before the draft is saved. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."

Previous value: -20New value: +100

Previous value: -"Stable ids from attachments that this question alone receives."New value: +"Stable ids from attachments that this question alone receives (at most 20)."

Added value: +{
+  "additionalProperties": false,
+  "description": "Save exact edits to draftPlanId and revision without a model call. Preserves method configuration, source policy, item IDs and exact wording. Questions are the complete selected instrument in module order; method-specific batteries are read-only. Cannot combine with planner inputs.",
+  "properties": {
+    "objective": {
+      "maxLength": 2000,
+      "minLength": 1,
+      "type": "string"
+    },
+    "promptContent": {
+      "maxLength": 20000,
+      "type": "string"
+    },
+    "questions": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "attachmentIds": {
+            "items": {
+              "maxLength": 255,
+              "minLength": 1,
+              "type": "string"
+            },
+            "maxItems": 50,
+            "type": "array"
+          },
+          "id": {
+            "maxLength": 80,
+            "minLength": 1,
+            "pattern": "^[a-z0-9_-]+$",
+            "type": "string"
+          },
+          "moduleId": {
+            "maxLength": 120,
+            "minLength": 1,
+            "type": "string"
+          },
+          "response": {
+            "additionalProperties": false,
+            "properties": {
+              "categoricalOptions": {
+                "items": {
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "maxItems": 100,
+                "minItems": 2,
+                "type": "array"
+              },
+              "maxSelections": {
+                "maximum": 100,
+                "minimum": 1,
+                "type": "integer"
+              },
+              "scaleRange": {
+                "items": {
+                  "maximum": 100,
+                  "minimum": -100,
+                  "type": "integer"
+                },
+                "maxItems": 2,
+                "minItems": 2,
+                "type": "array"
+              },
+              "type": {
+                "enum": [
+                  "qualitative",
+                  "categorical",
+                  "multiselect",
+                  "scale"
+                ],
+                "type": "string"
+              }
+            },
+            "required": [
+              "type"
+            ],
+            "type": "object"
+          },
+          "text": {
+            "maxLength": 2000,
+            "minLength": 1,
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "moduleId",
+          "text",
+          "response"
+        ],
+        "type": "object"
+      },
+      "maxItems": 200,
+      "minItems": 1,
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

Added value: +{
+  "description": "Read the latest saved revision of draftPlanId, without generating, saving or executing. Do not combine with edits or planner inputs.",
+  "type": "boolean"
+}

Previous value: -"Files available to the planned Study. Without questionAttachments every question receives every file. With questionAttachments each question receives only its assigned files. Give each scoped file a stable id. Remote URLs are copied into durable Minds storage before the draft is saved. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. The Study refuses to start if Minds cannot read the asset."New value: +"Files and websites available to the planned Study. With multiple assets, every question needs an explicit assignment and every asset must be used by at least one question. Use [] for no assets. Give each scoped file a stable id. Remote URLs are copied into durable Minds storage before the draft is saved. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."

Added value: +{
+  "const": "website",
+  "description": "Use website for a page to read as a website rather than download as a file.",
+  "type": "string"
+}

Added value: +{
+  "maxLength": 255,
+  "type": "string"
+}

Previous value: -"Storage path of a file already uploaded to Minds. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. The Study refuses to start if Minds cannot read the asset."New value: +"Storage path of a file already uploaded to Minds. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."

Previous value: -"Fetchable HTTP(S), signed, or Minds workspace upload URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. The Study refuses to start if Minds cannot read the asset."New value: +"Fetchable HTTP(S), signed, or Minds workspace upload URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."

Previous value: -"Question-to-file mapping. It may cover a subset of the planned questions: mapped questions receive exactly the named attachments, unmapped questions keep every study-level file. Each question at most once; every referenced attachment id must resolve."New value: +"Question-to-file mapping. Multi-asset blocks require every question to be mapped, using [] for no assets; every asset must appear on at least one question. Each question at most once; every referenced attachment id must resolve."

Removed value: -1

Previous value: -"The one main source this study is about. When Minds must evaluate pasted text, use kind prompt and put the exact respondent-visible material in content. Keep research objectives, requested questions, and planner-only instructions in request. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. The Study refuses to start if Minds cannot read the asset."New value: +"The one main source this study is about. When Minds must evaluate pasted text, use kind prompt and put the exact respondent-visible material in content. Keep research objectives, requested questions, and planner-only instructions in request. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."

Previous value: -"Fetchable source URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. The Study refuses to start if Minds cannot read the asset."New value: +"Fetchable source URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. A workspace upload reused as a Study asset must sit under chat/<userId>/: request the signed upload with folder \"chat\" and pass that storage path or its /api/uploads/chat/ URL. A temp/, portfolio/, or context/ path — and any /api/uploads/file-access/ URL — is refused as not belonging to the workspace owner and is never re-fetched; pass a plain external URL instead. The Study refuses to start if Minds cannot read the asset."

Previous value: -"Default true. Lets the planner tie an attached image, video, or document to the one question that is about it (attachmentIds on those questions). Pass false to leave questions unassigned unless questionAttachments names them."New value: +"Default true. Lets the planner assign each attached file or website to one or more questions (attachmentIds on those questions). Pass false to leave questions unassigned unless questionAttachments names them."

Added value: +{
+  "description": "Experimental per-Mind treatment assignments stored in the exact draft revision. Each Mind may appear once; unlisted Minds use sourcePolicy. Use only for a preregistered source-policy experiment.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "mindId": {
+        "description": "Exact Mind UUID in the Study cohort.",
+        "format": "uuid",
+        "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
+        "type": "string"
+      },
+      "sourcePolicy": {
+        "description": "Request-scoped evidence treatment for this Mind.",
+        "enum": [
+          "request_only",
+          "auto"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "mindId",
+      "sourcePolicy"
+    ],
+    "type": "object"
+  },
+  "maxItems": 2000,
+  "type": "array"
+}

Previous value: -"Exact response contract for this item: type qualitative, categorical (with categoricalOptions), multiselect, or scale (with inclusive integer scaleRange)."New value: +"Exact execution contract for this item: type qualitative, categorical (with categoricalOptions), multiselect, or scale (with inclusive integer scaleRange). Supplied categoricalOptions keep their exact labels and order even with attachments; files are evidence and do not generate replacement A/B options."

Added value: +{
+  "description": "Evidence policy stored in the draft and reviewed before execution. Defaults to request_only for a controlled Study. Use auto only for an explicitly designed experiment that should allow relevant Mind-knowledge retrieval; response-mode rules still control live web search.",
+  "enum": [
+    "request_only",
+    "auto"
+  ],
+  "type": "string"
+}

Added value: +{
+  "description": "Optional stable retry key. When omitted the tool derives one from its own arguments, so a repeated identical call (including a host retry after a timeout) returns the draft revision that was already saved instead of planning again. Pass a fresh key to force a new plan for identical input.",
+  "maxLength": 200,
+  "minLength": 1,
+  "type": "string"
+}

Added value: +{
+  "description": "Fixed instrument: use INSTEAD of request when the user supplies a pre-registered or fixed questionnaire whose wording, order, and response formats must not change. The planner is bypassed; every question is stored verbatim, in this order, with exactly this response contract. Cannot be combined with refinement, answers, questionResponses, or suggestQuestionStimuli. Repeated question texts or colliding ids are rejected.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "id": {
+        "description": "Stable item id (lower-cased to a slug). Defaults to q<position>.",
+        "maxLength": 80,
+        "minLength": 1,
+        "type": "string"
+      },
+      "module": {
+        "description": "Optional module (battery) label. Consecutive questions with the same label form one module.",
+        "maxLength": 200,
+        "minLength": 1,
+        "type": "string"
+      },
+      "response": {
+        "additionalProperties": false,
+        "description": "Exact response contract for this item: type qualitative, categorical (with categoricalOptions), multiselect, or scale (with inclusive integer scaleRange).",
+        "properties": {
+          "categoricalOptions": {
+            "description": "Predefined answer choices; only valid for categorical or multiselect responses.",
+            "items": {
+              "minLength": 1,
+              "type": "string"
+            },
+            "maxItems": 100,
+            "minItems": 2,
+            "type": "array"
+          },
+          "maxSelections": {
+            "description": "Maximum choices a respondent may select; only valid for multiselect responses.",
+            "maximum": 100,
+            "minimum": 1,
+            "type": "integer"
+          },
+          "scaleRange": {
+            "description": "Inclusive integer response range as [minimum, maximum]; required for scale responses.",
+            "items": {
+              "maximum": 100,
+              "minimum": -100,
+              "type": "integer"
+            },
+            "maxItems": 2,
+            "minItems": 2,
+            "type": "array"
+          },
+          "type": {
+            "enum": [
+              "qualitative",
+              "categorical",
+              "multiselect",
+              "scale"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "type"
+        ],
+        "type": "object"
+      },
+      "text": {
+        "description": "Exact respondent-visible question text, including any anchors or labels. Stored as given.",
+        "maxLength": 2000,
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "text",
+      "response"
+    ],
+    "type": "object"
+  },
+  "maxItems": 200,
+  "minItems": 1,
+  "type": "array"
+}

Previous value: -"Complete question-to-file mapping. When present, every planned question must appear exactly once and every referenced attachment id must resolve."New value: +"Question-to-file mapping. It may cover a subset of the planned questions: mapped questions receive exactly the named attachments, unmapped questions keep every study-level file. Each question at most once; every referenced attachment id must resolve."

Added value: +{
+  "description": "Default true. Lets the planner tie an attached image, video, or document to the one question that is about it (attachmentIds on those questions). Pass false to leave questions unassigned unless questionAttachments names them.",
+  "type": "boolean"
+}

Previous value: -"Files that every question in this planned Study must evaluate. Use one distinct entry per creative (for example four A/B/C/D videos). Remote URLs are copied into durable Minds storage before the draft is saved. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. The Study refuses to start if Minds cannot read the asset."New value: +"Files available to the planned Study. Without questionAttachments every question receives every file. With questionAttachments each question receives only its assigned files. Give each scoped file a stable id. Remote URLs are copied into durable Minds storage before the draft is saved. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. The Study refuses to start if Minds cannot read the asset."

Added value: +{
+  "description": "Stable asset ID used by questionAttachments to assign this file to specific planned questions.",
+  "maxLength": 255,
+  "minLength": 1,
+  "type": "string"
+}

Added value: +{
+  "description": "Complete question-to-file mapping. When present, every planned question must appear exactly once and every referenced attachment id must resolve.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "attachmentIds": {
+        "description": "Stable ids from attachments that this question alone receives.",
+        "items": {
+          "maxLength": 255,
+          "minLength": 1,
+          "type": "string"
+        },
+        "maxItems": 20,
+        "minItems": 1,
+        "type": "array"
+      },
+      "questionNumber": {
+        "description": "One-based question position in the returned plan, across modules in order.",
+        "maximum": 9007199254740991,
+        "minimum": 1,
+        "type": "integer"
+      }
+    },
+    "required": [
+      "questionNumber",
+      "attachmentIds"
+    ],
+    "type": "object"
+  },
+  "minItems": 1,
+  "type": "array"
+}

Added value: +{
+  "description": "Files that every question in this planned Study must evaluate. Use one distinct entry per creative (for example four A/B/C/D videos). Remote URLs are copied into durable Minds storage before the draft is saved. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. The Study refuses to start if Minds cannot read the asset.",
+  "items": {
+    "properties": {
+      "name": {
+        "description": "File name visible in the Study.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "path": {
+        "description": "Storage path of a file already uploaded to Minds. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. The Study refuses to start if Minds cannot read the asset.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "type": {
+        "description": "MIME type when known.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "url": {
+        "description": "Fetchable HTTP(S), signed, or Minds workspace upload URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. The Study refuses to start if Minds cannot read the asset.",
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "maxItems": 20,
+  "type": "array"
+}

Previous value: -"The one main source this study is about. When Minds must evaluate pasted text, use kind prompt and put the exact respondent-visible material in content. Keep research objectives, requested questions, and planner-only instructions in request. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. The Study refuses to start if Minds cannot read the asset."New value: +"The one main source this study is about. When Minds must evaluate pasted text, use kind prompt and put the exact respondent-visible material in content. Keep research objectives, requested questions, and planner-only instructions in request. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. The Study refuses to start if Minds cannot read the asset."

Previous value: -"Fetchable source URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. The Study refuses to start if Minds cannot read the asset."New value: +"Fetchable source URL. MCP cannot read or upload a local file:// path. Use a fetchable HTTP(S) URL, a signed URL supplied by the client for the attached file, or an existing Minds workspace upload URL/path. Study tools import external file URLs into durable Minds storage before saving or running. The Study refuses to start if Minds cannot read the asset."