confirm_upload
ChatGPTConfirm a presigned upload completed. Call after successfully PUTting the file to the uploadUrl from request_upload_url. The server verifies the object exists in S3, reads its metadata, and tracks workspace storage. Only s3Key is required — filename, size, and MIME type are resolved from S3. Returns { url, filename, mimeType, size } where url is the /s/ path usable as a File/Image field value. Returns 400 if the file is not found in S3 — ensure the PUT completed before calling.
confirm_upload
ChatGPTConfirm a presigned upload completed. Call after successfully PUTting the file to the uploadUrl from request_upload_url. The server verifies the object exists in S3, reads its metadata, and tracks workspace storage. Only s3Key is required — filename, size, and MIME type are resolved from S3. Returns { url, filename, mimeType, size } where url is the /s/ path usable as a File/Image field value. Returns 400 if the file is not found in S3 — ensure the PUT completed before calling.
create_module
ChatGPTCreate a new module. Supports workflow modules (states, activities, flows) and record list modules (fields only). Requires Administrator, Consultant, or Workspace Admin role. Always call validate_design first. See inistate://schema/configure for field types, color palette, and design rules.
create_module
ChatGPTCreate a new module. Supports workflow modules (states, activities, flows) and record list modules (fields only). Requires Administrator, Consultant, or Workspace Admin role. Always call validate_design first. See inistate://schema/configure for field types, color palette, and design rules.
design_workflow
ChatGPTGenerate a scaffolded ModuleSchema template from a natural language description. Use when the user wants to create a new module or workflow. Design workflow: design_workflow → (complete template) → validate_design → create_module → get_module_schema(tier=extended). Load resources inistate://schema and inistate://design-guide before designing for valid field types, colors, and design rules.
design_workflow
ChatGPTGenerate a scaffolded ModuleSchema template from a natural language description. Use when the user wants to create a new module or workflow. Design workflow: design_workflow → (complete template) → validate_design → create_module → get_module_schema(tier=extended). Load resources inistate://schema and inistate://design-guide before designing for valid field types, colors, and design rules.
download_file
ChatGPTDownload a file by module name. Construct the URL from a File/Image field value: field.path = '/s/{guid}/{fileName}'. Returns a pre-signed S3 URL (1hr TTL).
download_file
ChatGPTDownload a file by module name. Construct the URL from a File/Image field value: field.path = '/s/{guid}/{fileName}'. Returns a pre-signed S3 URL (1hr TTL).
get_entry
ChatGPTRead a single entry by its ID. Returns current field values, state, audit metadata, and available activities.
get_entry
ChatGPTRead a single entry by its ID. Returns current field values, state, audit metadata, and available activities.
get_entry_history
ChatGPTGet the audit trail and comments for an entry. Returns chronological list of actions (create, edit, state changes, comments) with field-level change details and AI traceability context.
get_entry_history
ChatGPTGet the audit trail and comments for an entry. Returns chronological list of actions (create, edit, state changes, comments) with field-level change details and AI traceability context.
get_form
ChatGPTGet the form fields, current values, and options for a module activity. ALWAYS call this before submit_activity to discover required fields, their types, valid options, default values, and the confidence threshold. Never fabricate form data — if required fields cannot be confidently populated, ask the user.
get_form
ChatGPTGet the form fields, current values, and options for a module activity. ALWAYS call this before submit_activity to discover required fields, their types, valid options, default values, and the confidence threshold. Never fabricate form data — if required fields cannot be confidently populated, ask the user.
get_module_canvas
ChatGPTGet the full module definition with stable IDs. The output is round-trippable — modify and send back via update_module. Use this when modifying a module to preserve IDs for renaming. Modify workflow: list_modules → get_module_canvas → (apply changes) → validate_design → update_module. Load resource inistate://schema before modifying to know valid field types, colors, and actors.
get_module_canvas
ChatGPTGet the full module definition with stable IDs. The output is round-trippable — modify and send back via update_module. Use this when modifying a module to preserve IDs for renaming. Modify workflow: list_modules → get_module_canvas → (apply changes) → validate_design → update_module. Load resource inistate://schema before modifying to know valid field types, colors, and actors.
get_module_schema
ChatGPTGet the canvas schema for a module. Use tier=basic (default) for fields and states only. Use tier=extended to also include activities and flows. Use basic for query operations. Use extended when you need to understand available activities and state transitions.
get_module_schema
ChatGPTGet the canvas schema for a module. Use tier=basic (default) for fields and states only. Use tier=extended to also include activities and flows. Use basic for query operations. Use extended when you need to understand available activities and state transitions.
list_entries
ChatGPTQuery entries with filters, sorting, pagination. Filter keys are field display names; values are equality (simple) or operator objects (contains/startsWith/endsWith/min/max/above/below/between/after/before/empty/exists/yes/no/is/not/excludes). Use {or:[…]} for OR; multiple keys are AND-ed. Use 'me' for User-field self-match. See FilterOperators in inistate://schema/runtime for the full set.
list_entries
ChatGPTQuery entries with filters, sorting, pagination. Filter keys are field display names; values are equality (simple) or operator objects (contains/startsWith/endsWith/min/max/above/below/between/after/before/empty/exists/yes/no/is/not/excludes). Use {or:[…]} for OR; multiple keys are AND-ed. Use 'me' for User-field self-match. See FilterOperators in inistate://schema/runtime for the full set.
list_modules
ChatGPTList all discoverable modules in the current workspace. Call this to find module names for execute, modify, and query operations.
list_modules
ChatGPTList all discoverable modules in the current workspace. Call this to find module names for execute, modify, and query operations.
list_workspaces
ChatGPTList workspaces the current user has access to. Call set_workspace to select one before any module or entry tools. This is typically the first tool to call in any session.
list_workspaces
ChatGPTList workspaces the current user has access to. Call set_workspace to select one before any module or entry tools. This is typically the first tool to call in any session.
request_upload_url
ChatGPTDEFAULT upload path — ALWAYS use this for every file upload (any size, up to 500MB). Only fall back to upload_file if this flow actually fails. Three-step flow: 1) call this tool, 2) PUT the raw bytes to uploadUrl with Content-Type exactly matching contentType (S3 rejects mismatches with 403 SignatureDoesNotMatch), 3) call confirm_upload({ s3Key }). The path returned by confirm_upload is used directly as the File/Image field value in submit_activity. uploadUrl expires in ~1 hour and cannot be renewed — call this again on expiry.
request_upload_url
ChatGPTDEFAULT upload path — ALWAYS use this for every file upload (any size, up to 500MB). Only fall back to upload_file if this flow actually fails. Three-step flow: 1) call this tool, 2) PUT the raw bytes to uploadUrl with Content-Type exactly matching contentType (S3 rejects mismatches with 403 SignatureDoesNotMatch), 3) call confirm_upload({ s3Key }). The path returned by confirm_upload is used directly as the File/Image field value in submit_activity. uploadUrl expires in ~1 hour and cannot be renewed — call this again on expiry.
set_workspace
ChatGPTSet the active workspace for the current session. In stateless/remote mode, prefer passing workspaceId directly to each tool instead. Workflow sequences after workspace is set: - Design: design_workflow → validate_design → create_module - Execute: list_modules → list_entries → get_form → submit_activity - Modify: list_modules → get_module_canvas → validate_design → update_module - Query: list_modules → list_entries → get_entry / get_entry_history
set_workspace
ChatGPTSet the active workspace for the current session. In stateless/remote mode, prefer passing workspaceId directly to each tool instead. Workflow sequences after workspace is set: - Design: design_workflow → validate_design → create_module - Execute: list_modules → list_entries → get_form → submit_activity - Modify: list_modules → get_module_canvas → validate_design → update_module - Query: list_modules → list_entries → get_entry / get_entry_history
submit_activities
ChatGPTBulk variant of submit_activity: same module + same activity applied to multiple entries, each with its own input payload. Use this instead of N sequential submit_activity calls when creating/editing many rows at once — saves substantial agent tokens by collapsing N tool turns into one. Shape: top-level module, activity, and a default ai block; per-item input (and optional entryId, state, comment, assignees, due, ai, clientRef). When an item supplies its own ai, it wholly replaces the top-level ai for that item — no partial merge. Execution: items run sequentially fail-soft on the server. One item's failure does not abort the rest; per-item outcomes (success/failure, entryId, flagged, validation details) are returned in results. Use clientRef to correlate items to your local plan. Limits: max 100 items per request. Beyond that, chunk and retry. Guardrails: same submit_activity rules apply at the batch level — actor='human' rejects the whole batch; actor='hybrid' or activity='changeStatus' or top-level state requires confirmed: true. Per-item state overrides also require confirmed: true.
submit_activities
ChatGPTBulk variant of submit_activity: same module + same activity applied to multiple entries, each with its own input payload. Use this instead of N sequential submit_activity calls when creating/editing many rows at once — saves substantial agent tokens by collapsing N tool turns into one. Shape: top-level module, activity, and a default ai block; per-item input (and optional entryId, state, comment, assignees, due, ai, clientRef). When an item supplies its own ai, it wholly replaces the top-level ai for that item — no partial merge. Execution: items run sequentially fail-soft on the server. One item's failure does not abort the rest; per-item outcomes (success/failure, entryId, flagged, validation details) are returned in results. Use clientRef to correlate items to your local plan. Limits: max 100 items per request. Beyond that, chunk and retry. Guardrails: same submit_activity rules apply at the batch level — actor='human' rejects the whole batch; actor='hybrid' or activity='changeStatus' or top-level state requires confirmed: true. Per-item state overrides also require confirmed: true.
submit_activity
ChatGPTPerform an activity on a module entry: standard (create [no entryId], edit, delete, changeStatus, comment, duplicate, manage) or any custom activity from get_module_schema. ALWAYS call get_form first. The ai object is REQUIRED (reasoning + model + confidence). If confidence < the activity's threshold, the transition is suppressed and the entry is flagged. Server-side guard rules (human/hybrid actor, state-change confirm, confidence-inflation) may block — see inistate://guardrails. Input shapes: ActivitySubmission in inistate://schema/runtime.
submit_activity
ChatGPTPerform an activity on a module entry: standard (create [no entryId], edit, delete, changeStatus, comment, duplicate, manage) or any custom activity from get_module_schema. ALWAYS call get_form first. The ai object is REQUIRED (reasoning + model + confidence). If confidence < the activity's threshold, the transition is suppressed and the entry is flagged. Server-side guard rules (human/hybrid actor, state-change confirm, confidence-inflation) may block — see inistate://guardrails. Input shapes: ActivitySubmission in inistate://schema/runtime.
switch_mode
ChatGPTSwitch tool surface. 'configure' (default) exposes entry CRUD plus module design tools (create_module, update_module, design_workflow, validate_design, get_module_canvas, get_module_schema) and schema/configure and design-guide resources. 'runtime' narrows to entry CRUD only. 'frontend' is a superset of 'configure' that also exposes the inistate://frontend-guide resource — REST API reference for generating Vue/React UIs that call the Inistate API directly with a user-supplied token. Use 'frontend' when the user wants to build a custom UI (and optionally iterate on the schema in the same session). The tool/resource list refreshes via list_changed after this call.
switch_mode
ChatGPTSwitch tool surface. 'configure' (default) exposes entry CRUD plus module design tools (create_module, update_module, design_workflow, validate_design, get_module_canvas, get_module_schema) and schema/configure and design-guide resources. 'runtime' narrows to entry CRUD only. 'frontend' is a superset of 'configure' that also exposes the inistate://frontend-guide resource — REST API reference for generating Vue/React UIs that call the Inistate API directly with a user-supplied token. Use 'frontend' when the user wants to build a custom UI (and optionally iterate on the schema in the same session). The tool/resource list refreshes via list_changed after this call.
update_module
ChatGPTUpdate an existing module. Merges changes into the existing canvas; items matched by id enable renaming. Omitted sections are left unchanged. Always call get_module_canvas first to obtain the stable module id and item ids, then validate_design before submitting.
update_module
ChatGPTUpdate an existing module. Merges changes into the existing canvas; items matched by id enable renaming. Omitted sections are left unchanged. Always call get_module_canvas first to obtain the stable module id and item ids, then validate_design before submitting.
upload_file
ChatGPTFALLBACK ONLY — do NOT use this by default. Always use request_upload_url + confirm_upload first; call this tool only after the presigned flow has actually failed (e.g. request_upload_url errored, or the PUT/confirm step failed for non-retryable reasons). Uploads a file to S3 via base64/multipart. Returns { path, filename, mimeType, size }. Use the returned path as the 'path' value in File/Image fields for submit_activity (e.g. { name: 'photo.jpg', path: result.path }). Max 50MB. Blocked: .exe, .bat, .cmd, .dll, .msi.
upload_file
ChatGPTFALLBACK ONLY — do NOT use this by default. Always use request_upload_url + confirm_upload first; call this tool only after the presigned flow has actually failed (e.g. request_upload_url errored, or the PUT/confirm step failed for non-retryable reasons). Uploads a file to S3 via base64/multipart. Returns { path, filename, mimeType, size }. Use the returned path as the 'path' value in File/Image fields for submit_activity (e.g. { name: 'photo.jpg', path: result.path }). Max 50MB. Blocked: .exe, .bat, .cmd, .dll, .msi.
validate_design
ChatGPTValidate a module schema before creating or updating. Checks structural integrity against all FACTSOps rules without submitting to the API. Passing validate_design guarantees the subsequent create_module/update_module call will not fail with 422. Always call this before create_module or update_module.
validate_design
ChatGPTValidate a module schema before creating or updating. Checks structural integrity against all FACTSOps rules without submitting to the API. Passing validate_design guarantees the subsequent create_module/update_module call will not fail with 422. Always call this before create_module or update_module.
